Thea K. Schulze

The paper combines variant effect data from six VAMP-seq experiments to analyze 31,614 substitution effects on protein abundance, finding that structural environment (buried/exposed) predicts abundance with high accuracy.

The paper develops a framework to train supervised models on MAVE data by accounting for experimental protocol differences, improving variant effect prediction across datasets.

The paper uses deep mutational scanning to show that protein degradation and toxicity are tightly correlated in ASPA variants linked to Canavans disease.