piwik-script

Center for Computational and Theoretical Biology

BioMedical Data Science

Through technological advances (e.g. DNA sequencing, new imaging technologies, ...) the life sciences have turned into a data heavy science. There is huge potential to discover novel insights and address big challenges of our society using these data.

Our research focuses on development and application of (bio)informatic methods and tools to gain insights from complex data sources. We apply these methods in two main areas: Molecular Ecology and Medical Imaging. At first glance, these topics seem to have nothing in common. But in both these fields large amounts of diverse data (images, text, DNA, quantitative measurements, ...) are available and we are not yet able to take full advantage of this rich pile of information. In both fields there are two major challenges:

  • Every data type only holds a fraction of the available information (like pieces of a puzzle). It is necessary to properly combine all data sources to gain new insights that can be used to recommend actions or improve diagnoses and therapies. Thus, one key research area of our group is multimodal methods.
  • In both fields, there is a so-called implementation gap. That means, that new methods (like machine learning and artificial intelligence) have been shown to have impressive performance but are still not used in practice. Reasons for this gap include a lack in explainability and interpretability of how these black-box models work. Further concerns are an apparent lack of generalizability, transparency and fairness. Thus, the focus of our group is on bridging this gap.

Projects

Thesis projects

Join our group for an internship, or for your Bachelor or Master thesis.

Some projects we currently offer:

  • Improving misas, a software tool developed in our group. It is used for analyzing the sensitivity of machine learning models to perturbations of the input. Depending on your interest your project can be more technical (e.g. coding new features) or more applied (e.g. applying misas to new data sets).
  • Combine imaging and genomics: find genomic associations through refined cardiac imaging phenotypes using the UK Biobank data.
  • Pulmonary Artery Segmentation Challenge. For this challenge we develop our own method and compare the performance to other groups.
  • Develop a VR app to interactively explore deep learning models working on cardiac magnetic resonance images. In collaboration with Annika Kreikenbohm.
  • If you have an idea that fits the research of our group, we are very happy to discuss it.

Are you fascinated by the possibilities of modern computational methods like machine learning and artificial intelligence? Do you want to develop and apply these methods to get insights from biological or medical data? Then join our team to train and apply your skills on an interesting project in the field of BioMedical Data Science.

As long as you are motivated and willing to learn, prior knowledge is not required.

Get in touch with Markus Ankenbrand to learn more.

 

 

Publications

[ 2022 ] [ 2021 ] [ 2020 ] [ 2019 ] [ 2017 ]

2022 [ nach oben ]

  • In Vitro Rearing Changes Social Task Performance and Physiology in Honeybees. Schilcher, Felix; Hilsmann, Lioba; Rauscher, Lisa; Değirmenci, Laura; Krischke, Markus; Krischke, Beate; Ankenbrand, Markus; Rutschmann, Benjamin; Mueller, Martin J.; Steffan-Dewenter, Ingolf; Scheiner, Ricarda in Insects (2022). 13(1)
     
  • A data-driven semantic segmentation model for direct cardiac functional analysis based on undersampled radial MR cine series. Wech, Tobias; Ankenbrand, Markus Johannes; Bley, Thorsten Alexander; Heidenreich, Julius Frederik in Magnetic Resonance in Medicine (2022). 87(2) 972–983.
     

2021 [ nach oben ]

  • Sensitivity analysis for interpretation of machine learning based segmentation models in cardiac MRI. Ankenbrand, Markus J.; Shainberg, Liliia; Hock, Michael; Lohr, David; Schreiber, Laura M. in BMC Medical Imaging (2021). 21(1) 27.
     
  • Self-configuring nnU-net pipeline enables fully automatic infarct segmentation in late enhancement MRI after myocardial infarction. Heidenreich, Julius F.; Gassenmaier, Tobias; Ankenbrand, Markus J.; Bley, Thorsten A.; Wech, Tobias in European Journal of Radiology (2021). 141 109817.
     
  • Open Science principles for accelerating trait-based science across the Tree of Life. Gallagher, Rachael; Falster, Daniel S.; Maitner, Brian; Enquist, Brian; Ankenbrand, Markus; Balk, Meghan; Bland, Lucie; Boyle, Brad; Bravo, Catherine; Cavazos, Brittany; Fadrique, Belen; Feng, Xiao; Halbritter, Aud; Hammock, Jennifer; Hogan, James Aaron; Iversen, Colleen; Jochum, Malte; Kattge, Jens; Keller, Alexander; Madin, Joshua; Manning, Peter; McCormack, Luke; Michaletz, Sean; Park, Daniel; Pearse, William; Penone, Caterina; Perez, Timothy; Pineda-Munoz, Silvia; Poelen, Joritt; Ray, Courtenay; Salguero-Gomez, Roberto; Sauquet, Herve; Schneider, Florian; Spasojevic, Marko J.; Vandvik, Vigdis; Violle, Cyrille; Weiss, Katherine in Nature Ecology & Evolution (2021). 294–303.
     
