Predict protein–ligand binding poses with per-pose confidence scores.
npx skills add https://github.com/shushuzn/Rairos --skill diffdock-shushuzn
Please help me install this Agent Skill. Skill: diffdock Source: https://github.com/shushuzn/Rairos/tree/main/skills/diffdock Command: npx skills add https://github.com/shushuzn/Rairos --skill diffdock-shushuzn
DiffDock solves the problem of identifying plausible 3D binding poses of small molecules in a protein binding site without running traditional docking search heuristics.
Run DiffDock inference for a protein PDB and a ligand SMILES to generate ranked pose SDF files and confidence scores in an output folder.
High-intent search queries and answers about installing and using this skill.
To predict protein-ligand binding poses, you provide a protein PDB file and a ligand SMILES string as inputs. The diffusion-based model generates ranked 3D binding poses and outputs them as SDF files along with confidence scores.
Yes, you can run batch virtual screening by providing a protein-ligand CSV file. This allows you to process large-scale docking campaigns for multiple complexes and receive ranked 3D poses with confidence scores.
Protein-ligand docking with this diffusion model does not provide binding affinity prediction. It generates 3D binding poses and per-pose confidence scores for ranking, requiring separate tools for ΔG or Kd affinity calculations.
You do not need an existing protein structure for molecular docking. You can provide a protein sequence, which is processed via ESMFold to generate a structure, alongside your small-molecule ligand input.
Supported small-molecule ligand input formats for structure-based drug design include SMILES strings and SDF or MOL2 files. These are combined with a protein_path or protein_sequence to run docking inference.
Diffusion models identify plausible 3D binding poses of small molecules without relying on traditional docking search heuristics. They provide per-pose confidence scores to help prioritize which generated structures to inspect next.
robinbarvaagPredict 3D ligand binding poses to protein targets using diffusion models.
ovachieverPredict protein-ligand docking poses and confidence scores from PDB structures or sequences.
AlterLab-IEUPredict protein-ligand binding poses and confidence scores via diffusion-model docking.
EdanStarfireMap direct changes, ripple dependencies, and side effects across code, APIs, and data models.
