Biology subjects

Troyanskaya, O. G.

Publications and source records attributed to Troyanskaya, O. G..

28 records · Page 2Linked to original sources

bioRxiv2020

An automated framework for efficiently designing deep convolutional neural networks in genomics

Convolutional neural networks (CNNs) have become a standard for analysis of biological sequences. Tuning of network architectures is essential for CNNs performance, yet it requires substantial knowledge of machine learning and commitment of time and effort. This process thus imposes a major barrier to broad and effective application of modern deep learning in genomics. Here, we present AMBER, a fully automated framework to efficiently design and apply CNNs for genomic sequences. AMBER designs optimal models for user-specified biological questions through the state-of-the-art Neural Architecture Search (NAS). We applied AMBER to the task of modelling genomic regulatory features and demonstrated that the predictions of the AMBER-designed model are significantly more accurate than the equivalent baseline non-NAS models and match or even exceed published expert-designed models. Interpretation of AMBER architecture search revealed its design principles of utilizing the full space of computational operations for accurately modelling genomic sequences. Furthermore, we illustrated the use of AMBER to accurately discover functional genomic variants in allele-specific binding and disease heritability enrichment. AMBER provides an efficient automated method for designing accurate deep learning models in genomics.

bioinformatics↗

bioRxiv2020

Towards Building a Smart Kidney Atlas: Network-based integration of multimodal transcriptomic, proteomic, metabolomic and imaging data in the Kidney Precision Medicine Project

AO_SCPLOWBSTRACTC_SCPLOWKidney Precision Medicine Project (KPMP) is building a spatially-specified human tissue atlas at the single-cell resolution with molecular details of the kidney in health and disease. Here, we describe the construction of an integrated reference tissue map of cells, pathways and genes using unaffected regions of nephrectomy tissues and undiseased human biopsies from 55 subjects. We use single-cell and -nucleus transcriptomics, subsegmental laser microdissection bulk transcriptomics and proteomics, near-single-cell proteomics, 3-D nondestructive and CODEX imaging, and spatial metabolomics data to hierarchically identify genes, pathways and cells. Integrated data from these different technologies coherently describe cell types/subtypes within different nephron segments and interstitium. These spatial profiles identify cell-level functional organization of the kidney tissue as indicative of their physiological functions and map different cell subtypes to genes, proteins, metabolites and pathways. Comparison of transcellular sodium reabsorption along the nephron to levels of mRNAs encoding the different sodium transporter genes indicate that mRNA levels are largely congruent with physiological activity.This reference atlas provides an initial framework for molecular classification of kidney disease when multiple molecular mechanisms underlie convergent clinical phenotypes.

bioinformatics↗

bioRxiv2020

Single nucleus multi-omics regulatory atlas of the murine pituitary

The pituitary regulates growth, reproduction and other endocrine systems. To investigate transcriptional network epigenetic mechanisms, we generated paired single nucleus (sn) transcriptome and chromatin accessibility profiles in single mouse pituitaries and genome-wide sn methylation datasets. Our analysis provided insight into cell type epigenetics, regulatory circuit and gene control mechanisms. Latent variable pathway analysis detected corresponding transcriptome and chromatin accessibility programs showing both inter-sexual and inter-individual variation. Multi-omics analysis of gene regulatory networks identified cell type-specific regulons whose composition and function were shaped by the promoter accessibility state of target genes. Co-accessibility analysis comprehensively identified putative cis-regulatory regions, including a domain 17kb upstream of Fshb that overlapped the fertility-linked rs11031006 human polymorphism. In vitro CRISPR-deletion at this locus increased Fshb levels, supporting this domains inferred regulatory role. The sn pituitary multi-omics atlas (snpituitaryatlas.princeton.edu) is a public resource for elucidating cell type-specific gene regulatory mechanisms and principles of transcription circuit control.

cell biology↗

bioRxiv2020

Genome-wide landscape of RNA-binding protein dysregulation reveals a major impact on psychiatric disorder risk

Despite the strong genetic basis of psychiatric disorders, the molecular origins of these diseases are still largely unmapped. RNA-binding proteins (RBPs) are responsible for most post-transcriptional regulation, from splicing to translational to localization. RBPs thus act as key gatekeepers of cellular homeostasis, especially in the brain. Here, we leverage a deep learning approach to interrogate variant effects genome-wide, and discover that the dysregulation of RBP target sites is a principal contributor to psychiatric disorder risk. We show that specific modes of RBP regulation are genetically linked to the heritability of psychiatric disorders, and demonstrate that diverse RBP regulatory functions are reflected in distinct genome-wide negative selection signatures. Notably, RBP dysregulation has a stronger impact on psychiatric disorders than common coding region variants and explains heritability not currently captured by large-scale molecular QTL studies (expression QTLs and splicing QTLs). We share genome-wide profiles of RBP target site dysregulation, which we used to identify DDHD2 as a candidate schizophrenia risk gene, in a public web server. This resource provides a novel analytical framework to connect the full range of RNA regulation to complex disease.

genetics↗

bioRxiv2020

Spatial Transcriptional Mapping of the Human Nephrogenic Program

Congenital abnormalities of the kidney and urinary tract are amongst the most common birth defects affecting 3% of newborns. The human kidney develops over a 30-week period in which a nephron progenitor pool gives rise to around a million nephrons. To establish a framework for human nephrogenesis, we spatially resolved a stereotypical process by which equipotent nephron progenitors generate a nephron anlagen, then applied data-driven approaches to construct three-dimensional protein maps on anatomical models of the nephrogenic program. Single cell RNA sequencing identified novel progenitor states which were spatially mapped to the nephron anatomy enabling the generation of functional gene-networks predicting interactions within and between nephron cell-types. Network mining identified known developmental disease genes and predicts new targets of interest. The spatially resolved nephrogenic program made available through the Human Nephrogenesis Atlas (https://sckidney.flatironinstitute.org/) will facilitate an understanding of kidney development and disease, and enhance efforts to generate new kidney structures.

cell biology↗

bioRxiv2020

DeepArk: modeling cis-regulatory codes of model species with deep learning

To enable large-scale analyses of regulatory logic in model species, we developed DeepArk (https://DeepArk.princeton.edu), a set of deep learning models of the cis-regulatory codes of four widely-studied species: Caenorhabditis elegans, Danio rerio, Drosophila melanogaster, and Mus musculus. DeepArk accurately predicts the presence of thousands of different context-specific regulatory features, including chromatin states, histone marks, and transcription factors. In vivo studies show that DeepArk can predict the regulatory impact of any genomic variant (including rare or not previously observed), and enables the regulatory annotation of understudied model species.

bioinformatics↗

bioRxiv2019

A Multimodal and Integrated Approach to Interrogate Human Kidney Biopsies with Rigor and Reproducibility: The Kidney Precision Medicine Project

Comprehensive and spatially mapped molecular atlases of organs at a cellular level are a critical resource to gain insights into pathogenic mechanisms and personalized therapies for diseases. The Kidney Precision Medicine Project (KPMP) is an endeavor to generate 3-dimensional (3D) molecular atlases of healthy and diseased kidney biopsies using multiple state-of-the-art OMICS and imaging technologies across several institutions. Obtaining rigorous and reproducible results from disparate methods and at different sites to interrogate biomolecules at a single cell level or in 3D space is a significant challenge that can be a futile exercise if not well controlled. We describe a "follow the tissue" pipeline for generating a reliable and authentic single cell/region 3D molecular atlas of human adult kidney. Our approach emphasizes quality assurance, quality control, validation and harmonization across different OMICS and imaging technologies from sample procurement, processing, storage, shipping to data generation, analysis and sharing. We established benchmarks for quality control, rigor, reproducibility and feasibility across multiple technologies through a pilot experiment using common source tissue that was processed and analyzed at different institutions and different technologies. A peer review system was established to critically review quality control measures and the reproducibility of data generated by each technology before being approved to interrogate clinical biopsy specimens. The process established economizes the use of valuable biopsy tissue for multi-OMICS and imaging analysis with stringent quality control to ensure rigor and reproducibility of results and serves as a model for precision medicine projects across laboratories, institutions and consortia.

scientific communication and education↗

bioRxiv2018

Organoid single-cell profiling identifies a transcriptional signature of glomerular disease

Podocyte injury is central to many forms of kidney disease, but transcriptional signatures reflecting podocyte injury and compensation mechanisms are challenging to analyze in vivo. Human kidney organoids derived from pluripotent stem cells (PSCs), a new model for disease and regeneration, present an opportunity to explore the transcriptional plasticity of podocytes. Here, transcriptional profiling of over 12,000 single cells from human PSC-derived kidney organoid cultures was used to identify robust and reproducible cell-lineage gene expression signatures shared with developing human kidneys based on trajectory analysis. Surprisingly, the gene expression signature characteristic of developing glomerular epithelial cells was also observed in glomerular tissue from a kidney disease cohort. This signature correlated with proteinuria and inverse eGFR, and was confirmed in an independent podocytopathy cohort. Three genes in particular were further identified as critical components of the glomerular disease signature. We conclude that cells in human PSC-derived kidney organoids reliably recapitulate the developmental transcriptional program of podocytes and other cell lineages in the human kidney, and that the early transcriptional profile seen in developing podocytes is reactivated in glomerular disease. Our findings demonstrate an innovative approach to identifying novel molecular programs involved in the pathogenesis of glomerulopathies.

systems biology↗

bioRxiv2018

Selene: a PyTorch-based deep learning library for sequence-level data

To enable the application of deep learning in biology, we present Selene (https://selene.flatironinstitute.org/), a PyTorch-based deep learning library for fast and easy development, training, and application of deep learning model architectures for any biological sequences. We demonstrate how Selene allows researchers to easily train a published architecture on new data, develop and evaluate a new architecture, and use a trained model to answer biological questions of interest.

bioinformatics↗

bioRxiv2017

Transcriptome Analysis of Adult C. elegans Cells Reveals Tissue-specific Gene and Isoform Expression

The biology and behavior of adults differ substantially from those of developing animals, and cell-specific information is critical for deciphering the biology of multicellular animals. Thus, adult tissue-specific transcriptomic data are critical for understanding molecular mechanisms that control their phenotypes. We used adult cell-specific isolation to identify the transcriptomes of C. elegans four major tissues (or \"tissue-ome\"), identifying ubiquitously expressed and tissue-specific \"super-enriched\" genes. These data newly reveal the hypodermis metabolic character, suggest potential worm-human tissue orthologies, and identify tissue-specific changes in the Insulin/IGF-1 signaling pathway. Tissue-specific alternative splicing analysis identified a large set of collagen isoforms and a neuron-specific CREB isoform. Finally, we developed a machine learning-based prediction tool for 70 sub-tissue cell types, which we used to predict cellular expression differences in IIS/FOXO signaling, stage-specific TGF-b activity, and basal vs. memory-induced CREB transcription. Together, these data provide a rich resource for understanding the biology governing multicellular adult animals

genomics↗