Utilize este identificador para referenciar este registo:
https://hdl.handle.net/10316/101280
Título: | SPOTONE: Hot Spots on Protein Complexes with Extremely Randomized Trees via Sequence-Only Features | Autor: | Preto, A. J. Moreira, Irina S. |
Palavras-chave: | big-data; hot-spots; machine learning; protein–protein complexes; structural biology | Data: | 1-Out-2020 | Título da revista, periódico, livro ou evento: | International Journal of Molecular Sciences | Volume: | 21 | Número: | 19 | Resumo: | Protein Hot-Spots (HS) are experimentally determined amino acids, key to small ligand binding and tend to be structural landmarks on protein-protein interactions. As such, they were extensively approached by structure-based Machine Learning (ML) prediction methods. However, the availability of a much larger array of protein sequences in comparison to determined tree-dimensional structures indicates that a sequence-based HS predictor has the potential to be more useful for the scientific community. Herein, we present SPOTONE, a new ML predictor able to accurately classify protein HS via sequence-only features. This algorithm shows accuracy, AUROC, precision, recall and F1-score of 0.82, 0.83, 0.91, 0.82 and 0.85, respectively, on an independent testing set. The algorithm is deployed within a free-to-use webserver at http://moreiralab.com/resources/spotone, only requiring the user to submit a FASTA file with one or more protein sequences. | URI: | https://hdl.handle.net/10316/101280 | ISSN: | 1422-0067 | DOI: | 10.3390/ijms21197281 | Direitos: | openAccess |
Aparece nas coleções: | I&D CNC - Artigos em Revistas Internacionais FCTUC Ciências da Vida - Artigos em Revistas Internacionais |
Ficheiros deste registo:
Ficheiro | Descrição | Tamanho | Formato | |
---|---|---|---|---|
ijms-21-07281-v2.pdf | 4.93 MB | Adobe PDF | Ver/Abrir |
Citações SCOPUSTM
6
Visto em 17/nov/2022
Citações WEB OF SCIENCETM
6
Visto em 2/mai/2023
Visualizações de página
61
Visto em 28/ago/2024
Downloads
71
Visto em 28/ago/2024
Google ScholarTM
Verificar
Altmetric
Altmetric
Este registo está protegido por Licença Creative Commons