eDiVA-Classification and prioritization of pathogenic variants for clinical diagnostics

Rare disease genomics and precision medicine

Rare diseases, though individually uncommon, collectively affect millions worldwide. Genomic technologies and big data analytics have revolutionized diagnosing and understanding these conditions. This review explores the role of genomics in rare disease research, the impact of large consortium initiatives, advancements in extensive data analysis, the integration of artificial intelligence (AI) and machine learning (ML), and the therapeutic implications in precision medicine. We also discuss the challenges of data sharing and privacy concerns, emphasizing the need for collaborative efforts and secure data practices to advance rare disease research.

Tissue-aware interpretation of genetic variants advances the etiology of rare diseases

Pathogenic variants underlying Mendelian diseases often disrupt the normal physiology of a few tissues and organs. However, variant effect prediction tools that aim to identify pathogenic variants are typically oblivious to tissue contexts. Here we report a machine-learning framework, denoted "Tissue Risk Assessment of Causality by Expression for variants" (TRACEvar, https://netbio.bgu.ac.il/TRACEvar/ ), that offers two advancements. First, TRACEvar predicts pathogenic variants that disrupt the normal physiology of specific tissues. This was achieved by creating 14 tissue-specific models that were trained on over 14,000 variants and combined 84 attributes of genetic variants with 495 attributes derived from tissue omics. TRACEvar outperformed 10 well-established and tissue-oblivious variant effect prediction tools. Second, the resulting models are interpretable, thereby illuminating variants' mode of action. Application of TRACEvar to variants of 52 rare-disease patients highlighted pathogenicity mechanisms and relevant disease processes. Lastly, the interpretation of all tissue models revealed that top-ranking determinants of pathogenicity included attributes of disease-affected tissues, particularly cellular process activities. Collectively, these results show that tissue contexts and interpretable machine-learning models can greatly enhance the etiology of rare diseases.

Genomes in clinical care

In the era of precision medicine, genome sequencing (GS) has become more affordable and the importance of genomics and multi-omics in clinical care is increasingly being recognized. However, how to scale and effectively implement GS on an institutional level remains a challenge for many. Here, we present Genome First and Ge-Med, two clinical implementation studies focused on identifying the key pillars and processes that are required to make routine GS and predictive genomics a reality in the clinical setting. We describe our experience and lessons learned for a variety of topics including test logistics, patient care processes, data reporting, and infrastructure. Our model of providing clinical care and comprehensive genomic analysis from a single source may be used by other centers with a similar structure to facilitate the implementation of omics-based personalized health concepts in medicine.

Rare disease research workflow using multilayer networks elucidates the molecular determinants of severity in Congenital Myasthenic Syndromes

Exploring the molecular basis of disease severity in rare disease scenarios is a challenging task provided the limitations on data availability. Causative genes have been described for Congenital Myasthenic Syndromes (CMS), a group of diverse minority neuromuscular junction (NMJ) disorders; yet a molecular explanation for the phenotypic severity differences remains unclear. Here, we present a workflow to explore the functional relationships between CMS causal genes and altered genes from each patient, based on multilayer network community detection analysis of complementary biomedical information provided by relevant data sources, namely protein-protein interactions, pathways and metabolomics. Our results show that CMS severity can be ascribed to the personalized impairment of extracellular matrix components and postsynaptic modulators of acetylcholine receptor (AChR) clustering. This work showcases how coupling multilayer network analysis with personalized -omics information provides molecular explanations to the varying severity of rare diseases; paving the way for sorting out similar cases in other rare diseases.

Artificial intelligence and database for NGS-based diagnosis in rare disease

Rare diseases (RDs) are rare complex genetic diseases affecting a conservative estimate of 300 million people worldwide. Recent Next-Generation Sequencing (NGS) studies are unraveling the underlying genetic heterogeneity of this group of diseases. NGS-based methods used in RDs studies have improved the diagnosis and management of RDs. Concomitantly, a suite of bioinformatics tools has been developed to sort through big data generated by NGS to understand RDs better. However, there are concerns regarding the lack of consistency among different methods, primarily linked to factors such as the lack of uniformity in input and output formats, the absence of a standardized measure for predictive accuracy, and the regularity of updates to the annotation database. Today, artificial intelligence (AI), particularly deep learning, is widely used in a variety of biological contexts, changing the healthcare system. AI has demonstrated promising capabilities in boosting variant calling precision, refining variant prediction, and enhancing the user-friendliness of electronic health record (EHR) systems in NGS-based diagnostics. This paper reviews the state of the art of AI in NGS-based genetics, and its future directions and challenges. It also compare several rare disease databases.

