Diese Seite ist aus Gründen der Barrierefreiheit optimiert für aktuelle Browser. Sollten Sie einen älteren Browser verwenden, kann es zu Einschränkungen der Darstellung und Benutzbarkeit der Website kommen!
Home  |  Research DBS  |  Publications DBS  |  Team DBS  |  Institut  |  Fakultät  |  LMU

Dr. Markus Bundschus

Ludwig-Maximilians-Universität München
Lehr- und Forschungseinheit für Datenbanksysteme
Oettingenstr. 67
80538 München

Email: Please contact me via my LinkedIn profile!

  • 13.08.2014 We are partners in the Marie Curie Initial Training Network MLPM - Machine Learning for Personalized Medicine [Link]
  • 01.03.2011 Interested in doing a Ph.D. or Postdoc in collaboration with the industry? Please drop me a line with your CV!
  • 01.06.2010 I am now working for Roche. The best way to contact me is via LinkedIn (link see above).
  • 01.03.2010 We have released a new version of the Literature-derived Human Gene-Disease Network. [MORE INFORMATION]

I received my diploma degree in bioinformatics from the Ludwig-Maximilians-Universität München (LMU) and the TU München (TUM) in 2007. In June 2007 I started my Ph.D., which was supervised by Prof.Dr. Hans-Peter Kriegel and Prof.Dr. Volker Tresp (Siemens AG, Corporate Technology). In June 2010, I finished my Ph.D. and after a total of six years at Siemens (working student, diploma and Ph.D. student), it was time for a change. I am now working for Roche.

During my diploma thesis I had the great opportunity to get supervised by Dr. Kai Yu, who is now Director of the Multimedia Department at Baidu, Inc.. During my Ph.D. I was collaborating with Prof.Dr. Volker Tresp , Dr. Mathaeus Dejori (Director Data Science at Zynx Health), Dr. Shipeng Yu, and Holger Arndt, which was a lot of fun.

The scope of my Ph.D. thesis was within THESEUS, a research program initiated by the Federal Ministry of Economy and Technology (BMWi), with the goal of developing a new Internet-based infrastructure in order to better use and utilize the knowledge available on the Internet. In particular, I developed and applied machine learning algorithms for semantic annotation of text corpora. In addition, I participated in a use case scenario of THESEUS: Medico. Another research program, I participated in, was LarKC (Large Knowledge Collider), with international partners such as the WHO or Astra Zenca.

Research is a very exciting thing, but I am also quite interested in economics. Especially I am interested in how to build bridges between the industry and research, i.e. how to launch new technologies and companies. Even this can be seen as a kind of science. My favourite site dedicated to innovation is MIT's technology review .

  • Machine Learning
  • Data Mining
  • Information Retrieval
  • Bioinformatics
  • Semantic Web
  • Text Mining
  • Document Modeling
From time to time, I am acting as external reviewer for various conferences and journals:


  • Bioinformatics [LINK]
  • IEEE Transactions on Knowledge and Data Engineering (TKDE) [LINK]


  • SIGKDD Conference on Knowledge Discovery and Data Mining (KDD)[LINK]
  • International Conference on Machine Learning (ICML) [LINK]
  • European Conference on Machine Learning (ECML) [LINK]

The Universal Java Matrix Package (UJMP) is a Java library that provides implementatio ns for sparse and dense matrices, as well as a large number of calculations for linear algebra like multiply, add, subtract. But also more advanced methods like mean, correlat ion, standard deviation, replacement of missing values or mutual information are supported.

Matrices can be imported from and exported to a large number of file formats, also linking to JDBC databases is supported.

Because of time constraints I am not active here anymore, but from 2009-2012 I was part of the UJMP team. The head behind UJMP is Holger Arndt. Please have a look at our UJMP to learn more about the features provided with this package!

Please note: the list shown below might not be up-to-date. Please see also my Google scholar profile for the latest publications! [LINK]

Type of publication:

IT --- Invited talk
JOUR --- Journal paper
CONF --- Conference paper
BC --- Book chapter
WS --- Workshop paper
O --- Other

