AlloPool is a deep learning framework that infers protein allostery from molecular dynamics simulations

Matthieu Marfoglia, Miguel A Pedraza-Joya, Lucas Guirardel, Aisima Chatzi Souleiman, Patrick Barth, Chaitan Khosla · 2026

Read AlloPool is a deep learning framework that infers protein allostery from molecular dynamics simulations by Matthieu Marfoglia, Miguel A Pedraza-Joya, Lucas Guirardel, Aisima Chatzi Souleiman, Patrick Barth, Chaitan Khosla (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/PMC13592721.txt.

Description

Matthieu Marfoglia and five colleagues present AlloPool, a deep learning system that reads protein motion from simulation movies. A protein's job depends on shape shifting, and distant parts of the chain talk to each other through allostery, yet training data for such motion stays scarce. Their graph network treats amino acids as nodes, then prunes links again and again to expose the smallest interaction webs that drive each transition. Time aware attention tracks how those webs evolve.

Across binding domains, force sensors, signaling receptors, and enzymes, the system rebuilt motion paths more faithfully than rival learning methods. It also mapped communication routes and predicted how binding, force, or mutation would ripple through a protein. Marfoglia and the team offer it as a general lens for drug design and protein engineering.

Catalog record

CREATORMatthieu Marfoglia, Miguel A Pedraza-Joya, Lucas Guirardel, Aisima Chatzi Souleiman, Patrick Barth, Chaitan Khosla
YEAR2026
COLLECTIONPAPERS
FORMATTXT
FILE SIZE54 KB
LICENSEhttps://creativecommons.org/licenses/by/4.0
RIGHTSCC BY
SOURCEEurope PMC

Source: https://europepmc.org/article/MED/PMC13592721

Browse the full library · About the Tower of Babel