Dr. John T. Macdonald Foundation Department of Human Genetics and John P. Hussman Institute for Human Genomics, University of Miami Miller School of Medicine, Miami, FL, USA.
Department of Neurology, Medical Faculty of the RWTH Aachen University, Aachen, Germany.
Nat Commun. 2023 Jul 13;14(1):4167. doi: 10.1038/s41467-023-39306-7.
Effective computer-aided or automated variant evaluations for monogenic diseases will expedite clinical diagnostic and research efforts of known and novel disease-causing genes. Here we introduce MAVERICK: a Mendelian Approach to Variant Effect pRedICtion built in Keras. MAVERICK is an ensemble of transformer-based neural networks that can classify a wide range of protein-altering single nucleotide variants (SNVs) and indels and assesses whether a variant would be pathogenic in the context of dominant or recessive inheritance. We demonstrate that MAVERICK outperforms all other major programs that assess pathogenicity in a Mendelian context. In a cohort of 644 previously solved patients with Mendelian diseases, MAVERICK ranks the causative pathogenic variant within the top five variants in over 95% of cases. Seventy-six percent of cases were solved by the top-ranked variant. MAVERICK ranks the causative pathogenic variant in hitherto novel disease genes within the first five candidate variants in 70% of cases. MAVERICK has already facilitated the identification of a novel disease gene causing a degenerative motor neuron disease. These results represent a significant step towards automated identification of causal variants in patients with Mendelian diseases.
有效的计算机辅助或自动化单基因疾病变异评估将加速已知和新型致病基因的临床诊断和研究工作。在这里，我们介绍了 MAVERICK：一种基于 Keras 的 Mendelian 方法，用于变体效应预测。MAVERICK 是一种基于转换器的神经网络的集合，它可以对广泛的蛋白质改变的单核苷酸变异（SNV）和插入缺失进行分类，并评估该变体在显性或隐性遗传情况下是否为致病性。我们证明，MAVERICK 在孟德尔背景下评估致病性的所有其他主要程序都表现出色。在 644 名先前解决的孟德尔疾病患者的队列中，MAVERICK 在超过 95%的病例中将致病的致病性变体排在前五个变体中。有 76%的病例是由排名最高的变体解决的。在迄今为止的新疾病基因中，MAVERICK 将前五个候选变体中的致病致病性变体排在前 70%的病例中。MAVERICK 已经促成了一种新的疾病基因的识别，该基因导致退行性运动神经元疾病。这些结果代表了朝着自动化识别孟德尔疾病患者的因果变体迈出的重要一步。
