OSCR

Deciphering spatial heterogeneity by multimodal spatial transcriptomics modelling with SpatialModal.

Code ↔ Paper

6 matches between paragraphs of the paper and lines of its authors' code, computed by the harvester (lexical-v1). Click a colored paragraph or line to see its counterpart.

The 6 matches
  1. [1] § 2 Materials and methods › 2.3 Data preprocessing ↔ Spatialmodal/data_process.py, lines 88 to 94 · score 0.75 · highly variable genes, Seurat v3, Scanpy, preprocessed · Report a mismatch
  2. [2] § 3 Results › 3.5 SpatialModal reveals spatiotemporal developmental trajectories in the embryonic heart ↔ Tutorial/Chicken_Heart.ipynb, lines 85 to 113 · score 0.62 · mural cells, endocardial cell, immature, cardiomyocytes, enriched, heart · Report a mismatch
  3. [3] § 3 Results › 3.2 SpatialModal delineates complex mouse brain structures ↔ Tutorial/Mouse_Brain.ipynb, lines 46 to 56 · score 0.61 · Davies Bouldin, Mouse Brain, Silhouette, DB, SC, clustering · Report a mismatch
  4. [4] § 2 Materials and methods › 2.3 Data preprocessing ↔ Tutorial/DLPFC.ipynb, lines 82 to 113 · score 0.50 · highly variable, Scanpy, HVGs, Genes expressed · Report a mismatch
  5. [5] § 3 Results › 3.2 SpatialModal delineates complex mouse brain structures ↔ Tutorial/Mouse_Brain.ipynb, lines 59 to 67 · score 0.50 · Mouse Brain, sagittal anterior, posterior, joint · Report a mismatch
  6. [6] § 2 Materials and methods › 2.2 Data description ↔ Tutorial/MTG.ipynb, lines 1 to 12 · score 0.50 · human middle temporal, MTG, gyrus, healthy, Alzheimer, disease · Report a mismatch

Paper

Loaded from Europe PMC by your browser; OSCR does not store it: doi.org · Europe PMC

The paper is loaded when this pane is shown.

