Peyton Greenside

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

The challenge of linking intergenic mutations to target genes has limited molecular understanding of human diseases. Here we show that 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 into T helper 17 cells or regulatory T cells creates 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 fourfold increase in the number of potential target genes for autoimmune and cardiovascular diseases.

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 generates chromatin accessibility profiles from archival frozen tissue samples and 50-μm 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.

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 on gene regulation across different cell types and as models for studies of complex disease. To do so, 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 levels, chromatin accessibility, and DNA methylation. Our analysis focused on a comparison of inter-individual regulatory variation across cell types. 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 regulatory QTLs are in shared open chromatin. This observation motivated us to develop a deep neural network to predict open chromatin regions from DNA sequence alone. Using this approach, we were able to use the sequences of segregating haplotypes to predict the effects of common SNPs on cell-type-specific chromatin accessibility.

Molecular definition of a metastatic lung cancer state reveals a targetable CD109-Janus kinase-Stat axis

Lung cancer is the leading cause of cancer deaths worldwide, with the majority of mortality resulting from metastatic spread. However, the molecular mechanism by which cancer cells acquire the ability to disseminate from primary tumors, seed distant organs, and grow into tissue-destructive metastases remains incompletely understood. We combined tumor barcoding in a mouse model of human lung adenocarcinoma with unbiased genomic approaches to identify a transcriptional program that confers metastatic ability and predicts patient survival. Small-scale in vivo screening identified several genes, including Cd109, that encode novel pro-metastatic factors. We uncovered signaling mediated by Janus kinases (Jaks) and the transcription factor Stat3 as a critical, pharmacologically targetable effector of CD109-driven lung cancer metastasis. In summary, by coupling the systematic genomic analysis of purified cancer cells in distinct malignant states from mouse models with extensive human validation, we uncovered several key regulators of metastatic ability, including an actionable pro-metastatic CD109–Jak–Stat3 axis.

Intertumoral Heterogeneity in SCLC Is Influenced by the Cell Type of Origin

The extent to which early events shape tumor evolution is largely uncharacterized, even though a better understanding of these early events may help identify key vulnerabilities in advanced tumors. Here, using genetically defined mouse models of small cell lung cancer (SCLC), we uncovered distinct metastatic programs attributable to the cell type of origin. In one model, tumors gain metastatic ability through amplification of the transcription factor NFIB and a widespread increase in chromatin accessibility, whereas in the other model, tumors become metastatic in the absence of NFIB-driven chromatin alterations. Gene-expression and chromatin accessibility analyses identify distinct mechanisms as well as markers predictive of metastatic progression in both groups. Underlying the difference between the two programs was the cell type of origin of the tumors, with NFIB-independent metastases arising from mature neuroendocrine cells. Our findings underscore the importance of the identity of cell type of origin in influencing tumor evolution and metastatic mechanisms.Significance: We show that SCLC can arise from different cell types of origin, which profoundly influences the eventual genetic and epigenetic changes that enable metastatic progression. Understanding intertumoral heterogeneity in SCLC, and across cancer types, may illuminate mechanisms of tumor progression and uncover how the cell type of origin affects tumor evolution. Cancer Discov; 8(10); 1316-31. ©2018 AACR. See related commentary by Pozo et al., p. 1216 This article is highlighted in the In This Issue feature, p. 1195.

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. Availability Our implementation is available at https://github.com/kundajelab/keras/tree/keras_1 Contact avanti@stanford.edu, pgreens@stanford.edu, akundaje@stanford.edu

Prediction of protein-ligand interactions from paired protein sequence motifs and ligand substructures

Identification of small molecule ligands that bind to proteins is a critical step in drug discovery. Computational methods have been developed to accelerate the prediction of protein-ligand binding, but often depend on 3D protein structures. As only a limited number of protein 3D structures have been resolved, the ability to predict protein-ligand interactions without relying on a 3D representation would be highly valuable. We use an interpretable confidence-rated boosting algorithm to predict protein-ligand interactions with high accuracy from ligand chemical substructures and protein 1D sequence motifs, without relying on 3D protein structures. We compare several protein motif definitions, assess generalization of our model’s predictions to unseen proteins and ligands, demonstrate recovery of well established interactions and identify globally predictive protein-ligand motif pairs. By bridging biological and chemical perspectives, we demonstrate that it is possible to predict protein-ligand interactions using only motif-based features and that interpretation of these features can reveal new insights into the molecular mechanics underlying each interaction. Our work also lays a foundation to explore more predictive feature sets and sophisticated machine learning approaches as well as other applications, such as predicting unintended interactions or the effects of mutations.

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 SNPpet, 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 SNPpet 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. SNPpet’s predictions were moderately correlated (Spearman ρ = 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 SNPpet 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.

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

Motivation Transcription factors bind regulatory DNA sequences in a combinatorial manner to modulate gene expression. Deep neural networks (DNNs) can learn the 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 feature interactions encoded by the models. Results 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. Availability and implementation Code is available at: https://github.com/kundajelab/dfim. Supplementary information Supplementary data are available at Bioinformatics online.

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. Availability: The implementation is publicly available here: https://github.com/kundajelab/boosting2D/.