Chronological Age Prediction: Developmental Evaluation of DNA Methylation-Based Machine Learning Models

Male-specific age prediction based on Y-chromosome DNA methylation with blood using pyrosequencing

Age prediction is an important aspect of forensic science that offers valuable insight into identification. In recent years, extensive studies have been conducted on age prediction based on DNA methylation, and numerous studies have demonstrated that DNA methylation is a reliable biomarker for age prediction. However, almost all studies on age prediction based on DNA methylation have focused on age-related CpG sites in autosomes, which are concentrated on single-source DNA samples. Mixed samples, especially male-female mixed samples, are common in forensic casework. The application of Y-STRs and Y-SNPs can provide clues for the genetic typing of male individuals in male-female mixtures, but they cannot provide the age information of male individuals. Studies on Y-chromosome DNA methylation can address this issue. In this study, we identified five age-related CpG sites on the Y chromosome (Y-CpGs) and developed a male-specific age prediction model using pyrosequencing combined with a support vector machine algorithm. The mean absolute deviation of the model was 5.50 years in the training set and 6.74 years in the testing set. When we used a male blood sample to predict age, the deviation between the predicted and chronological age was 1.18 years. Then, we mixed the genomic DNA of the male and a female at ratios of 1:1, 1:5, 1:10, and 1:50, the range of deviation between the predicted and chronological age of the male in the mixture was 1.16-1.74 years. In addition, there was no significant difference between the methylation values of bloodstains and blood in the same sample, which indicates that our model is also suitable for bloodstain samples. Overall, our results show that age prediction using DNA methylation of the Y chromosome has potential applications in forensic science and can be of great help in predicting the age of males in male-female mixtures. Furthermore, this work lays the foundation for future research on age-related applications of Y-CpGs.

Lipoproteins and metabolites in diagnosing and predicting Alzheimer's disease using machine learning

BACKGROUND

Alzheimer's disease (AD) is a chronic neurodegenerative disorder that poses a substantial economic burden. The Random forest algorithm is effective in predicting AD; however, the key factors influencing AD onset remain unclear. This study aimed to analyze the key lipoprotein and metabolite factors influencing AD onset using machine-learning methods. It provides new insights for researchers and medical personnel to understand AD and provides a reference for the early diagnosis, treatment, and early prevention of AD.

METHODS

A total of 603 participants, including controls and patients with AD with complete lipoprotein and metabolite data from the Alzheimer's disease Neuroimaging Initiative (ADNI) database between 2005 and 2016, were enrolled. Random forest, Lasso regression, and CatBoost algorithms were employed to rank and filter 213 lipoprotein and metabolite variables. Variables with consistently high importance rankings from any two methods were incorporated into the models. Finally, the variables selected from the three methods, with the participants' age, sex, and marital status, were used to construct a random forest predictive model.

RESULTS

Fourteen lipoprotein and metabolite variables were screened using the three methods, and 17 variables were included in the AD prediction model based on age, sex, and marital status of the participants. The optimal random forest modeling was constructed with "mtry" set to 3 and "ntree" set to 300. The model exhibited an accuracy of 71.01%, a sensitivity of 79.59%, a specificity of 65.28%, and an AUC (95%CI) of 0.724 (0.645-0.804). When Mean Decrease Accuracy and Gini were used to rank the proteins, age, phospholipids to total lipids ratio in intermediate-density lipoproteins (IDL_PL_PCT), and creatinine were among the top five variables.

CONCLUSIONS

Age, IDL_PL_PCT, and creatinine levels play crucial roles in AD onset. Regular monitoring of lipoproteins and their metabolites in older individuals is significant for early AD diagnosis and prevention.

