Related Experiment Video
Updated: Jan 6, 2026
09:45
Detection of Copy Number Alterations Using Single Cell Sequencing
Published on: February 17, 2017
12.1K
A Shallow Convolutional Learning Network for Classification of Cancers Based on Copy Number Variations.
Ahmad AlShibli1, Hassan Mathkour2
1Department of Computer Science, College of Computer and Information Sciences (CCIS), King Saud University, Riyadh 11543, Saudi Arabia. alshibli@ksu.edu.sa.
Sensors (Basel, Switzerland)
|October 2, 2019
Summary
Genomic copy number variations (CNVs) can help classify cancer types. Deep learning models like ResCNN6 achieved high accuracy, improving cancer diagnosis and management.
Area of Science:
- Genomics and Bioinformatics
- Computational Biology
- Machine Learning in Oncology
Background:
- Genomic copy number variations (CNVs) are significant structural variations linked to various diseases, including cancer.
- Cancer remains a leading cause of mortality globally, necessitating advanced methods for its management and treatment.
- Understanding the association between genomic alterations and cancer types is crucial for improving patient outcomes.
Purpose of the Study:
- To review and compare machine learning methods for cancer classification based on CNVs.
- To propose and evaluate novel deep learning techniques for classifying cancer types using CNV data.
- To investigate the impact of specific cancer types on classification accuracy and explore methods for improvement.
Main Methods:
- Reviewed existing machine learning algorithms for CNV-based cancer classification.
- Developed and tested three deep learning models: a six-layer convolutional neural network (CNN6), a residual six-layer convolutional neural network (ResCNN6), and VGG16 transfer learning.
- Conducted experiments on a dataset comprising six cancer types, including analysis of class-specific performance and data balancing strategies.
Main Results:
- ResCNN6 achieved 86% accuracy, CNN6 achieved 85%, and VGG16 achieved 77% accuracy in classifying six cancer types.
- Lower prediction accuracy was observed for uterine corpus endometrial carcinoma (UCEC), attributed to feature overlap with ovarian serous carcinoma (OV).
- Excluding UCEC improved CNN6 accuracy to 91% and ResCNN6 to 92%; data balancing via oversampling enhanced overall and UCEC classification accuracies.
Conclusions:
- Deep learning models, particularly ResCNN6 and CNN6, demonstrate high efficacy in classifying cancer types based on genomic CNVs.
- Feature similarity between certain cancer types (e.g., UCEC and OV) presents challenges for accurate classification.
- Data balancing techniques can significantly improve classification performance, especially for challenging classes.
Related Concept Videos
02:26Comparing Copy Number Variations and SNPs
18.5K
Sequencing of the human genome has opened up several best-kept secrets of the genome. Scientists have identified thousands of genome variations that exist within a population. These variations can be a single nucleotide or a larger chromosomal variation.
Copy number variations or CNVs are the structural variations that cover more than 1kb of DNA sequence. The single nucleotide polymorphism (SNP), on the other hand, is a single nucleotide change or a point mutation that is found in more than 1%...
Copy number variations or CNVs are the structural variations that cover more than 1kb of DNA sequence. The single nucleotide polymorphism (SNP), on the other hand, is a single nucleotide change or a point mutation that is found in more than 1%...
18.5K
02:21Cancers Originate from Somatic Mutations in a Single Cell
14.5K
Cancer arises from mutations in the critical genes that allow healthy cells to escape cell cycle regulation and acquire the ability to proliferate indefinitely. Though originating from a single mutation event in one of the originator cells, cancer progresses when the mutant cell lines continue to gain more and more mutations, and finally, become malignant. For example, chronic myelogenous leukemia (CML) develops initially as a non-lethal increase in white blood cells, which progressively...
14.5K
01:05Cancer-Critical Genes II: Tumor Suppressor Genes
9.3K
Genes usually encode proteins necessary for the proper functioning of a healthy cell. Mutations can often cause changes to the gene expression pattern, thereby altering the phenotype.
When the function of certain critical genes, especially those involved in cell cycle regulation and cell growth signaling cascades, gets disrupted, it upsets the cell cycle progression. Such cells with unchecked cell cycles start proliferating uncontrollably and eventually develop into tumors.
Such genes that act...
When the function of certain critical genes, especially those involved in cell cycle regulation and cell growth signaling cascades, gets disrupted, it upsets the cell cycle progression. Such cells with unchecked cell cycles start proliferating uncontrollably and eventually develop into tumors.
Such genes that act...
9.3K