A snapshot neural ensemble method for cancer-type prediction based on copy number variations
Authors:
Open Access
- 30 November 2019
- journal article
- research article
- Published by Springer Nature in Neural Computing and Applications
- Vol. 32 (19) , 15281-15299
Abstract
An accurate diagnosis and prognosis for cancer are specific to patients with particular cancer types and molecular traits, which needs to address carefully. The discovery of important biomarkers is becoming an important step toward understanding the molecular mechanisms of carcinogenesis in which genomics data and clinical outcomes need to be analyzed before making any clinical decision. Copy number variations (CNVs) are found to be associated with the risk of individual cancers and hence can be used to reveal genetic predispositions before cancer develops. In this paper, we collect the CNVs data about 8000 cancer patients covering 14 different cancer types from The Cancer Genome Atlas. Then, two different sparse representations of CNVs based on 578 oncogenes and 20,308 protein-coding genes, including genomic deletions and duplication across the samples, are prepared. Then, we train Conv-LSTM and convolutional autoencoder (CAE) networks using both representations and create snapshot models. While the Conv-LSTM can capture locally and globally important features, CAE can utilize unsupervised pretraining to initialize the weights in the subsequent convolutional layers against the sparsity. Model averaging ensemble (MAE) is then applied to combine the snapshot models in order to make a single prediction. Finally, we identify most significant CNVs biomarkers using guided-gradient class activation map plus (GradCAM++) and rank top genes for different cancer types. Results covering several experiments show fairly high prediction accuracies for the majority of cancer types. In particular, using protein-coding genes, Conv-LSTM and CAE networks can predict cancer types correctly at least 72.96% and 76.77% of the cases, respectively. Contrarily, using oncogenes gives moderately higher accuracies of 74.25% and 78.32%, whereas the snapshot model based on MAE shows overall 2.5% of accuracy improvement.Keywords
This publication has 45 references indexed in Scilit:
- MYC, FBXW7 and TP53 copy number variation and expression in Gastric CancerBMC Gastroenterology, 2013
- Copy Number Variation Analysis in Familial BRCA1/2-Negative Finnish Breast and Ovarian CancerPLOS ONE, 2013
- A classification model for distinguishing copy number variants from cancer-related alterationsBMC Bioinformatics, 2010
- Copy number variation at 1q21.1 associated with neuroblastomaNature, 2009
- Genome-wide Copy-Number-Variation Study Identified a Susceptibility Gene, UGT2B17, for OsteoporosisThe American Journal of Human Genetics, 2008
- Integrated detection and population-genetic analysis of SNPs and copy number variationNature Genetics, 2008
- A Fast Learning Algorithm for Deep Belief NetsNeural Computation, 2006
- Na + /monocarboxylate transport (SMCT) protein expression correlates with survival in colon cancer: Molecular characterization of SMCTProceedings of the National Academy of Sciences, 2006
- Bias of Selection on Human Copy-Number VariantsPLOS Genetics, 2006
- Detection of large-scale variation in the human genomeNature Genetics, 2004