SavedAdd your journal

Journals / Gazi Üniversitesi Mühendislik Mimarlık Fakültesi Dergisi / 2026 / Cilt: 41 Sayı: 2

Pathogenicity assessment of breast cancer associated BRCA1/2 variants using explainable machine learning approach

Açıklanabilir makine öğrenimi yaklaşımı kullanılarak meme kanseriyle ilişkili BRCA1/2 varyantlarının patojenite değerlendirmesi

Burak Kolukısa(Kayseri University)0000-0003-0423-4595
Pages
1117–1128
Publication Date
2026-07-20
🏛️Bibliographic metadata and full text access for this article are provided via DergiPark.
DergiPark Record ↗
✨

AI Summary & Key Takeaways

AI Insight
⚡ TL;DR(Too Long; Didn't Read)

These findings suggest that machine learning–based approaches can serve as scalable and clinically meaningful tools for the interpretation of BRCA1/2 variants.

📌 3 Key Takeaways

🎯
Objective & Hypothesis:Breast cancer is the most common type of cancer in women worldwide and represents a heterogeneous group of diseases resulting from the interaction of genetic and environmental factors.
📊
Key Findings & Data:Pathogenic mutations in the BRCA1/2 genes significantly increase lifetime breast cancer risk, highlighting the critical role of genetic testing in early diagnosis and preventive strategies.
💡
Conclusion & Impact:These findings suggest that machine learning–based approaches can serve as scalable and clinically meaningful tools for the interpretation of BRCA1/2 variants.
🔬Design:Modeling & Simulation
📍Scope:Comprehensive Sample
⚙️Variables:Makine öğrenimi · Bayes optimizasyonu · Açıklanabilir Yapay Zeka

Abstract

Breast cancer is the most common type of cancer in women worldwide and represents a heterogeneous group of diseases resulting from the interaction of genetic and environmental factors. Pathogenic mutations in the BRCA1/2 genes significantly increase lifetime breast cancer risk, highlighting the critical role of genetic testing in early diagnosis and preventive strategies. This study aimed to evaluate the pathogenicity of BRCA1/2 variants using machine learning algorithms. During model development, a comprehensive dataset comprising 32,719 BRCA1/2 variants was obtained from the ClinVar database. The dataset was systematically collected, preprocessed and analyzed within a multi-class classification framework (benign, likely benign, variant of uncertain significance, likely pathogenic, pathogenic). Seven different supervised classification algorithms were applied, and the best-performing model, Extreme Gradient Boosting (XGBoost), was trained using Bayesian optimization under 10-fold stratified cross-validation. The XGBoost model achieved the highest performance, with an accuracy of 96.12% and a weighted-F1 score of 95.67%. Furthermore, analyses with explainable artificial intelligence methods demonstrated which features the model relied on for classification decisions and highlighted the criteria with the greatest contribution. These findings suggest that machine learning–based approaches can serve as scalable and clinically meaningful tools for the interpretation of BRCA1/2 variants.

Özet

Meme kanseri, dünya genelinde kadınlarda en sık görülen kanser türüdür ve genetik ile çevresel faktörlerin etkileşimi sonucu ortaya çıkan heterojen bir hastalık grubunu temsil etmektedir. BRCA1/2 genlerindeki patojenik mutasyonlar, yaşam boyu meme kanseri riskini önemli ölçüde artırmakta ve bu durum, erken tanı ile önleyici stratejilerde genetik testlerin kritik rolünü vurgulamaktadır. Bu çalışmada, BRCA1/2 varyantlarının patojenitesinin makine öğrenimi algoritmaları kullanılarak değerlendirilmesi amaçlanmıştır. Model geliştirme sürecinde, BRCA1/2 genlerine ait 32.719 varyant içeren kapsamlı bir veri seti ClinVar veritabanından elde edilmiştir. Veri seti sistematik olarak hazırlanmış, ön işleme uygulanmış ve çoklu sınıflandırma (iyi huylu, muhtemel iyi huylu, belirsiz öneme sahip varyant, muhtemel patojenik, patojenik) çerçevesinde analiz edilmiştir. Yedi farklı denetimli sınıflandırma algoritması uygulanmış, en iyi performansı gösteren Aşırı Gradyan Artırma (AGA) modeli ise 10-katlı tabakalı çapraz doğrulama altında Bayes optimizasyonu ile çalıştırılmıştır. AGA modeli %96,12 doğruluk ve %95,67 ağırlıklı-F1 skoru ile en yüksek başarıyı elde etmiştir. Açıklanabilir yapay zekâ yöntemiyle yapılan analizler, modelin sınıflandırma kararlarını hangi özelliklere dayandırdığını ve en yüksek katkıyı sunan kriterlerin öne çıktığını göstermektedir. Bulgular, makine öğrenimi tabanlı yaklaşımların BRCA1/2 varyant yorumlamasında ölçeklenebilir ve klinik açıdan anlamlı araçlar olarak kullanılabileceğini göstermektedir.

