---
title: Fold, find pockets, dock, triage
description: >-
  From a protein sequence to a druggable pocket with a verified docking pose and
  an ADMET read — the standard structure-first entry point.
tags:
  - recipes
  - structure
  - docking
  - admet
tools:
  - esmfold
  - p2rank
  - diffdock
  - admet_ai
time: 2–10 min
---

**Best fit:** you have a target (a sequence or a UniProt ID) and want to know its shape, where a molecule could bind it, and whether a candidate compound looks tractable — in one pass.

**Try this prompt** — [open in a guest chat](/chat/new?guest=true&prompt=I%20want%20to%20see%20the%203D%20conformation%20of%20the%20EGFR%20kinase%20domain%20(P00533%2C%20residues%20696-1022)%20and%20every%20druggable%20binding%20pocket%20on%20it%20%E2%80%94%20which%20pockets%20beyond%20the%20ATP%20site%20score%20above%200.5%20druggability%2C%20and%20which%20is%20the%20best%20candidate%20for%20an%20allosteric%20fragment%20screen%20with%20verified%20pose%20docking%3F).

> I want to see the 3D conformation of the EGFR kinase domain (P00533, residues 696-1022) and every druggable binding pocket on it — which pockets beyond the ATP site score above 0.5 druggability, and which is the best candidate for an allosteric fragment screen with verified pose docking?

_A real `fold-then-pockets` quick-action prompt — open it in a guest chat, then swap in your own compound or target._

## The prompt

```text
I want the 3D shape of KRAS G12C (UniProt P01116) and every druggable pocket
on it — focus on the Switch II binding site and check whether sotorasib's
covalent binding mode is recapitulated. Then assess drug-likeness on the docked
compound and tell me which non-Switch-II pockets score above 0.5 druggability
for a non-covalent allosteric back-up.
```

## What it does

The orchestrator runs a structure-first chain, passing each result into the next:

1. **[ESMFold](/docs/esmfold)** predicts the 3D conformation from the sequence.
2. **[P2Rank](/docs/p2rank)** scores druggable pockets on that structure.
3. **[DiffDock](/docs/diffdock)** docks the named ligand into the pocket of interest and returns a pose with a confidence score.
4. **[ADMET-AI](/docs/admet-ai)** reads drug-likeness on the docked compound.

## Watch for

- **Low-confidence regions.** pLDDT below 70 marks disordered loops or uncertain geometry — treat pockets that sit in those regions with caution.
- **Pose plausibility.** A high DiffDock confidence is not proof; check whether the pose recapitulates a known binding mode, as the prompt asks.
- **Covalent binders.** Docking scores non-covalent poses; a covalent warhead's true binding mode may not be captured by the score alone.

## Read next

- [Which tool?](/docs/which-tool#structure) — pick a different structure or docking tool.
- [Hit to lead](/docs/workflows/hit-to-lead) — carry a docked hit forward to synthesis.
- [Virtual screening](/docs/workflows/virtual-screening) — the guided version: library docking step by step.