Ladon embeds 1M RNA-seq samples to let Claude search biology, not text
ycombinator · x · 2026-07-28
Ladon embeds more than 1 million public RNA-seq samples into a shared biological space and exposes that space through MCP so Claude can search by biological similarity instead of text.
- The project spans 20+ years of public transcriptomics data.
- The goal is to retrieve studies by transcriptomic signature — what changed biologically — rather than by titles, abstracts, or keywords.
- The authors argue this could make AI agents better at scientific discovery because they can search the biology itself, not just the literature metadata.
More from coding & agent
- Gemini shown off modding Minecraft to turn players into any Spider-Man — zacharynado · 2026-10-16
- IBM engineer maps 5 levels of AI coding, from manual to a 3-day agent software factory — TejasKumar_ · 2026-10-16
- 10 open-source repos that let your AI agent reverse-engineer apps and games — victor_explore · 2026-10-16
- The new CTO job: agent management and QA loops, 'cable management' instead of coding — HankYeomans · 2026-10-16
- Why company AI agents go stale: adoption needs in-house knowledge, not just better agents — EdenEmarco177 · 2026-10-16
- Open-source MCP lets coding agents search Obsidian's 9,000-plugin directory before reinventing wheels — pitfa19 · 2026-10-16