Predicting the functional effects of voltage-gated potassium channel missense variants with multi-task learning

Ligand distances as key predictors of pathogenicity and function in NMDA receptors

Genetic variants in the genes GRIN1, GRIN2A, GRIN2B, and GRIN2D, which encode subunits of the N-methyl-D-aspartate receptor (NMDAR), have been associated with severe and heterogeneous neurologic and neurodevelopmental disorders, including early onset epilepsy, developmental and epileptic encephalopathy, intellectual disability, and autism spectrum disorders. Missense variants in these genes can result in gain or loss of the NMDAR function, requiring opposite therapeutic treatments. Computational methods that predict pathogenicity and molecular functional effects of missense variants are therefore crucial for therapeutic applications. We assembled 223 missense variants from patients, 631 control variants from the general population, and 160 missense variants characterized by electrophysiological readouts that show whether they can enhance or reduce the function of the receptor. This includes new functional data from 33 variants reported here, for the first time. By mapping these variants onto the NMDAR protein structures, we found that pathogenic/benign variants and variants that increase/decrease the channel function were distributed unevenly on the protein structure, with spatial proximity to ligands bound to the agonist and antagonist binding sites being a key predictive feature for both variant pathogenicity and molecular functional consequences. Leveraging distances from ligands, we developed two machine-learning based predictors for NMDA variants: a pathogenicity predictor which outperforms currently available predictors and the first molecular function (increase/decrease) predictor. Our findings can have direct application to patient care by improving diagnostic yield for genetic neurodevelopmental disorders and by guiding personalized treatment informed by the knowledge of the molecular disease mechanism.

Plural molecular and cellular mechanisms of pore domain KCNQ2 encephalopathy

KCNQ2 variants in children with neurodevelopmental impairment are difficult to assess due to their heterogeneity and unclear pathogenic mechanisms. We describe a child with neonatal-onset epilepsy, developmental impairment of intermediate severity, and KCNQ2 G256W heterozygosity. Analyzing prior KCNQ2 channel cryoelectron microscopy models revealed G256 as a node of an arch-shaped non-covalent bond network linking S5, the pore turret, and the ion path. Co-expression with G256W dominantly suppressed conduction by wild-type subunits in heterologous cells. Ezogabine partly reversed this suppression. Kcnq2G256W/+ mice have epilepsy leading to premature deaths. Hippocampal CA1 pyramidal cells from G256W/+ brain slices showed hyperexcitability. G256W/+ pyramidal cell KCNQ2 and KCNQ3 immunolabeling was significantly shifted from axon initial segments to neuronal somata. Despite normal mRNA levels, G256W/+ mouse KCNQ2 protein levels were reduced by about 50%. Our findings indicate that G256W pathogenicity results from multiplicative effects, including reductions in intrinsic conduction, subcellular targeting, and protein stability. These studies provide evidence for an unexpected and novel role for the KCNQ2 pore turret and introduce a valid animal model of KCNQ2 encephalopathy. Our results, spanning structure to behavior, may be broadly applicable because the majority of KCNQ2 encephalopathy patients share variants near the selectivity filter.

Evaluating novel in silico tools for accurate pathogenicity classification in epilepsy-associated genetic missense variants

OBJECTIVE

Determining the pathogenicity of missense variants in clinical genetic tests for individuals with epilepsy is crucial for guiding personalized treatment. However, achieving a definitive pathogenic classification remains challenging, with most missense variants still classified as variants of uncertain significance (VUS) and with the availability of many computational tools which may provide conflicting predictions. Here, we aim to evaluate the performance of state-of-the-art computational tools in pathogenicity prediction of missense variants in epilepsy-associated genes. This will assist in selecting the most appropriate tool and critically assess their use in clinical setting.

METHODS

We assessed the performance of nine in silico pathogenicity prediction tools for missense variants in epilepsy-associated genes on three carefully curated data sets. The first two data sets comprise missense variants in epilepsy associated genes that have been uploaded to ClinVar in the last year and were, therefore, not part of the training set of any of the nine considered tools. These two data sets are based on two different lists of epilepsy-associated genes and comprise ~700 and ~ 250 missense variants, respectively. The third data set includes ~400 missense variants within epilepsy-associated genes for which the functional effects have been determined experimentally and are therefore used here to infer pathogenicity. These three data sets represent the best available approximation to blind and independent test sets.

RESULTS

Among the nine assessed tools, AlphaMissense (area under the curve [AUC]: .93, .88, and .95) and REVEL (AUC: .93, .88, and .93) showed the best classification performance, also outperforming other tools in the number of classified variants.

SIGNIFICANCE

We show which recently developed prediction tools achieve higher performance in epilepsy-associated genes and should be integrated, therefore, into the American College of Medical Genetics and Genomics/Association of Molecular Pathology (AGMC/AMP) variant classification process. Periodic reevaluation of genetic test results with newly developed or updated tools should be incorporated into standard clinical practice to improve diagnostic yield and better inform precision medicine.

Identification of neural alterations in patients with Crohn's disease with a novel multiparametric brain MRI-based radiomics model

OBJECTIVES

Gut-brain axis dysfunction has emerged as a key contributor to the pathogenesis of Crohn's disease (CD). The elucidation of neural alterations may provide novel insights into its management. We aimed to develop a multiparameter brain MRI-based radiomics model (RM) for characterizing neural alterations in CD patients and to interpret these alterations using multiomics traits.

METHODS

This prospective study enrolled 230 CD patients and 46 healthy controls (HCs). Participants voluntarily underwent brain MRI and psychological assessment (n = 155), blood metabolomics analysis (n = 260), and/or fecal 16S rRNA sequencing (n = 182). The RM was developed using 13 features selected from 13,870 first-order features extracted from multiparameter brain MRI in training cohort (CD, n = 75; HCs, n = 32) and validated in test cohort (CD, n = 34; HCs, n = 14). Multiomics data (including gut microbiomics, blood metabolomics, and brain radiomics) were compared between CD patients and HCs.

RESULTS

In the training cohort, area under the receiver operating characteristic curve (AUC) of RM for distinguishing CD patients from HCs was 0.991 (95% confidence interval (CI), 0.975-1.000). In test cohort, RM showed an AUC of 0.956 (95% CI, 0.881-1.000). CD-enriched blood metabolites such as triacylglycerol (TAG) exhibited significant correlations with both brain features detected by RM and CD-enriched microbiota (e.g., Veillonella). One notable correlation was found between Veillonella and Ctx-Lh-Middle-Temporal-CBF-p90 (r = 0.41). Mediation analysis further revealed that dysbiosis, such as of Veillonella, may regulate the blood flow in the middle temporal cortex through TAG.

CONCLUSION

We developed a multiparameter MRI-based RM that characterized the neural alterations of CD patients, and multiomics data offer potential evidence to support the validity of our model. Our study may offer clues to help provide potential therapeutic targets.

CRITICAL RELEVANCE STATEMENT

Our brain-gut axis study developed a novel model using multiparameter MRI and radiomics to characterize brain changes in patients with Crohn's disease. We validated this model's effectiveness using multiomics data, making it a potential biomarker for better patient management.

KEY POINTS

Utilizing multiparametric MRI and radiomics techniques could unveil Crohn's disease's neurophenotype. The neurophenotype radiomics model is interpreted using multiomics data. This model may serve as a novel biomarker for Crohn's disease management.