Epigenetic analyses in forensic medicine: future and challenges

The possibility of using epigenetics in forensic investigation has gradually risen over the last few years. Epigenetic changes with their dynamic nature can either be inherited or accumulated throughout a lifetime and be reversible, prompting investigation of their use across various fields. In forensic sciences, multiple applications have been proposed, such as the discrimination of monozygotic twins, identifying the source of a biological trace left at a crime scene, age prediction, determination of body fluids and tissues, human behavior association, wound healing progression, and determination of the post-mortem interval (PMI). Despite all these applications, not all the studies considered the impact of PMI and post-sampling effects on the epigenetic modifications and the tissue-specificity of the epigenetic marks.This review aims to highlight the substantial forensic significance that epigenetics could support in various forensic investigations. First, basic concepts in epigenetics, describing the main epigenetic modifications and their functions, in particular, DNA methylation, histone modifications, and non-coding RNA, with a particular focus on forensic applications, were covered. For each epigenetic marker, post-mortem stability and tissue-specificity, factors that should be carefully considered in the study of epigenetic biomarkers in the forensic context, have been discussed. The advantages and limitations of using post-mortem tissues have been also addressed, proposing directions for these innovative strategies to analyze forensic specimens.

Development and comparison of forensic interval age prediction models by statistical and machine learning methods based on the methylation rates of ELOVL2 in blood DNA

Age estimation can be useful information for narrowing down candidates of unidentified donors in criminal investigations. Various age estimation models based on DNA methylation biomarkers have been developed for forensic usage in the past decade. However, many of these models using ordinary least squares regression cannot generate an appropriate estimation due to the deterioration in prediction accuracy caused by an increased prediction error in older age groups. In the present study, to address this problem, we developed age estimation models that set an appropriate prediction interval for all age groups by two approaches: a statistical method using quantile regression (QR) and a machine learning method using an artificial neural network (ANN). Methylation datasets (n = 1280, age 0-91 years) of the promoter for the gene encoding ELOVL fatty acid elongase 2 were used to develop the QR and ANN models. By validation using several test datasets, both models were shown to enlarge prediction intervals in accordance with aging and have a high level of correct prediction (>90 %) for older age groups. The QR and ANN models also generated a point age prediction with high accuracy. The ANN model enabled a prediction with a mean absolute error (MAE) of 5.3 years and root mean square error (RMSE) of 7.3 years for the test dataset (n = 549), which were comparable to those of the QR model (MAE = 5.6 years, RMSE = 7.8 years). Their applicability to casework was also confirmed using bloodstain samples stored for various periods of time (1-14 years), indicating the stability of the models for aged bloodstain samples. From these results, it was considered that the proposed models can provide more useful and effective age estimation in forensic settings.

Estimation of Human Chronological Age from Buccal Swab Samples through a DNA Methylation Analysis Approach of a Five-Locus Multiple Regression Model

Recent advancements in forensic genetics have facilitated the extraction of additional characteristics from unidentified samples. This study delves into the predictive potential of a five-gene (ELOVL2, FHL2, KLF14, C1orf132, and TRIM59) methylation rate analysis for human age estimation using buccal swabs collected from 60 Italian volunteers. The methylation levels of specific CpG sites in the five genes were analyzed through bisulfite conversion, single-base extension, and capillary electrophoresis. A multivariate linear regression model was crafted on the training set, then the test set was employed to validate the predictive model. The multivariate predictive model revealed a mean absolute deviation of 3.49 years in the test set of our sample. While limitations include a modest sample size, the study provides valuable insights into the potential of buccal swab-based age prediction, aiding in criminal investigations where accurate age determination is crucial. Our results also highlight that it is necessary to investigate the effectiveness of predictive models specific to biological tissues and individual populations, since models already proven effective for other populations or different tissues did not show the same effectiveness in our study.

Yearning for machine learning: applications for the classification and characterisation of senescence

