Skip to content

Commit

Permalink
Set method_top_n_to_select=3
Browse files Browse the repository at this point in the history
  • Loading branch information
@amorehead
amorehead committed Aug 16, 2024
1 parent 9011367 commit 0d9781f
Show file tree
Hide file tree
Showing 5 changed files with 33 additions and 31 deletions.
24 changes: 12 additions & 12 deletions README.md
View file
Original file line number Diff line number Diff line change
Expand Up @@ -400,8 +400,8 @@ Analyze inference results for the CASP15 dataset

```bash
# first assemble (unrelaxed and post ranking-relaxed) CASP15-compliant prediction submission files for scoring
python3 posebench/models/ensemble_generation.py ensemble_methods=\[diffdock\] input_csv_filepath=data/test_cases/casp15/ensemble_inputs.csv output_dir=data/test_cases/casp15/top_diffdock_ensemble_predictions_1 skip_existing=true relax_method_ligands_post_ranking=false export_file_format=casp15 export_top_n=5 combine_casp_output_files=true max_method_predictions=40 method_top_n_to_select=5 resume=true ensemble_benchmarking=true ensemble_benchmarking_dataset=casp15 cuda_device_index=0 ensemble_benchmarking_repeat_index=1
python3 posebench/models/ensemble_generation.py ensemble_methods=\[diffdock\] input_csv_filepath=data/test_cases/casp15/ensemble_inputs.csv output_dir=data/test_cases/casp15/top_diffdock_ensemble_predictions_1 skip_existing=true relax_method_ligands_post_ranking=true export_file_format=casp15 export_top_n=5 combine_casp_output_files=true max_method_predictions=40 method_top_n_to_select=5 resume=true ensemble_benchmarking=true ensemble_benchmarking_dataset=casp15 cuda_device_index=0 ensemble_benchmarking_repeat_index=1
python3 posebench/models/ensemble_generation.py ensemble_methods=\[diffdock\] input_csv_filepath=data/test_cases/casp15/ensemble_inputs.csv output_dir=data/test_cases/casp15/top_diffdock_ensemble_predictions_1 skip_existing=true relax_method_ligands_post_ranking=false export_file_format=casp15 export_top_n=5 combine_casp_output_files=true max_method_predictions=40 method_top_n_to_select=3 resume=true ensemble_benchmarking=true ensemble_benchmarking_dataset=casp15 cuda_device_index=0 ensemble_benchmarking_repeat_index=1
python3 posebench/models/ensemble_generation.py ensemble_methods=\[diffdock\] input_csv_filepath=data/test_cases/casp15/ensemble_inputs.csv output_dir=data/test_cases/casp15/top_diffdock_ensemble_predictions_1 skip_existing=true relax_method_ligands_post_ranking=true export_file_format=casp15 export_top_n=5 combine_casp_output_files=true max_method_predictions=40 method_top_n_to_select=3 resume=true ensemble_benchmarking=true ensemble_benchmarking_dataset=casp15 cuda_device_index=0 ensemble_benchmarking_repeat_index=1
# NOTE: the suffixes for both `output_dir` and `ensemble_benchmarking_repeat_index` should be modified to e.g., 2, 3, ...
...
