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.

Real-world data on cannabidiol treatment of various epilepsy subtypes: A retrospective, multicenter study

OBJECTIVE

Cannabidiol (CBD) is approved for treatment of Dravet syndrome (DS), Lennox-Gastaut syndrome (LGS), and tuberous sclerosis complex (TSC). Several studies suggest antiseizure effects also beyond these three epilepsy syndromes.

METHODS

In a retrospective multicenter study, we analyzed the efficacy and tolerability of CBD in patients with epilepsy at 16 epilepsy centers.

RESULTS

The study cohort comprised 311 patients with epilepsy with a median age of 11.3 (0-72) years (235 children and adolescents, 76 adults). Therapy with CBD was off-label in 91.3% of cases due to age, epilepsy subtype, lack of adjunct therapy with clobazam, and/or higher dose applied. CBD titration regimens were slower than recommended, with good tolerability of higher doses particularly in children. Of all patients, 36.9% experienced a reduction in seizure frequency of >50%, independent of their epilepsy subtype or clobazam co-medication. The median observation period was 15.8 months. About one third of all patients discontinued therapy within the observation period due to adverse effects or lack of efficacy. Adverse effects were reported frequently (46.9%).

SIGNIFICANCE

Our study highlights that CBD has an antiseizure effect comparable to other antiseizure medications with a positive safety profile independent of the epilepsy subtype. Comedication with clobazam was not associated with a better outcome. Higher doses to achieve seizure frequency reduction were safe, particularly in children. These findings call for further trials for an extended approval of CBD for other epilepsy subtypes and for children <2 years of age.

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

BACKGROUND

Variants in genes encoding voltage-gated potassium channels are associated with a broad spectrum of neurological diseases including epilepsy, ataxia, and intellectual disability. Knowledge of the resulting functional changes, characterized as overall ion channel gain- or loss-of-function, is essential to guide clinical management including precision medicine therapies. However, for an increasing number of variants, little to no experimental data is available. New tools are needed to evaluate variant functional effects.

METHODS

We catalogued a comprehensive dataset of 959 functional experiments across 19 voltage-gated potassium channels, leveraging data from 782 unique disease-associated and synthetic variants. We used these data to train a taxonomy-based multi-task learning support vector machine (MTL-SVM), and compared performance to several baseline methods.

FINDINGS

MTL-SVM maintains channel family structure during model training, improving overall predictive performance (mean balanced accuracy 0·718 ± 0·041, AU-ROC 0·761 ± 0·063) over baseline (mean balanced accuracy 0·620 ± 0·045, AU-ROC 0·711 ± 0·022). We can obtain meaningful predictions even for channels with few known variants (KCNC1, KCNQ5).

INTERPRETATION

Our model enables functional variant prediction for voltage-gated potassium channels. It may assist in tailoring current and future precision therapies for the increasing number of patients with ion channel disorders.

FUNDING

This work was supported by intramural funding of the Medical Faculty, University of Tuebingen (PATE F.1315137.1), the Federal Ministry for Education and Research (Treat-ION, 01GM1907A/B/G/H) and the German Research Foundation (FOR-2715, Le1030/16-2, He8155/1-2).

Genetic testing before epilepsy surgery - An exploratory survey and case collection from German epilepsy centers

INTRODUCTION

Genetic testing in people with epilepsy may support presurgical decision-making. It is currently unclear to what extent epilepsy centres use genetic testing in presurgical evaluation.

METHODS

We performed an exploratory survey among members of the German Society for Epileptology to study the current practice of genetic testing in presurgical evaluation at the respective sites. Survey participants contributed educational case reports.

RESULTS

The majority of participants consider genetic testing to be useful in individuals with familial syndromes or phenotypic features suggesting a genetic etiology. We report 25 cases of individuals with a confirmed genetic diagnosis that have previously undergone epilepsy surgery. Our cases demonstrate that a genetic diagnosis has an impact on both the decision-making process during presurgical evaluation, as well as the postoperative outcome.

CONCLUSION

Genetic testing as part of the presurgical work-up is becoming increasingly established in epilepsy centres across Germany. mTORopathies and genetic hypothalamic hamartomas seem to be associated with a generally favourable surgical outcome. Synaptopathies and channelopathies may be associated with a worse outcome and should be considered on a case-by-case level. Prospective studies are needed to examine the impact of an established genetic diagnosis on postsurgical outcome.

Seizures, semiology, and syndromes: A narrative review

Clinical seizure signs continue to be of central importance to guide diagnosis, classification, treatment and prognosis. Some basic principles guide history-taking and observation in clinical epileptology. The information contained within subjective seizure descriptions can be framed within standardized vocabulary and a classification of ictal signs, seizure types, and the integrated framework of epilepsy syndromes. As illustrative examples, we discuss the historical origins and current research context of Dravet syndrome and Janz syndrome, two genetic epilepsy syndromes. In candidates for epilepsy surgery, ictal signs aid us in identifying the symptomatogenic zone and hence delineating the ictal onset zone. Here, historical reports from Victor Horsley and Hughlings Jackson provide valuable perspective on clinical reasoning. Lastly, the information contained within clinical signs and syndromes presents an indispensable data source in future efforts of large-scale genotype-phenotype correlations and machine learning methods.

Papillary tumor of the pineal region: a single-center experience

Papillary tumor of the pineal region (PTPR) is a rare entity. Its clinical presentation is diverse, and establishing an accurate and timely diagnosis may be challenging. Treatment recommendations are based on the evidence level of case series. Recently, several key advances have been made for immunohistochemical characterization, molecular diagnostics, and neurosurgical treatment of PTPR. Here, we describe our single-center experience.

Social media use in German visceral surgeons: a cross-sectional study of a national cohort

AIM

Engagement in social media is increasing. Medical professionals have been adapting LinkedIn, a professional networking site, and Twitter, a microblogging service, for a number of uses. This development has been described for a number of medical specialties, but there remains a paucity of European data. A study was undertaken to measure the engagement and activity of German visceral surgeons on social media platforms.

METHOD

Visceral surgeons were identified from 15 regional Associations of Statutory Health Insurance Physicians (Kassenärztliche Vereinigungen) opt-in registers. A manual search was subsequently performed across key professional social media platforms. The presence of a profile and key markers of use were recorded.

RESULTS

In total, 575 visceral surgeons were identified. 523 (93%) were men. 183 (31%) surgeons engaged in professional social media. 22 (3.8%) used Twitter, producing a mean of 16.43 tweets with a mean of 7.57 followers. 137 (24%) surgeons had a profile on LinkedIn with a mean of 46.36 connections. Female surgeons were less connected on LinkedIn (P < 0.005). 60 (10%) used Xing, with a mean of 27.95 connections. There were no significant differences in use of social media between surgeons from Eastern and Western Germany (P = 0.262) or male and female surgeons (P = 0.399).

CONCLUSIONS

German visceral surgeons are less engaged and less active on social media than previously examined cohorts. Loco-regional, cultural, demographic and regulatory matters may have a significant influence on uptake. If this surgical cohort wishes to have a wider international presence then education on the potential benefits of these tools may be needed.