Disease category-specific annotation of variants using an ensemble learning framework

Genome-wide classification of epigenetic activity reveals regions of enriched heritability in immune-related traits

Epigenetics underpins the regulation of genes known to play a key role in the adaptive and innate immune system (AIIS). We developed a method, EpiNN, that leverages epigenetic data to detect AIIS-relevant genomic regions and used it to detect 2,765 putative AIIS loci. Experimental validation of one of these loci, DNMT1, provided evidence for a novel AIIS-specific transcription start site. We built a genome-wide AIIS annotation and used linkage disequilibrium (LD) score regression to test whether it predicts regional heritability using association statistics for 176 traits. We detected significant heritability effects (average |τ∗|=1.65) for 20 out of 26 immune-relevant traits. In a meta-analysis, immune-relevant traits and diseases were 4.45× more enriched for heritability than other traits. The EpiNN annotation was also depleted of trans-ancestry genetic correlation, indicating ancestry-specific effects. These results underscore the effectiveness of leveraging supervised learning algorithms and epigenetic data to detect loci implicated in specific classes of traits and diseases.

HNRNPC haploinsufficiency affects alternative splicing of intellectual disability-associated genes and causes a neurodevelopmental disorder

Heterogeneous nuclear ribonucleoprotein C (HNRNPC) is an essential, ubiquitously abundant protein involved in mRNA processing. Genetic variants in other members of the HNRNP family have been associated with neurodevelopmental disorders. Here, we describe 13 individuals with global developmental delay, intellectual disability, behavioral abnormalities, and subtle facial dysmorphology with heterozygous HNRNPC germline variants. Five of them bear an identical in-frame deletion of nine amino acids in the extreme C terminus. To study the effect of this recurrent variant as well as HNRNPC haploinsufficiency, we used induced pluripotent stem cells (iPSCs) and fibroblasts obtained from affected individuals. While protein localization and oligomerization were unaffected by the recurrent C-terminal deletion variant, total HNRNPC levels were decreased. Previously, reduced HNRNPC levels have been associated with changes in alternative splicing. Therefore, we performed a meta-analysis on published RNA-seq datasets of three different cell lines to identify a ubiquitous HNRNPC-dependent signature of alternative spliced exons. The identified signature was not only confirmed in fibroblasts obtained from an affected individual but also showed a significant enrichment for genes associated with intellectual disability. Hence, we assessed the effect of decreased and increased levels of HNRNPC on neuronal arborization and neuronal migration and found that either condition affects neuronal function. Taken together, our data indicate that HNRNPC haploinsufficiency affects alternative splicing of multiple intellectual disability-associated genes and that the developing brain is sensitive to aberrant levels of HNRNPC. Hence, our data strongly support the inclusion of HNRNPC to the family of HNRNP-related neurodevelopmental disorders.

Comprehensive 100-bp resolution genome-wide epigenomic profiling data for the hg38 human reference genome

This manuscript presents a comprehensive collection of diverse epigenomic profiling data for the human genome in 100-bp resolution with full genome-wide coverage. The datasets are processed from raw read count data collected from five types of sequencing-based assays collected by the Encyclopedia of DNA Elements consortium (ENCODE, http://www.encodeproject.org). Data from high-throughput sequencing assays were processed and crystallized into a total of 6,305 genome-wide profiles. To ensure the quality of the features, we filtered out assays with low read depth, inconsistent read counts, and poor data quality. The types of sequencing-based experiment assays include DNase-seq, histone and TF ChIP-seq, ATAC-seq, and Poly(A) RNA-seq. Merging of processed data was done by averaging read counts across technical replicates to obtain signals in about 30 million predefined 100-bp bins that tile the entire genome. We provide an example of fetching read counts using disease-related risk variants from the GWAS Catalog. Additionally, we have created a tabix index enabling fast user retrieval of read counts given coordinates in the human genome. The data processing pipeline is replicable for users' own purposes and for other experimental assays. The processed data can be found on Zenodo at https://zenodo.org/record/7015783. These data can be used as features for statistical and machine learning models to predict or infer a wide range of variables of biological interest. They can also be applied to generate novel insights into gene expression, chromatin accessibility, and epigenetic modifications across the human genome. Finally, the processing pipeline can be easily applied to data from any other genome-wide profiling assays, expanding the amount of available data.

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.

Quantum Chemical Calculations with Machine Learning for Multipolar Electrostatics Prediction in RNA: An Application to Pentose

To develop a realistic electrostatic model that allows for the anisotropy of the atomic electron density, high-rank atomic multipole moments computed by quantum chemical calculations have been studied extensively. However, it is hard to process huge RNA systems only relying on quantum chemical calculations due to its highly computational cost. In this study, we employ five machine learning methods of Gaussian process regression with automatic relevance determination (ARDGPR), Kriging, radial basis function neural networks, Bagging, and generalized regression neural network to predict atomic multipole moments. Atom-atom electrostatic interaction energies are subsequently computed using the predicted atomic multipole moments in the pilot system pentose of RNA. Here, the performance of the five methods is compared in terms of both the multipole moment prediction errors and the electrostatic energy prediction errors. For the predicted high-rank multipole moments of the four elements (O, C, N, and H) in capped pentose, ARDGPR and Kriging consistently outperform the other three methods. Therefore, the multipole moments predicted by the two best methods of ARDGPR and Kriging are then used to predict electrostatic interaction energy of each pentose. Finally, the absolute average energy errors of ARDGPR and Kriging are 1.83 and 4.33 kJ mol^-1, respectively. Compared to Kriging, the ARDGPR method achieves a 58% decrease in the absolute average energy error. These satisfactory results demonstrated that the ARDGPR method with the strong feature extraction ability can predict the electrostatic interaction energy of pentose in RNA correctly and reliably.

scEpiLock: A Weakly Supervised Learning Framework for cis-Regulatory Element Localization and Variant Impact Quantification for Single-Cell Epigenetic Data

Recent advances in single-cell transposase-accessible chromatin using a sequencing assay (scATAC-seq) allow cellular heterogeneity dissection and regulatory landscape reconstruction with an unprecedented resolution. However, compared to bulk-sequencing, its ultra-high missingness remarkably reduces usable reads in each cell type, resulting in broader, fuzzier peak boundary definitions and limiting our ability to pinpoint functional regions and interpret variant impacts precisely. We propose a weakly supervised learning method, scEpiLock, to directly identify core functional regions from coarse peak labels and quantify variant impacts in a cell-type-specific manner. First, scEpiLock uses a multi-label classifier to predict chromatin accessibility via a deep convolutional neural network. Then, its weakly supervised object detection module further refines the peak boundary definition using gradient-weighted class activation mapping (Grad-CAM). Finally, scEpiLock provides cell-type-specific variant impacts within a given peak region. We applied scEpiLock to various scATAC-seq datasets and found that it achieves an area under receiver operating characteristic curve (AUC) of ~0.9 and an area under precision recall (AUPR) above 0.7. Besides, scEpiLock's object detection condenses coarse peaks to only ⅓ of their original size while still reporting higher conservation scores. In addition, we applied scEpiLock on brain scATAC-seq data and reported several genome-wide association studies (GWAS) variants disrupting regulatory elements around known risk genes for Alzheimer's disease, demonstrating its potential to provide cell-type-specific biological insights in disease studies.