Colorectal Cancer Prediction Based on Weighted Gene Co-Expression Network Analysis and Variational Auto-Encoder
An effective feature extraction method is key to improving the accuracy of a prediction model. From the Gene Expression Omnibus (GEO) database, which includes 13,487 genes, we obtained microarray gene expression data for 238 samples from colorectal cancer (CRC) samples and normal samples. Twelve gen...
Main Authors: | , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2020-08-01
|
Series: | Biomolecules |
Subjects: | |
Online Access: | https://www.mdpi.com/2218-273X/10/9/1207 |
_version_ | 1797556835455074304 |
---|---|
author | Dongmei Ai Yuduo Wang Xiaoxin Li Hongfei Pan |
author_facet | Dongmei Ai Yuduo Wang Xiaoxin Li Hongfei Pan |
author_sort | Dongmei Ai |
collection | DOAJ |
description | An effective feature extraction method is key to improving the accuracy of a prediction model. From the Gene Expression Omnibus (GEO) database, which includes 13,487 genes, we obtained microarray gene expression data for 238 samples from colorectal cancer (CRC) samples and normal samples. Twelve gene modules were obtained by weighted gene co-expression network analysis (WGCNA) on 173 samples. By calculating the Pearson correlation coefficient (PCC) between the characteristic genes of each module and colorectal cancer, we obtained a key module that was highly correlated with CRC. We screened hub genes from the key module by considering module membership, gene significance, and intramodular connectivity. We selected 10 hub genes as a type of feature for the classifier. We used the variational autoencoder (VAE) for 1159 genes with significantly different expressions and mapped the data into a 10-dimensional representation, as another type of feature for the cancer classifier. The two types of features were applied to the support vector machines (SVM) classifier for CRC. The accuracy was 0.9692 with an AUC of 0.9981. The result shows a high accuracy of the two-step feature extraction method, which includes obtaining hub genes by WGCNA and a 10-dimensional representation by variational autoencoder (VAE). |
first_indexed | 2024-03-10T17:08:36Z |
format | Article |
id | doaj.art-3c47c79bfe844ca7b1c3c6011313a1ea |
institution | Directory Open Access Journal |
issn | 2218-273X |
language | English |
last_indexed | 2024-03-10T17:08:36Z |
publishDate | 2020-08-01 |
publisher | MDPI AG |
record_format | Article |
series | Biomolecules |
spelling | doaj.art-3c47c79bfe844ca7b1c3c6011313a1ea2023-11-20T10:43:41ZengMDPI AGBiomolecules2218-273X2020-08-01109120710.3390/biom10091207Colorectal Cancer Prediction Based on Weighted Gene Co-Expression Network Analysis and Variational Auto-EncoderDongmei Ai0Yuduo Wang1Xiaoxin Li2Hongfei Pan3Basic Experimental Center of Natural Science, University of Science and Technology Beijing, Beijing 100083, ChinaSchool of Mathematics and Physics, University of Science and Technology Beijing, Beijing 100083, ChinaSchool of Mathematics and Physics, University of Science and Technology Beijing, Beijing 100083, ChinaSchool of Mathematics and Physics, University of Science and Technology Beijing, Beijing 100083, ChinaAn effective feature extraction method is key to improving the accuracy of a prediction model. From the Gene Expression Omnibus (GEO) database, which includes 13,487 genes, we obtained microarray gene expression data for 238 samples from colorectal cancer (CRC) samples and normal samples. Twelve gene modules were obtained by weighted gene co-expression network analysis (WGCNA) on 173 samples. By calculating the Pearson correlation coefficient (PCC) between the characteristic genes of each module and colorectal cancer, we obtained a key module that was highly correlated with CRC. We screened hub genes from the key module by considering module membership, gene significance, and intramodular connectivity. We selected 10 hub genes as a type of feature for the classifier. We used the variational autoencoder (VAE) for 1159 genes with significantly different expressions and mapped the data into a 10-dimensional representation, as another type of feature for the cancer classifier. The two types of features were applied to the support vector machines (SVM) classifier for CRC. The accuracy was 0.9692 with an AUC of 0.9981. The result shows a high accuracy of the two-step feature extraction method, which includes obtaining hub genes by WGCNA and a 10-dimensional representation by variational autoencoder (VAE).https://www.mdpi.com/2218-273X/10/9/1207weighted gene co-expression network analysisvariational autoencodercolorectal cancerhub genesclassifier |
spellingShingle | Dongmei Ai Yuduo Wang Xiaoxin Li Hongfei Pan Colorectal Cancer Prediction Based on Weighted Gene Co-Expression Network Analysis and Variational Auto-Encoder Biomolecules weighted gene co-expression network analysis variational autoencoder colorectal cancer hub genes classifier |
title | Colorectal Cancer Prediction Based on Weighted Gene Co-Expression Network Analysis and Variational Auto-Encoder |
title_full | Colorectal Cancer Prediction Based on Weighted Gene Co-Expression Network Analysis and Variational Auto-Encoder |
title_fullStr | Colorectal Cancer Prediction Based on Weighted Gene Co-Expression Network Analysis and Variational Auto-Encoder |
title_full_unstemmed | Colorectal Cancer Prediction Based on Weighted Gene Co-Expression Network Analysis and Variational Auto-Encoder |
title_short | Colorectal Cancer Prediction Based on Weighted Gene Co-Expression Network Analysis and Variational Auto-Encoder |
title_sort | colorectal cancer prediction based on weighted gene co expression network analysis and variational auto encoder |
topic | weighted gene co-expression network analysis variational autoencoder colorectal cancer hub genes classifier |
url | https://www.mdpi.com/2218-273X/10/9/1207 |
work_keys_str_mv | AT dongmeiai colorectalcancerpredictionbasedonweightedgenecoexpressionnetworkanalysisandvariationalautoencoder AT yuduowang colorectalcancerpredictionbasedonweightedgenecoexpressionnetworkanalysisandvariationalautoencoder AT xiaoxinli colorectalcancerpredictionbasedonweightedgenecoexpressionnetworkanalysisandvariationalautoencoder AT hongfeipan colorectalcancerpredictionbasedonweightedgenecoexpressionnetworkanalysisandvariationalautoencoder |