Interpreting functional effects of coding variants: challenges in proteome-scale prediction, annotation and assessment

Prioritizing genomic variants through neuro-symbolic, knowledge-enhanced learning

MOTIVATION

Whole-exome and genome sequencing have become common tools in diagnosing patients with rare diseases. Despite their success, this approach leaves many patients undiagnosed. A common argument is that more disease variants still await discovery, or the novelty of disease phenotypes results from a combination of variants in multiple disease-related genes. Interpreting the phenotypic consequences of genomic variants relies on information about gene functions, gene expression, physiology, and other genomic features. Phenotype-based methods to identify variants involved in genetic diseases combine molecular features with prior knowledge about the phenotypic consequences of altering gene functions. While phenotype-based methods have been successfully applied to prioritizing variants, such methods are based on known gene-disease or gene-phenotype associations as training data and are applicable to genes that have phenotypes associated, thereby limiting their scope. In addition, phenotypes are not assigned uniformly by different clinicians, and phenotype-based methods need to account for this variability.

RESULTS

We developed an Embedding-based Phenotype Variant Predictor (EmbedPVP), a computational method to prioritize variants involved in genetic diseases by combining genomic information and clinical phenotypes. EmbedPVP leverages a large amount of background knowledge from human and model organisms about molecular mechanisms through which abnormal phenotypes may arise. Specifically, EmbedPVP incorporates phenotypes linked to genes, functions of gene products, and the anatomical site of gene expression, and systematically relates them to their phenotypic effects through neuro-symbolic, knowledge-enhanced machine learning. We demonstrate EmbedPVP's efficacy on a large set of synthetic genomes and genomes matched with clinical information.

AVAILABILITY AND IMPLEMENTATION

EmbedPVP and all evaluation experiments are freely available at https://github.com/bio-ontology-research-group/EmbedPVP.

Phenotypes associated with genetic determinants of type I interferon regulation in the UK Biobank: a protocol

Background

Type I interferons are cytokines involved in innate immunity against viruses. Genetic disorders of type I interferon regulation are associated with a range of autoimmune and cerebrovascular phenotypes. Carriers of pathogenic variants involved in genetic disorders of type I interferons are generally considered asymptomatic. Preliminary data suggests, however, that genetically determined dysregulation of type I interferon responses is associated with autoimmunity, and may also be relevant to sporadic cerebrovascular disease and dementia. We aim to determine whether functional variants in genes involved in type I interferon regulation and signalling are associated with the risk of autoimmunity, stroke, and dementia in a population cohort.

Methods

We will perform a hypothesis-driven candidate pathway association study of type I interferon-related genes using rare variants in the UK Biobank (UKB). We will manually curate type I interferon regulation and signalling genes from a literature review and Gene Ontology, followed by clinical and functional filtering. Variants of interest will be included based on pre-defined clinical relevance and functional annotations (using LOFTEE, M-CAP and a minor allele frequency <0.1%). The association of variants with 15 clinical and three neuroradiological phenotypes will be assessed with a rare variant genetic risk score and gene-level tests, using a Bonferroni-corrected p-value threshold from the number of genetic units and phenotypes tested. We will explore the association of significant genetic units with 196 additional health-related outcomes to help interpret their relevance and explore the clinical spectrum of genetic perturbations of type I interferon.

Ethics and dissemination

The UKB has received ethical approval from the North West Multicentre Research Ethics Committee, and all participants provided written informed consent at recruitment. This research will be conducted using the UKB Resource under application number 93160. We expect to disseminate our results in a peer-reviewed journal and at an international cardiovascular conference.

From function to translation: Decoding genetic susceptibility to human diseases via artificial intelligence

While genome-wide association studies (GWAS) have discovered thousands of disease-associated loci, molecular mechanisms for a considerable fraction of the loci remain to be explored. The logical next steps for post-GWAS are interpreting these genetic associations to understand disease etiology (GWAS functional studies) and translating this knowledge into clinical benefits for the patients (GWAS translational studies). Although various datasets and approaches using functional genomics have been developed to facilitate these studies, significant challenges remain due to data heterogeneity, multiplicity, and high dimensionality. To address these challenges, artificial intelligence (AI) technology has demonstrated considerable promise in decoding complex functional datasets and providing novel biological insights into GWAS findings. This perspective first describes the landmark progress driven by AI in interpreting and translating GWAS findings and then outlines specific challenges followed by actionable recommendations related to data availability, model optimization, and interpretation, as well as ethical concerns.