Phenotype-aware prioritisation of rare Mendelian disease variants

A molecular diagnosis from the analysis of sequencing data in rare Mendelian diseases has a huge impact on the management of patients and their families. Numerous patient phenotype-aware variant prioritisation (VP) tools have been developed to help automate this process, and shorten the diagnostic odyssey, but performance statistics on real patient data are limited. Here we identify, assess, and compare the performance of all up-to-date, freely available, and programmatically accessible tools using a whole-exome, retinal disease dataset from 134 individuals with a molecular diagnosis. All tools were able to identify around two-thirds of the genetic diagnoses as the top-ranked candidate, with LIRICAL performing best overall. Finally, we discuss the challenges to overcome most cases remaining undiagnosed after current, state-of-the-art practices.

Knowledge structure and emerging trends in the application of deep learning in genetics research: A bibliometric analysis [2000–2021]

Introduction: Deep learning technology has been widely used in genetic research because of its characteristics of computability, statistical analysis, and predictability. Herein, we aimed to summarize standardized knowledge and potentially innovative approaches for deep learning applications of genetics by evaluating publications to encourage more research.

Methods: The Science Citation Index Expanded TM (SCIE) database was searched for deep learning applications for genomics-related publications. Original articles and reviews were considered. In this study, we derived a clustered network from 69,806 references that were cited by the 1,754 related manuscripts identified. We used CiteSpace and VOSviewer to identify countries, institutions, journals, co-cited references, keywords, subject evolution, path, current characteristics, and emerging topics.

Results: We assessed the rapidly increasing publications concerned about deep learning applications of genomics approaches and identified 1,754 articles that published reports focusing on this subject. Among these, a total of 101 countries and 2,487 institutes contributed publications, The United States of America had the most publications (728/1754) and the highest h-index, and the US has been in close collaborations with China and Germany. The reference clusters of SCI articles were clustered into seven categories: deep learning, logic regression, variant prioritization, random forests, scRNA-seq (single-cell RNA-seq), genomic regulation, and recombination. The keywords representing the research frontiers by year were prediction (2016–2021), sequence (2017–2021), mutation (2017–2021), and cancer (2019–2021).

Conclusion: Here, we summarized the current literature related to the status of deep learning for genetics applications and analyzed the current research characteristics and future trajectories in this field. This work aims to provide resources for possible further intensive exploration and encourages more researchers to overcome the research of deep learning applications in genetics.

An Educational Assessment of Evidence Used for Variant Classification: A Report of the Association for Molecular Pathology

The Association for Molecular Pathology Variant Interpretation Testing Among Laboratories (VITAL) Working Group convened to evaluate the Standards and Guidelines for the Interpretation of Sequence Variants implementation into clinical practice, identify problematic classification rules, and define implementation challenges. Variants and associated clinical information were provided to volunteer respondents. Participant variant classifications were compared with intended consensus-derived classifications of the Working Group. The 24 variant challenges received 1379 responses; 1119 agreed with the intended response (81%; 95% CI, 79% to 83%). Agreement ranged from 44% to 100%, with 16 challenges (67%; 47% to 82%) reaching consensus (≥80% agreement). Participant classifications were also compared to a calculated interpretation of the ACMG Guidelines using the participant-reported criteria as input. The 24 variant challenges had 1368 responses with specific evidence provided and 1121 (82%; 80% to 84%) agreed with the calculated interpretation. Agreement for challenges ranged from 63% to 98%; 15 (63%; 43% to 79%) reaching consensus. Among 81 individual participants, 32 (40%; 30% to 50%) reached agreement with at least 80% of the intended classifications and 42 (52%; 41% to 62%) with the calculated classifications. This study demonstrated that although variant classification remains challenging, published guidelines are being utilized and adapted to improve variant calling consensus. This study identified situations where clarifications are warranted and provides a model for competency assessment.

Evaluation of phenotype-driven gene prioritization methods for Mendelian diseases

It’s challenging work to identify disease-causing genes from the next-generation sequencing (NGS) data of patients with Mendelian disorders. To improve this situation, researchers have developed many phenotype-driven gene prioritization methods using a patient’s genotype and phenotype information, or phenotype information only as input to rank the candidate’s pathogenic genes. Evaluations of these ranking methods provide practitioners with convenience for choosing an appropriate tool for their workflows, but retrospective benchmarks are underpowered to provide statistically significant results in their attempt to differentiate. In this research, the performance of ten recognized causal-gene prioritization methods was benchmarked using 305 cases from the Deciphering Developmental Disorders (DDD) project and 209 in-house cases via a relatively unbiased methodology. The evaluation results show that methods using Human Phenotype Ontology (HPO) terms and Variant Call Format (VCF) files as input achieved better overall performance than those using phenotypic data alone. Besides, LIRICAL and AMELIE, two of the best methods in our benchmark experiments, complement each other in cases with the causal genes ranked highly, suggesting a possible integrative approach to further enhance the diagnostic efficiency. Our benchmarking provides valuable reference information to the computer-assisted rapid diagnosis in Mendelian diseases and sheds some light on the potential direction of future improvement on disease-causing gene prioritization methods.

