Human age prediction using DNA methylation and regression methods

Determination of a person’s age can be an important factor in forensic investigation. DNA methylation (DNAm) is a well-known factor signifying change during the aging process but also necessary for the development of mammals. Several studies reported that DNAm can be used as an important marker in predicting the age of a human. This study is carried out to develop the age prediction model using three different regression methods. Multiple linear regression, Support vector regression, and Random forest regression methods are applied using a set of four highly age-correlated CpG sites. For 180 blood samples having age between 2 and 87 years, the mean absolute deviation (MAD) for multiple linear regression method is 8.43 years, for support vector regression is 7.86 years and for random forest regression method is 8.25 years. Further, these models are tested on five different age-groups. The average MAD for multiple linear regression, support vector regression and random forest regression are 3.46, 3.44 and 3.56, respectively. Support vector regression gave the highest accuracy for combined samples as well as for 5 different age groups. It has been concluded from the results that support vector regression is a reliable method for human age prediction.

[1]  J. Shapiro,et al.  Why repetitive DNA is essential to genome function , 2005, Biological reviews of the Cambridge Philosophical Society.

[2]  D. Basak,et al.  Support Vector Regression , 2008 .

[3]  Shailendra Singh,et al.  A Review of Computational Intelligence Methods for Eukaryotic Promoter Prediction , 2015, Nucleosides, nucleotides & nucleic acids.

[4]  Lan Hu,et al.  A novel strategy for forensic age prediction by DNA methylation and support vector regression model , 2015, Scientific Reports.

[5]  V. Garg,et al.  Targeting Telomerase and Topoisomerase-II by Natural Moieties: An Anti-Cancer Approach , 2018, Novel Approaches in Cancer Study.

[6]  V. Wilson,et al.  Genomic 5-methyldeoxycytidine decreases with age. , 1987, The Journal of biological chemistry.

[7]  T. Huang,et al.  Profiling DNA Methylomes from Microarray to Genome-Scale Sequencing , 2010, Technology in cancer research & treatment.

[8]  M. Mukaka,et al.  Statistics corner: A guide to appropriate use of correlation coefficient in medical research. , 2012, Malawi medical journal : the journal of Medical Association of Malawi.

[9]  H. Pan,et al.  DNA Methylation in Aggressive Gastric Carcinoma , 2013 .

[10]  G. Fan,et al.  DNA Methylation and Its Basic Function , 2013, Neuropsychopharmacology.

[11]  B. Mcclintock,et al.  Controlling elements and the gene. , 1956, Cold Spring Harbor symposia on quantitative biology.

[12]  A. Riggs,et al.  DNA Methylation and Demethylation in Mammals* , 2011, The Journal of Biological Chemistry.

[13]  Daniel J. Denis,et al.  The early origins and development of the scatterplot. , 2005, Journal of the history of the behavioral sciences.

[14]  Yi Zhang,et al.  TET enzymes, TDG and the dynamics of DNA demethylation , 2013, Nature.

[15]  Thomas Mikeska,et al.  DNA Methylation Biomarkers: Cancer and Beyond , 2014, Genes.

[16]  C. Franceschi,et al.  Reconfiguration of DNA methylation in aging , 2015, Mechanisms of Ageing and Development.

[17]  W H DECKER,et al.  Some effects of relaxin in obstetrics. , 1958, Obstetrics and Gynecology.

[18]  S. Gras,et al.  Combinatorial DNA methylation codes at repetitive elements. , 2017, Genome research.

[19]  E. A. Habib.  MEAN ABSOLUTE DEVIATION ABOUT MEDIAN AS A TOOL OF EXPLANATORY DATA ANALYSIS , 2012 .

[20]  K. Robertson.  DNA methylation and human disease , 2005, Nature Reviews Genetics.

[21]  E. Maher,et al.  DNA methylation: a form of epigenetic control of gene expression , 2010 .

[22]  Andy Liaw,et al.  Classification and Regression by randomForest , 2007 .

[23]  W. Wagner,et al.  Epigenetic Aging Signatures Are Coherently Modified in Cancer , 2015, PLoS genetics.

[24]  Keith D Robertson,et al.  DNA methylation: superior or subordinate in the epigenetic hierarchy? , 2011, Genes & cancer.

[25]  Raimund Erbel,et al.  Aging of blood can be tracked by DNA methylation changes at just three CpG sites , 2014, Genome Biology.

[26]  Wolfgang Stephan,et al.  The evolutionary dynamics of repetitive DNA in eukaryotes , 1994, Nature.

[27]  S. Horvath,et al.  DNA methylation age of blood predicts all-cause mortality in later life , 2015, Genome Biology.

[28]  Aging and DNA methylation , 2015, BMC Biology.

[29]  Jack A. Taylor,et al.  Genome-wide age-related DNA methylation changes in blood and other tissues relate to histone modification, expression and cancer. , 2014, Carcinogenesis.

[30]  T. Ekström,et al.  Impact of inflammation on epigenetic DNA methylation – a novel risk factor for cardiovascular disease? , 2007, Journal of internal medicine.

[31]  Martin Hofmann,et al.  Support Vector Machines — Kernels and the Kernel Trick , 2006 .

[32]  Saif Nalband,et al.  Feature selection and classification methodology for the detection of knee-joint disorders , 2016, Comput. Methods Programs Biomed..

[33]  Jian-Kang Zhu,et al.  Regulation and function of DNA methylation in plants and animals , 2011, Cell Research.

[34]  V. Garg,et al.  Role of DNA methylation in human age prediction , 2017, Mechanisms of Ageing and Development.

[35]  E. Li,et al.  DNA methylation in mammals. , 2014, Cold Spring Harbor perspectives in biology.

[36]  R. Płoski,et al.  Development of a forensically useful age prediction method based on DNA methylation analysis. , 2015, Forensic science international. Genetics.

[37]  Christian Gieger,et al.  Tobacco Smoking Leads to Extensive Genome-Wide Changes in DNA Methylation , 2013, PloS one.

[38]  M. Kobor,et al.  DNA methylation and healthy human aging , 2015, Aging cell.

[39]  Neelam Goel,et al.  An Improved Method for Splice Site Prediction in DNA Sequences Using Support Vector Machines , 2015 .