Raquel Dias

The paper evaluates machine-learning models' ability to predict enzymatic functions for uncharacterized proteins and finds they fail to integrate scientific reasoning and make logic errors.

InteracTor extracts interatomic interaction features from protein 3D structures to improve characterization of structural properties and functional insights.

The paper identifies and characterizes constitutive promoters across three Proteobacteria classes, showing their expression range and portability between hosts.

STI is a transformer-based model for genome-scale genotype imputation that achieves high accuracy and handles multi-allelic variants effectively.

This paper introduces a denoising autoencoder for rapid, reference-free human genotype imputation, achieving higher accuracy and faster runtime than standard methods.

This study evaluates the impact of coronary artery disease polygenic risk scores on lipid-lowering therapy initiation via a mobile application, finding higher therapy rates among high-risk individuals.