PhD student in AI and machine learning for cancer research Full-time

PhD Student In Ai And Machine Learning For Cancer Research

The Department of Immunology, Genetics and Pathology at Uppsala University has a broad research profile with strong research groups focused on cancer, autoimmune and genetic diseases. A fundamental idea at the department is to stimulate translational research and thereby closer interactions between medical research and health care. Research is presently conducted in the following areas: medical and clinical genetics, clinical immunology, pathology, neuro biology, neuro-oncology, vascular biology, radiation science and molecular tools. Department activities are also integrated with the units for Oncology, Clinical Genetics, Clinical Immunology, Clinical Pathology, and Hospital Physics at Akademiska sjukhuset, Uppsala.

Do you want to use artificial intelligence and machine learning to understand — and reprogram — the behaviour of one of the world's most dangerous cancers? We are looking for a PhD student to conduct world-class research on glioblastoma: a brain tumour whose lethality is driven not by spread to other organs but by its ability to continuously shift biological identity and invade brain tissue. With us, you will combine cutting-edge AI method development with direct experimental validation, in an international research environment with strong collaborations and unique resources.

The research group is led by Professor Sven Nelander at the Department of Immunology, Genetics and Pathology, Uppsala University. We work at the intersection of AI/machine learning, systems biology, and experimental neuro-oncology. Over more than a decade we have built unique resources: a biobank of over 100 patient-derived glioblastoma cell lines (distributed to 54 laboratories in 17 countries), large-scale Perturb-seq data, custom CRISPR reporter tools, and a working prototype of a multi-modal AI system. The group is part of the national strategic research centre CNSx3 and is connected to the UUniFI AI institute. You will be supervised by Sven Nelander and Veronica Rendo, with support from experts in mathematical biology and high-dimensional statistics. The team combines computational biologists, experimental researchers, and mathematicians — a genuinely cross-disciplinary environment for cutting-edge research. The project is funded by the Swedish Research Council, the Swedish Cancer Society, KAW, and SSF.

The fundamental problem we want to solve is to understand how cells in a brain tumour choose to switch identity — and how that knowledge can be used to actively steer them towards more treatment-sensitive states. We call this concept state steering. Unlike conventional cancer therapy, which aims to kill tumour cells, state steering aims to reprogram them.

You will work with two main types of data collected within the strategic research centre CNS×3: large-scale intervention experiments, in which we systematically map how genetic and pharmacological perturbations affect tumour cell plasticity, and imaging-based tracking data, in which individual tumour cells are followed in real time as they migrate through brain tissue. The goal is to build AI models that integrate these data sources and predict how a given treatment affects tumour behaviour and outcome.

You will join an exciting computational team with a shared ambition: to integrate both data types within a unified mathematical framework — the theory of linear operators. Existing tools such as hidden Markov models (HMM), used to analyse individual cell movements in imaging data, are special cases of this broader framework. The new contribution, rewire-seq, is a more general and scalable version that combines large-scale intervention screens with imaging-based cell tracking to give an integrated picture of tumour dynamics. A key component of the project is cyclic experimentation: model predictions directly guide the choice of the next experiment, and results feed back into the model — a workflow that makes the research progressively more precise. You will work closely with experimental colleagues, jointly translating biological questions into computational solutions with clinical relevance.

To meet the entry requirements for doctoral studies, you must:

• hold a Master's (second-cycle) degree in computational biology, bioinformatics, machine learning, applied mathematics, biophysics, or a related field, or
• have completed at least 240 credits in higher education, with at least 60 credits at Master's level including an independent project worth at least 15 credits, or
• have acquired substantially equivalent knowledge in some other way.

The project requires a solid understanding of the mathematics underlying AI and machine learning — including linear algebra, probability theory, and statistical inference — and hands-on experience with demanding data analyses, e.g. in genomics, image analysis, or biochemical screening. Strong programming skills in Python and/or R are required. We are open to candidates with the potential to combine experimental and computational work. The position suits candidates who aspire to a long-term career at the frontier of academic or industrial research.

Additional qualifications: experience with single-cell RNA-seq analysis or CRISPR screens. Experience with deep learning or graph neural networks. Prior experience in method development or published research. Interest in cancer biology and the ability to derive biological hypotheses from data.

The employment is a temporary position according to the Higher Education Ordinance chapter 5 § 7. Scope of employment 100%. Starting date as soon as possible or as agreed. Placement: Uppsala.