Using DIVAN to assess disease/trait-associated single nucleotide variants in genome-wide scale

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.

scaDA: A novel statistical method for differential analysis of single-cell chromatin accessibility sequencing data

Single-cell ATAC-seq sequencing data (scATAC-seq) has been widely used to investigate chromatin accessibility on the single-cell level. One important application of scATAC-seq data analysis is differential chromatin accessibility (DA) analysis. However, the data characteristics of scATAC-seq such as excessive zeros and large variability of chromatin accessibility across cells impose a unique challenge for DA analysis. Existing statistical methods focus on detecting the mean difference of the chromatin accessible regions while overlooking the distribution difference. Motivated by real data exploration that distribution difference exists among cell types, we introduce a novel composite statistical test named "scaDA", which is based on zero-inflated negative binomial model (ZINB), for performing differential distribution analysis of chromatin accessibility by jointly testing the abundance, prevalence and dispersion simultaneously. Benefiting from both dispersion shrinkage and iterative refinement of mean and prevalence parameter estimates, scaDA demonstrates its superiority to both ZINB-based likelihood ratio tests and published methods by achieving the highest power and best FDR control in a comprehensive simulation study. In addition to demonstrating the highest power in three real sc-multiome data analyses, scaDA successfully identifies differentially accessible regions in microglia from sc-multiome data for an Alzheimer's disease (AD) study that are most enriched in GO terms related to neurogenesis and the clinical phenotype of AD, and AD-associated GWAS SNPs.

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.

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.

scaDA: A Novel Statistical Method for Differential Analysis of Single-Cell Chromatin Accessibility Sequencing Data

Single-cell ATAC-seq sequencing data (scATAC-seq) has been widely used to investigate chromatin accessibility on the single-cell level. One important application of scATAC-seq data analysis is differential chromatin accessibility analysis. However, the data characteristics of scATAC-seq such as excessive zeros and large variability of chromatin accessibility across cells impose a unique challenge for DA analysis. Existing statistical methods focus on detecting the mean difference of the chromatin accessible regions while overlooking the distribution difference. Motivated by real data exploration that distribution difference exists among cell types, we introduce a novel composite statistical test named "scaDA", which is based on zero-inflated negative binomial model (ZINB), for performing differential distribution analysis of chromatin accessibility by jointly testing the abundance, prevalence and dispersion simultaneously. Benefiting from both dispersion shrinkage and iterative refinement of mean and prevalence parameter estimates, scaDA demonstrates its superiority to both ZINB-based likelihood ratio tests and published methods by achieving the highest power and best FDR control in a comprehensive simulation study. In addition to demonstrating the highest power in three real sc-multiome data analyses, scaDA successfully identifies differentially accessible regions in microglia from sc-multiome data for an Alzheimer's disease (AD) study, regions which are most enriched in GO terms related to neurogenesis, the clinical phenotype of AD, and SNPs identified in AD-associated GWAS.

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

MOTIVATION

Small insertion and deletion (sindel) of human genome has an important implication for human disease. One important mechanism for non-coding sindel (nc-sindel) to have an impact on human diseases and phenotypes is through the regulation of gene expression. Nevertheless, current sequencing experiments may lack statistical power and resolution to pinpoint the functional sindel due to lower minor allele frequency or small effect size. As an alternative strategy, a supervised machine learning method can identify the otherwise masked functional sindels by predicting their regulatory potential directly. However, computational methods for annotating and predicting the regulatory sindels, especially in the non-coding regions, are underdeveloped.

RESULTS

By leveraging labeled nc-sindels identified by cis-expression quantitative trait loci analyses across 44 tissues in Genotype-Tissue Expression (GTEx), and a compilation of both generic functional annotations and large-scale epigenomic profiles, we develop TIssue-specific Variant Annotation for Non-coding indel (TIVAN-indel), which is a supervised computational framework for predicting non-coding regulatory sindels. As a result, we demonstrate that TIVAN-indel achieves the best prediction performance in both with-tissue prediction and cross-tissue prediction. As an independent evaluation, we train TIVAN-indel from the 'Whole Blood' tissue in GTEx and test the model using 15 immune cell types from an independent study named Database of Immune Cell Expression. Lastly, we perform an enrichment analysis for both true and predicted sindels in key regulatory regions such as chromatin interactions, open chromatin regions and histone modification sites, and find biologically meaningful enrichment patterns.

AVAILABILITY AND IMPLEMENTATION

https://github.com/lichen-lab/TIVAN-indel.

SUPPLEMENTARY INFORMATION

Supplementary data are available at Bioinformatics online.

