Overview

Original Research

BIOINFORMATICS ANALYSIS OF THE GENES INVOLVED IN THE EXTENSION OF PROSTATE CANCER TO ADJACENT LYMPH NODES USING ADAPTIVE ACTIVATION FUNCTIONS WITH DEEP KRONECKER NEURAL NETWORK

S. SUBASREE 1, N. K. SAKTHIVEL 2, S. PRIYA 3, and M. MAHABOOBA 4.

Vol 18, No 09 ( 2023 )   |  DOI: 10.5281/zenodo.8366457   |   Author Affiliation: Professor and Head, Department of Computer Science and Engineering, Nehru Institute of Engineering and Technology, (Autonomous), Coimbatore 641 105, TN, India 1; Dean (Computing), Nehru Institute of Engineering and Technology, (Autonomous), Coimbatore 641 105, TN, India 2; Assistant Professor (SG), Department of Computer Science and Engineering, Nehru Institute of Engineering and Technology, (Autonomous), Coimbatore 641 105, TN, India 3; Assistant Professor, Department of Computer Science and Engineering, Nehru Institute of Engineering and Technology, (Autonomous), Coimbatore 641 105, TN, India 4.   |   Licensing: CC 4.0   |   Pg no: 501-508   |   Published on: 19-09-2023

Abstract

The objective of this research was to discover the genes involved in prostate cancer (PCa) patients' participation in extra lymph nodes and offer useful insights for identifying possible diagnostic biomarkers and pathogenic genes in PCa metastasis. Using Adaptive activation functions with deep Kronecker neural network (AAF-DKNN) and PCA with or without down sampling, the most significant candidate genes were determined. In total, twenty one genes were identified as related to the lymph node involvement. Between these, 9 genes were observed in metastatic prostate cancer, 6 were identified in another metastatic cancer and 4 were found in another local cancer. Additionally, augmentation of candidate genes was assessed in another PCa data sets. A verified set of genes that contribute to PCa metastasis was also identified. The SPAG1 and PLEKHF2 gene amplification was linked with a reduced chance of survival in prostate cancer patients.

Keywords

Gene Expression Analysis, Metastasis Prostate Cancer, Adaptive Activation Functions With Deep Kronecker Neural Network.