Prediction of protein-protein interactions between HIV-1 and human using support vector machine combined with multivariate mutual information

Mohamad Irlin Sunggawa, Alhadi Bustamam, Devvi Sarwinda, Patuan Pangihutan Tampubolon, Wibowo Mangunwardoyo

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

Protein-protein interactions are the center of many biological processes. Studying protein-protein interaction have a vital role in learning how disease occurs and also crucial in drug design. Studying protein-protein interaction consumes much time and is very costly; even then the results are not always positive. Researchers have developed numerous methods to predict is there any interaction between a pair of protein using only use their amino acid sequences. In this paper, we use support vector machine (SVM) as the classifier combined with four types of multivariate mutual information (MMI) as the descriptor of amino acid sequences to predict protein-protein interaction (PPIs) based on interaction data between HIV1 and Humans. We use data of protein interactions between HIV1 and Humans that are provided in NCBI. The results show that MM1 type I, II, III, and IV have an average accuracy of 84.55%, 84.90%, 83.56%, and 83.61% respectively, when tested on validation datasets.

Original languageEnglish
Title of host publicationIBIOMED 2020 - Proceedings of the 37th International Conference on Biomedical Engineering
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages77-81
Number of pages5
ISBN (Electronic)9781728171562
DOIs
Publication statusPublished - 6 Oct 2020
Event37th International Conference on Biomedical Engineering, IBIOMED 2020 - Yogyakarta, Indonesia
Duration: 6 Oct 20208 Oct 2020

Publication series

NameIBIOMED 2020 - Proceedings of the 37th International Conference on Biomedical Engineering

Conference

Conference37th International Conference on Biomedical Engineering, IBIOMED 2020
Country/TerritoryIndonesia
CityYogyakarta
Period6/10/208/10/20

Keywords

  • Multivariate Mutual Information
  • Protein-protein Interactions
  • Support Vector Machine

Fingerprint

Dive into the research topics of 'Prediction of protein-protein interactions between HIV-1 and human using support vector machine combined with multivariate mutual information'. Together they form a unique fingerprint.

Cite this