Seminar by Dr. Carlo Vittorio Cannistraci

Biomedical Cybernetics Group, Technical University Dresden (Germany)

Machine learning and complex networks for complex systems big data analysis

The talk will present our research at the Biomedical Cybernetics Group that I established about four years ago in Technical University Dresden. We adopt a transdisciplinary approach integrating information theory, machine learning and network science to investigate the physics of adaptive complex systems at different scales, from molecules to ecosystems, with a particular attention to biology and medicine, and a new emerging interest for the analysis of complex big data in social and economic science. Our theoretical effort is to translate advanced mathematical paradigms typically adopted in theoretical physics (such as topology, network and manifold theory) to characterize many-body interactions in complex systems. We apply the theoretical frameworks we invent in the mission to develop computational tools for systems and network analysis. In particular, we deal with: prediction of wiring in networks and multiscale-combinatorial marker design for quantification of topological modifications in complex networks. Our attention for precision biomedicine is aimed to subjects with important impact from the economical point of view such as development of tools for disease biomarker discovery, drug repositioning and combinatorial drug therapy.
This talk will focus on two main theoretical innovation. Firstly, the development of machine learning for topological estimation of nonlinear relations in high-dimensional data¹ (or in complex networks²) and its relevance for applications in big data. The new topic of network embedding in the hyperbolic space will be also treated³, and the idea to develop quantitative markers in the latent geometry space - applicable, for instance, in brain network quantification of neurological disorders - will be introduced. Secondly, we will discuss the Local Community Paradigm (LCP)^4,5, which is a theory proposed to model local-topology-dependent link-growth in complex networks and therefore it is useful to devise topological methods for link prediction in monopartite and bipartite⁵ networks such as molecular drug-target interactions⁶ and product-consumer networks.

Biography
Carlo Vittorio Cannistraci is a theoretical engineer, head of the Biomedical Cybernetics Group and faculty member of the Department of Physics in the Technical University Dresden, which is a member of the TU9 excellence-league that consists of the nine most prestigious technical universities in Germany. Carlo’s area of research embraces information theory, machine learning and complex network theory including also applications in computational network science theory, systems biomedicine and network neuroscience. Nature Biotechnology selected Carlo’s article (Cell 2010)⁷ on machine learning in developmental biology to be nominated in the list of 2010 notable breakthroughs in computational biology. Circulation Research featured Carlo’s work (Circulation Research 2012)⁸ on leveraging a cardiovascular systems biology strategy to predict future outcomes in heart attacks, commenting: “a space-aged evaluation using computational biology”. In 2017, Springer-Nature scientific blog highlighted with an interview to Carlo its recent study on “How the brain handles pain through the lens of network science”⁹. The Technical University Dresden honoured Carlo of the Young Investigator Award 2016 in Physics for his recent work on the local-community-paradigm theory and link prediction in bipartite networks⁵.

References (* indicates first co-authorship)
1. Cannistraci, C. V., Ravasi, T., Montevecchi, F. M., Ideker, T. & Alessio, M. Nonlinear dimension reduction and clustering by minimum curvilinearity unfold neuropathic pain and tissue embryological classes. Bioinformatics 26, i531–i539 (2010).
2. Cannistraci, C. V., Alanis-Lobato, G. & Ravasi, T. Minimum curvilinearity to enhance topological prediction of protein interactions by network embedding. in Bioinformatics 29, (2013).
3. Muscoloni, A., Thomas, J. M., .., & Cannistraci, C. V. Machine learning meets complex networks via coalescent embedding of networks in the hyperbolic space. Nature Communication (2017).
4. Cannistraci, C. V., Alanis-Lobato, G. & Ravasi, T. From link-prediction in brain connectomes and protein interactomes to the local-community-paradigm in complex networks. Sci. Rep. 3, 1–13 (2013).
5. Daminelli, S., Thomas, J. M., Durán, C. & Vittorio Cannistraci, C. Common neighbours and the local-community-paradigm for topological link prediction in bipartite networks. New J. Phys. 17, 113037 (2015).
6. Duran, C., …, Cannistraci, C.V. Pioneering topological methods for network-based drug–target prediction by exploiting a brain-network self-organization theory. Briefings in Bioinformatics, bbx041 (2017).
7. Ravasi, T.*, Cannistraci C.V.*, et al. An atlas of combinatorial transcriptional regulation in mouse and man. Cell 140, (2010).
8. Ammirati, E.*, Cannistraci, C.V.*, et al. Identification and predictive value of interleukin-6+ interleukin-10+ and interleukin-6-interleukin-10+ cytokine patterns in st-elevation acute myocardial infarction. Circ. Res. 111, 1336–1348 (2012).
9. Narula, V., …, and Cannistraci, C.V. Can local-community-paradigm and epitopological learning enhance our understanding of how local brain connectivity is able to process, learn and memorize chronic pain? Applied Network Science 2 (1), 28