diff --git a/.gitignore b/.gitignore new file mode 100644 index 000000000..eb291f421 --- /dev/null +++ b/.gitignore @@ -0,0 +1,31 @@ +# mac os x +.DS_Store + +# related to files +params* +resources* +output/ +target/ +out/ +local/ +datasets_raw/ +state* +trace* +tw-* + +# related to python +.ipynb_checkpoints +__pycache__/ + +# ? +.$* +bin* +bin/ + +# related to nextflow +work +.nextflow* + +# IDE related +.idea +.vscode diff --git a/README.md b/README.md index 2426e1ce8..7d281f425 100644 --- a/README.md +++ b/README.md @@ -7,9 +7,7 @@ Do not edit this file directly. --> Benchmarking GRN inference methods The full documentation is hosted on -[ReadTheDocs](https://openproblems-grn-task.readthedocs.io/en/latest/index.html). -[![Documentation -Status](https://readthedocs.org/projects/grn-inference-benchmarking/badge/?version=latest.png)](https://grn-inference-benchmarking.readthedocs.io/en/latest/?badge=latest) +[ReadTheDocs](https://grn-inference-benchmarking.readthedocs.io/en/latest/index.html). Path to source: [`src`](https://github.com/openproblems-bio/task_grn_inference/tree/main/src) @@ -115,39 +113,37 @@ approaches to assess both accuracy and comprehensiveness. ``` mermaid flowchart LR - file_perturbation_h5ad("perturbation") - comp_control_method[/"Control Method"/] - comp_metric[/"Label"/] - file_prediction("GRN") - file_score("Score") file_multiomics_rna_h5ad("multiomics rna") comp_method[/"Method"/] + file_prediction("GRN") + comp_metric[/"Label"/] + file_score("Score") file_multiomics_atac_h5ad("multiomics atac") + file_perturbation_h5ad("perturbation") + comp_control_method[/"Control Method"/] comp_method_r[/"Method r"/] - file_perturbation_h5ad---comp_control_method - file_perturbation_h5ad---comp_metric - comp_control_method-->file_prediction - comp_metric-->file_score - file_prediction---comp_metric file_multiomics_rna_h5ad---comp_method comp_method-->file_prediction + file_prediction---comp_metric + comp_metric-->file_score file_multiomics_atac_h5ad---comp_method + file_perturbation_h5ad---comp_metric + comp_control_method-->file_prediction comp_method_r-->file_prediction ``` -## File format: perturbation +## File format: multiomics rna -Perturbation dataset for benchmarking. +RNA expression for multiomics data. -Example file: `resources_test/grn-benchmark/perturbation_data.h5ad` +Example file: `resources_test/grn-benchmark/multiomics_rna.h5ad` Format:
AnnData object - obs: 'cell_type', 'sm_name', 'donor_id', 'plate_name', 'row', 'well', 'cell_count' - layers: 'n_counts', 'pearson', 'lognorm' + obs: 'cell_type', 'donor_id'
@@ -158,44 +154,16 @@ Slot description: | Slot | Type | Description | |:---|:---|:---| | `obs["cell_type"]` | `string` | The annotated cell type of each cell based on RNA expression. | -| `obs["sm_name"]` | `string` | The primary name for the (parent) compound (in a standardized representation) as chosen by LINCS. This is provided to map the data in this experiment to the LINCS Connectivity Map data. | | `obs["donor_id"]` | `string` | Donor id. | -| `obs["plate_name"]` | `string` | Plate name 6 levels. | -| `obs["row"]` | `string` | Row name on the plate. | -| `obs["well"]` | `string` | Well name on the plate. | -| `obs["cell_count"]` | `string` | Number of single cells pseudobulked. | -| `layers["n_counts"]` | `double` | Pseudobulked values using mean approach. | -| `layers["pearson"]` | `double` | (*Optional*) Normalized values using pearson residuals. | -| `layers["lognorm"]` | `double` | (*Optional*) Normalized values using shifted logarithm . | - - - -## Component type: Control Method - -Path: -[`src/control_methods`](https://github.com/openproblems-bio/openproblems/tree/main/src/control_methods) - -A control method. - -Arguments: - -
- -| Name | Type | Description | -|:---|:---|:---| -| `--perturbation_data` | `file` | Perturbation dataset for benchmarking. | -| `--layer` | `string` | (*Optional*) Which layer of pertubation data to use to find tf-gene relationships. Default: `scgen_pearson`. | -| `--prediction` | `file` | (*Output*) GRN prediction. | -| `--tf_all` | `file` | (*Optional*) NA. |
-## Component type: Label +## Component type: Method Path: -[`src/metrics`](https://github.com/openproblems-bio/openproblems/tree/main/src/metrics) +[`src/methods`](https://github.com/openproblems-bio/openproblems/tree/main/src/methods) -A metric to evaluate the performance of the inferred GRN +A GRN inference method Arguments: @@ -203,15 +171,13 @@ Arguments: | Name | Type | Description | |:---|:---|:---| -| `--perturbation_data` | `file` | (*Optional*) Perturbation dataset for benchmarking. | -| `--prediction` | `file` | GRN prediction. | -| `--score` | `file` | (*Optional, Output*) File indicating the score of a metric. | -| `--reg_type` | `string` | (*Optional*) name of regretion to use. Default: `ridge`. | -| `--subsample` | `integer` | (*Optional*) number of samples randomly drawn from perturbation data. Default: `-2`. | -| `--max_workers` | `integer` | (*Optional*) NA. Default: `4`. | -| `--method_id` | `string` | (*Optional*) NA. | -| `--tf_all` | `file` | (*Optional*) NA. | -| `--apply_tf` | `boolean` | (*Optional*) NA. Default: `TRUE`. | +| `--multiomics_rna` | `file` | (*Optional*) RNA expression for multiomics data. Default: `resources/grn-benchmark/multiomics_rna.h5ad`. | +| `--multiomics_atac` | `file` | (*Optional*) Peak data for multiomics data. Default: `resources/grn-benchmark/multiomics_atac.h5ad`. | +| `--prediction` | `file` | (*Optional, Output*) GRN prediction. Default: `output/prediction.csv`. | +| `--temp_dir` | `string` | (*Optional*) NA. Default: `output/temdir`. | +| `--num_workers` | `integer` | (*Optional*) NA. Default: `4`. | +| `--tf_all` | `file` | (*Optional*) NA. Default: `resources/prior/tf_all.csv`. | +| `--max_n_links` | `integer` | (*Optional*) NA. Default: `50000`. | @@ -242,6 +208,32 @@ Slot description: +## Component type: Label + +Path: +[`src/metrics`](https://github.com/openproblems-bio/openproblems/tree/main/src/metrics) + +A metric to evaluate the performance of the inferred GRN + +Arguments: + +
+ +| Name | Type | Description | +|:---|:---|:---| +| `--perturbation_data` | `file` | (*Optional*) Perturbation dataset for benchmarking. Default: `resources/grn-benchmark/perturbation_data.h5ad`. | +| `--prediction` | `file` | GRN prediction. | +| `--score` | `file` | (*Optional, Output*) File indicating the score of a metric. Default: `output/score.h5ad`. | +| `--reg_type` | `string` | (*Optional*) name of regretion to use. Default: `ridge`. | +| `--subsample` | `integer` | (*Optional*) number of samples randomly drawn from perturbation data. Default: `-2`. | +| `--max_workers` | `integer` | (*Optional*) NA. Default: `4`. | +| `--method_id` | `string` | (*Optional*) NA. | +| `--tf_all` | `file` | (*Optional*) NA. Default: `resources/prior/tf_all.csv`. | +| `--apply_tf` | `boolean` | (*Optional*) NA. Default: `TRUE`. | +| `--clip_scores` | `boolean` | (*Optional*) clips the r2 scores for each gene to make them within \[0, 1\]. Default: `TRUE`. | + +
+ ## File format: Score File indicating the score of a metric. @@ -270,11 +262,11 @@ Slot description: -## File format: multiomics rna +## File format: multiomics atac -RNA expression for multiomics data. +Peak data for multiomics data. -Example file: `resources_test/grn-benchmark/multiomics_rna.h5ad` +Example file: `resources_test/grn-benchmark/multiomics_atac.h5ad` Format: @@ -296,52 +288,57 @@ Slot description: -## Component type: Method +## File format: perturbation -Path: -[`src/methods`](https://github.com/openproblems-bio/openproblems/tree/main/src/methods) +Perturbation dataset for benchmarking. -A GRN inference method +Example file: `resources_test/grn-benchmark/perturbation_data.h5ad` -Arguments: +Format:
-| Name | Type | Description | -|:---|:---|:---| -| `--multiomics_rna` | `file` | (*Optional*) RNA expression for multiomics data. | -| `--multiomics_atac` | `file` | (*Optional*) Peak data for multiomics data. | -| `--prediction` | `file` | (*Optional, Output*) GRN prediction. | -| `--temp_dir` | `string` | (*Optional*) NA. Default: `output/temdir`. | -| `--num_workers` | `integer` | (*Optional*) NA. Default: `4`. | -| `--tf_all` | `file` | (*Optional*) NA. | -| `--max_n_links` | `integer` | (*Optional*) NA. Default: `50000`. | + AnnData object + obs: 'cell_type', 'sm_name', 'donor_id', 'plate_name', 'row', 'well', 'cell_count' + layers: 'n_counts', 'pearson', 'lognorm'
-## File format: multiomics atac +Slot description: -Peak data for multiomics data. +
-Example file: `resources_test/grn-benchmark/multiomics_atac.h5ad` +| Slot | Type | Description | +|:---|:---|:---| +| `obs["cell_type"]` | `string` | The annotated cell type of each cell based on RNA expression. | +| `obs["sm_name"]` | `string` | The primary name for the (parent) compound (in a standardized representation) as chosen by LINCS. This is provided to map the data in this experiment to the LINCS Connectivity Map data. | +| `obs["donor_id"]` | `string` | Donor id. | +| `obs["plate_name"]` | `string` | Plate name 6 levels. | +| `obs["row"]` | `string` | Row name on the plate. | +| `obs["well"]` | `string` | Well name on the plate. | +| `obs["cell_count"]` | `string` | Number of single cells pseudobulked. | +| `layers["n_counts"]` | `double` | Pseudobulked values using mean approach. | +| `layers["pearson"]` | `double` | (*Optional*) Normalized values using pearson residuals. | +| `layers["lognorm"]` | `double` | (*Optional*) Normalized values using shifted logarithm . | -Format: +
-
+## Component type: Control Method - AnnData object - obs: 'cell_type', 'donor_id' +Path: +[`src/control_methods`](https://github.com/openproblems-bio/openproblems/tree/main/src/control_methods) -
+A control method. -Slot description: +Arguments:
-| Slot | Type | Description | +| Name | Type | Description | |:---|:---|:---| -| `obs["cell_type"]` | `string` | The annotated cell type of each cell based on RNA expression. | -| `obs["donor_id"]` | `string` | Donor id. | +| `--layer` | `string` | (*Optional*) Which layer of pertubation data to use to find tf-gene relationships. Default: `scgen_pearson`. | +| `--prediction` | `file` | (*Optional, Output*) GRN prediction. | +| `--tf_all` | `file` | NA. |
diff --git a/params/celloracle.yaml b/params/celloracle.yaml deleted file mode 100644 index feaf6087b..000000000 --- a/params/celloracle.yaml +++ /dev/null @@ -1,8 +0,0 @@ -param_list: - - id: celloracle - multiomics_rna: s3://openproblems-data/resources/grn/grn-benchmark/multiomics_rna.h5ad - multiomics_atac: s3://openproblems-data/resources/grn/grn-benchmark/multiomics_atac.h5ad - num_workers: 20 - temp_dir: ./tmp/grn -output_state: "state.yaml" -publish_dir: "s3://openproblems-data/resources/grn/results/celloracle" diff --git a/params/repo/grn_evaluation_.yaml b/params/repo/grn_evaluation_.yaml deleted file mode 100644 index 7a4859584..000000000 --- a/params/repo/grn_evaluation_.yaml +++ /dev/null @@ -1,159 +0,0 @@ -param_list: - - id: _collectri_pearson - perturbation_data: ./resources/grn-benchmark/perturbation_data.h5ad - reg_type: - method_id: collectri - subsample: -2 - max_workers: 10 - tf_all: ./resources/prior/tf_all.csv - layer: pearson - consensus: ./resources/prior/consensus-num-regulators.json - prediction: ./resources/grn_models/collectri.csv - - id: _celloracle_pearson - perturbation_data: ./resources/grn-benchmark/perturbation_data.h5ad - reg_type: - method_id: celloracle - subsample: -2 - max_workers: 10 - tf_all: ./resources/prior/tf_all.csv - layer: pearson - consensus: ./resources/prior/consensus-num-regulators.json - prediction: ./resources/grn_models/celloracle.csv - - id: _scenicplus_pearson - perturbation_data: ./resources/grn-benchmark/perturbation_data.h5ad - reg_type: - method_id: scenicplus - subsample: -2 - max_workers: 10 - tf_all: ./resources/prior/tf_all.csv - layer: pearson - consensus: ./resources/prior/consensus-num-regulators.json - prediction: ./resources/grn_models/scenicplus.csv - - id: _figr_pearson - perturbation_data: ./resources/grn-benchmark/perturbation_data.h5ad - reg_type: - method_id: figr - subsample: -2 - max_workers: 10 - tf_all: ./resources/prior/tf_all.csv - layer: pearson - consensus: ./resources/prior/consensus-num-regulators.json - prediction: ./resources/grn_models/figr.csv - - id: _granie_pearson - perturbation_data: ./resources/grn-benchmark/perturbation_data.h5ad - reg_type: - method_id: granie - subsample: -2 - max_workers: 10 - tf_all: ./resources/prior/tf_all.csv - layer: pearson - consensus: ./resources/prior/consensus-num-regulators.json - prediction: ./resources/grn_models/granie.csv - - id: _scglue_pearson - perturbation_data: ./resources/grn-benchmark/perturbation_data.h5ad - reg_type: - method_id: scglue - subsample: -2 - max_workers: 10 - tf_all: ./resources/prior/tf_all.csv - layer: pearson - consensus: ./resources/prior/consensus-num-regulators.json - prediction: ./resources/grn_models/scglue.csv - - id: _collectri_scgen_pearson - perturbation_data: ./resources/grn-benchmark/perturbation_data.h5ad - reg_type: - method_id: collectri - subsample: -2 - max_workers: 10 - tf_all: ./resources/prior/tf_all.csv - layer: scgen_pearson - consensus: ./resources/prior/consensus-num-regulators.json - prediction: ./resources/grn_models/collectri.csv - - id: _celloracle_scgen_pearson - perturbation_data: ./resources/grn-benchmark/perturbation_data.h5ad - reg_type: - method_id: celloracle - subsample: -2 - max_workers: 10 - tf_all: ./resources/prior/tf_all.csv - layer: scgen_pearson - consensus: ./resources/prior/consensus-num-regulators.json - prediction: ./resources/grn_models/celloracle.csv - - id: _scenicplus_scgen_pearson - perturbation_data: ./resources/grn-benchmark/perturbation_data.h5ad - reg_type: - method_id: scenicplus - subsample: -2 - max_workers: 10 - tf_all: ./resources/prior/tf_all.csv - layer: scgen_pearson - consensus: ./resources/prior/consensus-num-regulators.json - prediction: ./resources/grn_models/scenicplus.csv - - id: _figr_scgen_pearson - perturbation_data: ./resources/grn-benchmark/perturbation_data.h5ad - reg_type: - method_id: figr - subsample: -2 - max_workers: 10 - tf_all: ./resources/prior/tf_all.csv - layer: scgen_pearson - consensus: ./resources/prior/consensus-num-regulators.json - prediction: ./resources/grn_models/figr.csv - - id: _granie_scgen_pearson - perturbation_data: ./resources/grn-benchmark/perturbation_data.h5ad - reg_type: - method_id: granie - subsample: -2 - max_workers: 10 - tf_all: ./resources/prior/tf_all.csv - layer: scgen_pearson - consensus: ./resources/prior/consensus-num-regulators.json - prediction: ./resources/grn_models/granie.csv - - id: _scglue_scgen_pearson - perturbation_data: ./resources/grn-benchmark/perturbation_data.h5ad - reg_type: - method_id: scglue - subsample: -2 - max_workers: 10 - tf_all: ./resources/prior/tf_all.csv - layer: scgen_pearson - consensus: ./resources/prior/consensus-num-regulators.json - prediction: ./resources/grn_models/scglue.csv - - id: _negative_control_pearson - perturbation_data: ./resources/grn-benchmark/perturbation_data.h5ad - reg_type: - method_id: negative_control - subsample: -2 - max_workers: 10 - tf_all: ./resources/prior/tf_all.csv - layer: pearson - consensus: ./resources/prior/consensus-num-regulators.json - - id: _negative_control_scgen_pearson - perturbation_data: ./resources/grn-benchmark/perturbation_data.h5ad - reg_type: - method_id: negative_control - subsample: -2 - max_workers: 10 - tf_all: ./resources/prior/tf_all.csv - layer: scgen_pearson - consensus: ./resources/prior/consensus-num-regulators.json - - id: _positive_control_pearson - perturbation_data: ./resources/grn-benchmark/perturbation_data.h5ad - reg_type: - method_id: positive_control - subsample: -2 - max_workers: 10 - tf_all: ./resources/prior/tf_all.csv - layer: pearson - consensus: ./resources/prior/consensus-num-regulators.json - - id: _positive_control_scgen_pearson - perturbation_data: ./resources/grn-benchmark/perturbation_data.h5ad - reg_type: - method_id: positive_control - subsample: -2 - max_workers: 10 - tf_all: ./resources/prior/tf_all.csv - layer: scgen_pearson - consensus: ./resources/prior/consensus-num-regulators.json -output_state: "state.yaml" -publish_dir: "./resources/results/grn_evaluation_" diff --git a/params/repo/grn_evaluation_GB_figr.yaml b/params/repo/grn_evaluation_GB_figr.yaml deleted file mode 100644 index 0940a8c89..000000000 --- a/params/repo/grn_evaluation_GB_figr.yaml +++ /dev/null @@ -1,13 +0,0 @@ -param_list: - - id: GB_figr_scgen_pearson - perturbation_data: s3://openproblems-data/resources/grn/grn-benchmark/perturbation_data.h5ad - reg_type: GB - method_id: figr - subsample: -2 - max_workers: 10 - tf_all: s3://openproblems-data/resources/grn/prior/tf_all.csv - layer: scgen_pearson - consensus: s3://openproblems-data/resources/grn/prior/consensus-num-regulators.json - prediction: s3://openproblems-data/resources/grn/grn_models/figr.csv -output_state: "state.yaml" -publish_dir: "s3://openproblems-data/resources/grn/results/grn_evaluation_GB" diff --git a/params/repo/grn_evaluation_ridge.yaml b/params/repo/grn_evaluation_ridge.yaml deleted file mode 100644 index 69141b55e..000000000 --- a/params/repo/grn_evaluation_ridge.yaml +++ /dev/null @@ -1,81 +0,0 @@ -param_list: - - id: ridge_collectri_scgen_pearson - perturbation_data: s3://openproblems-data/resources/grn/grn-benchmark/perturbation_data.h5ad - reg_type: ridge - method_id: collectri - subsample: -2 - max_workers: 10 - tf_all: s3://openproblems-data/resources/grn/prior/tf_all.csv - layer: scgen_pearson - consensus: s3://openproblems-data/resources/grn/prior/consensus-num-regulators.json - prediction: s3://openproblems-data/resources/grn/grn_models/collectri.csv - - id: ridge_celloracle_scgen_pearson - perturbation_data: s3://openproblems-data/resources/grn/grn-benchmark/perturbation_data.h5ad - reg_type: ridge - method_id: celloracle - subsample: -2 - max_workers: 10 - tf_all: s3://openproblems-data/resources/grn/prior/tf_all.csv - layer: scgen_pearson - consensus: s3://openproblems-data/resources/grn/prior/consensus-num-regulators.json - prediction: s3://openproblems-data/resources/grn/grn_models/celloracle.csv - - id: ridge_scenicplus_scgen_pearson - perturbation_data: s3://openproblems-data/resources/grn/grn-benchmark/perturbation_data.h5ad - reg_type: ridge - method_id: scenicplus - subsample: -2 - max_workers: 10 - tf_all: s3://openproblems-data/resources/grn/prior/tf_all.csv - layer: scgen_pearson - consensus: s3://openproblems-data/resources/grn/prior/consensus-num-regulators.json - prediction: s3://openproblems-data/resources/grn/grn_models/scenicplus.csv - - id: ridge_figr_scgen_pearson - perturbation_data: s3://openproblems-data/resources/grn/grn-benchmark/perturbation_data.h5ad - reg_type: ridge - method_id: figr - subsample: -2 - max_workers: 10 - tf_all: s3://openproblems-data/resources/grn/prior/tf_all.csv - layer: scgen_pearson - consensus: s3://openproblems-data/resources/grn/prior/consensus-num-regulators.json - prediction: s3://openproblems-data/resources/grn/grn_models/figr.csv - - id: ridge_granie_scgen_pearson - perturbation_data: s3://openproblems-data/resources/grn/grn-benchmark/perturbation_data.h5ad - reg_type: ridge - method_id: granie - subsample: -2 - max_workers: 10 - tf_all: s3://openproblems-data/resources/grn/prior/tf_all.csv - layer: scgen_pearson - consensus: s3://openproblems-data/resources/grn/prior/consensus-num-regulators.json - prediction: s3://openproblems-data/resources/grn/grn_models/granie.csv - - id: ridge_scglue_scgen_pearson - perturbation_data: s3://openproblems-data/resources/grn/grn-benchmark/perturbation_data.h5ad - reg_type: ridge - method_id: scglue - subsample: -2 - max_workers: 10 - tf_all: s3://openproblems-data/resources/grn/prior/tf_all.csv - layer: scgen_pearson - consensus: s3://openproblems-data/resources/grn/prior/consensus-num-regulators.json - prediction: s3://openproblems-data/resources/grn/grn_models/scglue.csv - - id: ridge_negative_control_scgen_pearson - perturbation_data: s3://openproblems-data/resources/grn/grn-benchmark/perturbation_data.h5ad - reg_type: ridge - method_id: negative_control - subsample: -2 - max_workers: 10 - tf_all: s3://openproblems-data/resources/grn/prior/tf_all.csv - layer: scgen_pearson - consensus: s3://openproblems-data/resources/grn/prior/consensus-num-regulators.json - - id: ridge_positive_control_scgen_pearson - perturbation_data: s3://openproblems-data/resources/grn/grn-benchmark/perturbation_data.h5ad - reg_type: ridge - method_id: positive_control - subsample: -2 - max_workers: 10 - tf_all: s3://openproblems-data/resources/grn/prior/tf_all.csv - layer: scgen_pearson - consensus: s3://openproblems-data/resources/grn/prior/consensus-num-regulators.json -output_state: "state.yaml" -publish_dir: "s3://openproblems-data/resources/grn/results/grn_evaluation_ridge" diff --git a/params/repo/pearson_gb.yaml b/params/repo/pearson_gb.yaml deleted file mode 100644 index 049103b0a..000000000 --- a/params/repo/pearson_gb.yaml +++ /dev/null @@ -1,83 +0,0 @@ -param_list: - - id: pearson_collectri - perturbation_data: s3://openproblems-data/resources/grn/grn-benchmark/perturbation_data.h5ad - layer: pearson - reg_type: GB - method_id: collectri - subsample: -2 - max_workers: 20 - consensus: s3://openproblems-data/resources/grn/prior/consensus-num-regulators.json - - prediction: s3://openproblems-data/resources/grn/grn_models/collectri.csv - - id: pearson_celloracle - perturbation_data: s3://openproblems-data/resources/grn/grn-benchmark/perturbation_data.h5ad - layer: pearson - reg_type: GB - method_id: celloracle - subsample: -2 - max_workers: 20 - consensus: s3://openproblems-data/resources/grn/prior/consensus-num-regulators.json - - prediction: s3://openproblems-data/resources/grn/grn_models/celloracle.csv - - id: pearson_scenicplus - perturbation_data: s3://openproblems-data/resources/grn/grn-benchmark/perturbation_data.h5ad - layer: pearson - reg_type: GB - method_id: scenicplus - subsample: -2 - max_workers: 20 - consensus: s3://openproblems-data/resources/grn/prior/consensus-num-regulators.json - - prediction: s3://openproblems-data/resources/grn/grn_models/scenicplus.csv - - id: pearson_figr - perturbation_data: s3://openproblems-data/resources/grn/grn-benchmark/perturbation_data.h5ad - layer: pearson - reg_type: GB - method_id: figr - subsample: -2 - max_workers: 20 - consensus: s3://openproblems-data/resources/grn/prior/consensus-num-regulators.json - - prediction: s3://openproblems-data/resources/grn/grn_models/figr.csv - - id: pearson_granie - perturbation_data: s3://openproblems-data/resources/grn/grn-benchmark/perturbation_data.h5ad - layer: pearson - reg_type: GB - method_id: granie - subsample: -2 - max_workers: 20 - consensus: s3://openproblems-data/resources/grn/prior/consensus-num-regulators.json - - prediction: s3://openproblems-data/resources/grn/grn_models/granie.csv - - id: pearson_scglue - perturbation_data: s3://openproblems-data/resources/grn/grn-benchmark/perturbation_data.h5ad - layer: pearson - reg_type: GB - method_id: scglue - subsample: -2 - max_workers: 20 - consensus: s3://openproblems-data/resources/grn/prior/consensus-num-regulators.json - - prediction: s3://openproblems-data/resources/grn/grn_models/scglue.csv - - id: pearson_negative_control - perturbation_data: s3://openproblems-data/resources/grn/grn-benchmark/perturbation_data.h5ad - layer: pearson - reg_type: GB - method_id: negative_control - subsample: -2 - max_workers: 20 - consensus: s3://openproblems-data/resources/grn/prior/consensus-num-regulators.json - - prediction: s3://openproblems-data/resources/grn/grn_models/negative_control.csv - - id: pearson_positive_control - perturbation_data: s3://openproblems-data/resources/grn/grn-benchmark/perturbation_data.h5ad - layer: pearson - reg_type: GB - method_id: positive_control - subsample: -2 - max_workers: 20 - consensus: s3://openproblems-data/resources/grn/prior/consensus-num-regulators.json - tf_all: s3://openproblems-data/resources/grn/prior/tf_all.csv - -output_state: "state.yaml" -publish_dir: "s3://openproblems-data/resources/grn/results/pearson_gb" diff --git a/params/repo/pearson_gb_subsample.yaml b/params/repo/pearson_gb_subsample.yaml deleted file mode 100644 index 96764ac60..000000000 --- a/params/repo/pearson_gb_subsample.yaml +++ /dev/null @@ -1,83 +0,0 @@ -param_list: - - id: pearson_collectri - perturbation_data: s3://openproblems-data/resources/grn/grn-benchmark/perturbation_data.h5ad - layer: pearson - reg_type: GB - method_id: collectri - subsample: -2 - max_workers: 10 - consensus: s3://openproblems-data/resources/grn/prior/consensus-num-regulators.json - - prediction: s3://openproblems-data/resources/grn/grn_models/collectri.csv - - id: pearson_celloracle - perturbation_data: s3://openproblems-data/resources/grn/grn-benchmark/perturbation_data.h5ad - layer: pearson - reg_type: GB - method_id: celloracle - subsample: -2 - max_workers: 10 - consensus: s3://openproblems-data/resources/grn/prior/consensus-num-regulators.json - - prediction: s3://openproblems-data/resources/grn/grn_models/celloracle.csv - - id: pearson_scenicplus - perturbation_data: s3://openproblems-data/resources/grn/grn-benchmark/perturbation_data.h5ad - layer: pearson - reg_type: GB - method_id: scenicplus - subsample: -2 - max_workers: 