Senescence is a widely appreciated tumour suppressive mechanism, which acts as a barrier to cancer development by arresting cell cycle progression in response to harmful stimuli. However, senescent cell accumulation becomes deleterious in aging and contributes to a wide range of age-related pathologies. Furthermore, senescence has beneficial roles and is associated with a growing list of normal physiological processes including wound healing and embryonic development. Therefore, the biological role of senescent cells has become increasingly nuanced and complex. The emergence of sophisticated, next-generation profiling technologies, such as single-cell RNA sequencing, has accelerated our understanding of the heterogeneity of senescence, with distinct final cell states emerging within models as well as between cell types and tissues. In order to explore data sets of increasing size and complexity, the senescence field has begun to employ machine learning (ML) methodologies to probe these intricacies. Most notably, ML has been used to aid the classification of cells as senescent, as well as to characterise the final senescence phenotypes. Here, we provide a background to the principles of ML tasks, as well as some of the most commonly used methodologies from both traditional and deep ML. We focus on the application of these within the context of senescence research, by addressing the utility of ML for the analysis of data from different laboratory technologies (microscopy, transcriptomics, proteomics, methylomics), as well as the potential within senolytic drug discovery. Together, we aim to highlight both the progress and potential for the application of ML within senescence research.

How can we modulate aging through nutrition and physical exercise? An epigenetic approach

The World Health Organization predicts that by 2050, 2.1 billion people worldwide will be over 60 years old, a drastic increase from only 1 billion in 2019. Considering these numbers, strategies to ensure an extended "healthspan" or healthy longevity are urgently needed. The present study approaches the promotion of healthspan from an epigenetic perspective. Epigenetic phenomena are modifiable in response to an individual's environmental exposures, and therefore link an individual's environment to their gene expression pattern. Epigenetic studies demonstrate that aging is associated with decondensation of the chromatin, leading to an altered heterochromatin structure, which promotes the accumulation of errors. In this review, we describe how aging impacts epigenetics and how nutrition and physical exercise can positively impact the aging process, from an epigenetic point of view. Canonical histones are replaced by histone variants, concomitant with an increase in histone post-translational modifications. A slight increase in DNA methylation at promoters has been observed, which represses transcription of previously active genes, in parallel with global genome hypomethylation. Aging is also associated with deregulation of gene expression - usually provided by non-coding RNAs - leading to both the repression of previously transcribed genes and to the transcription of previously repressed genes. Age-associated epigenetic events are less common in individuals with a healthy lifestyle, including balanced nutrition, caloric restriction and physical exercise. Healthy aging is associated with more tightly condensed chromatin, fewer PTMs and greater regulation by ncRNAs.

An ELOVL2-Based Epigenetic Clock for Forensic Age Prediction: A Systematic Review

The prediction of chronological age from methylation-based biomarkers represents one of the most promising applications in the field of forensic sciences. Age-prediction models developed so far are not easily applicable for forensic caseworkers. Among the several attempts to pursue this objective, the formulation of single-locus models might represent a good strategy. The present work aimed to develop an accurate single-locus model for age prediction exploiting ELOVL2, a gene for which epigenetic alterations are most highly correlated with age. We carried out a systematic review of different published pyrosequencing datasets in which methylation of the ELOVL2 promoter was analysed to formulate age prediction models. Nine of these, with available datasets involving 2298 participants, were selected. We found that irrespective of which model was adopted, a very strong relationship between ELOVL2 methylation levels and age exists. In particular, the model giving the best age-prediction accuracy was the gradient boosting regressor with a prediction error of about 5.5 years. The findings reported here strongly support the use of ELOVL2 for the formulation of a single-locus epigenetic model, but the inclusion of additional, non-redundant markers is a fundamental requirement to apply a molecular model to forensic applications with more robust results.

Pyrosequencing: Current forensic methodology and future applications-a review

The recent development of small, single-amplicon-based benchtop systems for pyrosequencing has opened up a host of novel procedures for applications in forensic science. Pyrosequencing is a sequencing by synthesis technique, based on chemiluminescent inorganic pyrophosphate detection. This review explains the pyrosequencing workflow and illustrates the step-by-step chemistry, followed by a description of the assay design and factors to keep in mind for an exemplary assay. Existing and potential forensic applications are highlighted using this technology. Current applications include identifying species, identifying bodily fluids, and determining smoking status. We also review progress in potential applications for the future, including research on distinguishing monozygotic twins, detecting alcohol and drug abuse, and other phenotypic characteristics such as diet and body mass index. Overall, the versatility of the pyrosequencing technologies renders it a useful tool in forensic genomics.