Related Experiment Video
Updated: Apr 15, 2026

Applying Cheminformatics to Develop a Structure Searchable Database of Analytical Methods
Published on: June 6, 2025
tmChem: a high performance approach for chemical named entity recognition and normalization
Robert Leaman1, Chih-Hsuan Wei1, Zhiyong Lu1
1National Center for Biotechnology Information, 8600 Rockville Pike, Bethesda, Maryland 20894, USA.
tmChem is a new system for recognizing chemical named entities in biomedical literature. It achieves state-of-the-art performance, matching or exceeding recognition rates for genes and diseases.
Area of Science:
- Biomedical Informatics
- Natural Language Processing
- Cheminformatics
Background:
- Chemical compounds and drugs are crucial in biomedical research and clinical medicine.
- Identifying chemical named entities in text is vital for chemical text mining.
- Existing methods require improvement for accurate chemical entity recognition.
Purpose of the Study:
- To develop and evaluate tmChem, an advanced chemical named entity recognition system.
- To improve the identification of chemical mentions, properties, and relationships in scientific literature.
- To establish a new benchmark for chemical named entity recognition performance.
Main Methods:
- Developed tmChem by ensembling two independent machine learning models.
- Utilized the CHEMDNER task corpus for training and evaluation.
- Implemented both mention-level (CEM) and abstract-level (CDI) evaluation metrics.
Main Results:
- Achieved a micro-averaged F-measure of 0.8739 on the CEM subtask and 0.8745 on the CDI subtask.
- Reported a high-recall variant with 0.9212 (CEM) and 0.9224 (CDI) recall.
- Outperformed existing methods, achieving the highest reported F-measure on the CHEMDNER CEM subtask.
Conclusions:
- tmChem is a state-of-the-art tool for chemical named entity recognition.
- The performance of chemical named entity recognition now rivals that of gene and disease recognition.
- Future work should integrate named entity recognition and normalization for enhanced performance.
More Related Videos
09:04Identifying Per- and Polyfluorinated Chemical Species with a Combined Targeted and Non-Targeted-Screening High-Resolution Mass Spectrometry Workflow
Published on: April 18, 2019
09:24Standardized Identification of Compound Structure in Tibetan Medicine Using Ion Trap Mass Spectrometry and Multiple-Stage Fragmentation Analysis
Published on: March 17, 2023
Related Concept Videos
Chemical Symbols
Some symbols are derived from the common name of the element; others are abbreviations of the name in another language. Most symbols have one or two letters, but three-letter symbols have been used...
Molecular Compounds: Formulas and Nomenclature
Nomenclature of Aromatic Compounds with a Single Substituent
Coordination Compounds and Nomenclature
Nomenclature of Aromatic Compounds with Multiple Substituents
For disubstituted benzene derivatives, with two groups attached to the benzene ring, three constitutional isomers are possible. For example, consider dimethyl benzene, often called xylene, where the second methyl group can be substituted at the second, third, or fourth carbon. The relative position of the substituents is represented by prefixes ortho, meta, or...
Properties of Organometallic Compounds