Kütle Spektrometresi Verileri Kullanılarak Yumurtalık Kanserinin Yapay Sinir Ağlarıyla Sınıflandırılması

Year 2021, Volume: 36 Issue: 3, 781 - 790, 30.09.2021

Demet Yeşilbaş , Ayşegül Güven

https://doi.org/10.21605/cukurovaumfd.1005791

Cited By: 1

Abstract

Kanserin fark edilme aşaması, diğer kanser türlerinde olduğu gibi iyileşme oranını etkiler. Yaşı ilerlemiş kadınlar için ciddi bir hastalık olan yumurtalık kanseri başlangıç aşamasında fark edilmez, çoğu zaman diğer hastalıklarla karıştırılır. Yüzey Güçlendirmeli Lazer Desorpsiyon/İyonizasyon Uçuş Zamanlı Kütle Spektrometresi (SELDI-TOF-MS) kompleks numunelerin incelenmesine olanak sağlayarak yumurtalık ve diğer kanser türlerinin ayırt edilmesinde potansiyel belirteçtir. Bu çalışmada, FDA-NCI web sitesinde yer alan yumurtalıklara ait iki Düşük Çözünürlüklü SELDI-TOF-MS veri setini Yapay Sinir Ağları (YSA) ile sınıflandırarak, veri setlerini karşılaştırıyoruz. Ön işleme adımı olarak, Temel Bileşenler Analizi (PCAPrincipal Component Analysis) kullandık. PCA uygulanmış verinin en yüksek varyans oranına sahip 20 bileşeni seçildi, 10 nörondan oluşan tek gizli katmanlı İleri Yönlü YSA ile sınıflandırma yapıldı ve 4-3-02
isimli veri seti için %95 doğruluk elde edilirken, 8-7-02 isimli veri seti için %100 doğruluk elde edilmiştir

Keywords

Yapay sinir ağları, Temel bileşenler analizi, Yumurtalık kanseri, SELDI-TOF-MS

Classification of Ovarian Cancer with Neural Networks Using Mass Spectrometry Data

Abstract

The stage of cancer diagnosis affects the rate of recovery, as in other types of cancer. Ovarian cancer is a serious disease for older women, is not noticed at the initial stage and is often confused with other diseases. Surface-Enhanced Laser Desorption/Ionization Time-of-Flight Mass Spectrometry (SELDITOF-MS) is a potential biomarker for distinguishing ovarian and other types of cancer by allowing the examination of complex samples. In this study, we classified two Low-Resolution SELDI-TOF-MS ovarian datasets from the FDA-NCI website with Artificial Neural Networks (ANN) and compared them. We used Principal Component Analysis (PCA) as a preprocessing step of classification. 20 components of maximum variance in the PCA-applied data are selected and classified with the feed-forward ANN consists of a single hidden layer with 10 neurons, 95% accuracy was achieved for the data set named 4-3- 02 and 100% accuracy achieved for the data set named 8-7-02.

Keywords

Artificial neural networks, Principal components analysis, Ovarian cancer, SELDI-TOF-MS

