ntvНаучно-технический вестник информационных технологий, механики и оптикиScientific and Technical Journal of Information Technologies, Mechanics and Optics2226-14942500-0373Университет ИТМО10.17586/2226-1494-2024-24-4-594-601ntv-235Research ArticleКОМПЬЮТЕРНЫЕ СИСТЕМЫ И ИНФОРМАЦИОННЫЕ ТЕХНОЛОГИИCOMPUTER SCIENCEПредсказание связей «ген-болезнь» с помощью гетерогенной графовой нейронной сетиPredicting gene-disease associations using a heterogeneous graph neural networkhttps://orcid.org/0009-0004-0571-5192СидоренкоД. А.SidorenkoD. A.

Сидоренко Денис Александрович — аспирант

Санкт-Петербург, 197101

Denis A. Sidorenko — PhD Student

Saint Petersburg, 197101

denisissveta@mail.ruhttps://orcid.org/0000-0002-2723-2077ШалытоА. А.ShalytoA. A.

Шалыто Анатолий Абрамович — доктор технических наук, профессор, главный научный сотрудник, профессор

Санкт-Петербург, 197101

Anatoly A. Shalyto — D.Sc., Full Professor, Chief Scientific Researcher

Saint Petersburg, 197101

shalyto@mail.ifmo.ruУниверситет ИТМОРоссияITMO UniversityRussian Federation202411122024244594601Copyright © Сидоренко Д.А., Шалыто А.А., 20242024Сидоренко Д.А., Шалыто А.А.Sidorenko D.A., Shalyto A.A.Данная работа распространяется под лицензией Creative Commons Attribution 4.0.This work is licensed under a Creative Commons Attribution 4.0 License.https://ntv.elpub.ru/jour/article/view/235

Введение. Представлены результаты разработки модели гетерогенной графовой нейронной сети для предсказания ассоциаций между генами и заболеваниями на основе имеющихся геномных и медицинских данных. Новизна предложенного подхода состоит в объединении концепций графовых нейронных сетей и гетерогенных информационных сетей для эффективной обработки структурированных данных и учета сложных взаимодействий между генами и патологиями. Метод. Предложенное решение представляет собой гетерогенную графовую нейронную сеть, которая использует гетерогенную графовую структуру для представления генов, болезней и их взаимосвязей. Основные результаты. Оценка точности разработанной модели проведена на наборах данных DisGeNET, LASTFM, YELP. На этих же данных выполнено сравнение результатов с наиболее сильными моделями. Показано превосходство предложенной модели по метрикам точности Average Precision (AP), F1-меры (F1@S), Hit@k, Area Under Receiver Operating Characteristic curve (AUROC) при предсказании ассоциаций «ген-болезнь». Обсуждение. Разработанная модель может использоваться как инструмент биоинформатического анализа и в качестве вспомогательного средства для исследователей и врачей при изучении генетических заболеваний. Такой подход может ускорить процесс открытия новых лекарственных мишеней и разработку персонализированной медицины.

The research presents the development of a heterogeneous graph neural network model for predicting gene-disease using existing genomic and medical data. The novelty of the approach is in integrating the principles of graph neural networks and heterogeneous information networks for efficient processing of structured data and consideration of complex genepathology interactions. The solution proposed is a heterogeneous graph neural network which utilizes a heterogeneous graph structure for representing genes, diseases, and their relationships. The performance of the developed model was evaluated on the DisGeNET, LASTFM, YELP datasets. On these datasets, a comparison was made with current SOTA models. The comparison results demonstrated that the proposed model outperforms other models in terms of Average Precision (AP), F1-measure (F1@S), Hit@k, Area Under Receiver Operating Characteristic curve (AUROC) in predicting “gene-disease” associations. The model developed serves as a tool for bioinformatics analysis and can aid researchers and doctors in studying genetic diseases. This could expedite the discovery of new drug targets and the advancement of personalized medicine.

