Guido Sanguinetti


Research and PhD projects
Teaching
CV & Publications
Software Downloads
People
Other Interests

School of Informatics
Informatics Forum
10 Crichton Street
Edinburgh
EH8 9AB
Tel: +44 131 650 5136
Fax: +44 131 651 1426

email: G.Sanguinetti@ed.ac.uk

 


Welcome

I am a Reader in Machine Learning in the Institute for Adaptive and Neural Computation at the School of Informatics, University of Edinburgh. My interests focus on probabilistic modelling of biological systems, with particular emphasis on inference in dynamical systems. For more details of my research interests, including live projects and possible PhD projects, please see the research projects page. I'm also a potential supervisor on the newly funded EPSRC Centre for Doctoral Training in Data Science, see Data Science Ph.D. programme.


News

Some newly published papers

David Schnoerr, Guido Sanguinetti and Ramon Grima, The Complex Chemical Langevin Equation, Journal of Chemical Physics, in press, 2014.

Ezio Bartocci, Luca Bortolussi and Guido Sanguinetti, Data-driven Statistical Learning of Temporal Logic Properties, FORMATS 2014

Luca Bortolussi and Guido Sanguinetti, A statistical approach for computing reachability of non-linear and stochastic dynamical systems, QEST 2014

Anastasis Georgoulas, Jane Hillston and Guido Sanguinetti, Probabilistic Programming Process Algebra, QEST 2014

Gabriele Schweikert, Botond Cseke, Thomas Clouaire, Adrian Bird and Guido Sanguinetti, MMDiff: quantitative testing for shape changes in ChIP-Seq data sets, BMC Genomics 14:826, 2013, link

Botond Cseke, Manfred Opper and Guido Sanguinetti, Approximate Inference in Latent Diffusion Processes from Continuous Time Observations, to appear at NIPS 2013 camera-ready version and supplementary material

Luca Bortolussi and Guido Sanguinetti, Learning and designing stochastic processes from logical constraints, in Quantitative Evaluation of Systems (QEST) 13 pdf

Andrea Ocone, Andrew J. Millar and Guido Sanguinetti, Hybrid Regulatory Models: a statistically tractable approach to model regulatory network dynamics, Bioinformatics 29(7) (2013) journal link

Botond gets spotlight at NIPS!

Botond's paper "Approximate Inference in Latent Diffusion Processes from Continuous Time Observation" (joint with Manfred Opper and myself) is going to have a spotlight presentation at NIPS13. Only approx. 5% of submissions get spotlights, so very well done Botond!

Best paper award at QEST13

Luca Bortolussi's and my paper "Learning and designing stochastic processes from logical constraints" has been awarded the Best Paper Award at QEST13 (see press release by the University of Trieste here, in Italian). From my point of view, the interest of the paper is the attempt to perform learning directly from emerging properties of a stochastic process (in this sense, it is closely related to Botond's NIPS paper, item above).

Cozzarelli Prize 2012

Our PNAS paper "Point process Modelling of the Afghan War Diary" was awarded a Cozzarelli prize by the PNAS editorial board, an annual award to outstanding papers in the six main branches of the PNAS scope. Our paper won in the Engineering and Applied Science category. More details here

Andrew Zammit-Mangion wins IET Doctoral Prize in Control and Automation

Congratulations to Andrew, whom until recently worked with us as a postdoc and whose PhD was jointly supervised by Visakan Kadirkamanathan at Sheffield and myself. The IET Prize is a prestigious award for doctoral students at UK Universities, and deservedly acknowledges Andrew's great work during his doctorate. Well done Andrew!

ERC Starting Grant

I have been awarded an ERC Starting Independent Research Grant to investigate how machine learning techniques can be married with formal model descriptions of biological systems. This large project will run to 2017 and buy me out of teaching, as well as funding RAs and studentships. The official ads can be found here (postdoc) and here (studentship). If you are interested and would like some more info, do get in touch with me.

Arrivals and departures in the lab

Van Anh Huynh-Thu recently joined us to work on my ERC project from the University of Liege, where she worked on network reconstruction with Pierre Geurts and Louis Wehenkel.

David Schnoerr joined us and Ramon Grima's lab as a PhD student, after a theoretical physics degree in Heidelberg on renormalisation group techniques.

Daniel Trejo Banos arrived in February 2012 from the Universitad Nacional Autonoma de Mexico to pursue a PhD in computational systems biology. He will be looking to develop bioinformatics and machine learning methods to model plant oscillators.

Andrea Ocone submitted his thesis and is off to work in the Helmholtz Zentrum in Munich as a post doc with Fabian Theis.