StarGazer: A Hybrid Intelligence Platform for Drug Target Prioritization and Digital Drug Repositioning Using Streamlit

Target prioritization is essential for drug discovery and repositioning. Applying computational methods to analyze and process multi-omics data to find new drug targets is a practical approach for achieving this. Despite an increasing number of methods for generating datasets such as genomics, phenomics, and proteomics, attempts to integrate and mine such datasets remain limited in scope. Developing hybrid intelligence solutions that combine human intelligence in the scientific domain and disease biology with the ability to mine multiple databases simultaneously may help augment drug target discovery and identify novel drug-indication associations. We believe that integrating different data sources using a singular numerical scoring system in a hybrid intelligent framework could help to bridge these different omics layers and facilitate rapid drug target prioritization for studies in drug discovery, development or repositioning. Herein, we describe our prototype of the StarGazer pipeline which combines multi-source, multi-omics data with a novel target prioritization scoring system in an interactive Python-based Streamlit dashboard. StarGazer displays target prioritization scores for genes associated with 1844 phenotypic traits, and is available via https://github.com/AstraZeneca/StarGazer.

miRMut: Annotation of mutations in miRNA genes from human whole-exome or whole-genome sequencing

Here, we present the miRMut protocol to annotate mutations found in miRNA genes based on whole-exome sequencing (WES) or whole-genome sequencing (WGS) results. The pipeline assigns mutation characteristics, including miRNA gene IDs (miRBase and MirGeneDB), mutation localization within the miRNA precursor structure, potential RNA-binding motif disruption, the ascription of mutation according to Human Genome Variation Society (HGVS) nomenclature, and miRNA gene characteristics, such as miRNA gene confidence and miRNA arm balance. The pipeline includes creating tabular and graphical summaries. For complete details on the use and execution of this protocol, please refer to Urbanek-Trzeciak et al. (2020).

A method for scoring the cell type-specific impacts of noncoding variants in personal genomes

Here we use the expression and accessibility data from a diverse set of cell types to learn a model for the dependence of the accessibility of a regulatory element on its DNA sequence and TF expression. Using GTEx samples with WGS data, we show that the noncoding variants predicted to affect accessibility are more strongly associated with the expression of nearby genes. To interpret a personal genome, we combine the sequence information with context-specific TF expression to prioritize variants and regulatory elements in any genomic region of interest. This approach should be helpful in the study of risk loci previously identified by GWAS. Results from analysis of height and WGS data from the GTEx project support this hypothesis.

A person’s genome typically contains millions of variants which represent the differences between this personal genome and the reference human genome. The interpretation of these variants, i.e., the assessment of their potential impact on a person’s phenotype, is currently of great interest in human genetics and medicine. We have developed a prioritization tool called OpenCausal which takes as inputs 1) a personal genome and 2) a reference context-specific TF expression profile and returns a list of noncoding variants prioritized according to their impact on chromatin accessibility for any given genomic region of interest. We applied OpenCausal to 6,430 samples across 18 tissues derived from the GTEx project and found that the variants prioritized by OpenCausal are highly enriched for eQTLs and caQTLs. We further propose a strategy to integrate the predicted open scores with genome-wide association studies (GWAS) data to prioritize putative causal variants and regulatory elements for a given risk locus (i.e., fine-mapping analysis). As an initial example, we applied this method to a GWAS dataset of human height and found that the prioritized putative variants and elements are correlated with the phenotype (i.e., heights of individuals) better than others.

parSMURF, a high-performance computing tool for the genome-wide detection of pathogenic variants

BACKGROUND

Several prediction problems in computational biology and genomic medicine are characterized by both big data as well as a high imbalance between examples to be learned, whereby positive examples can represent a tiny minority with respect to negative examples. For instance, deleterious or pathogenic variants are overwhelmed by the sea of neutral variants in the non-coding regions of the genome: thus, the prediction of deleterious variants is a challenging, highly imbalanced classification problem, and classical prediction tools fail to detect the rare pathogenic examples among the huge amount of neutral variants or undergo severe restrictions in managing big genomic data.

