Skip to main content

Dr Nicos Angelopoulos

Lecturer in Computational Systems Immunity

School of Medicine


I am a computer scientist working on computational and statistical aspects of 
bio data analytics. I use knowledge representation methods and tools in machine
learning as well as in building practical, well engineered scientific code.

Currently a lecturer in Computational Systems Immunity at
Cardiff University's Systems Immunity Research Institute, working in close
collaboration with the sepsis group.

Previously I worked on (a) methodological projects in Markov chain Monte Carlo simulations
for Bayesian machine learning over priors defined with probabilistic logic programs
(Bims, University of York), (b) mass spectormetry functional data analytics (Imperial College)
and (c) genomic models of cancer evolution and cancer precision medicine (Sanger Institute).

I am staunch proponent of open source software, both in the systems I use in my 
research (SWI-Prolog, Linux, R, Latex) and in publishing open source code with all my 
papers (github page).


Since my PhD I worked as a researcher on a number of projects in the UK and the Netherlands.
The last few years my research has focused on the development and application of principled
formalisms that combine logic and probability along with associated stochastic algorithms in computational biology. 

Previously I worked in a number of research positions, including

  • senior staff scientist in applied statistics at the Sanger Institute's Cancer Genome Project (now CASM)
  • research fellow at University of York where I worked with James Cussens

Academic positions

July 2020 Joined Medical School at Cardiff University

2019-20 Lecturer in AI and Computational Biology - Essex University

              School of Computer Science and Electronic Engineering

2015-18 Senior Staff Scientist in Applied Statistics - Sanger Institute

              Cancer and Somatic Mutations Section

2014-15 Researcher in proteomics data analytics - Imperial College

              Cancer Signalling group

2010 - 13 Researcher in Computational Cancer Biology - Netherlands Cancer Institute

              Compuational biology group

2009  Senior Scientific officer - Institute of Cancer Research, London

             Computational cancer biology group.

2006-8 Research in Computational statistics - Edinburgh University

            Systems bio-physics group.

2003-5 Research in Bayesian machine learnin - University of York

            James Cussens' group.

Committees and reviewing

Senior PC member IJCAI 2021 (International Joint Conference on AI)

Workshop chair ICLP 2001 (International Conference of Logic Programming)

PC member

  • IJCAI 2021 (Senior)
  • ICLP 2020
  • CMSB 2020 (Comp. Meth in Sys Bio)
  • CBMS 2020 (33rd Int. Symp. on Comp. Based Med. Sys)
  • CP 2017 (Bioinformatics Track)
  • IJCAI 2015
  • Ciclops 2013ProBioMed 2011 (Probabilistic problem solving in biomedicine),
  • MLG 2008 + 2009 (Machine Learning with Graphs).

Review Editor Computational Intelligence section of Frontiers in Robotics & AI, (2014-2020)


  • Expert Systems With Applications 2020
  • Machine Learning 2019 (ILP special issue)
  • BMC Genomics 2019
  • AI Reviews, 2017
  • Theory and Practice of Logic Programming, 2018
  • Project reviewer for FWO (Belgian research council), 2016
  • J. of Molecular Modelling, 2010-2020
  • Bioinformatics, 2012, 2017-8
  • Machine Learning J., 2009
  • ECML, 2004

Workshop series initiator: PLP Series, 2014-20, workshop on Probabilistic Logic Programming












I have conducted my research at prestigious UK and Dutch universities and institutes.
My area of expertise lies in the intersection of machine learning, 
artificial intelligence and computational biology.
I am interested in theories that can model uncertainty and
have strong foundations in probability theory along with computational systems
that can reason with and learn such complex models from large data sets.

  •  during 2000-2010 I worked closely with James Cussens in York
       in developing an elegant Probabilistic Logic Programming language
       for Bayesian machine learning Bims. We published a number of papers 
       on theoretical aspects of the approach in high profile computer science conferences
       such as UAI and IJCAI as well as on the application to specific datasets.
  •   since 2011 I have been working in computational biology using AI techniques.
       I have pursued open source and open data research throughout my career, having published open source
       analysis methods and tools with the vast majority of my papers.
       My work in computational biology includes theoretical work blending knowledge and inference with logical 
       and probabilistic foundations. My work also encompasses applied tools such as Real, which provides a
       powerful bridge to the R statistical programming environment.  
  •   while at Sanger, I worked on high quality clinical and mutational datasets including survival analysis,  precision            oncology and cancer evolution based on mutational patterns in diverse cancers including hematological and solid tumour cancers. I was fortunate to work on a number papers, and substantially contributed to 3 substantial papers: 
    1.    GrinfeldJ+2018 (NEJM):  precision oncology in myeloproliferative neoplasm
    2.    MitchellTJ+2018 (Cell): statistical inference of landmark events in clear cell renal cell cancer
    3.   MauraF+2019 (Nat Coms):     Bayesian networks for cancer epistasis in multiple myeloma