Francesco Carli

This paper introduces Karenina, a framework that evaluates biomedical AI using expert knowledge across multiple dimensions beyond traditional scoring.

This paper introduces BioContextAI, an open-source initiative that provides standardized access to validated biomedical knowledge to improve the reliability of AI systems in biomedical research.

The paper develops interpretable models to predict cancer drug sensitivity using transcriptomics data and enhances predictions with large language models, validated on clinical samples.

The paper analyzes GPCR signaling dysregulation in cancer transcriptomics data to identify therapeutic targets and survival-associated signaling axes.