машинное обучениеграфовые нейронные сетигетерогенные информационные сетибиоинформатикагенетикапредсказание «ген-болезнь» ассоциацийmachine learninggraph neural networksheterogeneous information networksbioinformaticsgenetics“gene-disease” prediction associationsReferencesHenaff M., Bruna J., LeCun Y. Deep convolutional networks on graph-structured data // arXiv. 2015. arXiv:1506.05163. https://doi.org/10.48550/arXiv.1506.05163Henaff M., Bruna J., LeCun Y. Deep convolutional networks on graph-structured data. arXiv, 2015, arXiv:1506.05163. https://doi.org/10.48550/arXiv.1506.05163Wang X., Bo D., Shi C., Fan S., Ye Y., Yu P.S. A survey on heterogeneous graph embedding: methods, techniques, applications and sources // IEEE Transactions on Big Data. 2023. V. 9. N 2. P. 415–436. https://doi.org/10.1109/TBDATA.2022.3177455Wang X., Bo D., Shi C., Fan S., Ye Y., Yu P.S. A survey on heterogeneous graph embedding: methods, techniques, applications and sources. IEEE Transactions on Big Data, 2023, vol. 9, no. 2, pp. 415–436. https://doi.org/10.1109/TBDATA.2022.3177455Shao B., Li X., Bian G. A survey of research hotspots and frontier trends of recommendation systems from the perspective of knowledge graph // Expert Systems with Applications. 2021. V. 165. P. 113764. https://doi.org/10.1016/j.eswa.2020.113764Shao B., Li X., Bian G. A survey of research hotspots and frontier trends of recommendation systems from the perspective of knowledge graph. Expert Systems with Applications, 2021, vol. 165, pp. 113764. https://doi.org/10.1016/j.eswa.2020.113764László L. Random walks on graphs: a survey // Combinatorics. V. 2. 1993. P. 1–46.László L. Random walks on graphs: a survey. Combinatorics. V. 2. 1993, pp. 1–46.Li L., Wang Y., An L., Kong X., Huang T. A network-based method using a random walk with restart algorithm and screening tests to identify novel genes associated with Menière’s disease // PLOS ONE. 2017. V. 12. N 8. P. e0182592. https://doi.org/10.1371/journal.pone.0182592Li L., Wang Y., An L., Kong X., Huang T. A network-based method using a random walk with restart algorithm and screening tests to identify novel genes associated with Menière’s disease. PLOS ONE, 2017, vol. 12, no. 8, pp. e0182592. https://doi.org/10.1371/journal.pone.0182592Muslu Ö., Hoyt C.T., Lacerda M., Hofmann-Apitius M., Frohlich H. GuiltyTargets: Prioritization of novel therapeutic targets with network representation learning // IEEE/ACM Transactions on Computational Biology and Bioinformatics. 2022. V. 19. N 1. P. 491–500. https://doi.org/10.1109/TCBB.2020.3003830Muslu Ö., Hoyt C.T., Lacerda M., Hofmann-Apitius M., Frohlich H. GuiltyTargets: Prioritization of novel therapeutic targets with network representation learning. IEEE/ACM Transactions on Computational Biology and Bioinformatics, 2022, vol. 19, no. 1, pp. 491–500. https://doi.org/10.1109/TCBB.2020.3003830Li Y., Kuwahara H., Yang P., Song L., Gao X. PGCN: Disease gene prioritization by disease and gene embedding through graph convolutional neural networks // biorxiv.org. 2019. https://doi.org/10.1101/532226Li Y., Kuwahara H., Yang P., Song L., Gao X. PGCN: Disease gene prioritization by disease and gene embedding through graph convolutional neural networks. biorxiv.org, 2019. https://doi.org/10.1101/532226Dutta A., Alcaraz J., TehraniJamsaz A., Cesar E., Sikora A., Jannesari A. Performance optimization using multimodal modeling and heterogeneous GNN // arXiv. 2023. arXiv.2304.12568. https://doi.org/10.48550/arXiv.2304.12568Dutta A., Alcaraz J., TehraniJamsaz A., Cesar E., Sikora A., Jannesari A. Performance optimization using multimodal modeling and heterogeneous GNN. arXiv, 2023, arXiv.2304.12568. https://doi.org/10.48550/arXiv.2304.12568Thanapalasingam T., van Berkel L., Bloem P., Groth P. Relational graph convolutional networks: Closer Look // PeerJ Computer Science. 