Identification of protein–protein interaction associated functions based on gene ontology and KEGG pathway

Abstract

Protein–protein interactions (PPIs) are extremely important for gaining mechanistic insights into the functional organization of the proteome. The resolution of PPI functions can help in the identification of novel diagnostic and therapeutic targets with medical utility, thus facilitating the development of new medications. However, the traditional methods for resolving PPI functions are mainly experimental methods, such as co-immunoprecipitation, pull-down assays, cross-linking, label transfer, and far-Western blot analysis, that are not only expensive but also time-consuming. In this study, we constructed an integrated feature selection scheme for the large-scale selection of the relevant functions of PPIs by using the Gene Ontology and Kyoto Encyclopedia of Genes and Genomes (KEGG) pathway annotations of PPI participants. First, we encoded the proteins in each PPI with their gene ontologies and KEGG pathways. Then, the encoded protein features were refined as features of both positive and negative PPIs. Subsequently, Boruta was used for the initial filtering of features to obtain 5684 features. Three feature ranking algorithms, namely, least absolute shrinkage and selection operator, light gradient boosting machine, and max-relevance and min-redundancy, were applied to evaluate feature importance. Finally, the top-ranked features derived from multiple datasets were comprehensively evaluated, and the intersection of results mined by three feature ranking algorithms was taken to identify the features with high correlation with PPIs. Some functional terms were identified in our study, including cytokine–cytokine receptor interaction (hsa04060), intrinsic component of membrane (GO:0031224), and protein-binding biological process (GO:0005515). Our newly proposed integrated computational approach offers a novel perspective of the large-scale mining of biological functions linked to PPI.

The identification of key genes and pathways in glioblastoma by bioinformatics analysis

“… 11 The information was obtained from the KEGG (Kyoto Encyclopedia of Genes and Genomes) database. 12 , 13 …”

Exploring The Potential Of GANs In Biological Sequence Analysis

“…The combination of biological sequence analysis and ML models has gained quite a lot of attention among researchers in recent years [8], [9]. As a biological sequence consists of a long string of characters corresponding to either nucleotides or amino acids, it needs to be transformed into a numerical form to make it compatible with the ML model.…”

“…Moreover, the application of ML approaches for performing biological sequence analysis is a popular research topic these days [8], [9]. The ability of ML methods to determine the sequence's biological functions makes them desirable to be employed for sequence analysis.…”

“…Additionally, ML models can also determine the relationship between the primary structure of the sequence and its biological functions. Like [8] built a Random Forest-based algorithm to classify sucrose transporter (SUT) protein, [9] designed a novel tool for Protein-protein interactions data and functional analysis, [10] developed a new ML model to identify RNA pseudo-uridine modification sites. ML-based biological sequence analysis approaches can be categorized into feature-engineering-based methods [11], [12], kernel-based methods [13], neural network-based techniques [14], [15], and pre-trained deep learning models [16], [17].…”

Exploring the Potential of GANs in Biological Sequence Analysis

“…However, the availability of large-size sequence data exceeds the computational limit of such techniques. Moreover, the application of ML approaches for performing biological sequence analysis is a popular research topic these days [ 9 , 10 ]. The ability of ML methods to determine the sequence’s biological functions makes them desirable to be employed for sequence analysis.…”