Convolutional Neural Network Approach to Predict Tumor Samples Using Gene Expression Data

Yıl 2021, Cilt: 4 Sayı: 2, 136 - 141, 23.09.2021

Büşra Nur Darendeli Alper Yılmaz

https://doi.org/10.38016/jista.946954

Cited By: 2

Öz

Cancer is threatening millions of people each year and its early diagnosis is still a challenging task. Early diagnosis is one of the major ways to tackle the disease and lower the mortality rate. Advancements in deep learning approaches and the availability of biological data offer applications that can facilitate the diagnosis and characterization of cancer. Here, we aimed to provide a new perspective of cancer diagnosis using a deep learning approach on gene expression data.

In this study, RNA-Seq data of approximately 30 different types of cancer patients the Cancer Genome Atlas (TCGA) study, and normal tissue RNA-Seq data from GTEx were used. The input data for the training was transformed to RGB format and the training was carried out with a Convolutional Neural Network (CNN). The trained algorithm is able to predict cancer with 97% accuracy, using gene expression data. In conclusion, our study shows that the deep learning approach and biological data have a huge potential in the diagnosis and identification of tumor samples.

Anahtar Kelimeler

TCGA, RNA-Seq, cacer, CNN, gene expression

Gen İfade Verilerinde Konvolusyonel Sinir Ağı Kullanılarak Tümör Örneklerinin Tahmini

Öz

Kanser her yıl milyonlarca insanı tehdit eden, erken teşhisi hala mümkün olmayan yaygın bir hastalıktır. Erken teşhis, kanserle baş etmenin ve ölüm oranını düşürmenin en önemli yollarından biridir. Derin öğrenme yaklaşımlarındaki gelişmeler ve biyolojik verilerdeki artış, kanserin teşhisini ve karakterizasyonunu kolaylaştırabilecek uygulamalar sunmaktadır. Bu çalışmada, gen ifade verilerini kullanarak derin öğrenme yaklaşımı ile kanser teşhisine yeni bir bakış açısı sağlamayı amaçladık.
30 farklı kanser çeşidine ait RNA-Seq verisi Kanser Genom Atlası (TCGA) adlı kaynaktan normal dokuların RNA-Seq verileri GTEx adlı kaynaktan temin edilip model eğitiminde kullanılmıştır. Gen ifade verileri RGB formatına dönüştürülüp Konvolusyonel Sinir Ağı (CNN) eğitimi için kullanıldı. Eğitilen model, gen ifade verilerine dayanarak kanseri %97 doğrulukla tahmin edebilmektedir. Sonuç olarak çalışmamız, derin öğrenme yaklaşımının ve biyolojik verilerin tümör örneklerinin tanısında büyük bir potansiyele sahip olduğunu göstermektedir.

