Literature DB >> 35016607

GCRNN: graph convolutional recurrent neural network for compound-protein interaction prediction.

Ermal Elbasani1, Soualihou Ngnamsie Njimbouom1, Tae-Jin Oh2,3,4, Eung-Hee Kim5, Hyun Lee1, Jeong-Dong Kim6,7.   

Abstract

BACKGROUND: Compound-protein interaction prediction is necessary to investigate health regulatory functions and promotes drug discovery. Machine learning is becoming increasingly important in bioinformatics for applications such as analyzing protein-related data to achieve successful solutions. Modeling the properties and functions of proteins is important but challenging, especially when dealing with predictions of the sequence type. RESULT: We propose a method to model compounds and proteins for compound-protein interaction prediction. A graph neural network is used to represent the compounds, and a convolutional layer extended with a bidirectional recurrent neural network framework, Long Short-Term Memory, and Gate Recurrent unit is used for protein sequence vectorization. The convolutional layer captures regulatory protein functions, while the recurrent layer captures long-term dependencies between protein functions, thus improving the accuracy of interaction prediction with compounds. A database of 7000 sets of annotated compound protein interaction, containing 1000 base length proteins is taken into consideration for the implementation. The results indicate that the proposed model performs effectively and can yield satisfactory accuracy regarding compound protein interaction prediction.
CONCLUSION: The performance of GCRNN is based on the classification accordiong to a binary class of interactions between proteins and compounds The architectural design of GCRNN model comes with the integration of the Bi-Recurrent layer on top of CNN to learn dependencies of motifs on protein sequences and improve the accuracy of the predictions.
© 2022. The Author(s).

Entities:  

Keywords:  Bi-GRU; Bi-LSTM; CNN; Drug discovery; Machine learning; Protein compound interaction

Mesh:

Substances:

Year:  2022        PMID: 35016607      PMCID: PMC8753816          DOI: 10.1186/s12859-022-04560-x

Source DB:  PubMed          Journal:  BMC Bioinformatics        ISSN: 1471-2105            Impact factor:   3.169


  15 in total

1.  Predicting drug-target interaction for new drugs using enhanced similarity measures and super-target clustering.

Authors:  Jian-Yu Shi; Siu-Ming Yiu; Yiming Li; Henry C M Leung; Francis Y L Chin
Journal:  Methods       Date:  2015-05-06       Impact factor: 3.608

2.  Improved Protein-Ligand Binding Affinity Prediction with Structure-Based Deep Fusion Inference.

Authors:  Derek Jones; Hyojin Kim; Xiaohua Zhang; Adam Zemla; Garrett Stevenson; W F Drew Bennett; Daniel Kirshner; Sergio E Wong; Felice C Lightstone; Jonathan E Allen
Journal:  J Chem Inf Model       Date:  2021-03-23       Impact factor: 4.956

3.  How artificial intelligence is changing drug discovery.

Authors:  Nic Fleming
Journal:  Nature       Date:  2018-05       Impact factor: 49.962

4.  CGBVS-DNN: Prediction of Compound-protein Interactions Based on Deep Learning.

Authors:  Masatoshi Hamanaka; Kei Taneishi; Hiroaki Iwata; Jun Ye; Jianguo Pei; Jinlong Hou; Yasushi Okuno
Journal:  Mol Inform       Date:  2016-08-12       Impact factor: 3.353

5.  Improved prediction of drug-target interactions using regularized least squares integrating with kernel fusion technique.

Authors:  Ming Hao; Yanli Wang; Stephen H Bryant
Journal:  Anal Chim Acta       Date:  2016-01-14       Impact factor: 6.558

6.  Protein-ligand interaction prediction: an improved chemogenomics approach.

Authors:  Laurent Jacob; Jean-Philippe Vert
Journal:  Bioinformatics       Date:  2008-08-01       Impact factor: 6.937

7.  Deep mining heterogeneous networks of biomedical linked data to predict novel drug-target associations.

Authors:  Nansu Zong; Hyeoneui Kim; Victoria Ngo; Olivier Harismendy
Journal:  Bioinformatics       Date:  2017-08-01       Impact factor: 6.937

8.  Improving compound-protein interaction prediction by building up highly credible negative samples.

Authors:  Hui Liu; Jianjiang Sun; Jihong Guan; Jie Zheng; Shuigeng Zhou
Journal:  Bioinformatics       Date:  2015-06-15       Impact factor: 6.937

9.  DanQ: a hybrid convolutional and recurrent deep neural network for quantifying the function of DNA sequences.

Authors:  Daniel Quang; Xiaohui Xie
Journal:  Nucleic Acids Res       Date:  2016-04-15       Impact factor: 16.971

10.  Supervised prediction of drug-target interactions using bipartite local models.

Authors:  Kevin Bleakley; Yoshihiro Yamanishi
Journal:  Bioinformatics       Date:  2009-07-15       Impact factor: 6.937

View more

北京卡尤迪生物科技股份有限公司 © 2022-2023.