Cargando…

TopologyNet: Topology based deep convolutional and multi-task neural networks for biomolecular property predictions

Although deep learning approaches have had tremendous success in image, video and audio processing, computer vision, and speech recognition, their applications to three-dimensional (3D) biomolecular structural data sets have been hindered by the geometric and biological complexity. To address this p...

Descripción completa

Detalles Bibliográficos
Autores principales: Cang, Zixuan, Wei, Guo-Wei
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Public Library of Science 2017
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC5549771/
https://www.ncbi.nlm.nih.gov/pubmed/28749969
http://dx.doi.org/10.1371/journal.pcbi.1005690
_version_ 1783256030327603200
author Cang, Zixuan
Wei, Guo-Wei
author_facet Cang, Zixuan
Wei, Guo-Wei
author_sort Cang, Zixuan
collection PubMed
description Although deep learning approaches have had tremendous success in image, video and audio processing, computer vision, and speech recognition, their applications to three-dimensional (3D) biomolecular structural data sets have been hindered by the geometric and biological complexity. To address this problem we introduce the element-specific persistent homology (ESPH) method. ESPH represents 3D complex geometry by one-dimensional (1D) topological invariants and retains important biological information via a multichannel image-like representation. This representation reveals hidden structure-function relationships in biomolecules. We further integrate ESPH and deep convolutional neural networks to construct a multichannel topological neural network (TopologyNet) for the predictions of protein-ligand binding affinities and protein stability changes upon mutation. To overcome the deep learning limitations from small and noisy training sets, we propose a multi-task multichannel topological convolutional neural network (MM-TCNN). We demonstrate that TopologyNet outperforms the latest methods in the prediction of protein-ligand binding affinities, mutation induced globular protein folding free energy changes, and mutation induced membrane protein folding free energy changes. Availability: weilab.math.msu.edu/TDL/
format Online
Article
Text
id pubmed-5549771
institution National Center for Biotechnology Information
language English
publishDate 2017
publisher Public Library of Science
record_format MEDLINE/PubMed
spelling pubmed-55497712017-08-15 TopologyNet: Topology based deep convolutional and multi-task neural networks for biomolecular property predictions Cang, Zixuan Wei, Guo-Wei PLoS Comput Biol Research Article Although deep learning approaches have had tremendous success in image, video and audio processing, computer vision, and speech recognition, their applications to three-dimensional (3D) biomolecular structural data sets have been hindered by the geometric and biological complexity. To address this problem we introduce the element-specific persistent homology (ESPH) method. ESPH represents 3D complex geometry by one-dimensional (1D) topological invariants and retains important biological information via a multichannel image-like representation. This representation reveals hidden structure-function relationships in biomolecules. We further integrate ESPH and deep convolutional neural networks to construct a multichannel topological neural network (TopologyNet) for the predictions of protein-ligand binding affinities and protein stability changes upon mutation. To overcome the deep learning limitations from small and noisy training sets, we propose a multi-task multichannel topological convolutional neural network (MM-TCNN). We demonstrate that TopologyNet outperforms the latest methods in the prediction of protein-ligand binding affinities, mutation induced globular protein folding free energy changes, and mutation induced membrane protein folding free energy changes. Availability: weilab.math.msu.edu/TDL/ Public Library of Science 2017-07-27 /pmc/articles/PMC5549771/ /pubmed/28749969 http://dx.doi.org/10.1371/journal.pcbi.1005690 Text en © 2017 Cang, Wei http://creativecommons.org/licenses/by/4.0/ This is an open access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/4.0/) , which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.
spellingShingle Research Article
Cang, Zixuan
Wei, Guo-Wei
TopologyNet: Topology based deep convolutional and multi-task neural networks for biomolecular property predictions
title TopologyNet: Topology based deep convolutional and multi-task neural networks for biomolecular property predictions
title_full TopologyNet: Topology based deep convolutional and multi-task neural networks for biomolecular property predictions
title_fullStr TopologyNet: Topology based deep convolutional and multi-task neural networks for biomolecular property predictions
title_full_unstemmed TopologyNet: Topology based deep convolutional and multi-task neural networks for biomolecular property predictions
title_short TopologyNet: Topology based deep convolutional and multi-task neural networks for biomolecular property predictions
title_sort topologynet: topology based deep convolutional and multi-task neural networks for biomolecular property predictions
topic Research Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC5549771/
https://www.ncbi.nlm.nih.gov/pubmed/28749969
http://dx.doi.org/10.1371/journal.pcbi.1005690
work_keys_str_mv AT cangzixuan topologynettopologybaseddeepconvolutionalandmultitaskneuralnetworksforbiomolecularpropertypredictions
AT weiguowei topologynettopologybaseddeepconvolutionalandmultitaskneuralnetworksforbiomolecularpropertypredictions