Sophont CEO: even perfect molecular design won't fix Phase II failures—better disease models will
iScienceLuvr · x · 2026-10-23
Sophont AI's CEO agrees that even with perfect molecular design, today's target selection and disease models would still doom most drugs in Phase II, since in vitro and preclinical results poorly predict clinical success. That's why Sophont builds foundation models on clinical data—directly understanding human biology is the better lever.
More from Apps
- Escalate details plan for binder-based combinatorial proteomics to feed AI biology models — PatrickKidger · 2026-10-23
- Boardy AI chief of staff refuses to fake data, inspires a smarter market-ranking method — chickefitz · 2026-10-23
- LokalBot ships Linux/Windows alpha: open-source local transcription, dictation and autocomplete — stevyhacker · 2026-10-23
- How Speak uses GPT-Live and a Decisions API for ultra-responsive live AI language tutoring — pbbakkum · 2026-10-23
- Interactive voice decisions demo and docs for the Live API — pbbakkum · 2026-10-23
- Non-coder uses Opus 5.5 to track ADHD medication curves — Simple-Diver-2192 · 2026-10-23