diff --git a/_viash.yaml b/_viash.yaml
index 83d3568..ed50565 100644
--- a/_viash.yaml
+++ b/_viash.yaml
@@ -2,7 +2,7 @@ viash_version: 0.9.0
 
 # Step 1: Change the name of the task.
 # example: task_name_of_this_task
-name: task_template
+name: task_foundation_models
 organization: openproblems-bio
 version: dev
 
@@ -11,8 +11,8 @@ license: MIT
 keywords: [single-cell, openproblems, benchmark]
 # Step 3: Update the `task_template` to the name of the task from step 1.
 links:
-  issue_tracker: https://github.com/openproblems-bio/task_template/issues
-  repository: https://github.com/openproblems-bio/task_template
+  issue_tracker: https://github.com/openproblems-bio/task_foundation_models/issues
+  repository: https://github.com/openproblems-bio/task_foundation_models
   docker_registry: ghcr.io
 
 
@@ -50,11 +50,8 @@ info:
   # Step 5: Replace the task_template to the name of the task.
   test_resources:
     - type: s3
-      path: s3://openproblems-data/resources_test/common/
-      dest: resources_test/common
-    - type: s3
-      path: s3://openproblems-data/resources_test/task_template/
-      dest: resources_test/task_template
+      path: s3://openproblems-data/resources_test/task_foundation_models/
+      dest: resources_test/task_foundation_models
 
 # Step 6: Update the authors of the task.
 authors: 
@@ -81,8 +78,7 @@ config_mods: |
   .runners[.type == "nextflow"].config.labels := { lowmem : "memory = 20.Gb", midmem : "memory = 50.Gb", highmem : "memory = 100.Gb", lowcpu : "cpus = 5", midcpu : "cpus = 15", highcpu : "cpus = 30", lowtime : "time = 1.h", midtime : "time = 4.h", hightime : "time = 8.h", veryhightime : "time = 24.h" }
 
 repositories:
-  - name: core
+  - name: openproblems
     type: github
-    repo: openproblems-bio/core
+    repo: openproblems-bio/openproblems
     tag: build/main
-    path: viash/core
diff --git a/scripts/create_resources/test_resources.sh b/scripts/create_resources/test_resources.sh
index 9cb372a..5eeb639 100755
--- a/scripts/create_resources/test_resources.sh
+++ b/scripts/create_resources/test_resources.sh
@@ -6,48 +6,38 @@ REPO_ROOT=$(git rev-parse --show-toplevel)
 # ensure that the command below is run from the root of the repository
 cd "$REPO_ROOT"
 
-# # remove this when you have implemented the script
-# echo "TODO: replace the commands in this script with the sequence of components that you need to run to generate test_resources."
-# echo "  Inside this script, you will need to place commands to generate example files for each of the 'src/api/file_*.yaml' files."
-# exit 1
-
 set -e
 
-RAW_DATA=resources_test/common
-DATASET_DIR=resources_test/task_template
-
-mkdir -p $DATASET_DIR
-
-# process dataset
-viash run src/data_processors/process_dataset/config.vsh.yaml -- \
-  --input $RAW_DATA/cxg_mouse_pancreas_atlas/dataset.h5ad \
-  --output_train $DATASET_DIR/cxg_mouse_pancreas_atlas/train.h5ad \
-  --output_test $DATASET_DIR/cxg_mouse_pancreas_atlas/test.h5ad \
-  --output_solution $DATASET_DIR/cxg_mouse_pancreas_atlas/solution.h5ad
-
-# run one method
-viash run src/methods/logistic_regression/config.vsh.yaml -- \
-    --input_train $DATASET_DIR/cxg_mouse_pancreas_atlas/train.h5ad \
-    --input_test $DATASET_DIR/cxg_mouse_pancreas_atlas/test.h5ad \
-    --output $DATASET_DIR/cxg_mouse_pancreas_atlas/prediction.h5ad
-
-# run one metric
-viash run src/metrics/accuracy/config.vsh.yaml -- \
-    --input_prediction $DATASET_DIR/cxg_mouse_pancreas_atlas/prediction.h5ad \
-    --input_solution $DATASET_DIR/cxg_mouse_pancreas_atlas/solution.h5ad \
-    --output $DATASET_DIR/cxg_mouse_pancreas_atlas/score.h5ad
-
-# write manual state.yaml. this is not actually necessary but you never know it might be useful
-cat > $DATASET_DIR/cxg_mouse_pancreas_atlas/state.yaml << HERE
-id: cxg_mouse_pancreas_atlas
-train: !file train.h5ad
-test: !file test.h5ad
-solution: !file solution.h5ad
