Biology subjects

Kundaje, A.

Publications and source records attributed to Kundaje, A..

18 recordsLinked to original sources

bioRxiv2018

Deciphering regulatory DNA sequences and noncoding genetic variants using neural network models of massively parallel reporter assays

The relationship between noncoding DNA sequence and gene expression is not well-understood. Massively parallel reporter assays (MPRAs), which quantify the regulatory activity of large libraries of DNA sequences in parallel, are a powerful approach to characterize this relationship. We present MPRA-DragoNN, a convolutional neural network (CNN)-based framework to predict and interpret the regulatory activity of DNA sequences as measured by MPRAs. While our method is generally applicable to a variety of MPRA designs, here we trained our model on the Sharpr-MPRA dataset that measures the activity of ~500,000 constructs tiling 15,720 regulatory regions in human K562 and HepG2 cell lines. MPRA-DragoNN predictions were moderately correlated (Spearman{rho} = 0.28) with measured activity and were within range of replicate concordance of the assay. State-of-the-art model interpretation methods revealed high-resolution predictive regulatory sequence features that overlapped transcription factor (TF) binding motifs. We used the model to investigate the cell type and chromatin state preferences of predictive TF motifs. We explored the ability of our model to predict the allelic effects of regulatory variants in an independent MPRA experiment and fine map putative functional SNPs in loci associated with lipid traits. Our results suggest that interpretable deep learning models trained on MPRA data have the potential to reveal meaningful patterns in regulatory DNA sequences and prioritize regulatory genetic variants, especially as larger, higher-quality datasets are produced.

genomics↗

bioRxiv2018

Kipoi: accelerating the community exchange and reuse of predictive models for genomics

Advanced machine learning models applied to large-scale genomics datasets hold the promise to be major drivers for genome science. Once trained, such models can serve as a tool to probe the relationships between data modalities, including the effect of genetic variants on phenotype. However, lack of standardization and limited accessibility of trained models have hampered their impact in practice. To address this, we present Kipoi, a collaborative initiative to define standards and to foster reuse of trained models in genomics. Already, the Kipoi repository contains over 2,000 trained models that cover canonical prediction tasks in transcriptional and post-transcriptional gene regulation. The Kipoi model standard grants automated software installation and provides unified interfaces to apply and interpret models. We illustrate Kipoi through canonical use cases, including model benchmarking, transfer learning, variant effect prediction, and building new models from existing ones. By providing a unified framework to archive, share, access, use, and build on models developed by the community, Kipoi will foster the dissemination and use of machine learning models in genomics.

bioinformatics↗

bioRxiv2018

Remodeling of epigenome and transcriptome landscapes with aging in mice reveals widespread induction of inflammatory responses

Aging is accompanied by the functional decline of tissues. However, a systematic study of epigenomic and transcriptomic changes across tissues during aging is missing. Here we generated chromatin maps and transcriptomes from 4 tissues and one cell type from young, middle-age, and old mice, yielding 143 high-quality datasets. We focused specifically on chromatin marks linked to gene expression regulation and cell identity: histone H3 trimethylation at lysine 4 (H3K4me3), a mark enriched at promoters, and histone H3 acetylation at lysine 27 (H3K27ac), a mark enriched at active enhancers. Epigenomic and transcriptomic landscapes could easily distinguish between ages, and machine learning analysis showed that specific epigenomic states could predict transcriptional changes during aging. Analysis of datasets from all tissues identified recurrent age-related chromatin and transcriptional changes in key processes, including the upregulation of immune system response pathways such as the interferon signaling pathway. The upregulation of interferon response pathway with age was accompanied by increased transcription of various endogenous retroviral sequences. Pathways deregulated during mouse aging across tissues, notably innate immune pathways, were also deregulated with aging in other vertebrate species - African turquoise killifish, rat, and humans - indicating common signatures of age across species. To date, our dataset represents the largest multi-tissue epigenomic and transcriptomic dataset for vertebrate aging. This resource identifies chromatin and transcriptional states that are characteristic of youthful tissues, which could be leveraged to restore aspects of youthful functionality to old tissues.

genomics↗

bioRxiv2018

Discovering epistatic feature interactions from neural network models of regulatory DNA sequences