2022. V. 8. P. e1073. https://doi.org/10.7717/PEERJ-CS.1073Thanapalasingam T., van Berkel L., Bloem P., Groth P. Relational graph convolutional networks: Closer Look. PeerJ Computer Science, 2022, vol. 8, pp. e1073. https://doi.org/10.7717/PEERJ-CS.1073Wang X., Ji H., Shi C., Wang B., Ye Y., Cui P., Yu P.S. Heterogeneous graph attention network // Proc. of the WWW ‘19: The World Wide Web Conference. 2019. P. 2022–2032. https://doi.org/10.1145/3308558.3313562Wang X., Ji H., Shi C., Wang B., Ye Y., Cui P., Yu P.S. Heterogeneous graph attention network. Proc. of the WWW ‘19: The World Wide Web Conference, 2019, pp. 2022–2032. https://doi.org/10.1145/3308558.3313562Ali A., Bagchi A. An overview of protein-protein interaction // Current Chemical Biology. 2015. V. 9. N 1. P. 53–65. https://doi.org/10.2174/221279680901151109161126Ali A., Bagchi A. An overview of protein-protein interaction. Current Chemical Biology, 2015, vol. 9, no. 1, pp. 53–65. https://doi.org/10.2174/221279680901151109161126Malone J., Holloway E., Adamusiak T., Kapushesky M., Zheng J., Kolesnikov N., Zhukova A., Brazma A., Parkinson H. Modeling sample variables with an experimental factor ontology // Bioinformatics. 2010. V. 26. N 8. P. 1112–1118. https://doi.org/10.1093/bioinformatics/btq099Malone J., Holloway E., Adamusiak T., Kapushesky M., Zheng J., Kolesnikov N., Zhukova A., Brazma A., Parkinson H. Modeling sample variables with an experimental factor ontology. Bioinformatics, 2010, vol. 26, no. 8, pp. 1112–1118. https://doi.org/10.1093/bioinformatics/btq099Lee J., Yoon W., Kim S., Kim D., Kim S., So C.H., Kang J. BioBERT: a pre-trained biomedical language representation model for biomedical text mining // Bioinformatics. 2020. V. 36. N 4. P. 1234– 1240. https://doi.org/10.1093/bioinformatics/btz682Lee J., Yoon W., Kim S., Kim D., Kim S., So C.H., Kang J. BioBERT: a pre-trained biomedical language representation model for biomedical text mining. Bioinformatics, 2020, vol. 36, no. 4, pp. 1234–1240. https://doi.org/10.1093/bioinformatics/btz682Zhang X., Zou Y., Shi W. Dilated convolution neural network with LeakyReLU for environmental sound classification // Proc. of the 22nd International Conference on Digital Signal Processing (DSP). 2017. https://doi.org/10.1109/ICDSP.2017.8096153Zhang X., Zou Y., Shi W. Dilated convolution neural network with LeakyReLU for environmental sound classification. Proc. of the 22nd International Conference on Digital Signal Processing (DSP), 2017. https://doi.org/10.1109/ICDSP.2017.8096153Piñero J., Queralt-Rosinach N., Bravo A., Deu-Pons J., Bauer- Mehren A., Baron M., Sanz F., Furlong L.I. DisGeNET: A discovery platform for the dynamical exploration of human diseases and their genes // Database. 2015. V. 2015. https://doi.org/10.1093/database/bav028Piñero J., Queralt-Rosinach N., Bravo A., Deu-Pons J., Bauer-Mehren A., Baron M., Sanz F., Furlong L.I. DisGeNET: A discovery platform for the dynamical exploration of human diseases and their genes. Database, 2015, vol. 2015. https://doi.org/10.1093/database/bav028Alam M., Cevallos B., Flores O., Lunetto R., Yayoshi K., Woo J. Yelp Dataset Analysis using Scalable Big Data // arXiv. 2021. arXiv.2104.08396v1. https://doi.org/10.48550/arXiv.2104.08396Alam M., Cevallos B., Flores O., Lunetto R., Yayoshi K., Woo J. Yelp Dataset Analysis using Scalable Big Data. arXiv, 2021, arXiv.2104.08396v1. https://doi.org/10.48550/arXiv.2104.08396Li Y., Guo X., Lin W., Zhong M., Li Q., Liu Z., Zhong W., Zhu Z. Learning dynamic user interest sequence in knowledge graphs for click-through rate prediction // IEEE Transactions on Knowledge and Data Engineering. 