Gespeichert in:
| Hauptverfasser: | , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | https://arxiv.org/abs/2511.18259 |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866915663222669312 |
|---|---|
| author | Zheng, Xiaochen Serra, Alvaro Chernov, Ilya Schneider Marchesi, Maddalena Musvasva, Eunice Doktorova, Tatyana Y. |
| author_facet | Zheng, Xiaochen Serra, Alvaro Chernov, Ilya Schneider Marchesi, Maddalena Musvasva, Eunice Doktorova, Tatyana Y. |
| contents | Pharmaceutical research and development has accumulated vast and heterogeneous archives of data. Much of this knowledge stems from discontinued programs, and reusing these archives is invaluable for reverse translation. However, in practice, such reuse is often infeasible. In this work, we introduce DiscoVerse, a multi-agent co-scientist designed to support pharmaceutical research and development at Roche. Designed as a human-in-the-loop assistant, DiscoVerse enables domain-specific queries by delivering evidence-based answers: it retrieves relevant data, links across documents, summarises key findings and preserves institutional memory. We assess DiscoVerse through expert evaluation of source-linked outputs. Our evaluation spans a selected subset of 180 molecules from Roche's research and development repositories, encompassing over 0.87 billion BPE tokens and more than four decades of research. To our knowledge, this represents the first agentic framework to be systematically assessed on real pharmaceutical data for reverse translation, enabled by authorized access to confidential archives covering the full lifecycle of drug development. Our contributions include: role-specialized agent designs aligned with scientist workflows; human-in-the-loop support for reverse translation; expert evaluation; and a large-scale demonstration showing promising decision-making insights. In brief, across seven benchmark queries, DiscoVerse achieved near-perfect recall ($\geq 0.99$) with moderate precision ($0.71-0.91$). Qualitative assessments and three real-world pharmaceutical use cases further showed faithful, source-linked synthesis across preclinical and clinical evidence. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2511_18259 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | DiscoVerse: Multi-Agent Pharmaceutical Co-Scientist for Traceable Drug Discovery and Reverse Translation Zheng, Xiaochen Serra, Alvaro Chernov, Ilya Schneider Marchesi, Maddalena Musvasva, Eunice Doktorova, Tatyana Y. Computation and Language Multiagent Systems Pharmaceutical research and development has accumulated vast and heterogeneous archives of data. Much of this knowledge stems from discontinued programs, and reusing these archives is invaluable for reverse translation. However, in practice, such reuse is often infeasible. In this work, we introduce DiscoVerse, a multi-agent co-scientist designed to support pharmaceutical research and development at Roche. Designed as a human-in-the-loop assistant, DiscoVerse enables domain-specific queries by delivering evidence-based answers: it retrieves relevant data, links across documents, summarises key findings and preserves institutional memory. We assess DiscoVerse through expert evaluation of source-linked outputs. Our evaluation spans a selected subset of 180 molecules from Roche's research and development repositories, encompassing over 0.87 billion BPE tokens and more than four decades of research. To our knowledge, this represents the first agentic framework to be systematically assessed on real pharmaceutical data for reverse translation, enabled by authorized access to confidential archives covering the full lifecycle of drug development. Our contributions include: role-specialized agent designs aligned with scientist workflows; human-in-the-loop support for reverse translation; expert evaluation; and a large-scale demonstration showing promising decision-making insights. In brief, across seven benchmark queries, DiscoVerse achieved near-perfect recall ($\geq 0.99$) with moderate precision ($0.71-0.91$). Qualitative assessments and three real-world pharmaceutical use cases further showed faithful, source-linked synthesis across preclinical and clinical evidence. |
| title | DiscoVerse: Multi-Agent Pharmaceutical Co-Scientist for Traceable Drug Discovery and Reverse Translation |
| topic | Computation and Language Multiagent Systems |
| url | https://arxiv.org/abs/2511.18259 |