Triage of documents containing protein interactions affected by mutations using an NLP based machine learning approach

BMC Genomics

Jian Wang¹  Zhe He²  Tingting Zhao³  Jinfeng Zhang⁴  Jinchan Qu⁴  Jie Hao⁴  Dongrui Zhong⁴  Albert Steppi⁵  Pei-Yau Lung⁶ 

[1] CloudMedx, 94301, Palo Alto, CA, USA;College of Communication and Information, Florida State University, 32306, Tallahassee, FL, USA;Department of Geography, Florida State University, 32306, Tallahassee, FL, USA;Department of Statistics, Florida State University, 32306, Tallahassee, FL, USA;Laboratory of Systems Pharmacology at Harvard Medical School, 02115, Boston, MA, USA;Verisk – Insurance Solutions, 06457, Middletown, CT, USA;

关键词: Protein-protein interactions;    Mutations;    Text mining;    Biomedical literature retrieval;    Protein interactions affected by mutations;   

DOI  :  10.1186/s12864-020-07185-7

来源: Springer

【 摘 要 】

BackgroundInformation on protein-protein interactions affected by mutations is very useful for understanding the biological effect of mutations and for developing treatments targeting the interactions. In this study, we developed a natural language processing (NLP) based machine learning approach for extracting such information from literature. Our aim is to identify journal abstracts or paragraphs in full-text articles that contain at least one occurrence of a protein-protein interaction (PPI) affected by a mutation.ResultsOur system makes use of latest NLP methods with a large number of engineered features including some based on pre-trained word embedding. Our final model achieved satisfactory performance in the Document Triage Task of the BioCreative VI Precision Medicine Track with highest recall and comparable F1-score.ConclusionsThe performance of our method indicates that it is ideally suited for being combined with manual annotations. Our machine learning framework and engineered features will also be very helpful for other researchers to further improve this and other related biological text mining tasks using either traditional machine learning or deep learning based methods.

【 授权许可】

CC BY