Biomni is an autonomous AI agent framework developed by Stanford SNAP lab for executing complex biomedical research tasks across genomics, drug discovery, and clinical domains.

Is code execution safe with this skill?

Biomni executes LLM-generated code with system privileges to perform analysis; it is recommended to run tasks in isolated environments like Docker or virtual machines.

Do I need a specific LLM to use this skill?

While Biomni supports several providers including OpenAI and Gemini, Anthropic Claude 3.5 Sonnet is highly recommended for the best balance of biomedical reasoning and speed.

How does Biomni handle biomedical data?

It integrates approximately 11GB of biological knowledge sources, including Ensembl, UniProt, PDB, and PubMed, which are automatically downloaded to your local path on first use.

Can I use Biomni for clinical genomics?

Yes, Biomni excels at phenotype-genotype mapping, rare disease diagnosis, and variant pathogenicity interpretation using clinical datasets like ClinVar and OMIM.

Biomni Biomedical AI Agent

Name: Biomni Biomedical AI Agent
Author: Microck

byMicrock

•

데이터 과학 및 ML

Executes complex autonomous research tasks across genomics, drug discovery, and clinical analysis using integrated biomedical databases.

소개

Biomni is an open-source framework from Stanford's SNAP lab designed to function as an autonomous AI agent for multi-step biomedical research. It bridges the gap between high-level reasoning and technical execution by autonomously decomposing tasks, generating analysis code, and querying over 11GB of integrated biomedical data. This skill is ideal for researchers and bioinformaticians needing to streamline specialized workflows like CRISPR screen design, single-cell RNA-seq analysis, or drug ADMET prediction within their Claude environment.

주요 기능

Multi-step biological reasoning and autonomous task planning
Integrated access to 11GB of biomedical databases including NCBI and UniProt
Cross-domain support for genomics, proteomics, and drug discovery
Built-in evaluation framework for benchmarking biomedical research outputs
81 GitHub stars
Dynamic analysis pipeline creation via code generation and execution

사용 사례

Designing genome-wide CRISPR screens and prioritizing gene targets
Predicting ADMET properties and identifying targets for drug discovery
Performing end-to-end single-cell RNA-seq clustering and annotation

소개

주요 기능

Multi-step biological reasoning and autonomous task planning
Integrated access to 11GB of biomedical databases including NCBI and UniProt
Cross-domain support for genomics, proteomics, and drug discovery
Built-in evaluation framework for benchmarking biomedical research outputs
81 GitHub stars
Dynamic analysis pipeline creation via code generation and execution

사용 사례

Designing genome-wide CRISPR screens and prioritizing gene targets
Predicting ADMET properties and identifying targets for drug discovery
Performing end-to-end single-cell RNA-seq clustering and annotation