EPICURE :Ensemble pretrained models for extracting cancer mutations from literature
Cao, J. R. van Veen, E. M. Peek, N. Renehan, Andrew G Ananiadou, S.
Cao, J. R.
van Veen, E. M.
Peek, N.
Renehan, Andrew G
Ananiadou, S.
Citations
Altmetric:
Abstract
Abstract—To interpret the genetic profile present in a patient
sample, it is necessary to know which mutations have important
roles in the development of the corresponding cancer type. Named
entity recognition (NER) is a core step in the text mining pipeline
which facilitates mining valuable cancer information from the
scientific literature. However, due to the scarcity of related
datasets, previous NER attempts in this domain either suffer from
low performance when deep learning based models are deployed,
or they apply feature-based machine learning models or rule based models to tackle this problem, which requires intensive
efforts from domain experts, and limit the model generalization
capability. In this paper, we propose EPICURE, an ensemble pre trained model equipped with a conditional random field pattern
(CRF) layer and a span prediction pattern (Span) layer to extract
cancer mutations from text. We also adopt a data augmentation
strategy to expand our training set from multiple datasets. Ex perimental results on three benchmark datasets show competitive
results compared to the baseline models, validating our model’s
effectiveness and advances in generalization capability.
Description
Date
2021
Publisher
Collections
Keywords
Type
Article
Citation
Cao JR, van Veen EM, Peek N, Renehan AG, Ananiadou S. EPICURE :Ensemble Pretrained Models for Extracting Cancer Mutations from Literature. 2021 Ieee 34th International Symposium on Computer-Based Medical Systems (Cbms). 2021:461-7. PubMed PMID: WOS:000847341000079.