The next paradigm in bioinformatics: a review of multi-agent systems and foundational models for end-to-end scientific discovery

Francesco Branda, Mohamed M Ahmed, Massimo Ciccozzi, Pietro Hiram Guzzi, Fabio Scarpa · 2026

Read The next paradigm in bioinformatics: a review of multi-agent systems and foundational models for end-to-end scientific discovery by Francesco Branda, Mohamed M Ahmed, Massimo Ciccozzi, Pietro Hiram Guzzi, Fabio Scarpa (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-13189163.txt.

Description

Francesco Branda and co-authors review a shift in how computers help run biological research, in a 2026 paper. Bioinformatics has leaned on prediction models that answer one question at a time. The authors argue the next step is agentic systems: teams of AI agents that plan a study, use tools, check their own results, and repeat until a goal is met.

The review first surveys large foundation models trained across kinds of biological data, then takes apart working agent systems by their planning, action, reflection, and memory parts. It covers ways to keep agents honest, such as grounding answers in retrieved evidence and testing claims in sequence. Uses in drug hunting and personal medicine follow. The authors close with open problems, from made-up results to bias and regulation, and a roadmap for trustworthy systems.

Catalog record

CREATORFrancesco Branda, Mohamed M Ahmed, Massimo Ciccozzi, Pietro Hiram Guzzi, Fabio Scarpa
YEAR2026
COLLECTIONPAPERS
FORMATTXT
FILE SIZE90 KB
VERSION1.0
LICENSECC BY 4.0
RIGHTSCC BY
SOURCEEurope PMC

Source: https://europepmc.org/articles/PMC13189163

Browse the full library · About the Tower of Babel