Feature Extraction Using a Mutually-Competitive Autoencoder for Protein Function Prediction

Lester James Miranda, Takayuki Furuzuki

研究成果: Conference contribution

抄録

Learning new representations from data has been effective in predicting protein functions. However, common techniques tend to extract features irrelevant to the classification task. We propose an autoencoder network that selectively extracts features to produce meaningful representations. By increasing the activation of neurons kept by a winner-take-all operation, hidden units compete to form a subset that encodes relevant features, a process dubbed as mutual competition. We test this method on protein benchmarks, evaluating feature score distribution and classification performance. Results show that the autoencoder extracted features relevant to the classification task, and significantly outperformed other techniques in literature based on non-parameteric statistical tests. This demonstrates that adding competition between neurons encodes meaningful features, further improving the prediction of protein functions.

元の言語English
ホスト出版物のタイトルProceedings - 2018 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2018
出版者Institute of Electrical and Electronics Engineers Inc.
ページ1337-1342
ページ数6
ISBN(電子版)9781538666500
DOI
出版物ステータスPublished - 2019 1 16
イベント2018 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2018 - Miyazaki, Japan
継続期間: 2018 10 72018 10 10

出版物シリーズ

名前Proceedings - 2018 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2018

Conference

Conference2018 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2018
Japan
Miyazaki
期間18/10/718/10/10

Fingerprint

Feature extraction
Proteins
Neurons
Benchmarking
Statistical tests
Chemical activation
Learning
Prediction
Protein
Neuron
Activation
Benchmark
Test methods
Winner-take-all

ASJC Scopus subject areas

  • Information Systems
  • Information Systems and Management
  • Health Informatics
  • Artificial Intelligence
  • Computer Networks and Communications
  • Human-Computer Interaction

これを引用

Miranda, L. J., & Furuzuki, T. (2019). Feature Extraction Using a Mutually-Competitive Autoencoder for Protein Function Prediction. : Proceedings - 2018 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2018 (pp. 1337-1342). [8616230] (Proceedings - 2018 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2018). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/SMC.2018.00234

Feature Extraction Using a Mutually-Competitive Autoencoder for Protein Function Prediction. / Miranda, Lester James; Furuzuki, Takayuki.

Proceedings - 2018 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2018. Institute of Electrical and Electronics Engineers Inc., 2019. p. 1337-1342 8616230 (Proceedings - 2018 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2018).

研究成果: Conference contribution

Miranda, LJ & Furuzuki, T 2019, Feature Extraction Using a Mutually-Competitive Autoencoder for Protein Function Prediction. : Proceedings - 2018 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2018., 8616230, Proceedings - 2018 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2018, Institute of Electrical and Electronics Engineers Inc., pp. 1337-1342, 2018 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2018, Miyazaki, Japan, 18/10/7. https://doi.org/10.1109/SMC.2018.00234
Miranda LJ, Furuzuki T. Feature Extraction Using a Mutually-Competitive Autoencoder for Protein Function Prediction. : Proceedings - 2018 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2018. Institute of Electrical and Electronics Engineers Inc. 2019. p. 1337-1342. 8616230. (Proceedings - 2018 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2018). https://doi.org/10.1109/SMC.2018.00234
Miranda, Lester James ; Furuzuki, Takayuki. / Feature Extraction Using a Mutually-Competitive Autoencoder for Protein Function Prediction. Proceedings - 2018 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2018. Institute of Electrical and Electronics Engineers Inc., 2019. pp. 1337-1342 (Proceedings - 2018 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2018).
@inproceedings{ed8110ff91f747519cfc889734d6f371,
title = "Feature Extraction Using a Mutually-Competitive Autoencoder for Protein Function Prediction",
abstract = "Learning new representations from data has been effective in predicting protein functions. However, common techniques tend to extract features irrelevant to the classification task. We propose an autoencoder network that selectively extracts features to produce meaningful representations. By increasing the activation of neurons kept by a winner-take-all operation, hidden units compete to form a subset that encodes relevant features, a process dubbed as mutual competition. We test this method on protein benchmarks, evaluating feature score distribution and classification performance. Results show that the autoencoder extracted features relevant to the classification task, and significantly outperformed other techniques in literature based on non-parameteric statistical tests. This demonstrates that adding competition between neurons encodes meaningful features, further improving the prediction of protein functions.",
keywords = "autoencoder, bioinformatics, machine learning, neural networks",
author = "Miranda, {Lester James} and Takayuki Furuzuki",
year = "2019",
month = "1",
day = "16",
doi = "10.1109/SMC.2018.00234",
language = "English",
series = "Proceedings - 2018 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2018",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "1337--1342",
booktitle = "Proceedings - 2018 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2018",

}

TY - GEN

T1 - Feature Extraction Using a Mutually-Competitive Autoencoder for Protein Function Prediction

AU - Miranda, Lester James

AU - Furuzuki, Takayuki

PY - 2019/1/16

Y1 - 2019/1/16

N2 - Learning new representations from data has been effective in predicting protein functions. However, common techniques tend to extract features irrelevant to the classification task. We propose an autoencoder network that selectively extracts features to produce meaningful representations. By increasing the activation of neurons kept by a winner-take-all operation, hidden units compete to form a subset that encodes relevant features, a process dubbed as mutual competition. We test this method on protein benchmarks, evaluating feature score distribution and classification performance. Results show that the autoencoder extracted features relevant to the classification task, and significantly outperformed other techniques in literature based on non-parameteric statistical tests. This demonstrates that adding competition between neurons encodes meaningful features, further improving the prediction of protein functions.

AB - Learning new representations from data has been effective in predicting protein functions. However, common techniques tend to extract features irrelevant to the classification task. We propose an autoencoder network that selectively extracts features to produce meaningful representations. By increasing the activation of neurons kept by a winner-take-all operation, hidden units compete to form a subset that encodes relevant features, a process dubbed as mutual competition. We test this method on protein benchmarks, evaluating feature score distribution and classification performance. Results show that the autoencoder extracted features relevant to the classification task, and significantly outperformed other techniques in literature based on non-parameteric statistical tests. This demonstrates that adding competition between neurons encodes meaningful features, further improving the prediction of protein functions.

KW - autoencoder

KW - bioinformatics

KW - machine learning

KW - neural networks

UR - http://www.scopus.com/inward/record.url?scp=85062236544&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85062236544&partnerID=8YFLogxK

U2 - 10.1109/SMC.2018.00234

DO - 10.1109/SMC.2018.00234

M3 - Conference contribution

AN - SCOPUS:85062236544

T3 - Proceedings - 2018 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2018

SP - 1337

EP - 1342

BT - Proceedings - 2018 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2018

PB - Institute of Electrical and Electronics Engineers Inc.

ER -