EUVIMEDEUVIMED entdecken
Crossref

STADIA : A Spatio‐Temporal Deep‐Learning Framework for Cross‐Stage Integration and Batch Correction of Plant Developmental Spatial Transcriptomics

Dezhi Zhi, Xuemei Guan iD, Liuyan Wang, Wenhui Chen

Physiologia Plantarum · 2026

DOI: 10.1111/ppl.71143 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Physiologia Plantarum, 2026. Verfasst von Dezhi Zhi und 3 weiteren Autor:innen. Beteiligte Einrichtung: College of Control and Information Engineering, Northeast Forestry University, Harbin, Heilongjiang, China. Hauptthemen laut MEDLINE: Deep Learning, Plant Development, Transcriptome. Die Arbeit nennt 47 Literaturangaben. Gefördert von: Fundamental Research Funds for the Central Universities.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Spatial transcriptomics enables the spatial architecture and transcriptional dynamics of plant organ development to be resolved in situ. However, integrating plant spatial transcriptomic data across developmental stages is challenging because genuine developmental variation can be confounded with technical variation arising from section source, capture region and sequencing batch, making it difficult to attenuate technical effects without compromising developmental signals. To address this challenge, we developed STADIA, a spatio‐temporal deep‐learning framework for plant developmental spatial transcriptomics. STADIA combines a graph‐attention autoencoder with structural‐context‐conditioned batch‐predictability suppression, stage‐order constraints, PCGrad‐based gradient coordination and hierarchical unbalanced optimal transport to learn an integrated latent representation that attenuates batch‐associated variation while preserving spatial organization and developmental continuity and accommodating non‐equivalent tissue transitions. In a semi‐synthetic benchmark, STADIA maintained balanced performance across batch mixing, anatomical‐domain preservation and developmental‐information preservation under strong batch effects and high sparsity. In the same‐stage replicate sections from the soybean early‐maturation stage (EMS), STADIA increased local between‐section mixing while retaining major anatomical compartments. In a poplar stem developmental series spanning the shoot apex to internode 7, the integrated representation showed increased cross‐stage continuity while retaining stage‐specific organization and spatially coherent tissue compartments, and supported exploratory identification of cambium‐associated trajectory candidates. Together, these results support STADIA as a framework for cross‐stage integration of plant spatial transcriptomic data and for downstream analysis of spatial domains and developmentally ordered transcriptional patterns.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Deep LearningPlant DevelopmentTranscriptomeSpatial TranscriptomicsGlycine max

Stichwörter der Autor:innen

cambiumgraph attention autoencodersecondary growthstage‐batch confoundingunbalanced optimal transportwood formation

Autor:innen und Institutionen

  • College of Control and Information Engineering, Northeast Forestry University, Harbin, Heilongjiang, China.

ORCID-Profile: Xuemei Guan

Förderung

  • Fundamental Research Funds for the Central Universities

Zitieren

APA

Zhi, D., Guan, X., Wang, L., & Chen, W. (2026). STADIA : A Spatio‐Temporal Deep‐Learning Framework for Cross‐Stage Integration and Batch Correction of Plant Developmental Spatial Transcriptomics. Physiologia Plantarum. https://doi.org/10.1111/ppl.71143

Vancouver

Zhi D, Guan X, Wang L, Chen W. STADIA : A Spatio‐Temporal Deep‐Learning Framework for Cross‐Stage Integration and Batch Correction of Plant Developmental Spatial Transcriptomics. Physiologia Plantarum. 2026. doi:10.1111/ppl.71143

BibTeX
@article{Zhi2026,
  author = {Zhi, Dezhi and Guan, Xuemei and Wang, Liuyan and Chen, Wenhui},
  title = {STADIA : A Spatio‐Temporal Deep‐Learning Framework for Cross‐Stage Integration and Batch Correction of Plant Developmental Spatial Transcriptomics},
  journal = {Physiologia Plantarum},
  year = {2026},
  doi = {10.1111/ppl.71143}
}
Kostenlos starten →