Cargando…
Computational Prediction of Compound–Protein Interactions for Orphan Targets Using CGBVS
A variety of Artificial Intelligence (AI)-based (Machine Learning) techniques have been developed with regard to in silico prediction of Compound–Protein interactions (CPI)—one of which is a technique we refer to as chemical genomics-based virtual screening (CGBVS). Prediction calculations done via...
Autores principales: | , , , , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
MDPI
2021
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8434178/ https://www.ncbi.nlm.nih.gov/pubmed/34500569 http://dx.doi.org/10.3390/molecules26175131 |
_version_ | 1783751536765042688 |
---|---|
author | Kanai, Chisato Kawasaki, Enzo Murakami, Ryuta Morita, Yusuke Yoshimori, Atsushi |
author_facet | Kanai, Chisato Kawasaki, Enzo Murakami, Ryuta Morita, Yusuke Yoshimori, Atsushi |
author_sort | Kanai, Chisato |
collection | PubMed |
description | A variety of Artificial Intelligence (AI)-based (Machine Learning) techniques have been developed with regard to in silico prediction of Compound–Protein interactions (CPI)—one of which is a technique we refer to as chemical genomics-based virtual screening (CGBVS). Prediction calculations done via pairwise kernel-based support vector machine (SVM) is the main feature of CGBVS which gives high prediction accuracy, with simple implementation and easy handling. We studied whether the CGBVS technique can identify ligands for targets without ligand information (orphan targets) using data from G protein-coupled receptor (GPCR) families. As the validation method, we tested whether the ligand prediction was correct for a virtual orphan GPCR in which all ligand information for one selected target was omitted from the training data. We have specifically expressed the results of this study as applicability index and developed a method to determine whether CGBVS can be used to predict GPCR ligands. Validation results showed that the prediction accuracy of each GPCR differed greatly, but models using Multiple Sequence Alignment (MSA) as the protein descriptor performed well in terms of overall prediction accuracy. We also discovered that the effect of the type compound descriptors on the prediction accuracy was less significant than that of the type of protein descriptors used. Furthermore, we found that the accuracy of the ligand prediction depends on the amount of ligand information with regard to GPCRs related to the target. Additionally, the prediction accuracy tends to be high if a large amount of ligand information for related proteins is used in the training. |
format | Online Article Text |
id | pubmed-8434178 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2021 |
publisher | MDPI |
record_format | MEDLINE/PubMed |
spelling | pubmed-84341782021-09-12 Computational Prediction of Compound–Protein Interactions for Orphan Targets Using CGBVS Kanai, Chisato Kawasaki, Enzo Murakami, Ryuta Morita, Yusuke Yoshimori, Atsushi Molecules Article A variety of Artificial Intelligence (AI)-based (Machine Learning) techniques have been developed with regard to in silico prediction of Compound–Protein interactions (CPI)—one of which is a technique we refer to as chemical genomics-based virtual screening (CGBVS). Prediction calculations done via pairwise kernel-based support vector machine (SVM) is the main feature of CGBVS which gives high prediction accuracy, with simple implementation and easy handling. We studied whether the CGBVS technique can identify ligands for targets without ligand information (orphan targets) using data from G protein-coupled receptor (GPCR) families. As the validation method, we tested whether the ligand prediction was correct for a virtual orphan GPCR in which all ligand information for one selected target was omitted from the training data. We have specifically expressed the results of this study as applicability index and developed a method to determine whether CGBVS can be used to predict GPCR ligands. Validation results showed that the prediction accuracy of each GPCR differed greatly, but models using Multiple Sequence Alignment (MSA) as the protein descriptor performed well in terms of overall prediction accuracy. We also discovered that the effect of the type compound descriptors on the prediction accuracy was less significant than that of the type of protein descriptors used. Furthermore, we found that the accuracy of the ligand prediction depends on the amount of ligand information with regard to GPCRs related to the target. Additionally, the prediction accuracy tends to be high if a large amount of ligand information for related proteins is used in the training. MDPI 2021-08-24 /pmc/articles/PMC8434178/ /pubmed/34500569 http://dx.doi.org/10.3390/molecules26175131 Text en © 2021 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/). |
spellingShingle | Article Kanai, Chisato Kawasaki, Enzo Murakami, Ryuta Morita, Yusuke Yoshimori, Atsushi Computational Prediction of Compound–Protein Interactions for Orphan Targets Using CGBVS |
title | Computational Prediction of Compound–Protein Interactions for Orphan Targets Using CGBVS |
title_full | Computational Prediction of Compound–Protein Interactions for Orphan Targets Using CGBVS |
title_fullStr | Computational Prediction of Compound–Protein Interactions for Orphan Targets Using CGBVS |
title_full_unstemmed | Computational Prediction of Compound–Protein Interactions for Orphan Targets Using CGBVS |
title_short | Computational Prediction of Compound–Protein Interactions for Orphan Targets Using CGBVS |
title_sort | computational prediction of compound–protein interactions for orphan targets using cgbvs |
topic | Article |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8434178/ https://www.ncbi.nlm.nih.gov/pubmed/34500569 http://dx.doi.org/10.3390/molecules26175131 |
work_keys_str_mv | AT kanaichisato computationalpredictionofcompoundproteininteractionsfororphantargetsusingcgbvs AT kawasakienzo computationalpredictionofcompoundproteininteractionsfororphantargetsusingcgbvs AT murakamiryuta computationalpredictionofcompoundproteininteractionsfororphantargetsusingcgbvs AT moritayusuke computationalpredictionofcompoundproteininteractionsfororphantargetsusingcgbvs AT yoshimoriatsushi computationalpredictionofcompoundproteininteractionsfororphantargetsusingcgbvs |