Transcription factors bind complex regulatory DNA sequence patterns in a combinatorial manner to modulate gene expression. Deep neural networks (DNNs) can learn these cis-regulatory grammars encoded in regulatory DNA sequences associated with transcription factor binding and chromatin accessibility. Several feature attribution methods have been developed for estimating the predictive importance of individual features (nucleotides or motifs) in any input DNA sequence to its associated output prediction from a DNN model. However, these methods do not reveal higher-order, epistatic feature interactions encoded by the models. We present a new method called Deep Feature Interaction Maps (DFIM) to efficiently estimate interactions between all pairs of features in any input DNA sequence. DFIM accurately identifies ground truth motif interactions embedded in simulated regulatory DNA sequences. DFIM identifies synergistic interactions between GATA1 and TAL1 motifs from in vivo TF binding models. DFIM reveals epistatic interactions involving nucleotides flanking the core motif of the Cbf1 TF in yeast from in vitro TF binding models. We also apply DFIM to regulatory sequence models of in vivo chromatin accessibility to reveal interactions between regulatory genetic variants and proximal motifs of target TFs as validated by TF binding quantitative trait loci. Our approach makes significant strides in improving the interpretability of deep learning models for genomics.

bioinformatics↗

bioRxiv2017

Vulnerabilities of transcriptome-wide association studies

Transcriptome-wide association studies (TWAS) integrate GWAS and gene expression datasets to find gene-trait associations. In this Perspective, we explore properties of TWAS as a potential approach to prioritize causal genes, using simulations and case studies of literature-curated candidate causal genes for schizophrenia, LDL cholesterol and Crohns disease. We explore risk loci where TWAS accurately prioritizes the likely causal gene, as well as loci where TWAS prioritizes multiple genes, some of which are unlikely to be causal, because they share the same variants as eQTLs. We illustrate that TWAS is especially prone to spurious prioritization when using expression data from tissues or cell types that are less related to the trait, due to substantial variation in both expression levels and eQTL strengths across cell types. Nonetheless, TWAS prioritizes candidate causal genes at GWAS loci more accurately than simple baselines based on proximity to lead GWAS variant and expression in trait-related tissue. We discuss current strategies and future opportunities for improving the performance of TWAS for causal gene prioritization. Our results showcase the strengths and limitations of using expression variation across individuals to determine causal genes at GWAS loci and provide guidelines and best practices when using TWAS to prioritize candidate causal genes.

genetics↗

bioRxiv2017

A common pattern of DNase-I footprinting throughout the human mtDNA unveils clues for a chromatin-like organization

Human mitochondrial DNA (mtDNA) is believed to lack chromatin and histones. Instead, it is coated solely by the transcription factor TFAM, which binds the mtDNA without sequence specificity and packs it into a bacterial-like nucleoid in a dose-dependent fashion. We asked whether mtDNA packaging is more regulated than once thought. As a first step to address this question, we analyzed mtDNA DNase-I-seq experiments in 324 different human cell types and found, for the first time, a pattern of 29 Genomic footprinting (DGF) sites throughout the mtDNA shared by [~]90% of the tested samples. Low SNP density at the DGF sites, and their conservation in mouse DNase-seq experiments, reflect strong selective constraints. Co-localization of the DGFs with known mtDNA regulatory elements and with recently-discovered transcription pausing sites, suggest a role for such DGFs in mtDNA transcription. Altered mtDNA DGF pattern in IL-3 treated CD+34 cells offer first clue to their physiological importance. Taken together, human mtDNA has a conserved and regulated protein-DNA organization, which is likely involved in regulation of mtDNA gene expression.

genomics↗

bioRxiv2017

Measuring the reproducibility and quality of Hi-C data

Hi-C is currently the most widely used assay to investigate the 3D organization of the genome and to study its role in gene regulation, DNA replication, and disease. However, Hi-C experiments are costly to perform and involve multiple complex experimental steps; thus, accurate methods for measuring the quality and reproducibility of Hi-C data are essential to determine whether the output should be used further in a study. Using real and simulated data, we profile the performance of several recently proposed methods for assessing reproducibility of population Hi-C data, including HiCRep, GenomeDISCO, HiC-Spector and QuASAR-Rep. By explicitly controlling noise and sparsity through simulations, we demonstrate the deficiencies of performing simple correlation analysis on pairs of matrices, and we show that methods developed specifically for Hi-C data produce better measures of reproducibility. We also show how to use established (e.g., ratio of intra to interchromosomal interactions) and novel (e.g., QuASAR-QC) measures to identify low quality experiments. In this work, we assess reproducibility and quality measures by varying sequencing depth, resolution and noise levels in Hi-C data from 13 cell lines, with two biological replicates each, as well as 176 simulated matrices. Through this extensive validation and benchmarking of Hi-C data, we describe best practices for reproducibility and quality assessment of Hi-C experiments. We make all software publicly available at http://github.com/kundajelab/3DChromatin_ReplicateQC to facilitate adoption in the community.