RESULTS

To overcome these limitations we propose parSMURF, a method that adopts a hyper-ensemble approach and oversampling and undersampling techniques to deal with imbalanced data, and parallel computational techniques to both manage big genomic data and substantially speed up the computation. The synergy between Bayesian optimization techniques and the parallel nature of parSMURF enables efficient and user-friendly automatic tuning of the hyper-parameters of the algorithm, and allows specific learning problems in genomic medicine to be easily fit. Moreover, by using MPI parallel and machine learning ensemble techniques, parSMURF can manage big data by partitioning them across the nodes of a high-performance computing cluster. Results with synthetic data and with single-nucleotide variants associated with Mendelian diseases and with genome-wide association study hits in the non-coding regions of the human genome, involhing millions of examples, show that parSMURF achieves state-of-the-art results and an 80-fold speed-up with respect to the sequential version.

CONCLUSIONS

parSMURF is a parallel machine learning tool that can be trained to learn different genomic problems, and its multiple levels of parallelization and high scalability allow us to efficiently fit problems characterized by big and imbalanced genomic data. The C++ OpenMP multi-core version tailored to a single workstation and the C++ MPI/OpenMP hybrid multi-core and multi-node parSMURF version tailored to a High Performance Computing cluster are both available at https://github.com/AnacletoLAB/parSMURF.

Genetic variants in the LPL and GPIHBP1 genes, in patients with severe hypertriglyceridaemia, detected with high resolution melting analysis

INTRODUCTION

Pathogenic variants in lipoprotein lipase (LPL) and glycosylphosphatidylinositol-anchored high-density lipoprotein-binding protein 1 (GPIHBP1) have been described in patients with severe hypertriglyceridaemia. We aimed to optimise high resolution melting (HRM) assays to detect the presence of functional variants in these genes.

METHODS

One hundred and sixteen patients with severe hypertriglyceridaemia were studied. HRM assays were optimised to scan exons and splice junctions in LPL and GPIHBP1. Sanger sequencing was the reference method. Next-generation-sequencing (NGS) was performed in five patients, including one with Familial Chylomicronemia syndrome (FCS).

RESULTS

We identified 15 different variants in LPL and 6 in GPIHBP1. The variants revealed with NGS were also detected with HRM, including a rare premature stop codon in LPL (p.Trp421*) and two LPL pathogenic variants in the patient with FCS (p.His80Arg + p.Gly215Glu). Having multiple functional variant alleles was associated with pancreatitis onset at younger ages and higher baseline triglycerides.

CONCLUSIONS

Our HRM assays detected the presence of functional gene variants that were confirmed with Sanger and NGS sequencing. The presence of multiple functional variant alleles was associated with differences in the clinical profile. Therefore, these assays represent a reliable, cost-effective tool that can be used to complement the NGS approach for gene scanning.

VCF.Filter: interactive prioritization of disease-linked genetic variants from sequencing data

Next generation sequencing is widely used to link genetic variants to diseases, and it has massively accelerated the diagnosis and characterization of rare genetic diseases. After initial bioinformatic data processing, the interactive analysis of genome, exome, and panel sequencing data typically starts from lists of genetic variants in VCF format. Medical geneticists filter and annotate these lists to identify variants that may be relevant for the disease under investigation, or to select variants that are reported in a clinical diagnostics setting. We developed VCF.Filter to facilitate the search for disease-linked variants, providing a standalone Java program with a user-friendly interface for interactive variant filtering and annotation. VCF.Filter allows the user to define a broad range of filtering criteria through a graphical interface. Common workflows such as trio analysis and cohort-based filtering are pre-configured, and more complex analyses can be performed using VCF.Filter's support for custom annotations and filtering criteria. All filtering is documented in the results file, thus providing traceability of the interactive variant prioritization. VCF.Filter is an open source tool that is freely and openly available at http://vcffilter.rarediseases.at.

