Cargando…

Visualizing complex feature interactions and feature sharing in genomic deep neural networks

BACKGROUND: Visualization tools for deep learning models typically focus on discovering key input features without considering how such low level features are combined in intermediate layers to make decisions. Moreover, many of these methods examine a network’s response to specific input examples th...

Descripción completa

Detalles Bibliográficos
Autores principales: Liu, Ge, Zeng, Haoyang, Gifford, David K.
Formato: Online Artículo Texto
Lenguaje:English
Publicado: BioMed Central 2019
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6642501/
https://www.ncbi.nlm.nih.gov/pubmed/31324140
http://dx.doi.org/10.1186/s12859-019-2957-4
_version_ 1783436986582827008
author Liu, Ge
Zeng, Haoyang
Gifford, David K.
author_facet Liu, Ge
Zeng, Haoyang
Gifford, David K.
author_sort Liu, Ge
collection PubMed
description BACKGROUND: Visualization tools for deep learning models typically focus on discovering key input features without considering how such low level features are combined in intermediate layers to make decisions. Moreover, many of these methods examine a network’s response to specific input examples that may be insufficient to reveal the complexity of model decision making. RESULTS: We present DeepResolve, an analysis framework for deep convolutional models of genome function that visualizes how input features contribute individually and combinatorially to network decisions. Unlike other methods, DeepResolve does not depend upon the analysis of a predefined set of inputs. Rather, it uses gradient ascent to stochastically explore intermediate feature maps to 1) discover important features, 2) visualize their contribution and interaction patterns, and 3) analyze feature sharing across tasks that suggests shared biological mechanism. We demonstrate the visualization of decision making using our proposed method on deep neural networks trained on both experimental and synthetic data. DeepResolve is competitive with existing visualization tools in discovering key sequence features, and identifies certain negative features and non-additive feature interactions that are not easily observed with existing tools. It also recovers similarities between poorly correlated classes which are not observed by traditional methods. DeepResolve reveals that DeepSEA’s learned decision structure is shared across genome annotations including histone marks, DNase hypersensitivity, and transcription factor binding. We identify groups of TFs that suggest known shared biological mechanism, and recover correlation between DNA hypersensitivities and TF/Chromatin marks. CONCLUSIONS: DeepResolve is capable of visualizing complex feature contribution patterns and feature interactions that contribute to decision making in genomic deep convolutional networks. It also recovers feature sharing and class similarities which suggest interesting biological mechanisms. DeepResolve is compatible with existing visualization tools and provides complementary insights. ELECTRONIC SUPPLEMENTARY MATERIAL: The online version of this article (10.1186/s12859-019-2957-4) contains supplementary material, which is available to authorized users.
format Online
Article
Text
id pubmed-6642501
institution National Center for Biotechnology Information
language English
publishDate 2019
publisher BioMed Central
record_format MEDLINE/PubMed
spelling pubmed-66425012019-07-29 Visualizing complex feature interactions and feature sharing in genomic deep neural networks Liu, Ge Zeng, Haoyang Gifford, David K. BMC Bioinformatics Methodology Article BACKGROUND: Visualization tools for deep learning models typically focus on discovering key input features without considering how such low level features are combined in intermediate layers to make decisions. Moreover, many of these methods examine a network’s response to specific input examples that may be insufficient to reveal the complexity of model decision making. RESULTS: We present DeepResolve, an analysis framework for deep convolutional models of genome function that visualizes how input features contribute individually and combinatorially to network decisions. Unlike other methods, DeepResolve does not depend upon the analysis of a predefined set of inputs. Rather, it uses gradient ascent to stochastically explore intermediate feature maps to 1) discover important features, 2) visualize their contribution and interaction patterns, and 3) analyze feature sharing across tasks that suggests shared biological mechanism. We demonstrate the visualization of decision making using our proposed method on deep neural networks trained on both experimental and synthetic data. DeepResolve is competitive with existing visualization tools in discovering key sequence features, and identifies certain negative features and non-additive feature interactions that are not easily observed with existing tools. It also recovers similarities between poorly correlated classes which are not observed by traditional methods. DeepResolve reveals that DeepSEA’s learned decision structure is shared across genome annotations including histone marks, DNase hypersensitivity, and transcription factor binding. We identify groups of TFs that suggest known shared biological mechanism, and recover correlation between DNA hypersensitivities and TF/Chromatin marks. CONCLUSIONS: DeepResolve is capable of visualizing complex feature contribution patterns and feature interactions that contribute to decision making in genomic deep convolutional networks. It also recovers feature sharing and class similarities which suggest interesting biological mechanisms. DeepResolve is compatible with existing visualization tools and provides complementary insights. ELECTRONIC SUPPLEMENTARY MATERIAL: The online version of this article (10.1186/s12859-019-2957-4) contains supplementary material, which is available to authorized users. BioMed Central 2019-07-19 /pmc/articles/PMC6642501/ /pubmed/31324140 http://dx.doi.org/10.1186/s12859-019-2957-4 Text en © The Author(s) 2019 Open Access This article is distributed under the terms of the Creative Commons Attribution 4.0 International License (http://creativecommons.org/licenses/by/4.0/), which permits unrestricted use, distribution, and reproduction in any medium, provided 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 Creative Commons Public Domain Dedication waiver (http://creativecommons.org/publicdomain/zero/1.0/) applies to the data made available in this article, unless otherwise stated.
spellingShingle Methodology Article
Liu, Ge
Zeng, Haoyang
Gifford, David K.
Visualizing complex feature interactions and feature sharing in genomic deep neural networks
title Visualizing complex feature interactions and feature sharing in genomic deep neural networks
title_full Visualizing complex feature interactions and feature sharing in genomic deep neural networks
title_fullStr Visualizing complex feature interactions and feature sharing in genomic deep neural networks
title_full_unstemmed Visualizing complex feature interactions and feature sharing in genomic deep neural networks
title_short Visualizing complex feature interactions and feature sharing in genomic deep neural networks
title_sort visualizing complex feature interactions and feature sharing in genomic deep neural networks
topic Methodology Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6642501/
https://www.ncbi.nlm.nih.gov/pubmed/31324140
http://dx.doi.org/10.1186/s12859-019-2957-4
work_keys_str_mv AT liuge visualizingcomplexfeatureinteractionsandfeaturesharingingenomicdeepneuralnetworks
AT zenghaoyang visualizingcomplexfeatureinteractionsandfeaturesharingingenomicdeepneuralnetworks
AT gifforddavidk visualizingcomplexfeatureinteractionsandfeaturesharingingenomicdeepneuralnetworks