Hybrid Deep Learning Based on a Heterogeneous Network Profile for Functional Annotations of Plasmodium falciparum Genes

Abstract

Functional annotation of unknown function genes reveals unidentified functions that can enhance our understanding of complex genome communications. A common approach for inferring gene function involves the ortholog-based method. However, genetic data alone are often not enough to provide information for function annotation. Thus, integrating other sources of data can potentially increase the possibility of retrieving annotations. Network-based methods are efficient techniques for exploring interactions among genes and can be used for functional inference. In this study, we present an analysis framework for inferring the functions of Plasmodium falciparum genes based on connection profiles in a heterogeneous network between human and Plasmodium falciparum proteins. These profiles were fed into a hybrid deep learning algorithm to predict the orthologs of unknown function genes. The results show high performance of the model’s predictions, with an AUC of 0.89. One hundred and twenty-one predicted pairs with high prediction scores were selected for inferring the functions using statistical enrichment analysis. Using this method, PF3D7_1248700 and PF3D7_0401800 were found to be involved with muscle contraction and striated muscle tissue development, while PF3D7_1303800 and PF3D7_1201000 were found to be related to protein dephosphorylation. In conclusion, combining a heterogeneous network and a hybrid deep learning technique can allow us to identify unknown gene functions of malaria parasites. This approach is generalized and can be applied to other diseases that enhance the field of biomedical science.

Multi-Level Biological Network Analysis and Drug Repurposing Based on Leukocyte Transcriptomics in Severe COVID-19: In Silico Systems Biology to Precision Medicine

“…With the use of network analysis, central node identification using various centrality measurements and community detection by several network clustering algorithms [ 46 , 47 ] have been widely used in much research. These approaches were successfully applied in several applications to identify key disease-related genes, disease–disease associations, disease–protein associations, and drug–disease associations [ 48 , 49 , 50 , 51 , 52 , 53 , 54 , 55 , 56 , 57 ]. Additionally, the benefit of the network analysis is drug repositioning or drug repurposing, characterized by discovering a new role of treatment from existing drugs based on the key disease-related genes identified from the biological network [ 58 ].…”

Integration of various protein similarities using random forest technique to infer augmented drug-protein matrix for enhancing drug-disease association prediction

“…Network-based methods have been successfully used for predicting several tasks, including disease-disease association predictions, 18 disease protein association predictions, [19][20][21][22][23][24][25] and drug-disease association predictions. 26,27 Several computational drug repositioning approaches focus on a heterogeneous network of different types of nodes such as drugs, proteins, and diseases.…”

Heterogeneous network propagation with forward similarity integration to enhance drug–target association prediction

“…These probably lead to the non-optimal performance of predictions. Moreover, it has been known that network-based methods have been successfully applied in several applications ( Hengphasatporn et al, 2020 ; Janyasupab, Suratanee & Plaimas, 2021 ; Kawichai, Suratanee & Plaimas, 2021 ; Suratanee, Buaboocha & Plaimas, 2021 ; Suratanee et al, 2018 ; Suratanee & Plaimas, 2014 ; Suratanee & Plaimas, 2015 ; Suratanee & Plaimas, 2017 ; Suratanee & Plaimas, 2018 ; Suratanee & Plaimas, 2020 ; Suratanee & Plaimas, 2021 ). Therefore, in this work, we propose a network-based method with the forward similarity integration (FSI) framework to systemically integrate multiple similarities and predict new links between drugs and targets.…”