Identifying Protein-protein Interactions in Biomedical Literature using Recurrent Neural Networks with Long Short-Term Memory

Yu Lun Hsieh, Yung-Chun Chang, Nai Wen Chang, Wen Lian Hsu

研究成果: 書貢獻/報告類型會議貢獻

摘要

Accurate identification of protein-protein interaction (PPI) helps biomedical researchers to quickly capture crucial information in literatures. This work proposes a recurrent neural network (RNN) model to identify PPIs. Experiments on two largest public benchmark datasets, AIMed and BioInfer, demonstrate that RNN outperforms state-of-the-art methods with relative improvements of 10% and 18%, respectively. Cross-corpus evaluation also indicates that RNN is robust even when trained on data from different domains. These results suggest that RNN effectively captures semantic relationships among proteins without any feature engineering.
原文英語
主出版物標題Proceedings of the Eighth International Joint Conference on Natural Language Processing
發行者Asian Federation of Natural Language Processing
頁面240-245
出版狀態已發佈 - 2017

指紋

Recurrent neural networks
Proteins
Semantics
Long short-term memory
Experiments

引用此文

Hsieh, Y. L., Chang, Y-C., Chang, N. W., & Hsu, W. L. (2017). Identifying Protein-protein Interactions in Biomedical Literature using Recurrent Neural Networks with Long Short-Term Memory. 於 Proceedings of the Eighth International Joint Conference on Natural Language Processing (頁 240-245). Asian Federation of Natural Language Processing.

Identifying Protein-protein Interactions in Biomedical Literature using Recurrent Neural Networks with Long Short-Term Memory. / Hsieh, Yu Lun; Chang, Yung-Chun; Chang, Nai Wen; Hsu, Wen Lian.

Proceedings of the Eighth International Joint Conference on Natural Language Processing. Asian Federation of Natural Language Processing, 2017. p. 240-245.

研究成果: 書貢獻/報告類型會議貢獻

Hsieh, YL, Chang, Y-C, Chang, NW & Hsu, WL 2017, Identifying Protein-protein Interactions in Biomedical Literature using Recurrent Neural Networks with Long Short-Term Memory. 於 Proceedings of the Eighth International Joint Conference on Natural Language Processing. Asian Federation of Natural Language Processing, 頁 240-245.
Hsieh YL, Chang Y-C, Chang NW, Hsu WL. Identifying Protein-protein Interactions in Biomedical Literature using Recurrent Neural Networks with Long Short-Term Memory. 於 Proceedings of the Eighth International Joint Conference on Natural Language Processing. Asian Federation of Natural Language Processing. 2017. p. 240-245
Hsieh, Yu Lun ; Chang, Yung-Chun ; Chang, Nai Wen ; Hsu, Wen Lian. / Identifying Protein-protein Interactions in Biomedical Literature using Recurrent Neural Networks with Long Short-Term Memory. Proceedings of the Eighth International Joint Conference on Natural Language Processing. Asian Federation of Natural Language Processing, 2017. 頁 240-245
@inproceedings{53fccaf77c5e4d9e99057496e1f880fe,
title = "Identifying Protein-protein Interactions in Biomedical Literature using Recurrent Neural Networks with Long Short-Term Memory",
abstract = "Accurate identification of protein-protein interaction (PPI) helps biomedical researchers to quickly capture crucial information in literatures. This work proposes a recurrent neural network (RNN) model to identify PPIs. Experiments on two largest public benchmark datasets, AIMed and BioInfer, demonstrate that RNN outperforms state-of-the-art methods with relative improvements of 10{\%} and 18{\%}, respectively. Cross-corpus evaluation also indicates that RNN is robust even when trained on data from different domains. These results suggest that RNN effectively captures semantic relationships among proteins without any feature engineering.",
author = "Hsieh, {Yu Lun} and Yung-Chun Chang and Chang, {Nai Wen} and Hsu, {Wen Lian}",
year = "2017",
language = "English",
pages = "240--245",
booktitle = "Proceedings of the Eighth International Joint Conference on Natural Language Processing",
publisher = "Asian Federation of Natural Language Processing",

}

TY - GEN

T1 - Identifying Protein-protein Interactions in Biomedical Literature using Recurrent Neural Networks with Long Short-Term Memory

AU - Hsieh, Yu Lun

AU - Chang, Yung-Chun

AU - Chang, Nai Wen

AU - Hsu, Wen Lian

PY - 2017

Y1 - 2017

N2 - Accurate identification of protein-protein interaction (PPI) helps biomedical researchers to quickly capture crucial information in literatures. This work proposes a recurrent neural network (RNN) model to identify PPIs. Experiments on two largest public benchmark datasets, AIMed and BioInfer, demonstrate that RNN outperforms state-of-the-art methods with relative improvements of 10% and 18%, respectively. Cross-corpus evaluation also indicates that RNN is robust even when trained on data from different domains. These results suggest that RNN effectively captures semantic relationships among proteins without any feature engineering.

AB - Accurate identification of protein-protein interaction (PPI) helps biomedical researchers to quickly capture crucial information in literatures. This work proposes a recurrent neural network (RNN) model to identify PPIs. Experiments on two largest public benchmark datasets, AIMed and BioInfer, demonstrate that RNN outperforms state-of-the-art methods with relative improvements of 10% and 18%, respectively. Cross-corpus evaluation also indicates that RNN is robust even when trained on data from different domains. These results suggest that RNN effectively captures semantic relationships among proteins without any feature engineering.

UR - https://aclanthology.coli.uni-saarland.de/papers/I17-2041/i17-2041

UR - http://ijcnlp2017.org/site/page.aspx?pid=172&sid=1133&lang=en

M3 - Conference contribution

SP - 240

EP - 245

BT - Proceedings of the Eighth International Joint Conference on Natural Language Processing

PB - Asian Federation of Natural Language Processing

ER -