Satoshi Kodera

REN-former identifies gene regulators of kidney disease transitions by combining single-cell modeling and human genetics.

This paper evaluates Evo 2's ability to predict pathogenicity and mechanisms of cardiomyopathy variants, showing high accuracy and structural feature identification.

PAH-former uses transfer learning with Geneformer to identify PAH-associated genes by fine-tuning on public PAH lung tissue data and performing in silico perturbation analysis.

This paper develops a deep learning model to estimate patient age and sex from chest X-rays, finding that CXR age correlates with cardiovascular aging and disease outcomes.