Multi-scale inference of genetic trait architecture using biologically annotated neural networks.

In this article, we present Biologically Annotated Neural Networks (BANNs), a nonlinear probabilistic framework for association mapping in genome-wide association (GWA) studies. BANNs are feedforward models with partially connected architectures that are based on biological annotations. This setup y...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Pinar Demetci, Wei Cheng, Gregory Darnell, Xiang Zhou, Sohini Ramachandran, Lorin Crawford
Formato:	article
Lenguaje:	EN
Publicado:	Public Library of Science (PLoS) 2021
Materias:	Genetics QH426-470
Acceso en línea:	https://doaj.org/article/66812a19d2fa491a9fd1faa01ef7dfef
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:66812a19d2fa491a9fd1faa01ef7dfef
record_format	dspace
spelling	oai:doaj.org-article:66812a19d2fa491a9fd1faa01ef7dfef2021-12-02T20:02:52ZMulti-scale inference of genetic trait architecture using biologically annotated neural networks.1553-73901553-740410.1371/journal.pgen.1009754https://doaj.org/article/66812a19d2fa491a9fd1faa01ef7dfef2021-08-01T00:00:00Zhttps://doi.org/10.1371/journal.pgen.1009754https://doaj.org/toc/1553-7390https://doaj.org/toc/1553-7404In this article, we present Biologically Annotated Neural Networks (BANNs), a nonlinear probabilistic framework for association mapping in genome-wide association (GWA) studies. BANNs are feedforward models with partially connected architectures that are based on biological annotations. This setup yields a fully interpretable neural network where the input layer encodes SNP-level effects, and the hidden layer models the aggregated effects among SNP-sets. We treat the weights and connections of the network as random variables with prior distributions that reflect how genetic effects manifest at different genomic scales. The BANNs software uses variational inference to provide posterior summaries which allow researchers to simultaneously perform (i) mapping with SNPs and (ii) enrichment analyses with SNP-sets on complex traits. Through simulations, we show that our method improves upon state-of-the-art association mapping and enrichment approaches across a wide range of genetic architectures. We then further illustrate the benefits of BANNs by analyzing real GWA data assayed in approximately 2,000 heterogenous stock of mice from the Wellcome Trust Centre for Human Genetics and approximately 7,000 individuals from the Framingham Heart Study. Lastly, using a random subset of individuals of European ancestry from the UK Biobank, we show that BANNs is able to replicate known associations in high and low-density lipoprotein cholesterol content.Pinar DemetciWei ChengGregory DarnellXiang ZhouSohini RamachandranLorin CrawfordPublic Library of Science (PLoS)articleGeneticsQH426-470ENPLoS Genetics, Vol 17, Iss 8, p e1009754 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Genetics QH426-470
spellingShingle	Genetics QH426-470 Pinar Demetci Wei Cheng Gregory Darnell Xiang Zhou Sohini Ramachandran Lorin Crawford Multi-scale inference of genetic trait architecture using biologically annotated neural networks.
description	In this article, we present Biologically Annotated Neural Networks (BANNs), a nonlinear probabilistic framework for association mapping in genome-wide association (GWA) studies. BANNs are feedforward models with partially connected architectures that are based on biological annotations. This setup yields a fully interpretable neural network where the input layer encodes SNP-level effects, and the hidden layer models the aggregated effects among SNP-sets. We treat the weights and connections of the network as random variables with prior distributions that reflect how genetic effects manifest at different genomic scales. The BANNs software uses variational inference to provide posterior summaries which allow researchers to simultaneously perform (i) mapping with SNPs and (ii) enrichment analyses with SNP-sets on complex traits. Through simulations, we show that our method improves upon state-of-the-art association mapping and enrichment approaches across a wide range of genetic architectures. We then further illustrate the benefits of BANNs by analyzing real GWA data assayed in approximately 2,000 heterogenous stock of mice from the Wellcome Trust Centre for Human Genetics and approximately 7,000 individuals from the Framingham Heart Study. Lastly, using a random subset of individuals of European ancestry from the UK Biobank, we show that BANNs is able to replicate known associations in high and low-density lipoprotein cholesterol content.
format	article
author	Pinar Demetci Wei Cheng Gregory Darnell Xiang Zhou Sohini Ramachandran Lorin Crawford
author_facet	Pinar Demetci Wei Cheng Gregory Darnell Xiang Zhou Sohini Ramachandran Lorin Crawford
author_sort	Pinar Demetci
title	Multi-scale inference of genetic trait architecture using biologically annotated neural networks.
title_short	Multi-scale inference of genetic trait architecture using biologically annotated neural networks.
title_full	Multi-scale inference of genetic trait architecture using biologically annotated neural networks.
title_fullStr	Multi-scale inference of genetic trait architecture using biologically annotated neural networks.
title_full_unstemmed	Multi-scale inference of genetic trait architecture using biologically annotated neural networks.
title_sort	multi-scale inference of genetic trait architecture using biologically annotated neural networks.
publisher	Public Library of Science (PLoS)
publishDate	2021
url	https://doaj.org/article/66812a19d2fa491a9fd1faa01ef7dfef
work_keys_str_mv	AT pinardemetci multiscaleinferenceofgenetictraitarchitectureusingbiologicallyannotatedneuralnetworks AT weicheng multiscaleinferenceofgenetictraitarchitectureusingbiologicallyannotatedneuralnetworks AT gregorydarnell multiscaleinferenceofgenetictraitarchitectureusingbiologicallyannotatedneuralnetworks AT xiangzhou multiscaleinferenceofgenetictraitarchitectureusingbiologicallyannotatedneuralnetworks AT sohiniramachandran multiscaleinferenceofgenetictraitarchitectureusingbiologicallyannotatedneuralnetworks AT lorincrawford multiscaleinferenceofgenetictraitarchitectureusingbiologicallyannotatedneuralnetworks
_version_	1718375664253403136

Multi-scale inference of genetic trait architecture using biologically annotated neural networks.

Ejemplares similares