References

• 1. Global Cancer Observatory: Cancer Today: International Agency for Research on Cancer. https://gco.iarc.fr/today, Erişim Tarihi: 24.02.2021, 2020, Lyon, Fransa.
• 2. Global Cancer Observatory: Cancer nTomorrow. Lyon, Fransa: International Agency for Research on Cancer. https://gco.iarc.fr/tomorrow, Erişim Tarihi 24.02.2021, 2020, Lyon, Fransa.
• 3. Hamidou, Z., Causeret, S., Dabakuyo, T.S., Gentil, J., Arnould, L., Roignot, P., Altwegg,T., Poillot, M.L., Bonnetain, F., Arveux, P.,2010. Population-based Study of Ovarian Cancer in Côte d'Or: Prognostic Factors and Trends in Relative Survival Rates Over theLast 20 Years. BMC Cancer, 10, 622.
• 4. Torre, L.A., Trabert, B., DeSantis, C.E., Miller,K.D., Samimi, G., Runowicz, C.D., Gaudet, M.M., Jemal, A., Siegel, R.L., 2018. Ovarian Cancer Statistics. CA: A Cancer Journal forClinicians, 68, 284-296.
• 5. Jacobs, I.J., Menon, U., 2004. Progress and Challenges in Screening for Early Detection of Ovarian Cancer. Molecular & Cellular Proteomics, 3(4), 355-366.
• 6. Zhang, D.Y., Ye, F., Gao, L., Liu, X., Zhao, X., Che, Y., Wang, H., Wang, L., Wu, J., Song, D., Liu, W., Xu, H., Jiang, B., Zhang, W., Wang, J., Lee, P., 2009. Proteomics, Pathway Array and Signaling Network-based Medicinein Cancer. Cell Div., 4, 20.
• 7. Hood, L.E., Omenn, G.S., Moritz, R.L., Aebersold, R., Yamamoto, K.R., Amos, M.,Hunter-Cevera, J., Locascio, L., 2012. New and Improved Proteomics Technologies for Understanding Complex Biological Systems: Addressing a Grand Challenge in the life Sciences. Proteomics, 12, 2773-2783.
• 8. Shruthi, B., Vinodhkumar, P., Selvamani, M., 2016. Proteomics: A New Perspective for Cancer. Adv. Biomed. Res. 5, 67.
• 9. Taşkın, V., Doğan, B., Ölmez, T., 2012. Yumurtalık Kanserinin Kütle Spektrometresi Verilerinden Kısmi En Küçük Kareler Yöntemi ile Teşhisi. Biyomedikal Mühendisliği Ulusal Toplantısı (BİYOMUT), 151-154, İstanbul.
• 10.Issaq, H.J., Veenstra, T.D., Conrads, T.P., Felschow, D., 2002. The SELDI-TOF MS Approach to Proteomics: Protein Profiling and Biomarker Identification. Biochemical and Biophysical Research Communications, 292(3), 587-592.
• 11. Poon, T.C., 2007. Opportunities and Limitations of SELDI-TOF-MS in Biomedical Research: Practical Advices. Expert Review of Proteomics, 4(1), 51-65.
• 12. Muthu, M., Vimala, A., Mendoza, O.H., Gopal, J., 2016. Tracing the Voyage of SELDI-TOF MS in Cancer Biomarker Discovery and its Current Depreciation Trend-need for Resurrection? TrAC Trends in Analytical Chemistry, 76, 95-101.
• 13. Tang, K.L., Li, T.H., Xiong, W.W., Chen, K., 2010. Ovarian Cancer Classification Based on Dimensionality Reduction for SELDI-TOF Data. BMC Biyoinformatik 11, 109.
• 14.Bougioukos, P., Cavouras, D., Daskalakia, A., Kossida, S., Nikiforidia, G., Bezezerianos, A., 2006. Feature Extraction and Analysis of Prostate Cancer Proteomic Mass Spectra for Biomarkers Discovery. General Secretariat for Research and Technology, 1.
• 15. Hu, Q.Y., Wang, K.Z., Ding, Y.H., Zheng, L.F., Liang, S.H., Lei, Z.M., Fu, W.G., Yan, L., 2010. Application of SELDI-TOF-MS Coupled with an Artificial Neural Network Model to the Diagnosis of Pancreatic Cancer. Laboratory Medicine, 41(11), 676–681.
• 16. Wegdam, W., Moerland, P.D., Meijer, D., Jong, S.M de., Hoefsloot H.C.J., Kenter, G.G., Buist, M.R., Aerts, J.MF.G., 2012. A Critical Assessment of SELDI-TOF-MS for Biomarker Discovery in Serum and Tissue of Patients with an Ovarian Mass. Proteome Sci., 10, 45.
• 17. Simsek, C., Sonmez, O., Yurdakul, A.S.,Ozmen, F., Zengin, N., Keyf, A.I., Ozturk, C., 2013. Importance of Serum SELDI-TOF-MS Analysis in the Diagnosis of Early Lung Cancer. Asian Pacific Journal of Cancer Prevention, 14(3), 2037-2042.
• 18.Wu, J., Ji, Y., Zhao, L., Ji, M., Ye, Z., Li, S., 2016. A Mass Spectrometric Analysis Method Based on PPCA and SVM for Early Detection of Ovarian Cancer. Computational and Mathematical Methods in Medicine, 2016, 6169249.
• 19.Cohen, A., Messaoudi, C., Badir, H., 2018. A New Wavelet-based Approach for Mass Spectrometry Data Classification, in New Frontiers of Biostatistics and Bioinformatics. Springer, Cham, 175-189.
• 20. Thakur, A., Mishra, V., Jain, S.K., 2011. Feed Forward Artificial Neural Network: Tool for Early Detection of Ovarian Cancer. Scientia pharmaceutica, 79(3), 493-506.
• 21. Sharma, A., Singh, S., 2016. Neural Network for Diagnosis of Ovarian Cancer Based on Proteomic Patterns in Serum. Journal of Scientific and Technical Advancements, 2(2), 25-27.
• 22. Pei, S., Tong, L., Li, X., Jiang, J., Huang, J., 2017. Feed-forward Network for Cancer Detection, in 2017 13th International Conference on Natural Computation. Fuzzy Systems and Knowledge Discovery (ICNC-FSKD), (697-701). IEEE.
• 23.Rahman, M.A., Muniyandi, R.C., Islam, K.T., Rahman, M.M., 2019. Ovarian Cancer Classification Accuracy Analysis Using 15-Neuron Artificial Neural Networks Model, in 2019 IEEE Student Conference on Research and Development (SCOReD), IEEE, 33-38.
• 24. FDA-NCI Klinik Proteomik Program Veri Bankası:xhttps://home.ccr.cancer.gov/ncifdaproteomics/ppatterns.asp.
• 25. Akküçük, U., 2009. Birçok Boyutlu Ölçekleme Tekniği Olarak Torgersen Ölçekleme Yöntemi ve Temel Bileşenler Analizi ile Karşılaştırması. Dumlupınar Üniversitesi, Sosyal Bilimler Dergisi, (25), 311-322.
• 26.Brunton, S.L., Kutz, J.N., 2019. Data-driven Science and Engineering: Machine Learning, Dynamical Systems and Control. Cambridge University Press.
• 27. Gümüş, V., Soydan, N., Simsek, O., Aköz, M., Kırkgöz, M., 2016. Yağış-Akış İlişkisinin Belirlenmesinde Farklı Yapay Sinir Ağı Yöntemlerinin Karşılaştırılması. Çukurova Üniversitesi Mühendislik-Mimarlık Fakültesi Dergisi, 28(1), 37-50.
• 28. Ataseven, B., 2013. Yapay Sinir Ağları ile Öngörü Modellemesi. Öneri Dergisi, 10(39), 101-115.