biomni

Automate biomedical research tasks with code generation and database access.

8|Updated Nov 19, 2025
One-click install
npx skills add https://github.com/sanand0/scientific-research --skill biomni-sanand0
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: biomni
Source: https://github.com/sanand0/scientific-research/tree/main/.claude/skills/biomni
Command: npx skills add https://github.com/sanand0/scientific-research --skill biomni-sanand0

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill automates complex, multi-step biomedical research tasks, from experimental design to data analysis, by leveraging advanced AI reasoning and code execution.

Core Features & Use Cases

  • Autonomous Task Execution: Decomposes and executes complex biological queries across genomics, drug discovery, and clinical analysis.
  • Integrated Data Access: Utilizes ~11GB of biomedical databases for knowledge retrieval.
  • Code Generation & Execution: Dynamically creates and runs Python code for data processing and analysis pipelines.
  • Use Case: Design a CRISPR screen to identify genes regulating autophagy, analyze single-cell RNA-seq data, predict ADMET properties for drug candidates, or interpret GWAS results.

Quick Start

Use the biomni skill to design a CRISPR screen to identify genes regulating autophagy in HEK293 cells.

Frequently Asked Questions about biomni

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I automate CRISPR screening design for target genes?

CRISPR screening design is automated by decomposing biological queries into multi-step reasoning and code execution. You provide a target pathway, and the agent autonomously designs the screen using integrated biomedical databases and Python code generation.

Can I analyze single-cell RNA-seq data autonomously?

Single-cell RNA-seq analysis is supported through dynamic Python code generation and execution. The agent processes raw sequencing data by autonomously building and running analysis pipelines to identify cell populations and gene expression patterns.

How does ADMET prediction work for drug candidates?

ADMET prediction for drug candidates is performed by leveraging integrated access to large biomedical databases and code execution. The agent retrieves molecular properties and dynamically generates predictive models to assess pharmacokinetic profiles.

What's the best way to interpret GWAS results without manual coding?

GWAS interpretation is handled by autonomous multi-step reasoning that queries integrated biomedical databases and generates execution-ready Python code. The agent identifies significant loci and biological pathways without requiring manual pipeline construction.

Do I need to install external databases to perform biomedical research?

No external database installation is required. The agent utilizes approximately 11GB of integrated biomedical databases for knowledge retrieval, enabling autonomous genomics and drug discovery tasks directly within the environment.

Why use an autonomous agent for molecular biology analysis instead of standard scripts?

An autonomous agent decomposes complex molecular biology queries into multi-step reasoning and dynamically generates execution-ready code. Unlike static scripts, it adapts analysis pipelines on the fly by querying integrated databases for context-aware results.