-prediction: !file prediction.h5ad
-score: !file score.h5ad
-HERE
+OUT_DIR=resources_test/task_foundation_models/results
+
+TASKS=(
+  "task_label_projection"
+  "task_batch_integration"
+)
+
+if [ -d "$OUT_DIR" ]; then
+  echo "Removing existing directory '$OUT_DIR'"
+  rm -rf "$OUT_DIR"
+fi
+
+mkdir -p "$OUT_DIR"
+
+for TASK in "${TASKS[@]}"; do
+  BASE_DIR="s3://openproblems-data/resources/$TASK/results"
+  
+  # find subdir in bucket with latest date which has a 'task_info.yaml' file
+  DATE=$(aws s3 ls "$BASE_DIR/" --recursive --no-sign-request | awk '{print $4}' | grep 'task_info.yaml' | sort -r | head -n 1 | sed 's#.*/run_\(.*\)/[^/]*$#\1#')
+  
+  INPUT_DIR="$BASE_DIR/run_$DATE"
+  TASK_STRIP_PREFIX=$(echo $TASK | sed 's/task_//')
+  OUTPUT_DIR="$OUT_DIR/$TASK_STRIP_PREFIX"
+
+  echo "Syncing '$INPUT_DIR' to '$OUTPUT_DIR'"
+  aws s3 sync "$INPUT_DIR" "$OUTPUT_DIR" --delete --no-sign-request
+done
 
 # only run this if you have access to the openproblems-data bucket
 aws s3 sync --profile op \
-  "$DATASET_DIR" s3://openproblems-data/resources_test/task_template \
+  "resources_test/task_foundation_models" \
+  s3://openproblems-data/resources_test/task_foundation_models \
   --delete --dryrun
diff --git a/src/control_methods/true_labels/config.vsh.yaml b/src/control_methods/true_labels/config.vsh.yaml
deleted file mode 100644
index 741e3f2..0000000
--- a/src/control_methods/true_labels/config.vsh.yaml
+++ /dev/null
@@ -1,59 +0,0 @@
-# The API specifies which type of component this is.
-# It contains specifications for:
-#   - The input/output files
-#   - Common parameters
-#   - A unit test
-__merge__: ../../api/comp_control_method.yaml
-
-# A unique identifier for your component (required).
-# Can contain only lowercase letters or underscores.
-name: true_labels
-
-# A relatively short label, used when rendering visualisations (required)
-label: True Labels
-# A one sentence summary of how this method works (required). Used when 
-# rendering summary tables.
-summary: "a positive control, solution labels are copied 1 to 1 to the predicted data."
-# A multi-line description of how this component works (required). Used
-# when rendering reference documentation.
-description: |
-  A positive control, where the solution labels are copied 1 to 1 to the predicted data.
-
-# Metadata for your component
-info:
-  # Which normalisation method this component prefers to use (required).
-  preferred_normalization: counts
-
-# Component-specific parameters (optional)
-# arguments:
-#   - name: "--n_neighbors"
-#     type: "integer"
-#     default: 5
-#     description: Number of neighbors to use.
-
-# Resources required to run the component
-resources:
-  # The script of your component (required)
-  - type: python_script
-    path: script.py
-  # Additional resources your script needs (optional)
-  # - type: file
-  #   path: weights.pt
-
-engines:
-  # Specifications for the Docker image for this component.
-  - type: docker
-    image: openproblems/base_python:1.0.0
-    # Add custom dependencies here (optional). For more information, see
-    # https://viash.io/reference/config/engines/docker/#setup .
-    # setup:
-    #   - type: python
-    #     packages: scib==1.1.5
-
-runners:
-  # This platform allows running the component natively
-  - type: executable
-  # Allows turning the component into a Nextflow module / pipeline.
-  - type: nextflow
-    directives:
-      label: [midtime, lowmem, lowcpu]
diff --git a/src/control_methods/true_labels/script.py b/src/control_methods/true_labels/script.py
deleted file mode 100644
index 935f3af..0000000
--- a/src/control_methods/true_labels/script.py
+++ /dev/null
@@ -1,45 +0,0 @@
-import anndata as ad
-
-## VIASH START
-# Note: this section is auto-generated by viash at runtime. To edit it, make changes
-# in config.vsh.yaml and then run `viash config inject config.vsh.yaml`.
