Hackerathon team builds in silico drug discovery pipeline showing Hesperetin flattens glucose spikes
CatAstro_Piyush · x · 2026-10-23
An OSI Hackathon project built a fully in silico drug discovery pipeline using Rowan Science to validate that the natural plant metabolite Hesperetin targets alpha-glucosidase for Type 2 Diabetes management.
- Pocket analysis: identified a highly druggable primary active site (score 7.359, volume 1671.9) well-suited to accommodate multi-flavonoid structures like Hesperetin, supporting competitive inhibition.
- Co-folding: Hesperetin–enzyme co-folding achieved pTM 0.969, ipTM 0.933, and average pLDDT 0.963, with a predicted IC50 of 42.5 µM — an effective micromolar inhibitor.
- Kinetic simulation: un inhibited starch digestion peaks at 181 mg/dL post-meal (above the 140 mg/dL limit); with 90% enzyme blockade, the peak flattens to a safe 106 mg/dL.
The project demonstrates an end-to-end computational workflow from pocket analysis through co-folding to kinetic modeling, all without wet-lab experiments.
More from Research
- Researcher: vanilla LLMs/LRMs struggle with plan valuation and info-gathering in uncertain environments — xuanalogue · 2026-10-23
- MedSAM and EchoJEPA: Repurposing Meta's General AI Models for Medical Breakthroughs — BoWang87 · 2026-10-23
- Scott Wu's pub card game turned into a math RL environment built on OpenEnv — SergioPaniego · 2026-10-23
- AnyGoal research asks whether world models memorize trajectories instead of learning reusable rules — randall_balestr · 2026-10-23
- Stratified Sparse Attention unifies retrieval and sampling to close the sparse-to-dense gap at extreme sparsity — Skylight1 · 2026-10-23
- New paper with 25 coauthors examines feasibility of a hardwired pause on frontier AI training — wfithian · 2026-10-23