APOGEE 2: multi-layer machine-learning model for the interpretable prediction of mitochondrial missense variants

Abstract

Mitochondrial dysfunction has pleiotropic effects and is frequently caused by mitochondrial DNA mutations. However, factors such as significant variability in clinical manifestations make interpreting the pathogenicity of variants in the mitochondrial genome challenging. Here, we present APOGEE 2, a mitochondrially-centered ensemble method designed to improve the accuracy of pathogenicity predictions for interpreting missense mitochondrial variants. Built on the joint consensus recommendations by the American College of Medical Genetics and Genomics/Association for Molecular Pathology, APOGEE 2 features an improved machine learning method and a curated training set for enhanced performance metrics. It offers region-wise assessments of genome fragility and mechanistic analyses of specific amino acids that cause perceptible long-range effects on protein structure. With clinical and research use in mind, APOGEE 2 scores and pathogenicity probabilities are precompiled and available in MitImpact. APOGEE 2’s ability to address challenges in interpreting mitochondrial missense variants makes it an essential tool in the field of mitochondrial genetics.

A novel mitochondrial DNA variant in MT-ND6: m.14430A>C p.(Trp82Gly) identified in a patient with Leigh syndrome and complex I deficiency

“…This variant is absent from population databases, including Genbank, GnomAD, and Helix, is predicted to be likely pathogenic by Apogee2 (pathogenicity score of 0.854, probability: 0.977) [ 10 ], and occurs in a very conserved region of the mtDNA genome (97.8%). No causative variants were identified in exome data for any of the Leigh syndrome genes included in the Genomics England PanelApp genes listed for this disorder.…”

Mutational profiling of mitochondrial DNA reveals an epithelial ovarian cancer‐specific evolutionary pattern contributing to high oxidative metabolism

“…All mtDNA mutations were subsequently annotated by ANNOVAR software 34 . APOGEE2 scores were used to predict the functional impact of mitochondrial missense variants 35 . Additionally, mutations in mtDNA tRNA encoding regions were categorised as benign or deleterious as described by Sonney et al 36 .…”

“… 34 APOGEE2 scores were used to predict the functional impact of mitochondrial missense variants. 35 Additionally, mutations in mtDNA tRNA encoding regions were categorised as benign or deleterious as described by Sonney et al. 36 The annotation information of APOGEE2 scores for mitochondrial missense variants and Mitotip scores for mt‐tRNA mutations were summarised in Additional File 4 .…”

Mitochondrial and Nuclear DNA Variants in Amyotrophic Lateral Sclerosis: Enrichment in the Mitochondrial Control Region and Sirtuin Pathway Genes in Spinal Cord Tissue

“…The effects of variants in mitochondrial tRNA genes were annotated by PON-mt-tRNA and MitoTIP [59,60]. Coding mtDNA variants were assessed by MitImpact 3D [61], which incorporates PolyPhen [62], SIFT [63], and APOGEE 2 [64]); mtoolnote (https://github. com/mitoNGS/mtoolnote; accessed on 1 September 2023), which contains scores from MutPred [65], Panther [66], PhDSNP [67], SNPsGO [68], Polyphen2 HDIV, and Polyphen2 HVAR [69]; and HmtDB_Pathogenicity (score retrieved from https://mseqdr.org/mvtool.…”