A Gene Replacement Humanization Platform for Rapid Functional Testing of Clinical Variants in Epilepsy-associatedSTXBP1

Abstract

Purpose: Functional evidence is a pillar of variant interpretation according to ACMG guidelines. Functional evidence can be obtained in a variety of models and assay systems, including patient-derived tissues and iPSCs, in vitro cellular assays, and in vivo assays. Here we evaluate the reliability and practicality of variant interpretation in the small animal model, C. elegans, through a series of experiments evaluating the function of syntaxin binding protein, STXBP1, a well-known causative gene for Early infantile epileptic encephalopathy 1 (EIEE1). Methods: Using CRISPR, we replaced the coding sequence for unc-18 with the coding sequence for the human ortholog STXBP1. Next, we used CRISPR to introduce precise point mutations in the human STXBP1 coding sequence, reflecting three clinical categories (benign, pathogenic, and variants of uncertain significance (VUS)). We quantified 26 features of the resulting worms movement to train Random Forest (RF) and Support Vector Machines (SVM) machine learning classifiers on known pathogenic and benign variants. We characterized the classifiers, and then used the behavioral data from the VUS-expressing animals to predict the categorization of the VUS. Results: Whereas knock-out worms without unc-18 are severely impaired in motor function, worms expressing STXBP1 in its place have restored motor function. We produced worms with STXBP1 variants previously classified by ACMG criteria, including 25 benign variants, 32 pathogenic, and 24 variants of uncertain significance (VUS). Using either SVM or RF classifiers, we were able to obtain a sensitivity of 0.84-0.97 on known benign and pathogenic strains. By comparing multiple ML classification methods, we were able to classify 9 of the VUS as functionally abnormal, suggesting that these VUS are likely to be pathogenic. Conclusions: We demonstrate that automated analysis of a small animal system is an effective, scalable, and fast way to understand functional consequences of variants in STXBP1, one of the most common causes of genetic epilepsies and neurodevelopmental disorders. Keywords: STXBP1, C. elegans, CRISPR, Unc-18

Interpreting ciliopathy-associated missense variants of uncertain significance (VUS) in Caenorhabditis elegans

“…For example, live animal fluorescence-activated cell sorting (FACS) can be used for assessing cilium structure (via dye filling) and automated worm tracking can be applied to measure cilium function (roaming, chemotaxis) ( 70–72 ). Furthermore, machine learning can streamline the analysis of complex datasets to predict VUS pathogenicity ( 73 ). Another advantage of the nematode approach is that engineered patient alleles can be used for high-throughput small molecule suppressor screens to identify potential therapeutics.…”

“…The utility of the nematode approach to interpreting human gene variants goes well beyond TMEM67 and the ciliopathy gene class. Indeed, a humanized nematode model was very recently employed to interpret the pathogenicity of 29 missense VUS in an epilepsy gene ( 73 ). Thus, for genes functioning in conserved molecular pathways, worms offer a powerful system to generate in vivo evidence towards reclassifying VUS as pathogenic or benign.…”

Interpreting ciliopathy-associated missense variants of uncertain significance (VUS) in an animal model

“…Live animal fluorescence-activated cell sorting can be used for high throughput dye filling assays 36 and automated worm tracking can be used for high throughput roaming and chemotaxis assays 37 . Additionally, machine learning can streamline the analysis of complex datasets to predict VUS pathogenicity 38 . One limitation to modelling patient variants in endogenous C. elegans genes is the conservation of amino acid residues.…”

“…Although many cilia genes have clear orthologs in C. elegans , the amino acid conservation varies from 30-60%. C. elegans genes can be “humanized” to remove this limitation 38–40 . In summary, this study highlights that C. elegans is a practical model for variant interpretation of ciliary genes.…”

The GDAP1 p.Glu222Lys Variant-Weak Pathogenic Effect, Cumulative Effect of Weak Sequence Variants, or Synergy of Both Factors?

“…In 2015, nearly half of deposited sequence variants in the widely used ClinVar database were categorized as VUS. Five years later, in 2020, almost 75% of ClinVar variants were classified as VUS [ 1 ]. In other words, only one in four variants identified in the patients’ causative role of certain variants may be established.…”