Chorus: an agentic AI framework for genomics
lucapinello · x · 2026-07-20
The post introduces Chorus, an agentic AI framework for genomics. It targets sequence-to-function “genomic oracles” and turns natural-language questions into reproducible analysis workflows.
Key pieces shown in the diagram:
- Agentic orchestration with an MCP server and 24 tools
- Natural-language genomic analysis
- Autonomous multi-step workflows
- Cross-model comparison and reasoning
- Interactive genome-browser reports
- A unified Python API with per-track normalization and reproducible per-oracle environments
It also spans seven oracle types, from short-range reporter and chromatin tasks to long-context expression and a generalist setup, and says the system supports variant-effect analysis, causal fine-mapping, cross-oracle consensus, in-silico mutagenesis, sequence design, and high-throughput VCF/GWAS screening.
Related event: Anthropic Backs Chorus: An Agentic AI Framework for Genomics(3 posts)→
More from coding & agent
- HeyGen adds a media-sourcing skill for coding agents with 75k images and 10k tracks — HeyGen · 2026-07-22
- Agent search bottlenecks are now about variance, not raw latency — rohanpaul_ai · 2026-07-22
- LangSmith adds tracing for Pipecat, LiveKit, OpenAI Realtime, and Gemini Live — LangChain · 2026-07-22
- An MCP server signs every AI agent tool call into a verifiable Merkle chain — Funky_Chicken_22 · 2026-07-22
- Annotated transcript of a Claude Code team interview is now available — trq212 · 2026-07-22
- Claude Code skill uses 10 Markdown rules to make outputs ADHD-friendly — alex_verem · 2026-07-22