-par = {
-  'input_train': 'resources_test/task_template/cxg_mouse_pancreas_atlas/train.h5ad',
-  'input_test': 'resources_test/task_template/cxg_mouse_pancreas_atlas/test.h5ad',
-  'input_solution': 'resources_test/task_template/cxg_mouse_pancreas_atlas/solution.h5ad',
-  'output': 'output.h5ad'
-}
-meta = {
-  'name': 'true_labels'
-}
-## VIASH END
-
-print('Reading input files', flush=True)
-input_train = ad.read_h5ad(par['input_train'])
-input_test = ad.read_h5ad(par['input_test'])
-input_solution = ad.read_h5ad(par['input_solution'])
-
-print('Preprocess data', flush=True)
-# ... preprocessing ...
-
-print('Train model', flush=True)
-# ... train model ...
-
-print('Generate predictions', flush=True)
-# ... generate predictions ...
-obs_label_pred = input_solution.obs["label"]
-
-print("Write output AnnData to file", flush=True)
-output = ad.AnnData(
-  uns={
-    'dataset_id': input_train.uns['dataset_id'],
-    'normalization_id': input_train.uns['normalization_id'],
-    'method_id': meta['name']
-  },
-  obs={
-    'label_pred': obs_label_pred
-  }
-)
-output.obs_names = input_test.obs_names
-
-output.write_h5ad(par['output'], compression='gzip')
diff --git a/src/data_processors/process_dataset/config.vsh.yaml b/src/data_processors/process_dataset/config.vsh.yaml
deleted file mode 100644
index a997720..0000000
--- a/src/data_processors/process_dataset/config.vsh.yaml
+++ /dev/null
@@ -1,34 +0,0 @@
-__merge__: ../../api/comp_data_processor.yaml
-name: process_dataset
-arguments:
-  - name: "--method"
-    type: "string"
-    description: "The process method to assign train/test."
-    choices: ["batch", "random"]
-    default: "batch"
-  - name: "--obs_label"
-    type: "string"
-    description: "Which .obs slot to use as label."
-    default: "cell_type"
-  - name: "--obs_batch"
-    type: "string"
-    description: "Which .obs slot to use as batch covariate."
-    default: "batch"
-  - name: "--seed"
-    type: "integer"
-    description: "A seed for the subsampling."
-    example: 123
-resources:
-  - type: python_script
-    path: script.py
-  - path: /common/helper_functions/subset_h5ad_by_format.py
-
-engines:
-  - type: docker
-    image: openproblems/base_python:1.0.0
-
-runners:
-  - type: executable
-  - type: nextflow
-    directives:
-      label: [highmem, midcpu, midtime]
\ No newline at end of file
diff --git a/src/data_processors/process_dataset/script.py b/src/data_processors/process_dataset/script.py
deleted file mode 100644
index 3eb56c2..0000000
--- a/src/data_processors/process_dataset/script.py
+++ /dev/null
@@ -1,86 +0,0 @@
-import sys
-import random
-import numpy as np
-import anndata as ad
-import openproblems as op
-
-## VIASH START
-par = {
-    'input': 'resources_test/common/cxg_mouse_pancreas_atlas/dataset.h5ad',
-    'method': 'batch',
-    'seed': None,
-    'obs_batch': 'batch',
-    'obs_label': 'cell_type',
-    'output_train': 'train.h5ad',
-    'output_test': 'test.h5ad',
-    'output_solution': 'solution.h5ad'
-}
-meta = {
-    'resources_dir': 'target/executable/data_processors/process_dataset',
-    'config': 'target/executable/data_processors/process_dataset/.config.vsh.yaml'
-}
-## VIASH END
-
-# import helper functions
-sys.path.append(meta['resources_dir'])
-from subset_h5ad_by_format import subset_h5ad_by_format
-
-config = op.project.read_viash_config(meta["config"])
-
-# set seed if need be
-if par["seed"]:
-    print(f">> Setting seed to {par['seed']}")
-    random.seed(par["seed"])
-
-print(">> Load data", flush=True)
-adata = ad.read_h5ad(par["input"])
-print("input:", adata)
-
-print(f">> Process data using {par['method']} method")
-if par["method"] == "batch":
-    batch_info = adata.obs[par["obs_batch"]]
-    batch_categories = batch_info.dtype.categories
-    test_batches = random.sample(list(batch_categories), 1)
-    is_test = [ x in test_batches for x in batch_info ]
-elif par["method"] == "random":
-    train_ix = np.random.choice(adata.n_obs, round(adata.n_obs * 0.8), replace=False)
-    is_test = [ not x in train_ix for x in range(0, adata.n_obs) ]
-
-# subset the different adatas
-print(">> Figuring which data needs to be copied to which output file", flush=True)
-# use par arguments to look for label and batch value in different slots
-slot_mapping = {
-    "obs": {
-        "label": par["obs_label"],
-        "batch": par["obs_batch"],
-    }
-}
-
-print(">> Creating train data", flush=True)
-output_train = subset_h5ad_by_format(
-    adata[[not x for x in is_test]],
-    config,
-    "output_train",
-    slot_mapping
-)
-
-print(">> Creating test data", flush=True)
-output_test = subset_h5ad_by_format(
-    adata[is_test],
-    config,
-    "output_test",
-    slot_mapping
-)
-
-print(">> Creating solution data", flush=True)
-output_solution = subset_h5ad_by_format(
-    adata[is_test],
-    config,
-    "output_solution",
-    slot_mapping
-)
-
-print(">> Writing data", flush=True)
-output_train.write_h5ad(par["output_train"])
-output_test.write_h5ad(par["output_test"])
-output_solution.write_h5ad(par["output_solution"])
diff --git a/src/methods/logistic_regression/config.vsh.yaml b/src/methods/logistic_regression/config.vsh.yaml
deleted file mode 100644
index 479aa3a..0000000
--- a/src/methods/logistic_regression/config.vsh.yaml
+++ /dev/null
@@ -1,79 +0,0 @@
-# The API specifies which type of component this is.