# now score the CASP15-compliant submissions using the official CASP scoring pipeline
Expand Down Expand Up @@ -502,8 +502,8 @@ Analyze inference results for the CASP15 dataset

```bash
# first assemble (unrelaxed and post ranking-relaxed) CASP15-compliant prediction submission files for scoring
python3 posebench/models/ensemble_generation.py ensemble_methods=\[dynamicbind\] input_csv_filepath=data/test_cases/casp15/ensemble_inputs.csv output_dir=data/test_cases/casp15/top_dynamicbind_ensemble_predictions_1 skip_existing=true relax_method_ligands_post_ranking=false export_file_format=casp15 export_top_n=5 combine_casp_output_files=true max_method_predictions=40 method_top_n_to_select=5 resume=true ensemble_benchmarking=true ensemble_benchmarking_dataset=casp15 cuda_device_index=0 ensemble_benchmarking_repeat_index=1
python3 posebench/models/ensemble_generation.py ensemble_methods=\[dynamicbind\] input_csv_filepath=data/test_cases/casp15/ensemble_inputs.csv output_dir=data/test_cases/casp15/top_dynamicbind_ensemble_predictions_1 skip_existing=true relax_method_ligands_post_ranking=true export_file_format=casp15 export_top_n=5 combine_casp_output_files=true max_method_predictions=40 method_top_n_to_select=5 resume=true ensemble_benchmarking=true ensemble_benchmarking_dataset=casp15 cuda_device_index=0 ensemble_benchmarking_repeat_index=1
python3 posebench/models/ensemble_generation.py ensemble_methods=\[dynamicbind\] input_csv_filepath=data/test_cases/casp15/ensemble_inputs.csv output_dir=data/test_cases/casp15/top_dynamicbind_ensemble_predictions_1 skip_existing=true relax_method_ligands_post_ranking=false export_file_format=casp15 export_top_n=5 combine_casp_output_files=true max_method_predictions=40 method_top_n_to_select=3 resume=true ensemble_benchmarking=true ensemble_benchmarking_dataset=casp15 cuda_device_index=0 ensemble_benchmarking_repeat_index=1
python3 posebench/models/ensemble_generation.py ensemble_methods=\[dynamicbind\] input_csv_filepath=data/test_cases/casp15/ensemble_inputs.csv output_dir=data/test_cases/casp15/top_dynamicbind_ensemble_predictions_1 skip_existing=true relax_method_ligands_post_ranking=true export_file_format=casp15 export_top_n=5 combine_casp_output_files=true max_method_predictions=40 method_top_n_to_select=3 resume=true ensemble_benchmarking=true ensemble_benchmarking_dataset=casp15 cuda_device_index=0 ensemble_benchmarking_repeat_index=1
# NOTE: the suffixes for both `output_dir` and `ensemble_benchmarking_repeat_index` should be modified to e.g., 2, 3, ...
...
# now score the CASP15-compliant submissions using the official CASP scoring pipeline
Expand Down Expand Up @@ -572,8 +572,8 @@ Analyze inference results for the CASP15 dataset

```bash
# first assemble (unrelaxed and post ranking-relaxed) CASP15-compliant prediction submission files for scoring
python3 posebench/models/ensemble_generation.py ensemble_methods=\[neuralplexer\] input_csv_filepath=data/test_cases/casp15/ensemble_inputs.csv output_dir=data/test_cases/casp15/top_neuralplexer_ensemble_predictions_1 skip_existing=true relax_method_ligands_post_ranking=false export_file_format=casp15 export_top_n=5 combine_casp_output_files=true max_method_predictions=40 method_top_n_to_select=5 resume=true ensemble_benchmarking=true ensemble_benchmarking_dataset=casp15 cuda_device_index=0 ensemble_benchmarking_repeat_index=1
python3 posebench/models/ensemble_generation.py ensemble_methods=\[neuralplexer\] input_csv_filepath=data/test_cases/casp15/ensemble_inputs.csv output_dir=data/test_cases/casp15/top_neuralplexer_ensemble_predictions_1 skip_existing=true relax_method_ligands_post_ranking=true export_file_format=casp15 export_top_n=5 combine_casp_output_files=true max_method_predictions=40 method_top_n_to_select=5 resume=true ensemble_benchmarking=true ensemble_benchmarking_dataset=casp15 cuda_device_index=0 ensemble_benchmarking_repeat_index=1
python3 posebench/models/ensemble_generation.py ensemble_methods=\[neuralplexer\] input_csv_filepath=data/test_cases/casp15/ensemble_inputs.csv output_dir=data/test_cases/casp15/top_neuralplexer_ensemble_predictions_1 skip_existing=true relax_method_ligands_post_ranking=false export_file_format=casp15 export_top_n=5 combine_casp_output_files=true max_method_predictions=40 method_top_n_to_select=3 resume=true ensemble_benchmarking=true ensemble_benchmarking_dataset=casp15 cuda_device_index=0 ensemble_benchmarking_repeat_index=1
python3 posebench/models/ensemble_generation.py ensemble_methods=\[neuralplexer\] input_csv_filepath=data/test_cases/casp15/ensemble_inputs.csv output_dir=data/test_cases/casp15/top_neuralplexer_ensemble_predictions_1 skip_existing=true relax_method_ligands_post_ranking=true export_file_format=casp15 export_top_n=5 combine_casp_output_files=true max_method_predictions=40 method_top_n_to_select=3 resume=true ensemble_benchmarking=true ensemble_benchmarking_dataset=casp15 cuda_device_index=0 ensemble_benchmarking_repeat_index=1
# NOTE: the suffixes for both `output_dir` and `ensemble_benchmarking_repeat_index` should be modified to e.g., 2, 3, ...
