Promoter CpG Density Predicts Downstream Gene Loss-of-Function Intolerance

Epigenomic insights into common human disease pathology

The epigenome-the chemical modifications and chromatin-related packaging of the genome-enables the same genetic template to be activated or repressed in different cellular settings. This multi-layered mechanism facilitates cell-type specific function by setting the local sequence and 3D interactive activity level. Gene transcription is further modulated through the interplay with transcription factors and co-regulators. The human body requires this epigenomic apparatus to be precisely installed throughout development and then adequately maintained during the lifespan. The causal role of the epigenome in human pathology, beyond imprinting disorders and specific tumour suppressor genes, was further brought into the spotlight by large-scale sequencing projects identifying that mutations in epigenomic machinery genes could be critical drivers in both cancer and developmental disorders. Abrogation of this cellular mechanism is providing new molecular insights into pathogenesis. However, deciphering the full breadth and implications of these epigenomic changes remains challenging. Knowledge is accruing regarding disease mechanisms and clinical biomarkers, through pathogenically relevant and surrogate tissue analyses, respectively. Advances include consortia generated cell-type specific reference epigenomes, high-throughput DNA methylome association studies, as well as insights into ageing-related diseases from biological 'clocks' constructed by machine learning algorithms. Also, 3rd-generation sequencing is beginning to disentangle the complexity of genetic and DNA modification haplotypes. Cell-free DNA methylation as a cancer biomarker has clear clinical utility and further potential to assess organ damage across many disorders. Finally, molecular understanding of disease aetiology brings with it the opportunity for exact therapeutic alteration of the epigenome through CRISPR-activation or inhibition.

Bayesian estimation of gene constraint from an evolutionary model with gene features

Measures of selective constraint on genes have been used for many applications including clinical interpretation of rare coding variants, disease gene discovery, and studies of genome evolution. However, widely-used metrics are severely underpowered at detecting constraint for the shortest ∼25% of genes, potentially causing important pathogenic mutations to be overlooked. We developed a framework combining a population genetics model with machine learning on gene features to enable accurate inference of an interpretable constraint metric, shet. Our estimates outperform existing metrics for prioritizing genes important for cell essentiality, human disease, and other phenotypes, especially for short genes. Our new estimates of selective constraint should have wide utility for characterizing genes relevant to human disease. Finally, our inference framework, GeneBayes, provides a flexible platform that can improve estimation of many gene-level properties, such as rare variant burden or gene expression differences.

Deep multiple-instance learning accurately predicts gene haploinsufficiency and deletion pathogenicity

Copy number losses (deletions) are a major contributor to the etiology of severe genetic disorders. Although haploinsufficient genes play a critical role in deletion pathogenicity, current methods for deletion pathogenicity prediction fail to integrate multiple lines of evidence for haploinsufficiency at the gene level, limiting their power to pinpoint deleterious deletions associated with genetic disorders. Here we introduce DosaCNV, a deep multiple-instance learning framework that, for the first time, models deletion pathogenicity jointly with gene haploinsufficiency. By integrating over 30 gene-level features potentially predictive of haploinsufficiency, DosaCNV shows unmatched performance in prioritizing pathogenic deletions associated with a broad spectrum of genetic disorders. Furthermore, DosaCNV outperforms existing methods in predicting gene haploinsufficiency even though it is not trained on known haploinsufficient genes. Finally, DosaCNV leverages a state-of-the-art technique to quantify the contributions of individual gene-level features to haploinsufficiency, allowing for human-understandable explanations of model predictions. Altogether, DosaCNV is a powerful computational tool for both fundamental and translational research.

Epigenetic dynamics during capacitation of naïve human pluripotent stem cells

Human pluripotent stem cells (hPSCs) are of fundamental relevance in regenerative medicine. Naïve hPSCs hold promise to overcome some of the limitations of conventional (primed) hPSCs, including recurrent epigenetic anomalies. Naïve-to-primed transition (capacitation) follows transcriptional dynamics of human embryonic epiblast and is necessary for somatic differentiation from naïve hPSCs. We found that capacitated hPSCs are transcriptionally closer to postimplantation epiblast than conventional hPSCs. This prompted us to comprehensively study epigenetic and related transcriptional changes during capacitation. Our results show that CpG islands, gene regulatory elements, and retrotransposons are hotspots of epigenetic dynamics during capacitation and indicate possible distinct roles of specific epigenetic modifications in gene expression control between naïve and primed hPSCs. Unexpectedly, PRC2 activity appeared to be dispensable for the capacitation. We find that capacitated hPSCs acquire an epigenetic state similar to conventional hPSCs. Significantly, however, the X chromosome erosion frequently observed in conventional female hPSCs is reversed by resetting and subsequent capacitation.

An unsupervised deep learning framework for predicting human essential genes from population and functional genomic data

BACKGROUND

The ability to accurately predict essential genes intolerant to loss-of-function (LOF) mutations can dramatically improve the identification of disease-associated genes. Recently, there have been numerous computational methods developed to predict human essential genes from population genomic data. While the existing methods are highly predictive of essential genes of long length, they have limited power in pinpointing short essential genes due to the sparsity of polymorphisms in the human genome.

