MP-VHPPI: Meta predictor for viral host protein-protein interaction prediction in multiple hosts and viruses

Abstract

Viral-host protein-protein interaction (VHPPI) prediction is essential to decoding molecular mechanisms of viral pathogens and host immunity processes that eventually help to control the propagation of viral diseases and to design optimized therapeutics. Multiple AI-based predictors have been developed to predict diverse VHPPIs across a wide range of viruses and hosts, however, these predictors produce better performance only for specific types of hosts and viruses. The prime objective of this research is to develop a robust meta predictor (MP-VHPPI) capable of more accurately predicting VHPPI across multiple hosts and viruses. The proposed meta predictor makes use of two well-known encoding methods Amphiphilic Pseudo-Amino Acid Composition (APAAC) and Quasi-sequence (QS) Order that capture amino acids sequence order and distributional information to most effectively generate the numerical representation of complete viral-host raw protein sequences. Feature agglomeration method is utilized to transform the original feature space into a more informative feature space. Random forest (RF) and Extra tree (ET) classifiers are trained on optimized feature space of both APAAC and QS order separate encoders and by combining both encodings. Further predictions of both classifiers are utilized to feed the Support Vector Machine (SVM) classifier that makes final predictions. The proposed meta predictor is evaluated over 7 different benchmark datasets, where it outperforms existing VHPPI predictors with an average performance of 3.07, 6.07, 2.95, and 2.85% in terms of accuracy, Mathews correlation coefficient, precision, and sensitivity, respectively. To facilitate the scientific community, the MP-VHPPI web server is available at https://sds_genetic_analysis.opendfki.de/MP-VHPPI/.

PRIMITI: a computational approach for accurate prediction of miRNA-target mRNA interaction

“…In this work, PRIMITI-TS have implemented new sets of features, iFeature and single nucleotide polymorphisms (SNPs). iFeature, a nucleic acid sequence encoding scheme provided by iLearn, has demonstrated significant enhancements in various machine learning models across diverse research domains [27, 28]. Our analysis of the model’s performance indicated a substantial improvement when integrating iFeature into PRIMITI-TS (Table S10).…”

“…iLearn is a newly presented Python toolkit that implements a comprehensive set of descriptive variables (or features), named as iFeatures, to encode structural and physicochemical information of nucleic acid or peptide sequences [25, 26]. It has been widely used in multiple fields such as a prediction of mRNA subcellular localisation or protein-protein interaction [27, 28]. It is important to highlight and stress that this is the first time iFeatures are used to characterise miRNA-target site interactions. Statistical analysis for this set of features has been discussed in detail in Supplementary Material and Methods and thereafter provided in Supplementary Results.…”

“…In this context, iLearn, a versatile feature extraction tool designed for encoding DNA, RNA, and protein sequences, offers a comprehensive set of sequence-derived physicochemical descriptive variables (or features), known as iFeatures [25, 26]. Proven to enhance model performance in various biological problems [27, 28], iLearn presents a promising approach for enhancing miRNA-target prediction accuracy. Additionally, Genome-Wide Association Studies (GWAS) have been extensively conducted globally to collect comprehensive information on human genetic variation [29].…”

RPPSP: A Robust and Precise Protein Solubility Predictor by Utilizing Novel Protein Sequence Encoder

“…Proposed predictor is implemented in python language by utilizing three main APIs namely Biopython, 3 scikit-learn 4 and iLearn Plus. 5 Optimal hyperparameters selection has significant impact on the performance of machine learning classifiers. Following the success of grid search approach in previous studies [61], [66], [81], we performed classifiers hyperparameters optimization through grid search.…”

“…In the marathon of developing more powerful protein solubility predictor, to transform raw protein sequences into statistical vectors [5], [7], [8],researchers have utilized 19 different encoders. However, these encoders do not capture sequence order information such as interdependencies between amino acids and distributional, compositional as well as transitional information of amino acids [20], [34], [50], [51].…”