Gabriel Cia

The paper introduces AbAgym, a curated dataset of 335k mutations in antibody-antigen complexes, and evaluates models for predicting binding affinity changes.

The paper evaluates variant effect predictions for ARSA gene variants, finding that a bootcamp-trained model outperformed others and that deep learning slightly improved performance over simpler methods.

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

This paper introduces EvolveX, a computational pipeline for designing stable single-domain antibodies with high affinity, demonstrating improved binding affinity to human targets.

FiTMuSiC predicts protein fitness effects using structural and coevolutionary data, achieving high accuracy and providing mechanistic insights through functional and structural scores.

pyScoMotif identifies similar 3D structural motifs across proteins, enabling tasks like catalytic site detection and drug discovery.