Screening of Pathogenic Genes for Colorectal Cancer and Deep Learning in the Diagnosis of Colorectal Cancer

Abstract

Based on complex networks and machine learning methods, this paper studies the mining of colorectal cancer treatment genes, and innovatively combines a variety of feature extraction and comparative analysis methods, from gene network features, gene attribute features, network and attribute integration The three aspects of characteristics comprehensively excavate the genetic characteristics, and demonstrate the feasibility of the study through comparative analysis from different perspectives. Constructing a colorectal cancer gene network, analyzing the changes in the network structure during the development of colorectal cancer, and mining the network characteristics of genes are the first issues to be studied in this paper. The analysis of the network structure compares the changes in the network structure of the driver genes in the Normal network and the Tumor network and the edge mechanism of the driver genes, and the distribution of the eigenvalues of the driver genes and non-driver genes in the Tumor network. During the development of colorectal cancer, the network structure of the gene has changed significantly, and the prediction results based on the network structure show better prediction results than the non-network structure. These findings are feasible for the research direction of this paper. The argument is carried out, and the relevant analysis results are also given in the article. However, the research method of the thesis is based on network research, so comparing structural features with non-structural features only shows that structural features have a good classification ability, and cannot directly explain that modeling using gene networks is better than not using gene networks. Finally, based on the random forest, the optimized classification is improved to reveal the important factors affecting the diagnosis of colorectal cancer, and then to identify the true potential colorectal cancer driver genes, providing guidance for the clinical research of colorectal cancer and driving gene mining. INDEX TERMS colorectal cancer; gene screening; diagnosis; deep learning.

Comparative Analysis of Data Mining Algorithms for Cancer Gene Expression Data

“…J-48, on the other hand, performed best across the board. Yanke et al [15] mined 7 colorectal cancer related datasets using their new technique that combined NB (Naïve Bayes), RF and DT. After analysis the final result are optimized using an appropriate optimization technique.…”

“…It was found that all the three algorithms were performing well but kNN outperforms the other two by a difference of around 0.4 percent in accuracy. ROC [11], [14], [15], [18] 4 AUC [11], [13], [15], [18] 4 F-Measure [13], [14], [18], [19] 4…”

Automated Artificial Intelligence Empowered Colorectal Cancer Detection and Classification Model

“…In Colorectal Cancer (CRC), the morphology of intestinal gland includes gland formation whereas architectural appearance is a primary criterion for cancer grading. Glands are significant histological structures in almost all organs of the body with a primary purpose to achieve i.e., to secret carbohydrates and proteins [6]. Human colon contains masses of glands in it.…”

Identification and Segregation of Genes with Improved Recurrent Neural Network Trained with Optimal Gene Level and Mutation Level Features

“…Although numerous strategies have been tried to discuss cancer's complicated mutational heterogeneity, driver genes discovery continues to remain a difficulty owing to the restricted capacity to integrate other genomic elements for integrated studies [4]. Other genomic elements, including as nonsense mutations, penetrations, and omissions, as well as germ line variations, have been previously overlooked but now have recently been discovered to play an important effect on cancer formation [9] [21] [22]. When genomic components, such as somatic mutations, germ line variations, insertions and deletions, are investigated jointly, particularly inside an interaction term, modeling intricacy as well as investigation strength are obstacles [12].…”

“…These traditional teaching and learning algorithms are often created by domain specialists and depend significantly on data models. The human genome's sophistication as well as the degree of exercise requisite makes it tough to derive important information, whereas deep learning can gain knowledge a good feature representation automatically [22]. With power of parallel processing and advanced algorithms, deep learning has recently emerged as a result of advances in big data.…”