Human Age Prediction Based on DNA Methylation Using a Gradient Boosting Regressor

Li, Xingyan; Li, Weidong; Xu, Yan

doi:10.3390/genes9090424

Cited by 57 publications

(45 citation statements)

References 61 publications

(80 reference statements)

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The confusion matrix of Figure 3b shows the classification errors for the five-class label grouping. Finally, by examining the confusion matrix in the two previous cases, we re-labeled the data according to the three age classes obtained through the integration of classes (1, 2), (3,4,5), and (6,7,8,9,10). The accuracy of the model was 0.92 (+/− 0.12) using these three age groups.…”

Section: Classificationmentioning

confidence: 99%

“…DNAm, which often occurs in a CpG sequence, is an epigenetic sign and plays an important role in regulating cells to establish and maintain cellular identity. Various studies have shown that DNAm changes with age [4][5][6][7][8]. This change in DNAm can be disclosed at specific CpG-sites in all individuals, although individual differences may affect the "speed" of this change [6].…”

Section: Introductionmentioning

confidence: 99%

“…Various models for age prediction have been applied to DNAm data such as regression models including Linear regression [9,10], Multivariate linear regression [2,7], Multiple linear regression [3,11], or machine learning algorithms such as Support Vector Regression [1], Random Forest Regression [6], Artificial Neural Networks [12,13], and Gradient Boosting Regression [4,14]. In a vast majority of these studies, the mean absolute deviation (MAD) and the correlation between the actual value of age and DNAm (R 2 ) were reported to describe the model's performance.…”

Section: Introductionmentioning

confidence: 99%

“…In a vast majority of these studies, the mean absolute deviation (MAD) and the correlation between the actual value of age and DNAm (R 2 ) were reported to describe the model's performance. Furthermore, most of these studies only used a simple statistical feature selection algorithm such as Pearson's correlation to select age-related CpG-sites [1,4,14]. In general, traditional feature selection algorithms are divided into three categories: filter, wrapper and embedded methods.…”

Section: Introductionmentioning

confidence: 99%

“…As a consequence, many informative features may be ignored. For example, Naue et al [6] used the Mutual Information and Li et al [4] used the Pearson's correlation to select a subset of features. In wrapper methods, in contrast to filter methods, a model is used to evaluate a subset of features, so as the data volume increases, the model accuracy and algorithm time complexity are both increase.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

MapReduce-Based Parallel Genetic Algorithm for CpG-Site Selection in Age Prediction

Momeni

Abadeh

2019

Genes

View full text Add to dashboard Cite

Genomic biomarkers such as DNA methylation (DNAm) are employed for age prediction. In recent years, several studies have suggested the association between changes in DNAm and its effect on human age. The high dimensional nature of this type of data significantly increases the execution time of modeling algorithms. To mitigate this problem, we propose a two-stage parallel algorithm for selection of age related CpG-sites. The algorithm first attempts to cluster the data into similar age ranges. In the next stage, a parallel genetic algorithm (PGA), based on the MapReduce paradigm (MR-based PGA), is used for selecting age-related features of each individual age range. In the proposed method, the execution of the algorithm for each age range (data parallel), the evaluation of chromosomes (task parallel) and the calculation of the fitness function (data parallel) are performed using a novel parallel framework. In this paper, we consider 16 different healthy DNAm datasets that are related to the human blood tissue and that contain the relevant age information. These datasets are combined into a single unioned set, which is in turn randomly divided into two sets of train and test data with a ratio of 7:3, respectively. We build a Gradient Boosting Regressor (GBR) model on the selected CpG-sites from the train set. To evaluate the model accuracy, we compared our results with state-of-the-art approaches that used these datasets, and observed that our method performs better on the unseen test dataset with a Mean Absolute Deviation (MAD) of 3.62 years, and a correlation (R2) of 95.96% between age and DNAm. In the train data, the MAD and R2 are 1.27 years and 99.27%, respectively. Finally, we evaluate our method in terms of the effect of parallelization in computation time. The algorithm without parallelization requires 4123 min to complete, whereas the parallelized execution on 3 computing machines having 32 processing cores each, only takes a total of 58 min. This shows that our proposed algorithm is both efficient and scalable.

show abstract

Section: Classificationmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

MapReduce-Based Parallel Genetic Algorithm for CpG-Site Selection in Age Prediction

Momeni

Abadeh

2019

Genes

View full text Add to dashboard Cite

show abstract

Predicting human age by detecting DNA methylation status in hair

et al. 2021

View full text Add to dashboard Cite

Age prediction is of great importance for criminal investigation and judicial expertise. DNA methylation status is considered a promising method to infer tissue age by virtue of age‐dependent changes on methylation sites. In recent years, forensic scientists have established various models to predict the chronological age of blood, saliva, and semen based on DNA methylation status. However, hair‐inferred age has not been studied in the field of forensic science. In this study, we measured the methylation statuses of potential age‐related CpG sites by using the multiplex methylation SNaPshot method. A total of 10 CpG sites from the LAG3, SCGN, ELOVL2, KLF14, C1orf132, SLC12A5, GRIA2, and PDE4C genes were found to be tightly associated with age in hair follicles. A correlation coefficient above 0.7 was found for four CpG sites (cg24724428 and Chr6:11044628 in ELOVL2, cg25148589 in GRIA2, and cg07547549 in SLC12A5). Among four age‐prediction models, the multiple linear regression model consisting of 10 CpG sites provided the best‐fitting results, with a median absolute deviation of 3.68 years. It is feasible to obtain both human identification and age information from a single scalp hair follicle. No significant differences in methylation degree were found between different sexes, hair types, or hair colors. In conclusion, we established a method to evaluate chronological age by assessing DNA methylation status in hair follicles.

show abstract