AUTHOR=Meng Zixuan , Kuang Linai , Chen Zhiping , Zhang Zhen , Tan Yihong , Li Xueyong , Wang Lei 

TITLE=Method for Essential Protein Prediction Based on a Novel Weighted Protein-Domain Interaction Network

JOURNAL=Frontiers in Genetics

VOLUME=Volume 12 - 2021

YEAR=2021

URL=https://www.frontiersin.org/journals/genetics/articles/10.3389/fgene.2021.645932

DOI=10.3389/fgene.2021.645932

ISSN=1664-8021

ABSTRACT=Currently, lots of calculative models based on protein-protein interaction (PPI) networks have been proposed successively. However, due to the false positives, false negatives and incompleteness of PPI networks, it is still a challenging work to design computational models with satisfactory predictive accuracy to infer key proteins. In this study, a prediction model called WPDINM for detecting key proteins is proposed based on a novel weighted protein-domain interaction network. In WPDINM, a weighted PPI network is constructed first by combining the gene expression data of proteins with the topological information extracted from the original PPI network. And simultaneously, a weighted domain-domain interaction network is constructed based on the original protein-domain interaction network. Next, through integrating the newly obtained weighted PPI network and weighted domain-domain interaction network with the original protein-domain interaction network, a weighted protein-domain interaction network is further constructed. And then, based on the topological features and biological information including the subcellular localization and orthologous information of proteins, a novel PageRank-based iterative algorithm is designed and implemented on the newly constructed weighted protein-domain interaction network to estimate the criticality of proteins. Finally, in order to assess the prediction performance of WPDINM, we have compared it with 12 kinds of competitive measures, and experimental results show that WPDINM can achieve the predictive accuracy rate of 90.19%, 81.96%, 70.72%, 62.04%, 55.83% and 51.13% in top 1%, top5%, top10%, top15%, top20% and top25% separately, which exceeds the prediction accuracy achieved by those traditional state-of-the-art competing measures. Owing to the satisfactory identification effect, WPDINM measure may contribute to the further development of   key proteins identification.