KCNJ3 is a novel candidate gene for autosomal dominant pure hereditary spastic paraplegia identified using whole genome sequencing

Hereditary spastic paraplegia (HSP) is a group of familial diseases characterized by progressive corticospinal tract degeneration. Clinically, patients present with lower-limb spasticity and weakness. To date, more than 80 genetic HSP types have been identified. Despite advances in molecular genetics, novel HSP gene discoveries are ongoing, with a low genetic diagnostic yield. In this study, we aimed to determine pathogenic variants in a family with HSP, which was not diagnosed through conventional genetic testing. We clinically characterized a large family and conducted whole genome sequencing (WGS) analysis of four affected and three unaffected individuals in the family to identify the genetic cause of HSP. This family had autosomal dominant pure (uncomplicated) late childhood-onset HSP. The patients' symptoms accelerated between the ages of 20 and 30. Brain magnetic resonance images typically showed white matter changes, a thin corpus callosum, and cerebellar atrophy. We identified a heterozygous missense variant, KCNJ3 c.1297T>G (p.Leu433Val), through WGS and family genetic analysis, confirmed by Sanger sequencing. We suggest that the identification of KCNJ3 c.1297T>G (p.Leu433Val) constitutes the discovery of a potential novel gene responsible for HSP in this family. This is the first study to report the possible role of a KCNJ3 variant in HSP pathogenesis. Our findings further expand the phenotypic and genotypic spectrum of HSP.

Plural molecular and cellular mechanisms of pore domain KCNQ2 encephalopathy

KCNQ2 variants in children with neurodevelopmental impairment are difficult to assess due to their heterogeneity and unclear pathogenic mechanisms. We describe a child with neonatal-onset epilepsy, developmental impairment of intermediate severity, and KCNQ2 G256W heterozygosity. Analyzing prior KCNQ2 channel cryoelectron microscopy models revealed G256 as a node of an arch-shaped non-covalent bond network linking S5, the pore turret, and the ion path. Co-expression with G256W dominantly suppressed conduction by wild-type subunits in heterologous cells. Ezogabine partly reversed this suppression. G256W/+ mice have epilepsy leading to premature deaths. Hippocampal CA1 pyramidal cells from G256W/+ brain slices showed hyperexcitability. G256W/+ pyramidal cell KCNQ2 and KCNQ3 immunolabeling was significantly shifted from axon initial segments to neuronal somata. Despite normal mRNA levels, G256W/+ mouse KCNQ2 protein levels were reduced by about 50%. Our findings indicate that G256W pathogenicity results from multiplicative effects, including reductions in intrinsic conduction, subcellular targeting, and protein stability. These studies provide evidence for an unexpected and novel role for the KCNQ2 pore turret and introduce a valid animal model of KCNQ2 encephalopathy. Our results, spanning structure to behavior, may be broadly applicable because the majority of KCNQ2 encephalopathy patients share variants near the selectivity filter.

Distances from ligands as main predictive features for pathogenicity and functional effect of variants in NMDA receptors

Genetic variants in genes GRIN1 , GRIN2A , GRIN2B , and GRIN2D , which encode subunits of the N-methyl-D-aspartate receptor (NMDAR), have been associated with severe and heterogeneous neurologic diseases. Missense variants in these genes can result in gain or loss of the NMDAR function, requiring opposite therapeutic treatments. Computational methods that predict pathogenicity and molecular functional effects are therefore crucial for accurate diagnosis and therapeutic applications. We assembled missense variants: 201 from patients, 631 from general population, and 159 characterized by electrophysiological readouts showing whether they can enhance or reduce the receptor function. This includes new functional data from 47 variants reported here, for the first time. We found that pathogenic/benign variants and variants that increase/decrease the channel function were distributed unevenly on the protein structure, with spatial proximity to ligands bound to the agonist and antagonist binding sites being key predictive features. Leveraging distances from ligands, we developed two independent machine learning-based predictors for NMDAR missense variants: a pathogenicity predictor which outperforms currently available predictors (AUC=0.945, MCC=0.726), and the first binary predictor of molecular function (increase or decrease) (AUC=0.809, MCC=0.523). Using these, we reclassified variants of uncertain significance in the ClinVar database and refined a previous genome-informed epidemiological model to estimate the birth incidence of molecular mechanism-defined GRIN disorders. Our findings demonstrate that distance from ligands is an important feature in NMDARs that can enhance variant pathogenicity prediction and enable functional prediction. Further studies with larger numbers of phenotypically and functionally characterized variants will enhance the potential clinical utility of this method.