10 - consensus: s3://openproblems-data/resources/grn/prior/consensus-num-regulators.json - - prediction: s3://openproblems-data/resources/grn/grn_models/scenicplus.csv - - id: pearson_figr - perturbation_data: s3://openproblems-data/resources/grn/grn-benchmark/perturbation_data.h5ad - layer: pearson - reg_type: GB - method_id: figr - subsample: -2 - max_workers: 10 - consensus: s3://openproblems-data/resources/grn/prior/consensus-num-regulators.json - - prediction: s3://openproblems-data/resources/grn/grn_models/figr.csv - - id: pearson_granie - perturbation_data: s3://openproblems-data/resources/grn/grn-benchmark/perturbation_data.h5ad - layer: pearson - reg_type: GB - method_id: granie - subsample: -2 - max_workers: 10 - consensus: s3://openproblems-data/resources/grn/prior/consensus-num-regulators.json - - prediction: s3://openproblems-data/resources/grn/grn_models/granie.csv - - id: pearson_scglue - perturbation_data: s3://openproblems-data/resources/grn/grn-benchmark/perturbation_data.h5ad - layer: pearson - reg_type: GB - method_id: scglue - subsample: -2 - max_workers: 10 - consensus: s3://openproblems-data/resources/grn/prior/consensus-num-regulators.json - - prediction: s3://openproblems-data/resources/grn/grn_models/scglue.csv - - id: pearson_negative_control - perturbation_data: s3://openproblems-data/resources/grn/grn-benchmark/perturbation_data.h5ad - layer: pearson - reg_type: GB - method_id: negative_control - subsample: -2 - max_workers: 10 - consensus: s3://openproblems-data/resources/grn/prior/consensus-num-regulators.json - - prediction: s3://openproblems-data/resources/grn/grn_models/negative_control.csv - - id: pearson_positive_control - perturbation_data: s3://openproblems-data/resources/grn/grn-benchmark/perturbation_data.h5ad - layer: pearson - reg_type: GB - method_id: positive_control - subsample: -2 - max_workers: 10 - consensus: s3://openproblems-data/resources/grn/prior/consensus-num-regulators.json - tf_all: s3://openproblems-data/resources/grn/prior/tf_all.csv - -output_state: "state.yaml" -publish_dir: "s3://openproblems-data/resources/grn/results/pearson_gb_subsample" diff --git a/params/repo/pearson_gb_subsample_RF.yaml b/params/repo/pearson_gb_subsample_RF.yaml deleted file mode 100644 index 9b570e7c4..000000000 --- a/params/repo/pearson_gb_subsample_RF.yaml +++ /dev/null @@ -1,83 +0,0 @@ -param_list: - - id: pearson_collectri - perturbation_data: s3://openproblems-data/resources/grn/grn-benchmark/perturbation_data.h5ad - layer: pearson - reg_type: RF - method_id: collectri - subsample: -2 - max_workers: 10 - consensus: s3://openproblems-data/resources/grn/prior/consensus-num-regulators.json - - prediction: s3://openproblems-data/resources/grn/grn_models/collectri.csv - - id: pearson_celloracle - perturbation_data: s3://openproblems-data/resources/grn/grn-benchmark/perturbation_data.h5ad - layer: pearson - reg_type: RF - method_id: celloracle - subsample: -2 - max_workers: 10 - consensus: s3://openproblems-data/resources/grn/prior/consensus-num-regulators.json - - prediction: s3://openproblems-data/resources/grn/grn_models/celloracle.csv - - id: pearson_scenicplus - perturbation_data: s3://openproblems-data/resources/grn/grn-benchmark/perturbation_data.h5ad - layer: pearson - reg_type: RF - method_id: scenicplus - subsample: -2 - max_workers: 10 - consensus: s3://openproblems-data/resources/grn/prior/consensus-num-regulators.json - - prediction: s3://openproblems-data/resources/grn/grn_models/scenicplus.csv - - id: pearson_figr - perturbation_data: s3://openproblems-data/resources/grn/grn-benchmark/perturbation_data.h5ad - layer: pearson - reg_type: RF - method_id: figr - subsample: -2 - max_workers: 10 - consensus: s3://openproblems-data/resources/grn/prior/consensus-num-regulators.json - - prediction: s3://openproblems-data/resources/grn/grn_models/figr.csv - - id: pearson_granie - perturbation_data: s3://openproblems-data/resources/grn/grn-benchmark/perturbation_data.h5ad - layer: pearson - reg_type: RF - method_id: granie - subsample: -2 - max_workers: 10 - consensus: s3://openproblems-data/resources/grn/prior/consensus-num-regulators.json - - prediction: s3://openproblems-data/resources/grn/grn_models/granie.csv - - id: pearson_scglue - perturbation_data: s3://openproblems-data/resources/grn/grn-benchmark/perturbation_data.h5ad - layer: pearson - reg_type: RF - method_id: scglue - subsample: -2 - max_workers: 10 - consensus: s3://openproblems-data/resources/grn/prior/consensus-num-regulators.json - - prediction: s3://openproblems-data/resources/grn/grn_models/scglue.csv - - id: pearson_negative_control - perturbation_data: s3://openproblems-data/resources/grn/grn-benchmark/perturbation_data.h5ad - layer: pearson - reg_type: RF - method_id: negative_control - subsample: -2 - max_workers: 10 - consensus: s3://openproblems-data/resources/grn/prior/consensus-num-regulators.json - - prediction: s3://openproblems-data/resources/grn/grn_models/negative_control.csv - - id: pearson_positive_control - perturbation_data: s3://openproblems-data/resources/grn/grn-benchmark/perturbation_data.h5ad - layer: pearson - reg_type: RF - method_id: positive_control - subsample: -2 - max_workers: 10 - consensus: s3://openproblems-data/resources/grn/prior/consensus-num-regulators.json - tf_all: s3://openproblems-data/resources/grn/prior/tf_all.csv - -output_state: "state.yaml" -publish_dir: "s3://openproblems-data/resources/grn/results/pearson_gb_subsample_RF" diff --git a/params/repo/process_perturbation.yaml b/params/repo/process_perturbation.yaml deleted file mode 100644 index b3feb0d4f..000000000 --- a/params/repo/process_perturbation.yaml +++ /dev/null @@ -1,6 +0,0 @@ -param_list: - - id: process_perturatbion - perturbation_counts: s3://openproblems-data/resources/grn/datasets_raw/perturbation_counts.h5ad - -output_state: "state.yaml" -publish_dir: "s3://openproblems-data/resources/grn/results/process_perturbation" diff --git a/params/repo/robust_analy.yaml b/params/repo/robust_analy.yaml deleted file mode 100644 index 9b78e25c2..000000000 --- a/params/repo/robust_analy.yaml +++ /dev/null @@ -1,267 +0,0 @@ -param_list: - - id: collectri_links_10 - perturbation_data: s3://openproblems-data/resources/grn/grn-benchmark/perturbation_data.h5ad - layer: pearson - reg_type: ridge - method_id: collectri_links_10 - subsample: -2 - max_workers: 10 - consensus: s3://openproblems-data/resources/grn/prior/consensus-num-regulators.json - prediction: s3://openproblems-data/resources/grn/grn_models/collectri.csv - degree: 10 - type: links - - id: celloracle_links_10 - perturbation_data: s3://openproblems-data/resources/grn/grn-benchmark/perturbation_data.h5ad - layer: pearson - reg_type: ridge - method_id: celloracle_links_10 - subsample: -2 - max_workers: 10 - consensus: s3://openproblems-data/resources/grn/prior/consensus-num-regulators.json - prediction: s3://openproblems-data/resources/grn/grn_models/celloracle.csv - degree: 10 - type: links - - id: scenicplus_links_10 - perturbation_data: s3://openproblems-data/resources/grn/grn-benchmark/perturbation_data.h5ad - layer: pearson - reg_type: ridge - method_id: scenicplus_links_10 - subsample: -2 - max_workers: 10 - consensus: s3://openproblems-data/resources/grn/prior/consensus-num-regulators.json - prediction: s3://openproblems-data/resources/grn/grn_models/scenicplus.csv - degree: 10 - type: links - - id: figr_links_10 - perturbation_data: s3://openproblems-data/resources/grn/grn-benchmark/perturbation_data.h5ad - layer: pearson - reg_type: ridge - method_id: figr_links_10 - subsample: -2 - max_workers: 10 - consensus: s3://openproblems-data/resources/grn/prior/consensus-num-regulators.json - prediction: s3://openproblems-data/resources/grn/grn_models/figr.csv - degree: 10 - type: links - - id: granie_links_10 - perturbation_data: s3://openproblems-data/resources/grn/grn-benchmark/perturbation_data.h5ad - layer: pearson - reg_type: ridge - method_id: granie_links_10 - subsample: -2 - max_workers: 10 - consensus: s3://openproblems-data/resources/grn/prior/consensus-num-regulators.json - prediction: s3://openproblems-data/resources/grn/grn_models/granie.csv - degree: 10 - type: links - - id: scglue_links_10 - perturbation_data: s3://openproblems-data/resources/grn/grn-benchmark/perturbation_data.h5ad - layer: pearson - reg_type: ridge - method_id: scglue_links_10 - subsample: -2 - max_workers: 10 - consensus: s3://openproblems-data/resources/grn/prior/consensus-num-regulators.json - prediction: s3://openproblems-data/resources/grn/grn_models/scglue.csv - degree: 10 - type: links - - id: collectri_links_20 - perturbation_data: s3://openproblems-data/resources/grn/grn-benchmark/perturbation_data.h5ad - layer: pearson - reg_type: ridge - method_id: collectri_links_20 - subsample: -2 - max_workers: 10 - consensus: s3://openproblems-data/resources/grn/prior/consensus-num-regulators.json - prediction: s3://openproblems-data/resources/grn/grn_models/collectri.csv - degree: 20 - type: links - - id: celloracle_links_20 - perturbation_data: s3://openproblems-data/resources/grn/grn-benchmark/perturbation_data.h5ad - layer: pearson - reg_type: ridge - method_id: celloracle_links_20 - subsample: -2 - max_workers: 10 - consensus: s3://openproblems-data/resources/grn/prior/consensus-num-regulators.json - prediction: s3://openproblems-data/resources/grn/grn_models/celloracle.csv - degree: 20 - type: links - - id: scenicplus_links_20 - perturbation_data: s3://openproblems-data/resources/grn/grn-benchmark/perturbation_data.h5ad - layer: pearson - reg_type: ridge - method_id: scenicplus_links_20 - subsample: -2 - max_workers: 10 - consensus: s3://openproblems-data/resources/grn/prior/consensus-num-regulators.json - prediction: s3://openproblems-data/resources/grn/grn_models/scenicplus.csv - degree: 20 - type: links - - id: figr_links_20 - perturbation_data: s3://openproblems-data/resources/grn/grn-benchmark/perturbation_data.h5ad - layer: pearson - reg_type: ridge - method_id: figr_links_20 - subsample: -2 - max_workers: 10 - consensus: s3://openproblems-data/resources/grn/prior/consensus-num-regulators.json - prediction: s3://openproblems-data/resources/grn/grn_models/figr.csv - degree: 20 - type: links - - id: granie_links_20 - perturbation_data: s3://openproblems-data/resources/grn/grn-benchmark/perturbation_data.h5ad - layer: pearson - reg_type: ridge - method_id: granie_links_20 - subsample: -2 - max_workers: 10 - consensus: s3://openproblems-data/resources/grn/prior/consensus-num-regulators.json - prediction: s3://openproblems-data/resources/grn/grn_models/granie.csv - degree: 20 - type: links - - id: scglue_links_20 - perturbation_data: s3://openproblems-data/resources/grn/grn-benchmark/perturbation_data.h5ad - layer: pearson - reg_type: ridge - method_id: scglue_links_20 - subsample: -2 - max_workers: 10 - consensus: s3://openproblems-data/resources/grn/prior/consensus-num-regulators.json - prediction: s3://openproblems-data/resources/grn/grn_models/scglue.csv - degree: 20 - type: links - - id: collectri_links_50 - perturbation_data: s3://openproblems-data/resources/grn/grn-benchmark/perturbation_data.h5ad - layer: pearson - reg_type: ridge - method_id: collectri_links_50 - subsample: -2 - max_workers: 10 - consensus: s3://openproblems-data/resources/grn/prior/consensus-num-regulators.json - prediction: s3://openproblems-data/resources/grn/grn_models/collectri.csv - degree: 50 - type: links - - id: celloracle_links_50 - perturbation_data: s3://openproblems-data/resources/grn/grn-benchmark/perturbation_data.h5ad - layer: pearson - reg_type: ridge - method_id: celloracle_links_50 - subsample: -2 - max_workers: 10 - consensus: s3://openproblems-data/resources/grn/prior/consensus-num-regulators.json - prediction: s3://openproblems-data/resources/grn/grn_models/celloracle.csv - degree: 50 - type: links - - id: scenicplus_links_50 - perturbation_data: s3://openproblems-data/resources/grn/grn-benchmark/perturbation_data.h5ad - layer: pearson - reg_type: ridge - method_id: scenicplus_links_50 - subsample: -2 - max_workers: 10 - consensus: s3://openproblems-data/resources/grn/prior/consensus-num-regulators.json - prediction: s3://openproblems-data/resources/grn/grn_models/scenicplus.csv - degree: 50 - type: links - - id: figr_links_50 - perturbation_data: s3://openproblems-data/resources/grn/grn-benchmark/perturbation_data.h5ad - layer: pearson - reg_type: ridge - method_id: figr_links_50 - subsample: -2 - max_workers: 10 - consensus: s3://openproblems-data/resources/grn/prior/consensus-num-regulators.json - prediction: s3://openproblems-data/resources/grn/grn_models/figr.csv - degree: 50 - type: links - - id: granie_links_50 - perturbation_data: s3://openproblems-data/resources/grn/grn-benchmark/perturbation_data.h5ad - layer: pearson - reg_type: ridge - method_id: granie_links_50 - subsample: -2 - max_workers: 10 - consensus: s3://openproblems-data/resources/grn/prior/consensus-num-regulators.json - prediction: s3://openproblems-data/resources/grn/grn_models/granie.csv - degree: 50 - type: links - - id: scglue_links_50 - perturbation_data: s3://openproblems-data/resources/grn/grn-benchmark/perturbation_data.h5ad - layer: pearson - reg_type: ridge - method_id: scglue_links_50 - subsample: -2 - max_workers: 10 - consensus: s3://openproblems-data/resources/grn/prior/consensus-num-regulators.json - prediction: s3://openproblems-data/resources/grn/grn_models/scglue.csv - degree: 50 - type: links - - id: collectri_links_100 - perturbation_data: s3://openproblems-data/resources/grn/grn-benchmark/perturbation_data.h5ad - layer: pearson - reg_type: ridge - method_id: collectri_links_100 - subsample: -2 - max_workers: 10 - consensus: s3://openproblems-data/resources/grn/prior/consensus-num-regulators.json - prediction: s3://openproblems-data/resources/grn/grn_models/collectri.csv - degree: 100 - type: links - - id: celloracle_links_100 - perturbation_data: s3://openproblems-data/resources/grn/grn-benchmark/perturbation_data.h5ad - layer: pearson - reg_type: ridge - method_id: celloracle_links_100 - subsample: -2 - max_workers: 10 - consensus: s3://openproblems-data/resources/grn/prior/consensus-num-regulators.json - prediction: s3://openproblems-data/resources/grn/grn_models/celloracle.csv - degree: 100 - type: links - - id: scenicplus_links_100 - perturbation_data: s3://openproblems-data/resources/grn/grn-benchmark/perturbation_data.h5ad - layer: pearson - reg_type: ridge - method_id: scenicplus_links_100 - subsample: -2 - max_workers: 10 - consensus: s3://openproblems-data/resources/grn/prior/consensus-num-regulators.json - prediction: s3://openproblems-data/resources/grn/grn_models/scenicplus.csv - degree: 100 - type: links - - id: figr_links_100 - perturbation_data: s3://openproblems-data/resources/grn/grn-benchmark/perturbation_data.h5ad - layer: pearson - reg_type: ridge - method_id: figr_links_100 - subsample: -2 - max_workers: 10 - consensus: s3://openproblems-data/resources/grn/prior/consensus-num-regulators.json - prediction: s3://openproblems-data/resources/grn/grn_models/figr.csv - degree: 100 - type: links - - id: granie_links_100 - perturbation_data: s3://openproblems-data/resources/grn/grn-benchmark/perturbation_data.h5ad - layer: pearson - reg_type: ridge - method_id: granie_links_100 - subsample: -2 - max_workers: 10 - consensus: s3://openproblems-data/resources/grn/prior/consensus-num-regulators.json - prediction: s3://openproblems-data/resources/grn/grn_models/granie.csv - degree: 100 - type: links - - id: scglue_links_100 - perturbation_data: s3://openproblems-data/resources/grn/grn-benchmark/perturbation_data.h5ad - layer: pearson - reg_type: ridge - method_id: scglue_links_100 - subsample: -2 - max_workers: 10 - consensus: s3://openproblems-data/resources/grn/prior/consensus-num-regulators.json - prediction: s3://openproblems-data/resources/grn/grn_models/scglue.csv - degree: 100 - type: links -output_state: "state.yaml" -publish_dir: "s3://openproblems-data/resources/grn/results/robust_analy" diff --git a/params/repo/robust_analy_.yaml b/params/repo/robust_analy_.yaml deleted file mode 100644 index 23c2cc22f..000000000 --- a/params/repo/robust_analy_.yaml +++ /dev/null @@ -1,603 +0,0 @@ -param_list: - - id: collectri_0_pearson - perturbation_data: resources/grn-benchmark/perturbation_data.h5ad - reg_type: ridge - method_id: 0-collectri - subsample: -2 - max_workers: 10 - consensus: resources/prior/consensus-num-regulators.json - prediction: resources/grn_models/collectri.csv - degree: 0 - noise_type: - - id: celloracle_0_pearson - perturbation_data: resources/grn-benchmark/perturbation_data.h5ad - reg_type: ridge - method_id: 0-celloracle - subsample: -2 - max_workers: 10 - consensus: resources/prior/consensus-num-regulators.json - prediction: resources/grn_models/celloracle.csv - degree: 0 - noise_type: - - id: scenicplus_0_pearson - perturbation_data: resources/grn-benchmark/perturbation_data.h5ad - reg_type: ridge - method_id: 0-scenicplus - subsample: -2 - max_workers: 10 - consensus: resources/prior/consensus-num-regulators.json - prediction: resources/grn_models/scenicplus.csv - degree: 0 - noise_type: - - id: figr_0_pearson - perturbation_data: resources/grn-benchmark/perturbation_data.h5ad - reg_type: ridge - method_id: 0-figr - subsample: -2 - max_workers: 10 - consensus: resources/prior/consensus-num-regulators.json - prediction: resources/grn_models/figr.csv - degree: 0 - noise_type: - - id: granie_0_pearson - perturbation_data: resources/grn-benchmark/perturbation_data.h5ad - reg_type: ridge - method_id: 0-granie - subsample: -2 - max_workers: 10 - consensus: resources/prior/consensus-num-regulators.json - prediction: resources/grn_models/granie.csv - degree: 0 - noise_type: - - id: scglue_0_pearson - perturbation_data: resources/grn-benchmark/perturbation_data.h5ad - reg_type: ridge - method_id: 0-scglue - subsample: -2 - max_workers: 10 - consensus: resources/prior/consensus-num-regulators.json - prediction: resources/grn_models/scglue.csv - degree: 0 - noise_type: - - id: collectri_10_pearson - perturbation_data: resources/grn-benchmark/perturbation_data.h5ad - reg_type: ridge - method_id: 10-collectri - subsample: -2 - max_workers: 10 - consensus: resources/prior/consensus-num-regulators.json - prediction: resources/grn_models/collectri.csv - degree: 10 - noise_type: - - id: celloracle_10_pearson - perturbation_data: resources/grn-benchmark/perturbation_data.h5ad - reg_type: ridge - method_id: 10-celloracle - subsample: -2 - max_workers: 10 - consensus: resources/prior/consensus-num-regulators.json - prediction: resources/grn_models/celloracle.csv - degree: 10 - noise_type: - - id: scenicplus_10_pearson - perturbation_data: resources/grn-benchmark/perturbation_data.h5ad - reg_type: ridge - method_id: 10-scenicplus - subsample: -2 - max_workers: 10 - consensus: resources/prior/consensus-num-regulators.json - prediction: resources/grn_models/scenicplus.csv - degree: 10 - noise_type: - - id: figr_10_pearson - perturbation_data: resources/grn-benchmark/perturbation_data.h5ad - reg_type: ridge - method_id: 10-figr - subsample: -2 - max_workers: 10 - consensus: resources/prior/consensus-num-regulators.json - prediction: resources/grn_models/figr.csv - degree: 10 - noise_type: - - id: granie_10_pearson - perturbation_data: resources/grn-benchmark/perturbation_data.h5ad - reg_type: ridge - method_id: 10-granie - subsample: -2 - max_workers: 10 - consensus: resources/prior/consensus-num-regulators.json - prediction: resources/grn_models/granie.csv - degree: 10 - noise_type: - - id: scglue_10_pearson - perturbation_data: resources/grn-benchmark/perturbation_data.h5ad - reg_type: ridge - method_id: 10-scglue - subsample: -2 - max_workers: 10 - consensus: resources/prior/consensus-num-regulators.json - prediction: resources/grn_models/scglue.csv - degree: 10 - noise_type: - - id: collectri_20_pearson - perturbation_data: resources/grn-benchmark/perturbation_data.h5ad - reg_type: ridge - method_id: 20-collectri - subsample: -2 - max_workers: 10 - consensus: resources/prior/consensus-num-regulators.json - prediction: resources/grn_models/collectri.csv - degree: 20 - noise_type: - - id: celloracle_20_pearson - perturbation_data: resources/grn-benchmark/perturbation_data.h5ad - reg_type: ridge - method_id: 20-celloracle - subsample: -2 - max_workers: 10 - consensus: resources/prior/consensus-num-regulators.json - prediction: resources/grn_models/celloracle.csv - degree: 20 - noise_type: - - id: scenicplus_20_pearson - perturbation_data: resources/grn-benchmark/perturbation_data.h5ad - reg_type: ridge - method_id: 20-scenicplus - subsample: -2 - max_workers: 10 - consensus: resources/prior/consensus-num-regulators.json - prediction: resources/grn_models/scenicplus.csv - degree: 20 - noise_type: - - id: figr_20_pearson - perturbation_data: resources/grn-benchmark/perturbation_data.h5ad - reg_type: ridge - method_id: 20-figr - subsample: -2 - max_workers: 10 - consensus: resources/prior/consensus-num-regulators.json - prediction: resources/grn_models/figr.csv - degree: 20 - noise_type: - - id: granie_20_pearson - perturbation_data: resources/grn-benchmark/perturbation_data.h5ad - reg_type: ridge - method_id: 20-granie - subsample: -2 - max_workers: 10 - consensus: resources/prior/consensus-num-regulators.json - prediction: resources/grn_models/granie.csv - degree: 20 - noise_type: - - id: scglue_20_pearson - perturbation_data: resources/grn-benchmark/perturbation_data.h5ad - reg_type: ridge - method_id: 20-scglue - subsample: -2 - max_workers: 10 - consensus: resources/prior/consensus-num-regulators.json - prediction: resources/grn_models/scglue.csv - degree: 20 - noise_type: - - id: collectri_50_pearson - perturbation_data: resources/grn-benchmark/perturbation_data.h5ad - reg_type: ridge - method_id: 50-collectri - subsample: -2 - max_workers: 10 - consensus: resources/prior/consensus-num-regulators.json - prediction: resources/grn_models/collectri.csv - degree: 50 - noise_type: - - id: celloracle_50_pearson - perturbation_data: resources/grn-benchmark/perturbation_data.h5ad - reg_type: ridge - method_id: 50-celloracle - subsample: -2 - max_workers: 10 - consensus: resources/prior/consensus-num-regulators.json - prediction: resources/grn_models/celloracle.csv - degree: 50 - noise_type: - - id: scenicplus_50_pearson - perturbation_data: resources/grn-benchmark/perturbation_data.h5ad - reg_type: ridge - method_id: 50-scenicplus - subsample: -2 - max_workers: 10 - consensus: resources/prior/consensus-num-regulators.json - prediction: resources/grn_models/scenicplus.csv - degree: 50 - noise_type: - - id: figr_50_pearson - perturbation_data: resources/grn-benchmark/perturbation_data.h5ad - reg_type: ridge - method_id: 50-figr - subsample: -2 - max_workers: 10 - consensus: resources/prior/consensus-num-regulators.json - prediction: resources/grn_models/figr.csv - degree: 50 - noise_type: - - id: granie_50_pearson - perturbation_data: resources/grn-benchmark/perturbation_data.h5ad - reg_type: ridge - method_id: 50-granie - subsample: -2 - max_workers: 10 - consensus: resources/prior/consensus-num-regulators.json - prediction: resources/grn_models/granie.csv - degree: 50 - noise_type: - - id: scglue_50_pearson - perturbation_data: resources/grn-benchmark/perturbation_data.h5ad - reg_type: ridge - method_id: 50-scglue - subsample: -2 - max_workers: 10 - consensus: resources/prior/consensus-num-regulators.json - prediction: resources/grn_models/scglue.csv - degree: 50 - noise_type: - - id: collectri_100_pearson - perturbation_data: resources/grn-benchmark/perturbation_data.h5ad - reg_type: ridge - method_id: 100-collectri - subsample: -2 - max_workers: 10 - consensus: resources/prior/consensus-num-regulators.json - prediction: resources/grn_models/collectri.csv - degree: 100 - noise_type: - - id: celloracle_100_pearson - perturbation_data: resources/grn-benchmark/perturbation_data.h5ad - reg_type: ridge - method_id: 100-celloracle - subsample: -2 - max_workers: 10 - consensus: resources/prior/consensus-num-regulators.json - prediction: resources/grn_models/celloracle.csv - degree: 100 - noise_type: - - id: scenicplus_100_pearson - perturbation_data: resources/grn-benchmark/perturbation_data.h5ad - reg_type: ridge - method_id: 100-scenicplus - subsample: -2 - max_workers: 10 - consensus: resources/prior/consensus-num-regulators.json - prediction: resources/grn_models/scenicplus.csv - degree: 100 - noise_type: - - id: figr_100_pearson - perturbation_data: resources/grn-benchmark/perturbation_data.h5ad - reg_type: ridge - method_id: 100-figr - subsample: -2 - max_workers: 10 - consensus: resources/prior/consensus-num-regulators.json - prediction: resources/grn_models/figr.csv - degree: 100 - noise_type: - - id: granie_100_pearson - perturbation_data: resources/grn-benchmark/perturbation_data.h5ad - reg_type: ridge - method_id: 100-granie - subsample: -2 - max_workers: 10 - consensus: resources/prior/consensus-num-regulators.json - prediction: resources/grn_models/granie.csv - degree: 100 - noise_type: - - id: scglue_100_pearson - perturbation_data: resources/grn-benchmark/perturbation_data.h5ad - reg_type: ridge - method_id: 100-scglue - subsample: -2 - max_workers: 10 - consensus: resources/prior/consensus-num-regulators.json - prediction: resources/grn_models/scglue.csv - degree: 100 - noise_type: - - id: collectri_0_scgen_pearson - perturbation_data: resources/grn-benchmark/perturbation_data.h5ad - reg_type: ridge - method_id: 0-collectri - subsample: -2 - max_workers: 10 - consensus: resources/prior/consensus-num-regulators.json - prediction: resources/grn_models/collectri.csv - degree: 0 - noise_type: - - id: celloracle_0_scgen_pearson - perturbation_data: resources/grn-benchmark/perturbation_data.h5ad - reg_type: ridge - method_id: 0-celloracle - subsample: -2 - max_workers: 10 - consensus: resources/prior/consensus-num-regulators.json - prediction: resources/grn_models/celloracle.csv - degree: 0 - noise_type: - - id: scenicplus_0_scgen_pearson - perturbation_data: resources/grn-benchmark/perturbation_data.h5ad - reg_type: ridge - method_id: 0-scenicplus - subsample: -2 - max_workers: 10 - consensus: resources/prior/consensus-num-regulators.json - prediction: resources/grn_models/scenicplus.csv - degree: 0 - noise_type: - - id: figr_0_scgen_pearson - perturbation_data: resources/grn-benchmark/perturbation_data.h5ad - reg_type: ridge - method_id: 0-figr - subsample: -2 - max_workers: 10 - consensus: resources/prior/consensus-num-regulators.json - prediction: resources/grn_models/figr.csv - degree: 0 - noise_type: - - id: granie_0_scgen_pearson - perturbation_data: resources/grn-benchmark/perturbation_data.h5ad - reg_type: ridge - method_id: 0-granie - subsample: -2 - max_workers: 10 - consensus: resources/prior/consensus-num-regulators.json - prediction: resources/grn_models/granie.csv - degree: 0 - noise_type: - - id: scglue_0_scgen_pearson - perturbation_data: resources/grn-benchmark/perturbation_data.h5ad - reg_type: ridge - method_id: 0-scglue - subsample: -2 - max_workers: 10 - consensus: resources/prior/consensus-num-regulators.json - prediction: resources/grn_models/scglue.csv - degree: 0 - noise_type: - - id: collectri_10_scgen_pearson - perturbation_data: resources/grn-benchmark/perturbation_data.h5ad - reg_type: ridge - method_id: 10-collectri - subsample: -2 - max_workers: 10 - consensus: resources/prior/consensus-num-regulators.json - prediction: resources/grn_models/collectri.csv - degree: 10 - noise_type: - - id: celloracle_10_scgen_pearson - perturbation_data: resources/grn-benchmark/perturbation_data.h5ad - reg_type: ridge - method_id: 10-celloracle - subsample: -2 - max_workers: 10 - consensus: resources/prior/consensus-num-regulators.json - prediction: resources/grn_models/celloracle.csv - degree: 10 - noise_type: - - id: scenicplus_10_scgen_pearson - perturbation_data: resources/grn-benchmark/perturbation_data.h5ad - reg_type: ridge - method_id: 10-scenicplus - subsample: -2 - max_workers: 10 - consensus: resources/prior/consensus-num-regulators.json - prediction: resources/grn_models/scenicplus.csv - degree: 10 - noise_type: - - id: figr_10_scgen_pearson - perturbation_data: resources/grn-benchmark/perturbation_data.h5ad - reg_type: ridge - method_id: 10-figr - subsample: -2 - max_workers: 10 - consensus: resources/prior/consensus-num-regulators.json - prediction: resources/grn_models/figr.csv - degree: 10 - noise_type: - - id: granie_10_scgen_pearson - perturbation_data: resources/grn-benchmark/perturbation_data.h5ad - reg_type: ridge - method_id: 10-granie - subsample: -2 - max_workers: 10 - consensus: resources/prior/consensus-num-regulators.json - prediction: resources/grn_models/granie.csv - degree: 10 - noise_type: - - id: scglue_10_scgen_pearson - perturbation_data: resources/grn-benchmark/perturbation_data.h5ad - reg_type: ridge - method_id: 10-scglue - subsample: -2 - max_workers: 10 - consensus: resources/prior/consensus-num-regulators.json - prediction: resources/grn_models/scglue.csv - degree: 10 - noise_type: - - id: collectri_20_scgen_pearson - perturbation_data: resources/grn-benchmark/perturbation_data.h5ad - reg_type: ridge - method_id: 20-collectri - subsample: -2 - max_workers: 10 - consensus: resources/prior/consensus-num-regulators.json - prediction: resources/grn_models/collectri.csv - degree: 20 - noise_type: - - id: celloracle_20_scgen_pearson - perturbation_data: resources/grn-benchmark/perturbation_data.h5ad - reg_type: ridge - method_id: 20-celloracle - subsample: -2 - max_workers: 10 - consensus: resources/prior/consensus-num-regulators.json - prediction: resources/grn_models/celloracle.csv - degree: 20 - noise_type: - - id: scenicplus_20_scgen_pearson - perturbation_data: resources/grn-benchmark/perturbation_data.h5ad - reg_type: ridge - method_id: 20-scenicplus - subsample: -2 - max_workers: 10 - consensus: resources/prior/consensus-num-regulators.json - prediction: resources/grn_models/scenicplus.csv - degree: 20 - noise_type: - - id: figr_20_scgen_pearson - perturbation_data: resources/grn-benchmark/perturbation_data.h5ad - reg_type: ridge - method_id: 20-figr - subsample: -2 - max_workers: 10 - consensus: resources/prior/consensus-num-regulators.json - prediction: resources/grn_models/figr.csv - degree: 20 - noise_type: - - id: granie_20_scgen_pearson - perturbation_data: resources/grn-benchmark/perturbation_data.h5ad - reg_type: ridge - method_id: 20-granie - subsample: -2 - max_workers: 10 - consensus: resources/prior/consensus-num-regulators.json - prediction: resources/grn_models/granie.csv - degree: 20 - noise_type: - - id: scglue_20_scgen_pearson - perturbation_data: resources/grn-benchmark/perturbation_data.h5ad - reg_type: ridge - method_id: 20-scglue - subsample: -2 - max_workers: 10 - consensus: resources/prior/consensus-num-regulators.json - prediction: resources/grn_models/scglue.csv - degree: 20 - noise_type: - - id: collectri_50_scgen_pearson - perturbation_data: resources/grn-benchmark/perturbation_data.h5ad - reg_type: ridge - method_id: 50-collectri - subsample: -2 - max_workers: 10 - consensus: resources/prior/consensus-num-regulators.json - prediction: resources/grn_models/collectri.csv - degree: 50 - noise_type: - - id: celloracle_50_scgen_pearson - perturbation_data: resources/grn-benchmark/perturbation_data.h5ad - reg_type: ridge - method_id: 50-celloracle - subsample: -2 - max_workers: 10 - consensus: resources/prior/consensus-num-regulators.json - prediction: resources/grn_models/celloracle.csv - degree: 50 - noise_type: - - id: scenicplus_50_scgen_pearson - perturbation_data: resources/grn-benchmark/perturbation_data.h5ad - reg_type: ridge - method_id: 50-scenicplus - subsample: -2 - max_workers: 10 - consensus: resources/prior/consensus-num-regulators.json - prediction: resources/grn_models/scenicplus.csv - degree: 50 - noise_type: - - id: figr_50_scgen_pearson - perturbation_data: resources/grn-benchmark/perturbation_data.h5ad - reg_type: ridge - method_id: 50-figr - subsample: -2 - max_workers: 10 - consensus: resources/prior/consensus-num-regulators.json - prediction: resources/grn_models/figr.csv - degree: 50 - noise_type: - - id: granie_50_scgen_pearson - perturbation_data: resources/grn-benchmark/perturbation_data.h5ad - reg_type: ridge - method_id: 50-granie - subsample: -2 - max_workers: 10 - consensus: resources/prior/consensus-num-regulators.json - prediction: resources/grn_models/granie.csv - degree: 50 - noise_type: - - id: scglue_50_scgen_pearson - perturbation_data: resources/grn-benchmark/perturbation_data.h5ad - reg_type: ridge - method_id: 50-scglue - subsample: -2 - max_workers: 10 - consensus: resources/prior/consensus-num-regulators.json - prediction: resources/grn_models/scglue.csv - degree: 50 - noise_type: - - id: collectri_100_scgen_pearson - perturbation_data: resources/grn-benchmark/perturbation_data.h5ad - reg_type: ridge - method_id: 100-collectri - subsample: -2 - max_workers: 10 - consensus: resources/prior/consensus-num-regulators.json - prediction: resources/grn_models/collectri.csv - degree: 100 - noise_type: - - id: celloracle_100_scgen_pearson - perturbation_data: resources/grn-benchmark/perturbation_data.h5ad - reg_type: ridge - method_id: 100-celloracle - subsample: -2 - max_workers: 10 - consensus: resources/prior/consensus-num-regulators.json - prediction: resources/grn_models/celloracle.csv - degree: 100 - noise_type: - - id: scenicplus_100_scgen_pearson - perturbation_data: resources/grn-benchmark/perturbation_data.h5ad - reg_type: ridge - method_id: 100-scenicplus - subsample: -2 - max_workers: 10 - consensus: resources/prior/consensus-num-regulators.json - prediction: resources/grn_models/scenicplus.csv - degree: 100 - noise_type: - - id: figr_100_scgen_pearson - perturbation_data: resources/grn-benchmark/perturbation_data.h5ad - reg_type: ridge - method_id: 100-figr - subsample: -2 - max_workers: 10 - consensus: resources/prior/consensus-num-regulators.json - prediction: resources/grn_models/figr.csv - degree: 100 - noise_type: - - id: granie_100_scgen_pearson - perturbation_data: resources/grn-benchmark/perturbation_data.h5ad - reg_type: ridge - method_id: 100-granie - subsample: -2 - max_workers: 10 - consensus: resources/prior/consensus-num-regulators.json - prediction: resources/grn_models/granie.csv - degree: 100 - noise_type: - - id: scglue_100_scgen_pearson - perturbation_data: resources/grn-benchmark/perturbation_data.h5ad - reg_type: ridge - method_id: 100-scglue - subsample: -2 - max_workers: 10 - consensus: resources/prior/consensus-num-regulators.json - prediction: resources/grn_models/scglue.csv - degree: 100 - noise_type: -output_state: "state.yaml" -publish_dir: "output/robust_analy_" diff --git a/params/repo/robust_analy_binary.yaml b/params/repo/robust_analy_binary.yaml deleted file mode 100644 index 198d80d20..000000000 --- a/params/repo/robust_analy_binary.yaml +++ /dev/null @@ -1,333 +0,0 @@ -param_list: - - id: collectri_0 - perturbation_data: resources/grn-benchmark/perturbation_data.h5ad - layer: pearson - reg_type: ridge - method_id: 0-collectri - subsample: -2 - max_workers: 10 - consensus: resources/prior/consensus-num-regulators.json - prediction: resources/grn_models/collectri.csv - degree: 0 - noise_type: binary - - id: celloracle_0 - perturbation_data: resources/grn-benchmark/perturbation_data.h5ad - layer: pearson - reg_type: ridge - method_id: 0-celloracle - subsample: -2 - max_workers: 10 - consensus: resources/prior/consensus-num-regulators.json - prediction: resources/grn_models/celloracle.csv - degree: 0 - noise_type: binary - - id: scenicplus_0 - perturbation_data: resources/grn-benchmark/perturbation_data.h5ad - layer: pearson - reg_type: ridge - method_id: 0-scenicplus - subsample: -2 - max_workers: 10 - consensus: resources/prior/consensus-num-regulators.json - prediction: resources/grn_models/scenicplus.csv - degree: 0 - noise_type: binary - - id: figr_0 - perturbation_data: resources/grn-benchmark/perturbation_data.h5ad - layer: pearson - reg_type: ridge - method_id: 0-figr - subsample: -2 - max_workers: 10 - consensus: resources/prior/consensus-num-regulators.json - prediction: resources/grn_models/figr.csv - degree: 0 - noise_type: binary - - id: granie_0 - perturbation_data: resources/grn-benchmark/perturbation_data.h5ad - layer: pearson - reg_type: ridge - method_id: 0-granie - subsample: -2 - max_workers: 10 - consensus: resources/prior/consensus-num-regulators.json - prediction: resources/grn_models/granie.csv - degree: 0 - noise_type: binary - - id: scglue_0 - perturbation_data: resources/grn-benchmark/perturbation_data.h5ad - layer: pearson - reg_type: ridge - method_id: 0-scglue - subsample: -2 - max_workers: 10 - consensus: resources/prior/consensus-num-regulators.json - prediction: resources/grn_models/scglue.csv - degree: 0 - noise_type: binary - - id: collectri_10 - perturbation_data: resources/grn-benchmark/perturbation_data.h5ad - layer: pearson - reg_type: ridge - method_id: 10-collectri - subsample: -2 - max_workers: 10 - consensus: resources/prior/consensus-num-regulators.json - prediction: resources/grn_models/collectri.csv - degree: 10 - noise_type: binary - - id: celloracle_10 - perturbation_data: resources/grn-benchmark/perturbation_data.h5ad - layer: pearson - reg_type: ridge - method_id: 10-celloracle - subsample: -2 - max_workers: 10 - consensus: resources/prior/consensus-num-regulators.json - prediction: resources/grn_models/celloracle.csv - degree: 10 - noise_type: binary - - id: scenicplus_10 - perturbation_data: resources/grn-benchmark/perturbation_data.h5ad - layer: pearson - reg_type: ridge - method_id: 10-scenicplus - subsample: -2 - max_workers: 10 - consensus: resources/prior/consensus-num-regulators.json - prediction: resources/grn_models/scenicplus.csv - degree: 10 - noise_type: binary - - id: figr_10 - perturbation_data: resources/grn-benchmark/perturbation_data.h5ad - layer: pearson - reg_type: ridge - method_id: 10-figr - subsample: -2 - max_workers: 10 - consensus: resources/prior/consensus-num-regulators.json - prediction: resources/grn_models/figr.csv - degree: 10 - noise_type: binary - - id: granie_10 - perturbation_data: resources/grn-benchmark/perturbation_data.h5ad - layer: pearson - reg_type: ridge - method_id: 10-granie - subsample: -2 - max_workers: 10 - consensus: resources/prior/consensus-num-regulators.json - prediction: resources/grn_models/granie.csv - degree: 10 - noise_type: binary - - id: scglue_10 - perturbation_data: resources/grn-benchmark/perturbation_data.h5ad - layer: pearson - reg_type: ridge - method_id: 10-scglue - subsample: -2 - max_workers: 10 - consensus: resources/prior/consensus-num-regulators.json - prediction: resources/grn_models/scglue.csv - degree: 10 - noise_type: binary - - id: collectri_20 - perturbation_data: resources/grn-benchmark/perturbation_data.h5ad - layer: pearson - reg_type: ridge - method_id: 20-collectri - subsample: -2 - max_workers: 10 - consensus: resources/prior/consensus-num-regulators.json - prediction: resources/grn_models/collectri.csv - degree: 20 - noise_type: binary - - id: celloracle_20 - perturbation_data: resources/grn-benchmark/perturbation_data.h5ad - layer: pearson - reg_type: ridge - method_id: 20-celloracle - subsample: -2 - max_workers: 10 - consensus: resources/prior/consensus-num-regulators.json - prediction: resources/grn_models/celloracle.csv - degree: 20 - noise_type: binary - - id: scenicplus_20 - perturbation_data: resources/grn-benchmark/perturbation_data.h5ad - layer: pearson - reg_type: ridge - method_id: 20-scenicplus - subsample: -2 - max_workers: 10 - consensus: resources/prior/consensus-num-regulators.json - prediction: resources/grn_models/scenicplus.csv - degree: 20 - noise_type: binary - - id: figr_20 - perturbation_data: resources/grn-benchmark/perturbation_data.h5ad - layer: pearson - reg_type: ridge - method_id: 20-figr - subsample: -2 - max_workers: 10 - consensus: resources/prior/consensus-num-regulators.json - prediction: resources/grn_models/figr.csv - degree: 20 - noise_type: binary - - id: granie_20 - perturbation_data: resources/grn-benchmark/perturbation_data.h5ad - layer: pearson - reg_type: ridge - method_id: 20-granie - subsample: -2 - max_workers: 10 - consensus: resources/prior/consensus-num-regulators.json - prediction: resources/grn_models/granie.csv - degree: 20 - noise_type: binary - - id: scglue_20 - perturbation_data: resources/grn-benchmark/perturbation_data.h5ad - layer: pearson - reg_type: ridge - method_id: 20-scglue - subsample: -2 - max_workers: 10 - consensus: resources/prior/consensus-num-regulators.json - prediction: resources/grn_models/scglue.csv - degree: 20 - noise_type: binary - - id: collectri_50 - perturbation_data: resources/grn-benchmark/perturbation_data.h5ad - layer: pearson - reg_type: ridge - method_id: 50-collectri - subsample: -2 - max_workers: 10 - consensus: resources/prior/consensus-num-regulators.json - prediction: resources/grn_models/collectri.csv - degree: 50 - noise_type: binary - - id: celloracle_50 - perturbation_data: resources/grn-benchmark/perturbation_data.h5ad - layer: pearson - reg_type: ridge - method_id: 50-celloracle - subsample: -2 - max_workers: 10 - consensus: resources/prior/consensus-num-regulators.json - prediction: resources/grn_models/celloracle.csv - degree: 50 - noise_type: binary - - id: scenicplus_50 - perturbation_data: resources/grn-benchmark/perturbation_data.h5ad - layer: pearson - reg_type: ridge - method_id: 50-scenicplus - subsample: -2 - max_workers: 10 - consensus: resources/prior/consensus-num-regulators.json - prediction: resources/grn_models/scenicplus.csv - degree: 50 - noise_type: binary - - id: figr_50 - perturbation_data: resources/grn-benchmark/perturbation_data.h5ad - layer: pearson - reg_type: ridge - method_id: 50-figr - subsample: -2 - max_workers: 10 - consensus: resources/prior/consensus-num-regulators.json - prediction: resources/grn_models/figr.csv - degree: 50 - noise_type: binary - - id: granie_50 - perturbation_data: resources/grn-benchmark/perturbation_data.h5ad - layer: pearson - reg_type: ridge - method_id: 50-granie - subsample: -2 - max_workers: 10 - consensus: resources/prior/consensus-num-regulators.json - prediction: resources/grn_models/granie.csv - degree: 50 - noise_type: binary - - id: scglue_50 - perturbation_data: resources/grn-benchmark/perturbation_data.h5ad - layer: pearson - reg_type: ridge - method_id: 50-scglue - subsample: -2 - max_workers: 10 - consensus: resources/prior/consensus-num-regulators.json - prediction: resources/grn_models/scglue.csv - degree: 50 - noise_type: binary - - id: collectri_100 - perturbation_data: resources/grn-benchmark/perturbation_data.h5ad - layer: pearson - reg_type: ridge - method_id: 100-collectri - subsample: -2 - max_workers: 10 - consensus: resources/prior/consensus-num-regulators.json - prediction: resources/grn_models/collectri.csv - degree: 100 - noise_type: binary - - id: celloracle_100 - perturbation_data: resources/grn-benchmark/perturbation_data.h5ad - layer: pearson - reg_type: ridge - method_id: 100-celloracle - subsample: -2 - max_workers: 10 - consensus: resources/prior/consensus-num-regulators.json - prediction: resources/grn_models/celloracle.csv - degree: 100 - noise_type: binary - - id: scenicplus_100 - perturbation_data: resources/grn-benchmark/perturbation_data.h5ad - layer: pearson - reg_type: ridge - method_id: 100-scenicplus - subsample: -2 - max_workers: 10 - consensus: resources/prior/consensus-num-regulators.json - prediction: resources/grn_models/scenicplus.csv - degree: 100 - noise_type: binary - - id: figr_100 - perturbation_data: resources/grn-benchmark/perturbation_data.h5ad - layer: pearson - reg_type: ridge - method_id: 100-figr - subsample: -2 - max_workers: 10 - consensus: resources/prior/consensus-num-regulators.json - prediction: resources/grn_models/figr.csv - degree: 100 - noise_type: binary - - id: granie_100 - perturbation_data: resources/grn-benchmark/perturbation_data.h5ad - layer: pearson - reg_type: ridge - method_id: 100-granie - subsample: -2 - max_workers: 10 - consensus: resources/prior/consensus-num-regulators.json - prediction: resources/grn_models/granie.csv - degree: 100 - noise_type: binary - - id: scglue_100 - perturbation_data: resources/grn-benchmark/perturbation_data.h5ad - layer: pearson - reg_type: ridge - method_id: 100-scglue - subsample: -2 - max_workers: 10 - consensus: resources/prior/consensus-num-regulators.json - prediction: resources/grn_models/scglue.csv - degree: 100 - noise_type: binary -output_state: "state.yaml" -publish_dir: "output/robust_analy_binary" diff --git a/params/repo/robust_analy_links.yaml b/params/repo/robust_analy_links.yaml deleted file mode 100644 index 56a0a5df0..000000000 --- a/params/repo/robust_analy_links.yaml +++ /dev/null @@ -1,267 +0,0 @@ -param_list: - - id: collectri_10 - perturbation_data: resources/grn-benchmark/perturbation_data.h5ad - layer: pearson - reg_type: ridge - method_id: 10-collectri - subsample: -2 - max_workers: 10 - consensus: resources/prior/consensus-num-regulators.json - prediction: resources/grn_models/collectri.csv - degree: 10 - noise_type: links - - id: celloracle_10 - perturbation_data: resources/grn-benchmark/perturbation_data.h5ad - layer: pearson - reg_type: ridge - method_id: 10-celloracle - subsample: -2 - max_workers: 10 - consensus: resources/prior/consensus-num-regulators.json - prediction: resources/grn_models/celloracle.csv - degree: 10 - noise_type: links - - id: scenicplus_10 - perturbation_data: resources/grn-benchmark/perturbation_data.h5ad - layer: pearson - reg_type: ridge - method_id: 10-scenicplus - subsample: -2 - max_workers: 10 - consensus: resources/prior/consensus-num-regulators.json - prediction: resources/grn_models/scenicplus.csv - degree: 10 - noise_type: links - - id: figr_10 - perturbation_data: resources/grn-benchmark/perturbation_data.h5ad - layer: pearson - reg_type: ridge - method_id: 10-figr - subsample: -2 - max_workers: 10 - consensus: resources/prior/consensus-num-regulators.json - prediction: resources/grn_models/figr.csv - degree: 10 - noise_type: links - - id: granie_10 - perturbation_data: resources/grn-benchmark/perturbation_data.h5ad - layer: pearson - reg_type: ridge - method_id: 10-granie - subsample: -2 - max_workers: 10 - consensus: resources/prior/consensus-num-regulators.json - prediction: resources/grn_models/granie.csv - degree: 10 - noise_type: links - - id: scglue_10 - perturbation_data: resources/grn-benchmark/perturbation_data.h5ad - layer: pearson - reg_type: ridge - method_id: 10-scglue - subsample: -2 - max_workers: 10 - consensus: resources/prior/consensus-num-regulators.json - prediction: resources/grn_models/scglue.csv - degree: 10 - noise_type: links - - id: collectri_20 - perturbation_data: resources/grn-benchmark/perturbation_data.h5ad - layer: pearson - reg_type: ridge - method_id: 20-collectri - subsample: -2 - max_workers: 10 - consensus: resources/prior/consensus-num-regulators.json - prediction: resources/grn_models/collectri.csv - degree: 20 - noise_type: links - - id: celloracle_20 - perturbation_data: resources/grn-benchmark/perturbation_data.h5ad - layer: pearson - reg_type: ridge - method_id: 20-celloracle - subsample: -2 - max_workers: 10 - consensus: resources/prior/consensus-num-regulators.json - prediction: resources/grn_models/celloracle.csv - degree: 20 - noise_type: links - - id: scenicplus_20 - perturbation_data: resources/grn-benchmark/perturbation_data.h5ad - layer: pearson - reg_type: ridge - method_id: 20-scenicplus - subsample: -2 - max_workers: 10 - consensus: resources/prior/consensus-num-regulators.json - prediction: resources/grn_models/scenicplus.csv - degree: 20 - noise_type: links - - id: figr_20 - perturbation_data: resources/grn-benchmark/perturbation_data.h5ad - layer: pearson - reg_type: ridge - method_id: 20-figr - subsample: -2 - max_workers: 10 - consensus: resources/prior/consensus-num-regulators.json - prediction: resources/grn_models/figr.csv - degree: 20 - noise_type: links - - id: granie_20 - perturbation_data: resources/grn-benchmark/perturbation_data.h5ad - layer: pearson - reg_type: ridge - method_id: 20-granie - subsample: -2 - max_workers: 10 - consensus: resources/prior/consensus-num-regulators.json - prediction: resources/grn_models/granie.csv - degree: 20 - noise_type: links - - id: scglue_20 - perturbation_data: resources/grn-benchmark/perturbation_data.h5ad - layer: pearson - reg_type: ridge - method_id: 20-scglue - subsample: -2 - max_workers: 10 - consensus: resources/prior/consensus-num-regulators.json - prediction: resources/grn_models/scglue.csv - degree: 20 - noise_type: links - - id: collectri_50 - perturbation_data: resources/grn-benchmark/perturbation_data.h5ad - layer: pearson - reg_type: ridge - method_id: 50-collectri - subsample: -2 - max_workers: 10 - consensus: resources/prior/consensus-num-regulators.json - prediction: resources/grn_models/collectri.csv - degree: 50 - noise_type: links - - id: celloracle_50 - perturbation_data: resources/grn-benchmark/perturbation_data.h5ad - layer: pearson - reg_type: ridge - method_id: 50-celloracle - subsample: -2 - max_workers: 10 - consensus: resources/prior/consensus-num-regulators.json - prediction: resources/grn_models/celloracle.csv - degree: 50 - noise_type: links - - id: scenicplus_50 - perturbation_data: resources/grn-benchmark/perturbation_data.h5ad - layer: pearson - reg_type: ridge - method_id: 50-scenicplus - subsample: -2 - max_workers: 10 - consensus: resources/prior/consensus-num-regulators.json - prediction: resources/grn_models/scenicplus.csv - degree: 50 - noise_type: links - - id: figr_50 - perturbation_data: resources/grn-benchmark/perturbation_data.h5ad - layer: pearson - reg_type: ridge - method_id: 50-figr - subsample: -2 - max_workers: 10 - consensus: resources/prior/consensus-num-regulators.json - prediction: resources/grn_models/figr.csv - degree: 50 - noise_type: links - - id: granie_50 - perturbation_data: resources/grn-benchmark/perturbation_data.h5ad - layer: pearson - reg_type: ridge - method_id: 50-granie - subsample: -2 - max_workers: 10 - consensus: resources/prior/consensus-num-regulators.json - prediction: resources/grn_models/granie.csv - degree: 50 - noise_type: links - - id: scglue_50 - perturbation_data: resources/grn-benchmark/perturbation_data.h5ad - layer: pearson - reg_type: ridge - method_id: 50-scglue - subsample: -2 - max_workers: 10 - consensus: resources/prior/consensus-num-regulators.json - prediction: resources/grn_models/scglue.csv - degree: 50 - noise_type: links - - id: collectri_100 - perturbation_data: resources/grn-benchmark/perturbation_data.h5ad - layer: pearson - reg_type: ridge - method_id: 100-collectri - subsample: -2 - max_workers: 10 - consensus: resources/prior/consensus-num-regulators.json - prediction: resources/grn_models/collectri.csv - degree: 100 - noise_type: links - - id: celloracle_100 - perturbation_data: resources/grn-benchmark/perturbation_data.h5ad - layer: pearson - reg_type: ridge - method_id: 100-celloracle - subsample: -2 - max_workers: 10 - consensus: resources/prior/consensus-num-regulators.json - prediction: resources/grn_models/celloracle.csv - degree: 100 - noise_type: links - - id: scenicplus_100 - perturbation_data: resources/grn-benchmark/perturbation_data.h5ad - layer: pearson - reg_type: ridge - method_id: 100-scenicplus - subsample: -2 - max_workers: 10 - consensus: resources/prior/consensus-num-regulators.json - prediction: resources/grn_models/scenicplus.csv - degree: 100 - noise_type: links - - id: figr_100 - perturbation_data: resources/grn-benchmark/perturbation_data.h5ad - layer: pearson - reg_type: ridge - method_id: 100-figr - subsample: -2 - max_workers: 10 - consensus: resources/prior/consensus-num-regulators.json - prediction: resources/grn_models/figr.csv - degree: 100 - noise_type: links - - id: granie_100 - perturbation_data: resources/grn-benchmark/perturbation_data.h5ad - layer: pearson - reg_type: ridge - method_id: 100-granie - subsample: -2 - max_workers: 10 - consensus: resources/prior/consensus-num-regulators.json - prediction: resources/grn_models/granie.csv - degree: 100 - noise_type: links - - id: scglue_100 - perturbation_data: resources/grn-benchmark/perturbation_data.h5ad - layer: pearson - reg_type: ridge - method_id: 100-scglue - subsample: -2 - max_workers: 10 - consensus: resources/prior/consensus-num-regulators.json - prediction: resources/grn_models/scglue.csv - degree: 100 - noise_type: links -output_state: "state.yaml" -publish_dir: "output/robust_analy_links" diff --git a/params/repo/robust_analy_net.yaml b/params/repo/robust_analy_net.yaml deleted file mode 100644 index edbd85700..000000000 --- a/params/repo/robust_analy_net.yaml +++ /dev/null @@ -1,363 +0,0 @@ -param_list: - - id: collectri_0_scgen_pearson - perturbation_data: resources/grn-benchmark/perturbation_data.h5ad - reg_type: ridge - method_id: 0-collectri - layer: scgen_pearson - subsample: -2 - max_workers: 10 - consensus: resources/prior/consensus-num-regulators.json - prediction: resources/grn_models/collectri.csv - tf_all: resources/prior/tf_all.csv - degree: 0 - noise_type: net - - id: celloracle_0_scgen_pearson - perturbation_data: resources/grn-benchmark/perturbation_data.h5ad - reg_type: ridge - method_id: 0-celloracle - layer: scgen_pearson - subsample: -2 - max_workers: 10 - consensus: resources/prior/consensus-num-regulators.json - prediction: resources/grn_models/celloracle.csv - tf_all: resources/prior/tf_all.csv - degree: 0 - noise_type: net - - id: scenicplus_0_scgen_pearson - perturbation_data: resources/grn-benchmark/perturbation_data.h5ad - reg_type: ridge - method_id: 0-scenicplus - layer: scgen_pearson - subsample: -2 - max_workers: 10 - consensus: resources/prior/consensus-num-regulators.json - prediction: resources/grn_models/scenicplus.csv - tf_all: resources/prior/tf_all.csv - degree: 0 - noise_type: net - - id: figr_0_scgen_pearson - perturbation_data: resources/grn-benchmark/perturbation_data.h5ad - reg_type: ridge - method_id: 0-figr - layer: scgen_pearson - subsample: -2 - max_workers: 10 - consensus: resources/prior/consensus-num-regulators.json - prediction: resources/grn_models/figr.csv - tf_all: resources/prior/tf_all.csv - degree: 0 - noise_type: net - - id: granie_0_scgen_pearson - perturbation_data: resources/grn-benchmark/perturbation_data.h5ad - reg_type: ridge - method_id: 0-granie - layer: scgen_pearson - subsample: -2 - max_workers: 10 - consensus: resources/prior/consensus-num-regulators.json - prediction: resources/grn_models/granie.csv - tf_all: resources/prior/tf_all.csv - degree: 0 - noise_type: net - - id: scglue_0_scgen_pearson - perturbation_data: resources/grn-benchmark/perturbation_data.h5ad - reg_type: ridge - method_id: 0-scglue - layer: scgen_pearson - subsample: -2 - max_workers: 10 - consensus: resources/prior/consensus-num-regulators.json - prediction: resources/grn_models/scglue.csv - tf_all: resources/prior/tf_all.csv - degree: 0 - noise_type: net - - id: collectri_10_scgen_pearson - perturbation_data: resources/grn-benchmark/perturbation_data.h5ad - reg_type: ridge - method_id: 10-collectri - layer: scgen_pearson - subsample: -2 - max_workers: 10 - consensus: resources/prior/consensus-num-regulators.json - prediction: resources/grn_models/collectri.csv - tf_all: resources/prior/tf_all.csv - degree: 10 - noise_type: net - - id: celloracle_10_scgen_pearson - perturbation_data: resources/grn-benchmark/perturbation_data.h5ad - reg_type: ridge - method_id: 10-celloracle - layer: scgen_pearson - subsample: -2 - max_workers: 10 - consensus: resources/prior/consensus-num-regulators.json - prediction: resources/grn_models/celloracle.csv - tf_all: resources/prior/tf_all.csv - degree: 10 - noise_type: net - - id: scenicplus_10_scgen_pearson - perturbation_data: resources/grn-benchmark/perturbation_data.h5ad - reg_type: ridge - method_id: 10-scenicplus - layer: scgen_pearson - subsample: -2 - max_workers: 10 - consensus: resources/prior/consensus-num-regulators.json - prediction: resources/grn_models/scenicplus.csv - tf_all: resources/prior/tf_all.csv - degree: 10 - noise_type: net - - id: figr_10_scgen_pearson - perturbation_data: resources/grn-benchmark/perturbation_data.h5ad - reg_type: ridge - method_id: 10-figr - layer: scgen_pearson - subsample: -2 - max_workers: 10 - consensus: resources/prior/consensus-num-regulators.json - prediction: resources/grn_models/figr.csv - tf_all: resources/prior/tf_all.csv - degree: 10 - noise_type: net - - id: granie_10_scgen_pearson - perturbation_data: resources/grn-benchmark/perturbation_data.h5ad - reg_type: ridge - method_id: 10-granie - layer: scgen_pearson - subsample: -2 - max_workers: 10 - consensus: resources/prior/consensus-num-regulators.json - prediction: resources/grn_models/granie.csv - tf_all: resources/prior/tf_all.csv - degree: 10 - noise_type: net - - id: scglue_10_scgen_pearson - perturbation_data: resources/grn-benchmark/perturbation_data.h5ad - reg_type: ridge - method_id: 10-scglue - layer: scgen_pearson - subsample: -2 - max_workers: 10 - consensus: resources/prior/consensus-num-regulators.json - prediction: resources/grn_models/scglue.csv - tf_all: resources/prior/tf_all.csv - degree: 10 - noise_type: net - - id: collectri_20_scgen_pearson - perturbation_data: resources/grn-benchmark/perturbation_data.h5ad - reg_type: ridge - method_id: 20-collectri - layer: scgen_pearson - subsample: -2 - max_workers: 10 - consensus: resources/prior/consensus-num-regulators.json - prediction: resources/grn_models/collectri.csv - tf_all: resources/prior/tf_all.csv - degree: 20 - noise_type: net - - id: celloracle_20_scgen_pearson - perturbation_data: resources/grn-benchmark/perturbation_data.h5ad - reg_type: ridge - method_id: 20-celloracle - layer: scgen_pearson - subsample: -2 - max_workers: 10 - consensus: resources/prior/consensus-num-regulators.json - prediction: resources/grn_models/celloracle.csv - tf_all: resources/prior/tf_all.csv - degree: 20 - noise_type: net - - id: scenicplus_20_scgen_pearson - perturbation_data: resources/grn-benchmark/perturbation_data.h5ad - reg_type: ridge - method_id: 20-scenicplus - layer: scgen_pearson - subsample: -2 - max_workers: 10 - consensus: resources/prior/consensus-num-regulators.json - prediction: resources/grn_models/scenicplus.csv - tf_all: resources/prior/tf_all.csv - degree: 20 - noise_type: net - - id: figr_20_scgen_pearson - perturbation_data: resources/grn-benchmark/perturbation_data.h5ad - reg_type: ridge - method_id: 20-figr - layer: scgen_pearson - subsample: -2 - max_workers: 10 - consensus: resources/prior/consensus-num-regulators.json - prediction: resources/grn_models/figr.csv - tf_all: resources/prior/tf_all.csv - degree: 20 - noise_type: net - - id: granie_20_scgen_pearson - perturbation_data: resources/grn-benchmark/perturbation_data.h5ad - reg_type: ridge - method_id: 20-granie - layer: scgen_pearson - subsample: -2 - max_workers: 10 - consensus: resources/prior/consensus-num-regulators.json - prediction: resources/grn_models/granie.csv - tf_all: resources/prior/tf_all.csv - degree: 20 - noise_type: net - - id: scglue_20_scgen_pearson - perturbation_data: resources/grn-benchmark/perturbation_data.h5ad - reg_type: ridge - method_id: 20-scglue - layer: scgen_pearson - subsample: -2 - max_workers: 10 - consensus: resources/prior/consensus-num-regulators.json - prediction: resources/grn_models/scglue.csv - tf_all: resources/prior/tf_all.csv - degree: 20 - noise_type: net - - id: collectri_50_scgen_pearson - perturbation_data: resources/grn-benchmark/perturbation_data.h5ad - reg_type: ridge - method_id: 50-collectri - layer: scgen_pearson - subsample: -2 - max_workers: 10 - consensus: resources/prior/consensus-num-regulators.json - prediction: resources/grn_models/collectri.csv - tf_all: resources/prior/tf_all.csv - degree: 50 - noise_type: net - - id: celloracle_50_scgen_pearson - perturbation_data: resources/grn-benchmark/perturbation_data.h5ad - reg_type: ridge - method_id: 50-celloracle - layer: scgen_pearson - subsample: -2 - max_workers: 10 - consensus: resources/prior/consensus-num-regulators.json - prediction: resources/grn_models/celloracle.csv - tf_all: resources/prior/tf_all.csv - degree: 50 - noise_type: net - - id: scenicplus_50_scgen_pearson - perturbation_data: resources/grn-benchmark/perturbation_data.h5ad - reg_type: ridge - method_id: 50-scenicplus - layer: scgen_pearson - subsample: -2 - max_workers: 10 - consensus: resources/prior/consensus-num-regulators.json - prediction: resources/grn_models/scenicplus.csv - tf_all: resources/prior/tf_all.csv - degree: 50 - noise_type: net - - id: figr_50_scgen_pearson - perturbation_data: resources/grn-benchmark/perturbation_data.h5ad - reg_type: ridge - method_id: 50-figr - layer: scgen_pearson - subsample: -2 - max_workers: 10 - consensus: resources/prior/consensus-num-regulators.json - prediction: resources/grn_models/figr.csv - tf_all: resources/prior/tf_all.csv - degree: 50 - noise_type: net - - id: granie_50_scgen_pearson - perturbation_data: resources/grn-benchmark/perturbation_data.h5ad - reg_type: ridge - method_id: 50-granie - layer: scgen_pearson - subsample: -2 - max_workers: 10 - consensus: resources/prior/consensus-num-regulators.json - prediction: resources/grn_models/granie.csv - tf_all: resources/prior/tf_all.csv - degree: 50 - noise_type: net - - id: scglue_50_scgen_pearson - perturbation_data: resources/grn-benchmark/perturbation_data.h5ad - reg_type: ridge - method_id: 50-scglue - layer: scgen_pearson - subsample: -2 - max_workers: 10 - consensus: resources/prior/consensus-num-regulators.json - prediction: resources/grn_models/scglue.csv - tf_all: resources/prior/tf_all.csv - degree: 50 - noise_type: net - - id: collectri_100_scgen_pearson - perturbation_data: resources/grn-benchmark/perturbation_data.h5ad - reg_type: ridge - method_id: 100-collectri - layer: scgen_pearson - subsample: -2 - max_workers: 10 - consensus: resources/prior/consensus-num-regulators.json - prediction: resources/grn_models/collectri.csv - tf_all: resources/prior/tf_all.csv - degree: 100 - noise_type: net - - id: celloracle_100_scgen_pearson - perturbation_data: resources/grn-benchmark/perturbation_data.h5ad - reg_type: ridge - method_id: 100-celloracle - layer: scgen_pearson - subsample: -2 - max_workers: 10 - consensus: resources/prior/consensus-num-regulators.json - prediction: resources/grn_models/celloracle.csv - tf_all: resources/prior/tf_all.csv - degree: 100 - noise_type: net - - id: scenicplus_100_scgen_pearson - perturbation_data: resources/grn-benchmark/perturbation_data.h5ad - reg_type: ridge - method_id: 100-scenicplus - layer: scgen_pearson - subsample: -2 - max_workers: 10 - consensus: resources/prior/consensus-num-regulators.json - prediction: resources/grn_models/scenicplus.csv - tf_all: resources/prior/tf_all.csv - degree: 100 - noise_type: net - - id: figr_100_scgen_pearson - perturbation_data: resources/grn-benchmark/perturbation_data.h5ad - reg_type: ridge - method_id: 100-figr - layer: scgen_pearson - subsample: -2 - max_workers: 10 - consensus: resources/prior/consensus-num-regulators.json - prediction: resources/grn_models/figr.csv - tf_all: resources/prior/tf_all.csv - degree: 100 - noise_type: net - - id: granie_100_scgen_pearson - perturbation_data: resources/grn-benchmark/perturbation_data.h5ad - reg_type: ridge - method_id: 100-granie - layer: scgen_pearson - subsample: -2 - max_workers: 10 - consensus: resources/prior/consensus-num-regulators.json - prediction: resources/grn_models/granie.csv - tf_all: resources/prior/tf_all.csv - degree: 100 - noise_type: net - - id: scglue_100_scgen_pearson - perturbation_data: resources/grn-benchmark/perturbation_data.h5ad - reg_type: ridge - method_id: 100-scglue - layer: scgen_pearson - subsample: -2 - max_workers: 10 - consensus: resources/prior/consensus-num-regulators.json - prediction: resources/grn_models/scglue.csv - tf_all: resources/prior/tf_all.csv - degree: 100 - noise_type: net -output_state: "state.yaml" -publish_dir: "resources/results/robust_analy_net" diff --git a/params/repo/robust_analy_pc_vs_nc.yaml b/params/repo/robust_analy_pc_vs_nc.yaml deleted file mode 100644 index eab7f1cff..000000000 --- a/params/repo/robust_analy_pc_vs_nc.yaml +++ /dev/null @@ -1,201 +0,0 @@ -param_list: - - id: collectri_-2 - perturbation_data: resources/grn-benchmark/perturbation_data.h5ad - layer: pearson - reg_type: ridge - method_id: -2-collectri - subsample: -2 - max_workers: 10 - consensus: resources/prior/consensus-num-regulators.json - prediction: resources/grn_models/collectri.csv - degree: 0 - - - id: celloracle_-2 - perturbation_data: resources/grn-benchmark/perturbation_data.h5ad - layer: pearson - reg_type: ridge - method_id: -2-celloracle - subsample: -2 - max_workers: 10 - consensus: resources/prior/consensus-num-regulators.json - prediction: resources/grn_models/celloracle.csv - degree: 0 - - - id: scenicplus_-2 - perturbation_data: resources/grn-benchmark/perturbation_data.h5ad - layer: pearson - reg_type: ridge - method_id: -2-scenicplus - subsample: -2 - max_workers: 10 - consensus: resources/prior/consensus-num-regulators.json - prediction: resources/grn_models/scenicplus.csv - degree: 0 - - - id: figr_-2 - perturbation_data: resources/grn-benchmark/perturbation_data.h5ad - layer: pearson - reg_type: ridge - method_id: -2-figr - subsample: -2 - max_workers: 10 - consensus: resources/prior/consensus-num-regulators.json - prediction: resources/grn_models/figr.csv - degree: 0 - - - id: granie_-2 - perturbation_data: resources/grn-benchmark/perturbation_data.h5ad - layer: pearson - reg_type: ridge - method_id: -2-granie - subsample: -2 - max_workers: 10 - consensus: resources/prior/consensus-num-regulators.json - prediction: resources/grn_models/granie.csv - degree: 0 - - - id: scglue_-2 - perturbation_data: resources/grn-benchmark/perturbation_data.h5ad - layer: pearson - reg_type: ridge - method_id: -2-scglue - subsample: -2 - max_workers: 10 - consensus: resources/prior/consensus-num-regulators.json - prediction: resources/grn_models/scglue.csv - degree: 0 - - - id: collectri_-3 - perturbation_data: resources/grn-benchmark/perturbation_data.h5ad - layer: pearson - reg_type: ridge - method_id: -3-collectri - subsample: -3 - max_workers: 10 - consensus: resources/prior/consensus-num-regulators.json - prediction: resources/grn_models/collectri.csv - degree: 0 - - - id: celloracle_-3 - perturbation_data: resources/grn-benchmark/perturbation_data.h5ad - layer: pearson - reg_type: ridge - method_id: -3-celloracle - subsample: -3 - max_workers: 10 - consensus: resources/prior/consensus-num-regulators.json - prediction: resources/grn_models/celloracle.csv - degree: 0 - - - id: scenicplus_-3 - perturbation_data: resources/grn-benchmark/perturbation_data.h5ad - layer: pearson - reg_type: ridge - method_id: -3-scenicplus - subsample: -3 - max_workers: 10 - consensus: resources/prior/consensus-num-regulators.json - prediction: resources/grn_models/scenicplus.csv - degree: 0 - - - id: figr_-3 - perturbation_data: resources/grn-benchmark/perturbation_data.h5ad - layer: pearson - reg_type: ridge - method_id: -3-figr - subsample: -3 - max_workers: 10 - consensus: resources/prior/consensus-num-regulators.json - prediction: resources/grn_models/figr.csv - degree: 0 - - - id: granie_-3 - perturbation_data: resources/grn-benchmark/perturbation_data.h5ad - layer: pearson - reg_type: ridge - method_id: -3-granie - subsample: -3 - max_workers: 10 - consensus: resources/prior/consensus-num-regulators.json - prediction: resources/grn_models/granie.csv - degree: 0 - - - id: scglue_-3 - perturbation_data: resources/grn-benchmark/perturbation_data.h5ad - layer: pearson - reg_type: ridge - method_id: -3-scglue - subsample: -3 - max_workers: 10 - consensus: resources/prior/consensus-num-regulators.json - prediction: resources/grn_models/scglue.csv - degree: 0 - - - id: collectri_-4 - perturbation_data: resources/grn-benchmark/perturbation_data.h5ad - layer: pearson - reg_type: ridge - method_id: -4-collectri - subsample: -4 - max_workers: 10 - consensus: resources/prior/consensus-num-regulators.json - prediction: resources/grn_models/collectri.csv - degree: 0 - - - id: celloracle_-4 - perturbation_data: resources/grn-benchmark/perturbation_data.h5ad - layer: pearson - reg_type: ridge - method_id: -4-celloracle - subsample: -4 - max_workers: 10 - consensus: resources/prior/consensus-num-regulators.json - prediction: resources/grn_models/celloracle.csv - degree: 0 - - - id: scenicplus_-4 - perturbation_data: resources/grn-benchmark/perturbation_data.h5ad - layer: pearson - reg_type: ridge - method_id: -4-scenicplus - subsample: -4 - max_workers: 10 - consensus: resources/prior/consensus-num-regulators.json - prediction: resources/grn_models/scenicplus.csv - degree: 0 - - - id: figr_-4 - perturbation_data: resources/grn-benchmark/perturbation_data.h5ad - layer: pearson - reg_type: ridge - method_id: -4-figr - subsample: -4 - max_workers: 10 - consensus: resources/prior/consensus-num-regulators.json - prediction: resources/grn_models/figr.csv - degree: 0 - - - id: granie_-4 - perturbation_data: resources/grn-benchmark/perturbation_data.h5ad - layer: pearson - reg_type: ridge - method_id: -4-granie - subsample: -4 - max_workers: 10 - consensus: resources/prior/consensus-num-regulators.json - prediction: resources/grn_models/granie.csv - degree: 0 - - - id: scglue_-4 - perturbation_data: resources/grn-benchmark/perturbation_data.h5ad - layer: pearson - reg_type: ridge - method_id: -4-scglue - subsample: -4 - max_workers: 10 - consensus: resources/prior/consensus-num-regulators.json - prediction: resources/grn_models/scglue.csv - degree: 0 - -output_state: "state.yaml" -publish_dir: "output/robust_analy_pc_vs_nc" diff --git a/params/repo/robust_analy_reg2_net.yaml b/params/repo/robust_analy_reg2_net.yaml deleted file mode 100644 index eb39fa62b..000000000 --- a/params/repo/robust_analy_reg2_net.yaml +++ /dev/null @@ -1,363 +0,0 @@ -param_list: - - id: collectri_0_scgen_pearson - perturbation_data: s3://openproblems-data/resources/grn/grn-benchmark/perturbation_data.h5ad - reg_type: ridge - method_id: 0-collectri - layer: scgen_pearson - subsample: -2 - max_workers: 10 - consensus: s3://openproblems-data/resources/grn/prior/consensus-num-regulators.json - prediction: s3://openproblems-data/resources/grn/grn_models/collectri.csv - tf_all: s3://openproblems-data/resources/grn/prior/tf_all.csv - degree: 0 - noise_type: net - - id: celloracle_0_scgen_pearson - perturbation_data: s3://openproblems-data/resources/grn/grn-benchmark/perturbation_data.h5ad - reg_type: ridge - method_id: 0-celloracle - layer: scgen_pearson - subsample: -2 - max_workers: 10 - consensus: s3://openproblems-data/resources/grn/prior/consensus-num-regulators.json - prediction: s3://openproblems-data/resources/grn/grn_models/celloracle.csv - tf_all: s3://openproblems-data/resources/grn/prior/tf_all.csv - degree: 0 - noise_type: net - - id: scenicplus_0_scgen_pearson - perturbation_data: s3://openproblems-data/resources/grn/grn-benchmark/perturbation_data.h5ad - reg_type: ridge - method_id: 0-scenicplus - layer: scgen_pearson - subsample: -2 - max_workers: 10 - consensus: s3://openproblems-data/resources/grn/prior/consensus-num-regulators.json - prediction: s3://openproblems-data/resources/grn/grn_models/scenicplus.csv - tf_all: s3://openproblems-data/resources/grn/prior/tf_all.csv - degree: 0 - noise_type: net - - id: figr_0_scgen_pearson - perturbation_data: s3://openproblems-data/resources/grn/grn-benchmark/perturbation_data.h5ad - reg_type: ridge - method_id: 0-figr - layer: scgen_pearson - subsample: -2 - max_workers: 10 - consensus: s3://openproblems-data/resources/grn/prior/consensus-num-regulators.json - prediction: s3://openproblems-data/resources/grn/grn_models/figr.csv - tf_all: s3://openproblems-data/resources/grn/prior/tf_all.csv - degree: 0 - noise_type: net - - id: granie_0_scgen_pearson - perturbation_data: s3://openproblems-data/resources/grn/grn-benchmark/perturbation_data.h5ad - reg_type: ridge - method_id: 0-granie - layer: scgen_pearson - subsample: -2 - max_workers: 10 - consensus: s3://openproblems-data/resources/grn/prior/consensus-num-regulators.json - prediction: s3://openproblems-data/resources/grn/grn_models/granie.csv - tf_all: s3://openproblems-data/resources/grn/prior/tf_all.csv - degree: 0 - noise_type: net - - id: scglue_0_scgen_pearson - perturbation_data: s3://openproblems-data/resources/grn/grn-benchmark/perturbation_data.h5ad - reg_type: ridge - method_id: 0-scglue - layer: scgen_pearson - subsample: -2 - max_workers: 10 - consensus: s3://openproblems-data/resources/grn/prior/consensus-num-regulators.json - prediction: s3://openproblems-data/resources/grn/grn_models/scglue.csv - tf_all: s3://openproblems-data/resources/grn/prior/tf_all.csv - degree: 0 - noise_type: net - - id: collectri_10_scgen_pearson - perturbation_data: s3://openproblems-data/resources/grn/grn-benchmark/perturbation_data.h5ad - reg_type: ridge - method_id: 10-collectri - layer: scgen_pearson - subsample: -2 - max_workers: 10 - consensus: s3://openproblems-data/resources/grn/prior/consensus-num-regulators.json - prediction: s3://openproblems-data/resources/grn/grn_models/collectri.csv - tf_all: s3://openproblems-data/resources/grn/prior/tf_all.csv - degree: 10 - noise_type: net - - id: celloracle_10_scgen_pearson - perturbation_data: s3://openproblems-data/resources/grn/grn-benchmark/perturbation_data.h5ad - reg_type: ridge - method_id: 10-celloracle - layer: scgen_pearson - subsample: -2 - max_workers: 10 - consensus: s3://openproblems-data/resources/grn/prior/consensus-num-regulators.json - prediction: s3://openproblems-data/resources/grn/grn_models/celloracle.csv - tf_all: s3://openproblems-data/resources/grn/prior/tf_all.csv - degree: 10 - noise_type: net - - id: scenicplus_10_scgen_pearson - perturbation_data: s3://openproblems-data/resources/grn/grn-benchmark/perturbation_data.h5ad - reg_type: ridge - method_id: 10-scenicplus - layer: scgen_pearson - subsample: -2 - max_workers: 10 - consensus: s3://openproblems-data/resources/grn/prior/consensus-num-regulators.json - prediction: s3://openproblems-data/resources/grn/grn_models/scenicplus.csv - tf_all: s3://openproblems-data/resources/grn/prior/tf_all.csv - degree: 10 - noise_type: net - - id: figr_10_scgen_pearson - perturbation_data: s3://openproblems-data/resources/grn/grn-benchmark/perturbation_data.h5ad - reg_type: ridge - method_id: 10-figr - layer: scgen_pearson - subsample: -2 - max_workers: 10 - consensus: s3://openproblems-data/resources/grn/prior/consensus-num-regulators.json - prediction: s3://openproblems-data/resources/grn/grn_models/figr.csv - tf_all: s3://openproblems-data/resources/grn/prior/tf_all.csv - degree: 10 - noise_type: net - - id: granie_10_scgen_pearson - perturbation_data: s3://openproblems-data/resources/grn/grn-benchmark/perturbation_data.h5ad - reg_type: ridge - method_id: 10-granie - layer: scgen_pearson - subsample: -2 - max_workers: 10 - consensus: s3://openproblems-data/resources/grn/prior/consensus-num-regulators.json - prediction: s3://openproblems-data/resources/grn/grn_models/granie.csv - tf_all: s3://openproblems-data/resources/grn/prior/tf_all.csv - degree: 10 - noise_type: net - - id: scglue_10_scgen_pearson - perturbation_data: s3://openproblems-data/resources/grn/grn-benchmark/perturbation_data.h5ad - reg_type: ridge - method_id: 10-scglue - layer: scgen_pearson - subsample: -2 - max_workers: 10 - consensus: s3://openproblems-data/resources/grn/prior/consensus-num-regulators.json - prediction: s3://openproblems-data/resources/grn/grn_models/scglue.csv - tf_all: s3://openproblems-data/resources/grn/prior/tf_all.csv - degree: 10 - noise_type: net - - id: collectri_20_scgen_pearson - perturbation_data: s3://openproblems-data/resources/grn/grn-benchmark/perturbation_data.h5ad - reg_type: ridge - method_id: 