Constructing yeast genetic interaction network using biomedical literature and logistic regression

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

2 Scopus citations

Abstract

Various computational algorithms have been developed for constructing the genetic networks and by using text mining. The rapid growth in the biomedical literature, however, still encourages the importance of improving these algorithms for a better understanding of the protein/gene biochemical interactions. This paper proposes a text mining system that constructs a gene-gene-interaction network for the yeast genome by identifying the co-occurrence frequency of the genes in the biomedical text. The system determines connected genes based on their appearance in several levels of the text (i.e. abstract and sentence). This paper highlights the importance of recognizing the sparsity of biomedical data when designing a text mining prediction system. It does so by employing a rare event classification model that reflects the population using small samples of data. The results show that this method has the potential of improving the prediction accuracy for gene-gene-interactions.

Original languageBritish English
Title of host publication2017 International Conference on Electrical and Computing Technologies and Applications, ICECTA 2017
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages1-5
Number of pages5
ISBN (Electronic)9781538608722
DOIs
StatePublished - 28 Jun 2017
Event2017 International Conference on Electrical and Computing Technologies and Applications, ICECTA 2017 - Ras Al Khaimah, United Arab Emirates
Duration: 21 Nov 201723 Nov 2017

Publication series

Name2017 International Conference on Electrical and Computing Technologies and Applications, ICECTA 2017
Volume2018-January

Conference

Conference2017 International Conference on Electrical and Computing Technologies and Applications, ICECTA 2017
Country/TerritoryUnited Arab Emirates
CityRas Al Khaimah
Period21/11/1723/11/17

Keywords

  • biological NLP
  • biomedical literature
  • gene-gene-interaction
  • information extraction
  • Text mining

Fingerprint

Dive into the research topics of 'Constructing yeast genetic interaction network using biomedical literature and logistic regression'. Together they form a unique fingerprint.

Cite this