MLe-KCNQ2: An Artificial Intelligence Model for the Prognosis of Missense KCNQ2 Gene Variants

Despite the increasing availability of genomic data and enhanced data analysis procedures, predicting the severity of associated diseases remains elusive in the absence of clinical descriptors. To address this challenge, we have focused on the KV7.2 voltage-gated potassium channel gene (KCNQ2), known for its link to developmental delays and various epilepsies, including self-limited benign familial neonatal epilepsy and epileptic encephalopathy. Genome-wide tools often exhibit a tendency to overestimate deleterious mutations, frequently overlooking tolerated variants, and lack the capacity to discriminate variant severity. This study introduces a novel approach by evaluating multiple machine learning (ML) protocols and descriptors. The combination of genomic information with a novel Variant Frequency Index (VFI) builds a robust foundation for constructing reliable gene-specific ML models. The ensemble model, MLe-KCNQ2, formed through logistic regression, support vector machine, random forest and gradient boosting algorithms, achieves specificity and sensitivity values surpassing 0.95 (AUC-ROC > 0.98). The ensemble MLe-KCNQ2 model also categorizes pathogenic mutations as benign or severe, with an area under the receiver operating characteristic curve (AUC-ROC) above 0.67. This study not only presents a transferable methodology for accurately classifying KCNQ2 missense variants, but also provides valuable insights for clinical counseling and aids in the determination of variant severity. The research context emphasizes the necessity of precise variant classification, especially for genes like KCNQ2, contributing to the broader understanding of gene-specific challenges in the field of genomic research. The MLe-KCNQ2 model stands as a promising tool for enhancing clinical decision making and prognosis in the realm of KCNQ2-related pathologies.

SLC6A1 variant pathogenicity, molecular function and phenotype: a genetic and clinical analysis

Genetic variants in the SLC6A1 gene can cause a broad phenotypic disease spectrum by altering the protein function. Thus, systematically curated clinically relevant genotype-phenotype associations are needed to understand the disease mechanism and improve therapeutic decision-making. We aggregated genetic and clinical data from 172 individuals with likely pathogenic/pathogenic (lp/p) SLC6A1 variants and functional data for 184 variants (14.1% lp/p). Clinical and functional data were available for a subset of 126 individuals. We explored the potential associations of variant positions on the GAT1 3D structure with variant pathogenicity, altered molecular function and phenotype severity using bioinformatic approaches. The GAT1 transmembrane domains 1, 6 and extracellular loop 4 (EL4) were enriched for patient over population variants. Across functionally tested missense variants (n = 156), the spatial proximity from the ligand was associated with loss-of-function in the GAT1 transporter activity. For variants with complete loss of in vitro GABA uptake, we found a 4.6-fold enrichment in patients having severe disease versus non-severe disease (P = 2.9 × 10-3, 95% confidence interval: 1.5-15.3). In summary, we delineated associations between the 3D structure and variant pathogenicity, variant function and phenotype in SLC6A1-related disorders. This knowledge supports biology-informed variant interpretation and research on GAT1 function. All our data can be interactively explored in the SLC6A1 portal (https://slc6a1-portal.broadinstitute.org/).

