agentsclimarketplace
Sign in

Molecule evolution agent

Skill FridrichMethod/awesome-skills/skills/molecule-evolution-agent

Evolve MoleculesFrom its SKILL.md

Install
npx -y skills add FridrichMethod/awesome-skills --skill molecule-evolution-agent

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

2 things to look at

  • no licenseNo license file was found in the repository. Code published without one is not open source by default, so using it at work is a question for whoever answers licensing questions where you are.
  • 13 stars13 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

SKILL.md

2.0 KB, 471 tokens by cl100k_base, as published. Nobody here has run it

<!-- # COPYRIGHT NOTICE # This file is part of the "Universal Biomedical Skills" project. # Copyright (c) 2026 MD BABU MIA, PhD <[email protected]> # All Rights Reserved. # # This code is proprietary and confidential. # Unauthorized copying of this file, via any medium is strictly prohibited. # # Provenance: Authenticated by MD BABU MIA -->

Molecule Evolution Agent

The Molecule Evolution Agent acts as an autonomous medicinal chemist. It takes a starting molecule (or uses a default like Aspirin) and iteratively modifies its structure to optimize binding for a specific protein target.

When to Use This Skill

  • Lead Optimization: When you have a hit molecule and want to improve its potency.
  • De Novo Design: To explore chemical space around a target protein.
  • Idea Generation: To get creative structural modifications suggested by an LLM.

Core Capabilities

  1. SMILES Manipulation: Reads and writes chemical structures in SMILES format.
  2. LLM Chemist: Uses an LLM to suggest chemically valid modifications (e.g., "Add a fluorine group to the ring").
  3. Mock Scoring: (Currently) Uses a mock scoring function to simulate docking affinity.

Workflow

  1. Input: Target Protein Name (e.g., "GPRC5D").
  2. Process:
    • Start with a seed molecule.
    • Loop for N generations.
    • Ask LLM for a modification.
    • Score the new molecule.
    • Keep the best candidate.
  3. Output: Top candidate SMILES and the evolution history.

Example Usage

User: "Design a better binder for GPRC5D."

Agent Action:

python3 Skills/Drug_Discovery/Molecule_Design/evolution_agent.py
# (Note: The script currently defaults to GPRC5D, but can be extended for arguments)
<!-- AUTHOR_SIGNATURE: 9a7f3c2e-MD-BABU-MIA-2026-MSSM-SECURE -->

What ships with it: 2 files

3.0 KB alongside SKILL.md, 1 of them executable

Keep looking

Skills are one crate of 326,452. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.