FASTmC: A Suite of Predictive Models for Nonreference-Based Estimations of DNA Methylation.
Ontology highlight
ABSTRACT:
SUBMITTER: Bewick AJ
PROVIDER: S-EPMC4751562 | biostudies-literature | 2015 Dec
REPOSITORIES: biostudies-literature
Publications
FASTmC: A Suite of Predictive Models for Nonreference-Based Estimations of DNA Methylation.
Bewick Adam J AJ Hofmeister Brigitte T BT Lee Kevin K Zhang Xiaoyu X Hall David W DW Schmitz Robert J RJ
G3 (Bethesda, Md.) 20151217 2
We describe a suite of predictive models, coined FAST(m)C, for nonreference, cost-effective exploration and comparative analysis of context-specific DNA methylation levels. Accurate estimations of true DNA methylation levels can be obtained from as few as several thousand short-reads generated from whole-genome bisulfite sequencing. These models make high-resolution time course or developmental and large diversity studies practical regardless of species, genome size, and availability of a refere ...[more]
Similar Datasets
Project description:We describe a suite of predictive models, coined FASTmC, for non-reference, cost-effective exploration and comparative analysis of context-specific DNA methylation levels. Accurate estimations of true DNA methylation levels can be obtained from as few as several thousand short-reads generated from whole genome bisulfite sequencing. Our models make high-resolution time course or developmental, and large diversity studies practical regardless of species, genome size and availability of a reference genome.
2016-08-17 | GSE72155 | GEO
Project description:FASTmC: predictive models for non-reference-based estimations of DNA methylation
| PRJNA293211 | ENA
Project description:BackgroundThe computational prediction of methylation levels at single CpG resolution is promising to explore the methylation levels of CpGs uncovered by existing array techniques, especially for the 450?K beadchip array data with huge reserves. General prediction models concentrate on improving the overall prediction accuracy for the bulk of CpG loci while neglecting whether each locus is precisely predicted. This leads to the limited application of the prediction results, especially when performing downstream analysis with high precision requirements.ResultsHere we reported PretiMeth, a method for constructing precise prediction models for each single CpG locus. PretiMeth used a logistic regression algorithm to build a prediction model for each interested locus. Only one DNA methylation feature that shared the most similar methylation pattern with the CpG locus to be predicted was applied in the model. We found that PretiMeth outperformed other algorithms in the prediction accuracy, and kept robust across platforms and cell types. Furthermore, PretiMeth was applied to The Cancer Genome Atlas data (TCGA), the intensive analysis based on precise prediction results showed that several CpG loci and genes (differentially methylated between the tumor and normal samples) were worthy for further biological validation.ConclusionThe precise prediction of single CpG locus is important for both methylation array data expansion and downstream analysis of prediction results. PretiMeth achieved precise modeling for each CpG locus by using only one significant feature, which also suggested that our precise prediction models could be probably used for reference in the probe set design when the DNA methylation beadchip update. PretiMeth is provided as an open source tool via https://github.com/JxTang-bioinformatics/PretiMeth.
| S-EPMC7227319 | biostudies-literature
Project description:Cancer-specific DNA methylation from the tumor derived fraction of cell free DNA found in blood samples could be used for minimally invasive detection and monitoring of cancer. The knowledge of marker regions with cancer-specific DNA methylation is necessary to the success of such a process. We analyzed the largest cancer DNA methylation dataset available-TCGA Illumina HumanMethylation450 data with over 8,500 tumors-in order to find cancer-specific DNA methylation markers for most common human cancers. First, we identified differentially methylated regions for individual cancer types and those were further filtered against data from normal tissues to obtain marker regions with cancer-specific methylation, resulting in a total of 1,250 hypermethylated and 584 hypomethylated marker CpGs. From hypermethylated markers, optimal sets of six markers for each TCGA cancer type were chosen that could identify most tumors with high specificity and sensitivity [area under the curve (AUC): 0.969-1.000] and a universal 12 marker set that can detect tumors of all 33 TCGA cancer types (AUC >0.84). In addition to hundreds of new DNA methylation markers, our approach also identified markers that are in current clinical use, SEPT9 and GSTP1, indicating the validity of our approach and a significant potential utility for the newly discovered markers. The hypermethylated markers are linked to polycomb associated loci and a significant fraction of the discovered markers is within noncoding RNA genes; one of the best markers is MIR129-2. Future clinical testing of herein discovered markers will confirm new markers that will improve minimally invasive diagnosis and monitoring for multiple cancers.