genomics↗

bioRxiv2017

GenomeDISCO: A concordance score for chromosome conformation capture experiments using random walks on contact map graphs

MotivationThe three-dimensional organization of chromatin plays a critical role in gene regulation and disease. High-throughput chromosome conformation capture experiments such as Hi-C are used to obtain genome-wide maps of 3D chromatin contacts. However, robust estimation of data quality and systematic comparison of these contact maps is challenging due to the multi-scale, hierarchical structure of chromatin contacts and the resulting properties of experimental noise in the data. Measuring concordance of contact maps is important for assessing reproducibility of replicate experiments and for modeling variation between different cellular contexts.\n\nResultsWe introduce a concordance measure called GenomeDISCO (DIfferences between Smoothed COntact maps) for assessing the similarity of a pair of contact maps obtained from chromosome conformation capture experiments. The key idea is to smooth contact maps using random walks on the contact map graph, before estimating concordance. We use simulated datasets to benchmark GenomeDISCOs sensitivity to different types of noise that affect chromatin contact maps. When applied to a large collection of Hi-C datasets, GenomeDISCO accurately distinguishes biological replicates from samples obtained from different cell types. GenomeDISCO also generalizes to other chromosome conformation capture assays, such as HiChIP.\n\nAvailabilitySoftware implementing GenomeDISCO is available at https://github.com/kundajelab/genomedisco.\n\nContactakundaje@stanford.edu\n\nSupplementary informationSupplementary data are available at Bioinformatics online.

bioinformatics↗

bioRxiv2017

Enhancer connectome in primary human cells reveals target genes of disease-associated DNA elements

The challenge of linking intergenic mutations to target genes has limited molecular understanding of diverse human diseases. Here, we show H3K27ac HiChIP generates high-resolution contact maps of active enhancers and target genes in rare primary human T cell subtypes and coronary artery smooth muscle cells. Differentiation of naive T cells to either T helper 17 cells or regulatory T cells create subtype-specific enhancer-promoter interactions, specifically at regions of shared DNA accessibility. These data provide a principled means of assigning molecular functions to autoimmune and cardiovascular disease risk variants, linking hundreds of noncoding variants to putative gene targets. Target genes identified with HiChIP are further supported by CRISPR interference and activation at linked enhancers, by the presence of expression quantitative trait loci, and by allele-specific enhancer loops in patient-derived primary cells. The majority of disease-associated enhancers contact genes beyond the nearest gene in the linear genome, leading to a four-fold increase of potential target genes for autoimmune and cardiovascular diseases.

genomics↗

bioRxiv2017

An improved ATAC-seq protocol reduces background and enables interrogation of frozen tissues

We present Omni-ATAC, an improved ATAC-seq protocol for chromatin accessibility profiling that works across multiple applications with substantial improvement of signal-to-background ratio and information content. The Omni-ATAC protocol enables chromatin accessibility profiling from archival frozen tissue samples and 50 m sections, revealing the activities of disease-associated DNA elements in distinct human brain structures. The Omni-ATAC protocol enables the interrogation of personal regulomes in tissue context and translational studies.

genomics↗

bioRxiv2017

PyBoost: A parallelized Python implementation of 2D boosting with hierarchies

Motivation: Gene expression is controlled by networks of transcription factors that bind specific sequence motifs in regulatory DNA elements such as promoters and enhancers. GeneClass is a boosting-based algorithm that learns gene regulatory networks from complementary paired feature sets such as transcription factor expression levels and binding motifs across conditions. This algorithm can be used to predict functional genomics measures of cell state, such as gene expression and chromatin accessibility, in different cellular conditions. We present a parallelized, Python-based implementation of GeneClass, called PyBoost, along with a novel hierarchical implementation of the algorithm, called HiBoost. HiBoost allows regulatory logic to be constrained to a hierarchical group of conditions or cell types. The software can be used to dissect differentiation cascades, time courses or other perturbation data that naturally form a hierarchy or trajectory. We demonstrate the application of PyBoost and HiBoost to learn regulators of tadpole tail regeneration and hematopoeitic stem cell differentiation and validate learned regulators through an inducible CRISPR system.\n\nAvailability: The implementation is publicly available here: https://github.com/kundajelab/boosting2D/.

