SlotDeconv: spatial transcriptomics deconvolution via diversity-constrained prototype learning and spatial refinement
Bioinformatics · 2026
DOI: 10.1093/bioinformatics/btag424 ↗Kurz gefasst
Fachartikel in der Zeitschrift Bioinformatics, 2026. Verfasst von Hanzhang Fang und 4 weiteren Autor:innen. Beteiligte Einrichtung: Department of Computer Science, New Jersey Institute of Technology, University Heights, Newark, New Jersey 07102, United States. Hauptthemen laut MEDLINE: Software, Gene Expression Profiling, Computational Biology, Transcriptome. Die Arbeit nennt 15 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: NHGRI NIH HHS, NIGMS NIH HHS, NIH HHS.
Abstract (Originalsprache)
Motivation Spatial transcriptomics (ST) measures gene expression in intact tissues. In spot-based ST assays, each spot can contain mixtures of multiple cell types. Deconvolution is particularly challenging when closely related cell subtypes share highly similar expression profiles and when spatial context is underutilized during proportion estimation. Results We present SlotDeconv, a method for ST deconvolution consisting of a single-cell reference module and a spatial inference module. The reference module learns discriminative cell-type signatures using slot-based prototype vectors decoded into a reference matrix, trained with a negative binomial reconstruction loss and a max-margin diversity constraint that discourages similar cell-type signatures. Ablation studies confirm that both components are essential: removing the diversity constraint reduces spot-wise Pearson correlation by 41%, and replacing learned prototypes with cell-type mean expression reduces it to near zero. The spatial inference module initializes spot-level proportions via gene-weighted nonnegative least squares (NNLS), then refines them by minimizing Kullback–Leibler (KL) divergence between observed and reconstructed spot expression under a spatial neighborhood consistency regularizer. Benchmarked against CARD, RCTD, Cell2location, and Spotiphy on a 27 cell type mouse brain dataset, SlotDeconv achieves the highest spot wise Pearson correlation (approximately 0.56) and cosine similarity (0.633), outperforming competing methods in spot-wise correlation, with particularly strong gains on transcriptionally similar cortical neuronal subtypes. Biological validation on human pancreatic cancer and mouse olfactory bulb datasets further confirms spatial specificity. Availability Source code is available at https://github.com/HannahNJIT/SlotDeconv
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Autor:innen und Institutionen
- Department of Computer Science, New Jersey Institute of Technology, University Heights, Newark, New Jersey 07102, United States.
ORCID-Profile: Cong Qi
Förderung
- NHGRI NIH HHS
- NIGMS NIH HHS
- NIH HHS
- National Institutes of Health
Zitieren
APA
Fang, H., Qi, C., Zou, Y., Chen, Y., & Wei, Z. (2026). SlotDeconv: spatial transcriptomics deconvolution via diversity-constrained prototype learning and spatial refinement. Bioinformatics. https://doi.org/10.1093/bioinformatics/btag424
Vancouver
Fang H, Qi C, Zou Y, Chen Y, Wei Z. SlotDeconv: spatial transcriptomics deconvolution via diversity-constrained prototype learning and spatial refinement. Bioinformatics. 2026. doi:10.1093/bioinformatics/btag424
BibTeX
@article{Fang2026,
author = {Fang, Hanzhang and Qi, Cong and Zou, Yuanjie and Chen, Yeqing and Wei, Zhi},
title = {SlotDeconv: spatial transcriptomics deconvolution via diversity-constrained prototype learning and spatial refinement},
journal = {Bioinformatics},
year = {2026},
doi = {10.1093/bioinformatics/btag424}
}
EUVIMED