VPMBench: a test bench for variant prioritization methods

Background

Clinical diagnostics of whole-exome and whole-genome sequencing data requires geneticists to consider thousands of genetic variants for each patient. Various variant prioritization methods have been developed over the last years to aid clinicians in identifying variants that are likely disease-causing. Each time a new method is developed, its effectiveness must be evaluated and compared to other approaches based on the most recently available evaluation data. Doing so in an unbiased, systematic, and replicable manner requires significant effort.

Results

The open-source test bench “VPMBench” automates the evaluation of variant prioritization methods. VPMBench introduces a standardized interface for prioritization methods and provides a plugin system that makes it easy to evaluate new methods. It supports different input data formats and custom output data preparation. VPMBench exploits declaratively specified information about the methods, e.g., the variants supported by the methods. Plugins may also be provided in a technology-agnostic manner via containerization.

Conclusions

VPMBench significantly simplifies the evaluation of both custom and published variant prioritization methods. As we expect variant prioritization methods to become ever more critical with the advent of whole-genome sequencing in clinical diagnostics, such tool support is crucial to facilitate methodological research.

A domain damage index to prioritizing the pathogenicity of missense variants

Prioritizing causal variants is one major challenge for the clinical application of sequencing data. Prompted by the observation that 74.3% of missense pathogenic variants locate in protein domains, we developed an approach named domain damage index (DDI). DDI identifies protein domains depleted of rare missense variations in the general population, which can be further used as a metric to prioritize variants. DDI is significantly correlated with phylogenetic conservation, variant-level metrics, and reported pathogenicity. DDI achieved great performance for distinguishing pathogenic variants from benign ones in three benchmark datasets. The combination of DDI with the other two best approaches improved the performance of each individual method considerably, suggesting DDI provides a powerful and complementary way of variant prioritization.

Powerful use of automated prioritization of candidate variants in genetic hearing loss with extreme etiologic heterogeneity

Variant prioritization of exome sequencing (ES) data for molecular diagnosis of sensorineural hearing loss (SNHL) with extreme etiologic heterogeneity poses a significant challenge. This study used an automated variant prioritization system (“EVIDENCE”) to analyze SNHL patient data and assess its diagnostic accuracy. We performed ES of 263 probands manifesting mild to moderate or higher degrees of SNHL. Candidate variants were classified according to the 2015 American College of Medical Genetics guidelines, and we compared the accuracy, call rates, and efficiency of variant prioritizations performed manually by humans or using EVIDENCE. In our in silico panel, 21 synthetic cases were successfully analyzed by EVIDENCE. In our cohort, the ES diagnostic yield for SNHL by manual analysis was 50.19% (132/263) and 50.95% (134/263) by EVIDENCE. EVIDENCE processed ES data 24-fold faster than humans, and the concordant call rate between humans and EVIDENCE was 97.72% (257/263). Additionally, EVIDENCE outperformed human accuracy, especially at discovering causative variants of rare syndromic deafness, whereas flexible interpretations that required predefined specific genotype–phenotype correlations were possible only by manual prioritization. The automated variant prioritization system remarkably facilitated the molecular diagnosis of hearing loss with high accuracy and efficiency, fostering the popularization of molecular genetic diagnosis of SNHL.

FREQMAX provides an alternative approach for determining high-resolution allele frequency thresholds in carrier screening

As whole-genome data become available for increasing numbers of individuals across diverse populations, the list of genomic variants of unknown significance (VOUS) continues to grow. One powerful tool in VOUS interpretation is determining whether an allele is too common to be considered pathogenic. As genetic and epidemiological parameters vary across disease models, so too does the pathogenic allele frequency threshold for each disease gene. One threshold-setting approach is the maximum credible allele frequency (MCAF) method. However, estimating some of the input values MCAF requires, especially those involving heterogeneity, can present nontrivial statistical challenges. Here, we introduce FREQMAX, our alternative approach for determining allele frequency thresholds in carrier screening. FREQMAX makes efficient use of the data available for well-studied traits and exhibits flexibility for traits where information may be less complete. For cystic fibrosis, more alleles are excluded as benign by FREQMAX than by MCAF. For less-comprehensively characterized traits like ciliary dyskinesia and Smith-Lemli-Opitz syndrome, FREQMAX is able to set the allele frequency threshold without requiring a priori estimates of maximum genetic and allelic contributions. Furthermore, though we describe FREQMAX in the context of carrier screening, its classical population genetics framework also provides context for adaptation to other trait models.

The IL-2RG R328X nonsense mutation allows partial STAT-5 phosphorylation and defines a critical region involved in the leaky-SCID phenotype

In addition to their detection in typical X-linked severe combined immunodeficiency, hypomorphic mutations in the interleukin (IL)-2 receptor common gamma chain gene (IL2RG) have been described in patients with atypical clinical and immunological phenotypes. In this leaky clinical phenotype the diagnosis is often delayed, limiting prompt therapy in these patients. Here, we report the biochemical and functional characterization of a nonsense mutation in exon 8 (p.R328X) of IL2RG in two siblings: a 4-year-old boy with lethal Epstein-Barr virus-related lymphoma and his asymptomatic 8-month-old brother with a T^low B⁺ natural killer (NK)⁺ immunophenotype, dysgammaglobulinemia, abnormal lymphocyte proliferation and reduced levels of T cell receptor excision circles. After confirming normal IL-2RG expression (CD132) on T lymphocytes, signal transducer and activator of transcription-1 (STAT-5) phosphorylation was examined to evaluate the functionality of the common gamma chain (γ_c ), which showed partially preserved function. Co-immunoprecipitation experiments were performed to assess the interaction capacity of the R328X mutant with Janus kinase (JAK)3, concluding that R328X impairs JAK3 binding to γ_c . Here, we describe how the R328X mutation in IL-2RG may allow partial phosphorylation of STAT-5 through a JAK3-independent pathway. We identified a region of three amino acids in the γ_c intracellular domain that may be critical for receptor stabilization and allow this alternative signaling. Identification of the functional consequences of pathogenic IL2RG variants at the cellular level is important to enable clearer understanding of partial defects leading to leaky phenotypes.

Videira P, Valadão G. Artificial Intelligence (AI) in Rare Diseases: Is the Future Brighter?

The amount of data collected and managed in (bio)medicine is ever-increasing. Thus, there is a need to rapidly and efficiently collect, analyze, and characterize all this information. Artificial intelligence (AI), with an emphasis on deep learning, holds great promise in this area and is already being successfully applied to basic research, diagnosis, drug discovery, and clinical trials. Rare diseases (RDs), which are severely underrepresented in basic and clinical research, can particularly benefit from AI technologies. Of the more than 7000 RDs described worldwide, only 5% have a treatment. The ability of AI technologies to integrate and analyze data from different sources (e.g., multi-omics, patient registries, and so on) can be used to overcome RDs’ challenges (e.g., low diagnostic rates, reduced number of patients, geographical dispersion, and so on). Ultimately, RDs’ AI-mediated knowledge could significantly boost therapy development. Presently, there are AI approaches being used in RDs and this review aims to collect and summarize these advances. A section dedicated to congenital disorders of glycosylation (CDG), a particular group of orphan RDs that can serve as a potential study model for other common diseases and RDs, has also been included.

eDiVA-Classification and prioritization of pathogenic variants for clinical diagnostics

Mendelian diseases have shown to be an and efficient model for connecting genotypes to phenotypes and for elucidating the function of genes. Whole‐exome sequencing (WES) accelerated the study of rare Mendelian diseases in families, allowing for directly pinpointing rare causal mutations in genic regions without the need for linkage analysis. However, the low diagnostic rates of 20–30% reported for multiple WES disease studies point to the need for improved variant pathogenicity classification and causal variant prioritization methods. Here, we present the exome Disease Variant Analysis (eDiVA; http://ediva.crg.eu), an automated computational framework for identification of causal genetic variants (coding/splicing single‐nucleotide variants and small insertions and deletions) for rare diseases using WES of families or parent–child trios. eDiVA combines next‐generation sequencing data analysis, comprehensive functional annotation, and causal variant prioritization optimized for familial genetic disease studies. eDiVA features a machine learning‐based variant pathogenicity predictor combining various genomic and evolutionary signatures. Clinical information, such as disease phenotype or mode of inheritance, is incorporated to improve the precision of the prioritization algorithm. Benchmarking against state‐of‐the‐art competitors demonstrates that eDiVA consistently performed as a good or better than existing approach in terms of detection rate and precision. Moreover, we applied eDiVA to several familial disease cases to demonstrate its clinical applicability.