...
# now score the CASP15-compliant submissions using the official CASP scoring pipeline
Expand Down Expand Up @@ -640,8 +640,8 @@ Analyze inference results for the CASP15 dataset

```bash
# first assemble (unrelaxed and post ranking-relaxed) CASP15-compliant prediction submission files for scoring
python3 posebench/models/ensemble_generation.py ensemble_methods=\[rfaa\] input_csv_filepath=data/test_cases/casp15/ensemble_inputs.csv output_dir=data/test_cases/casp15/top_rfaa_ensemble_predictions_1 skip_existing=true relax_method_ligands_post_ranking=false export_file_format=casp15 export_top_n=5 combine_casp_output_files=true max_method_predictions=40 method_top_n_to_select=5 resume=true ensemble_benchmarking=true ensemble_benchmarking_dataset=casp15 cuda_device_index=0 ensemble_benchmarking_repeat_index=1
python3 posebench/models/ensemble_generation.py ensemble_methods=\[rfaa\] input_csv_filepath=data/test_cases/casp15/ensemble_inputs.csv output_dir=data/test_cases/casp15/top_rfaa_ensemble_predictions_1 skip_existing=true relax_method_ligands_post_ranking=true export_file_format=casp15 export_top_n=5 combine_casp_output_files=true max_method_predictions=40 method_top_n_to_select=5 resume=true ensemble_benchmarking=true ensemble_benchmarking_dataset=casp15 cuda_device_index=0 ensemble_benchmarking_repeat_index=1
python3 posebench/models/ensemble_generation.py ensemble_methods=\[rfaa\] input_csv_filepath=data/test_cases/casp15/ensemble_inputs.csv output_dir=data/test_cases/casp15/top_rfaa_ensemble_predictions_1 skip_existing=true relax_method_ligands_post_ranking=false export_file_format=casp15 export_top_n=5 combine_casp_output_files=true max_method_predictions=40 method_top_n_to_select=3 resume=true ensemble_benchmarking=true ensemble_benchmarking_dataset=casp15 cuda_device_index=0 ensemble_benchmarking_repeat_index=1
python3 posebench/models/ensemble_generation.py ensemble_methods=\[rfaa\] input_csv_filepath=data/test_cases/casp15/ensemble_inputs.csv output_dir=data/test_cases/casp15/top_rfaa_ensemble_predictions_1 skip_existing=true relax_method_ligands_post_ranking=true export_file_format=casp15 export_top_n=5 combine_casp_output_files=true max_method_predictions=40 method_top_n_to_select=3 resume=true ensemble_benchmarking=true ensemble_benchmarking_dataset=casp15 cuda_device_index=0 ensemble_benchmarking_repeat_index=1
# NOTE: the suffixes for both `output_dir` and `ensemble_benchmarking_repeat_index` should be modified to e.g., 2, 3, ...
...
