Assessing deep learning methods in cis-regulatory motif finding based on genomic sequencing data.
Ontology highlight
ABSTRACT:
SUBMITTER: Zhang S
PROVIDER: S-EPMC8769700 | biostudies-literature |
REPOSITORIES: biostudies-literature
Similar Datasets
Project description:BACKGROUND:In the human genome, 98% of DNA sequences are non-protein-coding regions that were previously disregarded as junk DNA. In fact, non-coding regions host a variety of cis-regulatory regions which precisely control the expression of genes. Thus, Identifying active cis-regulatory regions in the human genome is critical for understanding gene regulation and assessing the impact of genetic variation on phenotype. The developments of high-throughput sequencing and machine learning technologies make it possible to predict cis-regulatory regions genome wide. RESULTS:Based on rich data resources such as the Encyclopedia of DNA Elements (ENCODE) and the Functional Annotation of the Mammalian Genome (FANTOM) projects, we introduce DECRES based on supervised deep learning approaches for the identification of enhancer and promoter regions in the human genome. Due to their ability to discover patterns in large and complex data, the introduction of deep learning methods enables a significant advance in our knowledge of the genomic locations of cis-regulatory regions. Using models for well-characterized cell lines, we identify key experimental features that contribute to the predictive performance. Applying DECRES, we delineate locations of 300,000 candidate enhancers genome wide (6.8% of the genome, of which 40,000 are supported by bidirectional transcription data), and 26,000 candidate promoters (0.6% of the genome). CONCLUSION:The predicted annotations of cis-regulatory regions will provide broad utility for genome interpretation from functional genomics to clinical applications. The DECRES model demonstrates potentials of deep learning technologies when combined with high-throughput sequencing data, and inspires the development of other advanced neural network models for further improvement of genome annotations.
| S-EPMC5984344 | biostudies-literature
Project description:Differential gene expression is the fundamental mechanism underlying animal development and cell differentiation. However, it is a challenge to identify comprehensively and accurately the DNA sequences that are required to regulate gene expression: namely, cis-regulatory modules (CRMs). Three major features, either singly or in combination, are used to predict CRMs: clusters of transcription factor binding site motifs, non-coding DNA that is under evolutionary constraint and biochemical marks associated with CRMs, such as histone modifications and protein occupancy. The validation rates for predictions indicate that identifying diagnostic biochemical marks is the most reliable method, and understanding is enhanced by the analysis of motifs and conservation patterns within those predicted CRMs.
| S-EPMC3541939 | biostudies-literature
Project description:Computational methods attempting to identify instances of cis-regulatory modules (CRMs) in the genome face a challenging problem of searching for potentially interacting transcription factor binding sites while knowledge of the specific interactions involved remains limited. Without a comprehensive comparison of their performance, the reliability and accuracy of these tools remains unclear. Faced with a large number of different tools that address this problem, we summarized and categorized them based on search strategy and input data requirements. Twelve representative methods were chosen and applied to predict CRMs from the Drosophila CRM database REDfly, and across the human ENCODE regions. Our results show that the optimal choice of method varies depending on species and composition of the sequences in question. When discriminating CRMs from non-coding regions, those methods considering evolutionary conservation have a stronger predictive power than methods designed to be run on a single genome. Different CRM representations and search strategies rely on different CRM properties, and different methods can complement one another. For example, some favour homotypical clusters of binding sites, while others perform best on short CRMs. Furthermore, most methods appear to be sensitive to the composition and structure of the genome to which they are applied. We analyze the principal features that distinguish the methods that performed well, identify weaknesses leading to poor performance, and provide a guide for users. We also propose key considerations for the development and evaluation of future CRM-prediction methods.
