liveBook · Manning

Vina scoring function

As explained in Build AI Drug Discovery Pipelines

The Vina scoring function is AutoDock Vina's empirical function for estimating ligand binding favorability from pairwise atomic interaction terms and penalties.

The Vina scoring function estimates docking quality while AutoDock Vina searches ligand poses inside a defined binding box. Preparation still matters: protonation, atom typing, and hydrogen placement determine which atoms Vina scores. section 9.1.4

Using the Vina scoring function

A Python docking wrapper initializes Vina with sf_name='vina', assigns a prepared receptor, loads a ligand PDBQT file, computes maps for the binding box, and returns docked poses. Gasteiger charges may be computed during preparation, but Vina does not read them directly. section 9.1.4

How Build AI Drug Discovery Pipelines covers it

How deep it goes
Explains preparation effects and API selection, but does not detail the scoring formula or individual interaction terms.
Examples
Uses prepared protein and ligand PDBQT files, Gasteiger charge assignment, and a Python Vina docking wrapper.
What it assumes
Assumes prepared protein and ligand PDBQT files while emphasizing protonation, atom typing, and hydrogen placement.
What you can do after
Operate/configure AutoDock Vina through its Python API with prepared structures and a defined binding box.
How it connects
Connects docking, binding sites, PDBQT files, atom typing, protonation, and alternative scoring functions.

This explainer was generated by Manning's knowledge graph from the text of Build AI Drug Discovery Pipelines. The section links point to the parts of the book it draws on.