Dataset Information

An Equivariant Bayesian Convolutional Network predicts recombination hotspots and accurately resolves binding motifs.

ABSTRACT: Motivation:Convolutional neural networks (CNNs) have been tremendously successful in many contexts, particularly where training data is abundant and signal-to-noise ratios are large. However, when predicting noisily observed phenotypes from DNA sequence, each training instance is only weakly informative, and the amount of training data is often fundamentally limited, emphasizing the need for methods that make optimal use of training data and any structure inherent in the process. Results:Here we show how to combine equivariant networks, a general mathematical framework for handling exact symmetries in CNNs, with Bayesian dropout, a version of MC dropout suggested by a reinterpretation of dropout as a variational Bayesian approximation, to develop a model that exhibits exact reverse-complement symmetry and is more resistant to overtraining. We find that this model combines improved prediction consistency with better predictive accuracy compared to standard CNN implementations and state-of-art motif finders. We use our network to predict recombination hotspots from sequence, and identify binding motifs for the recombination-initiation protein PRDM9 previously unobserved in this data, which were recently validated by high-resolution assays. The network achieves a predictive accuracy comparable to that attainable by a direct assay of the H3K4me3 histone mark, a proxy for PRDM9 binding. Availability:https://github.com/luntergroup/EquivariantNetworks. Supplementary information:Supplementary data are available at Bioinformatics online.

SUBMITTER: Brown R

PROVIDER: S-EPMC6596897 | biostudies-other | 2018 Nov

REPOSITORIES: biostudies-other

ACCESS DATA

Publications

An equivariant Bayesian convolutional network predicts recombination hotspots and accurately resolves binding motifs.

Brown Richard C RC Lunter Gerton G

Bioinformatics (Oxford, England) 20190701 13

<h4>Motivation</h4>Convolutional neural networks (CNNs) have been tremendously successful in many contexts, particularly where training data are abundant and signal-to-noise ratios are large. However, when predicting noisily observed phenotypes from DNA sequence, each training instance is only weakly informative, and the amount of training data is often fundamentally limited, emphasizing the need for methods that make optimal use of training data and any structure inherent in the process.<h4>Res ...[more]

PMID: 30481258

Similar Datasets

Project description:Brain extraction or skull stripping of magnetic resonance images (MRI) is an essential step in neuroimaging studies, the accuracy of which can severely affect subsequent image processing procedures. Current automatic brain extraction methods demonstrate good results on human brains, but are often far from satisfactory on nonhuman primates, which are a necessary part of neuroscience research. To overcome the challenges of brain extraction in nonhuman primates, we propose a fully-automated brain extraction pipeline combining deep Bayesian convolutional neural network (CNN) and fully connected three-dimensional (3D) conditional random field (CRF). The deep Bayesian CNN, Bayesian SegNet, is used as the core segmentation engine. As a probabilistic network, it is not only able to perform accurate high-resolution pixel-wise brain segmentation, but also capable of measuring the model uncertainty by Monte Carlo sampling with dropout in the testing stage. Then, fully connected 3D CRF is used to refine the probability result from Bayesian SegNet in the whole 3D context of the brain volume. The proposed method was evaluated with a manually brain-extracted dataset comprising T1w images of 100 nonhuman primates. Our method outperforms six popular publicly available brain extraction packages and three well-established deep learning based methods with a mean Dice coefficient of 0.985 and a mean average symmetric surface distance of 0.220?mm. A better performance against all the compared methods was verified by statistical tests (all p-values?<?10-4, two-sided, Bonferroni corrected). The maximum uncertainty of the model on nonhuman primate brain extraction has a mean value of 0.116 across all the 100 subjects. The behavior of the uncertainty was also studied, which shows the uncertainty increases as the training set size decreases, the number of inconsistent labels in the training set increases, or the inconsistency between the training set and the testing set increases.

Project description:BackgroundAs a fundamental genomic element, meiotic recombination hotspot plays important roles in life sciences. Thus uncovering its regulatory mechanisms has broad impact on biomedical research. Despite the recent identification of the zinc finger protein PRDM9 and its 13-mer binding motif as major regulators for meiotic recombination hotspots, other regulators remain to be discovered. Existing methods for finding DNA sequence motifs of recombination hotspots often rely on the enrichment of co-localizations between hotspots and short DNA patterns, which ignore the cross-individual variation of recombination rates and sequence polymorphisms in the population. Our objective in this paper is to capture signals encoded in genetic variations for the discovery of recombination-associated DNA motifs.ResultsRecently, an algorithm called "LDsplit" has been designed to detect the association between single nucleotide polymorphisms (SNPs) and proximal meiotic recombination hotspots. The association is measured by the difference of population recombination rates at a hotspot between two alleles of a candidate SNP. Here we present an open source software tool of LDsplit, with integrative data visualization for recombination hotspots and their proximal SNPs. Applying LDsplit on SNPs inside an established 7-mer motif bound by PRDM9 we observed that SNP alleles preserving the original motif tend to have higher recombination rates than the opposite alleles that disrupt the motif. Running on SNP windows around hotspots each containing an occurrence of the 7-mer motif, LDsplit is able to guide the established motif finding algorithm of MEME to recover the 7-mer motif. In contrast, without LDsplit the 7-mer motif could not be identified.ConclusionsLDsplit is a software tool for the discovery of cis-regulatory DNA sequence motifs stimulating meiotic recombination hotspots by screening and narrowing down to hotspot associated SNPs. It is the first computational method that utilizes the genetic variation of recombination hotspots among individuals, opening a new avenue for motif finding. Tested on an established motif and simulated datasets, LDsplit shows promise to discover novel DNA motifs for meiotic recombination hotspots.

Dataset Information

An Equivariant Bayesian Convolutional Network predicts recombination hotspots and accurately resolves binding motifs.

Publications

An equivariant Bayesian convolutional network predicts recombination hotspots and accurately resolves binding motifs.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets