Kanser Alt-Türlerinin Sınıflandırılması İçin RNA-Sekanslama ve RPPA Verilerinin Karşılaştırılması

Hastaların kanser alt-türlerini henüz ameliyat olmadan kesin doğrulukla tespit edilebilmek, tanı ve tedavi masraflarının azaltılmasını sağlayacaktır. Bu çalışmanın amacı, over ya da akciğer kanseri olduğu tespit edilen bir hastanın kanser alt-türünü tespit edebilecek belirli sayıdaki biyoişaretin makine öğrenmesi yöntemleriyle bulunmasıdır. Bu amaçla, mRNA gen ekspresyon ve protein seviyesi bilgileri kullanılarak kısıtlı sayıda öz-nitelik seçilmiş, bu öz-niteliklerle gözetimli makine öğrenmesi metotları eğitilmiş, bu modeller ile yeni gelen bir hastanın kanser alt-türü tahmin edilmiştir. Destek vektör makineleri ve rastgele orman algoritmaları, yeni kanser hastalarının kanser alt-türlerini ortalama %87 ile %95 arasında değişen doğruluk dereceleriyle sınıflandırabilmiştir. mRNA gen ekspresyon verisi protein seviyesi verisine göre, her iki kanser türünde de daha başarılı sınıflandırma sonuçları sağlamıştır.

Comparison of RNA-Sequencing and RPPA Data for Classification of Cancer Subtypes

Accurate identification of cancer subtypes of patients before their surgery will decrease diagnostic and treatment costs. The goal of this study is the identification of a limited number of biomarkers, which can predict subtypes of cancer patients who were diagnosed as lung or ovarian cancer, by using machine learning methods. For this purpose, a limited number of features were selected by using gene expression and protein level data, then supervised machine learning methods were trained with selected features, cancer subtype of a new patient was predicted by using these models. Support vector machines and random forest algorithms can classify cancer subtypes of new patients with the average accuracies of 87% - 95%. mRNA gene expression data provided the better classification results compared to the protein level data.

PDF

___

van't Veer, L.J., Dai, H., van de Vijver, M.J., He, Y.D., Hart, A.A., Mao, M., Peterse, H.L., van der Kooy, K., Marton, M.J., Witteveen, A.T., Schreiber, G.J., Kerkhoven, R.M., Roberts, C., Linsley, P.S., Bernards, R., Friend, S.H. 2002. Gene Expression Profiling Predicts Clinical Outcome of Breast Cancer, Nature, Cilt. 415, s. 530-536. DOI: 10.1038/415530a
Paik, S., Shak, S., Tang, G., Kim, C., Baker, J., Cronin, M., Baehner, F.L., Walker, M.G., Watson, D., Park, T., Hiller, W., Fisher, E.R., Wickerham, D.L., Bryant, J., Wolmark, N. 2004. A Multigene Assay to Predict Recurrence of Tamoxifen-Treated, Node-Negative Breast Cancer, N Engl J Med, Cilt. 351, s. 2817-2826. DOI: 10.1056/NEJMoa041588
Zhang, Z., Huang, K., Gu, C., Zhao, L., Wang, N., Wang, X., Zhao, D., Zhang, C., Lu, Y., Meng, Y. 2016. Molecular Subtyping of Serous Ovarian Cancer Based on Multi-Omics Data, Sci Rep, Cilt. 6, s. 26001. DOI: 10.1038/srep26001
Chen, F., Zhang, Y., Şenbabaoğlu, Y., Ciriello, G., Yang, L., Reznik, E., Shuch, B., Micevic, G., De Velasco, G., Shinbrot, E., Noble, M.S., Lu, Y., Covington, K.R., Xi, L., Drummond, J.A., Muzny, D., Kang, H., Lee, J., Tamboli, P., Reuter, V., Shelley, C.S., Kaipparettu, B.A., Bottaro, D.P., Godwin, A.K., Gibbs, R.A., Getz, G., Kucherlapati, R., Park, P.J., Sander, C., Henske, E.P., Zhou, J.H., Kwiatkowski, D.J., Ho, T.H., Choueiri, T.K., Hsieh, J.J., Akbani, R., Mills, G.B., Hakimi, A.A., Wheeler, D.A., Creighton, C.J. 2016. Multilevel Genomics-Based Taxonomy of Renal Cell Carcinoma, Cell Rep, Cilt. 14, Sayı. 10, s. 2476–2489. DOI: 10.1016/j.celrep.2016.02.024
Wang, M., Klevebring, D., Lindberg, J., Czene, K., Grönberg, H., Rantalainen, M. 2016. Determining Breast Cancer Histological Grade From RNA-Sequencing Data, Breast Cancer Res, Cilt. 18, Sayı. 1, s. 48. DOI: 10.1186/s13058-016-0710-8
French, C.L., Ye, F., Revetta, F., Zhang, B., Coffey, R.J., Washington, M.K., Deane, N.G., Beauchamp, R.D., Weaver, A.M. 2015. Linking Patient Outcome to High Throughput Protein Expression Data Identifies Novel Regulators of Colorectal Adenocarcinoma Aggressiveness, F1000Research, Cilt. 4, s. 99. DOI: 10.12688/f1000research.6388.1
Cancer Genome Atlas Research Network. 2014. Comprehensive Molecular Profiling of Lung Adenocarcinoma, Nature, Cilt. 511, Sayı. 7511, s. 543–550. DOI: 10.1038/nature13385
Hung, F.H., Chiu, H.W. 2017. Cancer subtype prediction from a pathwaylevel perspective by using a support vector machine based on integrated gene expression and protein network, Computer Methods and Programs in Biomedicine, Cilt. 141, Sayı. Supplement C, s. 27-34. DOI: 10.1006/j.cmpb.2017.01.006
Kosti, I., Jain, N., Aran, D., Butte, A.J., Sirota, M. 2016. Cross-tissue Analysis of Gene and Protein Expression in Normal and Cancer Tissues, Sci Rep, Cilt. 6, Sayı. 24799, DOI: 10.1038/srep24799
Cancer Genome Atlas Research Network. 2017. Integrated genomic and molecular characterization of cervical cancer, Nature, Cilt. 543, s. 378–384. DOI: 10.1038/nature21386
Gao, S., Qiu, Z., Song, Y., Mo, C., Tan, W., Chen, Q., Liu, D., Chen, M., Zhou H. 2017. Unsupervised clustering reveals new prostate cancer subtypes, Translational Cancer Research, Cilt. 6, Sayı. 3, DOI: 10.21037/tcr.2017.05.15
Danaee, P., Ghaein, R., Hendrix, D.A. 2017. A Deep Learning Approach for Cancer Detection and Relevant Gene Identification. Proceedings of the Pacific Symposium, 5-8 Ocak, Hawaii-USA, 219-229.
The Cancer Genome Atlas. 2007. https://cancergenome.nih.gov/ (Erişim tarihi: 07.07.2016).
Özkan, S., Keskinkılıç, B., Gültekin, M., Karaca, AS., Öztürk, C., Boztaş, G. 2014. T.C. Sağlık Bakanlığı Türkiye Halk Sağlığı Kurumu. Ulusal kanser kontrol planı 2013-2018. Sağlık Bakanlığı Yayınları.
