An integrated pipeline model for biomedical entity alignment

Abstract

Biomedical entity alignment, composed of two subtasks: entity identification and entity-concept mapping, is of great research value in biomedical text mining while these techniques are widely used for name entity standardization, information retrieval, knowledge acquisition and ontology construction.

Previous works made many efforts on feature engineering to employ feature-basedmodels for entity identification and alignment. However, the models depended on subjective feature selection may suffer error propagation and are not able to utilize the hidden information.With rapid development in healthrelated research, researchers need an effective method to explore the large amount of available biomedical literatures.

Therefore, we propose a two-stage entity alignment process, biomedical entity exploring model, to identify biomedical entities and align them to the knowledge base interactively. The model aims to automatically obtain semantic information for extracting biomedical entities and mining semantic relations through the standard biomedical knowledge base. The experiments show that the proposed method achieves better performance on entity alignment. The proposed model dramatically improves the F1 scores of the task by about 4.5% in entity identification and 2.5% in entity-concept mapping.

Keywords

entity alignment / biomedical text mining / neural network model

References

[1] Amith M, Zhang Y, Xu H, Tao C. Knowledge-based approach for named entity recognition in biomedical literature: a use case in biomedical software identification, In: Benferhat S, Tabia K, Ali M, eds. Advances in Artificial Intelligence: From Theory to Practice. Springer, Cham, 2017

[2] Dang T H, Le H Q, Trang M N. D3NER: biomedical named entity recognition using CRF-biLSTM improved with fine-tuned embeddings of various linguistic information. Bioinformatics, 2018, 34(20): 3539–3546

[3] Dieter G, Ivan L, Kirill A V. Exploiting and assessing multi-source data for supervised biomedical named entity recognition. Bioinformatics, 2018, 34(14): 2474–2482

[4] Lossio-Ventura J A, Bian J, Jonguet C, Roche M, Teisseire M. A novel framework for biomedical entity sense induction. Journal of Biomedical Informatics, 2018, 84: 31–41

[5] Chris J L, Destinee T, Lynn M C. Enhanced lexsynonym acquisition for effective UMLS concept mapping. In: Proceedings of the 16th World Congress on Medical and Health Informatics. 2017, 501–505

[6] Mollie R C, Kristina D H, Joseph P. Automated mapping of NPDS data elements to the UMLS metathesaurus. In: Proceedings of American Medical Informatics Association Annual Symposium. 2013

[7] Paul T, John M N, Simonetta M. The BioLexicon: a large-scale terminological resource for biomedical text mining. BMC Bioinformatics, 2011, 12: 397–426

[8] Hans-Michael M, Kimberly V A, Li Y. Textpresso central: a customizable platform for searching, text mining, viewing, and curating biomedical literature. BMC Bioinformatics, 2018, 19(1): 1–16

[9] Song M, Han W S, Yu H. BoDBES: a boosted dictionary-based biomedical entity spotter. In: Proceeding of the 7rd International Workshop on Data and Text Mining in Bioinformatics. 2013, 21–22

[10] Song M, Yu H, Han W S. Developing a hybrid dictionary-based bio-entity recognition technique. BMC Medical Informatics and Decision Making, 2015, 15(S1): S9

[11] Lars J J. One tagger, many uses: illustrating the power of ontologies in dictionary-based named entity recognition. In: Proceedings of the Joint International Conference on Biological Ontology and BioCreative. 2016, 1747–1749

[12] Yang Z, Li H, Li Y. Exploiting the performance of dictionary-based bioentity name recognition in biomedical literature. Computational Biology and Chemistry, 2008, 32(4): 287–291

[13] Martijn J S, Barend M, Marc W. Evaluation of techniques for increasing recall in a dictionary approach to gene and protein name identification. Journal of Biomedical Informatics, 2007, 40(3): 316–324

[14] Zeng D, Sun C, Lin L, Liu B. Enlarging drug dictionary with semisupervised learning for drug entity recognition. In: Proceedings of IEEE International Conference on Bioinformatics and Biomedicine. 2016, 1929–1931

[15] Laura C, Rajasekar K, Li Y, Frederick R, Shivakumar V. Domain adaptation of rule-based annotators for named-entity recognition tasks. In: Proceedings of the 2010 Conference on Empirical Methods in Natural Language Processing. 2010, 1002–1012

[16] Ryan G, Jay D, Constantine L, Marjorie F, Ralph M W. Combining rulebased and statistical mechanisms for low-resource named entity recognition. Machine Translation, 2018, 32(1–2): 31–43

[17] Peng M, Xing X, Zhang Q, Fu J, Huang X. Distantly supervised named entity recognition using positive-unlabeled learning. In: Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics. 2019, 2409–2419

[18] Li Q, Wang X, Zhang Y, Ling F, Wu C H, Han J. Pattern discovery for wide-window open information extraction in biomedical literature. In: Proceedings of IEEE International Conference on Bioinformatics and Biomedicine. 2018, 420–427

[19] Hanisch D, Fundel K, Mevissen H T, Zimmer R, Fluck J. ProMiner: rulebased protein and gene entity recognition. BMC Bioinformatics, 2005, 6(S1): S14

[20] Nigel C, Chikashi N, Junichi T. Extracting the names of genes and gene products with a hidden markov model. In: Proceedings of the 18th International Conference on Computational Linguistics. 2000, 201–207

[21] Burr S. Biomedical named entity recognition using conditional random fields and rich feature sets. In: Proceedings of the International Joint Workshop on Natural Language Processing in Biomedicine and its Applications. 2004, 107–110

