Abstract
Natural language processing (NLP) and text mining technologies for the chemical domain (ChemNLP or chemical text mining) are key to improve the access and integration of information from unstructured data such as patents or the scientific literature. Therefore, the BioCreative organizers posed the CHEMDNER (chemical compound and drug name recognition) community challenge, which promoted the development of novel, competitive and accessible chemical text mining systems. This task allowed a comparative assessment of the performance of various methodologies using a carefully prepared collection of manually labeled text prepared by specially trained chemists as Gold Standard data. We evaluated two important aspects: one covered the indexing of documents with chemicals (chemical document indexing - CDI task), and the other was concerned with finding the exact mentions of chemicals in text (chemical entity mention recognition - CEM task). 27 teams (23 academic and 4 commercial, a total of 87 researchers) returned results for the CHEMDNER tasks: 26 teams for CEM and 23 for the CDI task. Top scoring teams obtained an F-score of 87.39% for the CEM task and 88.20% for the CDI task, a very promising result when compared to the agreement between human annotators (91%). The strategies used to detect chemicals included machine learning methods (e.g. conditional random fields) using a variety of features, chemistry and drug lexica, and domain-specific rules. We expect that the tools and resources resulting from this effort will have an impact in future developments of chemical text mining applications and will form the basis to find related chemical information for the detected entities, such as toxicological or pharmacogenomic properties.
Highlights
Unstructured data repositories contain fundamental descriptions of chemical entities, such as their targets and binding partners, metabolism, enzymatic reactions, potential adverse effects and therapeutic use, just to name a few
For the chemical document indexing (CDI) task, this strategy obtained a micro-averaged F-score of 53.85%, while in case of the chemical entity mention recognition (CEM) task it reached a micro averaged F-score of 57.11
The CHEMDNER task of BioCreative IV showed that the automatic recognition of chemical entities from PubMed abstracts is a feasible task by automated named entity recognition systems
Summary
Unstructured data repositories contain fundamental descriptions of chemical entities, such as their targets and binding partners, metabolism, enzymatic reactions, potential adverse effects and therapeutic use, just to name a few. Text-mining methods have shown promising results in the biomedical domain, where a considerable amount of methods and applications have been published [2,3]. Knowing which compounds are described in a given paper, and where exactly those descriptions are, is key to select appropriate papers. With such fine-grained annotations, it is possible to directly point to relevant sentences and to extract more detailed chemical entity relations. The recognition of gene and protein mentions was addressed in several community challenges (BioCreative I, II, JNLPBA) that served to determine the state of the art methodology and systems performance [5,12] in addition of providing valuable datasets for developing new systems [15]
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
