Cross-validation and cross-study validation of chronic lymphocytic leukemia with exome sequences and machine learning

The era of genomics brings the potential of better DNA based risk prediction and treatment. While genome-wide association studies are extensively studied for risk prediction, the potential of using whole exome data for this purpose is unclear. We explore this problem for chronic lymphocytic leukemia that is one of the largest whole exome dataset of 186 case and 169 controls available from the NIH dbGaP database. We perform a standard next generation sequence procedure to obtain SNP variants on 153 cases and 144 controls after exclusion of samples with missing data. To evaluate their predictive power we first conduct a 50% training and 50% test cross-validation study on the full dataset with the support vector machine as the classifier. There we obtain a mean accuracy of 82% with top 20 ranked SNPs obtained by the Pearson correlation coefficient. We then perform a cross-study validation on case and controls from a lymphoma external study and just controls from head and neck cancer and breast cancer studies (all obtained from NIH dbGaP). On the external dataset we obtain an accuracy of 70% with top ranked SNPs obtained from the original dataset. We also find our top Pearson ranked SNPs to lie on previously implicated genes for this disease. Our study shows that even with a small sample size we can obtain moderate to high accuracy with exome sequences and is thus encouraging for future work.

• Publication year

  2015

• Venue

  IEEE International Conference on Bioinformatics and Biomedicine

• Publication date

  2015-11-09

• Fields of study

  Biology, Medicine, Computer Science

• Identifiers
  DOI 10.1504/IJDMB.2016.10000562
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• Targeting Aberrant Epigenetic Networks Mediated by PRMT1 and KDM4C in Acute Myeloid Leukemia

  2016cited by this paper
• Decreased Expression of BNC1 and BNC2 Is Associated with Genetic or Epigenetic Regulation in Hepatocellular Carcinoma

  2016cited by this paper
• Genetic ancestry influences asthma susceptibility and lung function among Latinos.

  2015cited by this paper
• Genetics of follicular lymphoma transformation.

  2014cited by this paper
• Association of aminoacyl-tRNA synthetases with cancer.

  2014cited by this paper
• Genetic-based prediction of disease traits: prediction is very difficult, especially about the future†

  2014cited by this paper
• The Construction of Risk Prediction Models Using GWAS Data and Its Application to a Type 2 Diabetes Prospective Cohort

  2014cited by this paper
• Cross-study validation for the assessment of prediction algorithms

  2014cited by this paper
• Generalization and Dilution of Association Results from European GWAS in Populations of Non-European Ancestry: The PAGE Study

  2013cited by this paper
• Genetic variants and their interactions in disease risk prediction – machine learning and network perspectives

  2013cited by this paper
• Performance and Robustness of Penalized and Unpenalized Methods for Genetic Prediction of Complex Human Disease

  2013influential reference
• Genome-wide Association Study Identifies Multiple Risk Loci for Chronic Lymphocytic Leukemia

  2013cited by this paper
• From FastQ Data to High‐Confidence Variant Calls: The Genome Analysis Toolkit Best Practices Pipeline

  2013cited by this paper
• Population ancestry and genetic risk for diabetes and kidney, cardiovascular, and bone disease: modifiable environmental factors may produce the cures.

  2013cited by this paper
• A genome-wide association study identifies multiple susceptibility loci for chronic lymphocytic leukemia

  2013cited by this paper
• Benchmarking short sequence mapping tools

  2013cited by this paper
• Functional analysis of the two reciprocal fusion genes MLL-NEBL and NEBL-MLL reveal their oncogenic potential.

  2013cited by this paper
• Evolution and impact of subclonal mutations in chronic lymphocytic leukemia.

  2013cited by this paper
• Bringing genome-wide association findings into clinical use

  2013cited by this paper
• Projecting the performance of risk prediction based on polygenic analyses of genome-wide association studies

  2013cited by this paper
• Large sample size, wide variant spectrum, and advanced machine-learning technique boost risk prediction for inflammatory bowel disease.

  2013cited by this paper
• Five years of GWAS discovery.

