Disease-specific variant pathogenicity prediction significantly improves variant interpretation in inherited cardiac conditions,Genetics in Medicine

当前位置： X-MOL 学术 › Genet. Med. › 论文详情

Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)

Disease-specific variant pathogenicity prediction significantly improves variant interpretation in inherited cardiac conditions
Genetics in Medicine ( IF 8.8 ) Pub Date : 2020-10-13 , DOI: 10.1038/s41436-020-00972-3
Xiaolei Zhang _{1,

2} , Roddy Walsh _{1,

2} , Nicola Whiffin _{1,

2} , Rachel Buchan _{1,

2} , William Midwinter _{1,

2} , Alicja Wilk _{1,

2} , Risha Govind _{1,

2} , Nicholas Li _{2,

3} , Mian Ahmad _{1,

2} , Francesco Mazzarotto _{1,

4,

5} , Angharad Roberts _{1,

2} , Pantazis I Theotokis _{1,

2} , Erica Mazaika _{1,

2} , Mona Allouba _{1,

6} , Antonio de Marvao ₃ , Chee Jian Pua ₇ , Sharlene M Day ₈ , Euan Ashley ₉ , Steven D Colan ₁₀ , Michelle Michels ₁₁ , Alexandre C Pereira ₁₂ , Daniel Jacoby ₁₃ , Carolyn Y Ho ₁₄ , Iacopo Olivotto ₄ , Gunnar T Gunnarsson ₁₅ , John L Jefferies ₁₆ , Chris Semsarian _{17,

18} , Jodie Ingles ₁₇ , Declan P O'Regan ₃ , Yasmine Aguib _{1,

6} , Magdi H Yacoub _{1,

6} , Stuart A Cook _{1,

2,

7,

19} , Paul J R Barton _{1,

2} , Leonardo Bottolo _{20,

21,

22} , James S Ware _{1,

2,

3}

Affiliation

National Heart and Lung Institute, Imperial College London, London, United Kingdom.
Cardiovascular Research Centre, Royal Brompton and Harefield NHS, Foundation Trust London, London, United Kingdom.
MRC London Institute of Medical Sciences, Imperial College London, London, United Kingdom.
Cardiomyopathy Unit, Careggi University Hospital, Florence, Italy.
Department of Clinical and Experimental Medicine, University of Florence, Florence, Italy.
Aswan Heart Centre, Magdi Yacoub Heart Foundation, Aswan, Egypt.
National Heart Centre, Singapore, Singapore.
Division of Cardiovascular Medicine and Penn Cardiovascular Institute, Perelman School of Medicine, University of Pennsylvania, Philadelphia, USA.
Division of Cardiovascular Medicine, Stanford University Medical Center, Stanford, CA, USA.
Department of Cardiology, Boston Children's Hospital, Boston, MA, USA.
Department of Cardiology, Thoraxcenter, Erasmus MC Rotterdam, Rotterdam, Netherlands.
Heart Institute (InCor), University of Sao Paulo Medical School, Sao Paulo, Brazil.
Department of Internal Medicine, Yale University, New Haven, CT, USA.
Cardiovascular Division, Brigham and Women's Hospital, Boston, MA, USA.
Faculty of Medicine, University of Iceland, Akureyri, Iceland.
The Cardiovascular Institute, University of Tennessee, Memphis, TN, USA.
Centenary Institute, The University of Sydney, Sydney, Australia.
Department of Cardiology, Royal Prince Alfred Hospital, Sydney, Australia.
Duke-National University of Singapore, Singapore, Singapore.
Department of Medical Genetics, University of Cambridge, Cambridge, United Kingdom.
Alan Turing Institute, London, United Kingdom.
MRC Biostatistics Unit, University of Cambridge, Cambridge, United Kingdom.

Purpose

Accurate discrimination of benign and pathogenic rare variation remains a priority for clinical genome interpretation. State-of-the-art machine learning variant prioritization tools are imprecise and ignore important parameters defining gene–disease relationships, e.g., distinct consequences of gain-of-function versus loss-of-function variants. We hypothesized that incorporating disease-specific information would improve tool performance.

Methods

We developed a disease-specific variant classifier, CardioBoost, that estimates the probability of pathogenicity for rare missense variants in inherited cardiomyopathies and arrhythmias. We assessed CardioBoost’s ability to discriminate known pathogenic from benign variants, prioritize disease-associated variants, and stratify patient outcomes.

Results

CardioBoost has high global discrimination accuracy (precision recall area under the curve [AUC] 0.91 for cardiomyopathies; 0.96 for arrhythmias), outperforming existing tools (4–24% improvement). CardioBoost obtains excellent accuracy (cardiomyopathies 90.2%; arrhythmias 91.9%) for variants classified with >90% confidence, and increases the proportion of variants classified with high confidence more than twofold compared with existing tools. Variants classified as disease-causing are associated with both disease status and clinical severity, including a 21% increased risk (95% confidence interval [CI] 11–29%) of severe adverse outcomes by age 60 in patients with hypertrophic cardiomyopathy.

Conclusions

A disease-specific variant classifier outperforms state-of-the-art genome-wide tools for rare missense variants in inherited cardiac conditions (https://www.cardiodb.org/cardioboost/), highlighting broad opportunities for improved pathogenicity prediction through disease specificity.

中文翻译：

疾病特异性变异致病性预测显着改善遗传性心脏病的变异解释

目的

准确区分良性和致病性罕见变异仍然是临床基因组解释的优先事项。最先进的机器学习变体优先排序工具不精确，忽略了定义基因-疾病关系的重要参数，例如，功能获得变体与功能丧失变体的不同后果。我们假设结合疾病特异性信息将提高工具性能。

方法

我们开发了一种疾病特异性变异分类器 CardioBoost，它可以估计遗传性心肌病和心律失常中罕见错义变异的致病概率。我们评估了 CardioBoost 区分已知致病变异和良性变异、优先考虑疾病相关变异以及对患者结果进行分层的能力。

结果

CardioBoost 具有很高的全局识别准确度（心肌病曲线下的精确召回面积 [AUC] 为 0.91；心律失常为 0.96），优于现有工具（提高 4-24%）。CardioBoost 对于分类置信度 > 90% 的变异获得了出色的准确度（心肌病 90.2%；心律失常 91.9%），并且与现有工具相比，高置信度分类的变异比例增加了两倍以上。分类为致病的变异与疾病状态和临床严重程度相关，包括肥厚型心肌病患者在 60 岁时出现严重不良后果的风险增加 21%（95% 置信区间 [CI] 11-29%）。