Cargando…

Improving classification of correct and incorrect protein–protein docking models by augmenting the training set

MOTIVATION: Protein–protein interactions drive many relevant biological events, such as infection, replication and recognition. To control or engineer such events, we need to access the molecular details of the interaction provided by experimental 3D structures. However, such experiments take time a...

Descripción completa

Detalles Bibliográficos
Autores principales: Barradas-Bautista, Didier, Almajed, Ali, Oliva, Romina, Kalnis, Panos, Cavallo, Luigi
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Oxford University Press 2023
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9923443/
https://www.ncbi.nlm.nih.gov/pubmed/36789292
http://dx.doi.org/10.1093/bioadv/vbad012
_version_ 1784887741017751552
author Barradas-Bautista, Didier
Almajed, Ali
Oliva, Romina
Kalnis, Panos
Cavallo, Luigi
author_facet Barradas-Bautista, Didier
Almajed, Ali
Oliva, Romina
Kalnis, Panos
Cavallo, Luigi
author_sort Barradas-Bautista, Didier
collection PubMed
description MOTIVATION: Protein–protein interactions drive many relevant biological events, such as infection, replication and recognition. To control or engineer such events, we need to access the molecular details of the interaction provided by experimental 3D structures. However, such experiments take time and are expensive; moreover, the current technology cannot keep up with the high discovery rate of new interactions. Computational modeling, like protein–protein docking, can help to fill this gap by generating docking poses. Protein–protein docking generally consists of two parts, sampling and scoring. The sampling is an exhaustive search of the tridimensional space. The caveat of the sampling is that it generates a large number of incorrect poses, producing a highly unbalanced dataset. This limits the utility of the data to train machine learning classifiers. RESULTS: Using weak supervision, we developed a data augmentation method that we named hAIkal. Using hAIkal, we increased the labeled training data to train several algorithms. We trained and obtained different classifiers; the best classifier has 81% accuracy and 0.51 Matthews’ correlation coefficient on the test set, surpassing the state-of-the-art scoring functions. AVAILABILITY AND IMPLEMENTATION: Docking models from Benchmark 5 are available at https://doi.org/10.5281/zenodo.4012018. Processed tabular data are available at https://repository.kaust.edu.sa/handle/10754/666961. Google colab is available at https://colab.research.google.com/drive/1vbVrJcQSf6\_C3jOAmZzgQbTpuJ5zC1RP?usp=sharing SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics Advances online.
format Online
Article
Text
id pubmed-9923443
institution National Center for Biotechnology Information
language English
publishDate 2023
publisher Oxford University Press
record_format MEDLINE/PubMed
spelling pubmed-99234432023-02-13 Improving classification of correct and incorrect protein–protein docking models by augmenting the training set Barradas-Bautista, Didier Almajed, Ali Oliva, Romina Kalnis, Panos Cavallo, Luigi Bioinform Adv Original Paper MOTIVATION: Protein–protein interactions drive many relevant biological events, such as infection, replication and recognition. To control or engineer such events, we need to access the molecular details of the interaction provided by experimental 3D structures. However, such experiments take time and are expensive; moreover, the current technology cannot keep up with the high discovery rate of new interactions. Computational modeling, like protein–protein docking, can help to fill this gap by generating docking poses. Protein–protein docking generally consists of two parts, sampling and scoring. The sampling is an exhaustive search of the tridimensional space. The caveat of the sampling is that it generates a large number of incorrect poses, producing a highly unbalanced dataset. This limits the utility of the data to train machine learning classifiers. RESULTS: Using weak supervision, we developed a data augmentation method that we named hAIkal. Using hAIkal, we increased the labeled training data to train several algorithms. We trained and obtained different classifiers; the best classifier has 81% accuracy and 0.51 Matthews’ correlation coefficient on the test set, surpassing the state-of-the-art scoring functions. AVAILABILITY AND IMPLEMENTATION: Docking models from Benchmark 5 are available at https://doi.org/10.5281/zenodo.4012018. Processed tabular data are available at https://repository.kaust.edu.sa/handle/10754/666961. Google colab is available at https://colab.research.google.com/drive/1vbVrJcQSf6\_C3jOAmZzgQbTpuJ5zC1RP?usp=sharing SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics Advances online. Oxford University Press 2023-02-02 /pmc/articles/PMC9923443/ /pubmed/36789292 http://dx.doi.org/10.1093/bioadv/vbad012 Text en © The Author(s) 2023. Published by Oxford University Press. https://creativecommons.org/licenses/by/4.0/This is an Open Access article distributed under the terms of the Creative Commons Attribution License (https://creativecommons.org/licenses/by/4.0/), which permits unrestricted reuse, distribution, and reproduction in any medium, provided the original work is properly cited.
spellingShingle Original Paper
Barradas-Bautista, Didier
Almajed, Ali
Oliva, Romina
Kalnis, Panos
Cavallo, Luigi
Improving classification of correct and incorrect protein–protein docking models by augmenting the training set
title Improving classification of correct and incorrect protein–protein docking models by augmenting the training set
title_full Improving classification of correct and incorrect protein–protein docking models by augmenting the training set
title_fullStr Improving classification of correct and incorrect protein–protein docking models by augmenting the training set
title_full_unstemmed Improving classification of correct and incorrect protein–protein docking models by augmenting the training set
title_short Improving classification of correct and incorrect protein–protein docking models by augmenting the training set
title_sort improving classification of correct and incorrect protein–protein docking models by augmenting the training set
topic Original Paper
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9923443/
https://www.ncbi.nlm.nih.gov/pubmed/36789292
http://dx.doi.org/10.1093/bioadv/vbad012
work_keys_str_mv AT barradasbautistadidier improvingclassificationofcorrectandincorrectproteinproteindockingmodelsbyaugmentingthetrainingset
AT almajedali improvingclassificationofcorrectandincorrectproteinproteindockingmodelsbyaugmentingthetrainingset
AT olivaromina improvingclassificationofcorrectandincorrectproteinproteindockingmodelsbyaugmentingthetrainingset
AT kalnispanos improvingclassificationofcorrectandincorrectproteinproteindockingmodelsbyaugmentingthetrainingset
AT cavalloluigi improvingclassificationofcorrectandincorrectproteinproteindockingmodelsbyaugmentingthetrainingset