Open Positions

Support of applicants for the SNF Eccellenza Professorial Fellowship, the SNF PRIMA funding program and the ERC Starting Grant in the field of "Biomedical Modeling"

28.07.2020

The Department of Quantitative Biomedicine (DQBM) of the University of Zurich announces opportunities for applicants who seek to establish their own research group by obtaining independent third-party funding (SNF Eccellenza Professorial Fellowships, SNF PRIMA grant program and/or ERC Starting Grant Program (ERC-StG)). Successful candidates may be invited to negotiate an independent Assistant Professorship for a period of 5 years. To complement the independent external funding, the DQBM will provide laboratory facilities, administrative support and a first-class scientific environment.

The DQBM fosters research and education at the interface of biomedical research, biotechnology, and computational biology, to develop the foundations of next-generation precision medicine. The exploration of novel tools to extract knowledge from experimental quantitative data sets will accelerate the precision medicine revolution. For the forthcoming ERC/SNF application rounds, we particularly encourage proposals that match the following profile:

The Assistant Professorship will focus on the (multiscale) modeling of disease processes, using e.g. statistical interference methods, differential equations, neural network based methods or similar approaches, with the aim of conducting computer-assisted simulation experiments for the dynamic prediction of processes in multicellular systems. Such systems include, but are not limited to, immune systems, tumor micro-environments, neural circuits and microbiomes, taking into account spatial (3D) relationships. Further research interests could include system dynamics, perturbations, and evolution, such as evolutionary dynamics in chronic infections and tumor development, as well as prediction of complex emergent behavior resulting from multicomponent interactions, as seen in protein assembly and aggregation.

The Assistant Professorship is designed for a scientist with strong methodological expertise in the fields of Computer Science, Statistics, Mathematics or (Bio-) Physics, and excellent research experience in modeling quantitative systems data. Furthermore, the supported candidate is expected to have the ambition to establish a strong independent research group with an international profile, as well as the willingness to synergize with the current research groups at the DQBM. In addition to research activities, the Assistant Professorship will contribute to teaching in the quantitative biomedicine curriculum.

More information on the position and on how to apply can be found here

------------------------------------------------------------------------------------------------------------------

Postdoc Opening in Machine Learning in Biomedicine

28.07.2020

The University of Zurich together with the University Hospital of Zurich are embarking on a concerted effort to develop informatics programs to advance biomedical research using cutting edge computational approaches. As part of these efforts, the Krauthammer research group investigates topics in clinical data science and translational bioinformatics, such as knowledge discovery from Big Data sources (Electronic Medical Record), development of Natural Language processing, information retrieval and extraction routines, as well as the analysis of human Omics data. The group is headed by Prof. Michael Krauthammer and is part of the Department of Quantitative Biomedicine (DQBM).

For this position, we are looking for motivated PostDoc candidates who are interested in applying their computational skills to medical as well as biological problems. An example of Machine Learning (ML) in biology is our latest work on genome editing tools (base editors) for basic research and gene therapy. We developed BE-DICT 1, an attention-based deep learning algorithm capable of predicting base editing outcomes with high accuracy. 

An example of ML in healthcare is our work on time series analysis for patient readmission prediction. In this work 2, we explored the systematic application of neural network models for predicting 30 days all-cause readmission after discharge from a HF hospitalization.  And more recently, we are focused on the analysis of patient trajectories (i.e. using patients’ medical history) and “patient similarities” (i.e. patient similarity assessment on longitudinal health data) for care pathway/knowledge discovery, and personalized outcome prediction 3. Our goal is to develop state-of-the-art approaches and build best-in-class methods to capitalize on digital clinical information to automatically compare, analyze and visualize complex longitudinal patient journeys focusing on the concept of patient journey similarity. This involves building decision support systems powered by predictive algorithms for guiding patient therapy across all disease stages, the assessment of treatment effects using counterfactual inference and the identification of causal mechanisms driving disease progression.

  1. Marquart, K. F., Allam, A., et al. Predicting base editing outcomes with an attention-based deep learning algorithm trained on high-throughput target library screens. bioRxiv 2020.07.05.186544 (2020) doi:10.1101/2020.07.05.186544.
  2. Allam, A., Nagy, M., Thoma, G. & Krauthammer, M. Neural networks versus Logistic regression for 30 days all-cause readmission prediction. Sci. Rep. 9, 9277 (2019).
  3. Allam, A., Dittberner, M., Sintsova, A., Brodbeck, D. & Krauthammer, M. Patient Similarity Analysis with Longitudinal Health Data. (2020). http://arxiv.org/abs/2005.06630

 

Qualifications

  • PhD degree in computer science (focused on machine learning), optimization, statistics, applied math or closely related discipline.
  • Strong publication record with at least one first-author paper in top-tier conferences (such as NeurIPS, ICML , AISTATS, AAAI, ICLR, etc.)
  • Proficient in Python and the scientific computing stack (SciPy, Numpy, Scikit- learn, pandas)
  • Proficient in one of the deep learning frameworks (PyTorch, Tensorflow)

 

What we offer

We offer an interdisciplinary research environment, the possibility to direct your own research and access to state-of-the-art computational resources infrastructure.

  • Access to state-of-the-art infrastructure (computational resources), clinical datasets and medical expertise domain-knowledge (excellent medical doctors and research scientists)
  • Ability to make a real and tangible impact in healthcare research
  • Solve real-world problems and improve hospital-related processes and workflow
  • Stimulating research environment and a place to grow academically and professionally
  • Outstanding working conditions at the University of Zurich (more details here).


Please apply via Nature Careers

------------------------------------------------------------------------------------------------------------------

Postdoc Position with flexible starting date in the Polymenidou lab

13.02.2020

The Polymenidou lab has an open Postdoc position with flexible starting date.
Please send your application with CV, motivation letter and references to Magda and Julien.

-------------------------------------------------------------------------------------------------------------------

Computational Master Student Projects in the Krauthammer lab

20.12.2019

The Krauthammer lab is currently looking for Master’s students in the field of bioinformatics for the following topics:

  • Analyzing the effects of DNA secondary structure on the mutational pattern in cancer.
    The student will analyze the relationship between mutational patterns detected in various cancer types and the locations of non-B-DNA secondary structures in the human genome. The student should have basic experience with Unix systems and some experience with at least one scripting language (e.g. Python, R or bash). Prior experience with genomics software (mappers, samtools or variant callers) is an advantage.

  • Mapping structural variation in cancer.
    The student will use genome sequencing data in order to discover novel structural variants in various cancer types (melanoma, colorectal carcinoma, lung cancer, etc.). The clinical significance of the novel and already known structural variants will also be evaluated using genome annotations. The student should have basic experience with Unix systems and some experience with at least one scripting language (e.g. Python). Prior experience with genomics software (mappers, samtools or variant callers) is an advantage.

Applications can be done by sending a CV to this e-mail along with a short description of the student’s motivation to join our lab.

------------------------------------------------------------------------------------------------------------------

Master Student positions with flexible starting date in the Bodenmiller lab

The Bodenmiller lab is seeking to fill several Master Student positions, with flexible starting date. These projects are in the field of

  • Quantitative biology I: Simultaneous analysis of up to 100 markers in tumors using a new technology, called imaging mass cytometry [Link]
  • Quantitative biology II: Analysis of how tumor cells become metastatic
  • Computational biology: Computational analysis of signaling networks

Please send your CV and a few sentences why you would like to join our lab to Bernd Bodenmiller

------------------------------------------------------------------------------------------------------------------