Dr Nicos Angelopoulos

Nicos is a computer scientist working on computational and statistical aspects of bio data analytics. He works with classical AI knowledge representation methods and tools in machine learning as well as with practical, well-engineered scientific code.

Currently a group leader in Computational Biology at Pirbright, he works closely with biologists in the Institute on all computational and statistical aspects of generated datasets. He promotes good practice across the whole spectrum of scientific computing, from good data management to complex theoretical methods for machine learning in the presence of existing knowledge.

His theoretical interests lie in the intersection of machine learning, artificial intelligence and computational biology. He is 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.

He has conducted research at prestigious UK and Dutch universities and institutes. His work to date spans a variety of different areas including (a) methodological projects computational statistics for Bayesian machine learning over priors defined with probabilistic logic programs (Bims, University of York), (b) mass spectrometry functional data analytics (Imperial College) and (c) genomic models of cancer evolution and cancer precision medicine (Sanger Institute).

He is a staunch proponent of open source software, both in the systems he uses in research (SWI-Prolog, Linux, R, Latex) and in publishing open source code with all his published papers (available on GitHub).