Research

The main research topics of Anacleto Lab can be summarized as follows:

Machine Learning for Personalized Medicine

• Detection of pathogenic variants in the non coding human genome

Gene function prediction

• Hierarchical ensembles of learning machines for gene function prediction
• Cost-sensitive and parametrized Hopfield Networks for gene function prediction
• Network-based gene function prediction through kernelized score functions

Drug repositioning and drug-target prediction

• Drug ranking and repositioning through network projections and kernelized score functions

Disease gene prioritization

• Disease gene prioritization through semi-supervised transductive methods

Unsupervised search for patterns in biomolecular data

• Stability-based methods for the assessment of the reliability of clusters discovered in complex bio-molecular data
• Ensemble clustering methods for the analysis of patterns in bio-molecular data

Integration of multiple sources of bio-molecular data

• Network combination algorithms for the massive integration of omics data
• Supervised ensemble methods for biomolecular data integration

Phenotype/outcome prediction and biomarker selection

• Network-based semi-supervised methods for phenotype/outcome prediction and biomarker selection

Big data analysis in computational biology

• Scalable vertex centric algorithms based on data base technology

Computational biology software tools