The authors' code

Jupyter notebook · 90 lines · 3.2 KB · no license · 2 matches

  1. # %% [markdown]
  2. # ### **Tutorial:Mouse Brain**
  3. #
  4. # This experiment applies SpatialModal to mouse brain Sagittal Anterior, Sagittal Posterior, and Coronal slices, utilizing joint training for the sagittal sections to capture shared biological patterns. While this notebook specifically demonstrates the Coronal slice workflow, we also present the results of joint training to illustrate the framework's superior performance in integrating multiple tissue sections for enhanced spatial domain identification and gene reconstruction.
  6. # %% [markdown]
  7. # #### **Loading package**
  9. # %%
  10. import sys
  11. import os
  12. sys.path.append(os.path.abspath(".."))
  14. # %%
  15. import torch
  16. from Spatialmodal.spatialmodal import SpatialModal
  17. from Spatialmodal.reconstruction import RF
  18. from Spatialmodal.data_process import load_ST_file
  19. from Spatialmodal.utils import mclust_R
  20. from sklearn.decomposition import PCA
  21. import scanpy as sc
  22. from sklearn.metrics import silhouette_score, davies_bouldin_score
  23. import seaborn as sns
  24. import matplotlib.pyplot as plt
  26. import warnings
  27. warnings.filterwarnings("ignore")
  29. # %%
  30. device = torch.device('cuda:2' if torch.cuda.is_available() else 'cpu')
  32. # %% [markdown]
  33. # #### **Coronal slices**
  35. # %%
  36. sample = 'mouse_brain_coronal'
  37. fold = f"../Data/mouse_brain/{sample}"
  38. fold = "/home/zhaodongmin/SpatialModal/data/mouse_brain/mouse_brain_coronal"
  39. adata = load_ST_file(fold)
  40. n_clusters = 30
  42. # %%
  43. model = SpatialModal(adata, device=device, epochs=1000, fold=fold, image_use=True, if_img=True)
  44. adata = model.train()
  46. # %%
  47. pca = PCA(n_components=20, random_state=42)
  48. embedding = pca.fit_transform(adata.obsm['emb'].copy())
  49. adata.obsm['emb_pca'] = embedding
  51. mclust_R(adata, n_clusters, use_rep='emb_pca', key_added='domain')
  53. SC = silhouette_score(adata.obsm['emb_pca'], adata.obs['domain'])
  54. DB = davies_bouldin_score(adata.obsm['emb_pca'], adata.obs['domain'])
  56. sc.pl.spatial(adata, color='domain', show=True, img_key=None, size=1.5, title=f"SC={SC:.4f}, DB={DB:.4f}")
  59. # %% [markdown]
  60. # #### **Joint training**
  61. #
  62. # In this experiment, image features were first extracted individually from the sagittal anterior and posterior brain slices and subsequently concatenated to form a joint feature distribution. In this demonstration, we utilize a pre-processed .h5ad file composed of these combined sagittal datasets. For detailed information regarding the data construction process, please refer to the Methods section of the manuscript.
  64. # %%
  65. adata = sc.read_h5ad("/home/zhaodongmin/task_spa/data/mouse_brain_a_p/mouse_anterior_posterior_brain_merged.h5ad")
  67. adata
  69. # %%
  70. model = SpatialModal(adata, device=device, epochs=1000, image_use=True, if_img=True)
  71. adata = model.train()
  73. # %%
  74. pca = PCA(n_components=20, random_state=42)
  75. embedding = pca.fit_transform(adata.obsm['emb'].copy())
  76. adata.obsm['emb_pca'] = embedding
  77. mclust_R(adata, 36, use_rep='emb_pca', key_added='domain')
  79. rgb_values = sns.color_palette("tab20", len(adata.obs['domain'].unique()))
  80. color_fine = dict(zip(list(adata.obs['domain'].unique()), rgb_values))
  81. color_fine[1] = '#6B7900'
  82. color_fine[23] = '#63FFAC'
  83. plt.rcParams["figure.figsize"] = (12, 6)
  84. sc.pl.embedding(adata, basis="spatial",
  85. color="domain",
  86. s=100,
  87. palette=color_fine,
  88. show=False, )
  89. plt.gca().legend().set_visible(False)

Mouse_Brain.ipynb at commit abd5064, no license · at the source

Overview

Authors: Xingyi Li1,2, Dongmin Zhao1, Xiangting Jia1, Gaoyuan Du1, Jialuo Xu1, Yang Qi1, Yiqi Chen1, Yingfu Wu1, Jia Gu2, Junnan Zhu3, Xuequn Shang1
ORCID iDs: Xingyi Li, Yang Qi, Yingfu Wu
  1. School of Computer Science, Northwestern Polytechnical University, Shaanxi, 710129, China
  2. Faculty of Data Science, City University of Macau, Macau, Macau 999078, China
  3. State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, 100190, China
Institutions: Northwestern Polytechnical University (China); City University of Macau (Macao SAR China); Chinese Academy of Sciences (China); Institute of Automation (China)
Journal: Bioinformatics (Oxford, England), volume 42, issue 8, article btag540
Dates: received 21 May 2026; accepted 16 July 2026; published online 21 July 2026; in print August 2026
Type: Research article · Language: English
License: CC BY
Identifiers: DOI 10.1093/bioinformatics/btag540 · PMID 42482153 · PMCID PMC13453310 · OpenAlex W7170084557
Open access: gold, a free copy (OpenAlex)
Status: code verified (how the code is found and verified)
Categories: genetics / omics (modality), human (organism), mouse (organism), Alzheimer's / dementia (population), methods / tools (subfield)
Methods: Connectivity, Machine learning, Statistics
MeSH: Computational Biology*, Gene Expression Profiling*, Spatial Transcriptomics*, Transcriptome*, Alzheimer Disease, Animals, Brain, Breast Neoplasms, Humans, Mice (* major topic)
Journal subjects: Systems Biology
Topic: Single-cell and spatial transcriptomics (Molecular Biology, Biochemistry, Genetics and Molecular Biology), according to OpenAlex
Funding: National Natural Science Foundation of China (62433016); Fundamental and Interdisciplinary Disciplines Breakthrough Plan of the Ministry of Education of China (JYB2025XDXM202); Macau Young Scholars Program (AM2024027); Young Talent fund of Xi’an Association for science and technology (0959202513204)
Citations: not cited yet (Europe PMC); 42 references in the paper

