EUVIMEDOpdag EUVIMED
Open access · CC BY-NC 4.0

STIFT: spatiotemporal transcriptomics integration through spatially informed multi-timepoint bridging

Ji Qi iD, Muyang Ge, Jishuai Miao, Xiaocheng Zhou, Zhixiang Lin

Briefings in Bioinformatics · 2025

DOI: 10.1093/bib/bbaf644 ↗

At a glance

Journal article in Briefings in Bioinformatics, 2025. Written by Ji Qi and 4 co-authors. Institution: Department of Statistics and Data Science, The Chinese University of Hong Kong, Ma Liu Shui, Sha Tin, New Territories, Hong Kong SAR, China. Major MEDLINE topics: Transcriptome, Gene Expression Profiling, Computational Biology. Cited 1 times so far (Crossref); 40 references. The full text is freely available (open access, CC BY-NC 4.0). Funded by: Chinese University of Hong Kong Science Faculty's Collaborative Research Impact Matching Scheme, Research Grants Council, University Grants Committee, Chinese University of Hong Kong Science Faculty’s Collaborative Research Impact Matching Scheme.

AbstractSubjectsBibliografiske oplysningerCiteRelated studies

Abstract (original language)

Recent advances in spatial transcriptomics have highlighted the need for integrating spatiotemporal transcriptomics data, defined as spatially resolved gene expression profiles captured across sequential time points in developmental or regenerative processes. We present STIFT (SpatioTemporal Integration Framework for Transcriptomics) specifically designed for integrating spatiotemporal transcriptomics data. STIFT is a three-component framework combining developmental spatiotemporal optimal transport, spatiotemporal graph construction, and a graph attention autoencoder informed by temporal triplet learning. STIFT integrates large-scale 2D or 3D spatiotemporal transcriptomics data, enabling batch effect removal, spatial domain identification, trajectory inference and exploration of developmental dynamics. Applied to axolotl brain regeneration, mouse embryonic development, and 3D planarian regeneration datasets, STIFT removes batch effects and achieves clear spatial domain identification while preserving temporal developmental patterns and biological variations across hundreds of thousands of spots, demonstrating its effectiveness and specificity in integrating spatiotemporal transcriptomics data.

Subjects

MeSH terms (MEDLINE)

TranscriptomeGene Expression ProfilingComputational BiologyAnimalsMicePlanariansSpatio-Temporal AnalysisBrainAmbystoma mexicanumRegenerationEmbryonic Development

Author keywords

data integrationgraph attention autoencoderspatial transcriptomicsspatiotemporal data

Authors and institutions

  • Department of Statistics and Data Science, The Chinese University of Hong Kong, Ma Liu Shui, Sha Tin, New Territories, Hong Kong SAR, China.
  • Shenzhen Loop Area Institute, No. 6 Hongmian Road, Futian Free Trade Zone, Futian District, Shenzhen, Guangdong, 518038, China.
  • CUHK Shenzhen Research Institute, No. 10, 2nd Yuexing Road, Nanshan District, Shenzhen, Guangdong, 518000, China.

ORCID profiles: Ji Qi

Funding

  • Chinese University of Hong Kong Science Faculty's Collaborative Research Impact Matching Scheme
  • Research Grants Council, University Grants Committee
  • Chinese University of Hong Kong Science Faculty’s Collaborative Research Impact Matching Scheme

Cite

APA

Qi, J., Ge, M., Miao, J., Zhou, X., & Lin, Z. (2025). STIFT: spatiotemporal transcriptomics integration through spatially informed multi-timepoint bridging. Briefings in Bioinformatics. https://doi.org/10.1093/bib/bbaf644

Vancouver

Qi J, Ge M, Miao J, Zhou X, Lin Z. STIFT: spatiotemporal transcriptomics integration through spatially informed multi-timepoint bridging. Briefings in Bioinformatics. 2025. doi:10.1093/bib/bbaf644

BibTeX
@article{Qi2025,
  author = {Qi, Ji and Ge, Muyang and Miao, Jishuai and Zhou, Xiaocheng and Lin, Zhixiang},
  title = {STIFT: spatiotemporal transcriptomics integration through spatially informed multi-timepoint bridging},
  journal = {Briefings in Bioinformatics},
  year = {2025},
  doi = {10.1093/bib/bbaf644}
}
Start for free →