Your browser doesn't support javascript.
loading
AGF-PPIS: A protein-protein interaction site predictor based on an attention mechanism and graph convolutional networks.
Fu, Xiuhao; Yuan, Ye; Qiu, Haoye; Suo, Haodong; Song, Yingying; Li, Anqi; Zhang, Yupeng; Xiao, Cuilin; Li, Yazi; Dou, Lijun; Zhang, Zilong; Cui, Feifei.
Afiliación
  • Fu X; School of Computer Science and Technology, Hainan University, Haikou 570228, China.
  • Yuan Y; Beidahuang Industry Group General Hospital, Harbin 150001, China.
  • Qiu H; School of Computer Science and Technology, Hainan University, Haikou 570228, China.
  • Suo H; School of Computer Science and Technology, Hainan University, Haikou 570228, China.
  • Song Y; School of Computer Science and Technology, Hainan University, Haikou 570228, China.
  • Li A; School of Computer Science and Technology, Hainan University, Haikou 570228, China.
  • Zhang Y; School of Computer Science and Technology, Hainan University, Haikou 570228, China.
  • Xiao C; School of Computer Science and Technology, Hainan University, Haikou 570228, China.
  • Li Y; School of Computer Science and Technology, Hainan University, Haikou 570228, China.
  • Dou L; Genomic Medicine Institute, Lerner Research Institute, Cleveland, OH 44106, USA.
  • Zhang Z; School of Computer Science and Technology, Hainan University, Haikou 570228, China. Electronic address: zhangzilong@hainanu.edu.cn.
  • Cui F; School of Computer Science and Technology, Hainan University, Haikou 570228, China. Electronic address: feifeicui@hainanu.edu.cn.
Methods ; 222: 142-151, 2024 Feb.
Article en En | MEDLINE | ID: mdl-38242383
ABSTRACT
Protein-protein interactions play an important role in various biological processes. Interaction among proteins has a wide range of applications. Therefore, the correct identification of protein-protein interactions sites is crucial. In this paper, we propose a novel predictor for protein-protein interactions sites, AGF-PPIS, where we utilize a multi-head self-attention mechanism (introducing a graph structure), graph convolutional network, and feed-forward neural network. We use the Euclidean distance between each protein residue to generate the corresponding protein graph as the input of AGF-PPIS. On the independent test dataset Test_60, AGF-PPIS achieves superior performance over comparative methods in terms of seven different evaluation metrics (ACC, precision, recall, F1-score, MCC, AUROC, AUPRC), which fully demonstrates the validity and superiority of the proposed AGF-PPIS model. The source codes and the steps for usage of AGF-PPIS are available at https//github.com/fxh1001/AGF-PPIS.
Asunto(s)
Palabras clave
Texto completo
Añadir a Mi BVS
Imprimir
XML
PubMed Links
Buscar en Google

Texto completo: 1 Colección: 01-internacional Base de datos: MEDLINE Asunto principal: Benchmarking / Inhibidores de la Bomba de Protones Tipo de estudio: Prognostic_studies / Risk_factors_studies Idioma: En Revista: Methods Asunto de la revista: BIOQUIMICA Año: 2024 Tipo del documento: Article País de afiliación: China Pais de publicación: Estados Unidos
Texto completo
Añadir a Mi BVS
Imprimir
XML
PubMed Links
Buscar en Google

Texto completo: 1 Colección: 01-internacional Base de datos: MEDLINE Asunto principal: Benchmarking / Inhibidores de la Bomba de Protones Tipo de estudio: Prognostic_studies / Risk_factors_studies Idioma: En Revista: Methods Asunto de la revista: BIOQUIMICA Año: 2024 Tipo del documento: Article País de afiliación: China Pais de publicación: Estados Unidos