Chantriolnt-Andreas Kapourani

I am a PhD student in the IANC, School of Informatics, University of Edinburgh, supervised by Dr. Guido Sanguinetti.

I am interested in take a data science approach by proposing statistical models to understand (single-cell) epigenetic heterogeneity and uncover the interplay between genetic and epigenetic mechanisms in transcriptional regulation using high-throughput sequencing data. Also, I am interested in probabilistic integrative models for combining multimodal biological data, such as expression, methylation and accessibility.

Short Bio


MSc by Research in Data Science, University of Edinburgh.

Grade 82/100, with Distinction.

MSc in Artificial Intelligence, University of Edinburgh.

Grade 74/100, with Distinction.

BSc in Informatics and Telematics, Harokopio Univerisity of Athens.

Grade 9.1/10, with Distinction.


Teaching Assistant, Univeristy of Edinburgh

Junior Developer, DaXtra Technologies

DaXtra Technologies is a specialist company in high accuracy, multilingual CV/Resume and job parsing, as well as semantic search, matching and aggregation technologies.



Clark, S.J., Argelaguet, R., Kapourani, C.A., Stubbs, T.M., Lee, H.J., Alda-Catalinas, C., Krueger, F., Sanguinetti, G., Kelsey, G., Marioni, J.C., Stegle, O. and Reik, W., 2018. scNMT-seq enables joint profiling of chromatin accessibility DNA methylation and transcription in single cells. Nature communications, 9(1), p.781.

Kapourani, C.A. and Sanguinetti, G. (2016). Higher order methylation features for clustering and prediction in epigenomic studies. Bioinformatics, 32(17), i405-i412. (Best Paper Award in ECCB 2016).

Hatzi, O., Meletakis, G., Katsivelis, P., Kapouranis, A., Nikolaidou, M. and Anagnostopoulos, D. (2014). Extending the Social Network Interaction Model to Facilitate Collaboration through Service Provision. In Enterprise, Business-Process and Information Systems Modeling (pp. 94-108). Springer Berlin Heidelberg.

Talks & Posters

Kapourani, C.A. and Sanguinetti, G., 2017. Bayesian hierarchical modelling of single-cell methylation profiles. ISMB 2018 Prague, Czech Republic and Workshop on Statistical Challenges in Single-Cell Biology, Ascona, Switzerland.

Kapourani, C.A. and Sanguinetti, G., 2016. Higher order methylation features for clustering and prediction in epigenomic studies. 15th European Conference on Computational Biology (ECCB). The Hague, Netherlands.
slides poster

Kapourani, C.A. and Sanguinetti, G., 2016. Bayesian integrative clustering of heterogeneous types of high-throughput sequencing data. 10th International Workshop on Machine Learning in Systems Biology (MLSB). The Hague, Netherlands.

Kapourani, C.A. and Sanguinetti, G. (2016). Modelling methylation profiles. 10th Edinburgh Bioinformatics Meeting, IGMM, University of Edinburgh.

Kapourani, C.A. and Sanguinetti, G. (2015). Mixture Modelling of DNA Methylation Profiles. Workshop in Statistical Modeling of Epigenomics and Gene Regulation. Harvard University.

Theses & Projects

Kapourani, C.A. (2015). Mixture Modelling of High-Throughput Biomedical Data. MSc by Research Thesis, Centre for Doctoral Training in Data Science, University of Edinburgh.

Kapourani, C.A. (2013). Unsupervised Motif Discovery from Acoustic Time Series Data. MSc in Artificial Intelligence Thesis. University of Edinburgh.

Kapourani, C.A. (2012). Integration of external applications in the Unity academic social networking environment. BSc in Informatics Thesis. Harokopio University of Athens.

Kapourani, C.A., Marin, A.M. and Cervera, J.J.G. (2011). Find Friend Location, Distributed real-time location tracking system for Android provided by SOAP Web Services.Erasmus Student project. Roskilde University.


The following links contain simple tutorials I have been writing during my PhD studies. To better understand each topic, the tutorials contain a mix of theory and source code implementation.

Bayesian Binary Probit Model (R)

Bayesian Binomial Probit Regression (BPR) Model (R)

Beta-Binomial model for overdispresion (R)

Variational inference on Gaussian Mixture Model (R)

Variational Bayesian Linear Regression Model (R)

Variational Bayesian Probit Regression Model (R)

Variational Mixture of Bayesian Linear Regression Models (R)

Variational Mixture of Bayesian Probit Regression Models (R)