An agentic AI system for automated pharmacogenomic recommendation generation
Mike Zack, Anton Savinkov, Danil Stupichev, Alex Moore, David Sokolov, Igor Trifonov, Anastasia Yankovskiy, Kirill Reshetnikov, Nurkyz Ydyrysova, Allan Gobbs · 2026
Read An agentic AI system for automated pharmacogenomic recommendation generation by Mike Zack, Anton Savinkov, Danil Stupichev, Alex Moore, David Sokolov, Igor Trifonov, Anastasia Yankovskiy, Kirill Reshetnikov, Nurkyz Ydyrysova, Allan Gobbs (2026) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-13369662.txt.
Description
Mike Zack and co-authors built an AI agent system that drafts gene-based drug guidance, in a 2026 study. Genes shape how each person handles a drug, so dosing advice should fit the person's genes. Writing that advice by hand is slow, costly, and limited in reach. Their system aims to automate the work with large language models guided by firm evidence.
The pipeline gathers full papers and drug labels, then pulls out key clinical facts with high accuracy. It merges findings across studies and drafts dosing advice for each gene and drug pair. Experts rated a sample of its outputs against leading chatbots. The system won on clarity and on matching formal guidelines. Broader coverage and faster updates are the promised payoff.
Catalog record
| CREATOR | Mike Zack, Anton Savinkov, Danil Stupichev, Alex Moore, David Sokolov, Igor Trifonov, Anastasia Yankovskiy, Kirill Reshetnikov, Nurkyz Ydyrysova, Allan Gobbs |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 50 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |