MOTIVATION: Predicting the regulatory function of non-coding DNA using only the DNA sequence continues to be a major challenge in genomics. With the advent of improved optimization algorithms, faster GPU speeds, and more intricate machine-learning libraries, hybrid convolutional and recurrent neural network architectures can be constructed and applied to extract crucial information from non-coding DNA. RESULTS: Using a comparative analysis of the performance of thousands of Deep Learning architectures, we developed ChromDL, a neural network architecture combining bidirectional gated recurrent units, convolutional neural networks, and bidirectional long short-term memory units, which significantly improves upon a range of prediction metrics compared to its predecessors in transcription factor binding site, histone modification, and DNase-I hyper-sensitive site detection. Combined with a secondary model, it can be utilized for accurate classification of gene regulatory elements. The model can also detect weak transcription factor binding as compared to previously developed methods and has the potential to help delineate transcription factor binding motif specificities. AVAILABILITY AND IMPLEMENTATION: The ChromDL source code can be found at https://github.com/chrishil1/ChromDL.

SUMMARY: Addressing deleterious effects of noncoding mutations is an essential step towards the identification of disease-causal mutations of gene regulatory elements. Several methods for quantifying the deleteriousness of noncoding mutations using artificial intelligence, deep learning and other approaches have been recently proposed. Although the majority of the proposed methods have demonstrated excellent accuracy on different test sets, there is rarely a consensus. In addition, advanced statistical and artificial learning approaches used by these methods make it difficult porting these methods outside of the labs that have developed them. To address these challenges and to transform the methodological advances in predicting deleterious noncoding mutations into a practical resource available for the broader functional genomics and population genetics communities, we developed SNPDelScore, which uses a panel of proposed methods for quantifying deleterious effects of noncoding mutations to precompute and compare the deleteriousness scores of all common SNPs in the human genome in 44 cell lines. The panel of deleteriousness scores of a SNP computed using different methods is supplemented by functional information from the GWAS Catalog, libraries of transcription factor-binding sites, and genic characteristics of mutations. SNPDelScore comes with a genome browser capable of displaying and comparing large sets of SNPs in a genomic locus and rapidly identifying consensus SNPs with the highest deleteriousness scores making those prime candidates for phenotype-causal polymorphisms. AVAILABILITY AND IMPLEMENTATION: https://www.ncbi.nlm.nih.gov/research/snpdelscore/. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

BACKGROUND: Transcription factor binding site (TFBS) loss, gain, and reshuffling within the sequence of a regulatory element could alter the function of that regulatory element. Some of the changes will be detrimental to the fitness of the species and will result in gradual removal from a population, while other changes would be either beneficial or just a part of genetic drift and end up being fixed in a population. This "reprogramming" of regulatory elements results in modification of the gene regulatory landscape during evolution. RESULTS: We identified reprogrammed enhancers (RPEs) by comparing the distribution of tissue-specific enhancers in the human and mouse genomes. We observed that around 30% of mammalian enhancers have been reprogrammed after the human-mouse speciation. In 79% of cases, the reprogramming of an enhancer resulted in a quantifiably different expression of a flanking gene. In the case of the Thy-1 cell surface antigen gene, for example, enhancer reprogramming is associated with cortex to thymus change in gene expression. To understand the mechanisms of enhancer reprogramming, we profiled the evolutionary changes in the TFBS enhancer content and found that enhancer reprogramming took place through the acquisition of new TFBSs in 72% of reprogramming events. CONCLUSIONS: Our results suggest that enhancer reprogramming takes place within well-established regulatory loci with RPEs contributing additively to fine-tuning of the gene regulatory program in mammals. We also found evidence for acquisition of novel gene function through enhancer reprogramming, which allows expansion of gene regulatory landscapes into new regulatory domains.

UNLABELLED: CLARE is 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. AVAILABILITY: CLARE is freely accessible at http://clare.dcode.org/.

