1
|
Multiclass Cancer Prediction Based on Copy Number Variation Using Deep Learning. COMPUTATIONAL INTELLIGENCE AND NEUROSCIENCE 2022; 2022:4742986. [PMID: 35720914 PMCID: PMC9203194 DOI: 10.1155/2022/4742986] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 03/31/2022] [Accepted: 05/21/2022] [Indexed: 12/02/2022]
Abstract
DNA copy number variation (CNV) is the type of DNA variation which is associated with various human diseases. CNV ranges in size from 1 kilobase to several megabases on a chromosome. Most of the computational research for cancer classification is traditional machine learning based, which relies on handcrafted extraction and selection of features. To the best of our knowledge, the deep learning-based research also uses the step of feature extraction and selection. To understand the difference between multiple human cancers, we developed three end-to-end deep learning models, i.e., DNN (fully connected), CNN (convolution neural network), and RNN (recurrent neural network), to classify six cancer types using the CNV data of 24,174 genes. The strength of an end-to-end deep learning model lies in representation learning (automatic feature extraction). The purpose of proposing more than one model is to find which architecture among them performs better for CNV data. Our best model achieved 92% accuracy with an ROC of 0.99, and we compared the performances of our proposed models with state-of-the-art techniques. Our models have outperformed the state-of-the-art techniques in terms of accuracy, precision, and ROC. In the future, we aim to work on other types of cancers as well.
Collapse
|
2
|
Identifying Methylation Pattern and Genes Associated with Breast Cancer Subtypes. Int J Mol Sci 2019; 20:ijms20174269. [PMID: 31480430 PMCID: PMC6747348 DOI: 10.3390/ijms20174269] [Citation(s) in RCA: 24] [Impact Index Per Article: 4.8] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/01/2019] [Revised: 08/19/2019] [Accepted: 08/29/2019] [Indexed: 12/18/2022] Open
Abstract
Breast cancer is regarded worldwide as a severe human disease. Various genetic variations, including hereditary and somatic mutations, contribute to the initiation and progression of this disease. The diagnostic parameters of breast cancer are not limited to the conventional protein content and can include newly discovered genetic variants and even genetic modification patterns such as methylation and microRNA. In addition, breast cancer detection extends to detailed breast cancer stratifications to provide subtype-specific indications for further personalized treatment. One genome-wide expression–methylation quantitative trait loci analysis confirmed that different breast cancer subtypes have various methylation patterns. However, recognizing clinically applied (methylation) biomarkers is difficult due to the large number of differentially methylated genes. In this study, we attempted to re-screen a small group of functional biomarkers for the identification and distinction of different breast cancer subtypes with advanced machine learning methods. The findings may contribute to biomarker identification for different breast cancer subtypes and provide a new perspective for differential pathogenesis in breast cancer subtypes.
Collapse
|
3
|
Yu XJ, Chen G, Yang J, Yu GC, Zhu PF, Jiang ZK, Feng K, Lu Y, Bao B, Zhong FM. Smoking alters the evolutionary trajectory of non-small cell lung cancer. Exp Ther Med 2019; 18:3315-3324. [PMID: 31602204 PMCID: PMC6777332 DOI: 10.3892/etm.2019.7958] [Citation(s) in RCA: 3] [Impact Index Per Article: 0.6] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/20/2018] [Accepted: 05/16/2019] [Indexed: 12/14/2022] Open
Abstract
Smoking is the biggest risk factor for lung cancer. Smokers have a much higher chance of developing lung tumors with a worse survival rate; however, non-smokers also develop lung tumors. A number of questions remain including the underlying difference between smoker and non-smoker lung cancer patients and the involvement of genetic and epigenetic processes in tumor development. The present study analyzed the mutation data of 100 non-small cell lung cancer (NSCLC) patients, 12 non-smokers, 48 ex-smokers and 40 smokers, from Tracking Non-Small Cell Lung Cancer Evolution through Therapy Consortium. A total of 68 genes exhibited different mutation patterns across non-smokers, ex-smokers and smokers. A number of these 68 genes encode membrane proteins with biological regulation, metabolic process, and response to stimulus functions. For each group of patients, the top 10 most frequently mutated genes were selected and their oncogenetic tree inferred, which reflected how the genes evolve during tumor genesis. By comparing the oncogenetic trees of non-smokers and smokers, it was identified that in non-smokers, the mutation of epidermal growth factor receptor (EGFR) was an early genetic alteration event and EGFR was the key driver, but in smokers, the mutation of titin (TTN) was more important. Based on network analysis, TTN can interact with spectrin α erythrocytic 1 through calmodulin 2 and troponin C1. These genetic differences during tumorigenesis of non-smoker and smoker lung cancer patients provided novel insights into the effects of smoking on the evolutionary trajectory of non-small cell lung cancer and may prove helpful for targeted therapy of different lung cancer subtypes.
Collapse
Affiliation(s)
- Xiao-Jun Yu
- Department of Thoracic Surgery, The First People's Hospital of Fuyang Hangzhou, Hangzhou, Zhejiang 311400, P.R. China
| | - Gang Chen
- Department of Thoracic Surgery, Hangzhou Red Cross Hospital, Hangzhou, Zhejiang 310003, P.R. China
| | - Jun Yang
- Department of Thoracic Surgery, Hangzhou Red Cross Hospital, Hangzhou, Zhejiang 310003, P.R. China
| | - Guo-Can Yu
- Department of Thoracic Surgery, Hangzhou Red Cross Hospital, Hangzhou, Zhejiang 310003, P.R. China
| | - Peng-Fei Zhu
- Department of Thoracic Surgery, Hangzhou Red Cross Hospital, Hangzhou, Zhejiang 310003, P.R. China
| | - Zheng-Ke Jiang
- Department of Surgery, Hangzhou Fuyang Hospital of Traditional Chinese Medicine, Hangzhou, Zhejiang 311400, P.R. China
| | - Kan Feng
- Department of Thoracic Surgery, The First People's Hospital of Fuyang Hangzhou, Hangzhou, Zhejiang 311400, P.R. China
| | - Yong Lu
- Department of Thoracic Surgery, The First People's Hospital of Fuyang Hangzhou, Hangzhou, Zhejiang 311400, P.R. China
| | - Bin Bao
- Department of Thoracic Surgery, The First People's Hospital of Fuyang Hangzhou, Hangzhou, Zhejiang 311400, P.R. China
| | - Fang-Ming Zhong
- Department of Thoracic Surgery, Hangzhou Red Cross Hospital, Hangzhou, Zhejiang 310003, P.R. China
| |
Collapse
|