A Systematic Prediction of Multiple Drug-Target Interactions from Chemical, Genomic, and Pharmacological Data

Abstract

In silico prediction of drug-target interactions from heterogeneous biological data can advance our system-level search for drug molecules and therapeutic targets, which efforts have not yet reached full fruition. In this work, we report a systematic approach that efficiently integrates the chemical, genomic, and pharmacological information for drug targeting and discovery on a large scale, based on two powerful methods of Random Forest (RF) and Support Vector Machine (SVM). The performance of the derived models was evaluated and verified with internally five-fold cross-validation and four external independent validations. The optimal models show impressive performance of prediction for drug-target interactions, with a concordance of 82.83%, a sensitivity of 81.33%, and a specificity of 93.62%, respectively. The consistence of the performances of the RF and SVM models demonstrates the reliability and robustness of the obtained models. In addition, the validated models were employed to systematically predict known/unknown drugs and targets involving the enzymes, ion channels, GPCRs, and nuclear receptors, which can be further mapped to functional ontologies such as target-disease associations and target-target interaction networks. This approach is expected to help fill the existing gap between chemical genomics and network pharmacology and thus accelerate the drug discovery processes.

Prediction of Potential Lead Molecules through Systematic Integration of Multi-omics Datasets - A Mini-Review

“…Structural superposition is another alternative approach to compare similar protein structures based on the root mean square deviation (RMSD) calculation [64]. Moreover, systematic integration of large datasets of target-ligand molecular interaction network data with multi-omics data enables to predict or design a potential lead molecule [60]. ii.…”

“…ii. Maximum common substructure -It is a widely used method in CADD for finding similar 3D structures through structured-based or ligand-based virtual screening [60].Maximum common substructure search using SMILES (Simplified Molecular Input Line Entry System)pattern is commonly used to find structural similarity between large chemical datasets [65].The substructure search with compounds in the phenotype linked target-ligand interacting network datasets integrated with multi-omics data enables to predict or design a novel and potential lead molecule [66][67][68]. iii.…”

“…iii. Molecular interaction network -It is the modern and most successive approach to find a novel drug by systematic integration of large datasets of multiomics data [60].Data scientists integrates big data into complex network in the order of phenotype → target →target-ligand←ligand←chemical library to predict or design a novel and potential lead molecule ( Figure 2). Recently, many big pharmaceutical companies and R&D organizations have renewed their interest in discovering potential lead compounds from the natural products due to the structural diversity and medicinal properties [3,69,70].…”

“…The systematic integration of theoretical and experimental datasets of multi-omics, target-ligand interaction network, physicochemical properties, and functional properties leads to design a safe and efficient therapeutics [60].…”

Mining Multi Drug-Pathways via A Probabilistic Heterogeneous Network Multi-label Classifier

“…[26] developed three supervised inference methods to predict Drug-Target Interactions and used for drug repositioning, namely drug-based similarity inference (DBSI), target-based similarity inference (TBSI) and network-based inference (NBI). In addition, Yu et al [27] reported a systematic approach that efficiently integrates the chemical, genomic, and pharmacological information for multi drug targeting and discovery on a large scale, based on two powerful methods of Random Forest (RF) and Support Vector Machine (SVM). Finally, Singh-Blom et al [28] presented two methods for predicting gene-disease associations based on functional gene associations and gene-phenotype associations in model organisms, which is close to this work.…”