| S-EPMC2996316 | biostudies-literature
Project description:UnlabelledPrecise regulatory control of genes, particularly in eukaryotes, frequently requires the joint action of multiple sequence-specific transcription factors. A cis-regulatory module (CRM) is a genomic locus that is responsible for gene regulation and that contains multiple transcription factor binding sites in close proximity. Given a collection of known transcription factor binding motifs, many bioinformatics methods have been proposed over the past 15 years for identifying within a genomic sequence candidate CRMs consisting of clusters of those motifs.ResultsThe MCAST algorithm uses a hidden Markov model with a P-value-based scoring scheme to identify candidate CRMs. Here, we introduce a new version of MCAST that offers improved graphical output, a dynamic background model, statistical confidence estimates based on false discovery rate estimation and, most significantly, the ability to predict CRMs while taking into account epigenomic data such as DNase I sensitivity or histone modification data. We demonstrate the validity of MCAST's statistical confidence estimates and the utility of epigenomic priors in identifying CRMs.Availability and implementationMCAST is part of the MEME Suite software toolkit. A web server and source code are available at http://meme-suite.org and http://alternate.meme-suite.orgContactt.bailey@imb.uq.edu.au or william-noble@uw.eduSupplementary informationSupplementary data are available at Bioinformatics online.
| S-EPMC4907379 | biostudies-literature
Project description:Deep neural networks (DNNs) have greatly advanced the ability to predict genome function from sequence. Interpreting genomic DNNs in terms of biological mechanisms, however, remains difficult. Here we introduce SQUID, a genomic DNN interpretability framework based on surrogate modeling. SQUID approximates genomic DNNs in user-specified regions of sequence space using surrogate models, i.e., simpler models that are mechanistically interpretable. Importantly, SQUID removes the confounding effects that nonlinearities and heteroscedastic noise in functional genomics data can have on model interpretation. Benchmarking analysis on multiple genomic DNNs shows that SQUID, when compared to established interpretability methods, identifies motifs that are more consistent across genomic loci and yields improved single-nucleotide variant-effect predictions. SQUID also supports surrogate models that quantify epistatic interactions within and between cis-regulatory elements. SQUID thus advances the ability to mechanistically interpret genomic DNNs.
| S-EPMC10680760 | biostudies-literature
Project description:Accurate evaluation of the quality of genomic or proteomic data and computational methods is vital to our ability to use them for formulating novel biological hypotheses and directing further experiments. There is currently no standard approach to evaluation in functional genomics. Our analysis of existing approaches shows that they are inconsistent and contain substantial functional biases that render the resulting evaluations misleading both quantitatively and qualitatively. These problems make it essentially impossible to compare computational methods or large-scale experimental datasets and also result in conclusions that generalize poorly in most biological applications.We reveal issues with current evaluation methods here and suggest new approaches to evaluation that facilitate accurate and representative characterization of genomic methods and data. Specifically, we describe a functional genomics gold standard based on curation by expert biologists and demonstrate its use as an effective means of evaluation of genomic approaches. Our evaluation framework and gold standard are freely available to the community through our website.Proper methods for evaluating genomic data and computational approaches will determine how much we, as a community, are able to learn from the wealth of available data. We propose one possible solution to this problem here but emphasize that this topic warrants broader community discussion.
| S-EPMC1560386 | biostudies-literature
Project description:DNA sequences bound by a transcription factor (TF) are presumed to contain sequence elements that reflect its DNA binding preferences and its downstream-regulatory effects. Experimentally identified TF binding sites (TFBSs) are usually similar enough to be summarized by a 'consensus' motif, representative of the TF DNA binding specificity. Studies have shown that groups of nucleotide TFBS variants (subtypes) can contribute to distinct modes of downstream regulation by the TF via differential recruitment of cofactors. A TF(A) may bind to TFBS subtypes a(1) or a(2) depending on whether it associates with cofactors TF(B) or TF(C), respectively. While some approaches can discover motif pairs (dyads), none address the problem of identifying 'variants' of dyads. TFs are key components of multiple regulatory pathways targeting different sets of genes perhaps with different binding preferences. Identifying the discriminating TF-DNA associations that lead to the differential downstream regulation is thus essential. We present DiSCo (Discovery of Subtypes and Cofactors), a novel approach for identifying variants of dyad motifs (and their respective target sequence sets) that are instrumental for differential downstream regulation. Using both simulated and experimental datasets, we demonstrate how current motif discovery can be successfully leveraged to address this question.
