Doctoral Student in AI and Machine Learning for Single-cell Cancer Data

About the role

Four-year fully funded PhD at KTH on machine learning methods for single-cell cancer data, scRNA-seq, scATAC-seq, and spatial transcriptomics. The project develops models that combine these modalities to uncover tumour heterogeneity and therapeutic vulnerabilities. Deadline 3 June 2026.

Responsibilities

• Build deep generative and graph-based models for single-cell sequencing data.
• Integrate multiple modalities, RNA, ATAC, protein, spatial, into joint representations.
• Apply the methods to cancer cohorts in collaboration with clinical groups at Karolinska Institutet.
• Publish in NeurIPS, ICML, Nature Methods, or Genome Biology and complete the KTH doctoral coursework.

Requirements

• Master’s degree in computer science, applied mathematics, computational biology, statistics, or a related field.
• Strong background in machine learning, particularly representation learning or generative models.
• Python proficiency; experience with PyTorch or JAX.
• Fluent English.

Nice to have

• Hands-on experience with single-cell genomics tools (Scanpy, AnnData, Seurat).
• Familiarity with variational autoencoders, normalising flows, or graph neural networks.
• Prior publications or preprints in ML or computational biology.

How to apply

Search “Single-cell Cancer Data” on KTH’s Varbi portal at the apply link. Submit CV, transcripts, research statement, Master’s thesis, and two references via Varbi before 3 June 2026.