Cargando…

Epistatic Net allows the sparse spectral regularization of deep neural networks for inferring fitness functions

Despite recent advances in high-throughput combinatorial mutagenesis assays, the number of labeled sequences available to predict molecular functions has remained small for the vastness of the sequence space combined with the ruggedness of many fitness functions. While deep neural networks (DNNs) ca...

Descripción completa

Detalles Bibliográficos
Autores principales: Aghazadeh, Amirali, Nisonoff, Hunter, Ocal, Orhan, Brookes, David H., Huang, Yijie, Koyluoglu, O. Ozan, Listgarten, Jennifer, Ramchandran, Kannan
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Nature Publishing Group UK 2021
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8410946/
https://www.ncbi.nlm.nih.gov/pubmed/34471113
http://dx.doi.org/10.1038/s41467-021-25371-3
_version_ 1783747200888602624
author Aghazadeh, Amirali
Nisonoff, Hunter
Ocal, Orhan
Brookes, David H.
Huang, Yijie
Koyluoglu, O. Ozan
Listgarten, Jennifer
Ramchandran, Kannan
author_facet Aghazadeh, Amirali
Nisonoff, Hunter
Ocal, Orhan
Brookes, David H.
Huang, Yijie
Koyluoglu, O. Ozan
Listgarten, Jennifer
Ramchandran, Kannan
author_sort Aghazadeh, Amirali
collection PubMed
description Despite recent advances in high-throughput combinatorial mutagenesis assays, the number of labeled sequences available to predict molecular functions has remained small for the vastness of the sequence space combined with the ruggedness of many fitness functions. While deep neural networks (DNNs) can capture high-order epistatic interactions among the mutational sites, they tend to overfit to the small number of labeled sequences available for training. Here, we developed Epistatic Net (EN), a method for spectral regularization of DNNs that exploits evidence that epistatic interactions in many fitness functions are sparse. We built a scalable extension of EN, usable for larger sequences, which enables spectral regularization using fast sparse recovery algorithms informed by coding theory. Results on several biological landscapes show that EN consistently improves the prediction accuracy of DNNs and enables them to outperform competing models which assume other priors. EN estimates the higher-order epistatic interactions of DNNs trained on massive sequence spaces-a computational problem that otherwise takes years to solve.
format Online
Article
Text
id pubmed-8410946
institution National Center for Biotechnology Information
language English
publishDate 2021
publisher Nature Publishing Group UK
record_format MEDLINE/PubMed
spelling pubmed-84109462021-09-22 Epistatic Net allows the sparse spectral regularization of deep neural networks for inferring fitness functions Aghazadeh, Amirali Nisonoff, Hunter Ocal, Orhan Brookes, David H. Huang, Yijie Koyluoglu, O. Ozan Listgarten, Jennifer Ramchandran, Kannan Nat Commun Article Despite recent advances in high-throughput combinatorial mutagenesis assays, the number of labeled sequences available to predict molecular functions has remained small for the vastness of the sequence space combined with the ruggedness of many fitness functions. While deep neural networks (DNNs) can capture high-order epistatic interactions among the mutational sites, they tend to overfit to the small number of labeled sequences available for training. Here, we developed Epistatic Net (EN), a method for spectral regularization of DNNs that exploits evidence that epistatic interactions in many fitness functions are sparse. We built a scalable extension of EN, usable for larger sequences, which enables spectral regularization using fast sparse recovery algorithms informed by coding theory. Results on several biological landscapes show that EN consistently improves the prediction accuracy of DNNs and enables them to outperform competing models which assume other priors. EN estimates the higher-order epistatic interactions of DNNs trained on massive sequence spaces-a computational problem that otherwise takes years to solve. Nature Publishing Group UK 2021-09-01 /pmc/articles/PMC8410946/ /pubmed/34471113 http://dx.doi.org/10.1038/s41467-021-25371-3 Text en © The Author(s) 2021 https://creativecommons.org/licenses/by/4.0/Open Access This article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license, and indicate if changes were made. The images or other third party material in this article are included in the article’s Creative Commons license, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons license and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this license, visit http://creativecommons.org/licenses/by/4.0/ (https://creativecommons.org/licenses/by/4.0/) .
spellingShingle Article
Aghazadeh, Amirali
Nisonoff, Hunter
Ocal, Orhan
Brookes, David H.
Huang, Yijie
Koyluoglu, O. Ozan
Listgarten, Jennifer
Ramchandran, Kannan
Epistatic Net allows the sparse spectral regularization of deep neural networks for inferring fitness functions
title Epistatic Net allows the sparse spectral regularization of deep neural networks for inferring fitness functions
title_full Epistatic Net allows the sparse spectral regularization of deep neural networks for inferring fitness functions
title_fullStr Epistatic Net allows the sparse spectral regularization of deep neural networks for inferring fitness functions
title_full_unstemmed Epistatic Net allows the sparse spectral regularization of deep neural networks for inferring fitness functions
title_short Epistatic Net allows the sparse spectral regularization of deep neural networks for inferring fitness functions
title_sort epistatic net allows the sparse spectral regularization of deep neural networks for inferring fitness functions
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8410946/
https://www.ncbi.nlm.nih.gov/pubmed/34471113
http://dx.doi.org/10.1038/s41467-021-25371-3
work_keys_str_mv AT aghazadehamirali epistaticnetallowsthesparsespectralregularizationofdeepneuralnetworksforinferringfitnessfunctions
AT nisonoffhunter epistaticnetallowsthesparsespectralregularizationofdeepneuralnetworksforinferringfitnessfunctions
AT ocalorhan epistaticnetallowsthesparsespectralregularizationofdeepneuralnetworksforinferringfitnessfunctions
AT brookesdavidh epistaticnetallowsthesparsespectralregularizationofdeepneuralnetworksforinferringfitnessfunctions
AT huangyijie epistaticnetallowsthesparsespectralregularizationofdeepneuralnetworksforinferringfitnessfunctions
AT koyluogluoozan epistaticnetallowsthesparsespectralregularizationofdeepneuralnetworksforinferringfitnessfunctions
AT listgartenjennifer epistaticnetallowsthesparsespectralregularizationofdeepneuralnetworksforinferringfitnessfunctions
AT ramchandrankannan epistaticnetallowsthesparsespectralregularizationofdeepneuralnetworksforinferringfitnessfunctions