Matthew E. Mort

The paper evaluates how well variant effect predictors perform across different genetic ancestries, finding comparable performance across major groups after accounting for allele frequency.

MutPred-PPI predicts interaction-specific effects of missense variants using graph attention networks, showing strong performance on both seen and unseen proteins.

The paper evaluates missense variant effect predictors using CAGI6 data, finding strong performance across settings and highlighting biases in some predictors.

This study analyzes codon usage patterns in Parkin protein mutations associated with Parkinsonism and finds significant disease associations with mutations at the first two codon positions.

MutPred2 identifies pathogenic amino acid variants, predicts their molecular mechanisms, and validates their functional impact in neurodevelopmental disorders.

The paper identifies developmental gene expression differences between humans and mammalian models, finding that half of human genes differ from their mouse orthologs in temporal trajectories, particularly for disease-related genes.

PIVOTAL prioritizes variants of uncertain significance using 3D proteome spatial patterns, predicting pathogenicity for 140,000 VUS and providing a web tool for analysis.

The paper estimates that 15-18% of canonical GT 5' splice sites can generate wild-type transcripts when mutated to GC, with implications for disease and splicing mechanisms.

The paper develops regSNPs-intron, a random forest classifier to prioritize intronic SNVs for disease, validated using ASSET-seq functional assays.