Anahtar Kelimeler

CNN, Gen İfadesi, Kanser, RNA-Seq, TCGA

Kaynakça

• Ahmed, O., & Brifcani, A. (2019, April). Gene Expression Classification Based on Deep Learning. In 2019 4th Scientific International Conference Najaf (SICN) (pp. 145-149). IEEE.
• Ahn, T., Goo, T., Lee, C. H., Kim, S., Han, K., Park, S., & Park, T., 2018. Deep learning-based identification of cancer or normal tissue using gene expression data. In 2018 IEEE International Conference on Bioinformatics and Biomedicine (BIBM) (pp. 1748-1752). IEEE.
• Arvaniti, E.,Fricker, K.S.,Moret, M.,Rupp, N.,Hermanns, T.,Fankhauser, C.,Wey, N., Wild, P.J.,Rueschoff, J.H. and Claassen, M., 2018. Automated Gleason grading of prostate cancer tissue microarras via deep learning. Scientific reports,8(1), pp.1-11.
• Bejnordi, B.E., Mullooly, M., Pfeiffer, R.M., Fan, S.,Vacek, P.M., Weaver, D.L., Herschorn, S., Brinton, L.A., van Ginneken, B., Karssemeijer, N. and Beck, A.H., 2018. Using deep convolutional neural networks to identify and classify tumor associated stroma in diagnostic breast biopsies. Modern Pathology, 31(10), pp.1502-1512.
• Binder, A., Bockmayr, M., Hägele, M., Wienert, S., Heim, D., Hellweg, K., ... & Klauschen, F. (2021). Morphological and molecular breast cancer profiling through explainable machine learning. Nature Machine Intelligence, 1-12.
• Couture, H.D., Williams, L.A., Geradts, J., Nyante, S.J., Butler, E.N., Marron, J.S., Perou, C.M., Troester, M.A. and Niethammer, M., 2018. Image analysis with deep learning to predict breast cancer grade, Erstatus, histologic subtype, and intrinsic subtype. NPJ breast cancer, 4(1), pp.1-8.
• Danaee, P., Ghaeini, R., & Hendrix, D. A. (2017). A deep learning approach for cancer detection and relevant gene identification. In Pacific symposium on biocomputing 2017 (pp. 219-229).
• Dolezal, J.M., Trzcinska, A., Liao, C.Y., Kochanny, S., Blair, E., Agrawal, N., Keutgen, X.M.,   Angelos, P., Cipriani, N.A. and Pearson, A.T., 2020. Deep learning prediction of BRAF- RAS gene expression signature identifies noninvasive follicular thyroid neoplasms with papillary-like nuclear features. Modern Pathology, pp.1-13.
• Duran-Lopez, L., Dominguez-Morales, J.P., Conde-Martin, A.F., Vicente-Diaz, S. and Linares- Barranco, A., 2020. PROMETEO: A CNN-Based Computer-Aided Diagnosis System for WSI Prostate Cancer Detection. IEEE Access, 8, pp.128613-128628.
• Elbashir, M. K., Ezz, M., Mohammed, M., & Saloum, S. S. (2019). Lightweight convolutional neural network for breast cancer classification using RNA-seq gene expression data. IEEE Access, 7, 185338-185348.
• Esteva, A., Kuprel, B., Novoa, R.A., Ko, J., Swetter, S.M., Blau, H.M. and Thrun, S., 2017. Dermatologist-level classification of skin cancer with deep neural networks. Nature, 542(7639), pp.115-118.
• Esteva, A., Robicquet, A., Ramsundar, B., Kuleshov, V., DePristo, M., Chou, K., Cui, C., Corrado, G., Thrun, S. and Dean, J., 2019. Aguide to deep learning in healthcare. Nature medicine, 25(1), pp.24-29.
• Fontaine, P., Acosta, O., Castelli, J., De Crevoisier, R., Müller, H. and Depeursinge, A., 2020. The  importance of feature aggregation in radiomics: a head and neck cancer study. Scientific Reports, 10(1), pp.1-11.
• Galili, B., Tekpli, X., Kristensen, V. N., & Yakhini, Z., 2021. Efficient gene expression signature for a breast cancer immuno-subtype. Plos one, 16(1), e0245215.
• Gour, M., Jain, S. and SunilKumar, T., 2020. Residual learning based CNN for breast cancer histopathological image classification. International Journal of Imaging Systems and Technology.
• Hartenstein, A., Lübbe, F., Baur, A.D., Rudolph, M.M., Furth, C., Brenner, W., Amthauer, H., Hamm, B., Makowski, M. and Penzkofer, T., 2020. Prostate Cancer Nodal Staging: Using Deep Learning to Predict 68 Ga-PSMA-Positivity from CT Imaging Alone. Scientific Reports, 10(1), pp.1-11.
• Hu, Q., Whitney, H.M. and Giger, M.L., 2020. Adeep learning methodology for improved breast cancer diagnosis using multiparametric MRI. Scientific Reports, 10(1), pp.1-11.
• Jiang, D., Liao, J., Duan, H., Wu, Q., Owen, G. Shu, C., Chen, L., He, Y., Wu, Z., He, D. and Zhang, W., 2020. A machine learning-based prognostic predictor for stage III colon cancer. Scientific reports, 10(1), pp.1-9.
• Jiao, W., Atwal, G., Polak, P., Karlic, R., Cuppen, E., Danyi, A., De Ridder, J., van Herpen, C., Lolkema, M.P., Steeghs, N. and Getz, G., 2020. A deep learning system accurately classifies primary and metastatic cancers using passenger mutation patterns. Nature communications, 11(1), pp.1-12.
• Kanavati, F., Toyokawa, G., Momosaki, S., Rambeau, M., Kozuma, Y., Shoji, F., Yamazaki, K., Takeo, S., Iizuka, O. and Tsuneki, M., 2020. Weakly-supervised learning for lung carcinoma classification using deep learning. Scientific Reports, 10(1), pp.1-11.
