4-санға «Автоматтандыру және ақпараттық технологиялар», «Азық-түлік инженериясы және биотехнология», сондай-ақ «Химиялық технология» бағыттары бойынша мақалалар қабылдау жабылды.

Приём статей в четвёртый номер по направлениям «Автоматизация и информационные технологии», «Пищевая инженерия и биотехнология», а также «Химическая технология» закрыт.

Submissions for the fourth issue in the fields of Automation and Information Technology, Food Engineering and Biotechnology, as well as Chemical Technology, are now closed.

Preview

Bulletin of Shakarim University. Technical Sciences

Bulletin of Shakarim University. Technical Sciences

Advanced search

ONTOLOGY-AWARE FOR PHENOTYPE TERM NORMALIZATION AND GROUP ASSIGNMENT

https://doi.org/10.53360/2788-7995-2026-3(23)-5

Abstract

This study addresses the problem of automating the processing of terminological data using ontology-oriented methods of natural language processing. Modern information systems increasingly operate with heterogeneous and poorly structured terms presented in the form of lists or textual descriptions, which complicates their normalization, comparison, and subsequent automatic classification. This problem is particularly relevant in biomedical informatics, where phenotypic descriptions of hereditary diseases require standardized representation for integration into intelligent information systems.
The paper proposes an ontology-aware NLP algorithm aimed at the normalization of terms and their automatic distribution into a fixed set of semantic groups based on an ontological model. The approach combines methods for entity extraction and normalization, ontological linking, and taxonomic classification, enabling the generation of a formalized and reproducible representation of terminological data. As the semantic basis, the specialized PNGO ontology (Phenotype-based Normalized Group Ontology) is used, implemented in OWL 2 format and defining a fixed set of 23 phenotypic groups anchored to the Human Phenotype Ontology (HPO) hierarchy.
The proposed approach provides a deterministic and interpretable alternative to machine and deep learning methods, ensuring reproducibility and semantic consistency of results without requiring a training stage on annotated data. The effectiveness of the solution is confirmed by experimental evaluation on five hereditary diseases comprising 53 phenotype terms, where the algorithm achieved a macro-average F1-score of 0.919. The resulting structured profile is suitable for integration into information systems, analytical modules, and reproducible computational pipelines.

About the Authors

М. А. Sambetbayeva
«Q» University; L.N. Gumilyov Eurasian National University
Kazakhstan

Madina Aralbaevna Sambetbaeva – PhD, associate professor of the department of Information systems; leading researcher 

050026, Republic of Kazakhstan, Almaty, str. Baizakov 125/185

 



V. B. Barakhnin
Novosibirsk State Technical University
Russian Federation

Vladimir Borisovich Barakhnin – Doctor of technical sciences; head of the laboratory of Information resources at the federal research center for information and  computational technologies; Professor of the faculty of Applied mathematics and informatics 

Russia, Novosibirsk 630087, str. Nemirovicha-Danchenko 136



A. N. Sultangaziyeva
«Q» University; Astana International University
Kazakhstan

Anar Nesipbekkyzy Sultangaziyeva – master of computer science, doctoral student at the Higher School of Information Technologies and Engineering; junior researcher 

050026, Republic of Kazakhstan, Almaty, str. Baizakov 125/185 

010000, Republic of Kazakhstan, Astana, Qabanbay Batyr Avenue, 8



N. K. Mukazhanov
«Q» University; Narxoz University
Kazakhstan

Nurzhan Kakenovich Mukazhanov – project leader; PhD, associate professor of the School of Digital Technologies

050026, Republic of Kazakhstan, Almaty, str. Baizakov 125/185

Kazakhstan, Almaty 050035, str. Zhandosov 55



R. A. Begim
L.N. Gumilyov Eurasian National University
Kazakhstan

Raushan Ayankyzy Begim – master’s student of the Department of Information systems

010008, Republic of Kazakhstan, Astana, Satpayev str. 2



References

1. Uyghur–Kazakh–Kirghiz text keyword extraction based on morpheme segmentation / S. Parhat et al // Information. 2023. – Vol. 14, № 5. – P. 283. https://doi.org/10.3390/info14050283.

