An enhanced variant effect predictor based on a deep generative model and the Born-Again Networks

Abstract The development of an accurate and reliable variant effect prediction tool is important for research in human genetic diseases. A large number of predictors have been developed towards this goal, yet many of these predictors suffer from the problem of data circularity. Here we present MTBAN...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Ha Young Kim, Woosung Jeon, Dongsup Kim
Formato: article
Lenguaje:EN
Publicado: Nature Portfolio 2021
Materias:
R
Q
Acceso en línea:https://doaj.org/article/0732861a9c9b4e0a9f75b5da1897d2f6
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
id oai:doaj.org-article:0732861a9c9b4e0a9f75b5da1897d2f6
record_format dspace
spelling oai:doaj.org-article:0732861a9c9b4e0a9f75b5da1897d2f62021-12-02T18:51:35ZAn enhanced variant effect predictor based on a deep generative model and the Born-Again Networks10.1038/s41598-021-98693-32045-2322https://doaj.org/article/0732861a9c9b4e0a9f75b5da1897d2f62021-09-01T00:00:00Zhttps://doi.org/10.1038/s41598-021-98693-3https://doaj.org/toc/2045-2322Abstract The development of an accurate and reliable variant effect prediction tool is important for research in human genetic diseases. A large number of predictors have been developed towards this goal, yet many of these predictors suffer from the problem of data circularity. Here we present MTBAN (Mutation effect predictor using the Temporal convolutional network and the Born-Again Networks), a method for predicting the deleteriousness of variants. We apply a form of knowledge distillation technique known as the Born-Again Networks (BAN) to a previously developed deep autoregressive generative model, mutationTCN, to achieve an improved performance in variant effect prediction. As the model is fully unsupervised and trained only on the evolutionarily related sequences of a protein, it does not suffer from the problem of data circularity which is common across supervised predictors. When evaluated on a test dataset consisting of deleterious and benign human protein variants, MTBAN shows an outstanding predictive ability compared to other well-known variant effect predictors. We also offer a user-friendly web server to predict variant effects using MTBAN, freely accessible at http://mtban.kaist.ac.kr . To our knowledge, MTBAN is the first variant effect prediction tool based on a deep generative model that provides a user-friendly web server for the prediction of deleteriousness of variants.Ha Young KimWoosung JeonDongsup KimNature PortfolioarticleMedicineRScienceQENScientific Reports, Vol 11, Iss 1, Pp 1-7 (2021)
institution DOAJ
collection DOAJ
language EN
topic Medicine
R
Science
Q
spellingShingle Medicine
R
Science
Q
Ha Young Kim
Woosung Jeon
Dongsup Kim
An enhanced variant effect predictor based on a deep generative model and the Born-Again Networks
description Abstract The development of an accurate and reliable variant effect prediction tool is important for research in human genetic diseases. A large number of predictors have been developed towards this goal, yet many of these predictors suffer from the problem of data circularity. Here we present MTBAN (Mutation effect predictor using the Temporal convolutional network and the Born-Again Networks), a method for predicting the deleteriousness of variants. We apply a form of knowledge distillation technique known as the Born-Again Networks (BAN) to a previously developed deep autoregressive generative model, mutationTCN, to achieve an improved performance in variant effect prediction. As the model is fully unsupervised and trained only on the evolutionarily related sequences of a protein, it does not suffer from the problem of data circularity which is common across supervised predictors. When evaluated on a test dataset consisting of deleterious and benign human protein variants, MTBAN shows an outstanding predictive ability compared to other well-known variant effect predictors. We also offer a user-friendly web server to predict variant effects using MTBAN, freely accessible at http://mtban.kaist.ac.kr . To our knowledge, MTBAN is the first variant effect prediction tool based on a deep generative model that provides a user-friendly web server for the prediction of deleteriousness of variants.
format article
author Ha Young Kim
Woosung Jeon
Dongsup Kim
author_facet Ha Young Kim
Woosung Jeon
Dongsup Kim
author_sort Ha Young Kim
title An enhanced variant effect predictor based on a deep generative model and the Born-Again Networks
title_short An enhanced variant effect predictor based on a deep generative model and the Born-Again Networks
title_full An enhanced variant effect predictor based on a deep generative model and the Born-Again Networks
title_fullStr An enhanced variant effect predictor based on a deep generative model and the Born-Again Networks
title_full_unstemmed An enhanced variant effect predictor based on a deep generative model and the Born-Again Networks
title_sort enhanced variant effect predictor based on a deep generative model and the born-again networks
publisher Nature Portfolio
publishDate 2021
url https://doaj.org/article/0732861a9c9b4e0a9f75b5da1897d2f6
work_keys_str_mv AT hayoungkim anenhancedvarianteffectpredictorbasedonadeepgenerativemodelandthebornagainnetworks
AT woosungjeon anenhancedvarianteffectpredictorbasedonadeepgenerativemodelandthebornagainnetworks
AT dongsupkim anenhancedvarianteffectpredictorbasedonadeepgenerativemodelandthebornagainnetworks
AT hayoungkim enhancedvarianteffectpredictorbasedonadeepgenerativemodelandthebornagainnetworks
AT woosungjeon enhancedvarianteffectpredictorbasedonadeepgenerativemodelandthebornagainnetworks
AT dongsupkim enhancedvarianteffectpredictorbasedonadeepgenerativemodelandthebornagainnetworks
_version_ 1718377368082448384