Cargando…
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...
Autores principales: | , , , , , , , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
Elsevier
2022
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9250003/ https://www.ncbi.nlm.nih.gov/pubmed/35759918 http://dx.doi.org/10.1016/j.ebiom.2022.104115 |
_version_ | 1784739714301952000 |
---|---|
author | Boßelmann, Christian Malte Hedrich, Ulrike B.S. Müller, Peter Sonnenberg, Lukas Parthasarathy, Shridhar Helbig, Ingo Lerche, Holger Pfeifer, Nico |
author_facet | Boßelmann, Christian Malte Hedrich, Ulrike B.S. Müller, Peter Sonnenberg, Lukas Parthasarathy, Shridhar Helbig, Ingo Lerche, Holger Pfeifer, Nico |
author_sort | Boßelmann, Christian Malte |
collection | PubMed |
description | 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). |
format | Online Article Text |
id | pubmed-9250003 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2022 |
publisher | Elsevier |
record_format | MEDLINE/PubMed |
spelling | pubmed-92500032022-07-03 Predicting the functional effects of voltage-gated potassium channel missense variants with multi-task learning Boßelmann, Christian Malte Hedrich, Ulrike B.S. Müller, Peter Sonnenberg, Lukas Parthasarathy, Shridhar Helbig, Ingo Lerche, Holger Pfeifer, Nico eBioMedicine Articles 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). Elsevier 2022-06-24 /pmc/articles/PMC9250003/ /pubmed/35759918 http://dx.doi.org/10.1016/j.ebiom.2022.104115 Text en © 2022 The Authors https://creativecommons.org/licenses/by-nc-nd/4.0/This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/). |
spellingShingle | Articles Boßelmann, Christian Malte Hedrich, Ulrike B.S. Müller, Peter Sonnenberg, Lukas Parthasarathy, Shridhar Helbig, Ingo Lerche, Holger Pfeifer, Nico Predicting the functional effects of voltage-gated potassium channel missense variants with multi-task learning |
title | Predicting the functional effects of voltage-gated potassium channel missense variants with multi-task learning |
title_full | Predicting the functional effects of voltage-gated potassium channel missense variants with multi-task learning |
title_fullStr | Predicting the functional effects of voltage-gated potassium channel missense variants with multi-task learning |
title_full_unstemmed | Predicting the functional effects of voltage-gated potassium channel missense variants with multi-task learning |
title_short | Predicting the functional effects of voltage-gated potassium channel missense variants with multi-task learning |
title_sort | predicting the functional effects of voltage-gated potassium channel missense variants with multi-task learning |
topic | Articles |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9250003/ https://www.ncbi.nlm.nih.gov/pubmed/35759918 http://dx.doi.org/10.1016/j.ebiom.2022.104115 |
work_keys_str_mv | AT boßelmannchristianmalte predictingthefunctionaleffectsofvoltagegatedpotassiumchannelmissensevariantswithmultitasklearning AT hedrichulrikebs predictingthefunctionaleffectsofvoltagegatedpotassiumchannelmissensevariantswithmultitasklearning AT mullerpeter predictingthefunctionaleffectsofvoltagegatedpotassiumchannelmissensevariantswithmultitasklearning AT sonnenberglukas predictingthefunctionaleffectsofvoltagegatedpotassiumchannelmissensevariantswithmultitasklearning AT parthasarathyshridhar predictingthefunctionaleffectsofvoltagegatedpotassiumchannelmissensevariantswithmultitasklearning AT helbigingo predictingthefunctionaleffectsofvoltagegatedpotassiumchannelmissensevariantswithmultitasklearning AT lercheholger predictingthefunctionaleffectsofvoltagegatedpotassiumchannelmissensevariantswithmultitasklearning AT pfeifernico predictingthefunctionaleffectsofvoltagegatedpotassiumchannelmissensevariantswithmultitasklearning |