Dr Simon Kocbek is a computer scientist with several years of research and software engineering experience. Prior to joining Garvan, Simon held various research positions and was a recipient of internationally competitive fellowships.
Simon’s main research interest is in how data can be understood and used by computers to improve quality of life. He has spent most of his time applying and improving supervised machine learning algorithms to datasets in areas of health, medicine and biological research. He has a great interest in text mining and technologies like semantic web and ontologies. He has been a program committee member for prestigious Natural Language Processing (NLP) conferences such as ACL 2017 and EMNLP 2017.
Recently, Simon has been focusing on automatically classifying patients based on hospital admission data and applying topic modelling techniques to clinical text. Currently, he works on NLP problems within phenotype analytics stack. Any prospective students interested in these areas are welcome to get in touch.
Awards and Honours
2008-2009 - National Institute for International Education (NIIED) Research Fellowship Award, Korean Government
2006-2011 - Junior Researcher grant, Slovenian Government
2008 - Travel Support Award (Pattern Recognition in Bioinformatics 2008)
1999-2006 - Under graduate scholarship, Slovenian Government
2006 - BSc (Computer Science), University of Maribor - Slovenia
Simon Kocbek, Tudor Groza, "Extracting Disease-Phenotype Relations from Text with Disease-Phenotype Concept Recognisers and Association Rule Mining", Computer-Based Medical Systems (CBMS), IEEE 30th International Symposium on, 2017.
Simon Kocbek, Jin-Dong Kim, "Exploring biomedical ontology mappings with graph theory methods", PeerJ, 2017.
Simon Kocbek, Lawrence Cavedon, David Martinez, Christopher Bain, Chris Mac Manus, Gholamreza Haffari, Ingrid Zukerman, Karin Verspoor, "Text mining electronic hospital records to automatically classify admissions against disease: Measuring the impact of linking data sources", Journal of Biomedical Informatics, Volume 64, 158–167, doi: 10.1016/j.jbi.2016.10.008, 2016.
Toshiaki Katayama Email author, Mark D Wilkinson, Kiyoko F Aoki-Kinoshita, Shuichi Kawashima, Yasunori Yamamoto, Atsuko Yamaguchi, Shinobu Okamoto, Shin Kawano, Jin-Dong Kim, Yue Wang, Hongyan Wu, Yoshinobu Kano, Hiromasa Ono, Hidemasa Bono, Simon Kocbek, et al., "BioHackathon series in 2011 and 2012: penetration of ontology and linked data in life science domains." Journal of Biomedical Semantics 5, no. 1, 1-13, 2014.
Gregor Stiglic, Simon Kocbek, Igor Pernek, Peter Kokol, "Comprehensive Decision Tree Models in Bioinformatics", PLoS ONE, 7(3), 2012.
Simon Kocbek, Rune Sætre, Gregor Stiglic, Jin-dong Kim, Igor Pernek, Yoshimasa Tsuru-oka, Peter Kokol, Sophia Ananiadou, Jun’chi Tsujii, “AGRA: Analysis of Gene Ranking Algorithms”, Bioinformatics, 27(8), 1185-1186, 2011.