bioinformatics↗

bioRxiv2017

Separable Fully Connected Layers Improve Deep Learning Models For Genomics

Convolutional neural networks are rapidly gaining popularity in regulatory genomics. Typically, these networks have a stack of convolutional and pooling layers, followed by one or more fully connected layers. In genomics, the same positional patterns are often present across multiple convolutional channels. Therefore, in current state-of-the-art networks, there exists significant redundancy in the representations learned by standard fully connected layers. We present a new separable fully connected layer that learns a weights tensor that is the outer product of positional weights and cross-channel weights, thereby allowing the same positional patterns to be applied across multiple convolutional channels. Decomposing positional and cross-channel weights further enables us to readily impose biologically-inspired constraints on positional weights, such as symmetry. We also propose a novel regularizer and constraint that act on curvature in the positional weights. Using experiments on simulated and in vivo datasets, we show that networks that incorporate our separable fully connected layer outperform conventional models with analogous architectures and the same number of parameters. Additionally, our networks are more robust to hyperparameter tuning, have more informative gradients, and produce importance scores that are more consistent with known biology than conventional deep neural networks.\n\nAvailabilityImplementation: https://github.com/kundajelab/keras/tree/keras_1\n\nA gist illustrating model setup is at: goo.gl/gYooaa

bioinformatics↗

bioRxiv2017

Opportunities And Obstacles For Deep Learning In Biology And Medicine

Deep learning, which describes a class of machine learning algorithms, has recently showed impressive results across a variety of domains. Biology and medicine are data rich, but the data are complex and often ill-understood. Problems of this nature may be particularly well-suited to deep learning techniques. We examine applications of deep learning to a variety of biomedical problems--patient classification, fundamental biological processes, and treatment of patients--and discuss whether deep learning will transform these tasks or if the biomedical sphere poses unique challenges. We find that deep learning has yet to revolutionize or definitively resolve any of these problems, but promising advances have been made on the prior state of the art. Even when improvement over a previous baseline has been modest, we have seen signs that deep learning methods may speed or aid human investigation. More work is needed to address concerns related to interpretability and how to best model each problem. Furthermore, the limited amount of labeled data for training presents problems in some domains, as do legal and privacy constraints on work with sensitive health records. Nonetheless, we foresee deep learning powering changes at both bench and bedside with the potential to transform several areas of biology and medicine.

bioinformatics↗

bioRxiv2017

Reverse-complement parameter sharing improves deep learning models for genomics

Deep learning approaches that have produced breakthrough predictive models in computer vision, speech recognition and machine translation are now being successfully applied to problems in regulatory genomics. However, deep learning architectures used thus far in genomics are often directly ported from computer vision and natural language processing applications with few, if any, domain-specific modifications. In double-stranded DNA, the same pattern may appear identically on one strand and its reverse complement due to complementary base pairing. Here, we show that conventional deep learning models that do not explicitly model this property can produce substantially different predictions on forward and reverse-complement versions of the same DNA sequence. We present four new convolutional neural network layers that leverage the reverse-complement property of genomic DNA sequence by sharing parameters between forward and reverse-complement representations in the model. These layers guarantee that forward and reverse-complement sequences produce identical predictions within numerical precision. Using experiments on simulated and in vivo transcription factor binding data, we show that our proposed architectures lead to improved performance, faster learning and cleaner internal representations compared to conventional architectures trained on the same data.\n\nAvailabilityOur implementation is available at\n\nContactavanti@stanford.edu, pgreens@stanford.edu, akundaje@stanford.edu

