Prediction of antibody non-specificity using protein language models and biophysical parameters

Laila I Sakhnini, Ludovica Beltrame, Simone Fulle, Pietro Sormanni, Anette Henriksen, Nikolai Lorenzen, Michele Vendruscolo, Daniele Granata · 2026

Read Prediction of antibody non-specificity using protein language models and biophysical parameters by Laila I Sakhnini, Ludovica Beltrame, Simone Fulle, Pietro Sormanni, Anette Henriksen, Nikolai Lorenzen, Michele Vendruscolo, Daniele Granata (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-13217913.txt.

Description

Laila I. Sakhnini and colleagues present a 2026 computational study on predicting when therapeutic antibodies will bind to things they should not. Such non-specific binding can undermine a drug candidate, so developers want an early warning from the antibody's amino acid sequence alone. The team tested two routes to that prediction.

One route used embeddings from protein language models, which capture sequence context. The other used a set of plain physical descriptors that humans can read directly. Models were trained on published human and mouse antibody data and checked against three public datasets. The heavy chain, especially its third hypervariable loop, carried most of the predictive signal, and the best model reached about 71 percent accuracy in cross-validation. The isoelectric point stood out among the physical descriptors, and combining both approaches made the scores more reliable for early screening.

Catalog record

CREATORLaila I Sakhnini, Ludovica Beltrame, Simone Fulle, Pietro Sormanni, Anette Henriksen, Nikolai Lorenzen, Michele Vendruscolo, Daniele Granata
YEAR2026
COLLECTIONPAPERS
FORMATTXT
FILE SIZE61 KB
VERSION1.0
LICENSECC BY 4.0
RIGHTSCC BY
SOURCEEurope PMC

Source: https://europepmc.org/articles/PMC13217913

Browse the full library · About the Tower of Babel