Jovan Tanevski

See 👇 our new manuscript introducing SpaCEy, an explainable method for predicting clinical outcomes from spatial omics data 🧬

📄 Paper: www.biorxiv.org/content/10.6...
💻 Code repo: github.com/saezlab/SpaCEy

Robust multicellular programs dissect the complex tumor microenvironment and track disease progression in colorectal adenocarcinomas Colorectal cancer (CRC) is highly heterogeneous, with five-year survival rates dropping from $\sim$90% in localized disease to $\sim$15% with distant metastases. Disease progression is shaped not only...

🧭 Colorectal cancer doesn’t follow a single path.
Using spatial proteomics on ~500 tumors, we found distinct trajectories from early to late stage, involving the whole tumor microenvironment and its metabolic state.
📄 Preprint: arxiv.org/abs/2510.05083
#SpatialBiology #CRC #ImageBasedProfiling
1/5

Introducing ParTIpy, a python package for Pareto Task Inference that scales to large-scale datasets, including single-cell and spatial transcriptomics.
🔗 Manuscript: www.biorxiv.org/content/10.1...
💻 Code: partipy.readthedocs.io

🎉 Such a great work by everyone involved in this major push forward in spatial multiplexing and next-generation pathology. I‘m glad to have been able to contribute to this effort and shed a light on the discovery of sub-cellular to tissue level organization patterns by xAI based on this technology.

Learning tissue representation by identification of persistent local patterns in spatial omics data - Nature Communications Spatial omics reveal tissue structures and can aid patient stratification. The authors present a method to identify patterns in tissue patches, enabling analysis of disease progression and treatment r...

The latest version of the Kasumi manuscript is now published in Nature Comms www.nature.com/articles/s41... Kasumi identifies patterns in tissue patches, enabling analysis of disease progression and treatment response while providing insights into spatial coordination at cell-type or marker level

Brilliant session focused entirely on spatial multiomics @theaacr.bsky.social #AUA25

Well said @tanevski.bsky.social "Cancer is a spatial disease-spatialomics is the future of cancer science"!

Wonderful composite spatial data from Linghua Wang @mdanderson.bsky.social
www.nature.com/articles/s41...

This work was led by Francesco Ceccarelli in collaboration with Pietro Liò, Sean B. Holden, @saezlab.bsky.social and Tanevski Lab.

We demonstrate TOAST on tasks of intra-, intersample, and temporal alignment in:
🧠 Human cortical layers (Visium)
🧫 Axolotl regeneration (Stereo-seq)
🐭 Locallization in mouse embryo development (seqFISH)
🎯 Various cancer types (IMC)
... with state-of-the-art efficiency and performance.

TOAST quantifies spatial coherence using entropy in local neighborhoods—favoring alignments that keep the order of local spatial compositions. It also preserves neighborhood consistency—aligning spots with similar gene expression in the spatial neighborhood.

Alignment is an important step for data integration and transfer of information that can help gain insights into mechanisms, progression and structural changes in disease. When the spatial context is available it *has to* complement molecular similarity to yield more biologically plausible mappings.

🚨 New preprint: Topography Aware Optimal Transport for Alignment of Spatial Omics Data

We present our new alignment framework TOAST www.biorxiv.org/content/10.1...

@chiaraschiller.bsky.social did an amazing job describing the landscape of methods for pairwise-association analysis in immediate spatial neighborhoods. Addressing limitations she proposes COZI and shows its ability to consistently recover directional cell-type associations and generate new insights