PhD candidate in Machine Learning of Large-scale in vivo Perturbational Omics

Description

We are seeking a motivated new PhD candidate who wants to join an exciting collaborative research program within the VIB-Center for Inflammation Research between the Guilliams and Saelens team.

Research Project

In this research project you will develop probabilistic deep-learning models that automatically extract biological and statistical knowledge from in vivo perturbational omics data. We have developed in vivo single-cell CRISPR technologies to screen for dozens of molecular factors in vivo during developmental and disease. These technologies are a game-changer in the speed, scale and resolution in which in vivo pathways of immune cells can be unraveled. Furthermore, it provides a goldmine for training causal machine learning models to move towards precision medicine. Extracting this information is still a challenge though, given its intrinsic multidimensional nature (time, perturbation, tissue position, cell state, statistical power).

With modern probabilistic modelling, that combines diffusion and transformer models, there are clear indications that the analysis of this data can be automated. This will open new avenues in data interpretation and building predictive models. Ultimately, the goal is to move towards an active-learning-based screening to unravel particular developmental and disease states in its entirety. The automated analysis of this data will be a key building block within this process.

You will be embedded both within an experimental and computational team, providing a unique atmosphere where there is expertise to develop the deep-learning models while having ample opportunities for direct validation in biologically relevant settings. This interdisciplinary atmosphere has been a main catalyst for many past successes: , , , ,

Profile

• Master's in software engineering, computer science, data science, bioengineering, bioinformatics, engineering, physics or related
• Experience in either machine learning or computational biology. Interest in both.
• Programming experience in Python.
• Excellent communication skills and fluency in English.
• Collaborative personality with attention for detail.

Bonus but not required

• Experience with training and validating Pytorch and/or JAX deep learning models.
• Experience in single-cell or spatial omics data analysis.

What we offer

• Embedding within a computational team, with extensive experience in computational biology and machine learning.
• Embedding within an experimental team, with direct availability of experimental validation for machine learning models. The candidate is encouraged to follow along some experiments to understand the opportunities and pitfalls during data generation.
• Competitive salary and full benefits.
• Access to state-of-the-art computing infrastructure.

Want to apply?

Interested candidates are invited to apply online. Please use the VIB application tool to submit your application.

• Motivation letter of 1-1.5 pages
• Curriculum vitae
• University degree certificates

For more information, you are welcome to contact Prof. Wouter Saelens ) or Prof. Martin Guilliams )

Diversity & Inclusion

We are committed to creating and sustaining an inclusive, respectful, and collaborative environment where everyone can thrive. We value diversity in all its forms - including but not limited to gender identity, ethnicity, nationality, disability, sexual orientation, age, socio-economic background, and family situation. We welcome applications from individuals of all backgrounds and identities, and we are dedicated to providing equal opportunities and actively promoting a culture of belonging.

Feel free to let us know in your cover letter if there are any past or current circumstances that can impact your application.

By embracing the unique perspectives and experiences of our team members, we aim to foster innovation and advance excellence in research. We believe that a diverse and inclusive workplace is essential for scientific creativity, effective collaboration, and impactful discovery.