DDGemb: predicting protein stability change upon single- and multi-point variations with embeddings and deep learning

Castrense Savojardo, Matteo Manfredi, Pier Luigi Martelli, Rita Casadio · 2025

Read DDGemb: predicting protein stability change upon single- and multi-point variations with embeddings and deep learning by Castrense Savojardo, Matteo Manfredi, Pier Luigi Martelli, Rita Casadio (2025) 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-11783275.txt.

Description

Castrense Savojardo and co-authors present DDGemb, a 2025 tool (published 2024) that predicts how a mutation changes a protein's stability, for one change or several at once. Stability shifts decide whether a variant is harmless, disease causing, or useful in a designed protein. Lab measurement is slow, so computation does the screening.

The method feeds a protein language model's embeddings, rich numeric summaries of the sequence, into a transformer network. It was trained on a high quality literature derived data set. Tests on standard benchmarks for single and multi point changes put it at the state of the art, the authors report. Multi point prediction is the harder prize, since changes interact. A public web server and open data sets accompany the paper. Variant interpreters in clinics and protein engineers alike can use a fast, accurate stability call.

Catalog record

CREATORCastrense Savojardo, Matteo Manfredi, Pier Luigi Martelli, Rita Casadio
YEAR2025
COLLECTIONPAPERS
FORMATTXT
FILE SIZE26 KB
VERSION1.0
LICENSECC BY 4.0
RIGHTSCC BY
SOURCEEurope PMC

Source: https://europepmc.org/articles/PMC11783275

Browse the full library · About the Tower of Babel