Graham J. Mann

This paper identifies 116 risk loci for melanoma through GWAS, links susceptibility to immunity and Wnt signaling, and develops a PRS improving risk prediction.

This paper maps mutation-defined cancer vulnerabilities across 22 cohorts, identifying OXPHOS addiction in CDKN2A-loss LUSC and highlighting drug repurposing opportunities using a machine learning framework.

ProCanFDL uses federated deep learning to subtype cancers using proteomic data while preserving privacy, achieving performance gains over local models.

This study profiles genomic structural variation in Indigenous Australians using whole genome long-read sequencing, revealing abundant and previously unannotated variants and unique STR diversity.

The paper introduces a method to handle omics data variation across platforms and times, showing its use in three disease risk models for clinical application.

SurvBenchmark evaluates survival analysis methods on clinical and omics data, showing model performance varies with metrics and datasets.

This paper identifies novel pleiotropic risk loci for melanoma and nevus density, implicating multiple biological pathways and gene expression under MITF regulation.