A modular framework for biomedical concept recognition
- PMID: 24063607
- PMCID: PMC3849280
- DOI: 10.1186/1471-2105-14-281
A modular framework for biomedical concept recognition
Abstract
Background: Concept recognition is an essential task in biomedical information extraction, presenting several complex and unsolved challenges. The development of such solutions is typically performed in an ad-hoc manner or using general information extraction frameworks, which are not optimized for the biomedical domain and normally require the integration of complex external libraries and/or the development of custom tools.
Results: This article presents Neji, an open source framework optimized for biomedical concept recognition built around four key characteristics: modularity, scalability, speed, and usability. It integrates modules for biomedical natural language processing, such as sentence splitting, tokenization, lemmatization, part-of-speech tagging, chunking and dependency parsing. Concept recognition is provided through dictionary matching and machine learning with normalization methods. Neji also integrates an innovative concept tree implementation, supporting overlapped concept names and respective disambiguation techniques. The most popular input and output formats, namely Pubmed XML, IeXML, CoNLL and A1, are also supported. On top of the built-in functionalities, developers and researchers can implement new processing modules or pipelines, or use the provided command-line interface tool to build their own solutions, applying the most appropriate techniques to identify heterogeneous biomedical concepts. Neji was evaluated against three gold standard corpora with heterogeneous biomedical concepts (CRAFT, AnEM and NCBI disease corpus), achieving high performance results on named entity recognition (F1-measure for overlap matching: species 95%, cell 92%, cellular components 83%, gene and proteins 76%, chemicals 65%, biological processes and molecular functions 63%, disorders 85%, and anatomical entities 82%) and on entity normalization (F1-measure for overlap name matching and correct identifier included in the returned list of identifiers: species 88%, cell 71%, cellular components 72%, gene and proteins 64%, chemicals 53%, and biological processes and molecular functions 40%). Neji provides fast and multi-threaded data processing, annotating up to 1200 sentences/second when using dictionary-based concept identification.
Conclusions: Considering the provided features and underlying characteristics, we believe that Neji is an important contribution to the biomedical community, streamlining the development of complex concept recognition solutions. Neji is freely available at http://bioinformatics.ua.pt/neji.
Figures
![Figure 1](https://www.ncbi.nlm.nih.gov/pmc/articles/instance/3849280/bin/1471-2105-14-281-1.gif)
![Figure 2](https://www.ncbi.nlm.nih.gov/pmc/articles/instance/3849280/bin/1471-2105-14-281-2.gif)
![Figure 3](https://www.ncbi.nlm.nih.gov/pmc/articles/instance/3849280/bin/1471-2105-14-281-3.gif)
![Figure 4](https://www.ncbi.nlm.nih.gov/pmc/articles/instance/3849280/bin/1471-2105-14-281-4.gif)
![Figure 5](https://www.ncbi.nlm.nih.gov/pmc/articles/instance/3849280/bin/1471-2105-14-281-5.gif)
![Figure 6](https://www.ncbi.nlm.nih.gov/pmc/articles/instance/3849280/bin/1471-2105-14-281-6.gif)
![Figure 7](https://www.ncbi.nlm.nih.gov/pmc/articles/instance/3849280/bin/1471-2105-14-281-7.gif)
![Figure 8](https://www.ncbi.nlm.nih.gov/pmc/articles/instance/3849280/bin/1471-2105-14-281-8.gif)
![Figure 9](https://www.ncbi.nlm.nih.gov/pmc/articles/instance/3849280/bin/1471-2105-14-281-9.gif)
![Figure 10](https://www.ncbi.nlm.nih.gov/pmc/articles/instance/3849280/bin/1471-2105-14-281-10.gif)
Similar articles
-
Development of an information retrieval tool for biomedical patents.Comput Methods Programs Biomed. 2018 Jun;159:125-134. doi: 10.1016/j.cmpb.2018.03.012. Epub 2018 Mar 14. Comput Methods Programs Biomed. 2018. PMID: 29650307
-
NCBI disease corpus: a resource for disease name recognition and concept normalization.J Biomed Inform. 2014 Feb;47:1-10. doi: 10.1016/j.jbi.2013.12.006. Epub 2014 Jan 3. J Biomed Inform. 2014. PMID: 24393765 Free PMC article.
-
Concept annotation in the CRAFT corpus.BMC Bioinformatics. 2012 Jul 9;13:161. doi: 10.1186/1471-2105-13-161. BMC Bioinformatics. 2012. PMID: 22776079 Free PMC article.
-
Information retrieval and knowledge discovery utilising a biomedical Semantic Web.Brief Bioinform. 2005 Sep;6(3):252-62. doi: 10.1093/bib/6.3.252. Brief Bioinform. 2005. PMID: 16212773 Review.
-
A survey of current work in biomedical text mining.Brief Bioinform. 2005 Mar;6(1):57-71. doi: 10.1093/bib/6.1.57. Brief Bioinform. 2005. PMID: 15826357 Review.
Cited by
-
An automatic hypothesis generation for plausible linkage between xanthium and diabetes.Sci Rep. 2022 Oct 20;12(1):17547. doi: 10.1038/s41598-022-20752-0. Sci Rep. 2022. PMID: 36266295 Free PMC article.
-
Parallel sequence tagging for concept recognition.BMC Bioinformatics. 2022 Mar 24;22(Suppl 1):623. doi: 10.1186/s12859-021-04511-y. BMC Bioinformatics. 2022. PMID: 35331131 Free PMC article.
-
MedTAG: a portable and customizable annotation tool for biomedical documents.BMC Med Inform Decis Mak. 2021 Dec 18;21(1):352. doi: 10.1186/s12911-021-01706-4. BMC Med Inform Decis Mak. 2021. PMID: 34922517 Free PMC article.
-
Extraction of Family History Information From Clinical Notes: Deep Learning and Heuristics Approach.JMIR Med Inform. 2020 Dec 29;8(12):e22898. doi: 10.2196/22898. JMIR Med Inform. 2020. PMID: 33372893 Free PMC article.
-
Gold-standard ontology-based anatomical annotation in the CRAFT Corpus.Database (Oxford). 2017 Jan 1;2017:bax087. doi: 10.1093/database/bax087. Database (Oxford). 2017. PMID: 31725864 Free PMC article.
References
-
- Campos D, Matos S, Oliveira JL, Campos D, Matos S, Oliveira JL. In: Biological Knowledge Discovery Handbook: Preprocessing, Mining And Postprocessing Of Biological Data (to appear) Elloumi M, Zomaya AY, editor. Wiley Online Library; 2014. Current Methodologies for Biomedical Named Entity Recognition.
-
- He Y, Kayaalp M. A Comparison of 13 Tokenizers on MEDLINE. Bethesda, MD: U.S. National Library of Medicine; 2006.
-
- Ferrucci D, Lally A. UIMA: an architectural approach to unstructured information processing in the corporate research environment. Nat Lang Eng. 2004;10(3-4):327–348. doi: 10.1017/S1351324904003523. - DOI
-
- Cunningham H. GATE, a general architecture for text engineering. Comput Hum. 2002;36:223–254. doi: 10.1023/A:1014348124664. - DOI
Publication types
MeSH terms
LinkOut - more resources
Full Text Sources
Other Literature Sources