A Fast and Interpretable Deep Learning Approach for Accurate Electrostatics-Driven pK(a) Predictions in Proteins

[Image: see text] Existing computational methods for estimating pK(a) values in proteins rely on theoretical approximations and lengthy computations. In this work, we use a data set of 6 million theoretically determined pK(a) shifts to train deep learning models, which are shown to rival the physics...

Descripción completa

Detalles Bibliográficos
Autores principales: Reis, Pedro B.P.S., Bertolini, Marco, Montanari, Floriane, Rocchia, Walter, Machuqueiro, Miguel, Clevert, Djork-Arné
Formato: Online Artículo Texto
Lenguaje:English
Publicado: American Chemical Society 2022
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9369009/
https://www.ncbi.nlm.nih.gov/pubmed/35837736
http://dx.doi.org/10.1021/acs.jctc.2c00308

Internet

https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9369009/
https://www.ncbi.nlm.nih.gov/pubmed/35837736
http://dx.doi.org/10.1021/acs.jctc.2c00308

Ejemplares similares