-# It contains specifications for:
-#   - The input/output files
-#   - Common parameters
-#   - A unit test
-__merge__: ../../api/comp_method.yaml
-
-
-# A unique identifier for your component (required).
-# Can contain only lowercase letters or underscores.
-name: logistic_regression
-# A relatively short label, used when rendering visualisations (required)
-label: Logistic Regression
-# A one sentence summary of how this method works (required). Used when 
-# rendering summary tables.
-summary: "Logistic Regression with 100-dimensional PCA coordinates estimates parameters for multivariate classification by minimizing cross entropy loss over cell type classes."
-# A multi-line description of how this component works (required). Used
-# when rendering reference documentation.
-description: |
-  Logistic Regression estimates parameters of a logistic function for
-  multivariate classification tasks. Here, we use 100-dimensional whitened PCA
-  coordinates as independent variables, and the model minimises the cross
-  entropy loss over all cell type classes.
-# Metadata for your component
-# A reference key from the bibtex library at src/common/library.bib (required).
-references:
-  bibtex: 
-    - |
-      @book{hosmer2013applied,
-        title = {Applied logistic regression},
-        author = {Hosmer Jr, D.W. and Lemeshow, S. and Sturdivant, R.X.},
-        year = {2013},
-        publisher = {John Wiley \& Sons},
-        volume = {398}
-      }
-
-links:
-  # URL to the code repository for this method (required).
-  repository: https://github.com/scikit-learn/scikit-learn
-  # URL to the documentation for this method (required).
-  documentation: "https://scikit-learn.org/stable/modules/generated/sklearn.linear_model.LogisticRegression.html"
-
-info:
-  # Which normalisation method this component prefers to use (required).
-  preferred_normalization: log_cp10k
-
-# Component-specific parameters (optional)
-# arguments:
-#   - name: "--n_neighbors"
-#     type: "integer"
-#     default: 5
-#     description: Number of neighbors to use.
-
-# Resources required to run the component
-resources:
-  # The script of your component (required)
-  - type: python_script
-    path: script.py
-  # Additional resources your script needs (optional)
-  # - type: file
-  #   path: weights.pt
-
-engines:
-  # Specifications for the Docker image for this component.
-  - type: docker
-    image: openproblems/base_python:1.0.0
-    # Add custom dependencies here (optional). For more information, see
-    # https://viash.io/reference/config/engines/docker/#setup .
-    setup:
-      - type: python
-        packages: scikit-learn
-
-runners:
-  # This platform allows running the component natively
-  - type: executable
-  # Allows turning the component into a Nextflow module / pipeline.
-  - type: nextflow
-    directives:
-      label: [midtime, midmem, lowcpu]
diff --git a/src/methods/logistic_regression/script.py b/src/methods/logistic_regression/script.py
deleted file mode 100644
index 6ab5782..0000000
--- a/src/methods/logistic_regression/script.py
+++ /dev/null
@@ -1,46 +0,0 @@
-import anndata as ad
-import sklearn.linear_model
-
-## VIASH START
-# Note: this section is auto-generated by viash at runtime. To edit it, make changes
-# in config.vsh.yaml and then run `viash config inject config.vsh.yaml`.