| S-EPMC3113591 | biostudies-literature
Project description:BACKGROUND:Transforming large amounts of genomic data into valuable knowledge for predicting complex traits has been an important challenge for animal and plant breeders. Prediction of complex traits has not escaped the current excitement on machine-learning, including interest in deep learning algorithms such as multilayer perceptrons (MLP) and convolutional neural networks (CNN). The aim of this study was to compare the predictive performance of two deep learning methods (MLP and CNN), two ensemble learning methods [random forests (RF) and gradient boosting (GB)], and two parametric methods [genomic best linear unbiased prediction (GBLUP) and Bayes B] using real and simulated datasets. METHODS:The real dataset consisted of 11,790 Holstein bulls with sire conception rate (SCR) records and genotyped for 58k single nucleotide polymorphisms (SNPs). To support the evaluation of deep learning methods, various simulation studies were conducted using the observed genotype data as template, assuming a heritability of 0.30 with either additive or non-additive gene effects, and two different numbers of quantitative trait nucleotides (100 and 1000). RESULTS:In the bull dataset, the best predictive correlation was obtained with GB (0.36), followed by Bayes B (0.34), GBLUP (0.33), RF (0.32), CNN (0.29) and MLP (0.26). The same trend was observed when using mean squared error of prediction. The simulation indicated that when gene action was purely additive, parametric methods outperformed other methods. When the gene action was a combination of additive, dominance and of two-locus epistasis, the best predictive ability was obtained with gradient boosting, and the superiority of deep learning over the parametric methods depended on the number of loci controlling the trait and on sample size. In fact, with a large dataset including 80k individuals, the predictive performance of deep learning methods was similar or slightly better than that of parametric methods for traits with non-additive gene action. CONCLUSIONS:For prediction of traits with non-additive gene action, gradient boosting was a robust method. Deep learning approaches were not better for genomic prediction unless non-additive variance was sizable.
| S-EPMC7038529 | biostudies-literature
Project description:BackgroundFinding functional regulatory elements in DNA sequences is a very important problem in computational biology and providing a reliable algorithm for this task would be a major step towards understanding regulatory mechanisms on genome-wide scale. Major obstacles in this respect are that the fact that the amount of non-coding DNA is vast, and that the methods for predicting functional transcription factor binding sites tend to produce results with a high percentage of false positives. This makes the problem of finding regions significantly enriched in binding sites difficult.ResultsWe develop a novel method for predicting regulatory regions in DNA sequences, which is designed to exploit the evolutionary conservation of regulatory elements between species without assuming that the order of motifs is preserved across species. We have implemented our method and tested its predictive abilities on various datasets from different organisms.ConclusionWe show that our approach enables us to find a majority of the known CRMs using only sequence information from different species together with currently publicly available motif data. Also, our method is robust enough to perform well in predicting CRMs, despite differences in tissue specificity and even across species, provided that the evolutionary distances between compared species do not change substantially. The complexity of the proposed algorithm is polynomial, and the observed running times show that it may be readily applied.
| S-EPMC2669485 | biostudies-literature
Project description:Tumor type guides clinical treatment decisions in cancer, but histology-based diagnosis remains challenging. Genomic alterations are highly diagnostic of tumor type, and tumor type classifiers trained on genomic features have been explored, but the most accurate methods are not clinically feasible, relying on features derived from whole genome sequencing (WGS), or predicting across limited cancer types. We use genomic features from a dataset of 39,787 solid tumors sequenced using a clinical targeted cancer gene panel to develop Genome-Derived-Diagnosis Ensemble (GDD-ENS): a hyperparameter ensemble for classifying tumor type using deep neural networks. GDD-ENS achieves 93% accuracy for high-confidence predictions across 38 cancer types, rivalling performance of WGS-based methods. GDD-ENS can also guide diagnoses on rare type and cancers of unknown primary, and incorporate patient-specific clinical information for improved predictions. Overall, integrating GDD-ENS into prospective clinical sequencing workflows has enabled clinically-relevant tumor type predictions to guide treatment decisions in real time.
| S-EPMC10508812 | biostudies-literature