Ino de Bruijn

MetaHarmonizer improves metadata harmonization and addresses LLM contamination in biomedical data, outperforming existing methods on benchmark tasks.

The paper develops Mosaic, a machine learning system that classifies tumors into detailed subtypes and identifies molecular phenotypes using histopathologic and genomic data from a large patient cohort.

MutationAssessor version 4 provides updated functional impact scores for mutations using expanded data and improved analysis methods, now integrated into cBioPortal.

This study introduces tumor break load (TBL) as a measure of genomic instability across cancers, showing its association with gene expression changes and clinical outcomes.

The paper describes how the Human Tumor Atlas Network shares data through standards, infrastructure, and community engagement, making datasets accessible via multiple platforms.

This study uses spatial profiling to show immune suppression and microenvironment changes in fallopian tube precursors of high-grade serous ovarian cancer.

The paper identifies a subset of mismatch repair proficient colorectal cancers with high immune infiltration that may benefit from immune checkpoint inhibitors, using spatial profiling and genomics.

This study presents a paired tumor:normal sequencing dataset for hematologic malignancies, showing improved identification of somatic variants and their clinical relevance.