Abstract

Motivation: Advances in spatial transcriptomics (ST) technologies have made it possible to jointly acquire gene expression and histological image information while preserving spatial coordinates. This breakthrough presents unprecedented opportunities for the precise dissection of spatial heterogeneity in complex tissues. However, existing computational methods remain limited in their capacity for effective integration and synergistic modelling of multimodal ST data.

Results: We propose SpatialModal, a multimodal graph learning framework that learns robust joint representations by combining a hierarchical representation strategy with a dual-level contrastive learning mechanism. We perform extensive validation of SpatialModal across diverse ST datasets spanning human and mouse tissues. The results demonstrate that SpatialModal effectively reveals intricate brain architectures in humans and mice, dissects tumour microenvironment heterogeneity in breast cancer, delineates Alzheimer’s disease patterns, and characterizes spatiotemporal developmental trajectories within the embryonic heart, underscoring its capability to decipher the spatial heterogeneity of biological tissues. Furthermore, SpatialModal exhibits remarkable versatility and robustness, maintaining superior efficacy even on unimodal datasets devoid of histological images, thereby ensuring its broad applicability across diverse ST platforms.

Availability and Implementation: SpatialModal is implemented in Python and is freely available at https://github.com/xingyili/SpatialModal. The source code used in this study has been archived on Zenodo at DOI: https://doi.org/10.5281/zenodo.21264356. All datasets used in this study are publicly available at https://doi.org/10.5281/zenodo.18220735.

Reproduced under the paper's license (CC BY), from the paper cited above.

Repositories

Its files are read in the Code ↔ Paper reader above, with 6 matches between paragraphs and lines of code.

xingyili/SpatialModal

License: none: the authors keep all their rights
State: the link answers, verified on 26 September 2026
Evidence: files inventoried
Commit: abd50647998a8ce44cd4de47dba3029f38cfc62f, 8 July 2026
Languages: Jupyter (5), Python (4)
Size: 15 files, 9 scripts
Software Heritage: not archived
Found in: “Data availability”
Holds: README, environment (environment.yml), 5 notebooks
Not found: license file, CITATION.cff, tests, continuous integration, documentation
Tools: scikit-learn (9 files), PyTorch (8 files), Scanpy (7 files), NumPy (6 files), pandas (6 files), Matplotlib (5 files), SciPy (3 files), anndata (2 files), seaborn (2 files), Squidpy (2 files), h5py (1 file), imageio (1 file), Numba (1 file), Pillow (1 file), PyTorch Geometric (1 file), rpy2 (1 file)
Availability: 1 check, the latest on 26 September 2026: the link answers
  • 26 September 2026: the link answers
10 files
At the source: github.com/xingyili/SpatialModal

Zenodo 21264356

License: CC-BY-4.0
State: the link answers, verified on 26 September 2026
Evidence: files inventoried
Size: 1 file
Software Heritage: not checked
Found in: “Data availability”
Not found: README, license file, CITATION.cff, environment file, tests, continuous integration, documentation
Tools: scikit-learn (9 files), PyTorch (8 files), Scanpy (7 files), NumPy (6 files), pandas (6 files), Matplotlib (5 files), SciPy (3 files), anndata (2 files), seaborn (2 files), Squidpy (2 files), h5py (1 file), imageio (1 file), Numba (1 file), Pillow (1 file), PyTorch Geometric (1 file), rpy2 (1 file)
Availability: 1 check, the latest on 26 September 2026: the link answers (HTTP 200)
  • 26 September 2026: the link answers (HTTP 200)
10 files
At the source: doi.org/10.5281/zenodo.21264356

Availability and Implementation

SpatialModal is implemented in Python and is freely available at https://github.com/xingyili/SpatialModal. The source code used in this study has been archived on Zenodo at DOI: https://doi.org/10.5281/zenodo.21264356. All datasets used in this study are publicly available at https://doi.org/10.5281/zenodo.18220735.

