TIVAN-indel: a computational framework for annotating and predicting non-coding regulatory small insertions and deletions

Understanding disease-associated metabolic changes in human colon epithelial cells using i ColonEpithelium metabolic reconstruction

The colon epithelium plays a key role in the host-microbiome interactions, allowing uptake of various nutrients and driving important metabolic processes. To unravel detailed metabolic activities in the human colon epithelium, our present study focuses on the generation of the first cell-type specific genome-scale metabolic model (GEM) of human colonic epithelial cells, named iColonEpithelium. GEMs are powerful tools for exploring reactions and metabolites at systems level and predicting the flux distributions at steady state. Our cell-type-specific iColonEpithelium metabolic reconstruction captures genes specifically expressed in the human colonic epithelial cells. The iColonEpithelium is also capable of performing metabolic tasks specific to the cell type. A unique transport reaction compartment has been included to allow simulation of metabolic interactions with the gut microbiome. We used iColonEpithelium to identify metabolic signatures associated with inflammatory bowel disease. We integrated single-cell RNA sequencing data from Crohn's Diseases (CD) and ulcerative colitis (UC) samples with the iColonEpithelium metabolic network to predict metabolic signatures of colonocytes between CD and UC compared to healthy samples. We identified reactions in nucleotide interconversion, fatty acid synthesis and tryptophan metabolism were differentially regulated in CD and UC conditions, which were in accordance with experimental results. The iColonEpithelium metabolic network can be used to identify mechanisms at the cellular level, and our network has the potential to be integrated with gut microbiome models to explore the metabolic interactions between host and gut microbiota under various conditions.

Deep5hmC: predicting genome-wide 5-hydroxymethylcytosine landscape via a multimodal deep learning model

MOTIVATION

5-Hydroxymethylcytosine (5hmC), a crucial epigenetic mark with a significant role in regulating tissue-specific gene expression, is essential for understanding the dynamic functions of the human genome. Despite its importance, predicting 5hmC modification across the genome remains a challenging task, especially when considering the complex interplay between DNA sequences and various epigenetic factors such as histone modifications and chromatin accessibility.

RESULTS

Using tissue-specific 5hmC sequencing data, we introduce Deep5hmC, a multimodal deep learning framework that integrates both the DNA sequence and epigenetic features such as histone modification and chromatin accessibility to predict genome-wide 5hmC modification. The multimodal design of Deep5hmC demonstrates remarkable improvement in predicting both qualitative and quantitative 5hmC modification compared to unimodal versions of Deep5hmC and state-of-the-art machine learning methods. This improvement is demonstrated through benchmarking on a comprehensive set of 5hmC sequencing data collected at four developmental stages during forebrain organoid development and across 17 human tissues. Compared to DeepSEA and random forest, Deep5hmC achieves close to 4% and 17% improvement of Area Under the Receiver Operating Characteristic (AUROC) across four forebrain developmental stages, and 6% and 27% across 17 human tissues for predicting binary 5hmC modification sites; and 8% and 22% improvement of Spearman correlation coefficient across four forebrain developmental stages, and 17% and 30% across 17 human tissues for predicting continuous 5hmC modification. Notably, Deep5hmC showcases its practical utility by accurately predicting gene expression and identifying differentially hydroxymethylated regions (DhMRs) in a case-control study of Alzheimer's disease (AD). Deep5hmC significantly improves our understanding of tissue-specific gene regulation and facilitates the development of new biomarkers for complex diseases.

AVAILABILITY AND IMPLEMENTATION

Deep5hmC is available via https://github.com/lichen-lab/Deep5hmC.

In silico generation and augmentation of regulatory variants from massively parallel reporter assay using conditional variational autoencoder

Predicting the functional consequences of genetic variants in non-coding regions is a challenging problem. Massively parallel reporter assays (MPRAs), which are an in vitro high-throughput method, can simultaneously test thousands of variants by evaluating the existence of allele specific regulatory activity. Nevertheless, the identified labelled variants by MPRAs, which shows differential allelic regulatory effects on the gene expression are usually limited to the scale of hundreds, limiting their potential to be used as the training set for achieving a robust genome-wide prediction. To address the limitation, we propose a deep generative model, MpraVAE, to in silico generate and augment the training sample size of labelled variants. By benchmarking on several MPRA datasets, we demonstrate that MpraVAE significantly improves the prediction performance for MPRA regulatory variants compared to the baseline method, conventional data augmentation approaches as well as existing variant scoring methods. Taking autoimmune diseases as one example, we apply MpraVAE to perform a genome-wide prediction of regulatory variants and find that predicted regulatory variants are more enriched than background variants in enhancers, active histone marks, open chromatin regions in immune-related cell types, and chromatin states associated with promoter, enhancer activity and binding sites of cMyC and Pol II that regulate gene expression. Importantly, predicted regulatory variants are found to link immune-related genes by leveraging chromatin loop and accessible chromatin, demonstrating the importance of MpraVAE in genetic and gene discovery for complex traits.

Regeneration-specific promoter switching facilitates Mest expression in the mouse digit tip to modulate neutrophil response

The mouse digit tip regenerates following amputation, a process mediated by a cellularly heterogeneous blastema. We previously found the gene Mest to be highly expressed in mesenchymal cells of the blastema and a strong candidate pro-regenerative gene. We now show Mest digit expression is regeneration-specific and not upregulated in post-amputation fibrosing proximal digits. Mest homozygous knockout mice exhibit delayed bone regeneration though no phenotype is found in paternal knockout mice, inconsistent with the defined maternal genomic imprinting of Mest. We demonstrate that promoter switching, not loss of imprinting, regulates biallelic Mest expression in the blastema and does not occur during embryogenesis, indicating a regeneration-specific mechanism. Requirement for Mest expression is tied to modulating neutrophil response, as revealed by scRNAseq and FACS comparing wildtype and knockout blastemas. Collectively, the imprinted gene Mest is required for proper digit tip regeneration and its blastema expression is facilitated by promoter switching for biallelic expression.

Deep5hmC: Predicting genome-wide 5-Hydroxymethylcytosine landscape via a multimodal deep learning model

5-hydroxymethylcytosine (5hmC), a critical epigenetic mark with a significant role in regulating tissue-specific gene expression, is essential for understanding the dynamic functions of the human genome. Using tissue-specific 5hmC sequencing data, we introduce Deep5hmC, a multimodal deep learning framework that integrates both the DNA sequence and the histone modification information to predict genome-wide 5hmC modification. The multimodal design of Deep5hmC demonstrates remarkable improvement in predicting both qualitative and quantitative 5hmC modification compared to unimodal versions of Deep5hmC and state-of-the-art machine learning methods. This improvement is demonstrated through benchmarking on a comprehensive set of 5hmC sequencing data collected at four time points during forebrain organoid development and across 17 human tissues. Notably, Deep5hmC showcases its practical utility by accurately predicting gene expression and identifying differentially hydroxymethylated regions in a case-control study of Alzheimer's disease.

Design and deep learning of synthetic B-cell-specific promoters

Synthetic biology and deep learning synergistically revolutionize our ability for decoding and recoding DNA regulatory grammar. The B-cell-specific transcriptional regulation is intricate, and unlock the potential of B-cell-specific promoters as synthetic elements is important for B-cell engineering. Here, we designed and pooled synthesized 23 640 B-cell-specific promoters that exhibit larger sequence space, B-cell-specific expression, and enable diverse transcriptional patterns in B-cells. By MPRA (Massively parallel reporter assays), we deciphered the sequence features that regulate promoter transcriptional, including motifs and motif syntax (their combination and distance). Finally, we built and trained a deep learning model capable of predicting the transcriptional strength of the immunoglobulin V gene promoter directly from sequence. Prediction of thousands of promoter variants identified in the global human population shows that polymorphisms in promoters influence the transcription of immunoglobulin V genes, which may contribute to individual differences in adaptive humoral immune responses. Our work helps to decipher the transcription mechanism in immunoglobulin genes and offers thousands of non-similar promoters for B-cell engineering.