2. Hoehndorf R. The role of ontologies in biological and biomedical research: A functional perspective / R. Hoehndorf, P.N. Schofield, G.V. Gkoutos // Briefings in Bioinformatics. – 2015. – Vol. 16, № 6. – P. 1069-1080. https://doi.org/10.1093/bib/bbv011.

3. A review on knowledge graphs for healthcare: Resources, applications, and promises / H. Cui et al // Journal of Biomedical Informatics. – 2025. – Vol. 169. – P. 104861. https://doi.org/10.1016/j.jbi.2025.104861.

4. Explainable artificial intelligence for breast cancer: A visual case-based reasoning approach / J.-B. Lamy et al // Artificial Intelligence in Medicine. – 2019. – Vol. 94. – P. 42-53. https://doi.org/10.1016/j.artmed.2019.01.001.

5. Opportunities and challenges for ChatGPT and large language models in biomedicine and health / S. Tian et al // Briefings in Bioinformatics. – 2024. – Vol. 25, № 1. – P. bbad493. https://doi.org/10.1093/bib/bbad493.

6. Riquelme-García A. Annotation of biological samples data to standard ontologies with support from large language models / A. Riquelme-García, J. Mulero-Hernández, J.T. Fernández-Breis // Computational and Structural Biotechnology Journal. – 2025. – Vol. 27. – P. 2155-2167. https://doi.org/10.1016/j.csbj.2025.02.018.

7. Deep learning in clinical natural language processing: A methodical review / S. Wu et al // Journal of the American Medical Informatics Association. – 2020. – Vol. 27, № 3. – P. 457-470. https://doi.org/10.1093/jamia/ocz200.

8. Arora A. Named entity recognition for clinical text: A review / A. Arora, E. Nyberg, C.P. Rosé // Artificial Intelligence in Medicine. – 2021. – Vol. 113. – P. 102039. https://doi.org/10.1016/j.artmed.2021.102039.

9. Clinical natural language processing in languages other than English: Opportunities and challenges / A. Névéol et al // Journal of Biomedical Semantics. – 2020. – Vol. 11. – P. 12. https://doi.org/10.1186/s13326-020-00239-7.

10. Lu Z. Large language models in biomedicine and health / Z. Lu, Y. Peng // Journal of the American Medical Informatics Association. – 2024. – Vol. 31, № 8. – P. 1801-1811. https://doi.org/10.1093/jamia/ocae089.

11. BioPortal: An open community resource for sharing, searching, and utilizing biomedical ontologies / J. Vendetti et al // Bioinformatics. – 2025. – Vol. 41, № 2. – P. gkaf402. https://doi.org/10.1093/bioinformatics/gkaf4020.

12. Biomedical knowledge graph–optimized prompt generation for large language models / K. Soman et al // Bioinformatics. – 2024. – Vol. 40, № 9. – P. btae560. https://doi.org/10.1093/bioinformatics/btae560.

13. A survey on unifying large language models and knowledge graphs in biomedicine / R. Xu et al // Bioinformatics. – 2025. – Vol. 41, No. 1. – P. btaf018. – DOI: 10.1093/bioinformatics/btaf018

14. Nicholson D. N., Greene C. S. Constructing knowledge graphs and their biomedical applications // Computational and Structural Biotechnology Journal. – 2020. – Vol. 18. – P. 1414-1428. – DOI: 10.1016/j.csbj.2020.05.017

15. Hogan A., Blomqvist E., Cochez M. [et al.]. Knowledge graphs // ACM Computing Surveys. – 2021. – Vol. 54, No. 4. – P. 1-37. – DOI: 10.1145/3447772


Review

For citations:


Sambetbayeva М.А., Barakhnin V.B., Sultangaziyeva A.N., Mukazhanov N.K., Begim R.A. ONTOLOGY-AWARE FOR PHENOTYPE TERM NORMALIZATION AND GROUP ASSIGNMENT. Bulletin of Shakarim University. Technical Sciences. 2026;(3(23)):42-53. https://doi.org/10.53360/2788-7995-2026-3(23)-5

Views: 14

JATS XML


Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 License.


ISSN 2788-7995 (Print)
ISSN 3006-0524 (Online)
X