AUTHOR=Pan Jie , You Zhu-Hong , Li Li-Ping , Huang Wen-Zhun , Guo Jian-Xin , Yu Chang-Qing , Wang Li-Ping , Zhao Zheng-Yang 

TITLE=DWPPI: A Deep Learning Approach for Predicting Protein–Protein Interactions in Plants Based on Multi-Source Information With a Large-Scale Biological Network

JOURNAL=Frontiers in Bioengineering and Biotechnology

VOLUME=Volume 10 - 2022

YEAR=2022

URL=https://www.frontiersin.org/journals/bioengineering-and-biotechnology/articles/10.3389/fbioe.2022.807522

DOI=10.3389/fbioe.2022.807522

ISSN=2296-4185

ABSTRACT=The prediction of protein-protein interactions (PPIs) in plants is vital for probing cell function. Although multiple high-throughput approaches in biological domain have been developed to identify PPIs. However, with the increasing complexity of PPIs network, these methods fall into laborious and time-consuming situations. Thus, it is urgent to develop an effective and feasible computational method for the prediction of PPIs in plants. In this study, we present a network embedding-based method, called DWPPI, for predicting the interactions between different plant proteins based on multi-source information and combined with the Deep neural networks (DNN). The DWPPI model fused the protein natural language sequence information (attribute information) and protein behavior information to represent plant proteins as feature vectors, and finally send these features to a deep learning-based classifier for prediction. To validate the prediction performance of DWPPI, we performed it on three model plant data sets: Arabidopsis thaliana (A. thaliana), Mazie (Zea mays), and Rice (Oryza sativa). The experimental results with the 5-fold cross-validation technique demonstrated that DWPPI obtains great performance with the AUC (area under ROC curves) values of 0.9548, 0.9867 and 0.9213, respectively. To further verify the predictive capacity of DWPPI, we compared it with some different state-of-art machine learning classifiers. Moreover, case studies are performed with the AC149810.2_FGP003 protein. As a result, 14 of the top 20 PPIs pairs identified by DWPPI with the highest scores were confirmed by literature. These excellent results suggest that the DWPPI model can anticipate as a promising tool for related plant molecular biology.