-par = {
-  'input_train': 'resources_test/task_template/cxg_mouse_pancreas_atlas/train.h5ad',
-  'input_test': 'resources_test/task_template/cxg_mouse_pancreas_atlas/test.h5ad',
-  'output': 'output.h5ad'
-}
-meta = {
-  'name': 'logistic_regression'
-}
-## VIASH END
-
-print('Reading input files', flush=True)
-input_train = ad.read_h5ad(par['input_train'])
-input_test = ad.read_h5ad(par['input_test'])
-
-print('Preprocess data', flush=True)
-# ... preprocessing ...
-
-print('Train model', flush=True)
-# ... train model ...
-classifier = sklearn.linear_model.LogisticRegression()
-classifier.fit(input_train.obsm["X_pca"], input_train.obs["label"].astype(str))
-
-print('Generate predictions', flush=True)
-# ... generate predictions ...
-obs_label_pred = classifier.predict(input_test.obsm["X_pca"])
-
-print("Write output AnnData to file", flush=True)
-output = ad.AnnData(
-  uns={
-    'dataset_id': input_train.uns['dataset_id'],
-    'normalization_id': input_train.uns['normalization_id'],
-    'method_id': meta['name']
-  },
-  obs={
-    'label_pred': obs_label_pred
-  }
-)
-output.obs_names = input_test.obs_names
-
-output.write_h5ad(par['output'], compression='gzip')
diff --git a/src/metrics/accuracy/config.vsh.yaml b/src/metrics/accuracy/config.vsh.yaml
deleted file mode 100644
index 66fa835..0000000
--- a/src/metrics/accuracy/config.vsh.yaml
+++ /dev/null
@@ -1,70 +0,0 @@
-# The API specifies which type of component this is.
-# It contains specifications for:
-#   - The input/output files
-#   - Common parameters
-#   - A unit test
-__merge__: ../../api/comp_metric.yaml
-
-
-# A unique identifier for your component (required).
-# Can contain only lowercase letters or underscores.
-name: accuracy
-
-# Metadata for your component
-info:
-  metrics:
-    # A unique identifier for your metric (required).
-    # Can contain only lowercase letters or underscores.
-    - name: accuracy
-      # A relatively short label, used when rendering visualisarions (required)
-      label: Accuracy
-      # A one sentence summary of how this metric works (required). Used when 
-      # rendering summary tables.
-      summary: "The percentage of correctly predicted labels."
-      # A multi-line description of how this component works (required). Used
-      # when rendering reference documentation.
-      description: |
-        The percentage of correctly predicted labels.
-      # A reference key from the bibtex library at src/common/library.bib (required).
-      references:
-        doi: 10.48550/arXiv.2008.05756
-      # The minimum possible value for this metric (required)
-      min: 0
-      # The maximum possible value for this metric (required)
-      max: 1
-      # Whether a higher value represents a 'better' solution (required)
-      maximize: true
-
-# Component-specific parameters (optional)
-# arguments:
-#   - name: "--n_neighbors"
-#     type: "integer"
-#     default: 5
-#     description: Number of neighbors to use.
-
-# Resources required to run the component
-resources:
-  # The script of your component (required)
-  - type: python_script
-    path: script.py
-  # Additional resources your script needs (optional)
-  # - type: file
-  #   path: weights.pt
-
-engines:
-  # Specifications for the Docker image for this component.
-  - type: docker
-    image: openproblems/base_python:1.0.0
-    # Add custom dependencies here (optional). For more information, see
-    # https://viash.io/reference/config/engines/docker/#setup .
-    setup:
-      - type: python
-        packages: scikit-learn
-
-runners:
-  # This platform allows running the component natively
-  - type: executable
-  # Allows turning the component into a Nextflow module / pipeline.
-  - type: nextflow
-    directives:
-      label: [midtime, midmem, midcpu]
diff --git a/src/metrics/accuracy/script.py b/src/metrics/accuracy/script.py
deleted file mode 100644
index 054e809..0000000
--- a/src/metrics/accuracy/script.py
+++ /dev/null
@@ -1,47 +0,0 @@
-import anndata as ad
-import numpy as np
-import sklearn.preprocessing
-
-## VIASH START
-# Note: this section is auto-generated by viash at runtime. To edit it, make changes
-# in config.vsh.yaml and then run `viash config inject config.vsh.yaml`.
