Generate protein-ligand docking poses with diffusion models and confidence scores.
npx skills add https://github.com/OwnLabAI/ownlab --skill diffdock-ownlabai
Please help me install this Agent Skill. Skill: diffdock Source: https://github.com/OwnLabAI/ownlab/tree/main/mart/skills/scientific-skills/diffdock Command: npx skills add https://github.com/OwnLabAI/ownlab --skill diffdock-ownlabai
DiffDock provides a method to predict plausible protein-ligand binding poses from structural inputs, delivering 3D pose coordinates and per-pose confidence scores while not estimating binding affinity.
Run a docking job by supplying a protein PDB and a ligand SMILES, then inspect the top poses and their confidence scores.
High-intent search queries and answers about installing and using this skill.
To predict protein-ligand docking poses, supply a protein PDB and ligand SMILES as inputs. The diffusion models generate 3D binding configurations and output multiple docking poses with corresponding per-pose confidence scores.
Diffusion-based molecular docking uses diffusion models to predict 3D binding configurations between proteins and ligands. It generates multiple plausible ligand poses within the binding site and assigns per-pose confidence scores for evaluation.
Yes, you can run batch molecular docking and ensemble docking. The workflow accepts multiple protein inputs and ligand structures, enabling differential and ensemble docking to generate 3D binding configurations at scale.
You do not need a pre-folded structure for molecular docking; you can use a protein sequence. The workflow supports optional protein folding via ESMFold to generate the required 3D structures before predicting docking poses.
No, diffusion-based molecular docking does not estimate binding affinity. It predicts 3D binding configurations and provides confidence scores, which require integration with downstream rescoring workflows like GNINA or MM/GBSA for affinity assessment.
Confidence scores evaluate docking pose plausibility but cannot estimate binding affinity during virtual screening. You must use downstream rescoring and refinement workflows like GNINA or MM/GBSA to assess affinity and validate the predicted 3D binding configurations.
qinyan-aiPredict ranked 3D binding poses for protein-ligand complexes from PDB and SMILES inputs.
LogauaEngstromPredict protein-ligand binding poses and confidence scores via diffusion-based docking.
jaechang-hitsPerform molecular docking with AutoDock Vina to predict protein-ligand binding poses and affinities.
silversteinPredict ranked protein–ligand binding poses with confidence scores from PDB structures or sequences and SMILES inputs.