# now score the CASP15-compliant submissions using the official CASP scoring pipeline
Expand Down Expand Up @@ -712,8 +712,8 @@ Analyze inference results for the CASP15 dataset

```bash
# assemble (unrelaxed and post ranking-relaxed) CASP15-compliant prediction submission files for scoring
python3 posebench/models/ensemble_generation.py ensemble_methods=\[vina\] vina_binding_site_methods=\[diffdock\] input_csv_filepath=data/test_cases/casp15/ensemble_inputs.csv output_dir=data/test_cases/casp15/top_vina_diffdock_ensemble_predictions_1 skip_existing=true relax_method_ligands_post_ranking=false export_file_format=casp15 export_top_n=5 combine_casp_output_files=true max_method_predictions=40 method_top_n_to_select=5 resume=true ensemble_benchmarking=true ensemble_benchmarking_dataset=casp15 cuda_device_index=0 ensemble_benchmarking_repeat_index=1
python3 posebench/models/ensemble_generation.py ensemble_methods=\[vina\] vina_binding_site_methods=\[diffdock\] input_csv_filepath=data/test_cases/casp15/ensemble_inputs.csv output_dir=data/test_cases/casp15/top_vina_diffdock_ensemble_predictions_1 skip_existing=true relax_method_ligands_post_ranking=true export_file_format=casp15 export_top_n=5 combine_casp_output_files=true max_method_predictions=40 method_top_n_to_select=5 resume=true ensemble_benchmarking=true ensemble_benchmarking_dataset=casp15 cuda_device_index=0 ensemble_benchmarking_repeat_index=1
python3 posebench/models/ensemble_generation.py ensemble_methods=\[vina\] vina_binding_site_methods=\[diffdock\] input_csv_filepath=data/test_cases/casp15/ensemble_inputs.csv output_dir=data/test_cases/casp15/top_vina_diffdock_ensemble_predictions_1 skip_existing=true relax_method_ligands_post_ranking=false export_file_format=casp15 export_top_n=5 combine_casp_output_files=true max_method_predictions=40 method_top_n_to_select=3 resume=true ensemble_benchmarking=true ensemble_benchmarking_dataset=casp15 cuda_device_index=0 ensemble_benchmarking_repeat_index=1
python3 posebench/models/ensemble_generation.py ensemble_methods=\[vina\] vina_binding_site_methods=\[diffdock\] input_csv_filepath=data/test_cases/casp15/ensemble_inputs.csv output_dir=data/test_cases/casp15/top_vina_diffdock_ensemble_predictions_1 skip_existing=true relax_method_ligands_post_ranking=true export_file_format=casp15 export_top_n=5 combine_casp_output_files=true max_method_predictions=40 method_top_n_to_select=3 resume=true ensemble_benchmarking=true ensemble_benchmarking_dataset=casp15 cuda_device_index=0 ensemble_benchmarking_repeat_index=1
# NOTE: the suffixes for both `output_dir` and `ensemble_benchmarking_repeat_index` should be modified to e.g., 2, 3, ...
...
# now score the CASP15-compliant submissions using the official CASP scoring pipeline
Expand Down Expand Up @@ -758,8 +758,8 @@ Analyze inference results for the CASP15 dataset

```bash
# then assemble (unrelaxed and post ranking-relaxed) CASP15-compliant prediction submission files for scoring
python3 posebench/models/ensemble_generation.py ensemble_methods=\[tulip\] input_csv_filepath=data/test_cases/casp15/ensemble_inputs.csv output_dir=data/test_cases/casp15/top_tulip_ensemble_predictions_1 skip_existing=true relax_method_ligands_post_ranking=false export_file_format=casp15 export_top_n=5 combine_casp_output_files=true max_method_predictions=40 method_top_n_to_select=5 resume=true ensemble_benchmarking=true ensemble_benchmarking_dataset=casp15 cuda_device_index=0 ensemble_benchmarking_repeat_index=1
python3 posebench/models/ensemble_generation.py ensemble_methods=\[tulip\] input_csv_filepath=data/test_cases/casp15/ensemble_inputs.csv output_dir=data/test_cases/casp15/top_tulip_ensemble_predictions_1 skip_existing=true relax_method_ligands_post_ranking=true export_file_format=casp15 export_top_n=5 combine_casp_output_files=true max_method_predictions=40 method_top_n_to_select=5 resume=true ensemble_benchmarking=true ensemble_benchmarking_dataset=casp15 cuda_device_index=0 ensemble_benchmarking_repeat_index=1
python3 posebench/models/ensemble_generation.py ensemble_methods=\[tulip\] input_csv_filepath=data/test_cases/casp15/ensemble_inputs.csv output_dir=data/test_cases/casp15/top_tulip_ensemble_predictions_1 skip_existing=true relax_method_ligands_post_ranking=false export_file_format=casp15 export_top_n=5 combine_casp_output_files=true max_method_predictions=40 method_top_n_to_select=3 resume=true ensemble_benchmarking=true ensemble_benchmarking_dataset=casp15 cuda_device_index=0 ensemble_benchmarking_repeat_index=1
python3 posebench/models/ensemble_generation.py ensemble_methods=\[tulip\] input_csv_filepath=data/test_cases/casp15/ensemble_inputs.csv output_dir=data/test_cases/casp15/top_tulip_ensemble_predictions_1 skip_existing=true relax_method_ligands_post_ranking=true export_file_format=casp15 export_top_n=5 combine_casp_output_files=true max_method_predictions=40 method_top_n_to_select=3 resume=true ensemble_benchmarking=true ensemble_benchmarking_dataset=casp15 cuda_device_index=0 ensemble_benchmarking_repeat_index=1
# NOTE: the suffixes for both `output_dir` and `ensemble_benchmarking_repeat_index` should be modified to e.g., 2, 3, ...