Biocuration: Distilling data into knowledge

Data, including information generated from them by processing and analysis, are an asset with measurable value. The assets that biological research funding produces are the data generated, the information derived from these data, and, ultimately, the discoveries and knowledge these lead to. From the time when Henry Oldenburg published the first scientific journal in 1665 (Proceedings of the Royal Society) to the founding of the United States National Library of Medicine in 1879 to the present, there has been a sustained drive to improve how researchers can record and discover what is known. Researchers’ experimental work builds upon years and (collectively) billions of dollars’ worth of earlier work. Today, researchers are generating data at ever-faster rates because of advances in instrumentation and technology, coupled with decreases in production costs. Unfortunately, the ability of researchers to manage and disseminate their results has not kept pace, so their work cannot achieve its maximal impact. Strides have recently been made, but more awareness is needed of the essential role that biological data resources, including biocuration, play in maintaining and linking this ever-growing flood of data and information. The aim of this paper is to describe the nature of data as an asset, the role biocurators play in increasing its value, and consistent, practical means to measure effectiveness that can guide planning and justify costs in biological research information resources’ development and management.

Machine learning in cardiovascular medicine: are we there yet?

Artificial intelligence (AI) broadly refers to analytical algorithms that iteratively learn from data, allowing computers to find hidden insights without being explicitly programmed where to look. These include a family of operations encompassing several terms like machine learning, cognitive learning, deep learning and reinforcement learning-based methods that can be used to integrate and interpret complex biomedical and healthcare data in scenarios where traditional statistical methods may not be able to perform. In this review article, we discuss the basics of machine learning algorithms and what potential data sources exist; evaluate the need for machine learning; and examine the potential limitations and challenges of implementing machine in the context of cardiovascular medicine. The most promising avenues for AI in medicine are the development of automated risk prediction algorithms which can be used to guide clinical care; use of unsupervised learning techniques to more precisely phenotype complex disease; and the implementation of reinforcement learning algorithms to intelligently augment healthcare providers. The utility of a machine learning-based predictive model will depend on factors including data heterogeneity, data depth, data breadth, nature of modelling task, choice of machine learning and feature selection algorithms, and orthogonal evidence. A critical understanding of the strength and limitations of various methods and tasks amenable to machine learning is vital. By leveraging the growing corpus of big data in medicine, we detail pathways by which machine learning may facilitate optimal development of patient-specific models for improving diagnoses, intervention and outcome in cardiovascular medicine.

Accurately annotate compound effects of genetic variants using a context-sensitive framework

In genomics, effectively identifying the biological effects of genetic variants is crucial. Current methods handle each variant independently, assuming that each variant acts in a context-free manner. However, variants within the same gene may interfere with each other, producing combinational (compound) rather than individual effects. In this work, we introduce COPE, a gene-centric variant annotation tool that integrates the entire sequential context in evaluating the functional effects of intra-genic variants. Applying COPE to the 1000 Genomes dataset, we identified numerous cases of multiple-variant compound effects that frequently led to false-positive and false-negative loss-of-function calls by conventional variant-centric tools. Specifically, 64 disease-causing mutations were identified to be rescued in a specific genomic context, thus potentially contributing to the buffering effects for highly penetrant deleterious mutations. COPE is freely available for academic use at http://cope.cbi.pku.edu.cn.

Intrinsically disordered proteins in overcrowded milieu: Membrane-less organelles, phase separation, and intrinsic disorder

Although the cellular interior is crowded with various biological macromolecules, the distribution of these macromolecules is highly inhomogeneous. Eukaryotic cells contain numerous proteinaceous membrane-less organelles (PMLOs), which are condensed liquid droplets formed as a result of the reversible and highly controlled liquid-liquid phase transitions. The interior of these cellular bodies represents an overcrowded milieu, since their protein concentrations are noticeably higher than those of the crowded cytoplasm and nucleoplasm. PMLOs are different in size, shape, and composition, and almost invariantly contain intrinsically disordered proteins (e.g., eIF4B and TDP43 in stress granules, TTP in P-bodies, RDE-12 in nuage, RNG105 in RNA granules, centrins in centrosomes, NOPP140 in nucleoli, SRSF4 in nuclear speckles, Saf-B in nuclear stress bodies, NOLC1 in Cajal bodies, CBP in PML nuclear bodies, SOX9 in paraspeckles, KSRP in perinucleolar compartment, and hnRNPG and Sam68 in Sam68 nuclear body, to name a few), which indicates that the formation of these phase-separated droplets is crucially dependent on intrinsic disorder. The goal of this review is to show the roles of intrinsic disorder in the magic behind biological liquid-liquid phase transitions that lead to the formation of PMLOs.