Thesis title: APOGEE 2: multi-layer machine-learning model for the interpretable prediction of mitochondrial missense variants
In multicellular organisms, mitochondria are essential for producing energy metabolism; their
dysfunction has pleiotropic effects and is a common cause of genetic diseases. The failure
of the oxidative phosphorylation system is frequently caused by mitochondrial DNA
mutations. Their significant variability in terms of clinical manifestations and onset of
symptoms, which involve multiple tissues, their heteroplasmic levels, and mutational load in
tissues, all contribute to the challenging task of the pathogenicity interpretation.
Here, we present APOGEE 2, the latest release of a mitochondrially-centered ensemble
method designed to improve the accuracy of pathogenicity predictions for interpreting
missense mitochondrial variants. In 2020, It was included in the American College of Medical
Genetics and Genomics/Association for Molecular Pathology (ACMG/AMP)’s joint
consensus recommendations as being specifically tailored for mitochondrial variants
classification.
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, an online collection of
genomic, clinical and functional annotations for all nucleotide changes that cause
non-synonymous substitutions in human mitochondrial protein coding genes, developed by
our group. APOGEE 2’s ability to address challenges in interpreting mitochondrial missense
variants makes it a valuable tool in the field of mitochondrial genetics, aiding mtDNA variants
genotype-phenotype correlations, improving diagnostic accuracy, and supporting the
development of potential therapeutic interventions.