Classification and pattern discovery in complex biological data

Supervised and Unsupervised Machine Learning methods can detect biomarkers and discover patterns in complex biomolecular data and can help decipher mechanisms underlying biological processes. Moreover Machine Learning can generate predictive models for key applications both in fundamental Molecular Biology and Medicine.

Research areas

Our research in this area can be summarized as follows:

• Hierarchical Ensembles for the structured prediction of protein functions and abnormal human phenotypes
• Supervised Machine Learning for biomolecular data integration, biomarker discovery and support to diagnosis and prognosis
• Unsupervised analysis for patient stratification and pattern discovery in complex biomolecular data
• Lung Nodule Detection from PA Chest Radiographs
• Organ segmentation from abdominal CT scans
• (Immuno-)histochemical image analysis