Predicting molecular recognition features in protein sequences with MoRFchibi 2.0

Nawar Malhis, Jörg Gsponer · 2026

Read Predicting molecular recognition features in protein sequences with MoRFchibi 2.0 by Nawar Malhis, Jörg Gsponer (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/PMC13505122.txt.

Description

Nawar Malhis and Jörg Gsponer present MoRFchibi 2.0, a tool that predicts binding segments inside disordered protein regions, in a 2026 paper. Some protein stretches lack a fixed shape until they grip a partner, folding only on contact. Those segments, called molecular recognition features, are hard to find by experiment.

The new version beat all rival predictors in head-to-head tests, including top entries from three rounds of a public assessment contest. It even topped tools fed with predicted protein structures and large protein language models. Its scores come from an ensemble of small neural models adjusted for how common such segments are in training data. That design keeps each score easy to read and to mix with like tools. The authors aim it at mapping interaction sites across whole proteomes.

Catalog record

CREATORNawar Malhis, Jörg Gsponer
YEAR2026
COLLECTIONPAPERS
FORMATTXT
FILE SIZE37540
LICENSEhttps://creativecommons.org/licenses/by/4.0
RIGHTSCC BY
SOURCEEurope PMC

Source: https://europepmc.org/article/MED/PMC13505122

Browse the full library · About the Tower of Babel