Automating the Extraction of Essential Genes from Literature

Abstract

The construction of repositories with curated information about gene essentiality for organisms of interest in Biotechnology is a very relevant task, mainly in the design of cell factories for the enhanced production of added-value products. However, it requires retrieval and extraction of relevant information from literature, leading to high costs regarding manual curation. Text mining tools implementing methods addressing tasks as information retrieval, named entity recognition and event extraction have been developed to automate and reduce the time required to obtain relevant information from literature in many biomedical fields. However, current tools are not designed or optimized for the purpose of identifying mentions to essential genes in scientific texts. In this work, we propose a pipeline to automatically extract mentions to genes and to classify them accordingly to their essentiality for a specific organism. This pipeline implements a machine learning approach that is trained using a manually curated set of documents related with gene essentiality in yeast. This corpus is provided as a resource for the community, as a benchmark for the development of new methods. Our pipeline was evaluated performing resampling and cross validation over this curated dataset, presenting an accuracy of over 80%, and an f1-score over 75%.