Mutation extraction tools can be combined for robust recognition of genetic variants in the literature

Abstract

As the cost of genomic sequencing continues to fall, the amount of data being collected and studied for the purpose of understanding the genetic basis of disease is increasing dramatically. Much of the source information relevant to such efforts is available only from unstructured sources such as the scientific literature, and significant resources are expended in manually curating and structuring the information in the literature. As such, there have been a number of systems developed to target automatic extraction of mutations and other genetic variation from the literature using text mining tools. We have performed a broad survey of the existing publicly available tools for extraction of genetic variants from the scientific literature. We consider not just one tool but a number of different tools, individually and in combination, and apply the tools in two scenarios. First, they are compared in an intrinsic evaluation context, where the tools are tested for their ability to identify specific mentions of genetic variants in a corpus of manually annotated papers, the Variome corpus. Second, they are compared in an extrinsic evaluation context based on our previous study of text mining support for curation of the COSMIC and InSiGHT databases. Our results demonstrate that no single tool covers the full range of genetic variants mentioned in the literature. Rather, several tools have complementary coverage and can be used together effectively. In the intrinsic evaluation on the Variome corpus, the combined performance is above 0.95 in F-measure, while in the extrinsic evaluation the combined recall performance is above 0.71 for COSMIC and above 0.62 for InSiGHT, a substantial improvement over the performance of any individual tool. Based on the analysis of these results, we suggest several directions for the improvement of text mining tools for genetic variant extraction from the literature.

Associating disease-related genetic variants in intergenic regions to the genes they impact

“…This nomenclature in principle provides a technique for straightforward identification of intergenic regions, by looking for genomic variants and cross-referencing their positions with the gene starts/stops in the reference sequences. However, our prior experience with text mining of genetic variants ( Jimeno Yepes & Verspoor, 2014b ) suggests that these descriptors are extremely rarely used in practice. The vast majority of references to genetic variants in the literature refer to coding DNA or protein variants.…”

AVADA Enables Automated Genetic Variant Curation Directly from the Full Text Literature

“…Previous work on automatic variant discovery in the literature has largely focused on finding variant descriptions in paper titles and abstracts with high accuracy without converting the discovered variants to genomic coordinates [16][17][18][19][20][21][22] . Previous automatic variant curation tools have also focused on mapping variant mentions to dbSNP 23 variant identifiers (rsIDs).…”

Text Mining for Precision Medicine

“…However, there is still a gap between the research community and the biomedical textmining community. Yepes and Verspour compare in (Yepes & Verspoor, 2014) the performance of EMU, OMM, MF, tmVar and SETH intrinsically on the Variome corpus, and extrinsically on the COSMIC and InSiGHT database. The study also discusses the technical aspects related to using the tools; some of them require an intermediate to advanced level of programming knowledge to use them.…”