Interpreting Potts and Transformer Protein Models Through the Lens of Simplified Attention

The established approach to unsupervised protein contact prediction estimates coevolving positions using undirected graphical models. This approach trains a Potts model on a Multiple Sequence Alignment. Increasingly large Transformers are being pretrained on unlabeled, unaligned protein sequence dat...

Descripción completa

Detalles Bibliográficos
Autores principales: Bhattacharya, Nicholas, Thomas, Neil, Rao, Roshan, Dauparas, Justas, Koo, Peter K., Baker, David, Song, Yun S., Ovchinnikov, Sergey
Formato: Online Artículo Texto
Lenguaje:English
Publicado: 2022
Materias:
Article
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8752338/
https://www.ncbi.nlm.nih.gov/pubmed/34890134

Internet

https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8752338/
https://www.ncbi.nlm.nih.gov/pubmed/34890134

Ejemplares similares