Switch from 'src' to 'posebench' for package name

Author: amorehead

.pre-commit-config.yaml

@@ -70,7 +70,7 @@ repos:
             --ignore-nested-functions,
             -vv,
           ]
-        exclude: ^src/analysis/casp15_ligand_scoring/
+        exclude: ^posebench/analysis/casp15_ligand_scoring/
 
   # python check (PEP8), programming errors and code complexity
   - repo: https://github.com/PyCQA/flake8
@@ -82,7 +82,7 @@ repos:
             "--extend-ignore",
             "E203,E402,E501,F401,F841,RST2,RST301",
             "--exclude",
-            "logs/*,data/*,src/analysis/casp15_ligand_scoring/*",
+            "logs/*,data/*,posebench/analysis/casp15_ligand_scoring/*",
           ]
         additional_dependencies: [flake8-rst-docstrings==0.3.0]
 
@@ -126,7 +126,7 @@ repos:
     hooks:
       - id: codespell
         args:
-          - --skip=logs/**,data/**,*.ipynb,src/utils/data_utils.py,src/utils/residue_utils.py,src/data/components/esmfold_fasta_preparation.py,src/models/minimize_energy.py,src/data/components/create_casp15_ensemble_input_csv.py,src/analysis/casp15_ligand_scoring/casp_parser.py
+          - --skip=logs/**,data/**,*.ipynb,posebench/utils/data_utils.py,posebench/utils/residue_utils.py,posebench/data/components/esmfold_fasta_preparation.py,posebench/models/minimize_energy.py,posebench/data/components/create_casp15_ensemble_input_csv.py,posebench/analysis/casp15_ligand_scoring/casp_parser.py
           # - --ignore-words-list=abc,def
 
   # jupyter notebook cell output clearing

Makefile

@@ -27,4 +27,4 @@ test-full: ## Run all tests
 	pytest
 
 train: ## Train the model
-	python src/train.py
+	python posebench/train.py

README.md

@@ -1,6 +1,6 @@
 full_report: true # whether to generate a full PoseBusters report (i.e. with all metrics) or a summary report (i.e. with only the most important metrics)
 python_exec_path: ${oc.env:HOME}/mambaforge/envs/casp15_ligand_scoring/bin/python3 # the Python executable to use
-scoring_script_path: ${oc.env:PROJECT_ROOT}/src/analysis/casp15_ligand_scoring/score_predictions.py # the path to the script to use for scoring CASP predictions
+scoring_script_path: ${oc.env:PROJECT_ROOT}/posebench/analysis/casp15_ligand_scoring/score_predictions.py # the path to the script to use for scoring CASP predictions
 method: diffdock # the method for which to score predictions - NOTE: must be one of (`diffdock`, `fabind`, `dynamicbind`, `neuralplexer`, `rfaa`, `vina`, `ensemble`, `tulip`)
 vina_binding_site_method: diffdock # the method to use for Vina binding site prediction - NOTE: must be one of (`diffdock`, `fabind`, `dynamicbind`, `neuralplexer`, `rfaa`)
 dataset: casp15 # the dataset to use - NOTE: must be one of (`casp15`)

configs/analysis/inference_analysis_casp.yaml

@@ -5,7 +5,7 @@ output_bash_file_dir: ensemble_generation_scripts # the directory in which to sa
 cuda_device_index: 0 # the CUDA device to use for inference, or `null` to use CPU
 input_csv_filepath: ${oc.env:PROJECT_ROOT}/data/test_cases/5S8I_2LY/ensemble_inputs.csv # path to a CSV file containing the following columns: `protein_input`, `ligand_smiles`, `name`
 temp_protein_dir: ${oc.env:PROJECT_ROOT}/data/ensemble_proteins # directory path to which to save temporary predicted protein structures
-structure_prediction_script_path: ${oc.env:PROJECT_ROOT}/src/data/components/esmfold_batch_structure_prediction.py # path to the ESMFold structure prediction script to use
+structure_prediction_script_path: ${oc.env:PROJECT_ROOT}/posebench/data/components/esmfold_batch_structure_prediction.py # path to the ESMFold structure prediction script to use
 structure_prediction_chunk_size: null # optional chunk size to use during ESMFold structure prediction to reduce memory requirements
 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
@@ -103,7 +103,7 @@ rfaa_exec_dir: ${oc.env:PROJECT_ROOT}/forks/RoseTTAFold-All-Atom # the RoseTTAFo
 rfaa_config_dir: ${oc.env:PROJECT_ROOT}/forks/RoseTTAFold-All-Atom/rf2aa/config/inference # the config directory with which to run inference
 rfaa_output_dir: ${oc.env:PROJECT_ROOT}/forks/RoseTTAFold-All-Atom/inference/rfaa_ensemble_outputs # the output directory to which to save the inference results
 rfaa_max_cycles: 10 # the maximum number recycling iterations to run
-rfaa_inference_config_name: null # the name of the inference config to use - NOTE: if `run_inference_directly` is true, this must reference a valid YAML config file name e.g., that was generated by `python src/models/rfaa_inference.py` with `run_inference_directly=false`
+rfaa_inference_config_name: null # the name of the inference config to use - NOTE: if `run_inference_directly` is true, this must reference a valid YAML config file name e.g., that was generated by `python posebench/models/rfaa_inference.py` with `run_inference_directly=false`
 rfaa_inference_dir_name: null # the name of the inference output directory to use
 # Vina inference arguments:
 vina_binding_site_methods: [diffdock] # the methods to use for Vina binding site prediction - NOTE: must be one of (`diffdock`, `fabind`, `dynamicbind`, `neuralplexer`, `rfaa`)

configs/model/ensemble_generation.yaml

@@ -7,7 +7,7 @@ output_dir: ${oc.env:PROJECT_ROOT}/forks/RoseTTAFold-All-Atom/prediction_outputs
 max_cycles: 10 # the maximum number of recycling iterations to run
 cuda_device_index: 0 # the CUDA device to use for inference, or `null` to use CPU
 run_inference_directly: false # whether to run the inference code directly (true) or to rely on the user to run the generated scripts manually (false)
-inference_config_name: null # the name of the inference config to use - NOTE: if `run_inference_directly` is true, this must reference a valid YAML config file name e.g., that was generated by `python src/models/rfaa_inference.py` with `run_inference_directly=false`
+inference_config_name: null # the name of the inference config to use - NOTE: if `run_inference_directly` is true, this must reference a valid YAML config file name e.g., that was generated by `python posebench/models/rfaa_inference.py` with `run_inference_directly=false`
 inference_dir_name: null # the name of the inference output directory to use
 repeat_index: 1 # the repeat index to use for inference
 skip_existing: true # whether to skip running inference if the prediction for a target already exists