---
title: "Docking & MD overview"
description: "Locate the pocket, generate candidate poses for a small molecule, then rescore them by binding free energy — run as much of the arc as your question needs."
tags:
  - section
  - docking
generated: true
---

Docking answers whether and how a small molecule binds a target. It's a three-step arc — locate the pocket, generate candidate poses, then rescore them by binding free energy — and you run as much of it as your question needs. This is the core of structure-based hit finding and lead optimization.

> **Availability**

> These tools are metered by credits and gated by your plan — plans set your monthly credits, available model families, and which modal-app tools you can run. See [Plans & tiers](/docs/plans-and-tiers).

## What you can achieve here

- Find where a ligand could bind on a structure
- Predict a small molecule's binding pose
- Rescore poses by physics-based binding free energy
- Screen a set of compounds against one target

For which tool fits each, see [What you can achieve](/docs/capabilities).

## Tools in this section

| Tool | What it does |
|---|---|
| [DiffDock on the platform](/docs/diffdock) | Run blind, diffusion-based protein–ligand docking with DiffDock-L — confidence-ranked poses, not binding energies. |
| [MM-GBSA](/docs/mmgbsa) | Calculate binding free energies with GPU-accelerated MM-GBSA using OpenMM. |
| [P2Rank](/docs/p2rank) | Predict protein binding sites with ML-based pocket detection and druggability scoring. |

## Recipes using these tools

## Read next