20-collectri - layer: scgen_pearson - subsample: -2 - max_workers: 10 - consensus: s3://openproblems-data/resources/grn/prior/consensus-num-regulators.json - prediction: s3://openproblems-data/resources/grn/grn_models/collectri.csv - tf_all: s3://openproblems-data/resources/grn/prior/tf_all.csv - degree: 20 - noise_type: net - - id: celloracle_20_scgen_pearson - perturbation_data: s3://openproblems-data/resources/grn/grn-benchmark/perturbation_data.h5ad - reg_type: ridge - method_id: 20-celloracle - layer: scgen_pearson - subsample: -2 - max_workers: 10 - consensus: s3://openproblems-data/resources/grn/prior/consensus-num-regulators.json - prediction: s3://openproblems-data/resources/grn/grn_models/celloracle.csv - tf_all: s3://openproblems-data/resources/grn/prior/tf_all.csv - degree: 20 - noise_type: net - - id: scenicplus_20_scgen_pearson - perturbation_data: s3://openproblems-data/resources/grn/grn-benchmark/perturbation_data.h5ad - reg_type: ridge - method_id: 20-scenicplus - layer: scgen_pearson - subsample: -2 - max_workers: 10 - consensus: s3://openproblems-data/resources/grn/prior/consensus-num-regulators.json - prediction: s3://openproblems-data/resources/grn/grn_models/scenicplus.csv - tf_all: s3://openproblems-data/resources/grn/prior/tf_all.csv - degree: 20 - noise_type: net - - id: figr_20_scgen_pearson - perturbation_data: s3://openproblems-data/resources/grn/grn-benchmark/perturbation_data.h5ad - reg_type: ridge - method_id: 20-figr - layer: scgen_pearson - subsample: -2 - max_workers: 10 - consensus: s3://openproblems-data/resources/grn/prior/consensus-num-regulators.json - prediction: s3://openproblems-data/resources/grn/grn_models/figr.csv - tf_all: s3://openproblems-data/resources/grn/prior/tf_all.csv - degree: 20 - noise_type: net - - id: granie_20_scgen_pearson - perturbation_data: s3://openproblems-data/resources/grn/grn-benchmark/perturbation_data.h5ad - reg_type: ridge - method_id: 20-granie - layer: scgen_pearson - subsample: -2 - max_workers: 10 - consensus: s3://openproblems-data/resources/grn/prior/consensus-num-regulators.json - prediction: s3://openproblems-data/resources/grn/grn_models/granie.csv - tf_all: s3://openproblems-data/resources/grn/prior/tf_all.csv - degree: 20 - noise_type: net - - id: scglue_20_scgen_pearson - perturbation_data: s3://openproblems-data/resources/grn/grn-benchmark/perturbation_data.h5ad - reg_type: ridge - method_id: 20-scglue - layer: scgen_pearson - subsample: -2 - max_workers: 10 - consensus: s3://openproblems-data/resources/grn/prior/consensus-num-regulators.json - prediction: s3://openproblems-data/resources/grn/grn_models/scglue.csv - tf_all: s3://openproblems-data/resources/grn/prior/tf_all.csv - degree: 20 - noise_type: net - - id: collectri_50_scgen_pearson - perturbation_data: s3://openproblems-data/resources/grn/grn-benchmark/perturbation_data.h5ad - reg_type: ridge - method_id: 50-collectri - layer: scgen_pearson - subsample: -2 - max_workers: 10 - consensus: s3://openproblems-data/resources/grn/prior/consensus-num-regulators.json - prediction: s3://openproblems-data/resources/grn/grn_models/collectri.csv - tf_all: s3://openproblems-data/resources/grn/prior/tf_all.csv - degree: 50 - noise_type: net - - id: celloracle_50_scgen_pearson - perturbation_data: s3://openproblems-data/resources/grn/grn-benchmark/perturbation_data.h5ad - reg_type: ridge - method_id: 50-celloracle - layer: scgen_pearson - subsample: -2 - max_workers: 10 - consensus: s3://openproblems-data/resources/grn/prior/consensus-num-regulators.json - prediction: s3://openproblems-data/resources/grn/grn_models/celloracle.csv - tf_all: s3://openproblems-data/resources/grn/prior/tf_all.csv - degree: 50 - noise_type: net - - id: scenicplus_50_scgen_pearson - perturbation_data: s3://openproblems-data/resources/grn/grn-benchmark/perturbation_data.h5ad - reg_type: ridge - method_id: 50-scenicplus - layer: scgen_pearson - subsample: -2 - max_workers: 10 - consensus: s3://openproblems-data/resources/grn/prior/consensus-num-regulators.json - prediction: s3://openproblems-data/resources/grn/grn_models/scenicplus.csv - tf_all: s3://openproblems-data/resources/grn/prior/tf_all.csv - degree: 50 - noise_type: net - - id: figr_50_scgen_pearson - perturbation_data: s3://openproblems-data/resources/grn/grn-benchmark/perturbation_data.h5ad - reg_type: ridge - method_id: 50-figr - layer: scgen_pearson - subsample: -2 - max_workers: 10 - consensus: s3://openproblems-data/resources/grn/prior/consensus-num-regulators.json - prediction: s3://openproblems-data/resources/grn/grn_models/figr.csv - tf_all: s3://openproblems-data/resources/grn/prior/tf_all.csv - degree: 50 - noise_type: net - - id: granie_50_scgen_pearson - perturbation_data: s3://openproblems-data/resources/grn/grn-benchmark/perturbation_data.h5ad - reg_type: ridge - method_id: 50-granie - layer: scgen_pearson - subsample: -2 - max_workers: 10 - consensus: s3://openproblems-data/resources/grn/prior/consensus-num-regulators.json - prediction: s3://openproblems-data/resources/grn/grn_models/granie.csv - tf_all: s3://openproblems-data/resources/grn/prior/tf_all.csv - degree: 50 - noise_type: net - - id: scglue_50_scgen_pearson - perturbation_data: s3://openproblems-data/resources/grn/grn-benchmark/perturbation_data.h5ad - reg_type: ridge - method_id: 50-scglue - layer: scgen_pearson - subsample: -2 - max_workers: 10 - consensus: s3://openproblems-data/resources/grn/prior/consensus-num-regulators.json - prediction: s3://openproblems-data/resources/grn/grn_models/scglue.csv - tf_all: s3://openproblems-data/resources/grn/prior/tf_all.csv - degree: 50 - noise_type: net - - id: collectri_100_scgen_pearson - perturbation_data: s3://openproblems-data/resources/grn/grn-benchmark/perturbation_data.h5ad - reg_type: ridge - method_id: 100-collectri - layer: scgen_pearson - subsample: -2 - max_workers: 10 - consensus: s3://openproblems-data/resources/grn/prior/consensus-num-regulators.json - prediction: s3://openproblems-data/resources/grn/grn_models/collectri.csv - tf_all: s3://openproblems-data/resources/grn/prior/tf_all.csv - degree: 100 - noise_type: net - - id: celloracle_100_scgen_pearson - perturbation_data: s3://openproblems-data/resources/grn/grn-benchmark/perturbation_data.h5ad - reg_type: ridge - method_id: 100-celloracle - layer: scgen_pearson - subsample: -2 - max_workers: 10 - consensus: s3://openproblems-data/resources/grn/prior/consensus-num-regulators.json - prediction: s3://openproblems-data/resources/grn/grn_models/celloracle.csv - tf_all: s3://openproblems-data/resources/grn/prior/tf_all.csv - degree: 100 - noise_type: net - - id: scenicplus_100_scgen_pearson - perturbation_data: s3://openproblems-data/resources/grn/grn-benchmark/perturbation_data.h5ad - reg_type: ridge - method_id: 100-scenicplus - layer: scgen_pearson - subsample: -2 - max_workers: 10 - consensus: s3://openproblems-data/resources/grn/prior/consensus-num-regulators.json - prediction: s3://openproblems-data/resources/grn/grn_models/scenicplus.csv - tf_all: s3://openproblems-data/resources/grn/prior/tf_all.csv - degree: 100 - noise_type: net - - id: figr_100_scgen_pearson - perturbation_data: s3://openproblems-data/resources/grn/grn-benchmark/perturbation_data.h5ad - reg_type: ridge - method_id: 100-figr - layer: scgen_pearson - subsample: -2 - max_workers: 10 - consensus: s3://openproblems-data/resources/grn/prior/consensus-num-regulators.json - prediction: s3://openproblems-data/resources/grn/grn_models/figr.csv - tf_all: s3://openproblems-data/resources/grn/prior/tf_all.csv - degree: 100 - noise_type: net - - id: granie_100_scgen_pearson - perturbation_data: s3://openproblems-data/resources/grn/grn-benchmark/perturbation_data.h5ad - reg_type: ridge - method_id: 100-granie - layer: scgen_pearson - subsample: -2 - max_workers: 10 - consensus: s3://openproblems-data/resources/grn/prior/consensus-num-regulators.json - prediction: s3://openproblems-data/resources/grn/grn_models/granie.csv - tf_all: s3://openproblems-data/resources/grn/prior/tf_all.csv - degree: 100 - noise_type: net - - id: scglue_100_scgen_pearson - perturbation_data: s3://openproblems-data/resources/grn/grn-benchmark/perturbation_data.h5ad - reg_type: ridge - method_id: 100-scglue - layer: scgen_pearson - subsample: -2 - max_workers: 10 - consensus: s3://openproblems-data/resources/grn/prior/consensus-num-regulators.json - prediction: s3://openproblems-data/resources/grn/grn_models/scglue.csv - tf_all: s3://openproblems-data/resources/grn/prior/tf_all.csv - degree: 100 - noise_type: net -output_state: "state.yaml" -publish_dir: "s3://openproblems-data/resources/grn/results/robust_analy_reg2_net" diff --git a/params/repo/robust_analy_reg2_pc_vs_nc.yaml b/params/repo/robust_analy_reg2_pc_vs_nc.yaml deleted file mode 100644 index 9c568b0cb..000000000 --- a/params/repo/robust_analy_reg2_pc_vs_nc.yaml +++ /dev/null @@ -1,201 +0,0 @@ -param_list: - - id: collectri_-2 - perturbation_data: s3://openproblems-data/resources/grn/grn-benchmark/perturbation_data.h5ad - layer: scgen_pearson - reg_type: ridge - method_id: -2-collectri - subsample: -2 - max_workers: 10 - consensus: s3://openproblems-data/resources/grn/prior/consensus-num-regulators.json - prediction: s3://openproblems-data/resources/grn/grn_models/collectri.csv - degree: 0 - - - id: celloracle_-2 - perturbation_data: s3://openproblems-data/resources/grn/grn-benchmark/perturbation_data.h5ad - layer: scgen_pearson - reg_type: ridge - method_id: -2-celloracle - subsample: -2 - max_workers: 10 - consensus: s3://openproblems-data/resources/grn/prior/consensus-num-regulators.json - prediction: s3://openproblems-data/resources/grn/grn_models/celloracle.csv - degree: 0 - - - id: scenicplus_-2 - perturbation_data: s3://openproblems-data/resources/grn/grn-benchmark/perturbation_data.h5ad - layer: scgen_pearson - reg_type: ridge - method_id: -2-scenicplus - subsample: -2 - max_workers: 10 - consensus: s3://openproblems-data/resources/grn/prior/consensus-num-regulators.json - prediction: s3://openproblems-data/resources/grn/grn_models/scenicplus.csv - degree: 0 - - - id: figr_-2 - perturbation_data: s3://openproblems-data/resources/grn/grn-benchmark/perturbation_data.h5ad - layer: scgen_pearson - reg_type: ridge - method_id: -2-figr - subsample: -2 - max_workers: 10 - consensus: s3://openproblems-data/resources/grn/prior/consensus-num-regulators.json - prediction: s3://openproblems-data/resources/grn/grn_models/figr.csv - degree: 0 - - - id: granie_-2 - perturbation_data: s3://openproblems-data/resources/grn/grn-benchmark/perturbation_data.h5ad - layer: scgen_pearson - reg_type: ridge - method_id: -2-granie - subsample: -2 - max_workers: 10 - consensus: s3://openproblems-data/resources/grn/prior/consensus-num-regulators.json - prediction: s3://openproblems-data/resources/grn/grn_models/granie.csv - degree: 0 - - - id: scglue_-2 - perturbation_data: s3://openproblems-data/resources/grn/grn-benchmark/perturbation_data.h5ad - layer: scgen_pearson - reg_type: ridge - method_id: -2-scglue - subsample: -2 - max_workers: 10 - consensus: s3://openproblems-data/resources/grn/prior/consensus-num-regulators.json - prediction: s3://openproblems-data/resources/grn/grn_models/scglue.csv - degree: 0 - - - id: collectri_-3 - perturbation_data: s3://openproblems-data/resources/grn/grn-benchmark/perturbation_data.h5ad - layer: scgen_pearson - reg_type: ridge - method_id: -3-collectri - subsample: -3 - max_workers: 10 - consensus: s3://openproblems-data/resources/grn/prior/consensus-num-regulators.json - prediction: s3://openproblems-data/resources/grn/grn_models/collectri.csv - degree: 0 - - - id: celloracle_-3 - perturbation_data: s3://openproblems-data/resources/grn/grn-benchmark/perturbation_data.h5ad - layer: scgen_pearson - reg_type: ridge - method_id: -3-celloracle - subsample: -3 - max_workers: 10 - consensus: s3://openproblems-data/resources/grn/prior/consensus-num-regulators.json - prediction: s3://openproblems-data/resources/grn/grn_models/celloracle.csv - degree: 0 - - - id: scenicplus_-3 - perturbation_data: s3://openproblems-data/resources/grn/grn-benchmark/perturbation_data.h5ad - layer: scgen_pearson - reg_type: ridge - method_id: -3-scenicplus - subsample: -3 - max_workers: 10 - consensus: s3://openproblems-data/resources/grn/prior/consensus-num-regulators.json - prediction: s3://openproblems-data/resources/grn/grn_models/scenicplus.csv - degree: 0 - - - id: figr_-3 - perturbation_data: s3://openproblems-data/resources/grn/grn-benchmark/perturbation_data.h5ad - layer: scgen_pearson - reg_type: ridge - method_id: -3-figr - subsample: -3 - max_workers: 10 - consensus: s3://openproblems-data/resources/grn/prior/consensus-num-regulators.json - prediction: s3://openproblems-data/resources/grn/grn_models/figr.csv - degree: 0 - - - id: granie_-3 - perturbation_data: s3://openproblems-data/resources/grn/grn-benchmark/perturbation_data.h5ad - layer: scgen_pearson - reg_type: ridge - method_id: -3-granie - subsample: -3 - max_workers: 10 - consensus: s3://openproblems-data/resources/grn/prior/consensus-num-regulators.json - prediction: s3://openproblems-data/resources/grn/grn_models/granie.csv - degree: 0 - - - id: scglue_-3 - perturbation_data: s3://openproblems-data/resources/grn/grn-benchmark/perturbation_data.h5ad - layer: scgen_pearson - reg_type: ridge - method_id: -3-scglue - subsample: -3 - max_workers: 10 - consensus: s3://openproblems-data/resources/grn/prior/consensus-num-regulators.json - prediction: s3://openproblems-data/resources/grn/grn_models/scglue.csv - degree: 0 - - - id: collectri_-4 - perturbation_data: s3://openproblems-data/resources/grn/grn-benchmark/perturbation_data.h5ad - layer: scgen_pearson - reg_type: ridge - method_id: -4-collectri - subsample: -4 - max_workers: 10 - consensus: s3://openproblems-data/resources/grn/prior/consensus-num-regulators.json - prediction: s3://openproblems-data/resources/grn/grn_models/collectri.csv - degree: 0 - - - id: celloracle_-4 - perturbation_data: s3://openproblems-data/resources/grn/grn-benchmark/perturbation_data.h5ad - layer: scgen_pearson - reg_type: ridge - method_id: -4-celloracle - subsample: -4 - max_workers: 10 - consensus: s3://openproblems-data/resources/grn/prior/consensus-num-regulators.json - prediction: s3://openproblems-data/resources/grn/grn_models/celloracle.csv - degree: 0 - - - id: scenicplus_-4 - perturbation_data: s3://openproblems-data/resources/grn/grn-benchmark/perturbation_data.h5ad - layer: scgen_pearson - reg_type: ridge - method_id: -4-scenicplus - subsample: -4 - max_workers: 10 - consensus: s3://openproblems-data/resources/grn/prior/consensus-num-regulators.json - prediction: s3://openproblems-data/resources/grn/grn_models/scenicplus.csv - degree: 0 - - - id: figr_-4 - perturbation_data: s3://openproblems-data/resources/grn/grn-benchmark/perturbation_data.h5ad - layer: scgen_pearson - reg_type: ridge - method_id: -4-figr - subsample: -4 - max_workers: 10 - consensus: s3://openproblems-data/resources/grn/prior/consensus-num-regulators.json - prediction: s3://openproblems-data/resources/grn/grn_models/figr.csv - degree: 0 - - - id: granie_-4 - perturbation_data: s3://openproblems-data/resources/grn/grn-benchmark/perturbation_data.h5ad - layer: scgen_pearson - reg_type: ridge - method_id: -4-granie - subsample: -4 - max_workers: 10 - consensus: s3://openproblems-data/resources/grn/prior/consensus-num-regulators.json - prediction: s3://openproblems-data/resources/grn/grn_models/granie.csv - degree: 0 - - - id: scglue_-4 - perturbation_data: s3://openproblems-data/resources/grn/grn-benchmark/perturbation_data.h5ad - layer: scgen_pearson - reg_type: ridge - method_id: -4-scglue - subsample: -4 - max_workers: 10 - consensus: s3://openproblems-data/resources/grn/prior/consensus-num-regulators.json - prediction: s3://openproblems-data/resources/grn/grn_models/scglue.csv - degree: 0 - -output_state: "state.yaml" -publish_dir: "s3://openproblems-data/resources/grn/robust_analy_reg2_pc_vs_nc" diff --git a/params/repo/robust_analy_reg2_sign.yaml b/params/repo/robust_analy_reg2_sign.yaml deleted file mode 100644 index a0ab7b52c..000000000 --- a/params/repo/robust_analy_reg2_sign.yaml +++ /dev/null @@ -1,363 +0,0 @@ -param_list: - - id: collectri_0_scgen_pearson - perturbation_data: s3://openproblems-data/resources/grn/grn-benchmark/perturbation_data.h5ad - reg_type: ridge - method_id: 0-collectri - layer: scgen_pearson - subsample: -2 - max_workers: 10 - consensus: s3://openproblems-data/resources/grn/prior/consensus-num-regulators.json - prediction: s3://openproblems-data/resources/grn/grn_models/collectri.csv - tf_all: s3://openproblems-data/resources/grn/prior/tf_all.csv - degree: 0 - noise_type: sign - - id: celloracle_0_scgen_pearson - perturbation_data: s3://openproblems-data/resources/grn/grn-benchmark/perturbation_data.h5ad - reg_type: ridge - method_id: 0-celloracle - layer: scgen_pearson - subsample: -2 - max_workers: 10 - consensus: s3://openproblems-data/resources/grn/prior/consensus-num-regulators.json - prediction: s3://openproblems-data/resources/grn/grn_models/celloracle.csv - tf_all: s3://openproblems-data/resources/grn/prior/tf_all.csv - degree: 0 - noise_type: sign - - id: scenicplus_0_scgen_pearson - perturbation_data: s3://openproblems-data/resources/grn/grn-benchmark/perturbation_data.h5ad - reg_type: ridge - method_id: 0-scenicplus - layer: scgen_pearson - subsample: -2 - max_workers: 10 - consensus: s3://openproblems-data/resources/grn/prior/consensus-num-regulators.json - prediction: s3://openproblems-data/resources/grn/grn_models/scenicplus.csv - tf_all: s3://openproblems-data/resources/grn/prior/tf_all.csv - degree: 0 - noise_type: sign - - id: figr_0_scgen_pearson - perturbation_data: s3://openproblems-data/resources/grn/grn-benchmark/perturbation_data.h5ad - reg_type: ridge - method_id: 0-figr - layer: scgen_pearson - subsample: -2 - max_workers: 10 - consensus: s3://openproblems-data/resources/grn/prior/consensus-num-regulators.json - prediction: s3://openproblems-data/resources/grn/grn_models/figr.csv - tf_all: s3://openproblems-data/resources/grn/prior/tf_all.csv - degree: 0 - noise_type: sign - - id: granie_0_scgen_pearson - perturbation_data: s3://openproblems-data/resources/grn/grn-benchmark/perturbation_data.h5ad - reg_type: ridge - method_id: 0-granie - layer: scgen_pearson - subsample: -2 - max_workers: 10 - consensus: s3://openproblems-data/resources/grn/prior/consensus-num-regulators.json - prediction: s3://openproblems-data/resources/grn/grn_models/granie.csv - tf_all: s3://openproblems-data/resources/grn/prior/tf_all.csv - degree: 0 - noise_type: sign - - id: scglue_0_scgen_pearson - perturbation_data: s3://openproblems-data/resources/grn/grn-benchmark/perturbation_data.h5ad - reg_type: ridge - method_id: 0-scglue - layer: scgen_pearson - subsample: -2 - max_workers: 10 - consensus: s3://openproblems-data/resources/grn/prior/consensus-num-regulators.json - prediction: s3://openproblems-data/resources/grn/grn_models/scglue.csv - tf_all: s3://openproblems-data/resources/grn/prior/tf_all.csv - degree: 0 - noise_type: sign - - id: collectri_10_scgen_pearson - perturbation_data: s3://openproblems-data/resources/grn/grn-benchmark/perturbation_data.h5ad - reg_type: ridge - method_id: 10-collectri - layer: scgen_pearson - subsample: -2 - max_workers: 10 - consensus: s3://openproblems-data/resources/grn/prior/consensus-num-regulators.json - prediction: s3://openproblems-data/resources/grn/grn_models/collectri.csv - tf_all: s3://openproblems-data/resources/grn/prior/tf_all.csv - degree: 10 - noise_type: sign - - id: celloracle_10_scgen_pearson - perturbation_data: s3://openproblems-data/resources/grn/grn-benchmark/perturbation_data.h5ad - reg_type: ridge - method_id: 10-celloracle - layer: scgen_pearson - subsample: -2 - max_workers: 10 - consensus: s3://openproblems-data/resources/grn/prior/consensus-num-regulators.json - prediction: s3://openproblems-data/resources/grn/grn_models/celloracle.csv - tf_all: s3://openproblems-data/resources/grn/prior/tf_all.csv - degree: 10 - noise_type: sign - - id: scenicplus_10_scgen_pearson - perturbation_data: s3://openproblems-data/resources/grn/grn-benchmark/perturbation_data.h5ad - reg_type: ridge - method_id: 10-scenicplus - layer: scgen_pearson - subsample: -2 - max_workers: 10 - consensus: s3://openproblems-data/resources/grn/prior/consensus-num-regulators.json - prediction: s3://openproblems-data/resources/grn/grn_models/scenicplus.csv - tf_all: s3://openproblems-data/resources/grn/prior/tf_all.csv - degree: 10 - noise_type: sign - - id: figr_10_scgen_pearson - perturbation_data: s3://openproblems-data/resources/grn/grn-benchmark/perturbation_data.h5ad - reg_type: ridge - method_id: 10-figr - layer: scgen_pearson - subsample: -2 - max_workers: 10 - consensus: s3://openproblems-data/resources/grn/prior/consensus-num-regulators.json - prediction: s3://openproblems-data/resources/grn/grn_models/figr.csv - tf_all: s3://openproblems-data/resources/grn/prior/tf_all.csv - degree: 10 - noise_type: sign - - id: granie_10_scgen_pearson - perturbation_data: s3://openproblems-data/resources/grn/grn-benchmark/perturbation_data.h5ad - reg_type: ridge - method_id: 10-granie - layer: scgen_pearson - subsample: -2 - max_workers: 10 - consensus: s3://openproblems-data/resources/grn/prior/consensus-num-regulators.json - prediction: s3://openproblems-data/resources/grn/grn_models/granie.csv - tf_all: s3://openproblems-data/resources/grn/prior/tf_all.csv - degree: 10 - noise_type: sign - - id: scglue_10_scgen_pearson - perturbation_data: s3://openproblems-data/resources/grn/grn-benchmark/perturbation_data.h5ad - reg_type: ridge - method_id: 10-scglue - layer: scgen_pearson - subsample: -2 - max_workers: 10 - consensus: s3://openproblems-data/resources/grn/prior/consensus-num-regulators.json - prediction: s3://openproblems-data/resources/grn/grn_models/scglue.csv - tf_all: s3://openproblems-data/resources/grn/prior/tf_all.csv - degree: 10 - noise_type: sign - - id: collectri_20_scgen_pearson - perturbation_data: s3://openproblems-data/resources/grn/grn-benchmark/perturbation_data.h5ad - reg_type: ridge - method_id: 20-collectri - layer: scgen_pearson - subsample: -2 - max_workers: 10 - consensus: s3://openproblems-data/resources/grn/prior/consensus-num-regulators.json - prediction: s3://openproblems-data/resources/grn/grn_models/collectri.csv - tf_all: s3://openproblems-data/resources/grn/prior/tf_all.csv - degree: 20 - noise_type: sign - - id: celloracle_20_scgen_pearson - perturbation_data: s3://openproblems-data/resources/grn/grn-benchmark/perturbation_data.h5ad - reg_type: ridge - method_id: 20-celloracle - layer: scgen_pearson - subsample: -2 - max_workers: 10 - consensus: s3://openproblems-data/resources/grn/prior/consensus-num-regulators.json - prediction: s3://openproblems-data/resources/grn/grn_models/celloracle.csv - tf_all: s3://openproblems-data/resources/grn/prior/tf_all.csv - degree: 20 - noise_type: sign - - id: scenicplus_20_scgen_pearson - perturbation_data: s3://openproblems-data/resources/grn/grn-benchmark/perturbation_data.h5ad - reg_type: ridge - method_id: 20-scenicplus - layer: scgen_pearson - subsample: -2 - max_workers: 10 - consensus: s3://openproblems-data/resources/grn/prior/consensus-num-regulators.json - prediction: s3://openproblems-data/resources/grn/grn_models/scenicplus.csv - tf_all: s3://openproblems-data/resources/grn/prior/tf_all.csv - degree: 20 - noise_type: sign - - id: figr_20_scgen_pearson - perturbation_data: s3://openproblems-data/resources/grn/grn-benchmark/perturbation_data.h5ad - reg_type: ridge - method_id: 20-figr - layer: scgen_pearson - subsample: -2 - max_workers: 10 - consensus: s3://openproblems-data/resources/grn/prior/consensus-num-regulators.json - prediction: s3://openproblems-data/resources/grn/grn_models/figr.csv - tf_all: s3://openproblems-data/resources/grn/prior/tf_all.csv - degree: 20 - noise_type: sign - - id: granie_20_scgen_pearson - perturbation_data: s3://openproblems-data/resources/grn/grn-benchmark/perturbation_data.h5ad - reg_type: ridge - method_id: 20-granie - layer: scgen_pearson - subsample: -2 - max_workers: 10 - consensus: s3://openproblems-data/resources/grn/prior/consensus-num-regulators.json - prediction: s3://openproblems-data/resources/grn/grn_models/granie.csv - tf_all: s3://openproblems-data/resources/grn/prior/tf_all.csv - degree: 20 - noise_type: sign - - id: scglue_20_scgen_pearson - perturbation_data: s3://openproblems-data/resources/grn/grn-benchmark/perturbation_data.h5ad - reg_type: ridge - method_id: 20-scglue - layer: scgen_pearson - subsample: -2 - max_workers: 10 - consensus: s3://openproblems-data/resources/grn/prior/consensus-num-regulators.json - prediction: s3://openproblems-data/resources/grn/grn_models/scglue.csv - tf_all: s3://openproblems-data/resources/grn/prior/tf_all.csv - degree: 20 - noise_type: sign - - id: collectri_50_scgen_pearson - perturbation_data: s3://openproblems-data/resources/grn/grn-benchmark/perturbation_data.h5ad - reg_type: ridge - method_id: 50-collectri - layer: scgen_pearson - subsample: -2 - max_workers: 10 - consensus: s3://openproblems-data/resources/grn/prior/consensus-num-regulators.json - prediction: s3://openproblems-data/resources/grn/grn_models/collectri.csv - tf_all: s3://openproblems-data/resources/grn/prior/tf_all.csv - degree: 50 - noise_type: sign - - id: celloracle_50_scgen_pearson - perturbation_data: s3://openproblems-data/resources/grn/grn-benchmark/perturbation_data.h5ad - reg_type: ridge - method_id: 50-celloracle - layer: scgen_pearson - subsample: -2 - max_workers: 10 - consensus: s3://openproblems-data/resources/grn/prior/consensus-num-regulators.json - prediction: s3://openproblems-data/resources/grn/grn_models/celloracle.csv - tf_all: s3://openproblems-data/resources/grn/prior/tf_all.csv - degree: 50 - noise_type: sign - - id: scenicplus_50_scgen_pearson - perturbation_data: s3://openproblems-data/resources/grn/grn-benchmark/perturbation_data.h5ad - reg_type: ridge - method_id: 50-scenicplus - layer: scgen_pearson - subsample: -2 - max_workers: 10 - consensus: s3://openproblems-data/resources/grn/prior/consensus-num-regulators.json - prediction: s3://openproblems-data/resources/grn/grn_models/scenicplus.csv - tf_all: s3://openproblems-data/resources/grn/prior/tf_all.csv - degree: 50 - noise_type: sign - - id: figr_50_scgen_pearson - perturbation_data: s3://openproblems-data/resources/grn/grn-benchmark/perturbation_data.h5ad - reg_type: ridge - method_id: 50-figr - layer: scgen_pearson - subsample: -2 - max_workers: 10 - consensus: s3://openproblems-data/resources/grn/prior/consensus-num-regulators.json - prediction: s3://openproblems-data/resources/grn/grn_models/figr.csv - tf_all: s3://openproblems-data/resources/grn/prior/tf_all.csv - degree: 50 - noise_type: sign - - id: granie_50_scgen_pearson - perturbation_data: s3://openproblems-data/resources/grn/grn-benchmark/perturbation_data.h5ad - reg_type: ridge - method_id: 50-granie - layer: scgen_pearson - subsample: -2 - max_workers: 10 - consensus: s3://openproblems-data/resources/grn/prior/consensus-num-regulators.json - prediction: s3://openproblems-data/resources/grn/grn_models/granie.csv - tf_all: s3://openproblems-data/resources/grn/prior/tf_all.csv - degree: 50 - noise_type: sign - - id: scglue_50_scgen_pearson - perturbation_data: s3://openproblems-data/resources/grn/grn-benchmark/perturbation_data.h5ad - reg_type: ridge - method_id: 50-scglue - layer: scgen_pearson - subsample: -2 - max_workers: 10 - consensus: s3://openproblems-data/resources/grn/prior/consensus-num-regulators.json - prediction: s3://openproblems-data/resources/grn/grn_models/scglue.csv - tf_all: s3://openproblems-data/resources/grn/prior/tf_all.csv - degree: 50 - noise_type: sign - - id: collectri_100_scgen_pearson - perturbation_data: s3://openproblems-data/resources/grn/grn-benchmark/perturbation_data.h5ad - reg_type: ridge - method_id: 100-collectri - layer: scgen_pearson - subsample: -2 - max_workers: 10 - consensus: s3://openproblems-data/resources/grn/prior/consensus-num-regulators.json - prediction: s3://openproblems-data/resources/grn/grn_models/collectri.csv - tf_all: s3://openproblems-data/resources/grn/prior/tf_all.csv - degree: 100 - noise_type: sign - - id: celloracle_100_scgen_pearson - perturbation_data: s3://openproblems-data/resources/grn/grn-benchmark/perturbation_data.h5ad - reg_type: ridge - method_id: 100-celloracle - layer: scgen_pearson - subsample: -2 - max_workers: 10 - consensus: s3://openproblems-data/resources/grn/prior/consensus-num-regulators.json - prediction: s3://openproblems-data/resources/grn/grn_models/celloracle.csv - tf_all: s3://openproblems-data/resources/grn/prior/tf_all.csv - degree: 100 - noise_type: sign - - id: scenicplus_100_scgen_pearson - perturbation_data: s3://openproblems-data/resources/grn/grn-benchmark/perturbation_data.h5ad - reg_type: ridge - method_id: 100-scenicplus - layer: scgen_pearson - subsample: -2 - max_workers: 10 - consensus: s3://openproblems-data/resources/grn/prior/consensus-num-regulators.json - prediction: s3://openproblems-data/resources/grn/grn_models/scenicplus.csv - tf_all: s3://openproblems-data/resources/grn/prior/tf_all.csv - degree: 100 - noise_type: sign - - id: figr_100_scgen_pearson - perturbation_data: s3://openproblems-data/resources/grn/grn-benchmark/perturbation_data.h5ad - reg_type: ridge - method_id: 100-figr - layer: scgen_pearson - subsample: -2 - max_workers: 10 - consensus: s3://openproblems-data/resources/grn/prior/consensus-num-regulators.json - prediction: s3://openproblems-data/resources/grn/grn_models/figr.csv - tf_all: s3://openproblems-data/resources/grn/prior/tf_all.csv - degree: 100 - noise_type: sign - - id: granie_100_scgen_pearson - perturbation_data: s3://openproblems-data/resources/grn/grn-benchmark/perturbation_data.h5ad - reg_type: ridge - method_id: 100-granie - layer: scgen_pearson - subsample: -2 - max_workers: 10 - consensus: s3://openproblems-data/resources/grn/prior/consensus-num-regulators.json - prediction: s3://openproblems-data/resources/grn/grn_models/granie.csv - tf_all: s3://openproblems-data/resources/grn/prior/tf_all.csv - degree: 100 - noise_type: sign - - id: scglue_100_scgen_pearson - perturbation_data: s3://openproblems-data/resources/grn/grn-benchmark/perturbation_data.h5ad - reg_type: ridge - method_id: 100-scglue - layer: scgen_pearson - subsample: -2 - max_workers: 10 - consensus: s3://openproblems-data/resources/grn/prior/consensus-num-regulators.json - prediction: s3://openproblems-data/resources/grn/grn_models/scglue.csv - tf_all: s3://openproblems-data/resources/grn/prior/tf_all.csv - degree: 100 - noise_type: sign -output_state: "state.yaml" -publish_dir: "s3://openproblems-data/resources/grn/results/robust_analy_reg2_sign" diff --git a/params/repo/robust_analy_reg2_weight.yaml b/params/repo/robust_analy_reg2_weight.yaml deleted file mode 100644 index fd3476ce2..000000000 --- a/params/repo/robust_analy_reg2_weight.yaml +++ /dev/null @@ -1,363 +0,0 @@ -param_list: - - id: collectri_0_scgen_pearson - perturbation_data: s3://openproblems-data/resources/grn/grn-benchmark/perturbation_data.h5ad - reg_type: ridge - method_id: 0-collectri - layer: scgen_pearson - subsample: -2 - max_workers: 10 - consensus: s3://openproblems-data/resources/grn/prior/consensus-num-regulators.json - prediction: s3://openproblems-data/resources/grn/grn_models/collectri.csv - tf_all: s3://openproblems-data/resources/grn/prior/tf_all.csv - degree: 0 - noise_type: weight - - id: celloracle_0_scgen_pearson - perturbation_data: s3://openproblems-data/resources/grn/grn-benchmark/perturbation_data.h5ad - reg_type: ridge - method_id: 0-celloracle - layer: scgen_pearson - subsample: -2 - max_workers: 10 - consensus: s3://openproblems-data/resources/grn/prior/consensus-num-regulators.json - prediction: s3://openproblems-data/resources/grn/grn_models/celloracle.csv - tf_all: s3://openproblems-data/resources/grn/prior/tf_all.csv - degree: 0 - noise_type: weight - - id: scenicplus_0_scgen_pearson - perturbation_data: s3://openproblems-data/resources/grn/grn-benchmark/perturbation_data.h5ad - reg_type: ridge - method_id: 0-scenicplus - layer: scgen_pearson - subsample: -2 - max_workers: 10 - consensus: s3://openproblems-data/resources/grn/prior/consensus-num-regulators.json - prediction: s3://openproblems-data/resources/grn/grn_models/scenicplus.csv - tf_all: s3://openproblems-data/resources/grn/prior/tf_all.csv - degree: 0 - noise_type: weight - - id: figr_0_scgen_pearson - perturbation_data: s3://openproblems-data/resources/grn/grn-benchmark/perturbation_data.h5ad - reg_type: ridge - method_id: 0-figr - layer: scgen_pearson - subsample: -2 - max_workers: 10 - consensus: s3://openproblems-data/resources/grn/prior/consensus-num-regulators.json - prediction: s3://openproblems-data/resources/grn/grn_models/figr.csv - tf_all: s3://openproblems-data/resources/grn/prior/tf_all.csv - degree: 0 - noise_type: weight - - id: granie_0_scgen_pearson - perturbation_data: s3://openproblems-data/resources/grn/grn-benchmark/perturbation_data.h5ad - reg_type: ridge - method_id: 0-granie - layer: scgen_pearson - subsample: -2 - max_workers: 10 - consensus: s3://openproblems-data/resources/grn/prior/consensus-num-regulators.json - prediction: s3://openproblems-data/resources/grn/grn_models/granie.csv - tf_all: s3://openproblems-data/resources/grn/prior/tf_all.csv - degree: 0 - noise_type: weight - - id: scglue_0_scgen_pearson - perturbation_data: s3://openproblems-data/resources/grn/grn-benchmark/perturbation_data.h5ad - reg_type: ridge - method_id: 0-scglue - layer: scgen_pearson - subsample: -2 - max_workers: 10 - consensus: s3://openproblems-data/resources/grn/prior/consensus-num-regulators.json - prediction: s3://openproblems-data/resources/grn/grn_models/scglue.csv - tf_all: s3://openproblems-data/resources/grn/prior/tf_all.csv - degree: 0 - noise_type: weight - - id: collectri_10_scgen_pearson - perturbation_data: s3://openproblems-data/resources/grn/grn-benchmark/perturbation_data.h5ad - reg_type: ridge - method_id: 10-collectri - layer: scgen_pearson - subsample: -2 - max_workers: 10 - consensus: s3://openproblems-data/resources/grn/prior/consensus-num-regulators.json - prediction: s3://openproblems-data/resources/grn/grn_models/collectri.csv - tf_all: s3://openproblems-data/resources/grn/prior/tf_all.csv - degree: 10 - noise_type: weight - - id: celloracle_10_scgen_pearson - perturbation_data: s3://openproblems-data/resources/grn/grn-benchmark/perturbation_data.h5ad - reg_type: ridge - method_id: 10-celloracle - layer: scgen_pearson - subsample: -2 - max_workers: 10 - consensus: s3://openproblems-data/resources/grn/prior/consensus-num-regulators.json - prediction: s3://openproblems-data/resources/grn/grn_models/celloracle.csv - tf_all: s3://openproblems-data/resources/grn/prior/tf_all.csv - degree: 10 - noise_type: weight - - id: scenicplus_10_scgen_pearson - perturbation_data: s3://openproblems-data/resources/grn/grn-benchmark/perturbation_data.h5ad - reg_type: ridge - method_id: 10-scenicplus - layer: scgen_pearson - subsample: -2 - max_workers: 10 - consensus: s3://openproblems-data/resources/grn/prior/consensus-num-regulators.json - prediction: s3://openproblems-data/resources/grn/grn_models/scenicplus.csv - tf_all: s3://openproblems-data/resources/grn/prior/tf_all.csv - degree: 10 - noise_type: weight - - id: figr_10_scgen_pearson - perturbation_data: s3://openproblems-data/resources/grn/grn-benchmark/perturbation_data.h5ad - reg_type: ridge - method_id: 10-figr - layer: scgen_pearson - subsample: -2 - max_workers: 10 - consensus: s3://openproblems-data/resources/grn/prior/consensus-num-regulators.json - prediction: s3://openproblems-data/resources/grn/grn_models/figr.csv - tf_all: s3://openproblems-data/resources/grn/prior/tf_all.csv - degree: 10 - noise_type: weight - - id: granie_10_scgen_pearson - perturbation_data: s3://openproblems-data/resources/grn/grn-benchmark/perturbation_data.h5ad - reg_type: ridge - method_id: 10-granie - layer: scgen_pearson - subsample: -2 - max_workers: 10 - consensus: s3://openproblems-data/resources/grn/prior/consensus-num-regulators.json - prediction: s3://openproblems-data/resources/grn/grn_models/granie.csv - tf_all: s3://openproblems-data/resources/grn/prior/tf_all.csv - degree: 10 - noise_type: weight - - id: scglue_10_scgen_pearson - perturbation_data: s3://openproblems-data/resources/grn/grn-benchmark/perturbation_data.h5ad - reg_type: ridge - method_id: 10-scglue - layer: scgen_pearson - subsample: -2 - max_workers: 10 - consensus: s3://openproblems-data/resources/grn/prior/consensus-num-regulators.json - prediction: s3://openproblems-data/resources/grn/grn_models/scglue.csv - tf_all: s3://openproblems-data/resources/grn/prior/tf_all.csv - degree: 10 - noise_type: weight - - id: collectri_20_scgen_pearson - perturbation_data: s3://openproblems-data/resources/grn/grn-benchmark/perturbation_data.h5ad - reg_type: ridge - method_id: 20-collectri - layer: scgen_pearson - subsample: -2 - max_workers: 10 - consensus: s3://openproblems-data/resources/grn/prior/consensus-num-regulators.json - prediction: s3://openproblems-data/resources/grn/grn_models/collectri.csv - tf_all: s3://openproblems-data/resources/grn/prior/tf_all.csv - degree: 20 - noise_type: weight - - id: celloracle_20_scgen_pearson - perturbation_data: s3://openproblems-data/resources/grn/grn-benchmark/perturbation_data.h5ad - reg_type: ridge - method_id: 20-celloracle - layer: scgen_pearson - subsample: -2 - max_workers: 10 - consensus: s3://openproblems-data/resources/grn/prior/consensus-num-regulators.json - prediction: s3://openproblems-data/resources/grn/grn_models/celloracle.csv - tf_all: s3://openproblems-data/resources/grn/prior/tf_all.csv - degree: 20 - noise_type: weight - - id: scenicplus_20_scgen_pearson - perturbation_data: s3://openproblems-data/resources/grn/grn-benchmark/perturbation_data.h5ad - reg_type: ridge - method_id: 20-scenicplus - layer: scgen_pearson - subsample: -2 - max_workers: 10 - consensus: s3://openproblems-data/resources/grn/prior/consensus-num-regulators.json - prediction: s3://openproblems-data/resources/grn/grn_models/scenicplus.csv - tf_all: s3://openproblems-data/resources/grn/prior/tf_all.csv - degree: 20 - noise_type: weight - - id: figr_20_scgen_pearson - perturbation_data: s3://openproblems-data/resources/grn/grn-benchmark/perturbation_data.h5ad - reg_type: ridge - method_id: 20-figr - layer: scgen_pearson - subsample: -2 - max_workers: 10 - consensus: s3://openproblems-data/resources/grn/prior/consensus-num-regulators.json - prediction: s3://openproblems-data/resources/grn/grn_models/figr.csv - tf_all: s3://openproblems-data/resources/grn/prior/tf_all.csv - degree: 20 - noise_type: weight - - id: granie_20_scgen_pearson - perturbation_data: s3://openproblems-data/resources/grn/grn-benchmark/perturbation_data.h5ad - reg_type: ridge - method_id: 20-granie - layer: scgen_pearson - subsample: -2 - max_workers: 10 - consensus: s3://openproblems-data/resources/grn/prior/consensus-num-regulators.json - prediction: s3://openproblems-data/resources/grn/grn_models/granie.csv - tf_all: s3://openproblems-data/resources/grn/prior/tf_all.csv - degree: 20 - noise_type: weight - - id: scglue_20_scgen_pearson - perturbation_data: s3://openproblems-data/resources/grn/grn-benchmark/perturbation_data.h5ad - reg_type: ridge - method_id: 20-scglue - layer: scgen_pearson - subsample: -2 - max_workers: 10 - consensus: s3://openproblems-data/resources/grn/prior/consensus-num-regulators.json - prediction: s3://openproblems-data/resources/grn/grn_models/scglue.csv - tf_all: s3://openproblems-data/resources/grn/prior/tf_all.csv - degree: 20 - noise_type: weight - - id: collectri_50_scgen_pearson - perturbation_data: s3://openproblems-data/resources/grn/grn-benchmark/perturbation_data.h5ad - reg_type: ridge - method_id: 50-collectri - layer: scgen_pearson - subsample: -2 - max_workers: 10 - consensus: s3://openproblems-data/resources/grn/prior/consensus-num-regulators.json - prediction: s3://openproblems-data/resources/grn/grn_models/collectri.csv - tf_all: s3://openproblems-data/resources/grn/prior/tf_all.csv - degree: 50 - noise_type: weight - - id: celloracle_50_scgen_pearson - perturbation_data: s3://openproblems-data/resources/grn/grn-benchmark/perturbation_data.h5ad - reg_type: ridge - method_id: 50-celloracle - layer: scgen_pearson - subsample: -2 - max_workers: 10 - consensus: s3://openproblems-data/resources/grn/prior/consensus-num-regulators.json - prediction: s3://openproblems-data/resources/grn/grn_models/celloracle.csv - tf_all: s3://openproblems-data/resources/grn/prior/tf_all.csv - degree: 50 - noise_type: weight - - id: scenicplus_50_scgen_pearson - perturbation_data: s3://openproblems-data/resources/grn/grn-benchmark/perturbation_data.h5ad - reg_type: ridge - method_id: 50-scenicplus - layer: scgen_pearson - subsample: -2 - max_workers: 10 - consensus: s3://openproblems-data/resources/grn/prior/consensus-num-regulators.json - prediction: s3://openproblems-data/resources/grn/grn_models/scenicplus.csv - tf_all: s3://openproblems-data/resources/grn/prior/tf_all.csv - degree: 50 - noise_type: weight - - id: figr_50_scgen_pearson - perturbation_data: s3://openproblems-data/resources/grn/grn-benchmark/perturbation_data.h5ad - reg_type: ridge - method_id: 50-figr - layer: scgen_pearson - subsample: -2 - max_workers: 10 - consensus: s3://openproblems-data/resources/grn/prior/consensus-num-regulators.json - prediction: s3://openproblems-data/resources/grn/grn_models/figr.csv - tf_all: s3://openproblems-data/resources/grn/prior/tf_all.csv - degree: 50 - noise_type: weight - - id: granie_50_scgen_pearson - perturbation_data: s3://openproblems-data/resources/grn/grn-benchmark/perturbation_data.h5ad - reg_type: ridge - method_id: 50-granie - layer: scgen_pearson - subsample: -2 - max_workers: 10 - consensus: s3://openproblems-data/resources/grn/prior/consensus-num-regulators.json - prediction: s3://openproblems-data/resources/grn/grn_models/granie.csv - tf_all: s3://openproblems-data/resources/grn/prior/tf_all.csv - degree: 50 - noise_type: weight - - id: scglue_50_scgen_pearson - perturbation_data: s3://openproblems-data/resources/grn/grn-benchmark/perturbation_data.h5ad - reg_type: ridge - method_id: 50-scglue - layer: scgen_pearson - subsample: -2 - max_workers: 10 - consensus: s3://openproblems-data/resources/grn/prior/consensus-num-regulators.json - prediction: s3://openproblems-data/resources/grn/grn_models/scglue.csv - tf_all: s3://openproblems-data/resources/grn/prior/tf_all.csv - degree: 50 - noise_type: weight - - id: collectri_100_scgen_pearson - perturbation_data: s3://openproblems-data/resources/grn/grn-benchmark/perturbation_data.h5ad - reg_type: ridge - method_id: 100-collectri - layer: scgen_pearson - subsample: -2 - max_workers: 10 - consensus: s3://openproblems-data/resources/grn/prior/consensus-num-regulators.json - prediction: s3://openproblems-data/resources/grn/grn_models/collectri.csv - tf_all: s3://openproblems-data/resources/grn/prior/tf_all.csv - degree: 100 - noise_type: weight - - id: celloracle_100_scgen_pearson - perturbation_data: s3://openproblems-data/resources/grn/grn-benchmark/perturbation_data.h5ad - reg_type: ridge - method_id: 100-celloracle - layer: scgen_pearson - subsample: -2 - max_workers: 10 - consensus: s3://openproblems-data/resources/grn/prior/consensus-num-regulators.json - prediction: s3://openproblems-data/resources/grn/grn_models/celloracle.csv - tf_all: s3://openproblems-data/resources/grn/prior/tf_all.csv - degree: 100 - noise_type: weight - - id: scenicplus_100_scgen_pearson - perturbation_data: s3://openproblems-data/resources/grn/grn-benchmark/perturbation_data.h5ad - reg_type: ridge - method_id: 100-scenicplus - layer: scgen_pearson - subsample: -2 - max_workers: 10 - consensus: s3://openproblems-data/resources/grn/prior/consensus-num-regulators.json - prediction: s3://openproblems-data/resources/grn/grn_models/scenicplus.csv - tf_all: s3://openproblems-data/resources/grn/prior/tf_all.csv - degree: 100 - noise_type: weight - - id: figr_100_scgen_pearson - perturbation_data: s3://openproblems-data/resources/grn/grn-benchmark/perturbation_data.h5ad - reg_type: ridge - method_id: 100-figr - layer: scgen_pearson - subsample: -2 - max_workers: 10 - consensus: s3://openproblems-data/resources/grn/prior/consensus-num-regulators.json - prediction: s3://openproblems-data/resources/grn/grn_models/figr.csv - tf_all: s3://openproblems-data/resources/grn/prior/tf_all.csv - degree: 100 - noise_type: weight - - id: granie_100_scgen_pearson - perturbation_data: s3://openproblems-data/resources/grn/grn-benchmark/perturbation_data.h5ad - reg_type: ridge - method_id: 100-granie - layer: scgen_pearson - subsample: -2 - max_workers: 10 - consensus: s3://openproblems-data/resources/grn/prior/consensus-num-regulators.json - prediction: s3://openproblems-data/resources/grn/grn_models/granie.csv - tf_all: s3://openproblems-data/resources/grn/prior/tf_all.csv - degree: 100 - noise_type: weight - - id: scglue_100_scgen_pearson - perturbation_data: s3://openproblems-data/resources/grn/grn-benchmark/perturbation_data.h5ad - reg_type: ridge - method_id: 100-scglue - layer: scgen_pearson - subsample: -2 - max_workers: 10 - consensus: s3://openproblems-data/resources/grn/prior/consensus-num-regulators.json - prediction: s3://openproblems-data/resources/grn/grn_models/scglue.csv - tf_all: s3://openproblems-data/resources/grn/prior/tf_all.csv - degree: 100 - noise_type: weight -output_state: "state.yaml" -publish_dir: "s3://openproblems-data/resources/grn/results/robust_analy_reg2_weight" diff --git a/params/repo/robust_analy_sign.yaml b/params/repo/robust_analy_sign.yaml deleted file mode 100644 index ec59b7786..000000000 --- a/params/repo/robust_analy_sign.yaml +++ /dev/null @@ -1,333 +0,0 @@ -param_list: - - id: collectri_0 - perturbation_data: resources/grn-benchmark/perturbation_data.h5ad - layer: pearson - reg_type: ridge - method_id: 0-collectri - subsample: -2 - max_workers: 10 - consensus: resources/prior/consensus-num-regulators.json - prediction: resources/grn_models/collectri.csv - degree: 0 - noise_type: sign - - id: celloracle_0 - perturbation_data: resources/grn-benchmark/perturbation_data.h5ad - layer: pearson - reg_type: ridge - method_id: 0-celloracle - subsample: -2 - max_workers: 10 - consensus: resources/prior/consensus-num-regulators.json - prediction: resources/grn_models/celloracle.csv - degree: 0 - noise_type: sign - - id: scenicplus_0 - perturbation_data: resources/grn-benchmark/perturbation_data.h5ad - layer: pearson - reg_type: ridge - method_id: 0-scenicplus - subsample: -2 - max_workers: 10 - consensus: resources/prior/consensus-num-regulators.json - prediction: resources/grn_models/scenicplus.csv - degree: 0 - noise_type: sign - - id: figr_0 - perturbation_data: resources/grn-benchmark/perturbation_data.h5ad - layer: pearson - reg_type: ridge - method_id: 0-figr - subsample: -2 - max_workers: 10 - consensus: resources/prior/consensus-num-regulators.json - prediction: resources/grn_models/figr.csv - degree: 0 - noise_type: sign - - id: granie_0 - perturbation_data: resources/grn-benchmark/perturbation_data.h5ad - layer: pearson - reg_type: ridge - method_id: 0-granie - subsample: -2 - max_workers: 10 - consensus: resources/prior/consensus-num-regulators.json - prediction: resources/grn_models/granie.csv - degree: 0 - noise_type: sign - - id: scglue_0 - perturbation_data: resources/grn-benchmark/perturbation_data.h5ad - layer: pearson - reg_type: ridge - method_id: 0-scglue - subsample: -2 - max_workers: 10 - consensus: resources/prior/consensus-num-regulators.json - prediction: resources/grn_models/scglue.csv - degree: 0 - noise_type: sign - - id: collectri_10 - perturbation_data: resources/grn-benchmark/perturbation_data.h5ad - layer: pearson - reg_type: ridge - method_id: 10-collectri - subsample: -2 - max_workers: 10 - consensus: resources/prior/consensus-num-regulators.json - prediction: resources/grn_models/collectri.csv - degree: 10 - noise_type: sign - - id: celloracle_10 - perturbation_data: resources/grn-benchmark/perturbation_data.h5ad - layer: pearson - reg_type: ridge - method_id: 10-celloracle - subsample: -2 - max_workers: 10 - consensus: resources/prior/consensus-num-regulators.json - prediction: resources/grn_models/celloracle.csv - degree: 10 - noise_type: sign - - id: scenicplus_10 - perturbation_data: resources/grn-benchmark/perturbation_data.h5ad - layer: pearson - reg_type: ridge - method_id: 10-scenicplus - subsample: -2 - max_workers: 10 - consensus: resources/prior/consensus-num-regulators.json - prediction: resources/grn_models/scenicplus.csv - degree: 10 - noise_type: sign - - id: figr_10 - perturbation_data: resources/grn-benchmark/perturbation_data.h5ad - layer: pearson - reg_type: ridge - method_id: 10-figr - subsample: -2 - max_workers: 10 - consensus: resources/prior/consensus-num-regulators.json - prediction: resources/grn_models/figr.csv - degree: 10 - noise_type: sign - - id: granie_10 - perturbation_data: resources/grn-benchmark/perturbation_data.h5ad - layer: pearson - reg_type: ridge - method_id: 10-granie - subsample: -2 - max_workers: 10 - consensus: resources/prior/consensus-num-regulators.json - prediction: resources/grn_models/granie.csv - degree: 10 - noise_type: sign - - id: scglue_10 - perturbation_data: resources/grn-benchmark/perturbation_data.h5ad - layer: pearson - reg_type: ridge - method_id: 10-scglue - subsample: -2 - max_workers: 10 - consensus: resources/prior/consensus-num-regulators.json - prediction: resources/grn_models/scglue.csv - degree: 10 - noise_type: sign - - id: collectri_20 - perturbation_data: resources/grn-benchmark/perturbation_data.h5ad - layer: pearson - reg_type: ridge - method_id: 20-collectri - subsample: -2 - max_workers: 10 - consensus: resources/prior/consensus-num-regulators.json - prediction: resources/grn_models/collectri.csv - degree: 20 - noise_type: sign - - id: celloracle_20 - perturbation_data: resources/grn-benchmark/perturbation_data.h5ad - layer: pearson - reg_type: ridge - method_id: 20-celloracle - subsample: -2 - max_workers: 10 - consensus: resources/prior/consensus-num-regulators.json - prediction: resources/grn_models/celloracle.csv - degree: 20 - noise_type: sign - - id: scenicplus_20 - perturbation_data: resources/grn-benchmark/perturbation_data.h5ad - layer: pearson - reg_type: ridge - method_id: 20-scenicplus - subsample: -2 - max_workers: 10 - consensus: resources/prior/consensus-num-regulators.json - prediction: resources/grn_models/scenicplus.csv - degree: 20 - noise_type: sign - - id: figr_20 - perturbation_data: resources/grn-benchmark/perturbation_data.h5ad - layer: pearson - reg_type: ridge - method_id: 20-figr - subsample: -2 - max_workers: 10 - consensus: resources/prior/consensus-num-regulators.json - prediction: resources/grn_models/figr.csv - degree: 20 - noise_type: sign - - id: granie_20 - perturbation_data: resources/grn-benchmark/perturbation_data.h5ad - layer: pearson - reg_type: ridge - method_id: 20-granie - subsample: -2 - max_workers: 10 - consensus: resources/prior/consensus-num-regulators.json - prediction: resources/grn_models/granie.csv - degree: 20 - noise_type: sign - - id: scglue_20 - perturbation_data: resources/grn-benchmark/perturbation_data.h5ad - layer: pearson - reg_type: ridge - method_id: 20-scglue - subsample: -2 - max_workers: 10 - consensus: resources/prior/consensus-num-regulators.json - prediction: resources/grn_models/scglue.csv - degree: 20 - noise_type: sign - - id: collectri_50 - perturbation_data: resources/grn-benchmark/perturbation_data.h5ad - layer: pearson - reg_type: ridge - method_id: 50-collectri - subsample: -2 - max_workers: 10 - consensus: resources/prior/consensus-num-regulators.json - prediction: resources/grn_models/collectri.csv - degree: 50 - noise_type: sign - - id: celloracle_50 - perturbation_data: resources/grn-benchmark/perturbation_data.h5ad - layer: pearson - reg_type: ridge - method_id: 50-celloracle - subsample: -2 - max_workers: 10 - consensus: resources/prior/consensus-num-regulators.json - prediction: resources/grn_models/celloracle.csv - degree: 50 - noise_type: sign - - id: scenicplus_50 - perturbation_data: resources/grn-benchmark/perturbation_data.h5ad - layer: pearson - reg_type: ridge - method_id: 50-scenicplus - subsample: -2 - max_workers: 10 - consensus: resources/prior/consensus-num-regulators.json - prediction: resources/grn_models/scenicplus.csv - degree: 50 - noise_type: sign - - id: figr_50 - perturbation_data: resources/grn-benchmark/perturbation_data.h5ad - layer: pearson - reg_type: ridge - method_id: 50-figr - subsample: -2 - max_workers: 10 - consensus: resources/prior/consensus-num-regulators.json - prediction: resources/grn_models/figr.csv - degree: 50 - noise_type: sign - - id: granie_50 - perturbation_data: resources/grn-benchmark/perturbation_data.h5ad - layer: pearson - reg_type: ridge - method_id: 50-granie - subsample: -2 - max_workers: 10 - consensus: resources/prior/consensus-num-regulators.json - prediction: resources/grn_models/granie.csv - degree: 50 - noise_type: sign - - id: scglue_50 - perturbation_data: resources/grn-benchmark/perturbation_data.h5ad - layer: pearson - reg_type: ridge - method_id: 50-scglue - subsample: -2 - max_workers: 10 - consensus: resources/prior/consensus-num-regulators.json - prediction: resources/grn_models/scglue.csv - degree: 50 - noise_type: sign - - id: collectri_100 - perturbation_data: resources/grn-benchmark/perturbation_data.h5ad - layer: pearson - reg_type: ridge - method_id: 100-collectri - subsample: -2 - max_workers: 10 - consensus: resources/prior/consensus-num-regulators.json - prediction: resources/grn_models/collectri.csv - degree: 100 - noise_type: sign - - id: celloracle_100 - perturbation_data: resources/grn-benchmark/perturbation_data.h5ad - layer: pearson - reg_type: ridge - method_id: 100-celloracle - subsample: -2 - max_workers: 10 - consensus: resources/prior/consensus-num-regulators.json - prediction: resources/grn_models/celloracle.csv - degree: 100 - noise_type: sign - - id: scenicplus_100 - perturbation_data: resources/grn-benchmark/perturbation_data.h5ad - layer: pearson - reg_type: ridge - method_id: 100-scenicplus - subsample: -2 - max_workers: 10 - consensus: resources/prior/consensus-num-regulators.json - prediction: resources/grn_models/scenicplus.csv - degree: 100 - noise_type: sign - - id: figr_100 - perturbation_data: resources/grn-benchmark/perturbation_data.h5ad - layer: pearson - reg_type: ridge - method_id: 100-figr - subsample: -2 - max_workers: 10 - consensus: resources/prior/consensus-num-regulators.json - prediction: resources/grn_models/figr.csv - degree: 100 - noise_type: sign - - id: granie_100 - perturbation_data: resources/grn-benchmark/perturbation_data.h5ad - layer: pearson - reg_type: ridge - method_id: 100-granie - subsample: -2 - max_workers: 10 - consensus: resources/prior/consensus-num-regulators.json - prediction: resources/grn_models/granie.csv - degree: 100 - noise_type: sign - - id: scglue_100 - perturbation_data: resources/grn-benchmark/perturbation_data.h5ad - layer: pearson - reg_type: ridge - method_id: 100-scglue - subsample: -2 - max_workers: 10 - consensus: resources/prior/consensus-num-regulators.json - prediction: resources/grn_models/scglue.csv - degree: 100 - noise_type: sign -output_state: "state.yaml" -publish_dir: "output/robust_analy_sign" diff --git a/params/repo/robust_analy_weight.yaml b/params/repo/robust_analy_weight.yaml deleted file mode 100644 index 736278d8c..000000000 --- a/params/repo/robust_analy_weight.yaml +++ /dev/null @@ -1,333 +0,0 @@ -param_list: - - id: collectri_0 - perturbation_data: resources/grn-benchmark/perturbation_data.h5ad - layer: pearson - reg_type: ridge - method_id: 0-collectri - subsample: -2 - max_workers: 10 - consensus: resources/prior/consensus-num-regulators.json - prediction: resources/grn_models/collectri.csv - degree: 0 - noise_type: weight - - id: celloracle_0 - perturbation_data: resources/grn-benchmark/perturbation_data.h5ad - layer: pearson - reg_type: ridge - method_id: 0-celloracle - subsample: -2 - max_workers: 10 - consensus: resources/prior/consensus-num-regulators.json - prediction: resources/grn_models/celloracle.csv - degree: 0 - noise_type: weight - - id: scenicplus_0 - perturbation_data: resources/grn-benchmark/perturbation_data.h5ad - layer: pearson - reg_type: ridge - method_id: 0-scenicplus - subsample: -2 - max_workers: 10 - consensus: resources/prior/consensus-num-regulators.json - prediction: resources/grn_models/scenicplus.csv - degree: 0 - noise_type: weight - - id: figr_0 - perturbation_data: resources/grn-benchmark/perturbation_data.h5ad - layer: pearson - reg_type: ridge - method_id: 0-figr - subsample: -2 - max_workers: 10 - consensus: resources/prior/consensus-num-regulators.json - prediction: resources/grn_models/figr.csv - degree: 0 - noise_type: weight - - id: granie_0 - perturbation_data: resources/grn-benchmark/perturbation_data.h5ad - layer: pearson - reg_type: ridge - method_id: 0-granie - subsample: -2 - max_workers: 10 - consensus: resources/prior/consensus-num-regulators.json - prediction: resources/grn_models/granie.csv - degree: 0 - noise_type: weight - - id: scglue_0 - perturbation_data: resources/grn-benchmark/perturbation_data.h5ad - layer: pearson - reg_type: ridge - method_id: 0-scglue - subsample: -2 - max_workers: 10 - consensus: resources/prior/consensus-num-regulators.json - prediction: resources/grn_models/scglue.csv - degree: 0 - noise_type: weight - - id: collectri_10 - perturbation_data: resources/grn-benchmark/perturbation_data.h5ad - layer: pearson - reg_type: ridge - method_id: 10-collectri - subsample: -2 - max_workers: 10 - consensus: resources/prior/consensus-num-regulators.json - prediction: resources/grn_models/collectri.csv - degree: 10 - noise_type: weight - - id: celloracle_10 - perturbation_data: resources/grn-benchmark/perturbation_data.h5ad - layer: pearson - reg_type: ridge - method_id: 10-celloracle - subsample: -2 - max_workers: 10 - consensus: resources/prior/consensus-num-regulators.json - prediction: resources/grn_models/celloracle.csv - degree: 10 - noise_type: weight - - id: scenicplus_10 - perturbation_data: resources/grn-benchmark/perturbation_data.h5ad - layer: pearson - reg_type: ridge - method_id: 10-scenicplus - subsample: -2 - max_workers: 10 - consensus: resources/prior/consensus-num-regulators.json - prediction: resources/grn_models/scenicplus.csv - degree: 10 - noise_type: weight - - id: figr_10 - perturbation_data: resources/grn-benchmark/perturbation_data.h5ad - layer: pearson - reg_type: ridge - method_id: 10-figr - subsample: -2 - max_workers: 10 - consensus: resources/prior/consensus-num-regulators.json - prediction: resources/grn_models/figr.csv - degree: 10 - noise_type: weight - - id: granie_10 - perturbation_data: resources/grn-benchmark/perturbation_data.h5ad - layer: pearson - reg_type: ridge - method_id: 10-granie - subsample: -2 - max_workers: 10 - consensus: resources/prior/consensus-num-regulators.json - prediction: resources/grn_models/granie.csv - degree: 10 - noise_type: weight - - id: scglue_10 - perturbation_data: resources/grn-benchmark/perturbation_data.h5ad - layer: pearson - reg_type: ridge - method_id: 10-scglue - subsample: -2 - max_workers: 10 - consensus: resources/prior/consensus-num-regulators.json - prediction: resources/grn_models/scglue.csv - degree: 10 - noise_type: weight - - id: collectri_20 - perturbation_data: resources/grn-benchmark/perturbation_data.h5ad - layer: pearson - reg_type: ridge - method_id: 20-collectri - subsample: -2 - max_workers: 10 - consensus: resources/prior/consensus-num-regulators.json - prediction: resources/grn_models/collectri.csv - degree: 20 - noise_type: weight - - id: celloracle_20 - perturbation_data: resources/grn-benchmark/perturbation_data.h5ad - layer: pearson - reg_type: ridge - method_id: 20-celloracle - subsample: -2 - max_workers: 10 - consensus: resources/prior/consensus-num-regulators.json - prediction: resources/grn_models/celloracle.csv - degree: 20 - noise_type: weight - - id: scenicplus_20 - perturbation_data: resources/grn-benchmark/perturbation_data.h5ad - layer: pearson - reg_type: ridge - method_id: 20-scenicplus - subsample: -2 - max_workers: 10 - consensus: resources/prior/consensus-num-regulators.json - prediction: resources/grn_models/scenicplus.csv - degree: 20 - noise_type: weight - - id: figr_20 - perturbation_data: resources/grn-benchmark/perturbation_data.h5ad - layer: pearson - reg_type: ridge - method_id: 20-figr - subsample: -2 - max_workers: 10 - consensus: resources/prior/consensus-num-regulators.json - prediction: resources/grn_models/figr.csv - degree: 20 - noise_type: weight - - id: granie_20 - perturbation_data: resources/grn-benchmark/perturbation_data.h5ad - layer: pearson - reg_type: ridge - method_id: 20-granie - subsample: -2 - max_workers: 10 - consensus: resources/prior/consensus-num-regulators.json - prediction: resources/grn_models/granie.csv - degree: 20 - noise_type: weight - - id: scglue_20 - perturbation_data: resources/grn-benchmark/perturbation_data.h5ad - layer: pearson - reg_type: ridge - method_id: 20-scglue - subsample: -2 - max_workers: 10 - consensus: resources/prior/consensus-num-regulators.json - prediction: resources/grn_models/scglue.csv - degree: 20 - noise_type: weight - - id: collectri_50 - perturbation_data: resources/grn-benchmark/perturbation_data.h5ad - layer: pearson - reg_type: ridge - method_id: 50-collectri - subsample: -2 - max_workers: 10 - consensus: resources/prior/consensus-num-regulators.json - prediction: resources/grn_models/collectri.csv - degree: 50 - noise_type: weight - - id: celloracle_50 - perturbation_data: resources/grn-benchmark/perturbation_data.h5ad - layer: pearson - reg_type: ridge - method_id: 50-celloracle - subsample: -2 - max_workers: 10 - consensus: resources/prior/consensus-num-regulators.json - prediction: resources/grn_models/celloracle.csv - degree: 50 - noise_type: weight - - id: scenicplus_50 - perturbation_data: resources/grn-benchmark/perturbation_data.h5ad - layer: pearson - reg_type: ridge - method_id: 50-scenicplus - subsample: -2 - max_workers: 10 - consensus: resources/prior/consensus-num-regulators.json - prediction: resources/grn_models/scenicplus.csv - degree: 50 - noise_type: weight - - id: figr_50 - perturbation_data: resources/grn-benchmark/perturbation_data.h5ad - layer: pearson - reg_type: ridge - method_id: 50-figr - subsample: -2 - max_workers: 10 - consensus: resources/prior/consensus-num-regulators.json - prediction: resources/grn_models/figr.csv - degree: 50 - noise_type: weight - - id: granie_50 - perturbation_data: resources/grn-benchmark/perturbation_data.h5ad - layer: pearson - reg_type: ridge - method_id: 50-granie - subsample: -2 - max_workers: 10 - consensus: resources/prior/consensus-num-regulators.json - prediction: resources/grn_models/granie.csv - degree: 50 - noise_type: weight - - id: scglue_50 - perturbation_data: resources/grn-benchmark/perturbation_data.h5ad - layer: pearson - reg_type: ridge - method_id: 50-scglue - subsample: -2 - max_workers: 10 - consensus: resources/prior/consensus-num-regulators.json - prediction: resources/grn_models/scglue.csv - degree: 50 - noise_type: weight - - id: collectri_100 - perturbation_data: resources/grn-benchmark/perturbation_data.h5ad - layer: pearson - reg_type: ridge - method_id: 100-collectri - subsample: -2 - max_workers: 10 - consensus: resources/prior/consensus-num-regulators.json - prediction: resources/grn_models/collectri.csv - degree: 100 - noise_type: weight - - id: celloracle_100 - perturbation_data: resources/grn-benchmark/perturbation_data.h5ad - layer: pearson - reg_type: ridge - method_id: 100-celloracle - subsample: -2 - max_workers: 10 - consensus: resources/prior/consensus-num-regulators.json - prediction: resources/grn_models/celloracle.csv - degree: 100 - noise_type: weight - - id: scenicplus_100 - perturbation_data: resources/grn-benchmark/perturbation_data.h5ad - layer: pearson - reg_type: ridge - method_id: 100-scenicplus - subsample: -2 - max_workers: 10 - consensus: resources/prior/consensus-num-regulators.json - prediction: resources/grn_models/scenicplus.csv - degree: 100 - noise_type: weight - - id: figr_100 - perturbation_data: resources/grn-benchmark/perturbation_data.h5ad - layer: pearson - reg_type: ridge - method_id: 100-figr - subsample: -2 - max_workers: 10 - consensus: resources/prior/consensus-num-regulators.json - prediction: resources/grn_models/figr.csv - degree: 100 - noise_type: weight - - id: granie_100 - perturbation_data: resources/grn-benchmark/perturbation_data.h5ad - layer: pearson - reg_type: ridge - method_id: 100-granie - subsample: -2 - max_workers: 10 - consensus: resources/prior/consensus-num-regulators.json - prediction: resources/grn_models/granie.csv - degree: 100 - noise_type: weight - - id: scglue_100 - perturbation_data: resources/grn-benchmark/perturbation_data.h5ad - layer: pearson - reg_type: ridge - method_id: 100-scglue - subsample: -2 - max_workers: 10 - consensus: resources/prior/consensus-num-regulators.json - prediction: resources/grn_models/scglue.csv - degree: 100 - noise_type: weight -output_state: "state.yaml" -publish_dir: "output/robust_analy_weight" diff --git a/params/repo/single_omics.yaml b/params/repo/single_omics.yaml deleted file mode 100644 index b8fd85294..000000000 --- a/params/repo/single_omics.yaml +++ /dev/null @@ -1,11 +0,0 @@ -param_list: - - id: ridge - perturbation_data: s3://openproblems-data/resources/grn/grn-benchmark/perturbation_data.h5ad - multiomics_rna: s3://openproblems-data/resources/grn/grn-benchmark/multiomics_rna.h5ad - reg_type: ridge - subsample: -2 - max_workers: 10 - consensus: s3://openproblems-data/resources/grn/prior/consensus-num-regulators.json - tf_all: s3://openproblems-data/resources/grn/prior/tf_all.csv -output_state: "state.yaml" -publish_dir: "s3://openproblems-data/resources/grn/results/single_omics" diff --git a/params/repo/single_omics_all_test.yaml b/params/repo/single_omics_all_test.yaml deleted file mode 100644 index 4e5e2f01f..000000000 --- a/params/repo/single_omics_all_test.yaml +++ /dev/null @@ -1,12 +0,0 @@ -param_list: - - id: ridge - perturbation_data: s3://openproblems-data/resources_test/grn/grn-benchmark/perturbation_data.h5ad - multiomics_rna: s3://openproblems-data/resources_test/grn/grn-benchmark/multiomics_rna.h5ad - reg_type: ridge - subsample: -2 - max_workers: 10 - layer: pearson - consensus: s3://openproblems-data/resources_test/grn/prior/consensus-num-regulators.json - tf_all: s3://openproblems-data/resources_test/grn/prior/tf_all.csv -output_state: "state.yaml" -publish_dir: "s3://openproblems-data/resources_test/grn/results/single_omics_all_test" diff --git a/params/single_omics_all.yaml b/params/single_omics_all.yaml deleted file mode 100644 index 52d200398..000000000 --- a/params/single_omics_all.yaml +++ /dev/null @@ -1,12 +0,0 @@ -param_list: - - id: ridge - perturbation_data: s3://openproblems-data/resources/grn/grn-benchmark/perturbation_data.h5ad - multiomics_rna: s3://openproblems-data/resources/grn/grn-benchmark/multiomics_rna.h5ad - reg_type: ridge - subsample: -2 - max_workers: 10 - layer: pearson - consensus: s3://openproblems-data/resources/grn/prior/consensus-num-regulators.json - tf_all: s3://openproblems-data/resources/grn/prior/tf_all.csv -output_state: "state.yaml" -publish_dir: "s3://openproblems-data/resources/grn/results/single_omics_all" diff --git a/runs.ipynb b/runs.ipynb index 112bf0105..ace7c58df 100644 --- a/runs.ipynb +++ b/runs.ipynb @@ -2152,12 +2152,435 @@ "subprocess.run(cmd, shell=True)" ] }, + { + "cell_type": "code", + "execution_count": 37, + "metadata": {}, + "outputs": [ + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/tmp/ipykernel_247612/1517971497.py:5: FutureWarning: The default of observed=False is deprecated and will be changed to True in a future version of pandas. Pass observed=False to retain current behavior or observed=True to adopt the future default and silence this warning.\n", + " adata_df.groupby(['cell_type','donor_id']).apply(lambda df: create_meta_cells(df) )\n", + "/tmp/ipykernel_247612/1517971497.py:5: DeprecationWarning: DataFrameGroupBy.apply operated on the grouping columns. This behavior is deprecated, and in a future version of pandas the grouping columns will be excluded from the operation. Either pass `include_groups=False` to exclude the groupings or explicitly select the grouping columns after groupby to silence this warning.\n", + " adata_df.groupby(['cell_type','donor_id']).apply(lambda df: create_meta_cells(df) )\n" + ] + }, + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
locationAL627309.1AL627309.5AL627309.4LINC01409LINC01128LINC00115FAM41CAL645608.6SAMD11NOC2L...AC145212.1MAFIPAC011043.1AL354822.1AL592183.1AC240274.1AC004556.3AC007325.4cell_typedonor_id
cell_typedonor_id
\n", + "

0 rows × 22789 columns

\n", + "
" + ], + "text/plain": [ + "Empty DataFrame\n", + "Columns: [AL627309.1, AL627309.5, AL627309.4, LINC01409, LINC01128, LINC00115, FAM41C, AL645608.6, SAMD11, NOC2L, KLHL17, PLEKHN1, HES4, ISG15, AL645608.1, AGRN, C1orf159, AL390719.3, LINC01342, TTLL10, TNFRSF18, TNFRSF4, SDF4, B3GALT6, C1QTNF12, UBE2J2, LINC01786, SCNN1D, ACAP3, PUSL1, INTS11, CPTP, TAS1R3, DVL1, MXRA8, AURKAIP1, CCNL2, MRPL20-AS1, MRPL20, AL391244.2, ATAD3C, ATAD3B, ATAD3A, TMEM240, SSU72, AL645728.1, FNDC10, AL691432.4, AL691432.2, MIB2, MMP23B, CDK11B, FO704657.1, SLC35E2B, CDK11A, SLC35E2A, NADK, GNB1, AL109917.1, CFAP74, PRKCZ, AL590822.2, PRKCZ-AS1, FAAP20, AL590822.1, SKI, AL590822.3, MORN1, AL513477.2, RER1, PEX10, PLCH2, PANK4, AL139246.5, TNFRSF14-AS1, TNFRSF14, AL139246.3, PRXL2B, MMEL1, TTC34, PRDM16, MEGF6, AL513320.1, TPRG1L, WRAP73, TP73, CCDC27, SMIM1, LRRC47, CEP104, DFFB, C1orf174, LINC01134, AL805961.1, AJAP1, AL365255.1, NPHP4, KCNAB2, CHD5, RPL22, ...]\n", + "Index: []\n", + "\n", + "[0 rows x 22789 columns]" + ] + }, + "execution_count": 37, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "def create_meta_cells(df, n_cells=15):\n", + " meta_x = []\n", + " for i in range(0, df.shape[0], n_cells):\n", + " meta_x.append(df.iloc[i:n_cells, :].sum(axis=0))\n", + " \n", + "adata_df = pd.DataFrame(multiomics_rna.X, columns=multiomics_rna.var_names)\n", + "adata_df[['cell_type','donor_id']] = multiomics_rna.obs[['cell_type', 'donor_id']]\n", + "adata_df.groupby(['cell_type','donor_id']).apply(lambda df: create_meta_cells(df))" + ] + }, + { + "cell_type": "code", + "execution_count": 34, + "metadata": {}, + "outputs": [ + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/tmp/ipykernel_247612/3262953603.py:17: FutureWarning: The default of observed=False is deprecated and will be changed to True in a future version of pandas. Pass observed=False to retain current behavior or observed=True to adopt the future default and silence this warning.\n", + " groups = adata.obs.groupby([cell_type_col, donor_id_col])\n" + ] + }, + { + "ename": "ValueError", + "evalue": "invalid literal for int() with base 10: 'GTCTTTAGTTAGTGAT-3'", + "output_type": "error", + "traceback": [ + "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m", + "\u001b[0;31mValueError\u001b[0m Traceback (most recent call last)", + "Cell \u001b[0;32mIn[34], line 53\u001b[0m\n\u001b[1;32m 49\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m meta_adata\n\u001b[1;32m 51\u001b[0m \u001b[38;5;66;03m# Usage\u001b[39;00m\n\u001b[1;32m 52\u001b[0m \u001b[38;5;66;03m# Assuming you already have an AnnData object 'adata' with cell_type and donor_id in 'obs'\u001b[39;00m\n\u001b[0;32m---> 53\u001b[0m meta_adata \u001b[38;5;241m=\u001b[39m \u001b[43mcreate_meta_cells\u001b[49m\u001b[43m(\u001b[49m\u001b[43mmultiomics_rna\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mcell_type_col\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;124;43m'\u001b[39;49m\u001b[38;5;124;43mcell_type\u001b[39;49m\u001b[38;5;124;43m'\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mdonor_id_col\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;124;43m'\u001b[39;49m\u001b[38;5;124;43mdonor_id\u001b[39;49m\u001b[38;5;124;43m'\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mn_cells\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;241;43m15\u001b[39;49m\u001b[43m)\u001b[49m\n", + "Cell \u001b[0;32mIn[34], line 22\u001b[0m, in \u001b[0;36mcreate_meta_cells\u001b[0;34m(adata, cell_type_col, donor_id_col, n_cells)\u001b[0m\n\u001b[1;32m 19\u001b[0m \u001b[38;5;66;03m# For each group (cell_type, donor_id combination)\u001b[39;00m\n\u001b[1;32m 20\u001b[0m \u001b[38;5;28;01mfor\u001b[39;00m (cell_type, donor_id), indices \u001b[38;5;129;01min\u001b[39;00m groups\u001b[38;5;241m.\u001b[39mgroups\u001b[38;5;241m.\u001b[39mitems():\n\u001b[1;32m 21\u001b[0m \u001b[38;5;66;03m# Convert indices to a numpy array of integers\u001b[39;00m\n\u001b[0;32m---> 22\u001b[0m cell_indices \u001b[38;5;241m=\u001b[39m \u001b[43mnp\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43marray\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;28;43mlist\u001b[39;49m\u001b[43m(\u001b[49m\u001b[43mindices\u001b[49m\u001b[43m)\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mdtype\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;28;43mint\u001b[39;49m\u001b[43m)\u001b[49m\n\u001b[1;32m 24\u001b[0m \u001b[38;5;66;03m# Filter indices to ensure they are within bounds\u001b[39;00m\n\u001b[1;32m 25\u001b[0m cell_indices \u001b[38;5;241m=\u001b[39m cell_indices[cell_indices \u001b[38;5;241m<\u001b[39m n_cells_in_adata]\n", + "\u001b[0;31mValueError\u001b[0m: invalid literal for int() with base 10: 'GTCTTTAGTTAGTGAT-3'" + ] + } + ], + "source": [ + "import numpy as np\n", + "import pandas as pd\n", + "import scanpy as sc\n", + "\n", + "def create_meta_cells(adata, cell_type_col='cell_type', donor_id_col='donor_id', n_cells=15):\n", + " # Initialize lists to store the meta cell data\n", + " meta_cell_data = []\n", + " meta_cell_obs = []\n", + "\n", + " # Get the raw counts matrix from the AnnData object\n", + " raw_counts = adata.X\n", + "\n", + " # Get the total number of rows in raw_counts\n", + " n_cells_in_adata = raw_counts.shape[0]\n", + "\n", + " # Group by cell_type and donor_id\n", + " groups = adata.obs.groupby([cell_type_col, donor_id_col])\n", + "\n", + " # For each group (cell_type, donor_id combination)\n", + " for (cell_type, donor_id), indices in groups.groups.items():\n", + " # Convert indices to a numpy array of integers\n", + " cell_indices = np.array(list(indices), dtype=int)\n", + "\n", + " # Filter indices to ensure they are within bounds\n", + " cell_indices = cell_indices[cell_indices < n_cells_in_adata]\n", + "\n", + " # Process in chunks of 'n_cells' (15)\n", + " for i in range(0, len(cell_indices), n_cells):\n", + " meta_cell_indices = cell_indices[i:i + n_cells]\n", + " \n", + " # Sum the raw counts for the meta cell\n", + " meta_cell_counts = raw_counts[meta_cell_indices].sum(axis=0)\n", + "\n", + " # Create observation data for the meta cell\n", + " meta_cell_obs.append({\n", + " cell_type_col: cell_type,\n", + " donor_id_col: donor_id\n", + " })\n", + " \n", + " # Append the meta cell data\n", + " meta_cell_data.append(meta_cell_counts)\n", + "\n", + " # Create a new AnnData object for the meta cells\n", + " meta_cell_data = np.array(meta_cell_data)\n", + " meta_cell_obs = pd.DataFrame(meta_cell_obs)\n", + "\n", + " meta_adata = sc.AnnData(X=meta_cell_data, obs=meta_cell_obs)\n", + "\n", + " return meta_adata\n", + "\n", + "# Usage\n", + "# Assuming you already have an AnnData object 'adata' with cell_type and donor_id in 'obs'\n", + "meta_adata = create_meta_cells(multiomics_rna, cell_type_col='cell_type', donor_id_col='donor_id', n_cells=15)\n" + ] + }, + { + "cell_type": "code", + "execution_count": 30, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "AnnData object with n_obs × n_vars = 25551 × 22787\n", + " obs: 'cell_type', 'donor_id'\n", + " var: 'gene_ids', 'interval', 'mean', 'std'\n", + " uns: 'log1p'" + ] + }, + "execution_count": 30, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [] + }, + { + "cell_type": "code", + "execution_count": 1, + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Read data\n", + "Noramlize data\n" + ] + } + ], + "source": [ + "import os\n", + "import pandas as pd\n", + "import numpy as np\n", + "import anndata as ad\n", + "import scanpy as sc\n", + "from tqdm import tqdm\n", + "from scipy.stats import spearmanr\n", + "\n", + "## VIASH START\n", + "par = {\n", + " \"multiomics_rna\": \"resources/grn-benchmark/multiomics_rna.h5ad\",\n", + " \"tf_all\": \"resources_test/prior/tf_all.csv\",\n", + " \"corr_method\": \"spearman\"\n", + "}\n", + "## VIASH END\n", + "print('Read data')\n", + "multiomics_rna = ad.read_h5ad(par[\"multiomics_rna\"])\n", + "gene_names = multiomics_rna.var_names.to_numpy()\n", + "tf_all = np.loadtxt(par['tf_all'], dtype=str)\n", + "tf_all = np.intersect1d(tf_all, gene_names)\n", + "groups = multiomics_rna.obs.cell_type\n", + "print('Noramlize data')\n", + "sc.pp.normalize_total(multiomics_rna)\n", + "sc.pp.log1p(multiomics_rna)\n", + "sc.pp.scale(multiomics_rna)" + ] + }, + { + "cell_type": "code", + "execution_count": 2, + "metadata": {}, + "outputs": [ + { + "name": "stderr", + "output_type": "stream", + "text": [ + "Processing groups: 0%| | 0/4 [00:00 15\u001b[0m \u001b[43maa\u001b[49m\n\u001b[1;32m 16\u001b[0m \u001b[38;5;66;03m# grn = X_sub.T.dot(X_sub)\u001b[39;00m\n\u001b[1;32m 17\u001b[0m \u001b[38;5;66;03m# grn = grn/stds\u001b[39;00m\n\u001b[1;32m 18\u001b[0m grn\n", + "\u001b[0;31mNameError\u001b[0m: name 'aa' is not defined" + ] + } + ], + "source": [ + "X = multiomics_rna.X\n", + "for group in tqdm(np.unique(groups), desc=\"Processing groups\"):\n", + " mask_group = groups == group\n", + " X_sub = X[mask_group, :]\n", + " # stds = np.std(X_sub, axis=0)\n", + " # mask_g = stds != 0\n", + " # stds = stds[mask_g]\n", + " # X_sub = X_sub[:, mask_g]\n", + " # g_names = gene_names[mask_g]\n", + " \n", + " # grn = X_sub.T.dot(X_sub)/np.std(X_sub, axis=0)\n", + " grn = np.corrcoef(X_sub, rowvar=False)\n", + " # grn = np.nan_to_num(grn, nan=0.0, posinf=0.0, neginf=0.0)\n", + " print(grn)\n", + " aa\n", + " # grn = X_sub.T.dot(X_sub)\n", + " # grn = grn/stds\n", + "grn" + ] + }, + { + "cell_type": "code", + "execution_count": 34, + "metadata": {}, + "outputs": [ + { + "name": "stderr", + "output_type": "stream", + "text": [ + "Processing groups: 0%| | 0/4 [00:00 25\u001b[0m net \u001b[38;5;241m=\u001b[39m \u001b[43mcreate_corr_net\u001b[49m\u001b[43m(\u001b[49m\u001b[43mmultiomics_rna\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mX\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mgroups\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mpar\u001b[49m\u001b[43m[\u001b[49m\u001b[38;5;124;43m'\u001b[39;49m\u001b[38;5;124;43mcorr_method\u001b[39;49m\u001b[38;5;124;43m'\u001b[39;49m\u001b[43m]\u001b[49m\u001b[43m)\u001b[49m\n", + "Cell \u001b[0;32mIn[34], line 22\u001b[0m, in \u001b[0;36mcreate_corr_net\u001b[0;34m(X, groups, method)\u001b[0m\n\u001b[1;32m 20\u001b[0m grn \u001b[38;5;241m=\u001b[39m spearmanr(X_sub)\u001b[38;5;241m.\u001b[39mstatistic\n\u001b[1;32m 21\u001b[0m \u001b[38;5;28mprint\u001b[39m(grn)\n\u001b[0;32m---> 22\u001b[0m \u001b[43maa\u001b[49m \n\u001b[1;32m 23\u001b[0m grns\u001b[38;5;241m.\u001b[39mappend(grn)\n\u001b[1;32m 24\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m np\u001b[38;5;241m.\u001b[39mmean(grns, axis\u001b[38;5;241m=\u001b[39m\u001b[38;5;241m0\u001b[39m)\n", + "\u001b[0;31mNameError\u001b[0m: name 'aa' is not defined" + ] + } + ], + "source": [ + "from scipy.stats import pearsonr\n", + "\n", + "def create_corr_net(X: np.ndarray, groups: np.ndarray, method=\"pearson\"):\n", + " grns = []\n", + " for group in tqdm(np.unique(groups), desc=\"Processing groups\"):\n", + " mask_group = groups == group\n", + " X_sub = X[mask_group, :]\n", + " stds = np.std(X_sub, axis=0)\n", + " mask_g = stds != 0\n", + " stds = stds[mask_g]\n", + " X_sub = X_sub[:, mask_g]\n", + " g_names = gene_names[mask_g]\n", + " if method == \"pearson\":\n", + " # grn = np.corrcoef(X_sub.T)\n", + " grn = X_sub.T.dot(X_sub)\n", + " grn = grn/stds\n", + "\n", + " elif method == \"spearman\":\n", + " grn = spearmanr(X_sub).statistic\n", + "\n", + " grns.append(grn)\n", + " return np.mean(grns, axis=0)\n", + "net = create_corr_net(multiomics_rna.X, groups, par['corr_method'])" + ] + }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], - "source": [] + "source": [ + "\n", + "\n", + "print('Read data')\n", + "\n", + "\n", + "print('Create corr net')\n", + "\n", + "net = pd.DataFrame(net, index=gene_names, columns=gene_names)\n", + "\n", + "if par['causal']:\n", + " net = net[tf_all]\n", + "else:\n", + " net = net.sample(len(tf_all), axis=1, random_state=par['seed'])\n", + " \n", + "net = net.reset_index().melt(id_vars='index', var_name='source', value_name='weight')\n", + "net.rename(columns={'index': 'target'}, inplace=True)\n", + "\n", + "\n", + "print('Output GRN')\n", + "net.to_csv(par['prediction'])\n" + ] }, { "cell_type": "markdown", diff --git a/scripts/add_a_method.sh b/scripts/add_a_method.sh old mode 100755 new mode 100644 diff --git a/scripts/download_resources.sh b/scripts/download_resources.sh old mode 100755 new mode 100644 diff --git a/scripts/download_resources_test.sh b/scripts/download_resources_test.sh old mode 100755 new mode 100644 diff --git a/scripts/render_readme.sh b/scripts/render_readme.sh old mode 100755 new mode 100644 diff --git a/scripts/run_benchmark_single_omics.sh b/scripts/run_benchmark_single_omics.sh old mode 100755 new mode 100644 diff --git a/scripts/run_grn_evaluation.sh b/scripts/run_grn_evaluation.sh old mode 100755 new mode 100644 index 0d7f4dc70..528b5d27a --- a/scripts/run_grn_evaluation.sh +++ b/scripts/run_grn_evaluation.sh @@ -5,15 +5,15 @@ reg_type=ridge RUN_ID="grn_evaluation_so_all_${reg_type}" -resources_dir="s3://openproblems-data/resources/grn" -# resources_dir="./resources" +# resources_dir="s3://openproblems-data/resources/grn" +resources_dir="./resources" publish_dir="${resources_dir}/results/${RUN_ID}" grn_models_folder="${resources_dir}/grn_models" subsample=-2 max_workers=10 layer=scgen_pearson -metric_ids="[regression_1, regression_2]" +metric_ids="[regression_1]" param_file="./params/${RUN_ID}.yaml" @@ -51,11 +51,6 @@ append_entry() { HERE } -#Loop through grn_names and layers -for grn_name in "${grn_names[@]}"; do - append_entry "$grn_name" -done - append_entry_control() { cat >> $param_file << HERE - id: ${reg_type}_${1} @@ -70,13 +65,33 @@ append_entry_control() { layer: ${layer} consensus: ${resources_dir}/prior/consensus-num-regulators.json causal: ${2} + corr_method: ${3} + prediction: ${resources_dir}/grn_models/collectri.csv HERE + if [ -n "$4" ]; then + echo " cell_type_specific: ${4}" >> $param_file + fi + if [ -n "$5" ]; then + echo " metacell: ${5}" >> $param_file + fi } -# controls -append_entry_control "negative_control" "False" -append_entry_control "positive_control" "False" -append_entry_control "baseline_corr_causal" "True" -append_entry_control "baseline_corr" "False" + +# #Loop through grn_names and layers +# for grn_name in "${grn_names[@]}"; do +# append_entry "$grn_name" +# done + +## controls +# append_entry_control "negative_control" "False" "" +# append_entry_control "positive_control" "False" "" +# append_entry_control "baseline_pearson" "False" "pearson" +# append_entry_control "baseline_dotproduct" "False" "dotproduct" +append_entry_control "baseline_pearson_causal" "True" "pearson" +append_entry_control "baseline_dotproduct_causal" "True" "dotproduct" +append_entry_control "baseline_dotproduct_causal_cell_type" "True" "dotproduct" "true" +append_entry_control "baseline_dotproduct_causal_metacell" "True" "dotproduct" "false" "true" +# append_entry_control "baseline_corr_causal_spearman" "True" "spearman" + # Append the remaining output_state and publish_dir to the YAML file cat >> $param_file << HERE @@ -84,12 +99,12 @@ output_state: "state.yaml" publish_dir: "$publish_dir" HERE -# nextflow run . \ -# -main-script target/nextflow/workflows/run_grn_evaluation/main.nf \ -# -profile docker \ -# -with-trace \ -# -c src/common/nextflow_helpers/labels_ci.config \ -# -params-file ${param_file} +nextflow run . \ + -main-script target/nextflow/workflows/run_grn_evaluation/main.nf \ + -profile docker \ + -with-trace \ + -c src/common/nextflow_helpers/labels_ci.config \ + -params-file ${param_file} # ./tw-windows-x86_64.exe launch ` # https://github.com/openproblems-bio/task_grn_inference.git ` diff --git a/scripts/run_pc_vs_nc.sh b/scripts/run_pc_vs_nc.sh old mode 100755 new mode 100644 diff --git a/scripts/run_process_perturbation_tw.sh b/scripts/run_process_perturbation_tw.sh old mode 100755 new mode 100644 diff --git a/scripts/run_robust_analys.sh b/scripts/run_robust_analys.sh old mode 100755 new mode 100644 diff --git a/scripts/run_robust_analys_causal.sh b/scripts/run_robust_analys_causal.sh old mode 100755 new mode 100644 diff --git a/scripts/upload_resources.sh b/scripts/upload_resources.sh old mode 100755 new mode 100644 diff --git a/src/api/comp_control_method.yaml b/src/api/comp_control_method.yaml index e1d18734d..4e409d910 100644 --- a/src/api/comp_control_method.yaml +++ b/src/api/comp_control_method.yaml @@ -19,6 +19,11 @@ functionality: __merge__: file_prediction.yaml required: false direction: output + - name: --tf_all + type: file + required: true + direction: input + example: resources_test/prior/tf_all.csv diff --git a/src/api/task_info.yaml b/src/api/task_info.yaml index 11bfe8d53..2b928f650 100644 --- a/src/api/task_info.yaml +++ b/src/api/task_info.yaml @@ -11,7 +11,7 @@ description: | summary: | Benchmarking GRN inference methods - The full documentation is hosted on [ReadTheDocs](https://openproblems-grn-task.readthedocs.io/en/latest/index.html). [![Documentation Status](https://readthedocs.org/projects/grn-inference-benchmarking/badge/?version=latest)](https://grn-inference-benchmarking.readthedocs.io/en/latest/?badge=latest) + The full documentation is hosted on [ReadTheDocs](https://grn-inference-benchmarking.readthedocs.io/en/latest/index.html). readme: | ## Installation diff --git a/src/control_methods/baseline_corr/config.vsh.yaml b/src/control_methods/baseline_corr/config.vsh.yaml index 789c4ba28..34a8334b3 100644 --- a/src/control_methods/baseline_corr/config.vsh.yaml +++ b/src/control_methods/baseline_corr/config.vsh.yaml @@ -16,15 +16,25 @@ functionality: direction: input - name: --multiomics_rna type: file - required: false + required: true direction: input example: resources_test/grn-benchmark/multiomics_rna.h5ad - - name: --tf_all - type: file + - name: --corr_method + type: string required: false direction: input - example: resources_test/prior/tf_all.csv - default: resources/prior/tf_all.csv + default: dotproduct + description: corr method. + - name: --cell_type_specific + type: boolean + direction: input + default: false + description: whether to result cell type specific grn. if not, the mean of weights are taken + - name: --metacell + type: boolean + direction: input + default: false + description: whether to pseudobulk scRNA-seq with metacells resources: - type: python_script path: script.py diff --git a/src/control_methods/baseline_corr/script.py b/src/control_methods/baseline_corr/script.py index fb5958235..3011475d0 100644 --- a/src/control_methods/baseline_corr/script.py +++ b/src/control_methods/baseline_corr/script.py @@ -11,19 +11,56 @@ } ## VIASH END def create_corr_net(X: np.ndarray, groups: np.ndarray, method="pearson"): - grns = [] + grn = pd.DataFrame() for group in tqdm(np.unique(groups), desc="Processing groups"): X_sub = X[groups == group, :] - if method is "pearson": - grn = np.corrcoef(X_sub.T) - elif method is "spearman": - grn = spearmanr(X_sub).statistic - grns.append(grn) - return np.mean(grns, axis=0) + if method == "dotproduct": + net = X_sub.T.dot(X_sub) + elif method == "pearson": + net = np.corrcoef(X_sub.T) + elif method == "spearman": + net = spearmanr(X_sub).statistic + net = np.nan_to_num(net, nan=0.0, posinf=0.0, neginf=0.0) + + net = pd.DataFrame(net, index=gene_names, columns=gene_names) + if par['causal']: + net = net[tf_all] + else: + net = net.sample(len(tf_all), axis=1, random_state=par['seed']) + + net = net.reset_index().melt(id_vars='index', var_name='source', value_name='weight') + net.rename(columns={'index': 'target'}, inplace=True) + + net['cell_type'] = group + + grn = pd.concat([grn, net], axis=0).reset_index(drop=True) + + if par['cell_type_specific']==False: + print('Non specific') + grn.drop(columns=['cell_type'], inplace=True) + grn = grn.groupby(['source', 'target']).mean().reset_index() + print(grn) + return grn print('Read data') multiomics_rna = ad.read_h5ad(par["multiomics_rna"]) -# print('subsetting: remove this') -# multiomics_rna = multiomics_rna[:5000, :5000] +# multiomics_rna = multiomics_rna[:,:2000] #TODO: togo +if par['metacell']: + def create_meta_cells(df, n_cells=15): + meta_x = [] + for i in range(0, df.shape[0], n_cells): + meta_x.append(df.iloc[i:i+n_cells, :].sum(axis=0).values) + df = pd.DataFrame(meta_x, columns=df.columns) + return df + + adata_df = pd.DataFrame(multiomics_rna.X.todense(), columns=multiomics_rna.var_names) + adata_df['cell_type'] = multiomics_rna.obs['cell_type'].values + adata_df['donor_id'] = multiomics_rna.obs['donor_id'].values + df = adata_df.groupby(['cell_type','donor_id']).apply(lambda df: create_meta_cells(df)) + X = df.values + var = pd.DataFrame(index=df.columns) + obs = df.reset_index()[['cell_type','donor_id']] + multiomics_rna = ad.AnnData(X=X, obs=obs, var=var) + gene_names = multiomics_rna.var_names.to_numpy() tf_all = np.loadtxt(par['tf_all'], dtype=str) groups = multiomics_rna.obs.cell_type @@ -35,16 +72,9 @@ def create_corr_net(X: np.ndarray, groups: np.ndarray, method="pearson"): sc.pp.scale(multiomics_rna) print('Create corr net') -net = create_corr_net(multiomics_rna.X, groups) -net = pd.DataFrame(net, index=gene_names, columns=gene_names) - -if par['causal']: - net = net[tf_all] -else: - net = net.sample(len(tf_all), axis=1, random_state=par['seed']) - -net = net.reset_index().melt(id_vars='index', var_name='source', value_name='weight') -net.rename(columns={'index': 'target'}, inplace=True) +net = create_corr_net(multiomics_rna.X, groups, par['corr_method']) + + print('Output GRN') diff --git a/src/control_methods/positive_control/config.vsh.yaml b/src/control_methods/positive_control/config.vsh.yaml index 3366d82dd..4add99379 100644 --- a/src/control_methods/positive_control/config.vsh.yaml +++ b/src/control_methods/positive_control/config.vsh.yaml @@ -12,12 +12,6 @@ functionality: required: false direction: input default: resources/grn-benchmark/perturbation_data.h5ad - - name: --tf_all - type: file - required: false - direction: input - example: resources_test/prior/tf_all.csv - default: resources/prior/tf_all.csv resources: - type: python_script diff --git a/src/metrics/regression_1/main.py b/src/metrics/regression_1/main.py index 377a425ea..974da30a0 100644 --- a/src/metrics/regression_1/main.py +++ b/src/metrics/regression_1/main.py @@ -51,45 +51,29 @@ def cv_5(genes_n): np.random.shuffle(groups) return groups - -def regression_1( - net: pd.DataFrame, - train_df: pd.DataFrame, - reg_type: str = 'GB', - exclude_missing_genes: bool = False, - verbose: int = 0, - max_workers: int = 4) -> None: - """ - net: a df with index as genes and columns as tfs - train_df: a df with index as genes and columns as samples - """ - gene_names = train_df.index.to_numpy() - gene_names_grn = net.index.to_numpy() - # determine regressor - if reg_type=='ridge': - regr = Ridge(**dict(random_state=32)) - elif reg_type=='GB': - params = dict(random_state=32, - n_estimators=100, min_samples_leaf=2, min_child_samples=1, - feature_fraction=0.05, verbosity=-1 - ) - regr = lightgbm_wrapper(params, max_workers=max_workers) - elif reg_type=='RF': - params = dict(boosting_type='rf',random_state=32, n_estimators=100, - feature_fraction=0.05, verbosity=-1) - regr = lightgbm_wrapper(params, max_workers) +def cross_validation(net, prturb_adata, par:dict): + gene_names = prturb_adata.var_names + net = process_net(net.copy(), gene_names) + net_subset = net.copy() + # Subset TFs + if par['tf_n'] == -1: + degrees = net.abs().sum(axis=0) + net = net.loc[:, degrees >= degrees.quantile((1 - par['theta']))] else: - print(f'{reg_type} is not defined') - raise ValueError("define first") + degrees = net.abs().sum(axis=0) + net = net[degrees.nlargest(tf_n).index] + + gene_names_grn = net.index.to_numpy() n_tfs = net.shape[1] # construct feature and target space - if exclude_missing_genes: + if par['exclude_missing_genes']: included_genes = gene_names_grn else: included_genes = gene_names X_df = pd.DataFrame(np.zeros((len(included_genes), n_tfs)), index=included_genes) + train_df = pd.DataFrame(prturb_adata.X, columns=gene_names).T Y_df = train_df.loc[included_genes,:] mask_shared_genes = X_df.index.isin(net.index) @@ -111,18 +95,64 @@ def regression_1( y_true = Y.copy() unique_groups = np.unique(groups) + + # determine regressor + reg_type = par['reg_type'] + if reg_type=='ridge': + regr = Ridge(**dict(random_state=32)) + elif reg_type=='GB': + params = dict(random_state=32, + n_estimators=100, min_samples_leaf=2, min_child_samples=1, + feature_fraction=0.05, verbosity=-1 + ) + regr = lightgbm_wrapper(params, max_workers=max_workers) + elif reg_type=='RF': + params = dict(boosting_type='rf',random_state=32, n_estimators=100, + feature_fraction=0.05, verbosity=-1) + regr = lightgbm_wrapper(params, max_workers) + else: + print(f'{reg_type} is not defined') + raise ValueError("define first") for group in tqdm(unique_groups, desc="Processing groups"): mask_va = groups == group mask_tr = ~mask_va - # Use logical AND to combine masks correctly X_tr = X[mask_tr & mask_shared_genes, :] Y_tr = Y[mask_tr & mask_shared_genes, :] - regr.fit(X_tr, Y_tr) y_pred[mask_va & mask_shared_genes, :] = regr.predict(X[mask_va & mask_shared_genes, :]) + return y_true, y_pred - mean_score_r2 = r2_score(y_true, y_pred, multioutput='variance_weighted') #uniform_average', 'variance_weighted +def regression_1( + net: pd.DataFrame, + prturb_adata: ad.AnnData, + par:dict, + verbose: int = 0, + max_workers: int = 4) -> None: + """ + net: a df with index as genes and columns as tfs + prturb_adata: a adata + """ + + gene_names = prturb_adata.var_names + cell_types = prturb_adata.obs.cell_type.unique() + score_list = [] + for cell_type in cell_types: + print(f'----cross validate for {cell_type}----') + # check if net is cell type specific + if 'cell_type' in net.columns: + if cell_type not in net.cell_type.unique(): + raise ValueError(f'{cell_type} is not present in grn.') + net_sub = net[net.cell_type==cell_type] + else: + net_sub = net + + prturb_adata_sub = prturb_adata[prturb_adata.obs.cell_type==cell_type,:] + y_true_sub, y_pred_sub = cross_validation(net_sub, prturb_adata_sub, par) + + score = r2_score(y_true_sub, y_pred_sub, multioutput='variance_weighted') + score_list.append(score) + mean_score_r2 = np.mean(score_list) output = dict(mean_score_r2=mean_score_r2) return output @@ -146,23 +176,20 @@ def degree_centrality(net, source='source', target='target', normalize=False): return counts -def process_net(net, gene_names, manipulate): +def process_net(net, gene_names): # Remove self-regulations net = net[net['source'] != net['target']] # pivot net = pivot_grn(net) # subset net = net[net.index.isin(gene_names)] - # sign or shuffle - if manipulate=='signed': - net = net.map(lambda x: 1 if x>0 else (-1 if x<0 else 0)) return net def main(par): random_state = 42 set_global_seed(random_state) - theta = 1 # no subsetting based on theta + par['theta'] = 1 # no subsetting based on theta manipulate = None ## read and process input data @@ -178,7 +205,6 @@ def main(par): net = net[net.source.isin(tf_all)] subsample = par['subsample'] - reg_type = par['reg_type'] max_workers = par['max_workers'] layer = par["layer"] if subsample == -1: @@ -200,12 +226,10 @@ def main(par): perturbation_data = perturbation_data[np.random.choice(perturbation_data.n_obs, subsample, replace=False), :] print(perturbation_data.shape) + + perturbation_data.X = perturbation_data.layers[layer] - pert_df = pd.DataFrame(perturbation_data.layers[layer], columns=gene_names) - pert_df = pert_df.T # make it gene*sample - - # process net - net_processed = process_net(net.copy(), gene_names, manipulate) + print(f'Compute metrics for layer: {layer}', flush=True) tfs_cases = [-1] @@ -214,21 +238,12 @@ def main(par): layer_results = {} # Store results for this layer for exclude_missing_genes in [False, True]: # two settings on target gene for tf_n in tfs_cases: # two settings on tfs + par['exclude_missing_genes'] = exclude_missing_genes + par['tf_n'] = tf_n run_key = f'ex({exclude_missing_genes})_tf({tf_n})' print(run_key) - net_subset = net_processed.copy() - # Subset TFs - if tf_n == -1: - degrees = net_subset.abs().sum(axis=0) - net_subset = net_subset.loc[:, degrees >= degrees.quantile((1 - theta))] - else: - if tf_n > net_subset.shape[1]: - print(f'Skip running because tf_n ({tf_n}) is bigger than net.shape[1] ({net_subset.shape[1]})') - continue - degrees = net_subset.abs().sum(axis=0) - net_subset = net_subset[degrees.nlargest(tf_n).index] - - output = regression_1(net_subset, pert_df, exclude_missing_genes=exclude_missing_genes, reg_type=reg_type, max_workers=max_workers) + + output = regression_1(net, perturbation_data, par=par, max_workers=max_workers) layer_results[run_key] = [output['mean_score_r2']] diff --git a/src/metrics/regression_2/main.py b/src/metrics/regression_2/main.py index bd98a6f52..225a37ae0 100644 --- a/src/metrics/regression_2/main.py +++ b/src/metrics/regression_2/main.py @@ -277,6 +277,10 @@ def main(par: Dict[str, Any]) -> pd.DataFrame: # Load inferred GRN print(f'Loading GRN', flush=True) grn = load_grn(par['prediction'], gene_names) + if 'cell_type' in grn.columns: + print('Non specific') + grn.drop(columns=['cell_type'], inplace=True) + grn = grn.groupby(['source', 'target']).mean().reset_index() # Load and standardize perturbation data layer = par['layer'] diff --git a/src/workflows/run_grn_evaluation/config.vsh.yaml b/src/workflows/run_grn_evaluation/config.vsh.yaml index 38250919b..2f859110c 100644 --- a/src/workflows/run_grn_evaluation/config.vsh.yaml +++ b/src/workflows/run_grn_evaluation/config.vsh.yaml @@ -53,6 +53,21 @@ functionality: type: boolean required: false direction: input + - name: --corr_method + type: string + required: false + direction: input + default: pearson + - name: --cell_type_specific + type: boolean + required: false + direction: input + default: false + - name: --metacell + type: boolean + required: false + direction: input + default: false - name: Outputs arguments: diff --git a/src/workflows/run_grn_evaluation/main.nf b/src/workflows/run_grn_evaluation/main.nf index 99d639893..4339c2093 100644 --- a/src/workflows/run_grn_evaluation/main.nf +++ b/src/workflows/run_grn_evaluation/main.nf @@ -44,13 +44,84 @@ workflow run_wf { | baseline_corr.run( runIf: { id, state -> - state.method_id == 'baseline_corr_causal' + state.method_id == 'baseline_pearson_causal' }, fromState: [ multiomics_rna: "multiomics_rna", layer: "layer", tf_all: "tf_all", causal: "causal", + corr_method: "corr_method" + ], + toState: {id, output, state -> + state + [ + prediction: output.prediction + ] + } + ) + | baseline_corr.run( + runIf: { id, state -> + state.method_id == 'baseline_dotproduct_causal' + }, + fromState: [ + multiomics_rna: "multiomics_rna", + layer: "layer", + tf_all: "tf_all", + causal: "causal", + corr_method: "corr_method" + ], + toState: {id, output, state -> + state + [ + prediction: output.prediction + ] + } + ) + | baseline_corr.run( + runIf: { id, state -> + state.method_id == 'baseline_dotproduct_causal_cell_type' + }, + fromState: [ + multiomics_rna: "multiomics_rna", + layer: "layer", + tf_all: "tf_all", + causal: "causal", + corr_method: "corr_method", + cell_type_specific: "cell_type_specific" + ], + toState: {id, output, state -> + state + [ + prediction: output.prediction + ] + } + ) + | baseline_corr.run( + runIf: { id, state -> + state.method_id == 'baseline_dotproduct_causal_metacell' + }, + fromState: [ + multiomics_rna: "multiomics_rna", + layer: "layer", + tf_all: "tf_all", + causal: "causal", + corr_method: "corr_method", + metacell: "metacell" + ], + toState: {id, output, state -> + state + [ + prediction: output.prediction + ] + } + ) + | baseline_corr.run( + runIf: { id, state -> + state.method_id == 'baseline_corr_causal_spearman' + }, + fromState: [ + multiomics_rna: "multiomics_rna", + layer: "layer", + tf_all: "tf_all", + causal: "causal", + corr_method: "corr_method" ], toState: {id, output, state -> state + [ @@ -81,7 +152,8 @@ workflow run_wf { state.method_id == 'negative_control' }, fromState: [ - perturbation_data: "perturbation_data" + perturbation_data: "perturbation_data", + tf_all: "tf_all", ], toState: {id, output, state -> state + [