Computational Biology and Biostatistics
Faculty: Annalisa Barla, Alessandro Verri
Description: Our goal is to study and develop computational methods and models for the understanding of biological processes. The starting point is often derived from our work in learning theory and algorithms with particular emphasis on the problems related to the role played by prior knowledge and the integration of data coming from different sources and contexts.
Common trait of our efforts is a close collaboration with molecular biologists, geneticists, or clinicians interested in specific questions.
The main topics of our research are:
- Knowledge Driven Variable Selection (KDVS) - a new approach to enrichment analysis of gene signatures obtained from high-throughput data, Grzegorz Zycinski, Annalisa Barla, Margherita Squillario, Tiziana Sanavia, Barbara Di Camillo, Alessandro Verri, Source Code for Biology and Medicine, 2013
- A Machine Learning Pipeline For Discriminant Pathways Identification, Annalisa Barla, Giuseppe Jurman, Roberto Visintainer, Margherita Squillario, Michele Filosi, Samantha Riccadonna, Cesare Furlanello, LNCS/LNBI, 2012
- A procedure for functional characterization of potential biomarkers from heterogeneous molecular data: Alzheimer's as a case study, Margherita Squillario, Annalisa Barla, BMC Medical Genomics, 2011
- The l1-l2 regularization framework unmasks the hypoxia signature hidden in the transcriptome of a set of heterogeneous neuroblastoma cell lines, P. Fardin, Annalisa Barla, Sofia Mosci, Lorenzo Rosasco, Alessandro Verri, L. Varesio, BMC Genomics, 2009
- A method for robust variable selection with significance assessment, Annalisa Barla, Sofia Mosci, Lorenzo Rosasco, Alessandro Verri, Proceedings ESANN 2008, 2008