Biology subjects

Eddy, S. R.

Publications and source records attributed to Eddy, S. R..

3 recordsLinked to original sources

bioRxiv2018

Inferring Sequence-Structure Preferences of RNA-Binding Proteins with Convolutional Residual Networks

To infer the sequence and RNA structure specificities of RNA-binding proteins (RBPs) from experiments that enrich for bound sequences, we introduce a convolutional residual network which we call ResidualBind. ResidualBind significantly outperforms previous methods on experimental data from many RBP families. We interrogate ResidualBind to identify what features it has learned from high-affinity sequences with saliency analysis along with 1st-order and 2nd-order in silico mutagenesis. We show that in addition to sequence motifs, ResidualBind learns a model that includes the number of motifs, their spacing, and both positive and negative effects of RNA structure context. Strikingly, ResidualBind learns RNA structure context, including detailed base-pairing relationships, directly from sequence data, which we confirm on synthetic data. ResidualBind is a powerful, flexible, and interpretable model that can uncover cis-recognition preferences across a broad spectrum of RBPs.

genomics↗

bioRxiv2018

A genetic, genomic, and computational resource for exploring neural circuit function

The anatomy of many neural circuits is being characterized with increasing resolution, but their molecular properties remain mostly unknown. Here, we characterize gene expression patterns in distinct neural cell types of the Drosophila visual system using genetic lines to access individual cell types, the TAPIN-seq method to measure their transcriptomes, and a probabilistic method to interpret these measurements. We used these tools to build a resource of high-resolution transcriptomes for 100 driver lines covering 67 cell types, available at http://www.opticlobe.com. Combining these transcriptomes with recently reported connectomes helps characterize how information is transmitted and processed across a range of scales, from individual synapses to circuit pathways. We describe examples that include identifying neurotransmitters, including cases of co-release, generating functional hypotheses based on receptor expression, as well as identifying strong commonalities between different cell types.\n\nHighlightsO_LITranscriptomes reveal transmitters and receptors expressed in Drosophila visual neurons\nC_LIO_LITandem affinity purification of intact nuclei (TAPIN) enables neuronal genomics\nC_LIO_LITAPIN-seq and genetic drivers establish transcriptomes of 67 Drosophila cell types\nC_LIO_LIProbabilistic modeling simplifies interpretation of large transcriptome catalogs\nC_LI

neuroscience↗

bioRxiv2018

Representation Learning of Genomic Sequence Motifs with Convolutional Neural Networks

Although convolutional neural networks (CNNs) have been applied to a variety of computational genomics problems, there remains a large gap in our understanding of how they build representations of regulatory genomic sequences. Here we perform systematic experiments on synthetic sequences to reveal how CNN architecture, specifically convolutional filter size and max-pooling, influences the extent that sequence motif representations are learned by first layer filters. We find that CNNs designed to foster hierarchical representation learning of sequence motifs - assembling partial features into whole features in deeper layers - tend to learn distributed representations, i.e. partial motifs. On the other hand, CNNs that are designed to limit the ability to hierarchically build sequence motif representations in deeper layers tend to learn more interpretable localist representations, i.e. whole motifs. We then validate that this representation learning principle established from synthetic sequences generalizes to in vivo sequences.

genomics↗