PhD Student position: Deep Learning in antibody imaging to understand the immune synapse formation


Job Description
Helmholtz Zentrum Munich and Roche invite applications for an exciting PhD position as part of the Munich Data Science Grad School program The successful candidate will be working in a collaborative and stimulating research environment between the Institute of computational biology (ICB) at Helmholtz and Roche Pharma Research and Development (pRED) at the Roche Innovation Center Munich (RICM). The goal of this PhD position is to develop and apply methodology from the fields of machine learning and deep learning to understand and predict the immune response of different antibodies, ultimately, in order to help design antibody-based medicines for immune-related diseases including cancer.

In this project, we aim to understand how immune responses can be modulated by targeting different surface receptors with our bispecific antibodies and how this correlates with immune synapse formation. The assembly of the immunological synapse is an essential procedure during immune responses to transfer signals between two cells and plays an important role in manipulating cellular responses. By addressing different molecular addressees which are located either in the central, the periphery or outside of the immunological synapse we want to understand how the localization of the molecular addressees, as well as different formats of the bispecific antibodies, affect T and B cell activation.

We aim to leverage a novel technology, Imaging Flow Cytometry, that allows to capture in high-throughput tens of thousands of cells, recording multi-channel images of fluorescently labeled components and properties of the cells potentially affecting T and B cell activation. Using deep convolutional neural networks (CNNs), we aim to develop a methodology that can map end-to-end from these multi-channel input images to quantitative readouts of immunological synapse formation and thus be able to predict T and B cell response of different bispecific antibodies.

Key responsibilities
You will leverage your  expertise in computer vision, deep learning and machine learning, as well as strong communication skills to

  • Collaborate and coordinate with academic and industrial mentors to research the modulation of the immune response.
  • Develop and apply deep learning methodology to understand and predict how immune responses can be modulated by targeting different surface receptors.
  • Prototype, implement, document and test the developed algorithms, models and imaging/computer vision approaches.
  • Establish and integrate models into existing automation frameworks to allow scientists to utilize developed methodology in real-life projects.
  • Interface with immunologists, biologists and data scientists to communicate results and understand how to interpret data.
  • Present at international conferences and publish in peer-reviewed journals.


  • You hold a Masters (MSc) or equivalent in biostatistics, bioinformatics, physics, computer science or other related fields.
  • You have excellent programming skills and are fluent in at least one of the following languages: Python, R, Matlab.
  • You have experience in the field of machine learning.
  • Experience using deep learning frameworks (tensorflow, torch, keras, …) or a background in computer vision is a definite plus.
  • You have experience in databases, SQL, and are confident in aggregating, manipulating and pivoting data tables.
  • You are passionate about data visualisation and presenting results in a concise and clear way.
  • A background in molecular and cell biology with a focus on immunology desired but not required.
  • You are well known for your strong team spirit and your willingness to work in international teams.
  • In addition, you are interested to work interdisciplinary and you are ready to learn and explore new fields.
  • Excellent English skills, written and spoken, complete your profile.

Please send your electronic application (in English) in a single PDF file – including cover letter, statement of research interests, a description of a major accomplished scientific project (e.g. your Master thesis), CV, a complete list of publications, certificates and transcripts, and contact details of at least two references to:

We use cookies to improve your experience on our Website. We need cookies to continuously improve the services, to enable certain features and when embedding services or content of third parties, such as video player. By using our website, you agree to the use of cookies. We use different types of cookies. You can personalize your cookie settings here:

Show detail settings
Please find more information in our privacy statement.

There you may also change your settings later.