RESULTS

Motivated by the premise that population and functional genomic data may provide complementary evidence for gene essentiality, here we present an evolution-based deep learning model, DeepLOF, to predict essential genes in an unsupervised manner. Unlike previous population genetic methods, DeepLOF utilizes a novel deep learning framework to integrate both population and functional genomic data, allowing us to pinpoint short essential genes that can hardly be predicted from population genomic data alone. Compared with previous methods, DeepLOF shows unmatched performance in predicting ClinGen haploinsufficient genes, mouse essential genes, and essential genes in human cell lines. Notably, at a false positive rate of 5%, DeepLOF detects 50% more ClinGen haploinsufficient genes than previous methods. Furthermore, DeepLOF discovers 109 novel essential genes that are too short to be identified by previous methods.

CONCLUSION

The predictive power of DeepLOF shows that it is a compelling computational method to aid in the discovery of essential genes.

Bayesian estimation of gene constraint from an evolutionary model with gene features

Measures of selective constraint on genes have been used for many applications including clinical interpretation of rare coding variants, disease gene discovery, and studies of genome evolution. However, widely-used metrics are severely underpowered at detecting constraint for the shortest ~25% of genes, potentially causing important pathogenic mutations to be overlooked. We developed a framework combining a population genetics model with machine learning on gene features to enable accurate inference of an interpretable constraint metric, s het . Our estimates outperform existing metrics for prioritizing genes important for cell essentiality, human disease, and other phenotypes, especially for short genes. Our new estimates of selective constraint should have wide utility for characterizing genes relevant to human disease. Finally, our inference framework, GeneBayes, provides a flexible platform that can improve estimation of many gene-level properties, such as rare variant burden or gene expression differences.

DNMT3B overexpression downregulates genes with CpG islands, common motifs, and transcription factor binding sites that interact with DNMT3B

DNA methylation is a key epigenetic modification to regulate gene expression in mammalian cells. Abnormal DNA methylation in gene promoters is common across human cancer types. DNMT3B is the main de novo methyltransferase enhanced in several primary tumors. How de novo methylation is established in genes related to cancer is poorly understood. CpG islands (CGIs), common sequences, and transcription factors (TFs) that interact with DNMT3B have been associated with abnormal de novo methylation. We initially identified cis elements associated with DNA methylation to investigate the contribution of DNMT3B overexpression to the deregulation of its possible target genes in an epithelial cell model. In a set of downregulated genes (n = 146) from HaCaT cells with DNMT3B overexpression, we found CGI, common sequences, and TFs Binding Sites that interact with DNMT3B (we called them P-down-3B). PPL1, VAV3, IRF1, and BRAF are P-down-3B genes that are downregulated and increased their methylation in DNMT3B presence. Together these findings suggest that methylated promoters aberrantly have some cis elements that could conduce de novo methylation by DNMT3B.

Systematic analysis and prediction of genes associated with monogenic disorders on human chromosome X

Disease gene discovery on chromosome (chr) X is challenging owing to its unique modes of inheritance. We undertook a systematic analysis of human chrX genes. We observe a higher proportion of disorder-associated genes and an enrichment of genes involved in cognition, language, and seizures on chrX compared to autosomes. We analyze gene constraints, exon and promoter conservation, expression, and paralogues, and report 127 genes sharing one or more attributes with known chrX disorder genes. Using machine learning classifiers trained to distinguish disease-associated from dispensable genes, we classify 247 genes, including 115 of the 127, as having high probability of being disease-associated. We provide evidence of an excess of variants in predicted genes in existing databases. Finally, we report damaging variants in CDK16 and TRPC5 in patients with intellectual disability or autism spectrum disorders. This study predicts large-scale gene-disease associations that could be used for prioritization of X-linked pathogenic variants.

Prioritizing non-coding regions based on human genomic constraint and sequence context with deep learning

Elucidating functionality in non-coding regions is a key challenge in human genomics. It has been shown that intolerance to variation of coding and proximal non-coding sequence is a strong predictor of human disease relevance. Here, we integrate intolerance to variation, functional genomic annotations and primary genomic sequence to build JARVIS: a comprehensive deep learning model to prioritize non-coding regions, outperforming other human lineage-specific scores. Despite being agnostic to evolutionary conservation, JARVIS performs comparably or outperforms conservation-based scores in classifying pathogenic single-nucleotide and structural variants. In constructing JARVIS, we introduce the genome-wide residual variation intolerance score (gwRVIS), applying a sliding-window approach to whole genome sequencing data from 62,784 individuals. gwRVIS distinguishes Mendelian disease genes from more tolerant CCDS regions and highlights ultra-conserved non-coding elements as the most intolerant regions in the human genome. Both JARVIS and gwRVIS capture previously inaccessible human-lineage constraint information and will enhance our understanding of the non-coding genome.

Intolerance to variation is a strong indicator of disease relevance for coding regions of the human genome. Here, the authors present JARVIS, a deep learning method integrating intolerance to variation in non-coding regions and sequence-specific annotations to infer non-coding variant pathogenicity.