🔖

Cite This Article

Kolukısa, B. (2026). Pathogenicity assessment of breast cancer associated BRCA1/2 variants using explainable machine learning approach. Gazi Üniversitesi Mühendislik Mimarlık Fakültesi Dergisi, Cilt: 41 Sayı: 2, 1117–1128. https://doi.org/10.17341/gazimmfd.1781575

📄 Full Text PDF Viewer

📄

PDF görüntüleyici hazırlanıyor...

References (36)

  1. Xu H, Xu B. Breast cancer: Epidemiology, risk factors and screening. Chin J Cancer Res., 35(6), 565-583, 2023.
  2. ⁠Polyak K., Heterogeneity in breast cancer, J. Clin. Invest., 121 (10), 3786–3788, 2011.
  3. Arnold M., Morgan E., Rumgay H., Mafra A., Singh D., Laversanne M., Vignat J., Gralow J.R., Cardoso F., Siesling S., Soerjomataram I., Current and future burden of breast cancer: Global statistics for 2020 and 2040, Breast, 66, 15–23, 2022.
  4. Sung H., Ferlay J., Siegel R.L., Laversanne M., Soerjomataram I., Jemal A., Bray F., Global cancer statistics 2020: GLOBOCAN estimates of incidence and mortality worldwide for 36 cancers in 185 countries, CA Cancer J. Clin., 71 (3), 209–249, 2021.
  5. Etcil, M., Dedeturk, B. K., Kolukisa, B., Bakir‐Gungor, B., & Gungor, V. C., Breast Cancer Detection Using a New Parallel Hybrid Logistic Regression Model Trained by Particle Swarm Optimization and Clonal Selection Algorithms. Concurrency and Computation: Practice and Experience, 37 (12-14), e70107, 2025.
  6. ⁠Sanguinetti A., Polistena A., Lucchini R., Monacelli M., Galasse S., Avenia S., Triola R., Monacelli A., Avenia N., Male breast cancer, clinical presentation, diagnosis and treatment: Twenty years of experience in our Breast Unit, Int. J. Surg. Case Rep., 20 (Suppl), 8–11, 2016.
  7. Huang A., Li D., Fan Z., Chen J., Zhang W., Wu W., Long-term trends in the incidence of male breast cancer and nomogram for predicting survival in male breast cancer patients: a population-based epidemiologic study, Scientific Reports, 15, 2027, 2025.
  8. ⁠Karami F., Mehdipour P., A comprehensive focus on global spectrum of BRCA1 and BRCA2 mutations in breast cancer, Biomed. Res. Int., 2013 (1), 928562, 2013.
  9. Vatsyayan A., Scaria V., Machine learning approach to assess the pathogenicity of BRCA1/2 genetic variants: brca-NOVUS, medRxiv, 2023-10, 2023.
  10. Miki, Y., Swensen, J., Shattuck-Eidens, D., Futreal, P. A., Harshman, K., Tavtigian, S., Liu, Q., Cochran, C., Bennett, L. M., & Ding, W., A strong candidate for the breast and ovarian cancer susceptibility gene BRCA1, Science, 266 (5182), 66–71, 1994. 11. Richards S., Aziz N., Bale S., Bick D., Das S., Gastier-Foster J., Grody W.W., Hegde M., Lyon E., Spector E., Voelkerding K., Rehm H.L., Standards and guidelines for the interpretation of sequence variants: A joint consensus recommendation of the American College of Medical Genetics and Genomics and the Association for Molecular Pathology, Genet. Med., 17 (5), 405–423, 2015.
  11. Nicora G., Zucca S., Limongelli I., Bellazzi R., Magni P., A machine learning approach based on ACMG/AMP guidelines for genomic variant classification and prioritization, Sci. Rep., 12 (1), 2517, 2022.
  12. Vatsyayan A., Kumar M., Saikia B.J., Scaria V., BK B., WilsonGenAI: A deep learning approach to classify pathogenic variants in Wilson disease, PLoS One, 19 (5), e0303787, 2024.
  13. Adzhubei I., Jordan D.M., Sunyaev S.R., Predicting functional effect of human missense mutations using PolyPhen-2, Curr. Protoc. Hum. Genet., 76 (1), 7–20, 2013.
  14. Rentzsch P., Witten D., Cooper G.M., Shendure J., Kircher M., CADD: Predicting the deleteriousness of variants throughout the human genome, Nucleic Acids Res., 47 (D1), D886–D894, 2019.
  15. Niroula A., Vihinen M., How good are pathogenicity predictors in detecting benign variants?, PLoS Comput. Biol., 15 (2), e1006481, 2019.
  16. Ernst C., Hahnen E., Engel C., Nothnagel M., Weber J., Schmutzler R.K., Hauke J., Performance of in silico prediction tools for the classification of rare BRCA1/2 missense variants in clinical diagnostics, BMC Med. Genomics, 11 (1), 35, 2018.
  17. Bai K., Yang L., Xue J., Zhao L., Hao F., Pathogenicity classification of missense mutations based on deep generative model, Comput. Biol. Med., 170, 107980, 2024.
