Basset Learning the regulatory code of the accessible genome with deep convolutional neural networks, bioRxiv, 2015-10-06

AbstractThe complex language of eukaryotic gene expression remains incompletely understood. Despite the importance suggested by many noncoding variants statistically associated with human disease, nearly all such variants have unknown mechanism. Here, we address this challenge using an approach based on a recent machine learning advance—deep convolutional neural networks (CNNs). We introduce an open source package Basset (<jatsext-link xmlnsxlink=httpwww.w3.org1999xlink ext-link-type=uri xlinkhref=httpsgithub.comdavek44Basset>httpsgithub.comdavek44Basset<jatsext-link>) to apply CNNs to learn the functional activity of DNA sequences from genomics data. We trained Basset on a compendium of accessible genomic sites mapped in 164 cell types by DNaseI-seq and demonstrate far greater predictive accuracy than previous methods. Basset predictions for the change in accessibility between variant alleles were far greater for GWAS SNPs that are likely to be causal relative to nearby SNPs in linkage disequilibrium with them. With Basset, a researcher can perform a single sequencing assay in their cell type of interest and simultaneously learn that cell’s chromatin accessibility code and annotate every mutation in the genome with its influence on present accessibility and latent potential for accessibility. Thus, Basset offers a powerful computational approach to annotate and interpret the noncoding genome.

biorxiv genomics 0-100-users 2015

Missing Data and Technical Variability in Single-Cell RNA- Sequencing Experiments, bioRxiv, 2015-08-26

Until recently, high-throughput gene expression technology, such as RNA-Sequencing (RNA-seq) required hundreds of thousands of cells to produce reliable measurements. Recent technical advances permit genome-wide gene expression measurement at the single-cell level. Single-cell RNA-Seq (scRNA-seq) is the most widely used and numerous publications are based on data produced with this technology. However, RNA-Seq and scRNA-seq data are markedly different. In particular, unlike RNA-Seq, the majority of reported expression levels in scRNA-seq are zeros, which could be either biologically-driven, genes not expressing RNA at the time of measurement, or technically-driven, gene expressing RNA, but not at a sufficient level to detected by sequencing technology. Another difference is that the proportion of genes reporting the expression level to be zero varies substantially across single cells compared to RNA-seq samples. However, it remains unclear to what extent this cell-to-cell variation is being driven by technical rather than biological variation. Furthermore, while systematic errors, including batch effects, have been widely reported as a major challenge in high-throughput technologies, these issues have received minimal attention in published studies based on scRNA-seq technology. Here, we use an assessment experiment to examine data from published studies and demonstrate that systematic errors can explain a substantial percentage of observed cell-to-cell expression variability. Specifically, we present evidence that some of these reported zeros are driven by technical variation by demonstrating that scRNA-seq produces more zeros than expected and that this bias is greater for lower expressed genes. In addition, this missing data problem is exacerbated by the fact that this technical variation varies cell-to-cell. Then, we show how this technical cell-to-cell variability can be confused with novel biological results. Finally, we demonstrate and discuss how batch-effects and confounded experiments can intensify the problem.

biorxiv genomics 200-500-users 2015

Detection and interpretation of shared genetic influences on 40 human traits, bioRxiv, 2015-05-28

We performed a genome-wide scan for genetic variants that influence multiple human phenotypes by comparing large genome-wide association studies (GWAS) of 40 traits or diseases, including anthropometric traits (e.g. nose size and male pattern baldness), immune traits (e.g. susceptibility to childhood ear infections and Crohn's disease), metabolic phenotypes (e.g. type 2 diabetes and lipid levels), and psychiatric diseases (e.g. schizophrenia and Parkinson's disease). First, we identified 307 loci (at a false discovery rate of 10%) that influence multiple traits (excluding “trivial” phenotype pairs like type 2 diabetes and fasting glucose). Several loci influence a large number of phenotypes; for example, variants near the blood group gene ABO influence eleven of these traits, including risk of childhood ear infections (rs635634 log-odds ratio = 0.06, P = 1.4 × 10−8) and allergies (log-odds ratio = 0.05, P = 2.5 × 10−8), among others. Similarly, a nonsynonymous variant in the zinc transporter SLC39A8 influences seven of these traits, including risk of schizophrenia (rs13107325 log-odds ratio = 0.15, P = 2 × 10−12) and Parkinson’s disease (log-odds ratio = -0.15, P = 1.6 × 10−7), among others. Second, we used these loci to identify traits that share multiple genetic causes in common. For example, genetic variants that delay age of menarche in women also, on average, delay age of voice drop in men, decrease body mass index (BMI), increase adult height, and decrease risk of male pattern baldness. Finally, we identified four pairs of traits that show evidence of a causal relationship. For example, we show evidence that increased BMI causally increases triglyceride levels, and that increased liability to hypothyroidism causally decreases adult height.

biorxiv genomics 0-100-users 2015

 

Created with the audiences framework by Jedidiah Carlson

Powered by Hugo