-par = {
-  'input_solution': 'resources_test/task_template/cxg_mouse_pancreas_atlas/solution.h5ad',
-  'input_prediction': 'resources_test/task_template/cxg_mouse_pancreas_atlas/prediction.h5ad',
-  'output': 'output.h5ad'
-}
-meta = {
-  'name': 'accuracy'
-}
-## VIASH END
-
-print('Reading input files', flush=True)
-input_solution = ad.read_h5ad(par['input_solution'])
-input_prediction = ad.read_h5ad(par['input_prediction'])
-
-assert (input_prediction.obs_names == input_solution.obs_names).all(), "obs_names not the same in prediction and solution inputs"
-
-print("Encode labels", flush=True)
-cats = list(input_solution.obs["label"].dtype.categories) + list(input_prediction.obs["label_pred"].dtype.categories)
-encoder = sklearn.preprocessing.LabelEncoder().fit(cats)
-input_solution.obs["label"] = encoder.transform(input_solution.obs["label"])
-input_prediction.obs["label_pred"] = encoder.transform(input_prediction.obs["label_pred"])
-
-
-print('Compute metrics', flush=True)
-# metric_ids and metric_values can have length > 1
-# but should be of equal length
-uns_metric_ids = [ 'accuracy' ]
-uns_metric_values = np.mean(input_solution.obs["label"] == input_prediction.obs["label_pred"])
-
-print("Write output AnnData to file", flush=True)
-output = ad.AnnData(
-  uns={
-    'dataset_id': input_prediction.uns['dataset_id'],
-    'normalization_id': input_prediction.uns['normalization_id'],
-    'method_id': input_prediction.uns['method_id'],
-    'metric_ids': uns_metric_ids,
-    'metric_values': uns_metric_values
-  }
-)
-output.write_h5ad(par['output'], compression='gzip')
diff --git a/src/workflows/process_datasets/config.vsh.yaml b/src/workflows/process_datasets/config.vsh.yaml
deleted file mode 100644
index 64ff740..0000000
--- a/src/workflows/process_datasets/config.vsh.yaml
+++ /dev/null
@@ -1,38 +0,0 @@
-name: process_datasets
-namespace: workflows
-
-argument_groups:
-  - name: Inputs
-    arguments:
-      - name: "--input"
-        __merge__: /src/api/file_common_dataset.yaml
-        required: true
-        direction: input
-  - name: Outputs
-    arguments:
-      - name: "--output_train"
-        __merge__: /src/api/file_train.yaml
-        required: true
-        direction: output
-      - name: "--output_test"
-        __merge__: /src/api/file_test.yaml
-        required: true
-        direction: output
-      - name: "--output_solution"
-        __merge__: /src/api/file_solution.yaml
-        required: true
-        direction: output
-
-resources:
-  - type: nextflow_script
-    path: main.nf
-    entrypoint: run_wf
-  - path: /common/nextflow_helpers/helper.nf
-
-dependencies:
-  - name: schema/verify_data_structure
-    repository: core
-  - name: data_processors/process_dataset
-
-runners:
-  - type: nextflow
diff --git a/src/workflows/process_datasets/main.nf b/src/workflows/process_datasets/main.nf
deleted file mode 100644
index 25d1260..0000000
--- a/src/workflows/process_datasets/main.nf
+++ /dev/null
@@ -1,55 +0,0 @@
-include { findArgumentSchema } from "${meta.resources_dir}/helper.nf"
-
-workflow auto {
-  findStates(params, meta.config)
-    | meta.workflow.run(
-      auto: [publish: "state"]
-    )
-}
-
-workflow run_wf {
-  take:
-  input_ch
-
-  main:
-  output_ch = input_ch
-
-    | verify_data_structure.run(
-      fromState: { id, state ->
-        def schema = findArgumentSchema(meta.config, "input")
-        def schemaYaml = tempFile("schema.yaml")
-        writeYaml(schema, schemaYaml)
-        [
-          "input": state.input,
-          "schema": schemaYaml
-        ]
-      },
-      toState: { id, output, state ->
-        // read the output to see if dataset passed the qc
-        def checks = readYaml(output.output)
-        state + [
-          "dataset": checks["exit_code"] == 0 ? state.input : null,
-        ]
-      }
-    )
-
-    // remove datasets which didn't pass the schema check
-    | filter { id, state ->
-      state.dataset != null
-    }
-
-    | process_dataset.run(
-      fromState: [ input: "dataset" ],
-      toState: [
-        output_train: "output_train",
-        output_test: "output_test",
-        output_solution: "output_solution"
-      ]
-    )
-
-    // only output the files for which an output file was specified
-    | setState(["output_train", "output_test", "output_solution"])
-
-  emit:
-  output_ch
-}
diff --git a/src/workflows/process_datasets/test.sh b/src/workflows/process_datasets/test.sh
deleted file mode 100755
index d918102..0000000
--- a/src/workflows/process_datasets/test.sh
+++ /dev/null
@@ -1,33 +0,0 @@
-#!/bin/bash
-
-# Run this prior to executing this script:
-# bin/viash_build -q 'batch_integration'
-
-# get the root of the directory
-REPO_ROOT=$(git rev-parse --show-toplevel)
-
-# ensure that the command below is run from the root of the repository
-cd "$REPO_ROOT"
-
-set -e
-
-DATASETS_DIR="resources_test/common"
-OUTPUT_DIR="output/process_datasets_test"
-
-if [ ! -d "$OUTPUT_DIR" ]; then
-  mkdir -p "$OUTPUT_DIR"
-fi
-
-export NXF_VER=24.04.3
-
-nextflow run . \
-  -main-script target/nextflow/workflows/process_datasets/main.nf \
-  -profile docker \
-  -entry auto \
-  -c common/nextflow_helpers/labels_ci.config \
-  --id run_test \
-  --input_states "$DATASETS_DIR/**/state.yaml" \
-  --rename_keys 'input:output_dataset' \
-  --settings '{"output_train": "train.h5ad", "output_test": "test.h5ad"}' \
-  --publish_dir "$OUTPUT_DIR" \
-  --output_state "state.yaml"
\ No newline at end of file
diff --git a/src/workflows/run_benchmark/config.vsh.yaml b/src/workflows/run_benchmark/config.vsh.yaml
deleted file mode 100644
index 904a2b6..0000000
--- a/src/workflows/run_benchmark/config.vsh.yaml
+++ /dev/null
@@ -1,72 +0,0 @@
-name: run_benchmark
-namespace: workflows
-
-argument_groups:
-  - name: Inputs
-    arguments:
-      - name: "--input_train"
-        __merge__: /src/api/file_train.yaml
-        type: file
-        direction: input
-        required: true
-      - name: "--input_test"
-        __merge__: /src/api/file_test.yaml
-        type: file
-        direction: input
-        required: true
-      - name: "--input_solution"
-        __merge__: /src/api/file_solution.yaml
-        type: file
-        direction: input
-        required: true
-  - name: Outputs
-    arguments:
-      - name: "--output_scores"
-        type: file
-        required: true
-        direction: output
-        description: A yaml file containing the scores of each of the methods
-        default: score_uns.yaml
-      - name: "--output_method_configs"
-        type: file
-        required: true
-        direction: output
-        default: method_configs.yaml
-      - name: "--output_metric_configs"
-        type: file
-        required: true
-        direction: output
-        default: metric_configs.yaml
-      - name: "--output_dataset_info"
-        type: file
-        required: true
-        direction: output
-        default: dataset_uns.yaml
-      - name: "--output_task_info"
-        type: file
-        required: true
-        direction: output
-        default: task_info.yaml
-  - name: Methods
-    arguments:
-      - name: "--method_ids"
-        type: string
-        multiple: true
-        description: A list of method ids to run. If not specified, all methods will be run.
-
-resources:
-  - type: nextflow_script
-    path: main.nf
-    entrypoint: run_wf
-  - type: file
-    path: /_viash.yaml
-
-dependencies:
-  - name: h5ad/extract_uns_metadata
-    repository: core
-  - name: control_methods/true_labels
-  - name: methods/logistic_regression
-  - name: metrics/accuracy
-
-runners:
-  - type: nextflow
diff --git a/src/workflows/run_benchmark/main.nf b/src/workflows/run_benchmark/main.nf
deleted file mode 100644
index 826dec4..0000000
--- a/src/workflows/run_benchmark/main.nf
+++ /dev/null
@@ -1,191 +0,0 @@
-workflow auto {
-  findStates(params, meta.config)
-    | meta.workflow.run(
-      auto: [publish: "state"]
-    )
-}
-
-// construct list of methods and control methods
-methods = [
-  true_labels,
-  logistic_regression
-]
-
-// construct list of metrics
-metrics = [
-  accuracy
-]
-
-workflow run_wf {
-  take:
-  input_ch
-
-  main:
-
-  /****************************
-   * EXTRACT DATASET METADATA *
-   ****************************/
-  dataset_ch = input_ch
-    // store join id
-    | map{ id, state -> 
-      [id, state + ["_meta": [join_id: id]]]
-    }
-
-    // extract the dataset metadata
-    | extract_uns_metadata.run(
-      fromState: [input: "input_solution"],
-      toState: { id, output, state ->
-        state + [
-          dataset_uns: readYaml(output.output).uns
-        ]
-      }
-    )
-
-  /***************************
-   * RUN METHODS AND METRICS *
-   ***************************/
-  score_ch = dataset_ch
-
-    // run all methods
-    | runEach(
-      components: methods,
-
-      // use the 'filter' argument to only run a method on the normalisation the component is asking for
-      filter: { id, state, comp ->
-        def norm = state.dataset_uns.normalization_id
