Protein language models trained on multiple sequence alignments learn phylogenetic relationships

Self-supervised neural language models with attention have recently been applied to biological sequence data, advancing structure, function and mutational effect prediction. Some protein language models, including MSA Transformer and AlphaFold’s EvoFormer, take multiple sequence alignments (MSAs) of...

Descripción completa

Detalles Bibliográficos
Autores principales: Lupo, Umberto, Sgarbossa, Damiano, Bitbol, Anne-Florence
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Nature Publishing Group UK 2022
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9588007/
https://www.ncbi.nlm.nih.gov/pubmed/36273003
http://dx.doi.org/10.1038/s41467-022-34032-y

Ejemplares similares