  • On the way to routine cardiac MRI at 7 Tesla - a pilot study on consecutive 84 examinations. Reiter, Theresa; Lohr, David; Hock, Michael; Ankenbrand, Markus Johannes; Stefanescu, Maria Roxana; Kosmala, Aleksander; Kaspar, Mathias; Juchem, Christoph; Terekhov, Maxim; Schreiber, Laura Maria in PLOS ONE (2021). 16(7) 1–18.
     
  • Deep learning-based cardiac cine segmentation: Transfer learning application to 7T ultrahigh-field MRI. Ankenbrand, Markus Johannes; Lohr, David; Schlötelburg, Wiebke; Reiter, Theresa; Wech, Tobias; Schreiber, Laura Maria in Magnetic Resonance in Medicine (2021). 86(4) 2179–2191.
     
  • Dealing with software complexity in individual-based models. Vedder, Daniel; Ankenbrand, Markus; Cabral, Juliano in Methods in Ecology and Evolution (2021). 12 2324–2333.
     
  • B0 shimming of the human heart at 7T. Hock, Michael; Terekhov, Maxim; Stefanescu, Maria Roxana; Lohr, David; Herz, Stefan; Reiter, Theresa; Ankenbrand, Markus; Kosmala, Aleksander; Gassenmaier, Tobias; Juchem, Christoph; Schreiber, Laura Maria in Magnetic Resonance in Medicine (2021). 85(1) 182–196.
     

2020 [ nach oben ]

  • Genomes of the Venus Flytrap and Close Relatives Unveil the Roots of Plant Carnivory. Palfalvi, G.; Hackl, T.; Terhoeven, N.; Shibata, T. F.; Nishiyama, T.; Ankenbrand, M.; Becker, D.; Förster, F.; Freund, M.; Iosip, A.; Kreuzer, I.; Saul, F.; Kamida, C.; Fukushima, K.; Shigenobu, S.; Tamada, Y.; Adamec, L.; Hoshi, Y.; Ueda, K.; Winkelmann, T.; Fuchs, J.; Schubert, I.; Schwacke, R.; Al-Rasheid, K.; Schultz, J.; Hasebe, M.; Hedrich, R. in Current Biology (2020). 30(12) 2312–2320.
     
  • Exploring Ensemble Applications for Multi-sequence Myocardial Pathology Segmentation. Ankenbrand, Markus J.; Lohr, David; Schreiber, Laura M. X. Zhuang, L. Li (reds.) (2020). 60–67.
     
  • Chronic exposure to the pesticide flupyradifurone can lead to premature onset of foraging in honeybees (Apis mellifera). Hesselbach, Hannah; Seeger, Johannes; Schilcher, Felix; Ankenbrand, Markus; Scheiner, Ricarda in Journal of Applied Ecology (2020). 57 609–618.
     
  • BCdatabaser: on-the-fly reference database creation for DNA (meta-)barcoding. Keller, Alexander; Hohlfeld, Sonja; Kolter, Andreas; Schultz, Jörg; Gemeinholzer, Birgit; Ankenbrand, Markus J. in Bioinformatics (2020). 36(8) 2630–2631.
     
  • A systematic comparison of chloroplast genome assembly tools. Freudenthal, Jan A.; Pfaff, Simon; Terhoeven, Niklas; Korte, Arthur; Ankenbrand, Markus J.; Förster, Frank in Genome Biology (2020). 21(1) 254.
     

2019 [ nach oben ]

  • Linking pollen foraging of megachilid bees to their nest bacterial microbiota. Voulgari-Kokota, Anna; Ankenbrand, Markus; Grimmer, Gudrun; Steffan-Dewenter, Ingolf; Keller, Alexander in Ecology and Evolution (2019). 9(18) 10788–10800.
     

2017 [ nach oben ]

  • AliTV - interactive visualization of whole genome comparisons. Ankenbrand, Markus J.; Hohlfeld, Sonja; Hackl, Thomas; Förster, Frank in PeerJ Comput. Sci. (2017). 3 e116.