[22] Kazuhiro S, Javed M. A hybrid approach to protein name identification in biomedical texts. Information Processing and Management, 2005, 41(4): 723–743

[23] Liu J, Huang M, Zhu X. Recognizing biomedical named entities using skip-chain conditional random fields. In: Proceedings of the 2010 Workshop on Biomedical Natural Language Processing. 2010, 10–18

[24] Sujan K S, Sudeshna S, Pabitra M. Feature selection techniques for maximum entropy based biomedical named entity recognition. Journal of Biomedical Informatics, 2009, 42(5): 905–911

[25] Zhu Q, Li X, Ana C, Cecile P. GRAM-CNN: a deep learning approach with local context for named entity recognition in biomedical text. Bioinformatics, 2018, 34(9): 1547–1554

[26] Nathan G, Trapit B, Patrick V. Marginal likelihood training of BiLSTMCRF for biomedical named entity recognition from disjoint label sets. In: Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing. 2018, 2824–2829

[27] Maryam H, Leon W, Mariana L N. Deep learning with word embeddings improves biomedical named entity recognition. Bioinformatics, 2017, 33(14): i37–i48

[28] Li H, Yang M, Chen Q, Tang B, Wang X, Yan J. Chemical-induced disease extraction via recurrent piecewise convolutional neural networks. BMC Medical Informatics and Decision Making, 2018, 18(S2): 45–51

[29] Lucy L W, Chandra B, Mark N. Ontology alignment in the biomedical domain using entity definitions and context. In: Proceedings of the BioNLP 2018 Workshop. 2018, 47–55

[30] Wang Y, Majid R M, Ravikumar K E, Liu H. Leveraging word embeddings and medical entity extraction for biomedical dataset retrieval using unstructured texts. Database, 2017, 1: 13

[31] Naiara P, Montse C, German R. Biomedical term normalization of EHRs with UMLS. In: Proceedings of the 17th International Conference on Language Resources and Evaluation. 2018, 2045–2051

[32] Ali H P, Paul C. Do character-level neural network language models capture knowledge of multiword expression compositionality? In: Proceedings of the Joint Workshop on Linguistic Annotation, Multiword Expressions and Constructions. 2018, 185–192

[33] Michael H, Marco B. Tabula nearly rasa: probing the linguistic knowledge of character-level neural language models trained on unsegmented text. Transactions of the Association for Computational Linguistics, 2019, 7: 467–484

[34] Ruiz-Martinez J M, Valencia-Garcia R, Fernández-Breis J T, García-Sánchez F, Martinez-Béjar R. Ontology learning from biomedical natural language documents using UMLS. Expert Systems with Applications, 2011, 38(10): 12365–12378

[35] He Z, Yehoshua P, Gai E, Chen Y, James G, Bian J. Auditing the assignments of top-level semantic types in the UMLS semantic network to UMLS concepts. In: Proceedings of IEEE International Conference on Bioinformatics and Biomedicine. 2017, 1262–1269

[36] EI-Rab W G, Zaïane D R, EI-Hajj M. Biomedical text disambiguation using UMLS. In: Proceedings of IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining. 2013, 943–947

[37] Lin Y F, Tsai T H, Chou WC, Wu K P, Sung T Y, Hsu W L. A maximum entropy approach to biomedical named entity recognition. In: Proceedings of the 4th ACM SIGKDD Workshop on Data Mining in Bioinformatics. 2004, 56–61

[38] Zhang S, Noemie E. Unsupervised biomedical named entity recognition: experiments with clinical and biological texts. Journal of Biomedical Informatics, 2013, 46(6): 1088–1098

[39] Serhan T, Ilyas C. Two learning approaches for protein name extraction. Journal of Biomedical Informatics, 2009, 42(6): 1046–1055

[40] Lyu C, Chen B, Ren Y. Long short-term memory RNN for biomedical named entity recognition. BMC Bioinformatics, 2017, 18(1): 462–473

[41] Andrea B, Elisabeth L. Data-intensive modelling and simulation in life sciences and socio-economical and physical sciences. Data Science and Engineering, 2017, 2(3): 197–198

[42] Kim J D, Wang Y, Nicola C, Seung H B, Kim Y H, Song M. Refactoring the genia event extraction shared task toward a general framework for IEDriven KB development. In: Proceedings of the 4th BioNLP Shared Task Workshop. 2016, 23–31

[43] Ju Z, Wang J, Zhu F. Named entity recognition from biomedical text using SVM. In: Proceedings of the 5th International Conference on Bioinformatics and Biomedical Engineering. 2011, 1–4

[44] Kuo H C, Lin K. Extracting protein names from biological literature. Advances in Computer Science: an International Journal, 2017, 3(2): 58–68

[45] Nigel C, Hyun S P, Norihiro O. The GENIA project: corpus-based knowledge acquisition and information extraction from genome research papers. In: Proceedings of the 9th Conference of the European Chapter of the Association for Computational Linguistics. 1999, 271–272

[46] Li F, Zhang M, Fu G, Ji D. A neural joint model for entity and relation extraction from biomedical text. BMC Bioinformatics, 2017, 18(1): 1–11

[47] Huang Z, Xu W, Yu K. Bidirectional LSTM-CRF models for sequence tagging. 2015, arXiv preprint arXiv:1508.01991

RIGHTS & PERMISSIONS

2020 Higher Education Press