Peter T. Simpson

This paper integrates multiple foundation models to improve gene prediction in histopathology images, achieving better accuracy for breast cancer subtypes and drug-target genes.

STimage predicts gene expression and classifies cell types from histopathological images, improving robustness and interpretability for cancer and disease analysis.

This paper integrates tumor homologous recombination deficiency status with germline BRCA1 and BRCA2 variant classification to improve pathogenicity prediction.

The paper identifies breast cancer risk variants associated with tumor subtypes and shows their differential effects on luminal and non-luminal subtypes.

This paper introduces qCNV and sCNA-seq tools to profile somatic copy number alterations in cell-free DNA without a reference panel, showing effectiveness in detecting clinically relevant mutations from plasma samples.