Sequence-based prediction of protein protein interaction using a deep-learning algorithm
Abstract Background Protein-protein interactions (PPIs) are critical for many biological processes. It is therefore important to develop accurate high-throughput methods for identifying PPI to better understand protein function, disease occurrence, and therapy design. Though various computational me...
Main Authors: | , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
BMC
2017-05-01
|
Series: | BMC Bioinformatics |
Subjects: | |
Online Access: | http://link.springer.com/article/10.1186/s12859-017-1700-2 |
id |
doaj-293de1787b034876bd0de98d6c131b1c |
---|---|
record_format |
Article |
spelling |
doaj-293de1787b034876bd0de98d6c131b1c2020-11-25T00:26:20ZengBMCBMC Bioinformatics1471-21052017-05-011811810.1186/s12859-017-1700-2Sequence-based prediction of protein protein interaction using a deep-learning algorithmTanlin Sun0Bo Zhou1Luhua Lai2Jianfeng Pei3Center for Quantitative Biology, Academy for Advanced Interdisciplinary Studies, Peking UniversityCenter for Quantitative Biology, Academy for Advanced Interdisciplinary Studies, Peking UniversityCenter for Quantitative Biology, Academy for Advanced Interdisciplinary Studies, Peking UniversityCenter for Quantitative Biology, Academy for Advanced Interdisciplinary Studies, Peking UniversityAbstract Background Protein-protein interactions (PPIs) are critical for many biological processes. It is therefore important to develop accurate high-throughput methods for identifying PPI to better understand protein function, disease occurrence, and therapy design. Though various computational methods for predicting PPI have been developed, their robustness for prediction with external datasets is unknown. Deep-learning algorithms have achieved successful results in diverse areas, but their effectiveness for PPI prediction has not been tested. Results We used a stacked autoencoder, a type of deep-learning algorithm, to study the sequence-based PPI prediction. The best model achieved an average accuracy of 97.19% with 10-fold cross-validation. The prediction accuracies for various external datasets ranged from 87.99% to 99.21%, which are superior to those achieved with previous methods. Conclusions To our knowledge, this research is the first to apply a deep-learning algorithm to sequence-based PPI prediction, and the results demonstrate its potential in this field.http://link.springer.com/article/10.1186/s12859-017-1700-2Deep learningProtein-protein interaction |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Tanlin Sun Bo Zhou Luhua Lai Jianfeng Pei |
spellingShingle |
Tanlin Sun Bo Zhou Luhua Lai Jianfeng Pei Sequence-based prediction of protein protein interaction using a deep-learning algorithm BMC Bioinformatics Deep learning Protein-protein interaction |
author_facet |
Tanlin Sun Bo Zhou Luhua Lai Jianfeng Pei |
author_sort |
Tanlin Sun |
title |
Sequence-based prediction of protein protein interaction using a deep-learning algorithm |
title_short |
Sequence-based prediction of protein protein interaction using a deep-learning algorithm |
title_full |
Sequence-based prediction of protein protein interaction using a deep-learning algorithm |
title_fullStr |
Sequence-based prediction of protein protein interaction using a deep-learning algorithm |
title_full_unstemmed |
Sequence-based prediction of protein protein interaction using a deep-learning algorithm |
title_sort |
sequence-based prediction of protein protein interaction using a deep-learning algorithm |
publisher |
BMC |
series |
BMC Bioinformatics |
issn |
1471-2105 |
publishDate |
2017-05-01 |
description |
Abstract Background Protein-protein interactions (PPIs) are critical for many biological processes. It is therefore important to develop accurate high-throughput methods for identifying PPI to better understand protein function, disease occurrence, and therapy design. Though various computational methods for predicting PPI have been developed, their robustness for prediction with external datasets is unknown. Deep-learning algorithms have achieved successful results in diverse areas, but their effectiveness for PPI prediction has not been tested. Results We used a stacked autoencoder, a type of deep-learning algorithm, to study the sequence-based PPI prediction. The best model achieved an average accuracy of 97.19% with 10-fold cross-validation. The prediction accuracies for various external datasets ranged from 87.99% to 99.21%, which are superior to those achieved with previous methods. Conclusions To our knowledge, this research is the first to apply a deep-learning algorithm to sequence-based PPI prediction, and the results demonstrate its potential in this field. |
topic |
Deep learning Protein-protein interaction |
url |
http://link.springer.com/article/10.1186/s12859-017-1700-2 |
work_keys_str_mv |
AT tanlinsun sequencebasedpredictionofproteinproteininteractionusingadeeplearningalgorithm AT bozhou sequencebasedpredictionofproteinproteininteractionusingadeeplearningalgorithm AT luhualai sequencebasedpredictionofproteinproteininteractionusingadeeplearningalgorithm AT jianfengpei sequencebasedpredictionofproteinproteininteractionusingadeeplearningalgorithm |
_version_ |
1725344622564081664 |