Leiden University Medical Center

Self-supervised colorectal histopathology model turning H&E tiles into interpretable phenotype clusters and a disease-free survival risk score.

Physics-informed graph neural network predicting metabolite concentrations from gene expression, generalizing zero-shot to unseen metabolites.

Natural product chemistry prediction from biosynthetic gene clusters, assigning ChemOnt ontology classes from the cluster's Pfam domain composition.

RNA language model classifying transcripts as coding or long non-coding, using convolutional sequence encoding to fit whole transcripts in context.