Predicting primary sequence-based protein-protein interactions using a Mercer series representation of nonlinear support vector machine
Sohrabi Safa, Nader
Alenezi, Ali H.
Rahman, Md Arafatur
MetadataShow full item record
AbstractThe prediction of protein-protein interactions (PPIs) is essential to understand the cellular processes from a medical perspective. Among the various machine learning techniques, kernel-based Support Vector Machine (SVM) has been commonly employed to discriminate between interacting and non-interacting protein pairs. The main drawback of employing the kernel-based SVM to datasets with many features, such as the primary sequence-based protein-protein dataset, is the significant increase in computational time of training stage. This increase in computational time is mainly due to the presence of the kernel in solving the quadratic optimisation problem (QOP) involved in nonlinear SVM. In order to fix this issue, we propose a novel and efficient computational algorithm by approximating the kernel-based SVM using a low-rank truncated Mercer series as well as desired. As a result, the QOP for the approximated kernel-based SVM will be very tractable in the sense that there is a significant reduction in computational time of training and validating stages. We illustrate the novelty of the proposed method by predicting the PPIs of “S. Cerevisiae” where the protein features extracted using the multiscale local descriptor (MLD), and then we compare the predictive performance of the proposed low-rank approximation with the existing methods. Finally, the new method results in significant reduction in computational time for predicting PPIs with almost as accuracy as kernel-based SVM.
CitationChatrabgoun, O., Daneshkhah, A., Esmaeilbeigi, M., Sohrabi Safa, N., Alenezi, A.H. and Rahman, M.A. (2022) Predicting primary sequence-based protein-protein interactions using a Mercer series representation of nonlinear support vector machine. IEEE Access, 10, pp. 124345-124354.
Description© 2022 The Authors. Published by IEEE. This is an open access article available under a Creative Commons licence. The published version can be accessed at the following link on the publisher’s website: https://ieeexplore.ieee.org/document/9956991
SponsorsThe authors extend their appreciation to the Deputyship for Research & Innovation, Ministry of Education in Saudi Arabia for funding this research work through the project number IF-2020-NBU-412.
Except where otherwise noted, this item's license is described as https://creativecommons.org/licenses/by/4.0/
Showing items related by title, author, creator and subject.
Structural determinants of oligomerization of the aquaporin-4 channelKitchen, P; Conner, MT; Bill, RM; Conner, AC; From the Molecular Assembly and Organisation in Cells Doctoral Training Centre, University of Warwick, Coventry CV4 7AL, the School of Life & Health Sciences and Aston Research Centre for Healthy Ageing, Aston University, Aston Triangle, Birmingham, B4 7ET, and the Institute of Clinical Sciences, University of Birmingham, Edgbaston, Birmingham B15 2TT, United Kingdom. (American Society for Biochemistry & Molecular Biology (ASBMB), 2016-01-19)©2016 by The American Society for Biochemistry and Molecular Biology, Inc. The aquaporin (AQP) family of integral membrane protein channels mediate cellular water and solute flow. Although qualitative and quantitative differences in channel permeability, selectivity, subcellular localization, and trafficking responses have been observed for different members of the AQP family, the signature homotetrameric quaternary structure is conserved. Using a variety of biophysical techniques, we show that mutations to an intracellular loop (loop D) of human AQP4 reduce oligomerization. Non-tetrameric AQP4 mutants are unable to relocalize to the plasma membrane in response to changes in extracellular tonicity, despite equivalent constitutive surface expression levels and water permeability to wild-type AQP4. A network of AQP4 loop D hydrogen bonding interactions, identified using molecular dynamics simulations and based on a comparative mutagenic analysis of AQPs 1, 3, and 4, suggest that loop D interactions may provide a general structural framework for tetrameric assembly within theAQPfamily.
Plasma membrane abundance of human aquaporin 5 is dynamically regulated by multiple pathwaysKitchen, P; Öberg, F; Sjöhamn, J; Hedfalk, K; Bill, RM; Törnroth-Horsefield, S; Conner, Matthew T.; Conner, Alex C.; Molecular Organization and Assembly in Cells Doctoral Training Centre, University of Warwick, Coventry, United Kingdom. (Public Library of Science (PLoS), 2015-11-16)© 2015 Kitchen et al. This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited. Aquaporin membrane protein channels mediate cellular water flow. Human aquaporin 5 (AQP5) is highly expressed in the respiratory system and secretory glands where it facilitates the osmotically-driven generation of pulmonary secretions, saliva, sweat and tears. Dysfunctional trafficking of AQP5 has been implicated in several human disease states, including Sjögren's syndrome, bronchitis and cystic fibrosis. In order to investigate how the plasma membrane expression levels of AQP5 are regulated, we studied real-time translocation of GFP-tagged AQP5 in HEK293 cells. We show that AQP5 plasma membrane abundance in transfected HEK293 cells is rapidly and reversibly regulated by at least three independent mechanisms involving phosphorylation at Ser156, protein kinase A activity and extracellular tonicity. The crystal structure of a Ser156 phosphomimetic mutant indicates that its involvement in regulating AQP5 membrane abundance is not mediated by a conformational change of the carboxy-terminus. We suggest that together these pathways regulate cellular water flow.