  18. Kang M., Kim S., Lee D.B., Hong C., Hwang K.B., Gene-specific machine learning for pathogenicity prediction of rare BRCA1 and BRCA2 missense variants, Sci. Rep., 13 (1), 10478, 2023.
  19. Ansari, Z. A., Tripathi, M. M., Ahmed, R., The role of explainable AI in enhancing breast cancer diagnosis using machine learning and deep learning models. Discover Artificial Intelligence, 5 (1), 75, 2025.
  20. Güler, H., Avcı, D., Ulaş, M., Omma, T., In-depth analysis of machine learning models and explainable artificial intelligence methods in diabetes diagnosis. Journal of the Faculty of Engineering and Architecture of Gazi University, 40 (3), 1995–2012, 2025.
  21. Karczewski K.J., Francioli L.C., Tiao G., Cummings B.B., Alfoldi J., Wang Q., Collins R.L., Laricchia K.M., Ganna A., Birnbaum D.P., … MacArthur D.G., The mutational constraint spectrum quantified from variation in 141,456 humans, Nature, 581 (7809), 434–443, 2020.
  22. Li C., Zhi D., Wang K., Liu X., MetaRNN: Differentiating rare pathogenic and rare benign missense SNVs and InDels using deep learning, Genome Med., 14 (1), 115, 2022.
  23. Ioannidis N.M., Rothstein J.H., Pejaver V., Middha S., McDonnell S.K., Baheti S., Musolf A., Li Q., Holzinger E., Karyadi D., … Cooney K.A., REVEL: An ensemble method for predicting the pathogenicity of rare missense variants, Am. J. Hum. Genet., 99 (4), 877–885, 2016.
  24. Quang D., Chen Y., Xie X., DANN: A deep learning approach for annotating the pathogenicity of genetic variants, Bioinformatics, 31 (5), 761–763, 2014.
  25. Shihab H.A., Gough J., Cooper D.N., Stenson P.D., Barker G.L., Edwards K.J., Day I.N.M., Gaunt T.R., Predicting the functional, molecular, and phenotypic consequences of amino acid substitutions using hidden Markov models, Hum. Mutat., 34 (1), 57–65, 2013.
  26. Adzhubei I.A., Schmidt S., Peshkin L., Ramensky V.E., Gerasimova A., Bork P., Kondrashov A.S., Sunyaev S.R., A method and server for predicting damaging missense mutations, Nat. Methods, 7 (4), 248–249, 2010.
  27. Ng P.C., Henikoff S., SIFT: Predicting amino acid changes that affect protein function, Nucleic Acids Res., 31 (13), 3812–3814, 2003.
  28. Wu Y., Liu H., Li R., Sun S., Weile J., Roth F.P., Improved pathogenicity prediction for rare human missense variants, Am. J. Hum. Genet., 108 (10), 1891–1906, 2021.
  29. Cheng J., Novati G., Pan J., Bycroft C., Zemgulyte A., Applebaum T., Treiber M., Logan B., Yeager C., Leong J., Raghavan M., Taylor-Weiner A., Parker M., Esteban O., Salvatore M., Persikov A., Durbin R., Avsec Ž., Accurate proteome-wide missense variant effect prediction with AlphaMissense, Science, 381 (6664), eadg7492, 2023.
  30. Landrum M.J., Lee J.M., Benson M., Brown G., Chao C., Chitipiralla S., Gu B., Hart J., Hoffman D., Hoover J., Jang W., Katz K., Ovetsky M., Riley G., Sethi A., Tully R., Villamarin-Salomon R., Rubinstein W., Maglott D.R., ClinVar: Public archive of interpretations of clinically relevant variants, Nucleic Acids Res., 44 (D1), D862–D868, 2016.
  31. McLaren W., Gil L., Hunt S.E., Riat H.S., Ritchie G.R., Thormann A., Flicek P., Cunningham F., The Ensembl Variant Effect Predictor, Genome Biol., 17 (1), 122, 2016.
  32. Landrum, M. J., Chitipiralla, S., Kaur, K., Brown, G., Chen, C., Hart, J.,. & Kattman, B. L., ClinVar: updates to support classifications of both germline and somatic variants. Nucleic Acids Research, 53 (D1), D1313-D1321, 2025.
  33. Pedregosa F., Varoquaux G., Gramfort A., Michel V., Thirion B., Grisel O., Blondel M., Prettenhofer P., Weiss R., Dubourg V., VanderPlas J., Passos A., Cournapeau D., Brucher M., Perrot M., Duchesnay É., Scikit-learn: Machine learning in Python, J. Mach. Learn. Res., 12, 2825–2830, 2011.
  34. Snoek J., Larochelle H., Adams R.P., Practical Bayesian optimization of machine learning algorithms, Adv. Neural Inf. Process. Syst., 25, 2951–2959, Lake Tahoe, Nevada, USA, 2012.
  35. ⁠Lundberg S.M., Lee S.I., A unified approach to interpreting model predictions, Adv. Neural Inf. Process. Syst., 30, 4765–4774, Long Beach, CA, USA, 2017.
  36. Landrum, M. J., Chitipiralla, S., Kaur, K., Brown, G., Chen, C., Hart, J.,. & Kattman, B. L., ClinVar: updates to support classifications of both germline and somatic variants. Nucleic Acids Research, 53 (D1), D1313-D1321, 2025.