Reproduced under the paper's license (CC BY), from the paper cited above.

Tracing map

Proposed by the machine: these links were found in the paper and verified at the source, without human review. The map will receive a Zenodo DOI once one of the paper's authors has validated it with their ORCID.

What the map holds:

  • 2 repositories of the authors' code, each at its verified commit, with its license and how the link was found in the paper;
  • 18 scripts, each with its path and the digest of its content;
  • 6 matches between paragraphs of the paper and lines of the code (method lexical-v1);
  • neither the text of the paper nor the code itself.

Its JSON (tracing-map.json) is deposited on Zenodo with its DOI once the map is validated.

Data

Datasets cited

Data availability

The data underlying this article are publicly available on Zenodo at https://doi.org/10.5281/zenodo.18220735. The SpatialModal source code is openly accessible through GitHub at https://github.com/xingyili/SpatialModal, and the version used to generate the results reported in this study has been permanently archived on Zenodo at https://doi.org/10.5281/zenodo.21264356

Reproduced under the paper's license (CC BY), from the paper cited above.

Versions

The history of this record: each version stored by the harvester or made by a correction of its authors or of the maintainers of its code, and what changed in its facts. The texts of the paper (its abstract, its availability statements) are not part of it; versions that changed only those are not listed.

Version 1, 27 September 2026: the first record

Recorded: type, language, journal, volume, issue, pages, dates, 11 authors, 10 MeSH terms, 4 funders, 38 references.

Cite

This paper

Li, X., Zhao, D., Jia, X., Du, G., Xu, J., Qi, Y., Chen, Y., Wu, Y., Gu, J., Zhu, J., & Shang, X. (2026). Deciphering spatial heterogeneity by multimodal spatial transcriptomics modelling with SpatialModal. Bioinformatics (Oxford, England), 42(8), btag540. https://doi.org/10.1093/bioinformatics/btag540

BibTeX

@article{li2026deciphering,
author = {Li, Xingyi and Zhao, Dongmin and Jia, Xiangting and Du, Gaoyuan and Xu, Jialuo and Qi, Yang and Chen, Yiqi and Wu, Yingfu and Gu, Jia and Zhu, Junnan and Shang, Xuequn},
title = {{Deciphering spatial heterogeneity by multimodal spatial transcriptomics modelling with SpatialModal}},
journal = {Bioinformatics (Oxford, England)},
year = {2026},
month = aug,
volume = {42},
number = {8},
pages = {btag540},
publisher = {Oxford University Press},
issn = {1367-4803},
doi = {10.1093/bioinformatics/btag540},
url = {https://doi.org/10.1093/bioinformatics/btag540},
pmid = {42482153},
pmcid = {PMC13453310}
}

RIS

TY - JOUR
AU - Li, Xingyi
AU - Zhao, Dongmin
AU - Jia, Xiangting
AU - Du, Gaoyuan
AU - Xu, Jialuo
AU - Qi, Yang
AU - Chen, Yiqi
AU - Wu, Yingfu
AU - Gu, Jia
AU - Zhu, Junnan
AU - Shang, Xuequn
TI - Deciphering spatial heterogeneity by multimodal spatial transcriptomics modelling with SpatialModal
T2 - Bioinformatics (Oxford, England)
J2 - Bioinformatics
PY - 2026
DA - 2026/08/01
VL - 42
IS - 8
SP - btag540
SN - 1367-4803
PB - Oxford University Press
DO - 10.1093/bioinformatics/btag540
UR - https://doi.org/10.1093/bioinformatics/btag540
LA - en
ER -

