Postdoc position: single-cell regulatory genomics of tumor heterogeneity

Leuven VIB-KU Leuven Center for Brain & Disease Research

23 Apr 2022

Leuven

VIB-KU Leuven Center for Brain & Disease Research

Stein Aerts Lab

Post-doctoral

1

Description

The VIB-KU Leuven Center for Brain & Disease Research is part of the VIB Life Sciences Institute and is embedded within the University of Leuven, which ranks among the world’s top 50 universities. At our Center, more than 300 researchers study the basic mechanisms of the central nervous system and related diseases.

The Laboratory of Computational Biology (www.aertslab.org) is looking for a postdoc to decipher gene regulatory networks in cancer, using a combination of single-cell ATAC-seq, single-cell RNA-seq, and spatial transcriptomics. Central to this work will be the use of deep learning, to decipher the regulatory code of enhancers, and to identify regulatory programs that are shared across cancer types. In the next step, we aim to connect gene regulatory networks between cancer states and the microenvironment by linking signaling pathways to gene-regulatory dynamics. In our team, we work on deep learning applications for genomics and single-cell genomics, the integration of large datasets, and the interpretation of genomic variation in health and disease. Examples of recent deep learning models developed in the lab include DeepMEL and DeepMEL2, models trained on genomic regulatory sequences involved in melanoma skin cancer (Minnoye & Taskiran, Genome Research 2020; Kalender Atak & Taskiran, Genome Research 2021), and DeepFlyBrain, a deep learning model for gene regulation in the fruit fly brain (Janssens, Aibar & Taskiran, Nature 2022).

The candidate will develop new deep learning solutions, including convolutional neural networks, variational autoencoders, and generative adversarial networks, to build predictive models, particularly focused on cell type diversity in cancer. These models will be used to gain mechanistic insight into cancer cell states, hence the explainability of these models (XAI) is crucial. Depending on the interest, the candidate can be involved in single-cell technology and sequencing, to collect additional data sets from mouse models, organoids, patient-derived xenografts, and human tumor biopsies from the UZ Leuven hospital.

Profile

  • You obtained a Master or Ph.D. in Artificial Intelligence, Bioinformatics, Computer Science, Physics, Engineering, Bio-engineering, or equivalent.
  • Proficient in Python programming
  • Experience with machine learning is a plus (e.g., Tensorflow/Keras/PyTorch)
  • Experience with explainable AI (e.g., SHAP) is a plus
  • Experience with high-performance computing, software containers
  • Experience with cancer genomics is a plus, but not absolutely essential
  • Ability to work independently and in a team.

We offer

  • Access to state-of-the-art compute & GPU infrastructure 
  • A stimulating international research environment
  • You can be a driving force in a new EOS consortium across three Belgian Universities
  • Competitive salary and benefits
  • Minimally 2-year funding is available but candidates are encouraged to apply for international postdoc fellowships (e.g., EMBO, MSCA, etc.).
  • Starting date: as soon as possible

How to apply?

Please complete the online application procedure and include a detailed CV, two reference letters, and a motivation letter.

For more information: stein.aerts@kuleuven.be