文献类型：期刊文献

英文题名：PFmulDL: a novel strategy enabling multi-class and multi-label protein function annotation by integrating diverse deep learning methods

作者：Xia, Weiqi[1];Zheng, Lingyan[1,2];Fang, Jiebin[1];Li, Fengcheng[1];Zhou, Ying[1];Zeng, Zhenyu[2];Zhang, Bing[2];Li, Zhaorong[2];Li, Honglin[3];Zhu, Feng[1,2]

机构：[1]Zhejiang Univ, Sch Med, Affiliated Hosp 2, Coll Pharmaceut Sci, Hangzhou 310058, Peoples R China;[2]Zhejiang Univ, Alibaba Zhejiang Univ Joint Res Ctr Future Digita, Innovat Inst Artificial Intelligence Med, Hangzhou 330110, Peoples R China;[3]East China Univ Sci & Technol, Sch Pharm, Shanghai 200237, Peoples R China

年份：2022

卷号：145

外文期刊名：COMPUTERS IN BIOLOGY AND MEDICINE

收录：;EI(收录号：20221411910463);WOS:【SCI-EXPANDED(收录号:WOS:000819697000006)】；

基金：Funded by Natural Science Foundation of Zhejiang Province (LR21H300001); National Natural Science Foundation of China (81872798 & U1909208); Leading Talent of the 'Ten Thousand Plan' National High-Level Talents Special Support Plan of China; Fundamental Research Fund for Central Universities (2018QNA7023); "Double Top-Class" University Project (181201*194232101); Key R&D Program of Zhejiang Province (2020C03010). This work was supported by Westlake Laboratory (Westlake Laboratory of Life Sciences and Biomedicine); Alibaba-Zhejiang University Joint Research Center of Future Digital Healthcare; Alibaba Cloud; Information Technology Center of Zhejiang University.

语种：英文

外文关键词：Protein function prediction; Deep learning; Gene ontology; Convolutional neural network; Recurrent neural network

摘要：Bioinformatic annotation of protein function is essential but extremely sophisticated, which asks for extensive efforts to develop effective prediction method. However, the existing methods tend to amplify the representativeness of the families with large number of proteins by misclassifying the proteins in the families with small number of proteins. That is to say, the ability of the existing methods to annotate proteins in the 'rare classes' remains limited. Herein, a new protein function annotation strategy, PFmulDL, integrating multiple deep learning methods, was thus constructed. First, the recurrent neural network was integrated, for the first time, with the convolutional neural network to facilitate the function annotation. Second, a transfer learning method was introduced to the model construction for further improving the prediction performances. Third, based on the latest data of Gene Ontology, the newly constructed model could annotate the largest number of protein families comparing with the existing methods. Finally, this newly constructed model was found capable of significantly elevating the prediction performance for the 'rare classes' without sacrificing that for the 'major classes'. All in all, due to the emerging requirements on improving the prediction performance for the proteins in 'rare classes', this new strategy would become an essential complement to the existing methods for protein function prediction. All the models and source codes are freely available and open to all users at: https://github.com/idrblab/PFmulDL.