SVFX: a machine learning framework to quantify the pathogenicity of structural variants

Comprehensive and deep evaluation of structural variation detection pipelines with third-generation sequencing data

BACKGROUND

Structural variation (SV) detection methods using third-generation sequencing data are widely employed, yet accurately detecting SVs remains challenging. Different methods often yield inconsistent results for certain SV types, complicating tool selection and revealing biases in detection.

RESULTS

This study comprehensively evaluates 53 SV detection pipelines using simulated and real data from PacBio (CLR: Continuous Long Read, CCS: Circular Consensus Sequencing) and Nanopore (ONT) platforms. We assess their performance in detecting various sizes and types of SVs, breakpoint biases, and genotyping accuracy with various sequencing depths. Notably, pipelines such as Minimap2-cuteSV2, NGMLR-SVIM, PBMM2-pbsv, Winnowmap-Sniffles2, and Winnowmap-SVision exhibit comparatively higher recall and precision. Our findings also show that combining multiple pipelines with the same aligner, like pbmm2 or winnowmap, can significantly enhance performance. The individual pipelines' detailed ranking and performance metrics can be viewed in a dynamic table: http://pmglab.top/SVPipelinesRanking .

CONCLUSIONS

This study comprehensively characterizes the strengths and weaknesses of numerous pipelines, providing valuable insights that can improve SV detection in third-generation sequencing data and inform SV annotation and function prediction.

Comparison of germline and somatic structural variants in cancers reveal systematic differences in variant generating and selection processes

Although several recent studies have characterized structural variants (SVs) in germline and cancer genomes, the features of SVs in these different contexts have not been directly compared. We examined similarities and differences between 2 million germline and 115 thousand tumor SVs from a cohort of 963 patients from The Cancer Genome Atlas (TCGA). We found significant differences in features related to their genomic sequences and localization that suggest differences between SV-generating processes and selective pressures. For example, we found that transposon-mediated processes shape germline much more than somatic SVs, while somatic SVs more frequently show features characteristic of chromoanagenesis. These differences were extensive enough to enable us to develop a classifier - "the great GaTSV" - that accurately distinguishes between germline and cancer SVs in tumor samples that lack a matched normal sample.

PhenoSV: interpretable phenotype-aware model for the prioritization of genes affected by structural variants

Structural variants (SVs) represent a major source of genetic variation associated with phenotypic diversity and disease susceptibility. While long-read sequencing can discover over 20,000 SVs per human genome, interpreting their functional consequences remains challenging. Existing methods for identifying disease-related SVs focus on deletion/duplication only and cannot prioritize individual genes affected by SVs, especially for noncoding SVs. Here, we introduce PhenoSV, a phenotype-aware machine-learning model that interprets all major types of SVs and genes affected. PhenoSV segments and annotates SVs with diverse genomic features and employs a transformer-based architecture to predict their impacts under a multiple-instance learning framework. With phenotype information, PhenoSV further utilizes gene-phenotype associations to prioritize phenotype-related SVs. Evaluation on extensive human SV datasets covering all SV types demonstrates PhenoSV's superior performance over competing methods. Applications in diseases suggest that PhenoSV can determine disease-related genes from SVs. A web server and a command-line tool for PhenoSV are available at https://phenosv.wglab.org .

A review of genetic variant databases and machine learning tools for predicting the pathogenicity of breast cancer

Studies continue to uncover contributing risk factors for breast cancer (BC) development including genetic variants. Advances in machine learning and big data generated from genetic sequencing can now be used for predicting BC pathogenicity. However, it is unclear which tool developed for pathogenicity prediction is most suited for predicting the impact and pathogenicity of variant effects. A significant challenge is to determine the most suitable data source for each tool since different tools can yield different prediction results with different data inputs. To this end, this work reviews genetic variant databases and tools used specifically for the prediction of BC pathogenicity. We provide a description of existing genetic variants databases and, where appropriate, the diseases for which they have been established. Through example, we illustrate how they can be used for prediction of BC pathogenicity and discuss their associated advantages and disadvantages. We conclude that the tools that are specialized by training on multiple diverse datasets from different databases for the same disease have enhanced accuracy and specificity and are thereby more helpful to the clinicians in predicting and diagnosing BC as early as possible.

