DockM8_v1.1_Lit-PCBA_benchmarking_data_part3

Résumé fourni par la source

DockM8 v1.1 — Lit-PCBA benchmark data (Part 3 of 3)==================================================== This repository contains benchmarking data for the Lit-PCBA datasetproduced with DockM8 v1.1. It is intended for benchmarking scoringfunctions and machine-learning models, and as a large archive ofpre-docked poses generated by multiple docking algorithms. Because of Zenodo's per-record size limit, the Lit-PCBA data is splitacross THREE companion records, which must all be downloaded: lit-pcba_1.tar.bz2 lit-pcba_2.tar.bz2 lit-pcba_3.tar.bz2 Archive layout (nested compression)----------------------------------- The files are NOT directly browsable — each Zenodo download is acompressed archive of compressed archives of gzipped SDFs. You mustuse the `extract_zenodo.py` helper from the DockM8 v1.1 repositoryto unpack them. lit-pcba_N.tar.bz2 # outer archive (Zenodo download)└── phase2/ └── [target_name].tar.bz2 # one inner archive per Lit-PCBA target └── [target_name]/ ├── [target]_activity_data.csv # experimental binding data ├── [target]_docking_library.sdf # compounds to dock ├── [target]_ligand.sdf # reference ligand(s) ├── [target]_pocket.pdb # binding-site definition ├── [target]_pocket.pdbqt # binding site (AutoDock format) ├── [target]_protein.pdb # original structure ├── [target]_protein_prepared.pdb # prepared for docking └── results/ ├── allposes.sdf.gz # combined poses (gzipped) ├── allposes_rescored.csv # scores for all poses ├── [target]_prepared_library.sdf.gz ├── [docking_program]/ # per-engine outputs │ ├── [program]_poses.sdf.gz # raw poses (gzipped) │ └── [program]_poses_rescored.sdf.gz ├── performance/ │ └── [target]_[program]_[pose_selection]_performance.csv ├── scores/ │ └── [target]_[program]_[pose_selection]_scores.csv └── clustering/ └── [target]_[program]_[pose_selection]_selected_poses.sdf.gz How to extract-------------- Clone the DockM8 repo (main branch) and run the helper script — itreverses all three compression layers in one command: git clone https://github.com/DrugBud-Suite/DockM8.git cd DockM8 # Put all three downloaded archives in the same folder, then: python -m analysis.extract_zenodo /path/to/downloads /path/to/output # Or extract only specific parts: python -m analysis.extract_zenodo /path/to/downloads /path/to/output \ --archives lit-pcba_1.tar.bz2,lit-pcba_2.tar.bz2 The script will: 1. Extract the outer .tar.bz2, 2. Extract each per-target inner .tar.bz2, 3. Decompress every *.sdf.gz in place. Output layout: /path/to/output/lit-pcba/ ├── PART_1/ ├── PART_2/ └── PART_3/ IMPORTANT: Do NOT attempt manual extraction with `tar -xjf` alone —you will be left with nested tarballs and thousands of unreadable.sdf.gz files. Always use the helper script.

Ce résumé expose les affirmations des auteurs. BNTIC ne l’interprète pas comme une validation indépendante des résultats.