| S-EPMC5836970 | biostudies-literature
Project description:BackgroundProstate cancer has a variable clinical behaviour with frequently unpredictable outcome. DNA methylation plays an important role in determining the biology of cancer but prognostic information is scanty. We assessed the potential of gene-specific DNA methylation changes to predict death from prostate cancer in a cohort of untreated men in the UK.MethodsThis was a population-based study in which cases were identified from six cancer registries in Great Britain. DNA was extracted from formalin-fixed paraffin wax-embedded transurethral prostate resection tissues collected during 1990-96 from men with clinically-localised cancer who chose not to be treated for at least 6 months following diagnosis. The primary end point was death from prostate cancer. Outcomes were determined through medical records and cancer registry records. Pyrosequencing was used to quantify methylation in 13 candidate genes with established or suggested roles in cancer. Univariate and multivariate Cox models were used to identify possible predictors for prostate cancer-related death.ResultsOf 367 men, 99 died from prostate cancer during a median of 9.5 years follow-up (max = 20). Univariately, 12 genes were significantly associated with prostate cancer mortality, hazard ratios ranged between 1.09 and 1.28 per decile increase in methylation. Stepwise Cox regression modelling suggested that the methylation of genes HSPB1, CCND2 and DPYS contributed objective prognostic information to Gleason score and PSA with respect to cancer-related death during follow-up (p = 0.006).ConclusionMethylation of 13 genes was analysed in 367 men with localised prostate cancer who were conservatively treated and stratified with respect to death from prostate cancer and those who survived or died of other causes. Of the 13 genes analysed, differential methylation of HSPB1, CCND2 and DPYS provided independent prognostic information. Assessment of gene-methylation may provide independent objective information that can be used to segregate prostate cancers at diagnosis into predicted behavioural groups.
| S-EPMC4162944 | biostudies-literature
Project description:Machine learning and data analytics are being increasingly used for quantitative structure property relation (QSPR) applications in the chemical domain where the traditional Edisonian approach towards knowledge-discovery have not been fruitful. The perception of odorant stimuli is one such application as olfaction is the least understood among all the other senses. In this study, we employ machine learning based algorithms and data analytics to address the efficacy of using a data-driven approach to predict the perceptual attributes of an odorant namely the odorant characters (OC) of "sweet" and "musky". We first analyze a psychophysical dataset containing perceptual ratings of 55 subjects to reveal patterns in the ratings given by subjects. We then use the data to train several machine learning algorithms such as random forest, gradient boosting and support vector machine for prediction of the odor characters and report the structural features correlating well with the odor characters based on the optimal model. Furthermore, we analyze the impact of the data quality on the performance of the models by comparing the semantic descriptors generally associated with a given odorant to its perception by majority of the subjects. The study presents a methodology for developing models for odor perception and provides insights on the perception of odorants by untrained human subjects and the effect of the inherent bias in the perception data on the model performance. The models and methodology developed here could be used for predicting odor characters of new odorants.
| S-EPMC7553929 | biostudies-literature
Project description:Introduction: Despite the significant progress in understanding cancer biology, the deduction of metastasis is still a challenge in the clinic. Transcriptional regulation is one of the critical mechanisms underlying cancer development. Even though mRNA, microRNA, and DNA methylation mechanisms have a crucial impact on the metastatic outcome, there are no comprehensive data mining models that combine all transcriptional regulation aspects for metastasis prediction. This study focused on identifying the regulatory impact of genetic biomarkers for monitoring metastatic molecular signatures of melanoma by investigating the consolidated effect of miRNA, mRNA, and DNA methylation. Method: We developed multiple machine learning models to distinguish the metastasis by integrating miRNA, mRNA, and DNA methylation markers. We used the TCGA melanoma dataset to differentiate between metastatic melanoma samples by assessing a set of predictive models. For this purpose, machine learning models using a support vector machine with different kernels, artificial neural networks, random forests, AdaBoost, and Naïve Bayes are compared. An iterative combination of differentially expressed miRNA, mRNA, and methylation signatures is used as a candidate marker to reveal each new biomarker category's impact. In each iteration, the performances of the combined models are calculated. During all comparisons, the choice of the feature selection method and under and oversampling approaches are analyzed. Selected biomarkers of the highest performing models are further analyzed for the biological interpretation of functional enrichment. Results: In the initial model, miRNA biomarkers can identify metastatic melanoma with an 81% F-score. The addition of mRNA markers upon miRNA increased the F-score to 92%. In the final integrated model, the addition of the methylation data resulted in a similar F-score of 92% but produced a stable model with low variance across multiple trials. Conclusion: Our results support the role of miRNA regulation in metastatic melanoma as miRNA markers model metastasis outcomes with high accuracy. Moreover, the integrated evaluation of miRNA with mRNA and methylation biomarkers increases the model's power. It populates selected biomarkers on the metastasis-associated pathways of melanoma, such as the "osteoclast", "Rap1 signaling", and "chemokine signaling" pathways. Source Code: https://github.com/aysegul-kt/MelonomaMetastasisPrediction/.
