Dataset Information

Predictive models of gene regulation from high-throughput epigenomics data.

ABSTRACT: The epigenetic regulation of gene expression involves multiple factors. The synergistic or antagonistic action of these factors has suggested the existence of an epigenetic code for gene regulation. Highthroughput sequencing (HTS) provides an opportunity to explore this code and to build quantitative models of gene regulation based on epigenetic differences between specific cellular conditions. We describe a new computational framework that facilitates the systematic integration of HTS epigenetic data. Our method relates epigenetic signals to expression by comparing two conditions. We show its effectiveness by building a model that predicts with high accuracy significant expression differences between two cell lines, using epigenetic data from the ENCODE project. Our analyses provide evidence for a degenerate epigenetic code, which involves multiple genic regions. In particular, signal changes at the 1st exon, 1st intron, and downstream of the polyadenylation site are found to associate strongly with expression regulation. Our analyses also show a different epigenetic code for intron-less and intron-containing genes. Our work provides a general methodology to do integrative analysis of epigenetic differences between cellular conditions that can be applied to other studies, like cell differentiation or carcinogenesis.

SUBMITTER: Althammer S

PROVIDER: S-EPMC3424690 | biostudies-literature | 2012

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Predictive models of gene regulation from high-throughput epigenomics data.

Althammer Sonja S Pagès Amadís A Eyras Eduardo E

Comparative and functional genomics 20120813

The epigenetic regulation of gene expression involves multiple factors. The synergistic or antagonistic action of these factors has suggested the existence of an epigenetic code for gene regulation. Highthroughput sequencing (HTS) provides an opportunity to explore this code and to build quantitative models of gene regulation based on epigenetic differences between specific cellular conditions. We describe a new computational framework that facilitates the systematic integration of HTS epigeneti ...[more]

PMID: 22924024

Similar Datasets

Project description:BackgroundThe functions of human cells are carried out by biomolecular networks, which include proteins, genes, and regulatory sites within DNA that encode and control protein expression. Models of biomolecular network structure and dynamics can be inferred from high-throughput measurements of gene and protein expression. We build on our previously developed fuzzy logic method for bridging quantitative and qualitative biological data to address the challenges of noisy, low resolution high-throughput measurements, i.e., from gene expression microarrays. We employ an evolutionary search algorithm to accelerate the search for hypothetical fuzzy biomolecular network models consistent with a biological data set. We also develop a method to estimate the probability of a potential network model fitting a set of data by chance. The resulting metric provides an estimate of both model quality and dataset quality, identifying data that are too noisy to identify meaningful correlations between the measured variables.ResultsOptimal parameters for the evolutionary search were identified based on artificial data, and the algorithm showed scalable and consistent performance for as many as 150 variables. The method was tested on previously published human cell cycle gene expression microarray data sets. The evolutionary search method was found to converge to the results of exhaustive search. The randomized evolutionary search was able to converge on a set of similar best-fitting network models on different training data sets after 30 generations running 30 models per generation. Consistent results were found regardless of which of the published data sets were used to train or verify the quantitative predictions of the best-fitting models for cell cycle gene dynamics.ConclusionOur results demonstrate the capability of scalable evolutionary search for fuzzy network models to address the problem of inferring models based on complex, noisy biomolecular data sets. This approach yields multiple alternative models that are consistent with the data, yielding a constrained set of hypotheses that can be used to optimally design subsequent experiments.

Project description:BackgroundEpigenetic alterations are known to correlate with changes in gene expression among various diseases including cancers. However, quantitative models that accurately predict the up or down regulation of gene expression are currently lacking.MethodsA new machine learning-based method of gene expression prediction is developed in the context of lung cancer. This method uses the Illumina Infinium HumanMethylation450K Beadchip CpG methylation array data from paired lung cancer and adjacent normal tissues in The Cancer Genome Atlas (TCGA) and histone modification marker CHIP-Seq data from the ENCODE project, to predict the differential expression of RNA-Seq data in TCGA lung cancers. It considers a comprehensive list of 1424 features spanning the four categories of CpG methylation, histone H3 methylation modification, nucleotide composition, and conservation. Various feature selection and classification methods are compared to select the best model over 10-fold cross-validation in the training data set.ResultsA best model comprising 67 features is chosen by ReliefF based feature selection and random forest classification method, with AUC = 0.864 from the 10-fold cross-validation of the training set and AUC = 0.836 from the testing set. The selected features cover all four data types, with histone H3 methylation modification (32 features) and CpG methylation (15 features) being most abundant. Among the dropping-off tests of individual data-type based features, removal of CpG methylation feature leads to the most reduction in model performance. In the best model, 19 selected features are from the promoter regions (TSS200 and TSS1500), highest among all locations relative to transcripts. Sequential dropping-off of CpG methylation features relative to different regions on the protein coding transcripts shows that promoter regions contribute most significantly to the accurate prediction of gene expression.ConclusionsBy considering a comprehensive list of epigenomic and genomic features, we have constructed an accurate model to predict transcriptomic differential expression, exemplified in lung cancer.

Dataset Information

Predictive models of gene regulation from high-throughput epigenomics data.

Publications

Predictive models of gene regulation from high-throughput epigenomics data.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets