Assessing the Utility of ColabFold and AlphaMissense in Determining Missense Variant Pathogenicity for Congenital Myasthenic Syndromes

Background/Objectives: Congenital myasthenic syndromes (CMSs) are caused by variants in >30 genes with increasing numbers of variants of unknown significance (VUS) discovered by next-generation sequencing. Establishing VUS pathogenicity requires in vitro studies that slow diagnosis and treatment...

Full description

Saved in:
Bibliographic Details
Main Authors: Finlay Ryan-Phillips, Leighann Henehan, Sithara Ramdas, Jacqueline Palace, David Beeson, Yin Yao Dong
Format: Article
Language:English
Published: MDPI AG 2024-11-01
Series:Biomedicines
Subjects:
Online Access:https://www.mdpi.com/2227-9059/12/11/2549
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1846154148479762432
author Finlay Ryan-Phillips
Leighann Henehan
Sithara Ramdas
Jacqueline Palace
David Beeson
Yin Yao Dong
author_facet Finlay Ryan-Phillips
Leighann Henehan
Sithara Ramdas
Jacqueline Palace
David Beeson
Yin Yao Dong
author_sort Finlay Ryan-Phillips
collection DOAJ
description Background/Objectives: Congenital myasthenic syndromes (CMSs) are caused by variants in >30 genes with increasing numbers of variants of unknown significance (VUS) discovered by next-generation sequencing. Establishing VUS pathogenicity requires in vitro studies that slow diagnosis and treatment initiation. The recently developed protein structure prediction software AlphaFold2/ColabFold has revolutionized structural biology; such predictions have also been leveraged in AlphaMissense, which predicts ClinVar variant pathogenicity with 90% accuracy. Few reports, however, have tested these tools on rigorously characterized clinical data. We therefore assessed ColabFold and AlphaMissense as diagnostic aids for CMSs, using variants of the CHRN genes that encode the nicotinic acetylcholine receptor (nAChR). Methods: Utilizing a dataset of 61 clinically validated CHRN variants, (1) we evaluated the possibility of a ColabFold metric (either predicted structural disruption, prediction confidence, or prediction quality) that distinguishes variant pathogenicity; (2) we assessed AlphaMissense’s ability to differentiate variant pathogenicity; and (3) we compared AlphaMissense to the existing pathogenicity prediction programs AlamutVP and EVE. Results: Analyzing the variant effects on ColabFold CHRN structure prediction, prediction confidence, and prediction quality did not yield any reliable pathogenicity indicative metric. However, AlphaMissense predicted variant pathogenicity with 63.93% accuracy in our dataset—a much greater proportion than AlamutVP (27.87%) and EVE (28.33%). Conclusions: Emerging in silico tools can revolutionize genetic disease diagnosis—however, improvement, refinement, and clinical validation are imperative prior to practical acquisition.
format Article
id doaj-art-165e2ec6b1cd4076996f63eba6eaf57e
institution Kabale University
issn 2227-9059
language English
publishDate 2024-11-01
publisher MDPI AG
record_format Article
series Biomedicines
spelling doaj-art-165e2ec6b1cd4076996f63eba6eaf57e2024-11-26T17:53:11ZengMDPI AGBiomedicines2227-90592024-11-011211254910.3390/biomedicines12112549Assessing the Utility of ColabFold and AlphaMissense in Determining Missense Variant Pathogenicity for Congenital Myasthenic SyndromesFinlay Ryan-Phillips0Leighann Henehan1Sithara Ramdas2Jacqueline Palace3David Beeson4Yin Yao Dong5Nuffield Department of Clinical Neurosciences, University of Oxford, Oxford OX3 9DS, UKNeurology Department, John Radcliffe Hospital, Oxford OX3 9DU, UKDepartment of Paediatric Neurology, John Radcliffe Hospital, Oxford OX3 9DU, UKNuffield Department of Clinical Neurosciences, University of Oxford, Oxford OX3 9DS, UKNuffield Department of Clinical Neurosciences, University of Oxford, Oxford OX3 9DS, UKNuffield Department of Clinical Neurosciences, University of Oxford, Oxford OX3 9DS, UKBackground/Objectives: Congenital myasthenic