CSL-JSON

{
"id": "10.1093/bioinformatics/btag540",
"type": "article-journal",
"title": "Deciphering spatial heterogeneity by multimodal spatial transcriptomics modelling with SpatialModal",
"container-title": "Bioinformatics (Oxford, England)",
"author": [
{
"family": "Li",
"given": "Xingyi"
},
{
"family": "Zhao",
"given": "Dongmin"
},
{
"family": "Jia",
"given": "Xiangting"
},
{
"family": "Du",
"given": "Gaoyuan"
},
{
"family": "Xu",
"given": "Jialuo"
},
{
"family": "Qi",
"given": "Yang"
},
{
"family": "Chen",
"given": "Yiqi"
},
{
"family": "Wu",
"given": "Yingfu"
},
{
"family": "Gu",
"given": "Jia"
},
{
"family": "Zhu",
"given": "Junnan"
},
{
"family": "Shang",
"given": "Xuequn"
}
],
"container-title-short": "Bioinformatics",
"volume": "42",
"issue": "8",
"page": "btag540",
"DOI": "10.1093/bioinformatics/btag540",
"PMID": "42482153",
"PMCID": "PMC13453310",
"ISSN": "1367-4803",
"publisher": "Oxford University Press",
"URL": "https://doi.org/10.1093/bioinformatics/btag540",
"language": "en",
"issued": {
"date-parts": [
[
2026,
8,
1
]
]
}
}

The tracing map gets a citation of its own once an author has validated it and it has a DOI.

Similar papers

The papers with a page that share the most with this one: the tools found in their code, their categories, datasets, cited references and authors, the rarest counting most.

[1] doi:10.1002/advs.75969 [code]
Accurately Deciphering Tissue Heterogeneity From Spatial Multi-Modal and Multi-Omics With STransformer.
Journal: Advanced science (Weinheim, Baden-Wurttemberg, Germany)
In common: PyTorch Geometric, anndata, Scanpy, 7 other tools, Alzheimer's / dementia, genetics / omics, mouse, 14 references, author Xingyi Li
[2] doi:10.1002/advs.77003 [code]
SemanticST: A Scalable Multi-Contextual Graph Learning Framework for Uncovering Spatial Niches and Robust Multi-Sample Integration in Spatial Transcriptomics.
Journal: Advanced science (Weinheim, Baden-Wurttemberg, Germany)
In common: PyTorch Geometric, rpy2, anndata, 10 other tools, methods / tools, genetics / omics, 15 references
[3] doi:10.1038/s41592-026-03034-9 [code]
3d-OT: a deep geometry-aware framework for heterogeneous slices alignment of spatial multi-omics.
Journal: Nature methods
In common: Squidpy, PyTorch Geometric, rpy2, 11 other tools, genetics / omics, mouse, 12 references
[4] doi:10.1093/bib/bbaf316 [code]
TriCLFF: a multi-modal feature fusion framework using contrastive learning for spatial domain identification.
Journal: Briefings in bioinformatics
In common: PyTorch Geometric, rpy2, anndata, 9 other tools, genetics / omics, mouse, 14 references
[5] doi:10.1038/s41592-026-03194-8 [code]
Beyond benchmarking: an expert-guided consensus approach to spatially aware clustering.
Journal: Nature methods
In common: Squidpy, PyTorch Geometric, rpy2, 10 other tools, methods / tools, genetics / omics, 11 references
[6] doi:10.1186/s12864-024-10469-x [code]
HyperGCN: an effective deep representation learning framework for the integrative analysis of spatial transcriptomics data.
Journal: BMC genomics
In common: Squidpy, PyTorch Geometric, rpy2, 11 other tools, genetics / omics, mouse, 10 references
[7] doi:10.1038/s41467-023-44367-9 [code]
MENDER: fast and scalable tissue structure identification in spatial omics data.
Journal: Nature communications
In common: Squidpy, PyTorch Geometric, rpy2, 10 other tools, methods / tools, genetics / omics, 11 references
[8] doi:10.1093/bib/bbaf674 [code]
Probabilistic-graph-based spatial context-aware framework for interpretable spatial omics denoising and augmentation.
Journal: Briefings in bioinformatics
In common: Squidpy, rpy2, imageio, 11 other tools, methods / tools, 10 references
[9] doi:10.1093/bioinformatics/btaf350 [code]
Gene spatial integration: enhancing spatial transcriptomics analysis via deep learning and batch effect mitigation.
Journal: Bioinformatics (Oxford, England)
In common: Squidpy, rpy2, anndata, 8 other tools, genetics / omics, 12 references
[10] doi:10.1093/bib/bbag298 [code]
Empowering multifaceted analysis of spatial transcriptomics data with RGAST.
Journal: Briefings in bioinformatics
In common: PyTorch Geometric, rpy2, anndata, 9 other tools, methods / tools, genetics / omics, mouse, 10 references

