bio-ml-docking-rescoring
Performs ML-based protein-ligand pose prediction and scoring using DiffDock-L (diffusion-based), Boltz-1 / Boltz-2 (foundation model with affinity), Chai-1, AlphaFold3 ligand, EquiBind, TANKBind, NeuralPLexer, and hybrid workflows (DiffDock pose + GNINA rescore + PoseBusters QC). Explicit handling of when ML beats classical docking, when classical beats ML, the PB-invalid pose problem, and rescoring as the standard production hybrid. Use when modern docking is needed: foundation-model ligand-pose prediction, AI rescoring of classical poses, or scaffold-hopping in cross-docking scenarios.
npx skills add BioTender-max/awesome-bio-agent-skills --skill ml-docking-rescoring --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
## Version Compatibility Reference examples tested with: DiffDock-L (Corso 2024), Boltz-1 1.0+, Boltz-2 (Wohlwend 2025), Chai-1 0.4+, AlphaFold3 (DeepMind), EquiBind, TANKBind, GNINA 1.1+, PoseBusters 0.6+. Before using code patterns, verify installed versions match. If versions differ: - Python: `pip show <package>` then `help(module.function)` to check signatures - CLI: `diffdock --version`; `boltz --version` If code throws ImportError, AttributeError, or TypeError, introspect the installed package and adapt the example to match the actual API rather than retrying. # ML Docking and Rescoring Use machine learning models for protein-ligand pose prediction and affinity scoring. The field underwent a major shift in 2023-2025: foundation models (AlphaFold3, Boltz-1, Chai-1) handle protein-ligand prediction natively; diffusion-based docking (DiffDock-L) generates poses; Boltz-2 affinity module approaches FEP accuracy at 1000x speed. Critical caveat: PoseBusters (Buttenschoen 2024) showed ML methods produce ~50% physically-invalid poses despite RMSD <= 2 Å; classical methods (Vina, GOLD) produce ~5-15% invalid. The postdoc-grade workflow is hybrid: ML for pose sampling + classical resco
- Version Compatibility
- ML Docking Method Taxonomy
- Decision Tree by Scenario
- PoseBusters Problem (Critical)
- DiffDock-L + GNINA Hybrid Workflow (Production Standard)
- Boltz-2 for Affinity (Modern Alternative to FEP First-Pass)
- AlphaFold3 Ligand Prediction
- Chai-1 (Open Alternative to AlphaFold3)
- ML Docking Failure Modes by Tool
- DiffDock-L -- PB-invalid poses
- EquiBind -- bond length distortion
- TANKBind -- vdW overlap with protein
- Boltz-2 affinity -- novel chemotype error
- AlphaFold3 / Boltz-1 -- novel target
Step 1: DiffDock-L pose sampling (DiffDock has no `diffdock_inference` binary; the canonical entrypoint is `python -m inference` from the DiffDock checkout with either `--protein_ligand_csv` or `--complex_name --protein_path --ligand_description`) python -m inference \ Step 2: GNINA CNN rescoring gnina -r receptor.pdb -l diffdock_out/poses.sdf \ Step 3: PoseBusters validation posebusters bust \
What does the bio-ml-docking-rescoring skill do?
Performs ML-based protein-ligand pose prediction and scoring using DiffDock-L (diffusion-based), Boltz-1 / Boltz-2 (foundation model with affinity), Chai-1, AlphaFold3 ligand, EquiBind, TANKBind, NeuralPLexer, and hybrid workflows (DiffDock pose + GNINA rescore + PoseBusters QC). Explicit handling of when ML beats classical docking, when classical beats ML, the PB-invalid pose problem, and rescoring as the standard production hybrid. Use when modern docking is needed: foundation-model ligand-pose prediction, AI rescoring of classical poses, or scaffold-hopping in cross-docking scenarios.
How do I install it?
Run `npx skills add BioTender-max/awesome-bio-agent-skills --skill ml-docking-rescoring --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From BioTender-max/awesome-bio-agent-skills, a repository with 135 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.