...
# now score the CASP15-compliant submissions using the official CASP scoring pipeline
Expand Down
2 changes: 1 addition & 1 deletion configs/model/ensemble_generation.yaml
View file
Original file line number Diff line number Diff line change
Expand Up @@ -11,7 +11,7 @@ structure_prediction_chunk_size: null # optional chunk size to use during ESMFol
structure_prediction_cpu_only: false # whether to only use CPU for structure prediction
structure_prediction_cpu_offload: false # whether to offload structure prediction to CPU
max_method_predictions: 40 # maximum number of predictions to make with each method
method_top_n_to_select: 5 # number of top-ranked predictions to select from each method for subsequent ranking
method_top_n_to_select: 3 # number of top-ranked predictions to select from each method for subsequent ranking
skip_existing: false # whether to skip existing ensemble predictions
relax_method_ligands_pre_ranking: false # whether to relax the predicted ligands (method-specifically) before ranking
relax_method_ligands_post_ranking: true # whether to relax the predicted ligands (method-agnostically) after ranking
Expand Down
5 changes: 3 additions & 2 deletions notebooks/adding_new_dataset_tutorial.ipynb
View file
Original file line number Diff line number Diff line change
Expand Up @@ -16,12 +16,13 @@
"\n",
"`PoseBench` encompasses several datasets for benchmarking protein-ligand structure generation methods. However, you may want to add your own dataset to `PoseBench` to fulfill a specific use case or to test a specific idea. This tutorial will show you how to do so for a new collection of *single*-ligand protein complexes. For help integrating a new *multi*-ligand protein complex dataset, please create a new GitHub issue or send us an email. We would be happy to help you add this new collection to the benchmark!\n",
"\n",
"To add your custom *single*-ligand dataset to `PoseBench`, you just have to follow the following 4-step procedure:\n",
"To add your custom *single*-ligand dataset to `PoseBench`, you just have to follow the following 5-step procedure:\n",
"\n",
"1. Create a new directory under `data/` with the required suffix `_set` (e.g., `data/newest_set/`) and group your (ground-truth) data files by unique IDs within this new directory (e.g., `data/newest_set/1G9V_RQ4/1G9V_RQ4_{protein.pdb,ligand.sdf}`)\n",
"2. Update the config files throughout `configs/analysis/`, `configs/data/`, and `configs/model/` to list your new dataset as a CLI argument (e.g., `dataset: newest`)\n",
"3. Predict `apo` protein structures for your new dataset using a structure predictor of your choice (e.g., ESMFold) by integrating parsing for your dataset into the prediction-related source code within `src/data/components/protein_fasta_preparation.py` and `src/data/components/protein_apo_to_holo_alignment.py`\n",
"4. Using `notebooks/posebusters_astex_inference_results_plotting.ipynb` as a template, add a new Jupyter notebook to `notebooks/` for plotting each method's results on your new dataset (after preparing each method's dataset inputs and running inference with each desired method)"
"4. Using `notebooks/posebusters_astex_inference_results_plotting.ipynb` as a template, add a new Jupyter notebook to `notebooks/` for plotting each method's results on your new dataset (after preparing each method's dataset inputs and running inference with each desired method)\n",
"5. To enable convenient inference sweeps with your new dataset, add support for your new dataset to `scripts/build_inference_script.py`"
]
},
{
Expand Down
Loading

0 comments on commit 0d9781f

Please sign in to comment.