David Heise

The paper introduces a transformer-based language model to identify computable phenotype definitions in biomedical literature and integrates it into a platform for literature curation.

Population-stratified GWAS of 2,068 traits in 635,969 Million Veteran Program participants, 29% genetically non-European, yields 98,485 associations and 57,601 fine-mapped signals with largely shared cross-population architecture.