Cargando…
Contrastive learning on protein embeddings enlightens midnight zone
Experimental structures are leveraged through multiple sequence alignments, or more generally through homology-based inference (HBI), facilitating the transfer of information from a protein with known annotation to a query without any annotation. A recent alternative expands the concept of HBI from...
Autores principales: | Heinzinger, Michael, Littmann, Maria, Sillitoe, Ian, Bordin, Nicola, Orengo, Christine, Rost, Burkhard |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
Oxford University Press
2022
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9188115/ https://www.ncbi.nlm.nih.gov/pubmed/35702380 http://dx.doi.org/10.1093/nargab/lqac043 |
Ejemplares similares
-
CATHe: detection of remote homologues for CATH superfamilies using embeddings from protein language models
por: Nallapareddy, Vamsi, et al.
Publicado: (2023) -
Clustering FunFams using sequence embeddings improves EC purity
por: Littmann, Maria, et al.
Publicado: (2021) -
Novel machine learning approaches revolutionize protein knowledge
por: Bordin, Nicola, et al.
Publicado: (2023) -
Protein embeddings and deep learning predict binding residues for various ligand classes
por: Littmann, Maria, et al.
Publicado: (2021) -
Embeddings from deep learning transfer GO annotations beyond homology
por: Littmann, Maria, et al.
Publicado: (2021)