bioRxiv

Model infers spatial neighborhoods in dissociated single cells

The computational tool predicted cellular proximity across brain regions and identified age-associated neighborhood remodeling in an 8-month Alzheimer dataset.

Paper by Yuxiang Zhan, Binwei Yan, Ao Zhang, Manolis Kellis, Na Sun · Whitehead Institute for Biomedical Research
Figure 1. ProxiNet learns transferable transcriptomic signatures of cellular proximity.
Open the figure at full size
Figure 1. ProxiNet learns transferable transcriptomic signatures of cellular proximity.ProxiNet learns transferable transcriptomic signatures of cellular proximity.Zhan et al.

Our read

AI & data
Studied:
Preprint: computational study
In the record:
One of 12,957 papers on Alzheimer's disease on record: 2,814 with results in people, 185 in animals.

Editor of record: Boris Djordjevic · AgingResearch.News

Follow @agingbrief

In brain tissue transcriptomic datasets, researchers tested ProxiNet, a computational framework designed to infer cellular proximity from dissociated single-cell RNA sequencing. While spatial transcriptomics captures intact tissue architecture, dissociated single-cell methods lose spatial context. ProxiNet trains on spatial reference data to learn expression signatures of pairwise cell proximity and transfers those relationships to dissociated cells.

The framework predicted proximity across brain regions and across different spatial technologies. In datasets with known coordinates, it recovered anatomical structures and reproducible tissue organization. When applied to dissociated single-cell data, ProxiNet revealed cellular neighborhoods and candidate cell communication programs. In an Alzheimer dataset, the model detected age-associated neighborhood remodeling, including an altered neighborhood at 8 months marked by distinct astrocyte and neuronal transcriptional states.

Why it matters

Mapping how cellular neighborhoods reorganize over time could clarify how localized cell-to-cell communication programs change during aging and neurodegeneration.

Caveats

The findings were reported in a preprint and rely on computational inference, meaning the predicted spatial relationships and communication programs require direct experimental confirmation.

From the paper

Limitation

Although we found generalization across anatomical regions and three spatial technologies, testing additional organs, species, and disease contexts will be necessary to establish broader transferability.

Discussion

Quoted word for word from the full text on bioRxiv.

Comments

Be the first to comment.