bioinformatics↗

bioRxiv2016

Umap and Bismap: quantifying genome and methylome mappability

MotivationShort-read sequencing enables assessment of genetic and biochemical traits of individual genomic regions, such as the location of genetic variation, protein binding, and chemical modifications. Every region in a genome assembly has a property called mappability which measures the extent to which it can be uniquely mapped by sequence reads. In regions of lower mappability, estimates of genomic and epigenomic characteristics from sequencing assays are less reliable. At best, sequencing assays will produce misleadingly low numbers of reads in these regions. At worst, these regions have increased susceptibility to spurious mapping from reads from other regions of the genome with sequencing errors or unexpected genetic variation. Bisulfite sequencing approaches used to identify DNA methylation exacerbate these problems by introducing large numbers of reads that map to multiple regions. While many tools consider mappability during the read mapping process, subsequent analysis often loses this information. Both to correct assumptions of uniformity in downstream analysis, and to identify regions where the analysis is less reliable, it is necessary to know the mappability of both ordinary and bisulfite-converted genomes.\n\nResultsWe introduce the Umap software for identifying uniquely mappable regions of any genome. Its Bismap extension identifies mappability of the bisulfite-converted genome. With a read length of 24 bp, 18.7% of the unmodified genome and 33.5% of the bisulfite-converted genome is not uniquely mappable. This complicates interpretation of functional genomics experiments using short-read sequencing, especially in regulatory regions. For example, 81% of human CpG islands overlap with regions that are not uniquely mappable. Similarly, in some ENCODE ChIP-seq datasets, up to 50% of peaks overlap with regions that are not uniquely mappable. We also explored differentially methylated regions from a case-control study and identified regions that were not uniquely mappable. In the widely used 450K methylation array, 4,230 probes are not uniquely mappable. Genome mappability is higher with longer sequencing reads, but most publicly available ChIP-seq and reduced representation bisulfite sequencing datasets have shorter reads. Therefore, uneven and low mappability remains a concern in a majority of existing data.\n\nAvailabilityA Umap and Bismap track hub for human genome assemblies GRCh37/hg19 and GRCh38/hg38, and mouse assemblies GRCm37/mm9 and GRCm38/mm10 is available at http://bismap.hoffmanlab.org for use with the UCSC and Ensembl genome browsers. We have deposited in Zenodo the current version of our software (https://doi.org/10.5281/zenodo.800648) and the mappability data used in this project (https://doi.org/10.5281/zenodo.800645). In addition, the software (https://bitbucket.org/hoffmanlab/umap) is freely available under the GNU General Public License, version 3 (GPLv3).\n\nContactmichael.hoffman@utoronto.ca

genomics↗

bioRxiv2016

Impact of regulatory variation across human iPSCs and differentiated cells

Induced pluripotent stem cells (iPSCs) are an essential tool for studying cellular differentiation and cell types that are otherwise difficult to access. We investigated the use of iPSCs and iPSC-derived cells to study the impact of genetic variation across different cell types and as models for studies of complex disease. We established a panel of iPSCs from 58 well-studied Yoruba lymphoblastoid cell lines (LCLs); 14 of these lines were further differentiated into cardiomyocytes. We characterized regulatory variation across individuals and cell types by measuring gene expression, chromatin accessibility and DNA methylation. Regulatory variation between individuals is lower in iPSCs than in the differentiated cell types, consistent with the intuition that developmental processes are generally canalized. While most cell type-specific regulatory quantitative trait loci (QTLs) lie in chromatin that is open only in the affected cell types, we found that 20% of cell type-specific QTLs are in shared open chromatin. Finally, we developed a deep neural network to predict open chromatin regions from DNA sequence alone and were able to use the sequences of segregating haplotypes to predict the effects of common SNPs on cell type-specific chromatin accessibility.

genomics↗

bioRxiv2016

Chromatin accessibility dynamics reveal novel functional enhancers in C. elegans

Chromatin accessibility, a crucial component of genome regulation, has primarily been studied in homogeneous and simple systems, such as isolated cell populations or early-development models. Whether chromatin accessibility can be assessed in complex, dynamic systems in vivo with high sensitivity remains largely unexplored. In this study, we use ATAC-seq to identify chromatin accessibility changes in a whole animal, the model organism C. elegans, from embryogenesis to adulthood. Chromatin accessibility changes between developmental stages are highly reproducible, recapitulate histone modification changes, and reveal key regulatory aspects of the epigenomic landscape throughout organismal development. We find that over 5,000 distal non-coding regions exhibit dynamic changes in chromatin accessibility between developmental stages, and could thereby represent putative enhancers. When tested in vivo, several of these putative enhancers indeed drive novel cell-type-and temporal-specific patterns of expression. Finally, by integrating transcription factor binding motifs in a machine learning framework, we identify EOR-1 as a unique transcription factor that may regulate chromatin dynamics during development. Our study provides a unique resource for C. elegans, a system in which the prevalence and importance of enhancers remains poorly characterized, and demonstrates the power of using whole organism chromatin accessibility to identify novel regulatory regions in complex systems.

genomics↗

bioRxiv2016

Semi-automated genome annotation using epigenomic data and Segway

Biochemical techniques measure many individual properties of chromatin along the genome. These properties include DNA accessibility (measured by DNase-seq) and the presence of individual transcription factors and histone modifications (measured by ChIP-seq). Segway is software that transforms multiple datasets on chromatin properties into a single annotation of the genome that a biologist can more easily interpret. This protocol describes how to use Segway to annotate the genome, starting with reads from a ChIP-seq experiment. It includes pre-processing of data, training the Segway model, annotating the genome, assigning biological meanings to labels, and visualizing the annotation in a genome browser.

bioinformatics↗