platoseedplatoseed
Interpretable AI for drug discovery
Reticular helps pharma companies discover drugs with AI models like AlphaFold by making them steerable, just like you can prompt LLMs. Today, limited validation data means companies spend millions on failed experiments trying to steer these models through trial and error. We’re piloting our AI interpretability technology with early-stage biotechs and scaling rapidly. Just a week after our pivot, we identified the first interpretable features ever found in protein models, allowing precise control over biological functions. Nithin and John met competing in Biology Olympiads before spending 4 years as roommates at MIT publishing ML/bio research in NeurIPS and Nature. We believe biological models encode far more information than anyone is currently using - our goal is to unlock this potential.
MIT AI + Mathematics '24. Published ML research in NeurIPS and Nature. Prior quant intern at Goldman Sachs. National achievements include USA Brain Bee Champion, USA Biology Olympiad Bronze Medalist, and First Place Euro Challenge Team Captain.
We help biotech companies design better proteins by making AI models controllable and predictable.
Reticular enables pharma companies to steer protein AI models toward desired properties with interpretable features, enabling reliable design with limited data and fewer wasted experiments. They demonstrate direct model steering for protein designs and provide interpretability to back each design.
Formerly “Advocate” · why startups rename →
AI Inference Platform for Drug Discovery
Unsupervised Biological AI
