COMPARISON OF RNA-SEQUENCING AND RPPA DATA FOR CLASSIFICATION OF CANCER SUBTYPES

Abstract

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

Keywords

• Cancer Classification, RNA-Sequencing

KANSER ALT-TÜRLERİNİN SINIFLANDIRILMASI İÇİN RNA-SEKANSLAMA VE RPPA VERİLERİNİN KARŞILAŞTIRILMASI

Abstract

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

Keywords

• Kanser Sınıflandırma, RNA-Sekanslama

References

1. 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
2. Clinical Outcome of Breast Cancer, Nature, Cilt. 415, s. 530-536. DOI: 1038/415530a Predicts Assay to Predict
3. Zhang, Z., Huang, K., Gu, C., Zhao, L., Wang, N., Wang, X., Zhao, D., Zhang, C., Lu, Y., Meng, Y. 2016. Molecular
4. Subtyping of Serous Ovarian Cancer Based on Multi-Omics Data, Sci Rep, Cilt. 1038/srep26001 DOI:
5. 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, Creighton, C.J. 2016. Multilevel Genomics-Based
6. Renal Cell Carcinoma, Cell Rep, Cilt. , Sayı. 10, s. 2476–2489. DOI: 1016/j.celrep.2016.02.024
7. Wang, M., Klevebring, D., Lindberg, K., J., Rantalainen, M. 2016. Determining
8. Breast Cancer Histological Grade From RNA-Sequencing Data, Breast Cancer Res, Cilt. 18, Sayı. 1, s. 48. DOI: 10.1186/s13058-016-0710-8

9. 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
10. Outcome to High Throughput Protein Expression Data Identifies Novel Regulators of Colorectal Adenocarcinoma F1000Research, Cilt. 4, s. 99. DOI: 12688/f1000research.6388.1
11. Cancer Genome Atlas Research Network. 2014. Comprehensive Molecular
12. Adenocarcinoma, Nature, Cilt. 511, Sayı. 7511, s. 543–550. DOI: 1038/nature13385 of Lung
13. Hung, F.H., Chiu, H.W. 2017. Cancer subtype prediction from a pathway- level perspective by using a support vector machine based on integrated gene expression and protein network, Computer Methods and Programs in Biomedicine, Cilt. 141,
14. Sayı. Supplement C, s. 27-34. DOI: 1006/j.cmpb.2017.01.006
15. Kosti, I., Jain, N., Aran, D., Butte, A.J., Sirota, M. 2016. Cross-tissue
16. Analysis of Gene and Protein Expression in Normal and Cancer Tissues, Sci Rep, Cilt. 6, Sayı. 24799, DOI: 10.1038/srep24799
17. Cancer Genome Atlas Research Network. 2017. Integrated genomic and molecular characterization of cervical cancer, Nature, Cilt. 543, s. –384. 1038/nature21386 DOI:
18. 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
19. Cancer Research, Cilt. 6, Sayı. 3, DOI: 21037/tcr.2017.05.15
20. Danaee, P., Ghaein, R., Hendrix, D.A. 2017. A Deep Learning
21. Approach for Cancer Detection and Relevant Proceedings Symposium, 5-8 Ocak, Hawaii-USA, 229. Pacific s. 314. DOI: 1080/10618600.1996.1047471 Mortazavi, A., Williams,
22. B.A., McCue, K., Schaeffer, L., Wold, B. 2008. Mapping and Quantifying
23. Mammalian Transcriptomes by RNA-Seq, Nat Methods, Cilt. 5, Sayı. , s. 628. DOI: 1038/nmeth.1226
24. Li, B., Ruotti, V., Stewart, R.M., Thomson, J.A., Dewey, C.N. 2010. RNA-Seq
25. Estimation With Read Mapping Uncertainty, Bioinformatics, Cilt. 26, Sayı. 4, s. 1093/bioinformatics/btp692 DOI: Cortes, C. Vapnik, V. 1995.
26. Support Vector Networks, Machine Learning, Cilt. 20, s. 1-25. DOI: 1023/A:1022627411411
27. Ho, T.K. 1995. Random Decision
28. Forests, Proceedings of the 3rd International Document Recognition, 278–282. on and Bradley, A.P. 1997. The Use of
29. The Area Under The ROC Curve in The Evaluation of Machine Learning Algorithms, Pattern Recogn, Cilt. 30, Sayı. 7, s. 1145-1159. DOI: 1016/S0031-3203(96)00142-2
30. Maglogiannis, I.G., Karpouzis, K., Wallace, B.A., Soldatos, J. 2007.
31. Emerging Artificial Intelligence Applications 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
32. 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. Support Vector Machines in Biomedical Applications. s. 379–417. Ramanna, S., Jain, L.C., Howlett, R.J. ed. 2013.
33. Emerging Paradigms in Machine Learning, Springer Heidelberg, Germany, 498s. Berlin Boulesteix, A.-L., Janitza, S., Kruppa, J., König, I. R. 2012. Overview Methodology Guidance Computational
34. Bioinformatics, WIREs Data Mining Knowl Discov, Cilt. 2, s. 493– DOI: 10.1002/widm.1072 on and
35. Raponi, M., Zhang, Y., Yu, J., Chen, G., Lee, G., Taylor, J.M., Macdonald, Moskaluk, C., Wang, Y., Beer, D.G. Gene expression signatures for squamous adenocarcinomas of the lung. Cancer Res. Cilt. 66, Sayı. 15, s. 72. CAN-06-1191 D., predicting prognosis cell and DOI: 1158/0008
36. 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 immune- related gene signatures in a neoadjuvant setting of triple- negative breast cancer: relationship to tumor-infiltrating lymphocytes,
37. Breast Cancer Res Treat, Cilt. 151, Sayı. 1007/s10549-015-3438-8 DOI: Faruki, H., Mayhew, G.M.,
38. Serody, J.S., Hayes, D.N., Perou, C.M., Lai-Golgman, Adenocarcinoma and Squamous Cell Carcinoma Gene Expression Subtypes Demonstrate Significant Differences in Tumor Immune Landscape, J of Thoracic Onc, Cilt. , Sayı. 6 s. 943-953. DOI: 1016/j.jtho.2017.03.010 Lung Wilkerson, M.D., Yin, X.,
39. 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 Subtypes Clinically
40. Correspond to Normal Cell Types, Clin Cancer Res. Cilt. 16, Sayı. 19, s. 4875. DOI: 10.1158/1078- CCR-10-0199 Expression Reproducible, Important, and
41. 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. 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. –998. 1002/emmm.201201823 DOI:
42. Sfakianos, G.P., Iversen, E.S., Whitaker, R., Akushevich, L., Schildkraut, J.M., Murphy, S.K., Marks, J.R., Berchuck, A. 2013.
43. Validation of ovarian cancer gene expression signatures for survival and subtype in formalin fixed paraffin Gynecologic Oncology, Cilt. 129, Sayı. tissues, 1016/j.ygyno.2012.12.030 DOI:
44. 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
45. Relevance of Molecular Subtypes in High-Grade Serous Ovarian Cancer, Journal of the National Cancer Institute, Cilt. 106, Sayı. 10. DOI: 1093/jnci/dju249 Therapeutic
46. 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
47. Cross-Population Analysis of High- Grade Serous Ovarian Cancer Supports No More Than Three Subtypes, G3: Genes, Genomes, Genetics, Cilt. 6, Sayı. 12, s. 4097- DOI: 10.1534/g3.116.033514
48. Leong, H. S., Galletta, L., Etemadmoghadam, D., George, J., The Australian Ovarian Cancer Study, Köbel, M., Ramus, S. J., Bowtell, molecular subtype classification of high-grade serous ovarian cancer. J. Pathol., Cilt. 236, s. 272–277. DOI:10.1002/path.4536 Efficient