Transcription regulation in multicellular eukaryotes is orchestrated by a number of DNA functional elements located at gene regulatory regions. Some regulatory regions (e.g. enhancers) are located far away from the gene they affect. Identification of distal regulatory elements is a challenge for the bioinformatics research. Although existing methodologies increased the number of computationally predicted enhancers, performance inconsistency of computational models across different cell-lines, class imbalance within the learning sets and ad hoc rules for selecting enhancer candidates for supervised learning, are some key questions that require further examination. In this study we developed DEEP, a novel ensemble prediction framework. DEEP integrates three components with diverse characteristics that streamline the analysis of enhancer's properties in a great variety of cellular conditions. In our method we train many individual classification models that we combine to classify DNA regions as enhancers or non-enhancers. DEEP uses features derived from histone modification marks or attributes coming from sequence characteristics. Experimental results indicate that DEEP performs better than four state-of-the-art methods on the ENCODE data. We report the first computational enhancer prediction results on FANTOM5 data where DEEP achieves 90.2% accuracy and 90% geometric mean (GM) of specificity and sensitivity across 36 different tissues. We further present results derived using in vivo-derived enhancer data from VISTA database. DEEP-VISTA, when tested on an independent test set, achieved GM of 80.1% and accuracy of 89.64%. DEEP framework is publicly available at http://cbrc.kaust.edu.sa/deep/.

Many scientific problems can be formulated as classification tasks. Data that harbor relevant information are usually described by a large number of features. Frequently, many of these features are irrelevant for the class prediction. The efficient implementation of classification models requires identification of suitable combinations of features. The smaller number of features reduces the problem’s dimensionality and may result in higher classification performance. We developed DWFS, a web-based tool that allows for efficient selection of features for a variety of problems. DWFS follows the wrapper paradigm and applies a search strategy based on Genetic Algorithms (GAs). A parallel GA implementation examines and evaluates simultaneously large number of candidate collections of features. DWFS also integrates various filtering methods that may be applied as a pre-processing step in the feature selection process. Furthermore, weights and parameters in the fitness function of GA can be adjusted according to the application requirements. Experiments using heterogeneous datasets from different biomedical applications demonstrate that DWFS is fast and leads to a significant reduction of the number of features without sacrificing performance as compared to several widely used existing methods. DWFS can be accessed online at www.cbrc.kaust.edu.sa/dwfs.

Enhancers are cis-acting DNA elements that play critical roles in distal regulation of gene expression. Identifying enhancers is an important step for understanding distinct gene expression programs that may reflect normal and pathogenic cellular conditions. Experimental identification of enhancers is constrained by the set of conditions used in the experiment. This requires multiple experiments to identify enhancers, as they can be active under specific cellular conditions but not in different cell types/tissues or cellular states. This has opened prospects for computational prediction methods that can be used for high-throughput identification of putative enhancers to complement experimental approaches. Potential functions and properties of predicted enhancers have been catalogued and summarized in several enhancer-oriented databases. Because the current methods for the computational prediction of enhancers produce significantly different enhancer predictions, it will be beneficial for the research community to have an overview of the strategies and solutions developed in this field. In this review, we focus on the identification and analysis of enhancers by bioinformatics approaches. First, we describe a general framework for computational identification of enhancers, present relevant data types and discuss possible computational solutions. Next, we cover over 30 existing computational enhancer identification methods that were developed since 2000. Our review highlights advantages, limitations and potentials, while suggesting pragmatic guidelines for development of more efficient computational enhancer prediction methods. Finally, we discuss challenges and open problems of this topic, which require further consideration.

Tumor DNA circulates in the plasma of cancer patients admixed with DNA from noncancerous cells. The genomic landscape of plasma DNA has been characterized in metastatic castration-resistant prostate cancer (mCRPC) but the plasma methylome has not been extensively explored. Here, we performed next-generation sequencing (NGS) on plasma DNA with and without bisulfite treatment from mCRPC patients receiving either abiraterone or enzalutamide in the pre- or post-chemotherapy setting. Principal component analysis on the mCRPC plasma methylome indicated that the main contributor to methylation variance (principal component one, or PC1) was strongly correlated with genomically determined tumor fraction (r = –0.96; P < 10^–8) and characterized by hypermethylation of targets of the polycomb repressor complex 2 components. Further deconvolution of the PC1 top-correlated segments revealed that these segments are comprised of methylation patterns specific to either prostate cancer or prostate normal epithelium. To extract information specific to an individual’s cancer, we then focused on an orthogonal methylation signature, which revealed enrichment for androgen receptor binding sequences and hypomethylation of these segments associated with AR copy number gain. Individuals harboring this methylation pattern had a more aggressive clinical course. Plasma methylome analysis can accurately quantitate tumor fraction and identify distinct biologically relevant mCRPC phenotypes.

Profiling of circulating tumor DNA (ctDNA) may offer a non-invasive approach to monitor disease progression. Here, we develop a quantitative method, exploiting local tissue-specific cell-free DNA (cfDNA) degradation patterns, that accurately estimates ctDNA burden independent of genomic aberrations. Nucleosome-dependent cfDNA degradation at promoters and first exon-intron junctions is strongly associated with differential transcriptional activity in tumors and blood. A quantitative model, based on just 6 regulatory regions, could accurately predict ctDNA levels in colorectal cancer patients. Strikingly, a model restricted to blood-specific regulatory regions could predict ctDNA levels across both colorectal and breast cancer patients. Using compact targeted sequencing (<25 kb) of predictive regions, we demonstrate how the approach could enable quantitative low-cost tracking of ctDNA dynamics and disease progression.

Enhancers are cis -acting DNA regulatory regions that play a key role in distal control of transcriptional activities. Identification of enhancers, coupled with a comprehensive functional analysis of their properties, could improve our understanding of complex gene transcription mechanisms and gene regulation processes in general. We developed DENdb, a centralized on-line repository of predicted enhancers derived from multiple human cell-lines. DENdb integrates enhancers predicted by five different methods generating an enriched catalogue of putative enhancers for each of the analysed cell-lines. DENdb provides information about the overlap of enhancers with DNase I hypersensitive regions, ChIP-seq regions of a number of transcription factors and transcription factor binding motifs, means to explore enhancer interactions with DNA using several chromatin interaction assays and enhancer neighbouring genes. DENdb is designed as a relational database that facilitates fast and efficient searching, browsing and visualization of information. Database URL:http://www.cbrc.kaust.edu.sa/dendb/