-        def pref = comp.config.info.preferred_normalization
-        // if the preferred normalisation is none at all,
-        // we can pass whichever dataset we want
-        def norm_check = (norm == "log_cp10k" && pref == "counts") || norm == pref
-        def method_check = !state.method_ids || state.method_ids.contains(comp.config.name)
-
-        method_check && norm_check
-      },
-
-      // define a new 'id' by appending the method name to the dataset id
-      id: { id, state, comp ->
-        id + "." + comp.config.name
-      },
-
-      // use 'fromState' to fetch the arguments the component requires from the overall state
-      fromState: { id, state, comp ->
-        def new_args = [
-          input_train: state.input_train,
-          input_test: state.input_test
-        ]
-        if (comp.config.info.type == "control_method") {
-          new_args.input_solution = state.input_solution
-        }
-        new_args
-      },
-
-      // use 'toState' to publish that component's outputs to the overall state
-      toState: { id, output, state, comp ->
-        state + [
-          method_id: comp.config.name,
-          method_output: output.output
-        ]
-      }
-    )
-
-    // run all metrics
-    | runEach(
-      components: metrics,
-      id: { id, state, comp ->
-        id + "." + comp.config.name
-      },
-      // use 'fromState' to fetch the arguments the component requires from the overall state
-      fromState: [
-        input_solution: "input_solution", 
-        input_prediction: "method_output"
-      ],
-      // use 'toState' to publish that component's outputs to the overall state
-      toState: { id, output, state, comp ->
-        state + [
-          metric_id: comp.config.name,
-          metric_output: output.output
-        ]
-      }
-    )
-
-    // extract the scores
-    | extract_uns_metadata.run(
-      key: "extract_scores",
-      fromState: [input: "metric_output"],
-      toState: { id, output, state ->
-        state + [
-          score_uns: readYaml(output.output).uns
-        ]
-      }
-    )
-
-    | joinStates { ids, states ->
-      // store the scores in a file
-      def score_uns = states.collect{it.score_uns}
-      def score_uns_yaml_blob = toYamlBlob(score_uns)
-      def score_uns_file = tempFile("score_uns.yaml")
-      score_uns_file.write(score_uns_yaml_blob)
-
-      ["output", [output_scores: score_uns_file]]
-    }
-
-  /******************************
-   * GENERATE OUTPUT YAML FILES *
-   ******************************/
-  // TODO: can we store everything below in a separate helper function?
-
-  // extract the dataset metadata
-  meta_ch = dataset_ch
-    // only keep one of the normalization methods
-    | filter{ id, state ->
-      state.dataset_uns.normalization_id == "log_cp10k"
-    }
-    | joinStates { ids, states ->
-      // store the dataset metadata in a file
-      def dataset_uns = states.collect{state ->
-        def uns = state.dataset_uns.clone()
-        uns.remove("normalization_id")
-        uns
-      }
-      def dataset_uns_yaml_blob = toYamlBlob(dataset_uns)
-      def dataset_uns_file = tempFile("dataset_uns.yaml")
-      dataset_uns_file.write(dataset_uns_yaml_blob)
-
-      // store the method configs in a file
-      def method_configs = methods.collect{it.config}
-      def method_configs_yaml_blob = toYamlBlob(method_configs)
-      def method_configs_file = tempFile("method_configs.yaml")
-      method_configs_file.write(method_configs_yaml_blob)
-
-      // store the metric configs in a file
-      def metric_configs = metrics.collect{it.config}
-      def metric_configs_yaml_blob = toYamlBlob(metric_configs)
-      def metric_configs_file = tempFile("metric_configs.yaml")
-      metric_configs_file.write(metric_configs_yaml_blob)
-
-      // store the task info in a file
-      def viash_file = meta.resources_dir.resolve("_viash.yaml")
-
-      // create output state
-      def new_state = [
-        output_dataset_info: dataset_uns_file,
-        output_method_configs: method_configs_file,
-        output_metric_configs: metric_configs_file,
-        output_task_info: viash_file,
-        _meta: states[0]._meta
-      ]
-
-      ["output", new_state]
-    }
-
-  // merge all of the output data
-  output_ch = score_ch
-    | mix(meta_ch)
-    | joinStates{ ids, states ->
-      def mergedStates = states.inject([:]) { acc, m -> acc + m }
-      [ids[0], mergedStates]
-    }
-
-  emit:
-  output_ch
-}