Updated review of advances in microRNAs and complex diseases: taxonomy, trends and challenges of computational models

Since the problem proposed in late 2000s, microRNA-disease association (MDA) predictions have been implemented based on the data fusion paradigm. Integrating diverse data sources gains a more comprehensive research perspective, and brings a challenge to algorithm design for generating accurate, concise and consistent representations of the fused data. After more than a decade of research progress, a relatively simple algorithm like the score function or a single computation layer may no longer be sufficient for further improving predictive performance. Advanced model design has become more frequent in recent years, particularly in the form of reasonably combing multiple algorithms, a process known as model fusion. In the current review, we present 29 state-of-the-art models and introduce the taxonomy of computational models for MDA prediction based on model fusion and non-fusion. The new taxonomy exhibits notable changes in the algorithmic architecture of models, compared with that of earlier ones in the 2017 review by Chen et al. Moreover, we discuss the progresses that have been made towards overcoming the obstacles to effective MDA prediction since 2017 and elaborated on how future models can be designed according to a set of new schemas. Lastly, we analysed the strengths and weaknesses of each model category in the proposed taxonomy and proposed future research directions from diverse perspectives for enhancing model performance.

Exploiting deep transfer learning for the prediction of functional non-coding variants using genomic sequence

MOTIVATION

Though genome-wide association studies have identified tens of thousands of variants associated with complex traits and most of them fall within the non-coding regions, they may not be the causal ones. The development of high-throughput functional assays leads to the discovery of experimental validated non-coding functional variants. However, these validated variants are rare due to technical difficulty and financial cost. The small sample size of validated variants makes it less reliable to develop a supervised machine learning model for achieving a whole genome-wide prediction of non-coding causal variants.

RESULTS

We will exploit a deep transfer learning model, which is based on convolutional neural network, to improve the prediction for functional non-coding variants (NCVs). To address the challenge of small sample size, the transfer learning model leverages both large-scale generic functional NCVs to improve the learning of low-level features and context-specific functional NCVs to learn high-level features toward the context-specific prediction task. By evaluating the deep transfer learning model on three MPRA datasets and 16 GWAS datasets, we demonstrate that the proposed model outperforms deep learning models without pretraining or retraining. In addition, the deep transfer learning model outperforms 18 existing computational methods in both MPRA and GWAS datasets.

AVAILABILITY AND IMPLEMENTATION

https://github.com/lichen-lab/TLVar.

SUPPLEMENTARY INFORMATION

Supplementary data are available at Bioinformatics online.

WEVar: a novel statistical learning framework for predicting noncoding regulatory variants

Understanding the functional consequence of noncoding variants is of great interest. Though genome-wide association studies or quantitative trait locus analyses have identified variants associated with traits or molecular phenotypes, most of them are located in the noncoding regions, making the identification of causal variants a particular challenge. Existing computational approaches developed for prioritizing noncoding variants produce inconsistent and even conflicting results. To address these challenges, we propose a novel statistical learning framework, which directly integrates the precomputed functional scores from representative scoring methods. It will maximize the usage of integrated methods by automatically learning the relative contribution of each method and produce an ensemble score as the final prediction. The framework consists of two modes. The first 'context-free' mode is trained using curated causal regulatory variants from a wide range of context and is applicable to predict regulatory variants of unknown and diverse context. The second 'context-dependent' mode further improves the prediction when the training and testing variants are from the same context. By evaluating the framework via both simulation and empirical studies, we demonstrate that it outperforms integrated scoring methods and the ensemble score successfully prioritizes experimentally validated regulatory variants in multiple risk loci.

Mapping of cis-acting expression quantitative trait loci in human scalp hair follicles

BACKGROUND

The association of molecular phenotypes, such as gene transcript levels, with human common genetic variation can help to improve our understanding of interindividual variability of tissue-specific gene regulation and its implications for disease.

METHODS

With the aim to capture the spectrum of biological processes affected by regulatory common genetic variants (minor allele frequency ≥ 1%) in healthy hair follicles (HFs) from scalp tissue, we performed a genome-wide mapping of cis-acting expression quantitative trait loci (eQTLs) in plucked HFs, and applied these eQTLs to help further explain genomic findings for hair-related traits.

RESULTS

We report 374 high-confidence eQTLs found in occipital scalp tissue, whose associated genes (eGenes) showed enrichments for metabolic, mitotic and immune processes, as well as responses to steroid hormones. We were able to replicate 68 of these associations in a smaller, independent dataset, in either frontal and/or occipital scalp tissue. Furthermore, we found three genomic regions overlapping reported genetic loci for hair shape and hair color. We found evidence to confirm the contributions of PADI3 to human variation in hair traits and suggest a novel potential candidate gene within known loci for androgenetic alopecia.

CONCLUSIONS

Our study shows that an array of basic cellular functions relevant for hair growth are genetically regulated within the HF, and can be applied to aid the interpretation of interindividual variability on hair traits, as well as genetic findings for common hair disorders.