EUVIMEDEUVIMED entdecken
Crossref

ST-LDAW: A Topic-Model and Damped Weighted Least-Squares Method for Integrative Deconvolution of Single-Cell and Spatial Transcriptomics

Xiaoyang Wang, Li C Xia, Huiling Liu, Chunxia Du, Lulu Chen, Zhimin Li, Yang Du, Yujia Li, Dongmei Ai

Interdisciplinary Sciences: Computational Life Sciences · 09.06.2026

DOI: 10.1007/s12539-026-00850-7 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Interdisciplinary Sciences: Computational Life Sciences, online erschienen am 09.06.2026. Verfasst von Xiaoyang Wang und 8 weiteren Autor:innen. Beteiligte Einrichtung: School of Mathematics and Physics, University of Science and Technology Beijing, Beijing, 100083, China. Die Arbeit nennt 58 Literaturangaben. Gefördert von: National Natural Science Foundation of China.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Integrating single-cell RNA sequencing (scRNA-seq) with spatial transcriptomics (ST) enables the projection of cell-type-resolved transcriptional programs onto tissue architecture. However, existing integration methods are often unstable because spot-level inference is performed directly in high-dimensional gene space, where extreme sparsity, measurement noise, and strong multicollinearity among marker genes amplify the estimation variance. As a result, inferred cell type proportions may be dominated by a small subset of genes, making them highly sensitive to noise and systematically distorting rare or low-abundance cell types. Here, we present ST-LDAW, which is a computational framework explicitly designed to address these challenges. ST-LDAW combines probabilistic topic modeling with damped weighted least squares optimization to enhance robustness at both the representation and inference levels. Topic-based modeling reduces dimensionality and mitigates gene-level noise by capturing coherent transcriptional programs, whereas damped weighting constrains the influence of unstable or low-confidence features, preventing variance inflation and overfitting during deconvolution. Benchmarking of simulated spatial mixtures demonstrated that ST-LDAW achieved a recall rate of 94% and an accuracy of 80%, surpassing existing regression-based and mapping-based methods in terms of sensitivity and precision. These results highlight ST-LDAW's ability to reliably identify cell types in complex, sparse datasets and its robust performance in handling rare or low-abundance cell types. Application to breast cancer ST data further reveals the subtype-specific cellular composition, functional heterogeneity, intercellular communication patterns, and key epithelial hub genes.

Schlagwörter

Stichwörter der Autor:innen

Damped weighted least squaresLDA topic modelSpatial heterogeneity of tumorSpatial transcriptomeTumor microenvironment

Autor:innen und Institutionen

  • School of Mathematics and Physics, University of Science and Technology Beijing, Beijing, 100083, China.
  • School of Mathematics, South China University of Technology, Guangzhou, 510641, China.
  • Department of Medical Oncology, National Clinical Research Center for Cancer/Cancer Hospital, National Cancer Center, Chinese Academy of Medical Sciences and Peking Union Medical College, Beijing, 100021, China.
  • School of Mathematics and Physics, University of Science and Technology Beijing, Beijing, 100083, China. aidongmei@ustb.edu.cn.

Förderung

  • National Natural Science Foundation of China

Zitieren

APA

Wang, X., Xia, L. C., Liu, H., Du, C., Chen, L., Li, Z., Du, Y., Li, Y., & Ai, D. (2026). ST-LDAW: A Topic-Model and Damped Weighted Least-Squares Method for Integrative Deconvolution of Single-Cell and Spatial Transcriptomics. Interdisciplinary Sciences: Computational Life Sciences. https://doi.org/10.1007/s12539-026-00850-7

Vancouver

Wang X, Xia LC, Liu H, Du C, Chen L, Li Z, et al. ST-LDAW: A Topic-Model and Damped Weighted Least-Squares Method for Integrative Deconvolution of Single-Cell and Spatial Transcriptomics. Interdisciplinary Sciences: Computational Life Sciences. 2026. doi:10.1007/s12539-026-00850-7

BibTeX
@article{Wang2026,
  author = {Wang, Xiaoyang and Xia, Li C and Liu, Huiling and Du, Chunxia and Chen, Lulu and Li, Zhimin and Du, Yang and Li, Yujia and Ai, Dongmei},
  title = {ST-LDAW: A Topic-Model and Damped Weighted Least-Squares Method for Integrative Deconvolution of Single-Cell and Spatial Transcriptomics},
  journal = {Interdisciplinary Sciences: Computational Life Sciences},
  year = {2026},
  doi = {10.1007/s12539-026-00850-7}
}
Kostenlos starten →