1 - 35 of 35 results

kmer-SVM

Obsolete
A tool suite designed to aid in analysis of next-generation sequencing (NGS) data. kmer-SVM uses a support vector machine (SVM) with kmer sequence features to identify predictive combinations of short transcription factor binding sites which determine the tissue specificity of the original NGS assay. Information gained from kmer-SVM can be used as an additional source of confidence in genomic experiments by recovering known binding sites, and can also reveal novel sequence features and possible cooperative mechanisms to be tested experimentally.

Segway

Contains a method for analyzing multiple tracks of functional genomics data. Segway uses a dynamic Bayesian network (DBN) model, which enables it to analyze the entire genome at 1-bp resolution even in the face of heterogeneous patterns of missing data. This method is the first application of DBN techniques to genome-scale data and the first genomic segmentation method designed for use with the maximum resolution data available from ChIP-seq experiments without downsampling. Segway uses the Graphical Model Toolkit for efficient DBN inference.

EMERGE

A flexible and user-friendly tool to integrate the information from different types of genomic datasets, e.g. ATAC-seq, ChIP-seq, conservation, aiming to increase the ease and success rate of functional prediction. To this end, we developed the EMERGE program that merges all datasets that the user considers informative and uses a logistic regression framework, based on validated functional elements, to set optimal weights to these datasets. ROC curve analysis shows that a combination of datasets leads to improved prediction of tissue-specific enhancers in human, mouse and Drosophila genomes. Functional assays based on this prediction can be expected to have substantially higher success rates. The resulting integrated signal for prediction of functional elements can be plotted in a build-in genome browser or exported for further analysis.

i-cisTarget

An integrative genomics method for the prediction of regulatory features and cis-regulatory modules in Human, Mouse, and Fly. ii-cisTarget enables: (i) to detect transcription factor motifs in a set of peaks (e.g. differentially active peaks based on H3K27ac ChIP-seq between 2 conditions) or co-expressed genes, (ii) to detect overrepresented in vivo features (histone modifications, TF ChIP-seq, DHS, Faire) for gene signatures or peaks. These regulatory features help to improve motif discovery and candidate target gene prediction, (iii) to dissect a set of co-expressed genes into direct target genes of different transcription factor motifs or ChIP-seq tracks. Some of the key features of i-cisTarget are: (i) over-represented motifs are predicted in the set of co-expressed genes, using entire intergenic and intronic sequences, (ii) 10 vertebrate species are used for motif scoring in Human and Mouse version, 12 Drosophila species are used in Drosophila version.

iRF / iterative Random Forest

Grows feature-weighted Random Forests (RF) to perform soft dimension reduction of the feature space and stabilize decision paths. iRF searches for high-order feature interactions in three steps: (i) iterative feature reweighting adaptively regularizes RF fitting, (ii) decision rules extracted from a feature-weighted RF map from continuous or categorical to binary features and (iii) a bagging step assesses the stability of recovered interactions with respect to the bootstrap-perturbation of the data.

EnhancerAtlas

An interactive database which contains an atlas of 2,534,123 enhancers for 105 cell/tissue types. A consensus enhancer annotation was obtained for each cell by summation of independent experimental datasets with the relative weights derived from a cross-validation approach. Moreover, EnhancerAtlas provides a set of useful analytic tools that allow users to query and compare enhancers in a particular genomic region or associated with a gene of interest, and assign enhancers and their target genes from a custom dataset.

iEnhancer-2L

Identifies enhancers and their strength by pseudo k-tuple nucleotide composition. iEnhancer-2L is a two-layer predictor. Its 1st layer is to identify whether a query DNA element is of enhancer or not. If the outcome is yes, then the 2nd layer will automatically continue to identify its strength: strong or weak. To our best knowledge, it is the first predictor ever developed that can be also used to classify enhancers according to their strength. Rigorous cross validation tests have indicated that IENHANCER-2L holds very high potential to become a useful tool for genome analysis.

LMethyR-SVM

A framework for the prediction of enhancers using cell-type-specific low-methylated regions (LMRs) detected from the whole genome bisulfite sequencing (WGBS) data. In LMethyR-SVM, the set of cell-type-specific LMRs is further divided into three sets: reliable positive, like positive and likely negative, according to their resemblance to a small set of experimentally validated enhancers in the VISTA database based on an estimated non parametric density distribution. Then, the prediction model is trained by solving a weighted support vector machine.

NaviSE

Processes and integrates multiple genome-wide Next Generation Sequencing (NGS) epigenomics signals from various input file formats into an interactive HTML report. NaviSE was designed to perform automatic parallelised Super Enhancers (SEs) prediction from genome-wide epigenetic signals, or an algebra of them. This method is developed for users with working knowledge in informatics and integrates all the data into the Graphical User Interface (GUI) to navigate through all the results.

EP-sim

An alignment-free statistic for the classification of cis-regulatory modules, called 2EP2∗, that is based on multiple resolution patterns derived from the Entropic Profiles (EPs). The Entropic Profile is a function of the genomic location that captures the importance of that region with respect to the whole genome. As a byproduct we provide a formula to compute the exact variance of variable length word counts, a result that can be of general interest also in other applications. The new statistic, 2EP2∗, is highly successful in discriminating functionally related enhancers and, in almost all experiments, it outperforms fixed-resolution methods.

EnhancerPred

Obsolete
Formulates the prediction of enhancers and their strength as a binary classification problem and solves it using a machine learning algorithm. EnhancerPred extracts features using BPB, NC and PseNc and also takes advantage of efficient feature selection, which was shown here to be robust and high performing using a rigorous jackknife test. In comparison to existing tools, EnhancerPred achieved satisfactory MCC values, especially for the prediction of whether an enhancer has a strong or weak effect on gene expression.

PEDLA

A deep learning-based algorithmic framework to systematically and precisely predict enhancers on a genome-wide scale using heterogeneous types of data. PEDLA has three outstanding characteristics that make it ideal for achieving state-of-the-art performance relative to five existing methods for enhancer predictions. First, PEDLA is capable of learning an enhancer predictor based on massively heterogeneous data to fully capture the universal patterns of enhancers, which makes its enhancer predictions more comprehensive and accurate. Second, PEDLA can generalize enhancer predictions in ways that are mostly consistent across various cell types/tissues. Third, PEDLA is capable of extending to input data of any type and to predictions of any type of functional element/domain.

EnhancerFinder

Allows the seamless integration of feature data from a variety of experimental techniques and biological contexts that have previously been used individually to predict enhancers. One motivation for developing EnhancerFinder was to explore whether combining previous successful approaches to enhancer prediction would improve performance. The EnhancerFinder's integration of diverse types of data from different cellular contexts significantly improves prediction of validated enhancers over approaches based on a single context or type of data. Applying EnhancerFinder to the entire human genome allowed us to predict more than 80,000 developmental enhancers, with tissue-specific predictions for brain, limb, and heart.

CLARE / Cracking the LAnguage of Regulatory Elements

A computational method designed to reveal sequence encryption of tissue-specific regulatory elements. Starting with a set of regulatory elements known to be active in a particular tissue/process, it learns the sequence code of the input set and builds a predictive model from features specific to those elements. The resulting model can then be applied to user-supplied genomic regions to identify novel candidate regulatory elements. CLARE's model also provides a detailed analysis of transcription factors that most likely bind to the elements, making it an invaluable tool for understanding mechanisms of tissue-specific gene regulation.

DENdb / Dragon Enhancers database

Obsolete
A centralized on-line repository of predicted enhancers derived from multiple human cell-lines. DENdb integrates enhancers predicted by five different methods (ChromHMM, Segway, RFECS, CSI-ANN, and ENCODE integrated annotation) generating an enriched catalogue of enhancers for each of the analyzed cell-lines. DENdb contains overlap of enhancers with DNase I hypersensitive regions, and transcription factor binding sites. It also provides means to investigate enhancer interactions with DNA using several chromatin interaction assays, and the ability to explore genes neighbouring enhancers.

zTrap

A useful resource to find gene trap and enhancer trap fish lines that express GFP and Gal4FF in desired patterns, and to find insertions of the gene trap and enhancer trap constructs that are located within or near genes of interest. These transgenic fish can be utilized to observe specific cell types during embryogenesis, to manipulate their functions, and to discover novel genes and cis-regulatory elements. Therefore, zTrap facilitates studies on genomics, developmental biology and neurobiology utilizing the transgenic zebrafish resource.

IM-PET / Integrated Methods for Predicting Enhancer Targets

An integrated method for predicting enhancer targets. Leveraging abundant omics data, we develop multiple features and integrate them probabilistically to make robust predictions of enhancer–promoter (EP) pairs. The selected features are based on our current understanding of enhancer structure, function, and evolution. Using both computational and experimental validations, we show IM-PET significantly outperforms state-of-the-art methods.

ZETRAP / Zebrafish Enhancer TRAP transgenic line database

Obsolete
A web-based system that provides data and information to the scientific community about the developmental, genetic and genomic aspects of transgenic zebrafish lines obtained using Tol2 transposon-mediated transgenesis. ZETRAP was expanded further by generation of transgenics expressing the membrane-tethered version of a novel red protein KillerRed. The new version contains the sequence of regions flanking the insertion sites, links to genes in zebrafish genome, and confocal images of embryos/larvae of these transgenics.