syndromes (CMSs) are caused by variants in >30 genes with increasing numbers of variants of unknown significance (VUS) discovered by next-generation sequencing. Establishing VUS pathogenicity requires in vitro studies that slow diagnosis and treatment initiation. The recently developed protein structure prediction software AlphaFold2/ColabFold has revolutionized structural biology; such predictions have also been leveraged in AlphaMissense, which predicts ClinVar variant pathogenicity with 90% accuracy. Few reports, however, have tested these tools on rigorously characterized clinical data. We therefore assessed ColabFold and AlphaMissense as diagnostic aids for CMSs, using variants of the CHRN genes that encode the nicotinic acetylcholine receptor (nAChR). Methods: Utilizing a dataset of 61 clinically validated CHRN variants, (1) we evaluated the possibility of a ColabFold metric (either predicted structural disruption, prediction confidence, or prediction quality) that distinguishes variant pathogenicity; (2) we assessed AlphaMissense’s ability to differentiate variant pathogenicity; and (3) we compared AlphaMissense to the existing pathogenicity prediction programs AlamutVP and EVE. Results: Analyzing the variant effects on ColabFold CHRN structure prediction, prediction confidence, and prediction quality did not yield any reliable pathogenicity indicative metric. However, AlphaMissense predicted variant pathogenicity with 63.93% accuracy in our dataset—a much greater proportion than AlamutVP (27.87%) and EVE (28.33%). Conclusions: Emerging in silico tools can revolutionize genetic disease diagnosis—however, improvement, refinement, and clinical validation are imperative prior to practical acquisition.https://www.mdpi.com/2227-9059/12/11/2549CMSAlphaFold2ColabFoldAlphaMissensepathogenicityprediction
spellingShingle Finlay Ryan-Phillips
Leighann Henehan
Sithara Ramdas
Jacqueline Palace
David Beeson
Yin Yao Dong
Assessing the Utility of ColabFold and AlphaMissense in Determining Missense Variant Pathogenicity for Congenital Myasthenic Syndromes
Biomedicines
CMS
AlphaFold2
ColabFold
AlphaMissense
pathogenicity
prediction
title Assessing the Utility of ColabFold and AlphaMissense in Determining Missense Variant Pathogenicity for Congenital Myasthenic Syndromes
title_full Assessing the Utility of ColabFold and AlphaMissense in Determining Missense Variant Pathogenicity for Congenital Myasthenic Syndromes
title_fullStr Assessing the Utility of ColabFold and AlphaMissense in Determining Missense Variant Pathogenicity for Congenital Myasthenic Syndromes
title_full_unstemmed Assessing the Utility of ColabFold and AlphaMissense in Determining Missense Variant Pathogenicity for Congenital Myasthenic Syndromes
title_short Assessing the Utility of ColabFold and AlphaMissense in Determining Missense Variant Pathogenicity for Congenital Myasthenic Syndromes
title_sort assessing the utility of colabfold and alphamissense in determining missense variant pathogenicity for congenital myasthenic syndromes
topic CMS
AlphaFold2
ColabFold
AlphaMissense
pathogenicity
prediction
url https://www.mdpi.com/2227-9059/12/11/2549
work_keys_str_mv AT finlayryanphillips assessingtheutilityofcolabfoldandalphamissenseindeterminingmissensevariantpathogenicityforcongenitalmyasthenicsyndromes
AT leighannhenehan assessingtheutilityofcolabfoldandalphamissenseindeterminingmissensevariantpathogenicityforcongenitalmyasthenicsyndromes
AT sithararamdas assessingtheutilityofcolabfoldandalphamissenseindeterminingmissensevariantpathogenicityforcongenitalmyasthenicsyndromes
AT jacquelinepalace assessingtheutilityofcolabfoldandalphamissenseindeterminingmissensevariantpathogenicityforcongenitalmyasthenicsyndromes
AT davidbeeson assessingtheutilityofcolabfoldandalphamissenseindeterminingmissensevariantpathogenicityforcongenitalmyasthenicsyndromes
AT yinyaodong assessingtheutilityofcolabfoldandalphamissenseindeterminingmissensevariantpathogenicityforcongenitalmyasthenicsyndromes