Cancer Genome Atlas Research Network. 2011. Integrated Genomic Analyses of Ovarian Carcinoma, Nature, Cilt. 474, Sayı. 7353, s. 609– 615. DOI: 10.1038/nature10166 [
Ihaka, R., Gentleman, R. 1996. R: A Language for Data Analysis and Graphics, Journal of Computational and Graphical Statistics, Cilt. 5, Sayı 3, s. 299-314. DOI: 10.1080/10618600.1996.1047471 3
Mortazavi, A., Williams, B.A., McCue, K., Schaeffer, L., Wold, B. 2008. Mapping and Quantifying Mammalian Transcriptomes by RNA-Seq, Nat Methods, Cilt. 5, Sayı. 7, s. 621-628. DOI: 10.1038/nmeth.1226
Li, B., Ruotti, V., Stewart, R.M., Thomson, J.A., Dewey, C.N. 2010. RNA-Seq Gene Expression Estimation With Read Mapping Uncertainty, Bioinformatics, Cilt. 26, Sayı. 4, s. 493-500. DOI: 10.1093/bioinformatics/btp692
Cortes, C. Vapnik, V. 1995. Support Vector Networks, Machine Learning, Cilt. 20, s. 1-25. DOI: 10.1023/A:1022627411411
Ho, T.K. 1995. Random Decision Forests, Proceedings of the 3rd International Conference on Document Analysis and Recognition, 278–282.
Bradley, A.P. 1997. The Use of The Area Under The ROC Curve in The Evaluation of Machine Learning Algorithms, Pattern Recogn, Cilt. 30, Sayı. 7, s. 1145-1159. DOI: 10.1016/S0031-3203(96)00142-2 [
Maglogiannis, I.G., Karpouzis, K., Wallace, B.A., Soldatos, J. 2007. Emerging Artificial Intelligence Applications in Computer Engineering : Real Word AI Systems with Applications in EHealth, HCI, Information Retrieval and Pervasive Technologies, 1st edition, IOS Press, Washington, DC, 408s.
Dietterich, T.G. 2000. Ensemble Methods in Machine Learning, The First International Workshop on Multiple Classifier Systems, 21-23 Haziran, İtalya, 1-15.
Cyran, K.A., Kawulok, J., Kawulok, M., Stawarz, M., Michalak, M., Pietrowska, M., Polańska, J. 2013. Support Vector Machines in Biomedical and Biometrical Applications. s. 379–417. Ramanna, S., Jain, L.C., Howlett, R.J. ed. 2013. Emerging Paradigms in Machine Learning, Springer Berlin Heidelberg, Germany, 498s.
Boulesteix, A.-L., Janitza, S., Kruppa, J., König, I. R. 2012. Overview of Random Forest Methodology and Practical Guidance With Emphasis on Computational Biology and Bioinformatics, WIREs Data Mining Knowl Discov, Cilt. 2, s. 493– 507. DOI: 10.1002/widm.1072 [
Raponi, M., Zhang, Y., Yu, J., Chen, G., Lee, G., Taylor, J.M., Macdonald, J., Thomas, D., Moskaluk, C., Wang, Y., Beer, D.G. 2006. Gene expression signatures for predicting prognosis of squamous cell and adenocarcinomas of the lung. Cancer Res. Cilt. 66, Sayı. 15, s. 7466-72. DOI: 10.1158/00085472.CAN-06-1191
Lee, H.J., Lee, J.J., Song, I.H., Park, I.H., Kang, J., Yu, J.H., Ahn, J.H., Gong, G. 2015. Prognostic and predictive value of NanoString-based immunerelated gene signatures in a neoadjuvant setting of triplenegative breast cancer: relationship to tumor-infiltrating lymphocytes, Breast Cancer Res Treat, Cilt. 151, Sayı. 3. S. 619-627. DOI: 10.1007/s10549-015-3438-8
Faruki, H., Mayhew, G.M., Serody, J.S., Hayes, D.N., Perou, C.M., Lai-Golgman, M. 2017. Lung Adenocarcinoma and Squamous Cell Carcinoma Gene Expression Subtypes Demonstrate Significant Differences in Tumor Immune Landscape, J of Thoracic Onc, Cilt. 12, Sayı. 6 s. 943-953. DOI: 10.1016/j.jtho.2017.03.010