2023. V. 35. N 1. P. 647–657. https://doi.org/10.1109/TKDE.2021.3073717Li Y., Guo X., Lin W., Zhong M., Li Q., Liu Z., Zhong W., Zhu Z. Learning dynamic user interest sequence in knowledge graphs for click-through rate prediction. IEEE Transactions on Knowledge and Data Engineering, 2023, vol. 35, no. 1, pp. 647–657. https://doi.org/10.1109/TKDE.2021.3073717Kuo Y., Wang R., Liu G., Shu Z., Wang N., Zhang R., Yu J., Chen J., Li X., Zhou X. HerGePred: Heterogeneous network embedding representation for disease gene prediction // IEEE Journal of Biomedical and Health Informatics. 2019. V. 23. N 4. P. 1805–1815. https://doi.org/10.1109/JBHI.2018.2870728Kuo Y., Wang R., Liu G., Shu Z., Wang N., Zhang R., Yu J., Chen J., Li X., Zhou X. HerGePred: Heterogeneous network embedding representation for disease gene prediction. IEEE Journal of Biomedical and Health Informatics, 2019, vol. 23, no. 4, pp. 1805– 1815. https://doi.org/10.1109/JBHI.2018.2870728Grover A., Leskovec J. node2vec: Scalable feature learning for networks // Proc. of the KDD’16 . International Conference on Knowledge Discovery & Data Mining. 2016. P. 855–864. https://doi.org/10.1145/2939672.2939754Grover A., Leskovec J. node2vec: Scalable feature learning for networks. Proc. of the KDD’16 . International Conference on Knowledge Discovery & Data Mining, 2016, pp. 855–864. https://doi.org/10.1145/2939672.2939754Yuxiao D., Chawla N., Swami A. metapath2vec: Scalable representation learning for heterogeneous networks // Proc. of the KDD’17 . International Conference on Knowledge Discovery & Data Mining. 2017. P 135–144. https://doi.org/10.1145/3097983.3098036Yuxiao D., Chawla N., Swami A. metapath2vec: Scalable representation learning for heterogeneous networks. Proc. of the KDD’17 . International Conference on Knowledge Discovery & Data Mining, 2017, pp 135–144. https://doi.org/10.1145/3097983.3098036Mikolov T., Chen K., Corrado G., Dean J. Efficient estimation of word representations in vector space // Proc. of the Workshop ICLR. 2013.Mikolov T., Chen K., Corrado G., Dean J. Efficient Estimation of Word Representations in Vector Space. Proc. of the Workshop ICLR, 2013.Perozzi B., Al-Rfou R., Skiena S. DeepWalk: Online learning of social representations // Proc. of the KDD’14. 20th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. 2014. P. 701–710. https://doi.org/10.1145/2623330.2623732Perozzi B., Al-Rfou R., Skiena S. DeepWalk: Online learning of social representations. Proc. of the KDD’14. 20th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 2014, pp. 701–710. https://doi.org/10.1145/2623330.2623732Hu Z., Dong Y., Wang K., Sun Y. Heterogeneous graph transformer // Proc. of the WWW ’20. The Web Conference. 2020. P. 2704–2710. https://doi.org/10.1145/3366423.3380027Hu Z., Dong Y., Wang K., Sun Y. Heterogeneous graph transformer. Proc. of the WWW ’20. The Web Conference, 2020, pp. 2704–2710. https://doi.org/10.1145/3366423.3380027He M., Huang C., Liu B., Wang Y., Li J. Factor graph-aggregated heterogeneous network embedding for disease-gene association prediction // BMC Bioinformatics. 2021. V. 22. P. 165. https://doi.org/10.1186/s12859-021-04099-3He M., Huang C., Liu B., Wang Y., Li J. Factor graph-aggregated heterogeneous network embedding for disease-gene association prediction. BMC Bioinformatics, 2021, vol. 22, pp. 165. https://doi.org/10.1186/s12859-021-04099-3

The authors declare that there are no conflicts of interest present.