Algorithms that accurately predict gene structure from primary sequence alone were transformative for annotating the human genome. Can we also predict the expression levels of genes based solely on ...genome sequence? Here, we sought to apply deep convolutional neural networks toward that goal. Surprisingly, a model that includes only promoter sequences and features associated with mRNA stability explains 59% and 71% of variation in steady-state mRNA levels in human and mouse, respectively. This model, termed Xpresso, more than doubles the accuracy of alternative sequence-based models and isolates rules as predictive as models relying on chromatic immunoprecipitation sequencing (ChIP-seq) data. Xpresso recapitulates genome-wide patterns of transcriptional activity, and its residuals can be used to quantify the influence of enhancers, heterochromatic domains, and microRNAs. Model interpretation reveals that promoter-proximal CpG dinucleotides strongly predict transcriptional activity. Looking forward, we propose cell-type-specific gene-expression predictions based solely on primary sequences as a grand challenge for the field.
Display omitted
•Deep neural networks strongly predict gene expression levels solely from DNA sequence•Models help infer transcriptional and post-transcriptional gene regulatory mechanisms•Predictive power is competitive with models using thousands of biochemical datasets•CpG dinucleotide content at core promoters is strongly predictive of mRNA abundance
Agarwal and Shendure show that deep neural networks can strongly predict mRNA abundance solely from promoter sequence. The residuals of these predictions facilitate inferences about the regulatory influence of enhancers, heterochromatic domains, and microRNAs. Model interpretation reveals that CpG dinucleotide content at core promoters is associated with transcriptional activity.
How noncoding DNA determines gene expression in different cell types is a major unsolved problem, and critical downstream applications in human genetics depend on improved solutions. Here, we report ...substantially improved gene expression prediction accuracy from DNA sequences through the use of a deep learning architecture, called Enformer, that is able to integrate information from long-range interactions (up to 100 kb away) in the genome. This improvement yielded more accurate variant effect predictions on gene expression for both natural genetic variants and saturation mutagenesis measured by massively parallel reporter assays. Furthermore, Enformer learned to predict enhancer-promoter interactions directly from the DNA sequence competitively with methods that take direct experimental data as input. We expect that these advances will enable more effective fine-mapping of human disease associations and provide a framework to interpret cis-regulatory evolution.
The recent reports of two circular RNAs (circRNAs) with strong potential to act as microRNA (miRNA) sponges suggest that circRNAs might play important roles in regulating gene expression. However, ...the global properties of circRNAs are not well understood.
We developed a computational pipeline to identify circRNAs and quantify their relative abundance from RNA-seq data. Applying this pipeline to a large set of non-poly(A)-selected RNA-seq data from the ENCODE project, we annotated 7,112 human circRNAs that were estimated to comprise at least 10% of the transcripts accumulating from their loci. Most circRNAs are expressed in only a few cell types and at low abundance, but they are no more cell-type-specific than are mRNAs with similar overall expression levels. Although most circRNAs overlap protein-coding sequences, ribosome profiling provides no evidence for their translation. We also annotated 635 mouse circRNAs, and although 20% of them are orthologous to human circRNAs, the sequence conservation of these circRNA orthologs is no higher than that of their neighboring linear exons. The previously proposed miR-7 sponge, CDR1as, is one of only two circRNAs with more miRNA sites than expected by chance, with the next best miRNA-sponge candidate deriving from a gene encoding a primate-specific zinc-finger protein, ZNF91.
Our results provide a new framework for future investigation of this intriguing topological isoform while raising doubts regarding a biological function of most circRNAs.
MicroRNA targets are often recognized through pairing between the miRNA seed region and complementary sites within target mRNAs, but not all of these canonical sites are equally effective, and both ...computational and in vivo UV-crosslinking approaches suggest that many mRNAs are targeted through non-canonical interactions. Here, we show that recently reported non-canonical sites do not mediate repression despite binding the miRNA, which indicates that the vast majority of functional sites are canonical. Accordingly, we developed an improved quantitative model of canonical targeting, using a compendium of experimental datasets that we pre-processed to minimize confounding biases. This model, which considers site type and another 14 features to predict the most effectively targeted mRNAs, performed significantly better than existing models and was as informative as the best high-throughput in vivo crosslinking approaches. It drives the latest version of TargetScan (v7.0; targetscan.org), thereby providing a valuable resource for placing miRNAs into gene-regulatory networks.
Degradation rate is a fundamental aspect of mRNA metabolism, and the factors governing it remain poorly characterized. Understanding the genetic and biochemical determinants of mRNA half-life would ...enable more precise identification of variants that perturb gene expression through post-transcriptional gene regulatory mechanisms.
