From a0d2338dfa76d7824aca5076b0d8b7305b710368 Mon Sep 17 00:00:00 2001 From: Alex Morehead Date: Sun, 20 Oct 2024 18:57:32 -0500 Subject: [PATCH] Update README.md --- README.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/README.md b/README.md index 3e9eaa6..b7338f8 100644 --- a/README.md +++ b/README.md @@ -219,7 +219,7 @@ rm dockgen_ensemble_benchmark_method_predictions.tar.gz rm casp15_ensemble_benchmark_method_predictions.tar.gz ``` -**NOTE:** One can reproduce the *pocket-only* experiments with the PoseBusters Benchmark set by adding the argument `pocket_only_baseline=true` to each command below used to run PoseBusters Benchmark dataset inference with all the baseline methods (n.b., besides `tulip`, which does not support pocket-level docking currently), since the pocket-only versions of the dataset's holo-aligned predicted protein structures have also been included in the downloadable Zenodo archive `posebusters_benchmark_set.tar.gz` referenced above. Similarly, one can reproduce the *NeuralPLexer w/o inter-ligand clash loss (ILCL)* experiments with the CASP15 set by adding the argument `no_ilcl=true` (`neuralplexer_no_ilcl=true`) to the commands `python3 posebench/models/neuralplexer_inference.py dataset=casp15 ...` and `python3 posebench/analysis/inference_analysis_casp.py dataset=casp15 ...` below (`python3 posebench/models/ensemble_generation.py ensemble_benchmarking_dataset=casp15 ...`) used to run CASP15 dataset inference with NeuralPLexer. Lastly, one can reproduce the *DiffDock w/o structural cluster training (SCT)* by adding the argument `v1_baseline=true` to the DiffDock inference commands below. Please see the config files within `configs/data/`, `configs/model/`, and `configs/analysis/` for more details. +**NOTE:** One can reproduce the *pocket-only* experiments with the PoseBusters Benchmark set by adding the argument `pocket_only_baseline=true` to each command below used to run PoseBusters Benchmark dataset inference with all the baseline methods (n.b., besides `tulip`, which does not support pocket-level docking currently), since the pocket-only versions of the dataset's holo-aligned predicted protein structures have also been included in the downloadable Zenodo archive `posebusters_benchmark_set.tar.gz` referenced above. Similarly, one can reproduce the *NeuralPLexer w/o inter-ligand clash loss (ILCL)* experiments with the CASP15 set by adding the argument `no_ilcl=true` (`neuralplexer_no_ilcl=true`) to the commands `python3 posebench/models/neuralplexer_inference.py dataset=casp15 ...` and `python3 posebench/analysis/inference_analysis_casp.py dataset=casp15 ...` below (`python3 posebench/models/ensemble_generation.py ensemble_benchmarking_dataset=casp15 ...`) used to run CASP15 dataset inference with NeuralPLexer. Lastly, one can reproduce the *DiffDock w/o structural cluster training (SCT)* experiments by adding the argument `v1_baseline=true` to the DiffDock inference commands below. Please see the config files within `configs/data/`, `configs/model/`, and `configs/analysis/` for more details. ### Downloading sequence databases (required only for RoseTTAFold-All-Atom inference)