DeepConv-DTI: Prediction of drug-target interactions via deep learning with convolution on protein sequences

Summary

Identification of drug-target interactions (DTIs) plays a key role in drug discovery. The high cost and labor-intensive nature of in vitro and in vivo experiments have highlighted the importance of in silico-based DTI prediction approaches. In several computational models, conventional protein descriptors have been shown to not be sufficiently informative to predict accurate DTIs. Thus, in this study, we propose a deep learning based DTI prediction model capturing local residue patterns of proteins participating in DTIs. When we employ a convolutional neural network (CNN) on raw protein sequences, we perform convolution on various lengths of amino acids subsequences to capture local residue patterns of generalized protein classes. We train our model with large-scale DTI information and demonstrate the performance of the proposed model using an independent dataset that is not seen during the training phase. As a result, our model performs better than previous protein descriptor-based models. Also, our model performs better than the recently developed deep learning models for massive prediction of DTIs. By examining pooled convolution results, we confirmed that our model can detect binding sites of proteins for DTIs. In conclusion, our prediction model for detecting local residue patterns of target proteins successfully enriches the protein features of a raw protein sequence, yielding better prediction results than previous approaches. Our code is available at https://github.com/GIST-CSBL/DeepConv-DTI.

Key Points

• 1Identification of drug-target interactions is crucial for drug discovery
• 2Traditional protein descriptors are often insufficient for accurate predictions
• 3DeepConv-DTI leverages convolutional neural networks to capture protein residue patterns
• 4The model outperforms conventional and several recent deep learning approaches
• 5Code and models are accessible for further research and application.

Related articles

• Weathering and Soil Formation: A Comprehensive Overview of Rocks and Petrology

  This document serves as an educational resource detailing the classification, formation, and weathering processes of different types of rocks, including igneous, sedimentary, and metamorphic. It also covers the essential elements of soil formation and the various factors influencing soil development.

• PRINCIPLES OF WEED SCIENCE Prepared by: DARWIN M. CACAL, R.Agr., M.Sc., Ph.D.

  This document provides an in-depth exploration of weeds, including their classification, characteristics, impacts on ecosystems and agriculture, and strategies for identification and management.

• LICENSURE EXAMINATION FOR AGRICULTURIST 2025 LECTURE NOTES FOR ANIMAL SCIENCE

  This document serves as a comprehensive review material for the Licensure Examination for Agriculturists in 2025, focusing specifically on Animal Science. It includes essential information about livestock species, production statistics, relevant laws, anatomy and physiology of farm animals, and key concepts in animal science.

• BRANCHES OF SCIENCE: Understanding the Different Fields of Science and Their Relationship to Chemistry

  This document provides an overview of the various branches of science, emphasizing their interrelationships and the role of chemistry as the central science connecting different disciplines. It aims to educate students on defining science, identifying its major branches, and appreciating the importance of scientific study.

• The Skeletal System: Overview and Functions

  This document provides a comprehensive overview of the skeletal system, detailing its components, major functions, and anatomical classification of bones. It also discusses bone anatomy, development, healing, and various skeletal pathologies.