Sophont Launches Holon-S1 to Predict Genes and Biomarkers from Pathology Slides Across 16 Organ Types
iScienceLuvr · x · 2026-10-22
Sophont (@iScienceLuvr) unveils Holon-S1, a platform that predicts genes and biomarkers directly from routine pathology slides, replacing slow and expensive molecular testing. Key points:
- Beat two other models in a controlled comparison on spatial gene activity prediction
- Has surfaced potentially novel biomarkers in breast and colon cancer
- Evaluated across 16 organ types and 15+ scanners, on both FFPE and fresh-frozen slides
Retweeted with praise from EA-adjacent researchers, framing it as a notable AI-for-science milestone.
More from Research
- MIT ML technique breaks records for 2-6 week weather forecasts by learning to correct model errors — LesterMackey · 2026-10-22
- Microsoft's Nature research uses ML to sharpen weather forecasts 2-6 weeks out — LesterMackey · 2026-10-22
- Microsoft, MIT and ECMWF's Nature paper doubles 2-6 week forecast accuracy with open-source CPU bias correction — LesterMackey · 2026-10-22
- Harvard undergrad's ML subseasonal weather forecasting work, started at Microsoft Research, lands in Nature — LesterMackey · 2026-10-22
- Chatlet: generative UI that emerges from group chats to power collaborative decisions — HaijunXia · 2026-10-22
- If your research idea is concrete enough, agents can mostly execute it, says AI practitioner — burny_tech · 2026-10-22