  2012cited by this paper
• Risk estimation and risk prediction using machine-learning methods

  2012influential reference
• Tools for mapping high-throughput sequencing data

  2012cited by this paper
• Comparison of Family History and SNPs for Predicting Risk of Complex Disease

  2012cited by this paper
• Sequence analysis of mutations and translocations across breast cancer subtypes

  2012cited by this paper
• The Mutational Landscape of Head and Neck Squamous Cell Carcinoma

  2011cited by this paper
• Ranking causal variants and associated regions in genome-wide association studies by the support vector machine and random forest

  2011cited by this paper
• Genome-wide association study identifies a novel susceptibility locus at 6p21.3 among familial CLL.

  2011cited by this paper
• A framework for variation discovery and genotyping using next-generation DNA sequencing data

  2011cited by this paper
• SF3B1 and other novel cancer genes in chronic lymphocytic leukemia.

  2011influential reference
• ANNOVAR: functional annotation of genetic variants from high-throughput sequencing data

  2010cited by this paper
• Genomic risk prediction.

  2010cited by this paper
• The Genome Analysis Toolkit: a MapReduce framework for analyzing next-generation DNA sequencing data.

  2010cited by this paper
• Risk prediction using genome‐wide association studies

  2010cited by this paper
• The Sequence Alignment/Map format and SAMtools

  2009cited by this paper
• Harnessing the information contained within genome-wide association studies to improve individual prediction of complex disease risk.

  2009cited by this paper
• Genetic risk prediction--are we there yet?

  2009cited by this paper
• Pitfalls of supervised feature selection

  2009cited by this paper
• Cardiovascular Disease Risk Prediction With and Without Knowledge of Genetic Variation at Chromosome 9p21.3

  2009cited by this paper
• Pathway Analysis of GWAS Provides New Insights into Genetic Susceptibility to 3 Inflammatory Diseases

  2009cited by this paper
• Genome-based prediction of common diseases: advances and prospects.

  2008influential reference
• Polymorphisms associated with cholesterol and risk of cardiovascular events.

  2008cited by this paper
• Aminoacyl tRNA synthetases and their connections to disease

  2008cited by this paper
• Prediction of individual genetic risk of complex disease.

  2008cited by this paper
• Discriminatory accuracy from single-nucleotide polymorphisms in models to predict breast cancer risk.

  2008cited by this paper
• A genome-wide association study identifies six susceptibility loci for chronic lymphocytic leukemia

  2008cited by this paper
• Prediction of coronary heart disease risk using a genetic risk score: the Atherosclerosis Risk in Communities Study.

  2007cited by this paper
• Prediction of individual genetic risk to disease from genome-wide association studies.

  2007cited by this paper
• Genome-wide association study of 14,000 cases of seven common diseases and 3,000 shared controls

  2007cited by this paper
• The NCBI dbGaP database of genotypes and phenotypes

  2007cited by this paper
• Fusion of EML1 to ABL1 in T-cell acute lymphoblastic leukemia with cryptic t(9;14)(q34;q32).

  2005cited by this paper
• Fusion of EML 1 to ABL 1 in T-cell acute lymphoblastic leukemia with cryptic t ( 9 ; 14 ) ( q 34 ; q 32 )

  2005cited by this paper
• Result Analysis of the NIPS 2003 Feature Selection Challenge

  2004cited by this paper
• An Introduction to Variable and Feature Selection

  2003cited by this paper
• Advances in kernel methods: support vector learning

  1999cited by this paper
• Making large scale SVM learning practical

  1998cited by this paper
• Induction of apoptosis of human leukemia cells by α-anordrin

  1997cited by this paper
• Support-Vector Networks

  1995cited by this paper
• BIOINFORMATICS ORIGINAL PAPER

  year unknowninfluential reference

• Genetic data visualization using literature text-based neural networks: Examples associated with myocardial infarction

  2023cites this paper
• Cross-validation and cross-study validation of kidney cancer with machine learning and whole exome sequences from the National Cancer Institute

  2018cites this paper
• Artificial neural network classification of microarray data using new hybrid gene selection method

  2017cites this paper
• Disease diagnostic classifier for chronic lymphocytic leukemia using genomic data

  2017cites this paper