Dataset Information

A machine learning case-control classifier for schizophrenia based on DNA methylation in blood.

ABSTRACT: Epigenetic dysregulation is thought to contribute to the etiology of schizophrenia (SZ), but the cell type-specificity of DNA methylation makes population-based epigenetic studies of SZ challenging. To train an SZ case-control classifier based on DNA methylation in blood, therefore, we focused on human genomic regions of systemic interindividual epigenetic variation (CoRSIVs), a subset of which are represented on the Illumina Human Methylation 450K (HM450) array. HM450 DNA methylation data on whole blood of 414 SZ cases and 433 non-psychiatric controls were used as training data for a classification algorithm with built-in feature selection, sparse partial least squares discriminate analysis (SPLS-DA); application of SPLS-DA to HM450 data has not been previously reported. Using the first two SPLS-DA dimensions we calculated a "risk distance" to identify individuals with the highest probability of SZ. The model was then evaluated on an independent HM450 data set on 353 SZ cases and 322 non-psychiatric controls. Our CoRSIV-based model classified 303 individuals as cases with a positive predictive value (PPV) of 80%, far surpassing the performance of a model based on polygenic risk score (PRS). Importantly, risk distance (based on CoRSIV methylation) was not associated with medication use, arguing against reverse causality. Risk distance and PRS were positively correlated (Pearson r = 0.28, P = 1.28 × 10^-12), and mediational analysis suggested that genetic effects on SZ are partially mediated by altered methylation at CoRSIVs. Our results indicate two innate dimensions of SZ risk: one based on genetic, and the other on systemic epigenetic variants.

SUBMITTER: Gunasekara CJ

PROVIDER: S-EPMC8329061 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description:BackgroundSeveral reports have suggested a role for epigenetic mechanisms in ASD etiology. Epigenome-wide association studies (EWAS) in autism spectrum disorder (ASD) may shed light on particular biological mechanisms. However, studies of ASD cases versus controls have been limited by post-mortem timing and severely small sample sizes. Reports from in-life sampling of blood or saliva have also been very limited in sample size and/or genomic coverage. We present the largest case-control EWAS for ASD to date, combining data from population-based case-control and case-sibling pair studies.MethodsDNA from 968 blood samples from children in the Study to Explore Early Development (SEED 1) was used to generate epigenome-wide array DNA methylation (DNAm) data at 485,512 CpG sites for 453 cases and 515 controls, using the Illumina 450K Beadchip. The Simons Simplex Collection (SSC) provided 450K array DNAm data on an additional 343 cases and their unaffected siblings. We performed EWAS meta-analysis across results from the two data sets, with adjustment for sex and surrogate variables that reflect major sources of biological variation and technical confounding such as cell type, batch, and ancestry. We compared top EWAS results to those from a previous brain-based analysis. We also tested for enrichment of ASD EWAS CpGs for being targets of meQTL associations using available SNP genotype data in the SEED sample.FindingsIn this meta-analysis of blood-based DNA from 796 cases and 858 controls, no single CpG met a Bonferroni discovery threshold of p < 1.12 × 10- 7. Seven CpGs showed differences at p < 1 × 10- 5 and 48 at 1 × 10- 4. Of the top 7, 5 showed brain-based ASD associations as well, often with larger effect sizes, and the top 48 overall showed modest concordance (r = 0.31) in direction of effect with cerebellum samples. Finally, we observed suggestive evidence for enrichment of CpG sites controlled by SNPs (meQTL targets) among the EWAS CpG hits, which was consistent across EWAS and meQTL discovery p value thresholds.ConclusionsNo single CpG site showed a large enough DNAm difference between cases and controls to achieve epigenome-wide significance in this sample size. However, our results suggest the potential to observe disease associations from blood-based samples. Among the seven sites achieving suggestive statistical significance, we observed consistent, and stronger, effects at the same sites among brain samples. Discovery-oriented EWAS for ASD using blood samples will likely need even larger samples and unified genetic data to further understand DNAm differences in ASD.

Project description:Background:Current standard methods used to detect and monitor bladder cancer (BC) are invasive or have low sensitivity. This study aimed to develop a urine methylation biomarker classifier for BC monitoring and validate this classifier in patients in follow-up for bladder cancer (PFBC). Methods:Voided urine samples (N?=?725) from BC patients, controls, and PFBC were prospectively collected in four centers. Finally, 626 urine samples were available for analysis. DNA was extracted from the urinary cells and bisulfite modificated, and methylation status was analyzed using pyrosequencing. Cytology was available from a subset of patients (N?=?399). In the discovery phase, seven selected genes from the literature (CDH13, CFTR, NID2, SALL3, TMEFF2, TWIST1, and VIM2) were studied in 111 BC and 57 control samples. This training set was used to develop a gene classifier by logistic regression and was validated in 458 PFBC samples (173 with recurrence). Results:A three-gene methylation classifier containing CFTR, SALL3, and TWIST1 was developed in the training set (AUC 0.874). The classifier achieved an AUC of 0.741 in the validation series. Cytology results were available for 308 samples from the validation set. Cytology achieved AUC 0.696 whereas the classifier in this subset of patients reached an AUC 0.768. Combining the methylation classifier with cytology results achieved an AUC 0.86 in the validation set, with a sensitivity of 96%, a specificity of 40%, and a positive and negative predictive value of 56 and 92%, respectively. Conclusions:The combination of the three-gene methylation classifier and cytology results has high sensitivity and high negative predictive value in a real clinical scenario (PFBC). The proposed classifier is a useful test for predicting BC recurrence and decrease the number of cystoscopies in the follow-up of BC patients. If only patients with a positive combined classifier result would be cystoscopied, 36% of all cystoscopies can be prevented.

Project description:Pediatric sarcomas provide a unique diagnostic challenge. There is considerable morphologic overlap between entities, increasing the importance of molecular studies in the diagnosis, treatment, and identification of therapeutic targets. We developed and validated a genome-wide DNA methylation based classifier to differentiate between osteosarcoma, Ewing's sarcoma, and synovial sarcoma. DNA methylation status of 482,421 CpG sites in 10 Ewing's sarcoma, 11 synovial sarcoma, and 15 osteosarcoma samples were determined using the Illumina Infinium HumanMethylation450 array. We developed a random forest classifier trained from the 400 most differentially methylated CpG sites within the training set of 36 sarcoma samples. This classifier was validated on data drawn from The Cancer Genome Atlas (TCGA) synovial sarcoma, TARGET Osteosarcoma, and a recently published series of Ewing's sarcoma. Methylation profiling revealed three distinct patterns, each enriched with a single sarcoma subtype. Within the validation cohorts, all samples from TCGA were accurately classified as synovial sarcoma (10/10, sensitivity and specificity 100%), all but one sample from TARGET-OS were classified as osteosarcoma (85/86, sensitivity 98%, specificity 100%) and 14/15 Ewing's sarcoma samples classified correctly (sensitivity 93%, specificity 100%). The single misclassified osteosarcoma sample demonstrated high EWSR1 and ETV1 expression on RNA-seq although no fusion was found on manual curation of the transcript sequence. Two additional clinical samples, that were difficult to classify by morphology and molecular methods, were classified as osteosarcoma when previously suspected to be a synovial sarcoma and Ewing's sarcoma on initial diagnosis, respectively. Osteosarcoma, synovial sarcoma, and Ewing's sarcoma have distinct epigenetic profiles. Our validated methylation-based classifier can be used to provide diagnostic assistance when histological and standard techniques are inconclusive.

Dataset Information

A machine learning case-control classifier for schizophrenia based on DNA methylation in blood.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets