Tooluniverse Binder Discovery

This is a structured workflow for finding small molecule binders against protein targets using 60+ ToolUniverse tools. It walks Claude through druggability assessment, known ligand mining from ChEMBL and BindingDB, similarity expansion, ADMET filtering, and synthesis feasibility checks. The workflow is opinionated about methodology: it creates a markdown report file first, then populates it progressively while hiding tool outputs from the user. It includes binding site reasoning upfront to catch undruggable targets like flat protein-protein interfaces before wasting time on screens. Good for hit identification and virtual screening when you want a systematic, evidence-graded approach rather than ad-hoc compound searches. Requires NVIDIA API key for structure prediction via AlphaFold2 or ESMFold.

skills.sh installs: 394
GitHub stars: 1.8K
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add mims-harvard/tooluniverse --skill tooluniverse-binder-discovery --agent claude-code

Installs into .claude/skills of the current project.

Files

Small Molecule Binder Discovery Strategy

Systematic discovery of novel small molecule binders using 60+ ToolUniverse tools across druggability assessment, known ligand mining, similarity expansion, ADMET filtering, and synthesis feasibility.

LOOK UP DON'T GUESS - Always retrieve actual data from tools before drawing conclusions. Do not assume druggability, binding sites, or compound properties based on target class alone.

KEY PRINCIPLES:

Report-first approach - Create report file FIRST, then populate progressively
Target validation FIRST - Confirm druggability before compound searching
Multi-strategy approach - Combine structure-based and ligand-based methods
ADMET-aware filtering - Eliminate poor compounds early
Evidence grading - Grade candidates by supporting evidence
Actionable output - Provide prioritized candidates with rationale
English-first queries - Always use English terms in tool calls. Respond in the user's language