BACKGROUND: Researchers seeking to unlock the genetic basis of human physiology and diseases have been studying gene transcription regulation. The temporal and spatial patterns of gene expression are controlled by mainly non-coding elements known as cis-regulatory modules (CRMs) and epigenetic factors. CRMs modulating related genes share the regulatory signature which consists of transcription factor (TF) binding sites (TFBSs). Identifying such CRMs is a challenging problem due to the prohibitive number of sequence sets that need to be analyzed. RESULTS: We formulated the challenge as a supervised classification problem even though experimentally validated CRMs were not required. Our efforts resulted in a software system named CrmMiner. The system mines for CRMs in the vicinity of related genes. CrmMiner requires two sets of sequences: a mixed set and a control set. Sequences in the vicinity of the related genes comprise the mixed set, whereas the control set includes random genomic sequences. CrmMiner assumes that a large percentage of the mixed set is made of background sequences that do not include CRMs. The system identifies pairs of closely located motifs representing vertebrate TFBSs that are enriched in the training mixed set consisting of 50% of the gene loci. In addition, CrmMiner selects a group of the enriched pairs to represent the tissue-specific regulatory signature. The mixed and the control sets are searched for candidate sequences that include any of the selected pairs. Next, an optimal Bayesian classifier is used to distinguish candidates found in the mixed set from their control counterparts. Our study proposes 62 tissue-specific regulatory signatures and putative CRMs for different human tissues and cell types. These signatures consist of assortments of ubiquitously expressed TFs and tissue-specific TFs. Under controlled settings, CrmMiner identified known CRMs in noisy sets up to 1:25 signal-to-noise ratio. CrmMiner was 21-75% more precise than a related CRM predictor. The sensitivity of the system to locate known human heart enhancers reached up to 83%. CrmMiner precision reached 82% while mining for CRMs specific to the human CD4+ T cells. On several data sets, the system achieved 99% specificity. CONCLUSION: These results suggest that CrmMiner predictions are accurate and likely to be tissue-specific CRMs. We expect that the predicted tissue-specific CRMs and the regulatory signatures broaden our knowledge of gene transcription regulation.

MOTIVATION: Several functional gene annotation databases have been developed in the recent years, and are widely used to infer the biological function of gene sets, by scrutinizing the attributes that appear over- and underrepresented. However, this strategy is not directly applicable to the study of non-coding DNA, as the non-coding sequence span varies greatly among different gene loci in the human genome and longer loci have a higher likelihood of being selected purely by chance. Therefore, conclusions involving the function of non-coding elements that are drawn based on the annotation of neighboring genes are often biased. We assessed the systematic bias in several particular Gene Ontology (GO) categories using the standard hypergeometric test, by randomly sampling non-coding elements from the human genome and inferring their function based on the functional annotation of the closest genes. While no category is expected to occur significantly over- or underrepresented for a random selection of elements, categories such as 'cell adhesion', 'nervous system development' and 'transcription factor activities' appeared to be systematically overrepresented, while others such as 'olfactory receptor activity'-underrepresented. RESULTS: Our results suggest that functional inference for non-coding elements using gene annotation databases requires a special correction. We introduce a set of correction coefficients for the probabilities of the GO categories that accounts for the variability in the length of the non-coding DNA across different loci and effectively eliminates the ascertainment bias from the functional characterization of non-coding elements. Our approach can be easily generalized to any other gene annotation database.

Evolutionary conservation of DNA sequences provides a tool for the identification of functional elements in genomes. We have created a database of evolutionary conserved regions (ECRs) in vertebrate genomes, entitled ECRbase, which is constructed from a collection of whole-genome alignments produced by the ECR Browser. ECRbase features a database of syntenic blocks that recapitulate the evolution of rearrangements in vertebrates and a comprehensive collection of promoters in all vertebrate genomes generated using multiple sources of gene annotation. The database also contains a collection of annotated transcription factor binding sites (TFBSs) in evolutionary conserved and promoter elements. ECRbase currently includes human, rhesus macaque, dog, opossum, rat, mouse, chicken, frog, zebrafish and fugu genomes. It is freely accessible at http://ecrbase.dcode.org.

BACKGROUND: There are several isolated tools for partial analysis of microarray expression data. To provide an integrative, easy-to-use and automated toolkit for the analysis of Affymetrix microarray expression data we have developed Array2BIO, an application that couples several analytical methods into a single web based utility. RESULTS: Array2BIO converts raw intensities into probe expression values, automatically maps those to genes, and subsequently identifies groups of co-expressed genes using two complementary approaches: (1) comparative analysis of signal versus control and (2) clustering analysis of gene expression across different conditions. The identified genes are assigned to functional categories based on Gene Ontology classification and KEGG protein interaction pathways. Array2BIO reliably handles low-expressor genes and provides a set of statistical methods for quantifying expression levels, including Benjamini-Hochberg and Bonferroni multiple testing corrections. An automated interface with the ECR Browser provides evolutionary conservation analysis for the identified gene loci while the interconnection with Crème allows prediction of gene regulatory elements that underlie observed expression patterns. CONCLUSION: We have developed Array2BIO - a web based tool for rapid comprehensive analysis of Affymetrix microarray expression data, which also allows users to link expression data to Dcode.org comparative genomics tools and integrates a system for translating co-expression data into mechanisms of gene co-regulation. Array2BIO is publicly available at http://array2bio.dcode.org.