DiscoVerse: multi-agent pharmaceutical co-scientist for traceable drug discovery and reverse translation
Xiaochen Zheng, Alvaro Serra, Ilya Schneider Chernov, Maddalena Marchesi, Eunice Musvasva, Tatyana Y. Doktorova · 2026
Read DiscoVerse: multi-agent pharmaceutical co-scientist for traceable drug discovery and reverse translation by Xiaochen Zheng, Alvaro Serra, Ilya Schneider Chernov, Maddalena Marchesi, Eunice Musvasva, Tatyana Y. Doktorova (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/PMC13323300.txt.
Description
Xiaochen Zheng and co-authors present DiscoVerse, a multi-agent AI assistant for drug discovery at Roche, in a 2026 report. Drug archives hold decades of work, much from stopped programmes, and reusing that knowledge for reverse translation is often impractical without help.
The system answers specialist questions by retrieving records, linking across documents and summarising findings with sources attached, keeping people in the loop. Testing covered 180 molecules from Roche repositories holding over four decades of research. Across seven benchmark questions, recall sat near perfect while precision ranged lower in their expert checks. Case examples suggest the tool can surface decision-relevant history that teams would otherwise miss.
Catalog record
| CREATOR | Xiaochen Zheng, Alvaro Serra, Ilya Schneider Chernov, Maddalena Marchesi, Eunice Musvasva, Tatyana Y. Doktorova |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 37879 |
| LICENSE | https://creativecommons.org/licenses/by/4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |