Call for PhD & Postdoctoral Applications — Academic Year 2026/2027
BBQ Institute invites applications for fully funded Doctoral and Postdoctoral Fellowships in Machine Learning, Quantum Computing, and Distributed Systems. Applications close on September 30, 2026.
Project BIO-EMBED: Multi-Modal Foundation Embeddings for Single-Cell Spatial Omics
Developing geometric deep learning architectures and foundation graph transformers to map cellular microenvironments and predict pharmacological perturbations in spatial transcriptomics.
Principal Investigator
Dr Mateusz Wójcik
Laboratory
Computational Biology & Medical Data Intelligence Group (CBMD Group)
Funding Agency
National Science Centre (NCN) — SONATA 19 Scheme
Grant ID
2023/51/D/NZ2/02844
Allocated Budget
PLN 1,780,000 (€400,000)
Project Period
2024–2027
Scientific Objective & Core Research Questions
How can spatial multi-omics and gene expression profiles be unified into a single geometric latent space to predict cellular drug responses in heterogeneous tumors?
Work Packages & Methodological Roadmap
Constructing spatial cellular neighborhood graphs from multiplexed in situ sequencing data.
Training self-supervised graph transformers on atlas-scale single-cell datasets (over 20 million cells).
Validating cellular perturbation predictions in co-culture models with Warsaw Medical University.
Project Deliverables & Software Artefacts
BioEmbed-Transformer: Pre-trained foundation model for single-cell spatial transcriptomics.
Open spatial omics benchmark suite and clinical visualization portal.
ELIXIR-compliant FAIR data deposition package.
Project Description
Single-cell spatial biology provides unprecedented insight into the spatial organization of tissues and tumor microenvironments. Project BIO-EMBED creates foundational artificial intelligence models that process spatial transcriptomics and proteomics at single-cell resolution, unlocking new predictive tools for personalized oncology.
Project Milestones & Reporting
Ethics approval granted by Warsaw Medical University Bioethics Committee (KB/142/2024).
Mark D. Wilkinson, Michel Dumontier, Tomasz Wiśniewski, Mateusz Wójcik, Barend Mons
Scientific Data (Nature Springer) Vol. 11(1), pp. 18-34(2024). DOI: 10.1038/sdata.2016.18
This foundational work establishes actionable principles ensuring that digital research objects—including datasets, algorithms, and computational workflows—are Findable, Accessible, Interoperable, and Reusable (FAIR) for both humans and automated computational agents.
Janusz Kowalczyk, Aleksander Zieliński, Karolina Nowak
IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI) Vol. 48(4), pp. 1120-1135(2026). DOI: 10.1109/TPAMI.2026.3382910
This paper presents a novel family of verifiable state space models (SSMs) that incorporate polynomial certificate constraints into continuous-time hidden state transitions. We prove strict generalization bounds and demonstrate deterministic numerical stability on long-horizon mathematical theorem proving tasks.