Literature DB >> 29590309

Generalizing biomedical relation classification with neural adversarial domain adaptation.

Anthony Rios1,2, Ramakanth Kavuluru2,3, Zhiyong Lu1.   

Abstract

Motivation: Creating large datasets for biomedical relation classification can be prohibitively expensive. While some datasets have been curated to extract protein-protein and drug-drug interactions (PPIs and DDIs) from text, we are also interested in other interactions including gene-disease and chemical-protein connections. Also, many biomedical researchers have begun to explore ternary relationships. Even when annotated data are available, many datasets used for relation classification are inherently biased. For example, issues such as sample selection bias typically prevent models from generalizing in the wild. To address the problem of cross-corpora generalization, we present a novel adversarial learning algorithm for unsupervised domain adaptation tasks where no labeled data are available in the target domain. Instead, our method takes advantage of unlabeled data to improve biased classifiers through learning domain-invariant features via an adversarial process. Finally, our method is built upon recent advances in neural network (NN) methods.
Results: We experiment by extracting PPIs and DDIs from text. In our experiments, we show domain invariant features can be learned in NNs such that classifiers trained for one interaction type (protein-protein) can be re-purposed to others (drug-drug). We also show that our method can adapt to different source and target pairs of PPI datasets. Compared to prior convolutional and recurrent NN-based relation classification methods without domain adaptation, we achieve improvements as high as 30% in F1-score. Likewise, we show improvements over state-of-the-art adversarial methods. Availability and implementation: Experimental code is available at https://github.com/bionlproc/adversarial-relation-classification. Supplementary information: Supplementary data are available at Bioinformatics online.

Mesh:

Substances:

Year:  2018        PMID: 29590309      PMCID: PMC6129312          DOI: 10.1093/bioinformatics/bty190

Source DB:  PubMed          Journal:  Bioinformatics        ISSN: 1367-4803            Impact factor:   6.937


  14 in total

1.  Learning to forget: continual prediction with LSTM.

Authors:  F A Gers; J Schmidhuber; F Cummins
Journal:  Neural Comput       Date:  2000-10       Impact factor: 2.026

2.  Lessons learnt from the DDIExtraction-2013 Shared Task.

Authors:  Isabel Segura-Bedmar; Paloma Martínez; María Herrero-Zazo
Journal:  J Biomed Inform       Date:  2014-05-21       Impact factor: 6.317

3.  Extracting Drug-Drug Interactions with Word and Character-Level Recurrent Neural Networks.

Authors:  Ramakanth Kavuluru; Anthony Rios; Tung Tran
Journal:  IEEE Int Conf Healthc Inform       Date:  2017-09-14

Review 4.  Tackling the widespread and critical impact of batch effects in high-throughput data.

Authors:  Jeffrey T Leek; Robert B Scharpf; Héctor Corrada Bravo; David Simcha; Benjamin Langmead; W Evan Johnson; Donald Geman; Keith Baggerly; Rafael A Irizarry
Journal:  Nat Rev Genet       Date:  2010-09-14       Impact factor: 53.242

5.  Toward a complete dataset of drug-drug interaction information from publicly available sources.

Authors:  Serkan Ayvaz; John Horn; Oktie Hassanzadeh; Qian Zhu; Johann Stan; Nicholas P Tatonetti; Santiago Vilar; Mathias Brochhausen; Matthias Samwald; Majid Rastegar-Mojarad; Michel Dumontier; Richard D Boyce
Journal:  J Biomed Inform       Date:  2015-04-24       Impact factor: 6.317

6.  Open source tool for prediction of genome wide protein-protein interaction network based on ortholog information.

Authors:  Chandra Sekhar Pedamallu; Janos Posfai
Journal:  Source Code Biol Med       Date:  2010-08-04

7.  Removal of batch effects using distribution-matching residual networks.

Authors:  Uri Shaham; Kelly P Stanton; Jun Zhao; Huamin Li; Khadir Raddassi; Ruth Montgomery; Yuval Kluger
Journal:  Bioinformatics       Date:  2017-08-15       Impact factor: 6.937

8.  BioInfer: a corpus for information extraction in the biomedical domain.

Authors:  Sampo Pyysalo; Filip Ginter; Juho Heimonen; Jari Björne; Jorma Boberg; Jouni Järvinen; Tapio Salakoski
Journal:  BMC Bioinformatics       Date:  2007-02-09       Impact factor: 3.169

9.  Text Mining Genotype-Phenotype Relationships from Biomedical Literature for Database Curation and Precision Medicine.

Authors:  Ayush Singhal; Michael Simmons; Zhiyong Lu
Journal:  PLoS Comput Biol       Date:  2016-11-30       Impact factor: 4.475

10.  Drug drug interaction extraction from biomedical literature using syntax convolutional neural network.

Authors:  Zhehuan Zhao; Zhihao Yang; Ling Luo; Hongfei Lin; Jian Wang
Journal:  Bioinformatics       Date:  2016-07-27       Impact factor: 6.937

View more
  8 in total

1.  Chemical-protein interaction extraction via contextualized word representations and multihead attention.

Authors:  Yijia Zhang; Hongfei Lin; Zhihao Yang; Jian Wang; Yuanyuan Sun
Journal:  Database (Oxford)       Date:  2019-01-01       Impact factor: 3.451

2.  Cross-registry neural domain adaptation to extract mutational test results from pathology reports.

Authors:  Anthony Rios; Eric B Durbin; Isaac Hands; Susanne M Arnold; Darshil Shah; Stephen M Schwartz; Bernardo H L Goulart; Ramakanth Kavuluru
Journal:  J Biomed Inform       Date:  2019-08-08       Impact factor: 6.317

3.  Exploring semi-supervised variational autoencoders for biomedical relation extraction.

Authors:  Yijia Zhang; Zhiyong Lu
Journal:  Methods       Date:  2019-02-27       Impact factor: 3.608

4.  An investigation of single-domain and multidomain medication and adverse drug event relation extraction from electronic health record notes using advanced deep learning models.

Authors:  Fei Li; Hong Yu
Journal:  J Am Med Inform Assoc       Date:  2019-07-01       Impact factor: 4.497

5.  CoCoScore: context-aware co-occurrence scoring for text mining applications using distant supervision.

Authors:  Alexander Junge; Lars Juhl Jensen
Journal:  Bioinformatics       Date:  2020-01-01       Impact factor: 6.937

6.  Inferring RNA-binding protein target preferences using adversarial domain adaptation.

Authors:  Ying Liu; Ruihui Li; Jiawei Luo; Zhaolei Zhang
Journal:  PLoS Comput Biol       Date:  2022-02-24       Impact factor: 4.475

7.  BioADAPT-MRC: Adversarial Learning-based Domain Adaptation Improves Biomedical Machine Reading Comprehension Task.

Authors:  Maria Mahbub; Sudarshan Srinivasan; Edmon Begoli; Gregory D Peterson
Journal:  Bioinformatics       Date:  2022-07-25       Impact factor: 6.931

8.  Broad-coverage biomedical relation extraction with SemRep.

Authors:  Halil Kilicoglu; Graciela Rosemblat; Marcelo Fiszman; Dongwook Shin
Journal:  BMC Bioinformatics       Date:  2020-05-14       Impact factor: 3.169

  8 in total

北京卡尤迪生物科技股份有限公司 © 2022-2023.