Markus Bundschus
Text and Data Mining in a Nutshell
European Commission, Brussels
Markus Bundschus
Analyzing Technology Landscapes & Emerging Trends in an Era of Information Revolution.
Guest Lecture for the LMU Executive Life Science MBA
Markus Bundschus, Manuel Dietrich, Dave Thorne, Steve Pettifer
Utopia Documents@Roche: text mining as enabler for next-generation PDF reading.
PDR special meeting on Text mining STM Content: New Perspectives, Emerging Solutions, [Link]
Daniel Eisinger, George Tsatsaronis, Markus Bundschus, Ulrich Wieneke, Michael Schroeder:
Automated Patent Categorization and Guided Patent Search using IPC as Inspired by MeSH and PubMed.
Journal of Biomedical Semantics Vol. 4, S1, S3 [LINK]
D. Eisinger, T. Waechter, M. Bundschus, U. Wieneke, M. Schroeder:
Analysis of MeSH and IPC as a Prerequisite for Guided Patent Search.
Bio-Ontologies 2012 [LINK]
Markus Bundschus, Martin Baron:
Biomarker Decision Support with Text Mining
PDR Special Meeting on Text Mining
Markus Bundschus:
Text Mining in the pharmaceutical industry: desire and reality.
AGMB conference 2011
Anna Bauer-Mehren, Markus Bundschus, Michael Rautschka, Miguel A. Mayer, Ferran Sanz, Laura I. Furlong.:
Gene-disease network analysis reveals functional modules in mendelian, complex and environmental diseases.
Bauer-Mehren A, Bundschus M , Rautschka M, Mayer MA, Sanz F, Furlong LI:
Combination of network topology and pathway analysis to reveal functional modules in human disease.
Poster presentation at the 9th European Conference on Computational Biology (ECCB 2010), Ghent Belgium.
M. Bundschus:
From Text to Knowledge: Bridging the Gap with Probabilistic Graphical Models.
Dissertation, LMU München: Fakultät für Mathematik, Informatik und Statistik. [Link]
M. Bundschus, A. Bauer-Mehren, V. Tresp, L. Furlong and H-P. Kriegel:
Digging for Knowledge with Information Extraction: A Case Study on Human Gene-Disease Associations.
In Proc. of the 19th ACM International Conference on Information and Knowledge Management (CIKM 2010), Toronto, Canada . [PDF]
Y. Huang, V. Tresp, M. Bundschus and A. Rettinger:
Multivariate Structured Prediction for Learning on the Semantic Web
In Proc. of the 20th International Conference on Inductive Logic Programming (ILP 2010), Florence, Italy. [PDF]
D. Magatti, F. Steinke, M. Bundschus and V. Tresp:
Combined Structured and Keyword-Based Search in Textually Enriched Entity-Relationship Graphs
In 1st Workshop on Automated Knowledge Base Construction (AKBC 2010), Grenoble, France (2010). [PDF]
M. Bundschus, V. Tresp and H-P. Kriegel:
Topic Models for Semantically Annotated Document Collections
In NIPS workshop: Applications for Topic Models: Text and Beyond (NIPS WS 2009), Vancouver, Canada (2009). [PDF]
M. Bundschus, Sh. Yu, V. Tresp, A. Rettinger, M. Dejori and H-P. Kriegel:
Hierarchical Bayesian Models for Collaborative Tagging Systems
In Proc. IEEE International Conference on Data Mining (ICDM 2009), Miami, USA (2009). [PDF]
Volker Tresp, Yi Huang, Markus Bundschus and Achim Rettinger:
Scalable Relational Learning for Sparse and Incomplete Domains.
In International Workshop on Statistical Relational Learning (SRL 2009). [PDF]
Volker Tresp, Yi Huang, Markus Bundschus and Achim Rettinger:
Materializing and Querying Learned Knowledge.
In ESWC Workshop on Inductive Reasoning and Machine Learning on the Semantic Web (IRMLES 2009). [PDF]
Holger Arndt, Markus Bundschus and Andreas Naegele:
Towards a Next-Generation Matrix Library for Java
33rd Annual IEEE International Computer Software and Applications Conference (COMPSAC 2009).
Fabian Moerchen, Mathaeus Dejori, Dmitriy Fradkin, Julien Etienne, Bernd Wachmann and Markus Bundschus:
Anticipating Annotations and Emerging Trends in Biomedical Literature.
In Proc. of the 14th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (SIGKDD 2008).
V. Tresp, M. Bundschus, A. Rettinger, Y. Huang:
Towards machine learning on the semantic web.
Book chapter in Uncertainty Reasoning for the Semantic Web, Lecture Notes in AI, Springer. Extended version: [PDF]
M. Bundschus, M.Dejori, Sh. Yu, V. Tresp and H-P. Kriegel:
Statistical modeling of medical indexing processes for biomedical knowledge information discovery from text.
In KDD Workshop on Data Mining in Bioinformatics (BIOKDD '08).
[Proc. from the BioKDD site] [PDF] [Supplementary Data]
M. Bundschus, M.Dejori, M. Stetter, V. Tresp and H-P. Kriegel:
Extraction of semantic biomedical relations from text using conditional random fields.
BMC Bioinformatics 2008, 9:207
M. Bundschus:
Entity - and relation extraction from biomedical text corpora.
Diploma Thesis 2006. [PDF]
M. Bundschus, S. Paradies, M. Siebert, F. Birzele, K. Fundel, R. Küffner, R. Zimmer:
Disease-relevant gene clusters derived by joint literature and gene expression analysis.,
Poster at the German Conference on Bioinformatics (GCB) 2005. [PDF]
Datenschutz   Impressum   WWW Archive