DDIT: An Online Predictor for Multiple Clinical Phenotypic Drug-Disease Associations.

Lu Lu,Hao Wu,Jiale Qin,Jiandong Chen,Satoru Miyano,Qiang Zhao,Hua Yu,Yaozhong Zhang,Chen Li

doi:10.3389/fphar.2021.772026

Abstract

Background: Drug repurposing provides an effective method for high-speed, low-risk drug development. Clinical phenotype-based screening exceeded target-based approaches in discovering first-in-class small-molecule drugs. However, most of these approaches predict only binary phenotypic associations between drugs and diseases; the types of drug and diseases have not been well exploited. Principally, the clinical phenotypes of a known drug can be divided into indications (Is), side effects (SEs), and contraindications (CIs). Incorporating these different clinical phenotypes of drug–disease associations (DDAs) can improve the prediction accuracy of the DDAs. Methods: We develop Drug Disease Interaction Type (DDIT), a user-friendly online predictor that supports drug repositioning by submitting known Is, SEs, and CIs for a target drug of interest. The dataset for Is, SEs, and CIs was extracted from PREDICT, SIDER, and MED-RT, respectively. To unify the names of the drugs and diseases, we mapped their names to the Unified Medical Language System (UMLS) ontology using Rest API. We then integrated multiple clinical phenotypes into a conditional restricted Boltzmann machine (RBM) enabling the identification of different phenotypes of drug–disease associations, including the prediction of as yet unknown DDAs in the input. Results: By 10-fold cross-validation, we demonstrate that DDIT can effectively capture the latent features of the drug–disease association network and represents over 0.217 and over 0.072 improvement in AUC and AUPR, respectively, for predicting the clinical phenotypes of DDAs compared with the classic K-nearest neighbors method (KNN, including drug-based KNN and disease-based KNN), Random Forest, and XGBoost. By conducting leave-one-drug-class-out cross-validation, the AUC and AUPR of DDIT demonstrated an improvement of 0.135 in AUC and 0.075 in AUPR compared to any of the other four methods. Within the top 10 predicted indications, side effects, and contraindications, 7/10, 9/10, and 9/10 hit known drug–disease associations. Overall, DDIT is a useful tool for predicting multiple clinical phenotypic types of drug–disease associations.

Highlights

Novel drug development is a complicated, time-consuming, and expensive process
By 10-fold cross-validation, we demonstrate that Drug Disease Interaction Type (DDIT) can effectively capture the latent features of the drug–disease association network and represents over 0.217 and over 0.072 improvement in area under Receiver operator characteristic (ROC) curve (AUC) and area under the PR curve (AUPR), respectively, for predicting the clinical phenotypes of drug–disease associations (DDAs) compared with the classic K-nearest neighbors method (KNN, including drug-based KNN and disease-based KNN), Random Forest, and XGBoost
One shortcoming is represented in that our study observed that an restricted Boltzmann machine (RBM) cannot make predictions for a disease class without any known related drugs (AUC, ∼0.549)

Summary

Introduction

Novel drug development is a complicated, time-consuming, and expensive process. It often takes 10–15 years of research and 0.8–1.5 billion dollars to bring a drug to market (Li et al, 2016). One classic example is the discovery of the drug sildenafil for the treatment of male sexual dysfunction, which had been previously developed as a hypertension drug in 1989 (Ghofrani et al, 2006). Another is azidothymidine, originally failing in trials as a tumor chemotherapy drug, but succeeding as a treatment for AIDS in 1980 (Broder, 2010). Clinical phenotype-based screening exceeded target-based approaches in discovering first-in-class small-molecule drugs Most of these approaches predict only binary phenotypic associations between drugs and diseases; the types of drug and diseases have not been well exploited. Incorporating these different clinical phenotypes of drug–disease associations (DDAs) can improve the prediction accuracy of the DDAs

Methods

Results

Conclusion