Abstract
MotivationDrug–target interaction (DTI) prediction is a foundational task for in-silico drug discovery, which is costly and time-consuming due to the need of experimental search over large drug compound space. Recent years have witnessed promising progress for deep learning in DTI predictions. However, the following challenges are still open: (i) existing molecular representation learning approaches ignore the sub-structural nature of DTI, thus produce results that are less accurate and difficult to explain and (ii) existing methods focus on limited labeled data while ignoring the value of massive unlabeled molecular data.ResultsWe propose a Molecular Interaction Transformer (MolTrans) to address these limitations via: (i) knowledge inspired sub-structural pattern mining algorithm and interaction modeling module for more accurate and interpretable DTI prediction and (ii) an augmented transformer encoder to better extract and capture the semantic relations among sub-structures extracted from massive unlabeled biomedical data. We evaluate MolTrans on real-world data and show it improved DTI prediction performance compared to state-of-the-art baselines.Availability and implementationThe model scripts are available at https://github.com/kexinhuang12345/moltrans.Supplementary information Supplementary data are available at Bioinformatics online.
Highlights
Drug discovery is notoriously costly and time-consuming due to the need of experimental search over large drug compound space
drugtarget protein interaction (DTI) serves as the foundation for finding new drugs and new indications of existing drugs, since the therapeutic effects of drug compounds are detected by examining DTIs [1]
We show empirically that MolTrans has robust improved predictive performance over state-of-the-art baselines
Summary
Drug discovery is notoriously costly and time-consuming due to the need of experimental search over large drug compound space. They often take drug and protein data as inputs, cast DTI as a classification problem, and make prediction by feeding the inputs through deep learning models such as deep neural network (DNN) [3], deep belief network (DBN) [4], and convolutional neural network (CNN) [5, 6, 7] Despite these efforts, the following challenges are still open. The model architectures in previous works are not designed to enable the integration of massive dataset To solve these challenges, we propose a transformer [12]-based bio-inspired molecular data representation method (coined as MolTrans) to leverage vast unlabelled data for in silico DTI prediction. We show empirically that MolTrans has robust improved predictive performance over state-of-the-art baselines
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
