Literature-derived, context-aware gene regulatory networks improve biological predictions and mathematical modeling

Masato Tsutsui, Kiwamu Arakane, Mariko Okada · 2026

Read Literature-derived, context-aware gene regulatory networks improve biological predictions and mathematical modeling by Masato Tsutsui, Kiwamu Arakane, Mariko Okada (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/PMC13441170.txt.

Description

Tsutsui and colleagues built a framework in 2026 that gives gene regulatory links a context, since a gene switch that matters in one disease or cell type may be idle in another. Databases and papers usually record gene regulations as bare facts, stripped of the setting where they were seen. Their method, powered by a large language model, mines the literature and assigns each regulation a quantitative weight for the context it belongs to.

Networks rebuilt with these weights matched gene activity data across many diseases far better than context-free versions, and drug-target predictions grew more accurate when context was added. As a showcase, the team automatically assembled a working differential-equation model, a set of rate equations, of a breast cancer signaling network from the contextualized network. The authors argue that context is not decoration but a requirement for biological prediction, and they release the code openly.

Catalog record

CREATORMasato Tsutsui, Kiwamu Arakane, Mariko Okada
YEAR2026
COLLECTIONPAPERS
FORMATTXT
FILE SIZE51 KB
LICENSEhttps://creativecommons.org/licenses/by/4.0
RIGHTSCC BY
SOURCEEurope PMC

Source: https://europepmc.org/article/MED/PMC13441170

Browse the full library · About the Tower of Babel