Predicting drug-target interactions using restricted Boltzmann machines

By Yuhao Wang, Jianyang Zeng. 2013

202 citations recorded by the source corpus.

Motivation: In silico prediction of drug-target interactions plays an important role toward identifying and developing new uses of existing or abandoned drugs. Network-based approaches have recently become a popular tool for discovering new drug-target interactions (DTIs). Unfortunately, most of these network-based approaches can only predict binary interactions between drugs and targets, and information about different types of interactions has not been well exploited for DTI prediction in previous studies. On the other hand, incorporating additional information about drug-target relationships or drug modes of action can improve prediction of DTIs. Furthermore, the predicted types of DTIs can broaden our understanding about the molecular basis of drug action. Results: We propose a first machine learning approach to integrate multiple types of DTIs and predict unknown drug-target relationships or drug modes of action. We cast the new DTI prediction problem into a two-layer graphical model, called restricted Boltzmann machine, and apply a practical learning algorithm to train our model and make predictions. Tests on two public databases show that our restricted Boltzmann machine model can effectively capture the latent features of a DTI network and achieve excellent performance on predicting different types of DTIs, with the area under precision-recall curve up to 89.6. In addition, we demonstrate that integrating multiple types of DTIs can significantly outperform other predictions either by simply mixing multiple types of interactions without distinction or using only a single interaction type. Further tests show that our approach can infer a high fraction of novel DTIs that has been validated by known experiments in the literature or other databases. These results indicate that our approach can have highly practical relevance to DTI prediction and drug repositioning, and hence advance the drug discovery process. Availability: Software and datasets are available on request. Contact: zengjy321@tsinghua.edu.cn Supplementary information: Supplementary data are available at Bioinformatics online.

Subfields: Computational Theory and Mathematics, Molecular Biology, Toxicology

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computational Theory and Mathematics

In Molecular Biology

In Toxicology

Citations in the corpus

Opportunities and obstacles for deep learning in biology and medicine (2017, methodology): “[36] trained individual RBMs for each target in a drug-target interaction network and used these models to predict novel interactions pointing to new indications for existing drugs.”
A network integration approach for drug-target interaction prediction and computational drug repositioning from heterogeneous information (2017, methodology): “To investigate this issue, as in [71], we performed an additional test, in which we only kept those DTIs in which proteins had sequence identity scores < 40% in both training and test data.”
Machine learning approaches and databases for prediction of drug–target interaction: a survey paper (2020, methodology): “Restricted Boltzmann Machine A two-layer undirected graphical model to represent a multidimensional DTI network and encode different types of DTIs [204].”
DeepAffinity: Interpretable Deep Learning of Compound-Protein Affinity through Unified Recurrent and Convolutional Neural Networks (2018, methodology): “However, they have been restricted to classifying CPIs (Chen et al. , 2016) mainly into two types (binding or not) and occasionally more (e.g., binding, activating, or inhibiting (Wang and Zeng, 2013)).”
NeoDTI: Neural integration of neighbor information from a heterogeneous network for discovering new drug-target interactions (2018, background): “compound–protein interaction prediction, drug discovery with one-shot learning) (Altae-Tran et al., 2017; Hamanaka et al., 2017; Tian et al., 2016; Wang and Zeng, 2013; Wan and Zeng, 2016; Xu et al., 2017).”
Drug-target interaction prediction: databases, web servers and computational models (2016, methodology): “Chen and Zeng [32] predicted target group of drugs using a two-step similarity-based method, which integrated graphrepresentation-based method and chemical-functional-grouprepresentation-based method.”
Artificial Intelligence for Clinical Trial Design. (2019, background): “The field of biomedicine has also benefited from this surge in AI methods at many levels, from sophisticated natural language processing (NLP) searches of the biomedical literature [55], to cancer sub-phenotyping using DL [56], to predictions of gene targets of microRNAs [57], drug–target interactio”
Optimizing distributions over molecular space. An Objective-Reinforced Generative Adversarial Network for Inverse-design Chemistry (ORGANIC) (2017, background): “This strategy has achieved many important triumphs in pharmaceutical contexts [6, 7], design of organic photovoltaics [8, 9], OLEDs [10] and ﬂow batteries [11, 12], among many others.”
LRBM: A Restricted Boltzmann Machine Based Approach for Representation Learning on Linked Data (2014, methodology): “In [34], RBM as well as cRBM have been applied to the task of learning Drug-Target relations on multidimensional networks.”