Contribute

The authors of this paper can claim it, correct its record and validate its tracing map, and the maintainers of its code (its owner, or a public member of its organization) correct what it says of their repository; anyone signed in can ask for its removal. Every request goes to OSCR's own machine, which answers it; your account page follows them.

Sign in with ORCID to claim this paper as one of its authors, correct its record or validate its tracing map: when the paper's metadata lists your ORCID iD, you are recognized at once. Maintainers of its code: sign in with GitHub, then claim the repository on your account page.

Add the badge to the code's README

OSCR: the badge of this paper

If you are an author or a maintainer of this paper's code, you can add this badge. It says what OSCR knows of the paper (its code, its validated tracing map) and links the code to this page. Paste one of these snippets under the README's title. Keep the two marks around it, so that the badge can be replaced in place and is never added twice. OSCR changes nothing in your repository.

Markdown
<!-- oscr-badge:start -->
[![OSCR](https://openscicode.org/badge/doi/10.1093/bioinformatics/btag540.svg)](https://openscicode.org/badge/doi/10.1093/bioinformatics/btag540)
<!-- oscr-badge:end -->
reStructuredText
.. oscr-badge:start

.. image:: https://openscicode.org/badge/doi/10.1093/bioinformatics/btag540.svg
   :target: https://openscicode.org/badge/doi/10.1093/bioinformatics/btag540
   :alt: OSCR

.. oscr-badge:end
HTML
<!-- oscr-badge:start -->
<a href="https://openscicode.org/badge/doi/10.1093/bioinformatics/btag540"><img src="https://openscicode.org/badge/doi/10.1093/bioinformatics/btag540.svg" alt="OSCR"></a>
<!-- oscr-badge:end -->

On GitHub, open the README, choose Edit (the pencil), paste the snippet under the title, then "Commit changes".

If you choose to, you can have the badge kept up to date for you, with oscr badge --write from the command line or with the GitHub Action in your repository's workflows. Every other form and option (a card, AsciiDoc, LaTeX, shields.io) is on the badge page.

Request its removal

To ask OSCR to remove this record, the copies of its authors' scripts or its tracing map, use the removal request page: signed in, you say who you are, what to remove and why, then review and confirm the request. Published rules decide every request (how).

Discussion, reproductions, activity

Discussion: code errors and mismatches between the code and the paper about this paper and its code, from readers and its authors, beside the paper and its tracing map.

Report a mismatch between the code and the paper · Report a code error (signed in)

Reproductions: reports from readers who ran the authors' code and did not get the paper's result, what they ran, with which environment, commit and data.

Report a reproduction failure (signed in)

Versions of its code: the releases of its code tied to a version of this paper (the preprint, the accepted manuscript, the version of record…), each with the tracing map versioned with it.

Activity: what happens around this paper: new versions of its record, its map's validation, discussions and reproductions. It opens with sign-in.