Predicting the functional effects of voltage-gated potassium channel missense variants with multi-task learning
Christian Malte Boßelmann,
Ulrike B.S. Hedrich,
Peter Müller,
Lukas Sonnenberg,
Shridhar Parthasarathy,
Ingo Helbig,
Holger Lerche,
Nico Pfeifer
Affiliations
Christian Malte Boßelmann
Department of Neurology and Epileptology, Hertie Institute for Clinical Brain Research, University of Tuebingen, Hoppe-Seyler-Str. 3, D-72076 Tuebingen, Germany; Methods in Medical Informatics, Department of Computer Science, University of Tuebingen, Sand 14, D-72076 Tuebingen, Germany
Ulrike B.S. Hedrich
Department of Neurology and Epileptology, Hertie Institute for Clinical Brain Research, University of Tuebingen, Hoppe-Seyler-Str. 3, D-72076 Tuebingen, Germany
Peter Müller
Department of Neurology and Epileptology, Hertie Institute for Clinical Brain Research, University of Tuebingen, Hoppe-Seyler-Str. 3, D-72076 Tuebingen, Germany
Lukas Sonnenberg
Institute for Neurobiology, University of Tuebingen, Tuebingen, Germany
Shridhar Parthasarathy
Division of Neurology, Children's Hospital of Philadelphia, Philadelphia, PA, USA; The Epilepsy NeuroGenetics Initiative (ENGIN), Children's Hospital of Philadelphia, Philadelphia, PA, USA; Department of Biomedical and Health Informatics (DBHi), Children's Hospital of Philadelphia, Philadelphia, PA, USA
Ingo Helbig
Division of Neurology, Children's Hospital of Philadelphia, Philadelphia, PA, USA; The Epilepsy NeuroGenetics Initiative (ENGIN), Children's Hospital of Philadelphia, Philadelphia, PA, USA; Department of Biomedical and Health Informatics (DBHi), Children's Hospital of Philadelphia, Philadelphia, PA, USA; Department of Neurology, University of Pennsylvania, Philadelphia, PA, USA
Holger Lerche
Department of Neurology and Epileptology, Hertie Institute for Clinical Brain Research, University of Tuebingen, Hoppe-Seyler-Str. 3, D-72076 Tuebingen, Germany; Corresponding authors.
Nico Pfeifer
Methods in Medical Informatics, Department of Computer Science, University of Tuebingen, Sand 14, D-72076 Tuebingen, Germany; Interfaculty Institute for Biomedical Informatics (IBMI), University of Tuebingen, Tuebingen, Germany; Faculty of Medicine, University of Tuebingen, Tuebingen, Germany; German Center for Infection Research, Partner Site Tuebingen, Tuebingen, Germany; Corresponding authors.
Summary: 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).
