PGxCorpus, a manually annotated corpus for pharmacogenomics.

Legrand J1, Gogdemir R2, Bousquet C3, Dalleau K2, Devignes MD2, Digan W4,5, Lee CJ6, Ndiaye NC7, Petitpain N8, Ringot P2, Smaïl-Tabbone M2, Toussaint Y2, Coulet A2,9.

Author information

1: Université de Lorraine, CNRS, Inria, LORIA, Nancy, France. joel.legrand@inria.fr.
2: Université de Lorraine, CNRS, Inria, LORIA, Nancy, France.
3: Sorbonne Université, INSERM, Université Paris 13, LIMICS, Paris, France.
4: Hôpital Européen Georges Pompidou, AP-HP, Université Paris Descartes, Université Sorbonne Paris Cité, Paris, France.
5: INSERM UMR 1138 Equipe 22, Université Paris Descartes, Université Sorbonne Paris Cité, Paris, France.
6: Department of Biomedical Informatics and Medical Education, University of Washington, Seattle, Washington, USA.
7: INSERM U1256 - NGERE, Université de Lorraine, Nancy, France.
8: Centre Régional de Pharmacovigilance, CHRU of Nancy, Nancy, France.
9: Stanford Center for Biomedical Informatics Research, Stanford University, Stanford, California, USA.

Abstract

Pharmacogenomics (PGx) studies how individual gene variations impact drug response phenotypes, which makes PGx-related knowledge a key component towards precision medicine. A significant part of the state-of-the-art knowledge in PGx is accumulated in scientific publications, where it is hardly reusable by humans or software. Natural language processing techniques have been developed to guide experts who curate this amount of knowledge. But existing works are limited by the absence of a high quality annotated corpus focusing on PGx domain. In particular, this absence restricts the use of supervised machine learning. This article introduces PGxCorpus, a manually annotated corpus, designed to fill this gap and to enable the automatic extraction of PGx relationships from text. It comprises 945 sentences from 911 PubMed abstracts, annotated with PGx entities of interest (mainly gene variations, genes, drugs and phenotypes), and relationships between those. In this article, we present the corpus itself, its construction and a baseline experiment that illustrates how it may be leveraged to synthesize and summarize PGx knowledge.