Predicting drug target interactions using meta-path-based semantic network analysis.

Gang Fu,Bin Chen,Yizhou Sun,Ying Ding,Evan Bolton,Abhik Seal

doi:10.1186/s12859-016-1005-x

Abstract

BackgroundIn the context of drug discovery, drug target interactions (DTIs) can be predicted based on observed topological features of a semantic network across the chemical and biological space. In a semantic network, the types of the nodes and links are different. In order to take into account the heterogeneity of the semantic network, meta-path-based topological patterns were investigated for link prediction.ResultsSupervised machine learning models were constructed based on meta-path topological features of an enriched semantic network, which was derived from Chem2Bio2RDF, and was expanded by adding compound and protein similarity neighboring links obtained from the PubChem databases. The additional semantic links significantly improved the predictive performance of the supervised learning models. The binary classification model built upon the enriched feature space using the Random Forest algorithm significantly outperformed an existing semantic link prediction algorithm, Semantic Link Association Prediction (SLAP), to predict unknown links between compounds and protein targets in an evolving network. In addition to link prediction, Random Forest also has an intrinsic feature ranking algorithm, which can be used to select the important topological features that contribute to link prediction.ConclusionsThe proposed framework has been demonstrated as a powerful alternative to SLAP in order to predict DTIs using the semantic network that integrates chemical, pharmacological, genomic, biological, functional, and biomedical information into a unified framework. It offers the flexibility to enrich the feature space by using different normalization processes on the topological features, and it can perform model construction and feature selection at the same time.Electronic supplementary materialThe online version of this article (doi:10.1186/s12859-016-1005-x) contains supplementary material, which is available to authorized users.

Highlights

In the context of drug discovery, drug target interactions (DTIs) can be predicted based on observed topological features of a semantic network across the chemical and biological space
Rather than using a statistical model to study the significance of meta-path topological features, we propose a framework to take advantage of machine learning algorithms, including Random Forest (RF) and Support Vector Machine (SVM), to construct binary classification models to predict DTI
In combination with random walk (RW) normalization, the predictive performance of RF models was improved by 2 %, and the predictive performance of SVM models were boosted by 3.5 %

Summary

Introduction

In the context of drug discovery, drug target interactions (DTIs) can be predicted based on observed topological features of a semantic network across the chemical and biological space. In order to take into account the heterogeneity of the semantic network, meta-path-based topological patterns were investigated for link prediction. Semantic standards and technologies facilitate seamless data integration across multiple domains, and enable the construction of a heterogeneous network consisting of various biological entities of different types, Predicting DTI is equivalent to link prediction, which is a fundamental problem and long-standing challenge in complex network analysis [16]. Most similarity-based link prediction algorithms designed for homogeneous networks cannot take into account the heterogeneous types and relations defined in semantic networks; it is fairly challenging to consider the long paths connecting two end nodes (indirect connections), which can significantly increase large volumes of randomness in the connectivity. It has been proven that meta-path-based similarity can improve the performance of information retrieval in heterogeneous information networks [23]

Methods

Results

Conclusion