NeuroCNVscore: a tissue-specific framework to prioritise the pathogenicity of CNVs in neurodevelopmental disorders

BACKGROUND

Neurodevelopmental disorders (NDDs) are associated with altered development of the brain especially in childhood. Copy number variants (CNVs) play a crucial role in the genetic aetiology of NDDs by disturbing gene expression directly at linear sequence or remotely at three-dimensional genome level in a tissue-specific manner. Despite the substantial increase in NDD studies employing whole-genome sequencing, there is no specific tool for prioritising the pathogenicity of CNVs in the context of NDDs.

METHODS

Using an XGBoost classifier, we integrated 189 features that represent genomic sequences, gene information and functional/genomic segments for evaluating genome-wide CNVs in a neuro/brain-specific manner, to develop a new tool, neuroCNVscore. We used Human Phenotype Ontology to construct an independent NDD-related set.

RESULTS

Our neuroCNVscore framework (https://github.com/lxsbch/neuroCNVscore) achieved high predictive performance (precision recall=0.82; area under curve=0.85) and outperformed an existing reference method SVScore. Notably, the predicted pathogenic CNVs showed enrichment in known genes associated with autism.

CONCLUSIONS

NeuroCNVscore prioritises functional, deleterious and pathogenic CNVs in NDDs at whole genome-wide level, which is important for genetic studies and clinical genomic screening of NDDs as well as for providing novel biological insights into NDDs.

Unified views on variant impact across many diseases

Genomic studies of human disorders are often performed by distinct research communities (i.e., focused on rare diseases, common diseases, or cancer). Despite underlying differences in the mechanistic origin of different disease categories, these studies share the goal of identifying causal genomic events that are critical for the clinical manifestation of the disease phenotype. Moreover, these studies face common challenges, including understanding the complex genetic architecture of the disease, deciphering the impact of variants on multiple scales, and interpreting noncoding mutations. Here, we highlight these challenges in depth and argue that properly addressing them will require a more unified vocabulary and approach across disease communities. Toward this goal, we present a unified perspective on relating variant impact to various genomic disorders.

In it for the long run: perspectives on exploiting long-read sequencing in livestock for population scale studies of structural variants

Studies have demonstrated that structural variants (SV) play a substantial role in the evolution of species and have an impact on Mendelian traits in the genome. However, unlike small variants (< 50 bp), it has been challenging to accurately identify and genotype SV at the population scale using short-read sequencing. Long-read sequencing technologies are becoming competitively priced and can address several of the disadvantages of short-read sequencing for the discovery and genotyping of SV. In livestock species, analysis of SV at the population scale still faces challenges due to the lack of resources, high costs, technological barriers, and computational limitations. In this review, we summarize recent progress in the characterization of SV in the major livestock species, the obstacles that still need to be overcome, as well as the future directions in this growing field. It seems timely that research communities pool resources to build global population-scale long-read sequencing consortiums for the major livestock species for which the application of genomic tools has become cost-effective.

Annotation of structural variants with reported allele frequencies and related metrics from multiple datasets using SVAFotate

BACKGROUND

Identification of deleterious genetic variants using DNA sequencing data relies on increasingly detailed filtering strategies to isolate the small subset of variants that are more likely to underlie a disease phenotype. Datasets reflecting population allele frequencies of different types of variants serve as powerful filtering tools, especially in the context of rare disease analysis. While such population-scale allele frequency datasets now exist for structural variants (SVs), it remains a challenge to match SV calls between multiple datasets, thereby complicating estimates of a putative SV's population allele frequency.

RESULTS

We introduce SVAFotate, a software tool that enables the annotation of SVs with variant allele frequency and related information from existing SV datasets. As a result, VCF files annotated by SVAFotate offer a variety of metrics to aid in the stratification of SVs as common or rare in the broader human population.

CONCLUSIONS

Here we demonstrate the use of SVAFotate in the classification of SVs with regards to their population frequency and illustrate how SVAFotate's annotations can be used to filter and prioritize SVs. Lastly, we detail how best to utilize these SV annotations in the analysis of genetic variation in studies of rare disease.

Scalable approaches for functional analyses of whole-genome sequencing non-coding variants

Non-coding genetic variants outside of protein-coding genome regions play an important role in genetic and epigenetic regulation. It has become increasingly important to understand their roles, as non-coding variants often make up the majority of top findings of genome-wide association studies (GWAS). In addition, the growing popularity of disease-specific whole-genome sequencing (WGS) efforts expands the library of and offers unique opportunities for investigating both common and rare non-coding variants, which are typically not detected in more limited GWAS approaches. However, the sheer size and breadth of WGS data introduce additional challenges to predicting functional impacts in terms of data analysis and interpretation. This review focuses on the recent approaches developed for efficient, at-scale annotation and prioritization of non-coding variants uncovered in WGS analyses. In particular, we review the latest scalable annotation tools, databases and functional genomic resources for interpreting the variant findings from WGS based on both experimental data and in silico predictive annotations. We also review machine learning-based predictive models for variant scoring and prioritization. We conclude with a discussion of future research directions which will enhance the data and tools necessary for the effective functional analyses of variants identified by WGS to improve our understanding of disease etiology.

Computational and experimental methods for classifying variants of unknown clinical significance

The increase in sequencing capacity, reduction in costs, and national and international coordinated efforts have led to the widespread introduction of next-generation sequencing (NGS) technologies in patient care. More generally, human genetics and genomic medicine are gaining importance for more and more patients. Some communities are already discussing the prospect of sequencing each individual's genome at time of birth. Together with digital health records, this shall enable individualized treatments and preventive measures, so-called precision medicine. A central step in this process is the identification of disease causal mutations or variant combinations that make us more susceptible for diseases. Although various technological advances have improved the identification of genetic alterations, the interpretation and ranking of the identified variants remains a major challenge. Based on our knowledge of molecular processes or previously identified disease variants, we can identify potentially functional genetic variants and, using different lines of evidence, we are sometimes able to demonstrate their pathogenicity directly. However, the vast majority of variants are classified as variants of uncertain clinical significance (VUSs) with not enough experimental evidence to determine their pathogenicity. In these cases, computational methods may be used to improve the prioritization and an increasing toolbox of experimental methods is emerging that can be used to assay the molecular effects of VUSs. Here, we discuss how computational and experimental methods can be used to create catalogs of variant effects for a variety of molecular and cellular phenotypes. We discuss the prospects of integrating large-scale functional data with machine learning and clinical knowledge for the development of accurate pathogenicity predictions for clinical applications.

TADA-a machine learning tool for functional annotation-based prioritisation of pathogenic CNVs

Few methods have been developed to investigate copy number variants (CNVs) based on their predicted pathogenicity. We introduce TADA, a method to prioritise pathogenic CNVs through assisted manual filtering and automated classification, based on an extensive catalogue of functional annotation supported by rigourous enrichment analysis. We demonstrate that our classifiers are able to accurately predict pathogenic CNVs, outperforming current alternative methods, and produce a well-calibrated pathogenicity score. Our results suggest that functional annotation-based prioritisation of pathogenic CNVs is a promising approach to support clinical diagnostics and to further the understanding of mechanisms controlling the disease impact of larger genomic alterations.

A framework to score the effects of structural variants in health and disease

While technological advances improved the identification of structural variants (SVs) in the human genome, their interpretation remains challenging. Several methods utilize individual mechanistic principles like the deletion of coding sequence or 3D genome architecture disruptions. However, a comprehensive tool using the broad spectrum of available annotations is missing. Here, we describe CADD-SV, a method to retrieve and integrate a wide set of annotations to predict the effects of SVs. Previously, supervised learning approaches were limited due to a small number and biased set of annotated pathogenic or benign SVs. We overcome this problem by using a surrogate training-objective, the Combined Annotation Dependent Depletion (CADD) of functional variants. We use human and chimpanzee derived SVs as proxy-neutral and contrast them with matched simulated variants as proxy-deleterious, an approach that has proven powerful for short sequence variants. Our tool computes summary statistics over diverse variant annotations and uses random forest models to prioritize deleterious structural variants. The resulting CADD-SV scores correlate with known pathogenic and rare population variants. We further show that we can prioritize somatic cancer variants as well as noncoding variants known to affect gene expression. We provide a website and offline-scoring tool for easy application of CADD-SV.

