ABSTRACT
The grade of cancer is a way to classify cancer based on certain characteristics of cancer tissue. It is an important issue for the precise diagnosis, treatment, and mechanistic research of cancer. With the rapid development of genome sequencing technology, it has become possible to obtain large amounts of gene expression data, and large-scale genomic data to predict the grade of cancer is a challenging problem. In this study, we used gene expression data to propose a pathway-related deep neural network (K-Net) for predicting the grade of Kidney renal clear cell carcinoma (KIRC) tissues. K-Net provides the capability of model interpretability that most conventional fully-connected neural networks lack, describing which pathways play an important role in the process of predicting grade. The predictive performance of K-Net was evaluated with multiple cross-validation experiments. The K-Net prediction accuracy of 74%. More meaningfully, in contrast to using genes as features, this new classification model using enriched pathways as features can well explain which pathways play an important role in KIRC tissues from highly differentiated to poorly differentiated. Cancer development is a process of degradation of certain functions and enhancement of certain functions of tumor tissue, and understanding which pathways play an important role in cancer development can help explore research directions in cancer treatment.
- Bray, F., Ferlay, J., Soerjomataram, I., Siegel, R. L., & Jemal, A. . (2018). Global cancer statistics 2018: globocan estimates of incidence and mortality worldwide for 36 cancers in 185 countries: global cancer statistics 2018. CA A Cancer Journal for Clinicians, 68(suppl 8).Google Scholar
- Protzel, C., Maruschke, M., & Hakenberg,O. W. (2012). Epidemiology, aetiology, and pathogenesis of renal cell carcinoma. European Urology Supplements, 11(3), 52-59.Google ScholarCross Ref
- Curtis, S. A., Cohen, J. V., & Kluger, H. M.. (2016). Evolving immunotherapy approaches for renal cell carcinoma. Current Oncology Reports, 18(9), 57.Google ScholarCross Ref
- Matias, Casás-Selves, James, & DeGregori. (2011). How cancer shapes evolution and how evolution shapes cancer. Evolution Education & Outreach.Google Scholar
- Kirkali, Z. , Chan, T. , Manoharan, M. , Algaba, F. , Busch, C. , & Cheng, L. , (2005). Bladder cancer: epidemiology, staging and grading, and diagnosis. Urology, 66(6-supp-S1), 4-34.Google Scholar
- George, V. S. , & Raj, C. . (2011). Review on feature selection techniques and the impact of svm for cancer classification using gene expression profile. International Journal of Computer Science & Engineering Survey, 2(3), 16-27.Google ScholarCross Ref
- Yuanyuan, Li, Kai, Kang, Juno, & M., (2017). A comprehensive genomic pan-cancer classification using the cancer genome atlas gene expression data. Bmc Genomics.Google Scholar
- Ram, M., Najafi, A. , & Shakeri, M. T. . (2017). Classification and biomarker genes selection for cancer gene expression data using random forest. Iranian Journal of Pathology, 12(4), 339-347.Google ScholarCross Ref
- Hnzelmann, S. , Castelo, R. , & Guinney, J. (2013). Gsva: gene set variation analysis for microarray and rna-seq data. Bmc Bioinformatics, 14(1), 7-7.Google ScholarCross Ref
- Shrikumar, A., Greenside, P., Kundaje, A. (2017). Learning important features through propagating activation differences. arXiv preprint arXiv:1704.02685.Google ScholarDigital Library
- Tomczak, K., Czerwińska, P. and Wiznerowicz, M (2015). The Cancer Genome Atlas (TCGA): An immeasurable source of knowledge. Contemporary Oncology, 19, 1A, A68-77.Google Scholar
- Liu, H. . (1998). Feature selection for knowledge discovery and data mining. Kluwer Academic Publishers.Google ScholarCross Ref
- Ding, C. , & Peng, H. (2005). Minimum redundancy feature selection from microarray gene expression data. Journal of Bioinformatics & Computational Biology, 3(02), 185-205.Google ScholarCross Ref
- AE Akadi, Amine, A. , AE Ouardighi, & D Aboutajdine. (2011). A two-stage gene selection scheme utilizing mrmr filter and ga wrapper. Knowledge and Information Systems, 26(3), 487-500.Google ScholarCross Ref
- Sakar, O. , Kursun, O. , Seker, H. , & Gurgen, F. . (2010). Prediction of Protein Sub-nuclear Location by Clustering mRMR Ensemble Feature Selection. International Conference on Pattern Recognition. IEEE Computer Society.Google ScholarDigital Library
- Direito B, Duarte J, Teixeira C, Le Van Quyen M, Schulze-Bonhage A, Sales F, Dourado A (2011). Feature selection in high dimensional EEG features spaces for epileptic seizure prediction. IFAC Proceedings Volumes. 44(1), 6206–11.Google ScholarCross Ref
- Kokhlikyan, N. , Miglani, V. , Martin, M. , Wang, E. , & Reblitz-Richardson, O. (2020). Captum: a unified and generic model interpretability library for pytorch.Google Scholar
- Yamada, M. , Jitkrittum, W. , Sigal, L., Xing, E. P. , & Sugiyama, M. . (2014). High-dimensional feature selection by feature-wise kernelized lasso. Neural Computation, 26(1), 185-207.Google ScholarDigital Library
Index Terms
- Grading Prediction of Kidney Renal Clear Cell Carcinoma by Deep Learning
Recommendations
Revealing pathway maps of renal cell carcinoma by gene expression change
Protein-protein interactions (PPIs) and gene expression profiles interact with each other in the regulation of a pathway. Many studies have expressed the feasibility of deriving the pathway from the PPI network or gene expression information. However, ...
Screening disrupted molecular functions and pathways associated with clear cell renal cell carcinoma using Gibbs sampling
Display Omitted Gibbs sampling was employed to identify disrupted molecular functions.We identified 13 differentially expressed molecular functions and 79 pivotal genes in ccRCC.Cases with alterations in pivotal genes showed poor ...
On the reproducibility of results of pathway analysis in genome-wide expression studies of colorectal cancers
One of the major problems in genomics and medicine is the identification of gene networks and pathways deregulated in complex and polygenic diseases, like cancer. In this paper, we address the problem of assessing the variability of results of pathways ...
Comments