Alex Alves Freitas

This study uses machine learning to predict lifespan-extending compounds in mice by analyzing drug-target annotations, identifying key receptors and pathways associated with longevity.

The paper introduces Gen-DNA-TCN, a method for generating functional yeast promoter sequences using deep learning, and shows it produces diverse and functional sequences with similar transcription factor binding sites.

The paper uses machine learning to predict lifespan-extending compounds in C. elegans using biological features from DrugAge data, achieving 82% and 80% accuracy with GO terms and protein interactors.

This paper uses machine learning to classify ageing-related genes as CR-related or not based on various predictive features, finding that curated knowledge features are most predictive.

This study identifies common ageing transcriptomic signatures across mammalian tissues using meta-analysis and machine learning, revealing shared functional changes and network properties.

The paper reports results from the CAFA3 challenge, showing improved computational protein function prediction and new annotations for over 1000 genes through experimental screens in C. albicans, P. aureginosa, and Drosophila.

PICKER-HG is a web server that uses random forests to classify human genes into categories based on user-provided annotations and outputs classification rules.