In silico versus functional characterization of genetic variants: lessons from muscle channelopathies

Accurate determination of the pathogenicity of missense genetic variants of uncertain significance is a huge challenge for implementing genetic data in clinical practice. In silico predictive tools are used to score variants' pathogenicity. However, their value in clinical settings is often unclear, as they have not usually been validated against robust functional assays. We compared nine widely used in silico predictive tools, including more recently developed tools (EVE and REVEL) with detailed cell-based electrophysiology, for 126 CLCN1 variants discovered in patients with the skeletal muscle channelopathy myotonia congenita. We found poor accuracy for most tools. The highest accuracy was obtained with MutationTaster (84.58%) and REVEL (82.54%). Both of these scores showed poor specificity, although specificity was better using EVE. Combining methods based on concordance improved performance overall but still lacked specificity. Our calculated statistics for the predictive tools were different to reported values for other genes in the literature, suggesting that the utility of the tools varies between genes. Overall, current predictive tools for this chloride channel are not reliable for clinical use, and tools with better specificity are urgently required. Improving the accuracy of predictive tools is a wider issue and a huge challenge for effective clinical implementation of genetic data.

Predicting functional effects of ion channel variants using new phenotypic machine learning methods

Missense variants in genes encoding ion channels are associated with a spectrum of severe diseases. Variant effects on biophysical function correlate with clinical features and can be categorized as gain- or loss-of-function. This information enables a timely diagnosis, facilitates precision therapy, and guides prognosis. Functional characterization presents a bottleneck in translational medicine. Machine learning models may be able to rapidly generate supporting evidence by predicting variant functional effects. Here, we describe a multi-task multi-kernel learning framework capable of harmonizing functional results and structural information with clinical phenotypes. This novel approach extends the human phenotype ontology towards kernel-based supervised machine learning. Our gain- or loss-of-function classifier achieves high performance (mean accuracy 0.853 SD 0.016, mean AU-ROC 0.912 SD 0.025), outperforming both conventional baseline and state-of-the-art methods. Performance is robust across different phenotypic similarity measures and largely insensitive to phenotypic noise or sparsity. Localized multi-kernel learning offered biological insight and interpretability by highlighting channels with implicit genotype-phenotype correlations or latent task similarity for downstream analysis.

KCNA1 gain-of-function epileptic encephalopathy treated with 4-aminopyridine

Precision medicine for Mendelian epilepsy is rapidly developing. We describe an early infant with severely pharmacoresistant multifocal epilepsy. Exome sequencing revealed the de novo variant p.(Leu296Phe) in the gene KCNA1, encoding the voltage-gated K⁺ channel subunit K_V 1.1. So far, loss-of-function variants in KCNA1 have been associated with episodic ataxia type 1 or epilepsy. Functional studies of the mutated subunit in oocytes revealed a gain-of-function caused by a hyperpolarizing shift of voltage dependence. Leu296Phe channels are sensitive to block by 4-aminopyridine. Clinical use of 4-aminopyridine was associated with reduced seizure burden, enabled simplification of co-medication and prevented rehospitalization.

[Gene Therapy for Epilepsy: Clinical Studies are on the Road]

For more than 10 years, research has been conducted on gene therapies for the most severe forms of epilepsy, which until now have proven resistant to treatment. First gene therapies are now in clinical trials for pharmacoresistant focal epilepsies and Dravet syndrome. In this article, we describe how these and many more gene therapies work and what they target.

Current practice in diagnostic genetic testing of the epilepsies

Epilepsy genetics is a rapidly developing field, in which novel disease-associated genes, novel mechanisms associated with epilepsy, and precision medicine approaches are continuously being identified. In the past decade, advances in genomic knowledge and analysis platforms have begun to make clinical genetic testing accessible for, in principle, people of all ages with epilepsy. For this reason, the Genetics Commission of the International League Against Epilepsy (ILAE) presents this update on clinical genetic testing practice, including current techniques, indications, yield of genetic testing, recommendations for pre- and post-test counseling, and follow-up after genetic testing is completed. We acknowledge that the resources vary across different settings but highlight that genetic diagnostic testing for epilepsy should be prioritized when the likelihood of an informative finding is high. Results of genetic testing, in particular the identification of causative genetic variants, are likely to improve individual care. We emphasize the importance of genetic testing for individuals with epilepsy as we enter the era of precision therapy.