Amirali Aghazadeh

The paper shows that protein fitness landscapes appear simpler when analyzed using an evolution-aware framework that accounts for the non-uniform distribution of sequences in nature.

GOLF predicts the pathogenicity of myocilin OLF domain variants using generative AI and interpretable models, achieving accurate classification of known pathogenic and benign variants.

The paper studies the sparsity of fitness functions in biological sequences and develops a framework to estimate the number of samples needed for accurate recovery.

This paper introduces a method to improve deep neural network predictions of fitness functions by leveraging sparse epistatic interactions in genetic sequences.