GCAT|Panel, a comprehensive structural variant haplotype map of the Iberian population from high-coverage whole-genome sequencing

The combined analysis of haplotype panels with phenotype clinical cohorts is a common approach to explore the genetic architecture of human diseases. However, genetic studies are mainly based on single nucleotide variants (SNVs) and small insertions and deletions (indels). Here, we contribute to fill this gap by generating a dense haplotype map focused on the identification, characterization, and phasing of structural variants (SVs). By integrating multiple variant identification methods and Logistic Regression Models (LRMs), we present a catalogue of 35 431 441 variants, including 89 178 SVs (≥50 bp), 30 325 064 SNVs and 5 017 199 indels, across 785 Illumina high coverage (30x) whole-genomes from the Iberian GCAT Cohort, containing a median of 3.52M SNVs, 606 336 indels and 6393 SVs per individual. The haplotype panel is able to impute up to 14 360 728 SNVs/indels and 23 179 SVs, showing a 2.7-fold increase for SVs compared with available genetic variation panels. The value of this panel for SVs analysis is shown through an imputed rare Alu element located in a new locus associated with Mononeuritis of lower limb, a rare neuromuscular disease. This study represents the first deep characterization of genetic variation within the Iberian population and the first operational haplotype panel to systematically include the SVs into genome-wide genetic studies.

SVPath: an accurate pipeline for predicting the pathogenicity of human exon structural variants

Although there are a large number of structural variations in the chromosomes of each individual, there is a lack of more accurate methods for identifying clinical pathogenic variants. Here, we proposed SVPath, a machine learning-based method to predict the pathogenicity of deletions, insertions and duplications structural variations that occur in exons. We constructed three types of annotation features for each structural variation event in the ClinVar database. First, we treated complex structural variations as multiple consecutive single nucleotide polymorphisms events, and annotated them with correlation scores based on single nucleic acid substitutions, such as the impact on protein function. Second, we determined which genes the variation occurred in, and constructed gene-based annotation features for each structural variation. Third, we also calculated related features based on the transcriptome, such as histone signal, the overlap ratio of variation and genomic element definitions, etc. Finally, we employed a gradient boosting decision tree machine learning method, and used the deletions, insertions and duplications in the ClinVar database to train a structural variation pathogenicity prediction model SVPath. These structural variations are clearly indicated as pathogenic or benign. Experimental results show that our SVPath has achieved excellent predictive performance and outperforms existing state-of-the-art tools. SVPath is very promising in evaluating the clinical pathogenicity of structural variants. SVPath can be used in clinical research to predict the clinical significance of unknown pathogenicity and new structural variation, so as to explore the relationship between diseases and structural variations in a computational way.

StrVCTVRE: A supervised learning method to predict the pathogenicity of human genome structural variants

Whole-genome sequencing resolves many clinical cases where standard diagnostic methods have failed. However, at least half of these cases remain unresolved after whole-genome sequencing. Structural variants (SVs; genomic variants larger than 50 base pairs) of uncertain significance are the genetic cause of a portion of these unresolved cases. As sequencing methods using long or linked reads become more accessible and SV detection algorithms improve, clinicians and researchers are gaining access to thousands of reliable SVs of unknown disease relevance. Methods to predict the pathogenicity of these SVs are required to realize the full diagnostic potential of long-read sequencing. To address this emerging need, we developed StrVCTVRE to distinguish pathogenic SVs from benign SVs that overlap exons. In a random forest classifier, we integrated features that capture gene importance, coding region, conservation, expression, and exon structure. We found that features such as expression and conservation are important but are absent from SV classification guidelines. We leveraged multiple resources to construct a size-matched training set of rare, putatively benign and pathogenic SVs. StrVCTVRE performs accurately across a wide SV size range on independent test sets, which will allow clinicians and researchers to eliminate about half of SVs from consideration while retaining a 90% sensitivity. We anticipate clinicians and researchers will use StrVCTVRE to prioritize SVs in probands where no SV is immediately compelling, empowering deeper investigation into novel SVs to resolve cases and understand new mechanisms of disease. StrVCTVRE runs rapidly and is publicly available.

Automated prediction of the clinical impact of structural copy number variations

Copy number variants (CNVs) play an important role in many biological processes, including the development of genetic diseases, making them attractive targets for genetic analyses. The interpretation of the effect of these structural variants is a challenging problem due to highly variable numbers of gene, regulatory, or other genomic elements affected by the CNV. This led to the demand for the interpretation tools that would relieve researchers, laboratory diagnosticians, genetic counselors, and clinical geneticists from the laborious process of annotation and classification of CNVs. We designed and validated a prediction method (ISV; Interpretation of Structural Variants) that is based on boosted trees which takes into account annotations of CNVs from several publicly available databases. The presented approach achieved more than 98% prediction accuracy on both copy number loss and copy number gain variants while also allowing CNVs being assigned "uncertain" significance in predictions. We believe that ISV's prediction capability and explainability have a great potential to guide users to more precise interpretations and classifications of CNVs.

SVInterpreter: A Comprehensive Topologically Associated Domain-Based Clinical Outcome Prediction Tool for Balanced and Unbalanced Structural Variants

With the advent of genomic sequencing, a number of balanced and unbalanced structural variants (SVs) can be detected per individual. Mainly due to incompleteness and the scattered nature of the available annotation data of the human genome, manual interpretation of the SV's clinical significance is laborious and cumbersome. Since bioinformatic tools developed for this task are limited, a comprehensive tool to assist clinical outcome prediction of SVs is warranted. Herein, we present SVInterpreter, a free Web application, which analyzes both balanced and unbalanced SVs using topologically associated domains (TADs) as genome units. Among others, gene-associated data (as function and dosage sensitivity), phenotype similarity scores, and copy number variants (CNVs) scoring metrics are retrieved for an informed SV interpretation. For evaluation, we retrospectively applied SVInterpreter to 97 balanced (translocations and inversions) and 125 unbalanced (deletions, duplications, and insertions) previously published SVs, and 145 SVs identified from 20 clinical samples. Our results showed the ability of SVInterpreter to support the evaluation of SVs by (1) confirming more than half of the predictions of the original studies, (2) decreasing 40% of the variants of uncertain significance, and (3) indicating several potential position effect events. To our knowledge, SVInterpreter is the most comprehensive TAD-based tool to identify the possible disease-causing candidate genes and to assist prediction of the clinical outcome of SVs. SVInterpreter is available at http://dgrctools-insa.min-saude.pt/cgi-bin/SVInterpreter.py.

Computational Tools to Assess the Functional Consequences of Rare and Noncoding Pharmacogenetic Variability

Interindividual differences in drug response are a common concern in both drug development and across layers of care. While genetics clearly influences drug response and toxicity of many drugs, a substantial fraction of the heritable pharmacological and toxicological variability remains unexplained by known genetic polymorphisms. In recent years, population-scale sequencing projects have unveiled tens of thousands of coding and noncoding pharmacogenetic variants with unclear functional effects that might explain at least part of this missing heritability. However, translating these personalized variant signatures into drug response predictions and actionable advice remains challenging and constitutes one of the most important frontiers of contemporary pharmacogenomics. Conventional prediction methods are primarily based on evolutionary conservation, which drastically reduces their predictive accuracy when applied to poorly conserved pharmacogenes. Here, we review the current state-of-the-art of computational variant effect predictors across variant classes and critically discuss their utility for pharmacogenomics. Besides missense variants, we discuss recent progress in the evaluation of synonymous, splice, and noncoding variations. Furthermore, we discuss emerging possibilities to assess haplotypes and structural variations. We advocate for the development of algorithms trained on pharmacogenomic instead of pathogenic data sets to improve the predictive accuracy in order to facilitate the utilization of next-generation sequencing data for personalized clinical decision support and precision pharmacogenomics.

