A Silver Standard Corpus of Human Phenotype-Gene Relations
This provides a resource for biomedical researchers to improve relation extraction tools for understanding phenotypic abnormalities and diseases, though it is incremental as it builds on existing NER methods.
The paper tackles the lack of annotated data for human phenotype-gene relations by creating the PGR corpus, a silver standard with 1712 abstracts and 4283 relations, achieving 87.01% precision in annotation and enabling deep learning tools to reach 78.05% precision.
Human phenotype-gene relations are fundamental to fully understand the origin of some phenotypic abnormalities and their associated diseases. Biomedical literature is the most comprehensive source of these relations, however, we need Relation Extraction tools to automatically recognize them. Most of these tools require an annotated corpus and to the best of our knowledge, there is no corpus available annotated with human phenotype-gene relations. This paper presents the Phenotype-Gene Relations (PGR) corpus, a silver standard corpus of human phenotype and gene annotations and their relations. The corpus consists of 1712 abstracts, 5676 human phenotype annotations, 13835 gene annotations, and 4283 relations. We generated this corpus using Named-Entity Recognition tools, whose results were partially evaluated by eight curators, obtaining a precision of 87.01%. By using the corpus we were able to obtain promising results with two state-of-the-art deep learning tools, namely 78.05% of precision. The PGR corpus was made publicly available to the research community.