"PhD Position Study Genetic Impacts on Brain Cells Using Single-Cell and Spatial ML Techniques"

Join us to decode how genetic variation reprograms brain cells and disrupts their communication using AI.

We are looking for a PhD student to work at the intersection of machine learning, single-cell genomics, and neurogenetics. Your project will focus on developing new methods to understand how genetic variants affect not only individual brain cells but also change the way cells interact and communicate — insights that are essential for understanding the cellular origins of brain disorders.

Despite major progress in genetics research, we still don’t know how genetic risk factors for brain disorders like schizophrenia, Alzheimer’s, and depression disrupt brain function. Genetic discoveries point to thousands of disease-associated SNPs, but most of them act in subtle and cell type–specific ways, and their downstream biological effects remain poorly understood.

This project tackles this fundamental gap — by building computational models that simulate what goes wrong in the brain, one cell (and one cell–cell interaction) at a time.

You will work with large-scale single-cell and spatial transcriptomics data to develop and apply single-cell foundation models — generative machine learning models that represent the structure and variation of cell states. These models act as virtual cells simulating how perturbing the expression of genes altered by genetic variants affects the cell’s identity, behavior, and trajectory. You will extend these models to understand how genetic risk factors alter cell–cell communication networks. Spatial transcriptomics datasets will be used to anchor these models in real tissue context, revealing how spatially organized cell communities rewire under genetic perturbation.

Key challenges

• Use and improve single-cell foundation models to predict SNP-driven shifts in cell state and cell fate.
• Integrate spatial transcriptomics data to anchor these predictions in tissue context.
• Develop machine learning methods (e.g., graph neural networks, variational or diffusion models) to model cell–cell communication dynamics under genetic perturbation.
• Investigate how local interactions between perturbed and unperturbed cells reshape signaling networks and tissue states.
• Closely collaborate with neuroscientists in the BRAINSCAPES consortium to link model predictions to experimental and clinical relevance.

Benefits

• Shape next-generation models for understanding brain disease mechanisms.
• Work in a collaborative, interdisciplinary, and dynamic environment with leading experts in machine learning, computational biology, and neurogenomics.
• Access cutting-edge datasets, infrastructure, and computational and experimental facilities.
• Receive support for professional development and participation in international conferences.

Job requirements

• A Master’s degree in computational biology, machine learning, bioinformatics, AI, or a related field.
• Strong background in machine learning and data analysis.
• Interest in single-cell omics, spatial data, or systems neuroscience.
• Intellectual curiosity, independence, and motivation to tackle open-ended problems with real-world impact.
• Strong analytical thinking and problem-solving skills.
• A passion for using AI to answer fundamental questions in biology and medicine.
• Ability to work independently and as part of a multidisciplinary team.
• Strong interpersonal communication and collaboration abilities.
• Strong communication skills and proficiency in English.