Noninvasive early diagnosis of intestinal diseases based on artificial intelligence in genomics and microbiome

The maturing development in artificial intelligence (AI) and genomics has propelled the advances in intestinal diseases including intestinal cancer, inflammatory bowel disease (IBD), and irritable bowel syndrome (IBS). On the other hand, colorectal cancer is the second most deadly and the third most common type of cancer in the world according to GLOBOCAN 2020 data. The mechanisms behind IBD and IBS are still speculative. The conventional methods to identify colorectal cancer, IBD, and IBS are based on endoscopy or colonoscopy to identify lesions. However, it is invasive, demanding, and time-consuming for early-stage intestinal diseases. To address those problems, new strategies based on blood and/or human microbiome in gut, colon, or even feces were developed; those methods took advantage of high-throughput sequencing and machine learning approaches. In this review, we summarize the recent research and methods to diagnose intestinal diseases with machine learning technologies based on cell-free DNA and microbiome data generated by amplicon sequencing or whole-genome sequencing. Those methods play an important role in not only intestinal disease diagnosis but also therapy development in the near future.

Dawson E, De Coster W, Du H, Dunn C, Esteban R, Jolly A, Kalra D, Liao C, Liu Y, Lu TY, M Havrilla J, M Khayat M, Marin M, Monlong J, Price S, Rafael Gener A, Ren J, Sagayaradj S, Sapoval N, Sinner C, C. Soto D, Soylev A, Subramaniyan A, Syed N, Tadimeti N, Tater P, Vats P, Vaughn J, Walker K, Wang G, Zeng Q, Zhang S, Zhao T, Kille B, Biederstedt E, Chaisson M, English A, Kronenberg Z, J. Treangen T, Hefferon T, Chin CS, Busby B, J Sedlazeck F. An international virtual hackathon to build tools for the analysis of structural variants within species ranging from coronaviruses to vertebrates

In October 2020, 62 scientists from nine nations worked together remotely in the Second Baylor College of Medicine & DNAnexus hackathon, focusing on different related topics on Structural Variation, Pan-genomes, and SARS-CoV-2 related research.   The overarching focus was to assess the current status of the field and identify the remaining challenges. Furthermore, how to combine the strengths of the different interests to drive research and method development forward. Over the four days, eight groups each designed and developed new open-source methods to improve the identification and analysis of variations among species, including humans and SARS-CoV-2. These included improvements in SV calling, genotyping, annotations and filtering. Together with advancements in benchmarking existing methods. Furthermore, groups focused on the diversity of SARS-CoV-2. Daily discussion summary and methods are available publicly at  https://github.com/collaborativebioinformatics provides valuable insights for both participants and the research community.

Dawson E, De Coster W, Du H, Dunn C, Esteban R, Jolly A, Kalra D, Liao C, Liu Y, Lu TY, M Havrilla J, M Khayat M, Marin M, Monlong J, Price S, Rafael Gener A, Ren J, Sagayaradj S, Sapoval N, Sinner C, C. Soto D, Soylev A, Subramaniyan A, Syed N, Tadimeti N, Tater P, Vats P, Vaughn J, Walker K, Wang G, Zeng Q, Zhang S, Zhao T, Kille B, Biederstedt E, Chaisson M, English A, Kronenberg Z, J. Treangen T, Hefferon T, Chin CS, Busby B, J Sedlazeck F. An international virtual hackathon to build tools for the analysis of structural variants within species ranging from coronaviruses to vertebrates

In October 2020, 62 scientists from nine nations worked together remotely in the Second Baylor College of Medicine & DNAnexus hackathon, focusing on different related topics on Structural Variation, Pan-genomes, and SARS-CoV-2 related research.   The overarching focus was to assess the current status of the field and identify the remaining challenges. Furthermore, how to combine the strengths of the different interests to drive research and method development forward. Over the four days, eight groups each designed and developed new open-source methods to improve the identification and analysis of variations among species, including humans and SARS-CoV-2. These included improvements in SV calling, genotyping, annotations and filtering. Together with advancements in benchmarking existing methods. Furthermore, groups focused on the diversity of SARS-CoV-2. Daily discussion summary and methods are available publicly at  https://github.com/collaborativebioinformatics provides valuable insights for both participants and the research community.