Browse
Submit Data
Databases
API
Help

Dataset Information

0 Views

0 Connections

0 Citations

0 Reanalyses

0 Downloads

Omics score: 0

Longitudinal prediction of DNA methylation to forecast epigenetic outcomes

ABSTRACT: We introduce a probabilistic and longitudinal machine learning framework based on multi-mean Gaussian processes (GPs), accounting for individual and gene correlations across time. This method provides future predictions of DNA methylation status at different individual ages while accounting for uncertainty.

ORGANISM(S): Homo sapiens

PROVIDER: GSE254135 | GEO | 2025/05/14

REPOSITORIES: GEO

ACCESS DATA

Json Xml

Dataset's files

Source:

			Action	DRS
		Other

Items per page:

1 - 1 of 1

Similar Datasets

Accurate age prediction from blood using a small set of DNA methylation sites and a cohort-based machine learning algorithm

Project description:Chronological age prediction from DNA methylation sheds light on human aging, indicates poor health and predicts lifespan. Previous studies developed methylation clocks based on linear regression models on methylation array data. While accurate, these models are limited to fixed-rate changes in methylation levels across age. Moreover, the high cost of methylation arrays, compared to targeted-PCR sequencing, hinders widespread utility of such predictors. We present an AI-based alternative termed GP-age, which uses a non-parametric approach based on Gaussian Process Regression of a large cohort of ~12K blood methylomes. Given a new blood sample, methylation levels are compared to the cohort samples, which are then weighted to predict the query age. Using only 30 CpG sites, our approach outperforms state-of-the-art methylation clocks that use hundreds of sites, with a median error of 2.1 years (on held-out data). Our model was also applied to sequencing-based data yielding highly accurate predictions. Overall, we provide an accessible alternative to current array-based methylation clocks, with future applications in aging research, forensic profiling, and monitoring epigenetic processes in transplantation medicine and cancer.

2023-01-20 | GSE207605 | GEO

Mouse QRNA novel ncRNA prediction array

Project description:We used this array as described in Babak, Blencowe, anf Hughes (2005), to screen novel ncRNA predictions. See author supplementary data for more detailed probe information. Keywords: parallel sample

2005-03-08 | GSE2366 | GEO

Homo sapiens

Project description:Accounting for small variations in the tracrRNA sequence improves sgRNA activity predictions for CRISPR screening

| PRJNA832308 | ENA

Project description:GPS sequence

| PRJNA1058779 | ENA

Prediction of neurological outcomes shortly after cardiac arrest

Project description:Prediction of neurological outcomes shortly after cardiac arrest would represent a major breakthrough. We tested the ability of gene expression profiles of blood cells to predict outcome in cardiac arrest patients. 35 consecutive cardiac arrest patients treated with therapeutic hypothermia (33Â°C for 24h) were included in this prospective monocentre study. Cerebral Performance Category (CPC) was determined at discharge and 6 months later. All patients had blood sampling at the end of hypothermia. Gene expression profiles of blood cells were determined using 25,000~gene microarray in two groups of patients: good outcome (CPC 1-2) and bad outcome (CPC 3-5).

2013-06-01 | E-GEOD-29540 | biostudies-arrayexpress

Autism and anorexia nervosa: Longitudinal prediction of eating disorder outcomes.

Project description:BackgroundRecently, elevated levels of autistic features and autism diagnoses have been reported among people with anorexia nervosa (AN). In clinical settings high levels of autistic features have been linked to more complex, highly comorbid illness presentation and poorer treatment outcome. This study aimed to examine whether autistic features predict AN symptom profile in long term.MethodsAltogether 118 women with lived experience of AN completed two autism assessments at time 1, the Autism Diagnostic Observation Schedule (ADOS) and the short version of the Autism Quotient (AQ10). Measures assessing AN symptom profile, including eating disorders symptoms, anxiety, depression, OCD symptoms, and Body Mass Index (BMI), were also recorded. The symptom profile measures were administered again 6 months and 2 years later. We conducted two analyses to examine the extent to which the ADOS and AQ10 scores predicted broad AN symptom profile at each three time points.ResultsOverall, high levels of autistic features were consistently associated with worse psychological symptoms, but not BMI, across all time points. Both the analysis using baseline ADOS scores and self-reported AQ10 scores showed similar pattern.ConclusionThe present findings consolidate previously reported associations between autistic features and worse psychological outcome among people with AN. The findings also suggest that self-report measures may be sufficient for assessing the impact of autistic features on illness outcome among people with AN. Importantly, the study highlights the need for development and further investigation of neurodiversity accommodations in the treatment of AN.

| S-EPMC9533087 | biostudies-literature

Causal Modeling Using Network Ensemble Simulations Predicts Novel Lipid Metabolism Genes

Project description:We describe a simulation strategy for prediction of drug targets and functional analysis of genetically defined associations. This strategy utilizes Bayesian model averaging over a sample of parameterized networks to achieve robust predictions in light of uncertainty of the network structure. We illustrate the method with an analysis of liver gene expression, serum lipid profiles and body weight measured on 120 male mice from a mouse intercross population. An ensemble of 1024 networks, gave accurate predictions of animals that were not part of the training data and explained almost twice the variance compared to quantitative trait loci alone. Additional in silico experiments identified 38 transcripts that are predicted to impact serum lipid profiles and suggest that they play a role in controlling high density lipoprotein and free triglycerides plasma concentrations.

2010-03-10 | GSE15226 | GEO

Gene epxression profiling in murine Flt3+ granulocyte progenitors (Flt3+ GPs) and Flt3- granulocyte progenitors (Flt3- GPs)

Project description:To understand the mechanism by which IRF8 promotes basophil differentiation Murine bone marrow Flt3+ GPs and Flt3- GPs were isolated by cell sorting from wild-type or Irf8 deficient mice. Two independent experiments were performed.

2014-11-17 | E-GEOD-54887 | biostudies-arrayexpress

Alignment of multiple metabolomics LC-MS datasets from disparate diseases to reveal fever-associated metabolites

Project description:<p>Acute febrile illnesses are still a major cause of mortality and morbidity globally, particularly in low to middle income countries. The aim of this study was to determine any possible metabolic commonalities of patients infected with disparate pathogens that cause fever. Three liquid chromatography-mass spectrometry (LC-MS) datasets investigating the metabolic effects of malaria, leishmaniasis and Zika virus infection were used. The retention time (RT) drift between the datasets was determined using landmarks obtained from the internal standards generally used in the quality control of the LC-MS experiments. Fitted Gaussian Process models (GPs) were used to perform a high level correction of the RT drift between the experiments, which was followed by standard peakset alignment between the samples with corrected RTs of the three LC-MS datasets. Statistical analysis, annotation and pathway analysis of the integrated peaksets were subsequently performed. Metabolic dysregulation patterns common across the datasets were identified, with kynurenine pathway being the most affected pathway between all three fever-associated datasets.</p>

2023-07-17 | MTBLS4895 | MetaboLights

Prediction of neurological outcomes shortly after cardiac arrest

2013-06-01 | GSE29540 | GEO