• Li, Z., Zou, D., Tang, J., Zhang, Z., Sun, M., & Jin, H., 2019. A comparative study of deep learning-based vulnerability detection system. IEEE Access, 7, 103184-103197.
• Lai, Y.H., Chen, W.N., Hsu, T.C., Lin, C., Tsao, Y. and Wu, S., 2020. overall survival prediction of non-small cell lung cancer by integrating microarray and clinical data with deep learning. Scientific reports, 10(1), pp.1-11.
• Marra, F., Gragnaniello, D., & Verdoliva, L., 2018. On the vulnerability of deep learning to adversarial attacks for camera model identification. Signal Processing: Image Communication, 65, 240-248.
• Mencattini, A., Di Giuseppe, D., Comes, M.C., Casti, P., Corsi, F., Bertani, F.R., Ghibelli, L., Businaro, L., Di Natale, C., Parrini, M.C. and Martinelli, E., 2020. Discovering the hidden messages within cell trajectories using a deep learning approach for in vitro evaluation of cancer drug treatments. Scientific reports, 10(1), pp.1-11.
• Nagpal, K., Foote, D., Liu, Y., Chen, P.H.C., Wulczyn, E., Tan, F., Olson, N., Smith, J.L.   Mohtashamian, A., Wren, J.H. and Corrado, G.S., 2019. Development and validation of a deep learning algorithm for improving Gleason scoring of prostate cancer. NPJ digital medicine, 2(1), pp.1-10.
• Parnian, A., Arash, M., Tyrrell, P.N., Cheung, P., Ahmed, S., Plataniotis, K.N., Nguyen, E.T. and Anastasia, O., 2020. DRTOP: deep learning-based radiomics for the time-to-event outcome prediction in lung cancer. Scientific Reports (Nature Publisher Group), 10(1).
• Persi, E., Wolf, Y.I., Horn, D., Ruppin, E., Demichelis, F., Gatenby, R.A., Gillies, R.J. and Koonin, E.V., 2020. Mutation–selection balance and compensatory mechanisms in tumour evolution. Nature Reviews Genetics, pp.1-12.
• Ramirez, R., Chiu, Y. C., Zhang, S., Ramirez, J., Chen, Y., Huang, Y., & Jin, Y. F., 2021. Prediction and interpretation of cancer survival using graph convolution neural networks. Methods.
• Rouillard, A. D., Gundersen, G. W., Fernandez, N. F., Wang, Z., Monteiro, C. D., McDermott, M.G., & Ma’ayan, A., 2016. The harmonizome: a collection of processed datasets gathered to serve and mine knowledge about genes and proteins. Database, 2016.
• Shon, H. S., Yi, Y., Kim, K. O., Cha, E. J., & Kim, K. A. (2019). Classification of stomach cancer gene expression data using CNN algorithm of deep learning. Journal of Biomedical and Translational Research (JBTR), 20(1), 15-20.
• Sinha, S., & Saranya, S. S., 2021. One Pixel Attack for Fooling Neural Networks. Annals of the Romanian Society for Cell Biology, 8405-8412.
• Su, J., Vargas, D. V., & Sakurai, K., 2019. Attacking convolutional neural network using differential evolution. IPSJ Transactions on Computer Vision and Applications, 11(1), 1-16.
• Swiderska-Chadaj, Z., de Bel, T., Blanchet, L., Baidoshvili, A., Vossen, D., van der Laak, J. and Litjens, G., 2020. Impact of rescanning and normalization on convolutional neural network performance in multi-center, whole-slide classification of prostate cancer. Scientific Reports, 10(1), pp.1-14. Tran, N.H., Qiao, R., Xin, L., Chen, X., Shan, B. and Li, M., 2020. Personalized deep learning of individual immunopeptidomes to identify neoantigens for cancer vaccines. Nature Machine Intelligence, pp.1-8.
• Tschandl, P., Rinner, C., Apalla, Z., Argenziano, G., Codella, N., Halpern, A., Janda, M., Lallas, A., Longo, C., Malvehy, J. and Paoli, J., 2020. Human–computer collaboration for skin cancer recognition. Nature Medicine, 26(8), pp.1229-1234.
• Xie, Y., Meng, W. Y., Li, R. Z., Wang, Y. W., Qian, X., Chan, C., ... & Leung, E. L. H., 2021. Early lung cancer diagnostic biomarker discovery by machine learning methods. Translational oncology, 14(1), 100907.
• Yoo, S., Gujrathi, I., Haider, M.A. an Khalvati, F., 2019. prostate cancer Detection using Deep convolutional neural networks. Scientific Reports, 9.
• Zeng, B., Glicksberg, B. S., Newbury, P., Chekalin, E., Xing, J., Liu, K., ... & Chen, B., 2021. OCTAD: an open workspace for virtually screening therapeutics targeting precise cancer patient groups using gene expression features. Nature Protocols, 16(2), 728-753.
• Zhang, Y., Chan, S., Park, V.Y., Chang, K.T., Mehta, S., Kim, M.J., Combs, F.J., Chang, P., Chow, D., Parajuli, R. and Mehta, R.S., 2020. Automatic Detection and Segmentation of Breast Cancer on MRI Using Mask R-CNN Trained on Non–Fat-Sat Images and Tested on Fat-Sat Images. Academic Radiology.
• Zuluaga-Gomez, J., Al Masry, Z., Benaggoune, K., Meraghni, S. and Zerhouni, N., 2020. A CNN-based methodology for breast cancer diagnosis using thermal images. Computer Methods in Biomechanics and Biomedical Engineering: Imaging & Visualization, pp.1-15.