| S-EPMC8495312 | biostudies-literature
Project description:Schizophrenia (SZ) is a debilitating disease that impacts 1% of the population worldwide. Association studies have shown that inherited genetic mutations account for a portion of disease risk. However, environmental factors play an important role in the pathophysiology of the disease by altering cellular epigenetic marks at the level of chromatin. Postmortem brain studies of SZ subjects suggest that the dynamic equilibrium between DNA methylation and demethylation network components is disrupted at the level of individual SZ target genes. Herein, we review the role of DNA methylation and demethylation in the context of what is currently known regarding SZ. Furthermore, we describe the deficits that accompany two mouse models of SZ. The chronic methionine mouse model of SZ is predicated on the administration of methionine to SZ patients and controls in the context of clinical studies that were carried out during the 1960s and 1970s. The prenatal restraint stress model of SZ is based on a prolonged stress paradigm administered to pregnant dams during gestation days 7-21. The adult offspring of these dams show various behavioral and biochemical deficits in adulthood. Both models are epigenetic in origin and mimic the positive and negative symptoms, as well as the cognitive endophenotypes commonly observed in SZ patients. We also discuss the utility of typical and atypical antipsychotic drugs in alleviating these symptoms in each model.
| S-EPMC7939130 | biostudies-literature
Project description:DNA methylation has been identified as the most promising molecular biomarker for the prediction of age. Several DNA methylation-based models have been proposed for age prediction based on blood samples, using mainly pyrosequencing. These methods present different performances for age prediction and have rarely, if ever, been evaluated and intercompared in an independent validation study. Here, for the first time, we evaluate and compare six blood-based age prediction models (Bekaert1, Park2, Thong3, Weidner4, and the Zbiec-Piekarska 15 and Zbiec-Piekarska 26), using DNA methylation analysis by pyrosequencing on 100 blood samples from French individuals aged between 19-65 years. For each model, we perform correlation analysis and evaluate age-prediction performance (mean absolute deviation (MAD) and standard error of the estimate (SEE)). The best age-prediction performances were found with the Bekaert and Thong models (MAD of 4.5-5.2, SEE of 6.8-7.2), followed by the Zbiec-Piekarska 1 model (MAD of 6.8 and SEE of 9.2), while the Park, Weidner and Zbiec-Piekarska 2 models presented lower performances (MAD of 7.2-8.7 and SEE of 9.2-10.3). Given these results, we recommend performing systematic, independent evaluation of all age prediction models on a same cohort to validate the different models and compare their performance.
| S-EPMC6586942 | biostudies-literature
Project description:In allostery, a binding event at one site in a protein modulates the behavior of a distant site. Identifying residues that relay the signal between sites remains a challenge. We have developed predictive models using support-vector machines, a widely used machine-learning method. The training data set consisted of residues classified as either hotspots or non-hotspots based on experimental characterization of point mutations from a diverse set of allosteric proteins. Each residue had an associated set of calculated features. Two sets of features were used, one consisting of dynamical, structural, network, and informatic measures, and another of structural measures defined by Daily and Gray. The resulting models performed well on an independent data set consisting of hotspots and non-hotspots from five allosteric proteins. For the independent data set, our top 10 models using Feature Set 1 recalled 68-81% of known hotspots, and among total hotspot predictions, 58-67% were actual hotspots. Hence, these models have precision P = 58-67% and recall R = 68-81%. The corresponding models for Feature Set 2 had P = 55-59% and R = 81-92%. We combined the features from each set that produced models with optimal predictive performance. The top 10 models using this hybrid feature set had R = 73-81% and P = 64-71%, the best overall performance of any of the sets of models. Our methods identified hotspots in structural regions of known allosteric significance. Moreover, our predicted hotspots form a network of contiguous residues in the interior of the structures, in agreement with previous work. In conclusion, we have developed models that discriminate between known allosteric hotspots and non-hotspots with high accuracy and sensitivity. Moreover, the pattern of predicted hotspots corresponds to known functional motifs implicated in allostery, and is consistent with previous work describing sparse networks of allosterically important residues.
| S-EPMC2748687 | biostudies-literature