Cargando…
Machine Learning Models to Predict Protein–Protein Interaction Inhibitors
Protein–protein interaction (PPI) inhibitors have an increasing role in drug discovery. It is hypothesized that machine learning (ML) algorithms can classify or identify PPI inhibitors. This work describes the performance of different algorithms and molecular fingerprints used in chemoinformatics to...
Autores principales: | , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
MDPI
2022
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9694076/ https://www.ncbi.nlm.nih.gov/pubmed/36432086 http://dx.doi.org/10.3390/molecules27227986 |
_version_ | 1784837708282068992 |
---|---|
author | Díaz-Eufracio, Bárbara I. Medina-Franco, José L. |
author_facet | Díaz-Eufracio, Bárbara I. Medina-Franco, José L. |
author_sort | Díaz-Eufracio, Bárbara I. |
collection | PubMed |
description | Protein–protein interaction (PPI) inhibitors have an increasing role in drug discovery. It is hypothesized that machine learning (ML) algorithms can classify or identify PPI inhibitors. This work describes the performance of different algorithms and molecular fingerprints used in chemoinformatics to develop a classification model to identify PPI inhibitors making the codes freely available to the community, particularly the medicinal chemistry research groups working with PPI inhibitors. We found that classification algorithms have different performances according to various features employed in the training process. Random forest (RF) models with the extended connectivity fingerprint radius 2 (ECFP4) had the best classification abilities compared to those models trained with ECFP6 o MACCS keys (166-bits). In general, logistic regression (LR) models had lower performance metrics than RF models, but ECFP4 was the representation most appropriate for LR. ECFP4 also generated models with high-performance metrics with support vector machines (SVM). We also constructed ensemble models based on the top-performing models. As part of this work and to help non-computational experts, we developed a pipeline code freely available. |
format | Online Article Text |
id | pubmed-9694076 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2022 |
publisher | MDPI |
record_format | MEDLINE/PubMed |
spelling | pubmed-96940762022-11-26 Machine Learning Models to Predict Protein–Protein Interaction Inhibitors Díaz-Eufracio, Bárbara I. Medina-Franco, José L. Molecules Article Protein–protein interaction (PPI) inhibitors have an increasing role in drug discovery. It is hypothesized that machine learning (ML) algorithms can classify or identify PPI inhibitors. This work describes the performance of different algorithms and molecular fingerprints used in chemoinformatics to develop a classification model to identify PPI inhibitors making the codes freely available to the community, particularly the medicinal chemistry research groups working with PPI inhibitors. We found that classification algorithms have different performances according to various features employed in the training process. Random forest (RF) models with the extended connectivity fingerprint radius 2 (ECFP4) had the best classification abilities compared to those models trained with ECFP6 o MACCS keys (166-bits). In general, logistic regression (LR) models had lower performance metrics than RF models, but ECFP4 was the representation most appropriate for LR. ECFP4 also generated models with high-performance metrics with support vector machines (SVM). We also constructed ensemble models based on the top-performing models. As part of this work and to help non-computational experts, we developed a pipeline code freely available. MDPI 2022-11-17 /pmc/articles/PMC9694076/ /pubmed/36432086 http://dx.doi.org/10.3390/molecules27227986 Text en © 2022 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 Díaz-Eufracio, Bárbara I. Medina-Franco, José L. Machine Learning Models to Predict Protein–Protein Interaction Inhibitors |
title | Machine Learning Models to Predict Protein–Protein Interaction Inhibitors |
title_full | Machine Learning Models to Predict Protein–Protein Interaction Inhibitors |
title_fullStr | Machine Learning Models to Predict Protein–Protein Interaction Inhibitors |
title_full_unstemmed | Machine Learning Models to Predict Protein–Protein Interaction Inhibitors |
title_short | Machine Learning Models to Predict Protein–Protein Interaction Inhibitors |
title_sort | machine learning models to predict protein–protein interaction inhibitors |
topic | Article |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9694076/ https://www.ncbi.nlm.nih.gov/pubmed/36432086 http://dx.doi.org/10.3390/molecules27227986 |
work_keys_str_mv | AT diazeufraciobarbarai machinelearningmodelstopredictproteinproteininteractioninhibitors AT medinafrancojosel machinelearningmodelstopredictproteinproteininteractioninhibitors |