Effect of sequence padding on the performance of deep learning models in archaeal protein functional prediction

The use of raw amino acid sequences as input for deep learning models for protein functional prediction has gained popularity in recent years. This scheme obliges to manage proteins with different lengths, while deep learning models require same-shape input. To accomplish this, zeros are usually add...

Full description

Bibliographic Details
Authors: Lopez-Del Rio A, Martin M, Perera-Lluna A, Saidi R
Format: article
Status:Published version
Publication Date:2020
Country:España
Institution:Fundació Sant Joan de Déu
Repository:r-FSJD. Repositorio Institucional de Producción Científica de la Fundació Sant Joan de Déu
OAI Identifier:oai:fsjd.fundanetsuite.com:p19273
Online Access:https://fsjd.fundanetsuite.com/Publicaciones/ProdCientif/PublicacionFrw.aspx?id=19273
Access Level:Open access
id ES_aa76bb2c89cacd44643b4cea54aebcdf
oai_identifier_str oai:fsjd.fundanetsuite.com:p19273
network_acronym_str ES
network_name_str España
repository_id_str
spelling Effect of sequence padding on the performance of deep learning models in archaeal protein functional predictionLopez-Del Rio AMartin MPerera-Lluna ASaidi RThe use of raw amino acid sequences as input for deep learning models for protein functional prediction has gained popularity in recent years. This scheme obliges to manage proteins with different lengths, while deep learning models require same-shape input. To accomplish this, zeros are usually added to each sequence up to a established common length in a process called zero-padding. However, the effect of different padding strategies on model performance and data structure is yet unknown. We propose and implement four novel types of padding the amino acid sequences. Then, we analysed the impact of different ways of padding the amino acid sequences in a hierarchical Enzyme Commission number prediction problem. Results show that padding has an effect on model performance even when there are convolutional layers implied. Contrastingly to most of deep learning works which focus mainly on architectures, this study highlights the relevance of the deemed-of-low-importance process of padding and raises awareness of the need to refine it for better performance. The code of this analysis is publicly available at https://github.com/b2slab/padding_benchmark.NATURE PORTFOLIO2020info:eu-repo/semantics/articleinfo:eu-repo/semantics/publishedVersionhttps://fsjd.fundanetsuite.com/Publicaciones/ProdCientif/PublicacionFrw.aspx?id=19273Scientific ReportsISSN: 20452322reponame:r-FSJD. Repositorio Institucional de Producción Científica de la Fundació Sant Joan de Déuinstname:Fundació Sant Joan de DéuInglésinfo:eu-repo/semantics/openAccessoai:fsjd.fundanetsuite.com:p192732026-05-27T12:37:41Z
dc.title.none.fl_str_mv Effect of sequence padding on the performance of deep learning models in archaeal protein functional prediction
title Effect of sequence padding on the performance of deep learning models in archaeal protein functional prediction
spellingShingle Effect of sequence padding on the performance of deep learning models in archaeal protein functional prediction
Lopez-Del Rio A
title_short Effect of sequence padding on the performance of deep learning models in archaeal protein functional prediction
title_full Effect of sequence padding on the performance of deep learning models in archaeal protein functional prediction
title_fullStr Effect of sequence padding on the performance of deep learning models in archaeal protein functional prediction
title_full_unstemmed Effect of sequence padding on the performance of deep learning models in archaeal protein functional prediction
title_sort Effect of sequence padding on the performance of deep learning models in archaeal protein functional prediction
dc.creator.none.fl_str_mv Lopez-Del Rio A
Martin M
Perera-Lluna A
Saidi R
author Lopez-Del Rio A
author_facet Lopez-Del Rio A
Martin M
Perera-Lluna A
Saidi R
author_role author
author2 Martin M
Perera-Lluna A
Saidi R
author2_role author
author
author
description The use of raw amino acid sequences as input for deep learning models for protein functional prediction has gained popularity in recent years. This scheme obliges to manage proteins with different lengths, while deep learning models require same-shape input. To accomplish this, zeros are usually added to each sequence up to a established common length in a process called zero-padding. However, the effect of different padding strategies on model performance and data structure is yet unknown. We propose and implement four novel types of padding the amino acid sequences. Then, we analysed the impact of different ways of padding the amino acid sequences in a hierarchical Enzyme Commission number prediction problem. Results show that padding has an effect on model performance even when there are convolutional layers implied. Contrastingly to most of deep learning works which focus mainly on architectures, this study highlights the relevance of the deemed-of-low-importance process of padding and raises awareness of the need to refine it for better performance. The code of this analysis is publicly available at https://github.com/b2slab/padding_benchmark.
publishDate 2020
dc.date.none.fl_str_mv 2020
dc.type.none.fl_str_mv info:eu-repo/semantics/article
info:eu-repo/semantics/publishedVersion
format article
status_str publishedVersion
dc.identifier.none.fl_str_mv https://fsjd.fundanetsuite.com/Publicaciones/ProdCientif/PublicacionFrw.aspx?id=19273
url https://fsjd.fundanetsuite.com/Publicaciones/ProdCientif/PublicacionFrw.aspx?id=19273
dc.language.none.fl_str_mv Inglés
language_invalid_str_mv Inglés
dc.rights.none.fl_str_mv info:eu-repo/semantics/openAccess
eu_rights_str_mv openAccess
dc.publisher.none.fl_str_mv NATURE PORTFOLIO
publisher.none.fl_str_mv NATURE PORTFOLIO
dc.source.none.fl_str_mv Scientific Reports
ISSN: 20452322
reponame:r-FSJD. Repositorio Institucional de Producción Científica de la Fundació Sant Joan de Déu
instname:Fundació Sant Joan de Déu
instname_str Fundació Sant Joan de Déu
reponame_str r-FSJD. Repositorio Institucional de Producción Científica de la Fundació Sant Joan de Déu
collection r-FSJD. Repositorio Institucional de Producción Científica de la Fundació Sant Joan de Déu
repository.name.fl_str_mv
repository.mail.fl_str_mv
_version_ 1869416184025186304
score 15,811543

Similar Items