Wilkerson, M.D., Yin, X., Hoadley, K.A., Liu, Y., Hayward, M.C., Cabanski, C.R., Muldrew, K., Miller, C.R., Randell, S.H., Socinski, M.A., Parsons, A.M., Funkhouser, W.K., Lee, C.B., Roberts, P.J., Thorne, L., Bernard, P.S., Perou, C.M., Hayes, D.N. 2010. Lung Squamous Cell Carcinoma mRNA Expression Subtypes Are Reproducible, Clinically Important, and Correspond to Normal Cell Types, Clin Cancer Res. Cilt. 16, Sayı. 19, s. 4864-4875. DOI: 10.1158/10780432.CCR-10-0199
Verhaak, R.G., Tamayo, P., Yang, J.Y., Hubbard, D., Zhang, H., Creighton, C.J., Fereday, S., Lawrence, M., Carter, S.L., Mermel, C.H., Kostic, A.D., Etemadmoghadam, D., Saksena, G., Cibulskis, K., Duraisamy, S., Levanon, K., Sougnez, C., Tsherniak, A., Gomez, S., Onofrio, R., Gabriel, S., Chin, L., Zhang, N., Spellman, P.T., Zhang, Y., Akbani, R., Hoadley, K.A., Kahn, A. Kobel, M., Huntsman, D., Soslow, R.A., Defazio, A., Birrer, M.J., Gray, J.W., Weinstein, J.N., Bowtell, D.D., Drapkin, R., Mesirov, J.P., Getz, G., Levine, D.A., Meyerson, M., Cancer Genome Atlas Research Network. 2013. Prognostically relevant gene signatures of highgrade serous ovarian carcinoma, J. Clin. Invest., Cilt. 123, Sayı. 1, s. 517525. DOI: 10.1172/JCI65833
Tan, T. Z., Miow, Q. H., Huang, R. Y.-J., Wong, M. K., Ye, J., Lau, J. A., Wu, M.C., Hadi, L.H.B.A., Soong, R., Choolani, M., Davidson, B., Nesland J.M., Wang, L.Z., Matsumura, N., Mandai, M., Konishi, I., Goh, B.C., Chang, J.T., Thiery, J.P., Mori, S. 2013. Functional genomics identifies five distinct molecular subtypes with clinical relevance and pathways for growth control in epithelial ovarian cancer. EMBO Molecular Medicine, Cilt. 5, Sayı. 7, s. 983–998. DOI: 10.1002/emmm.201201823 [
Sfakianos, G.P., Iversen, E.S., Whitaker, R., Akushevich, L., Schildkraut, J.M., Murphy, S.K., Marks, J.R., Berchuck, A. 2013. Validation of ovarian cancer gene expression signatures for survival and subtype in formalin fixed paraffin embedded tissues, Gynecologic Oncology, Cilt. 129, Sayı. 1, s. 159-164. DOI: 10.1016/j.ygyno.2012.12.030
Konecny, G.E., Wang, C., Hamidi, H., Winterhoff, B., Kalli, K.R., Dering, J., Ginther, C., Chen, H.W., Dowdy, S., Cliby, W., Gostout, B., Podratz, K.C., Keeney, G., Wang, H.J., Hartmann, L.C., Slamon, D.J., Goode, E.L. 2014. Prognostic and Therapeutic Relevance of Molecular Subtypes in High-Grade Serous Ovarian Cancer, Journal of the National Cancer Institute, Cilt. 106, Sayı. 10. DOI: 10.1093/jnci/dju249
Way, G.P., Rudd, J., Wang, C., Hamidi, H., Fridley, B.L., Konecny, G.E., Goode E.L., Greene, C.S., Doherty, J.A. 2016. Comprehensive Cross-Population Analysis of HighGrade Serous Ovarian Cancer Supports No More Than Three Subtypes, G3: Genes, Genomes, Genetics, Cilt. 6, Sayı. 12, s. 40974103. DOI: 10.1534/g3.116.033514
Leong, H. S., Galletta, L., Etemadmoghadam, D., George, J., The Australian Ovarian Cancer Study, Köbel, M., Ramus, S. J., Bowtell, D. 2015. Efficient molecular subtype classification of high-grade serous ovarian cancer. J. Pathol., Cilt. 236, s. 272–277. DOI:10.1002/path.4536