We establish a compendium of 39 human and 27 mouse transcriptome-wide mRNA decay rate datasets. A meta-analysis of these data identified a prevalence of technical noise and measurement bias, induced partially by the underlying experimental strategy. Correcting for these biases allowed us to derive more precise, consensus measurements of half-life which exhibit enhanced consistency between species. We trained substantially improved statistical models based upon genetic and biochemical features to better predict half-life and characterize the factors molding it. Our state-of-the-art model, Saluki, is a hybrid convolutional and recurrent deep neural network which relies only upon an mRNA sequence annotated with coding frame and splice sites to predict half-life (r=0.77). The key novel principle learned by Saluki is that the spatial positioning of splice sites, codons, and RNA-binding motifs within an mRNA is strongly associated with mRNA half-life. Saluki predicts the impact of RNA sequences and genetic mutations therein on mRNA stability, in agreement with functional measurements derived from massively parallel reporter assays.
Our work produces a more robust ground truth for transcriptome-wide mRNA half-lives in mammalian cells. Using these revised measurements, we trained Saluki, a model that is over 50% more accurate in predicting half-life from sequence than existing models. Saluki succinctly captures many of the known determinants of mRNA half-life and can be rapidly deployed to predict the functional consequences of arbitrary mutations in the transcriptome.
Abstract
3′ untranslated regions (3′ UTRs) post-transcriptionally regulate mRNA stability, localization, and translation rate. While 3′-UTR isoforms have been globally quantified in limited cell ...types using bulk measurements, their differential usage among cell types during mammalian development remains poorly characterized. In this study, we examine a dataset comprising ~2 million nuclei spanning E9.5–E13.5 of mouse embryonic development to quantify transcriptome-wide changes in alternative polyadenylation (APA). We observe a global lengthening of 3′ UTRs across embryonic stages in all cell types, although we detect shorter 3′ UTRs in hematopoietic lineages and longer 3′ UTRs in neuronal cell types within each stage. An analysis of RNA-binding protein (RBP) dynamics identifies ELAV-like family members, which are concomitantly induced in neuronal lineages and developmental stages experiencing 3′-UTR lengthening, as putative regulators of APA. By measuring 3′-UTR isoforms in an expansive single cell dataset, our work provides a transcriptome-wide and organism-wide map of the dynamic landscape of alternative polyadenylation during mammalian organogenesis.
To date, genome-wide association studies have implicated at least 35 loci in osteoarthritis but, due to linkage disequilibrium, the specific variants underlying these associations and the mechanisms ...by which they contribute to disease risk have yet to be pinpointed. Here, we functionally test 1,605 single nucleotide variants associated with osteoarthritis for regulatory activity using a massively parallel reporter assay. We identify six single nucleotide polymorphisms (SNPs) with differential regulatory activity between the major and minor alleles. We show that the most significant SNP, rs4730222, exhibits differential nuclear protein binding in electrophoretic mobility shift assays and drives increased expression of an alternative isoform of HBP1 in a heterozygote chondrosarcoma cell line, in a CRISPR-edited osteosarcoma cell line, and in chondrocytes derived from osteoarthritis patients. This study provides a framework for prioritization of GWAS variants and highlights a role of HBP1 and Wnt signaling in osteoarthritis pathogenesis.
Abstract
Non-homologous end-joining (NHEJ) plays an important role in double-strand break (DSB) repair of DNA. Recent studies have shown that the error patterns of NHEJ are strongly biased by ...sequence context, but these studies were based on relatively few templates. To investigate this more thoroughly, we systematically profiled ∼1.16 million independent mutational events resulting from CRISPR/Cas9-mediated cleavage and NHEJ-mediated DSB repair of 6872 synthetic target sequences, introduced into a human cell line via lentiviral infection. We find that: (i) insertions are dominated by 1 bp events templated by sequence immediately upstream of the cleavage site, (ii) deletions are predominantly associated with microhomology and (iii) targets exhibit variable but reproducible diversity with respect to the number and relative frequency of the mutational outcomes to which they give rise. From these data, we trained a model that uses local sequence context to predict the distribution of mutational outcomes. Exploiting the bias of NHEJ outcomes towards microhomology mediated events, we demonstrate the programming of deletion patterns by introducing microhomology to specific locations in the vicinity of the DSB site. We anticipate that our results will inform investigations of DSB repair mechanisms as well as the design of CRISPR/Cas9 experiments for diverse applications including genome-wide screens, gene therapy, lineage tracing and molecular recording.
Massively parallel reporter assays (MPRAs) functionally screen thousands of sequences for regulatory activity in parallel. To date, there are limited studies that systematically compare differences ...in MPRA design. Here, we screen a library of 2,440 candidate liver enhancers and controls for regulatory activity in HepG2 cells using nine different MPRA designs. We identify subtle but significant differences that correlate with epigenetic and sequence-level features, as well as differences in dynamic range and reproducibility. We also validate that enhancer activity is largely independent of orientation, at least for our library and designs. Finally, we assemble and test the same enhancers as 192-mers, 354-mers and 678-mers and observe sizable differences. This work provides a framework for the experimental design of high-throughput reporter assays, suggesting that the extended sequence context of tested elements and to a lesser degree the precise assay, influence MPRA results.