A deep learning method for drug-target affinity prediction based on sequence interaction information mining
Background A critical aspect of in silico drug discovery involves the prediction of drug-target affinity (DTA). Conducting wet lab experiments to determine affinity is both expensive and time-consuming, making it necessary to find alternative approaches. In recent years, deep learning has emerged as...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
PeerJ Inc.
2023-12-01
|
| Series: | PeerJ |
| Subjects: | |
| Online Access: | https://peerj.com/articles/16625.pdf |
| _version_ | 1827585516165398528 |
|---|---|
| author | Mingjian Jiang Yunchang Shao Yuanyuan Zhang Wei Zhou Shunpeng Pang |
| author_facet | Mingjian Jiang Yunchang Shao Yuanyuan Zhang Wei Zhou Shunpeng Pang |
| author_sort | Mingjian Jiang |
| collection | DOAJ |
| description | Background A critical aspect of in silico drug discovery involves the prediction of drug-target affinity (DTA). Conducting wet lab experiments to determine affinity is both expensive and time-consuming, making it necessary to find alternative approaches. In recent years, deep learning has emerged as a promising technique for DTA prediction, leveraging the substantial computational power of modern computers. Methods We proposed a novel sequence-based approach, named KC-DTA, for predicting drug-target affinity (DTA). In this approach, we converted the target sequence into two distinct matrices, while representing the molecule compound as a graph. The proposed method utilized k-mers analysis and Cartesian product calculation to capture the interactions and evolutionary information among various residues, enabling the creation of the two matrices for target sequence. For molecule, it was represented by constructing a molecular graph where atoms serve as nodes and chemical bonds serve as edges. Subsequently, the obtained target matrices and molecule graph were utilized as inputs for convolutional neural networks (CNNs) and graph neural networks (GNNs) to extract hidden features, which were further used for the prediction of binding affinity. Results In order to evaluate the effectiveness of the proposed method, we conducted several experiments and made a comprehensive comparison with the state-of-the-art approaches using multiple evaluation metrics. The results of our experiments demonstrated that the KC-DTA method achieves high performance in predicting drug-target affinity (DTA). The findings of this research underscore the significance of the KC-DTA method as a valuable tool in the field of in silico drug discovery, offering promising opportunities for accelerating the drug development process. All the data and code are available for access on https://github.com/syc2017/KCDTA. |
| first_indexed | 2024-03-08T23:47:37Z |
| format | Article |
| id | doaj.art-66f6eeaeb23b4825a353d47f994210d1 |
| institution | Directory Open Access Journal |
| issn | 2167-8359 |
| language | English |
| last_indexed | 2024-03-08T23:47:37Z |
| publishDate | 2023-12-01 |
| publisher | PeerJ Inc. |
| record_format | Article |
| series | PeerJ |
| spelling | doaj.art-66f6eeaeb23b4825a353d47f994210d12023-12-13T15:05:25ZengPeerJ Inc.PeerJ2167-83592023-12-0111e1662510.7717/peerj.16625A deep learning method for drug-target affinity prediction based on sequence interaction information miningMingjian Jiang0Yunchang Shao1Yuanyuan Zhang2Wei Zhou3Shunpeng Pang4School of Information and Control Engineering, Qingdao University of Technology, Qingdao, Shandong, ChinaSchool of Information and Control Engineering, Qingdao University of Technology, Qingdao, Shandong, ChinaSchool of Information and Control Engineering, Qingdao University of Technology, Qingdao, Shandong, ChinaSchool of Information and Control Engineering, Qingdao University of Technology, Qingdao, Shandong, ChinaSchool of Computer Engineering, WeiFang University, Weifang, Shandong, ChinaBackground A critical aspect of in silico drug discovery involves the prediction of drug-target affinity (DTA). Conducting wet lab experiments to determine affinity is both expensive and time-consuming, making it necessary to find alternative approaches. In recent years, deep learning has emerged as a promising technique for DTA prediction, leveraging the substantial computational power of modern computers. Methods We proposed a novel sequence-based approach, named KC-DTA, for predicting drug-target affinity (DTA). In this approach, we converted the target sequence into two distinct matrices, while representing the molecule compound as a graph. The proposed method utilized k-mers analysis and Cartesian product calculation to capture the interactions and evolutionary information among various residues, enabling the creation of the two matrices for target sequence. For molecule, it was represented by constructing a molecular graph where atoms serve as nodes and chemical bonds serve as edges. Subsequently, the obtained target matrices and molecule graph were utilized as inputs for convolutional neural networks (CNNs) and graph neural networks (GNNs) to extract hidden features, which were further used for the prediction of binding affinity. Results In order to evaluate the effectiveness of the proposed method, we conducted several experiments and made a comprehensive comparison with the state-of-the-art approaches using multiple evaluation metrics. The results of our experiments demonstrated that the KC-DTA method achieves high performance in predicting drug-target affinity (DTA). The findings of this research underscore the significance of the KC-DTA method as a valuable tool in the field of in silico drug discovery, offering promising opportunities for accelerating the drug development process. All the data and code are available for access on https://github.com/syc2017/KCDTA.https://peerj.com/articles/16625.pdfDeep learningDrug-target affinity predictionProtein sequenceGraph neural networkConvolutional neural network |
| spellingShingle | Mingjian Jiang Yunchang Shao Yuanyuan Zhang Wei Zhou Shunpeng Pang A deep learning method for drug-target affinity prediction based on sequence interaction information mining PeerJ Deep learning Drug-target affinity prediction Protein sequence Graph neural network Convolutional neural network |
| title | A deep learning method for drug-target affinity prediction based on sequence interaction information mining |
| title_full | A deep learning method for drug-target affinity prediction based on sequence interaction information mining |
| title_fullStr | A deep learning method for drug-target affinity prediction based on sequence interaction information mining |
| title_full_unstemmed | A deep learning method for drug-target affinity prediction based on sequence interaction information mining |
| title_short | A deep learning method for drug-target affinity prediction based on sequence interaction information mining |
| title_sort | deep learning method for drug target affinity prediction based on sequence interaction information mining |
| topic | Deep learning Drug-target affinity prediction Protein sequence Graph neural network Convolutional neural network |
| url | https://peerj.com/articles/16625.pdf |
| work_keys_str_mv | AT mingjianjiang adeeplearningmethodfordrugtargetaffinitypredictionbasedonsequenceinteractioninformationmining AT yunchangshao adeeplearningmethodfordrugtargetaffinitypredictionbasedonsequenceinteractioninformationmining AT yuanyuanzhang adeeplearningmethodfordrugtargetaffinitypredictionbasedonsequenceinteractioninformationmining AT weizhou adeeplearningmethodfordrugtargetaffinitypredictionbasedonsequenceinteractioninformationmining AT shunpengpang adeeplearningmethodfordrugtargetaffinitypredictionbasedonsequenceinteractioninformationmining AT mingjianjiang deeplearningmethodfordrugtargetaffinitypredictionbasedonsequenceinteractioninformationmining AT yunchangshao deeplearningmethodfordrugtargetaffinitypredictionbasedonsequenceinteractioninformationmining AT yuanyuanzhang deeplearningmethodfordrugtargetaffinitypredictionbasedonsequenceinteractioninformationmining AT weizhou deeplearningmethodfordrugtargetaffinitypredictionbasedonsequenceinteractioninformationmining AT shunpengpang deeplearningmethodfordrugtargetaffinitypredictionbasedonsequenceinteractioninformationmining |