An agentic AI environment to support biomedical research in collaborative academic environments
- 1Western University
Abstract
Agentic artificial intelligence (AAI) is increasingly used by biomedical scientists, where it has substantially lowered the difficulty of integrating computational, statistical and data-science approaches into day-to-day research activities, assisting with project design, analysis and manuscript preparation. Significant barriers remain, however, which are unlikely to be removed solely by releasing more capable AI models. Meaningful use still demands a technical fluency that many biomedical researchers lack: a PI and their lab members must learn how to use the AAI system, establish standard operating procedures (SOPs) for managing, sharing and curating data, and enforce rules that address data privacy and security. Existing commercial AAI systems, which were designed primarily for software engineering purposes, need to be significantly re-purposed for biomedical-related data science. We present Murmurent, shared software that sits beneath the agentic AI and provides the skills, procedures and protections to address the concerns above, removing the need for a lab to develop them independently. This includes (1) infrastructure to support projects and so-called choreographies} involving multiple group members; (2) a set of specialized agents each dedicated to typical biomedical data science tasks including software and statistical development, data visualization, literature search, equity, diversity, inclusion, and decolonization (EDID) review, and others; (3) a tiered memory which can retain important research decisions, intermediate, derived outputs and sensitive data, and which can exploit this information to automatically build better contexts in AAI sessions; (4) traceability records which are used by the AAI session to better plan and execute data analyses and software builds by, for example, helping to avoid repeating decisions that lead to dead-ends; (5) enforcement of SOPs for data maintenance and data governance across all lab members; and (6) multi-user capacity to allow groups to interact and collaborate. We use the system to identify putative inhibitors of Peptidyl-prolyl cis-trans Isomerase NIMA-interacting 1 (Pin1), a protein with a shallow catalytic site making it difficult to target. We describe the construction of several approaches to identify Pin1 inhibitors and the results they yield. Murmurent is open source.
Related
- Efficacy of statistical and design interventions for improving reproducibility in biomedical research
- Developing an inclusive research (methods) strategy for the Manchester Biomedical Research Centre and Clinical Research Facility
- From Tool State to Scientific Action: Auditing Decision Provenance in Biomedical Research Agents
- PromptBio: An Agentic Platform for End-to-End Computational Biomedical Research
- Novel Target Combinations in Lung Squamous Cell Carcinoma proposed by the Emet AI Research Environment and supported by discovery stage experimentation
BibTeX
@misc{wu2026agentic,
title = {{An agentic AI environment to support biomedical research in collaborative academic environments}},
author = {T. Wu and T. S. Browne and M. Meawad and H. E. Emam and N. H. Simsam and Y. Xia and A. Jaafar and A. Ma and B. Kabbani and V. Gupta and E. J. Mucaki and S. L. Bishop and D. R. Edgell and G. Gloor and K. P. Lu and L. Weir and X. Z. Zhou and V. Dumeaux and M. T. Hallett},
howpublished = {bioRxiv},
year = {2026},
month = sep,
doi = {10.64898/2026.09.24.753565},
url = {https://www.biorxiv.org/content/10.64898/2026.09.24.753565v1},
note = {CC BY},
}
RIS
TY - UNPB
TI - An agentic AI environment to support biomedical research in collaborative academic environments
AU - T. Wu
AU - T. S. Browne
AU - M. Meawad
AU - H. E. Emam
AU - N. H. Simsam
AU - Y. Xia
AU - A. Jaafar
AU - A. Ma
AU - B. Kabbani
AU - V. Gupta
AU - E. J. Mucaki
AU - S. L. Bishop
AU - D. R. Edgell
AU - G. Gloor
AU - K. P. Lu
AU - L. Weir
AU - X. Z. Zhou
AU - V. Dumeaux
AU - M. T. Hallett
PY - 2026
DA - 2026/09/24
PB - bioRxiv
DO - 10.64898/2026.09.24.753565
UR - https://www.biorxiv.org/content/10.64898/2026.09.24.753565v1
AB - Agentic artificial intelligence (AAI) is increasingly used by biomedical scientists, where it has substantially lowered the difficulty of integrating computational, statistical and data-science approaches into day-to-day research activities, assisting with project design, analysis and manuscript preparation. Significant barriers remain, however, which are unlikely to be removed solely by releasing more capable AI models. Meaningful use still demands a technical fluency that many biomedical researchers lack: a PI and their lab members must learn how to use the AAI system, establish standard operating procedures (SOPs) for managing, sharing and curating data, and enforce rules that address data privacy and security. Existing commercial AAI systems, which were designed primarily for software engineering purposes, need to be significantly re-purposed for biomedical-related data science. We present Murmurent, shared software that sits beneath the agentic AI and provides the skills, procedures and protections to address the concerns above, removing the need for a lab to develop them independently. This includes (1) infrastructure to support projects and so-called choreographies} involving multiple group members; (2) a set of specialized agents each dedicated to typical biomedical data science tasks including software and statistical development, data visualization, literature search, equity, diversity, inclusion, and decolonization (EDID) review, and others; (3) a tiered memory which can retain important research decisions, intermediate, derived outputs and sensitive data, and which can exploit this information to automatically build better contexts in AAI sessions; (4) traceability records which are used by the AAI session to better plan and execute data analyses and software builds by, for example, helping to avoid repeating decisions that lead to dead-ends; (5) enforcement of SOPs for data maintenance and data governance across all lab members; and (6) multi-user capacity to allow groups to interact and collaborate. We use the system to identify putative inhibitors of Peptidyl-prolyl cis-trans Isomerase NIMA-interacting 1 (Pin1), a protein with a shallow catalytic site making it difficult to target. We describe the construction of several approaches to identify Pin1 inhibitors and the results they yield. Murmurent is open source.
ER -