SPOmiAlign: a modality-agnostic computational framework for multimodal spatial omics alignment enabled by a feature matching foundation model.

Code ↔ Paper

8 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 8 matches

[1] § Methods › Data preprocessing in SPOmiAlign ↔ SHARP-Track/Convert_CCF_Coords_to_FP_Regions.m, lines 11–47 · score 0.77 · coordinate transformation, Allen CCF, annotation volume, mouse brain, Brain Atlas, spaced
[2] § Methods › Data preprocessing in SPOmiAlign ↔ Tutorial/Tutorial 1 omic-to-image (spatial transcriptomics to CCF)/spatial transcriptomic section (Slide-seq_29) to Allen Brain Atlas.ipynb, lines 44–77 · score 0.64 · Allen Brain Atlas, Slide seq, SSI rendering, UMI, radius, filtered
[3] § Results › SPOmiAlign enables registration of spatial omic sections to the common coordinate framework and anatomical annotation retrieval ↔ Tutorial/Tutorial 1 omic-to-image (spatial transcriptomics to CCF)/spatial transcriptomic section (Slide-seq_29) to Allen Brain Atlas.py, lines 56–75 · score 0.56 · Allen Brain Atlas, Slide seq, spatial transcriptomic, spot, CCF
[4] § Methods › Differential analysis of multiomic data ↔ Flow2Spatial/model/utils.py, lines 216–273 · score 0.55 · AnnData, Scanpy, protein, gene, matrices, intensity
[5] § Results › SPOmiAlign enables registration of spatial omic sections to the common coordinate framework and anatomical annotation retrieval ↔ Tutorial/Tutorial 1 omic-to-image (spatial transcriptomics to CCF)/spatial transcriptomic section (Slide-seq_29) to Allen Brain Atlas.ipynb, lines 1–42 · score 0.55 · Allen Brain Atlas, Slide seq, image alignment, spatial omics, SPOmiAlign
[6] § Methods › Data preprocessing in SPOmiAlign ↔ Tutorial/Tutorial 1 omic-to-image (spatial transcriptomics to CCF)/spatial transcriptomic section (Slide-seq_29) to Allen Brain Atlas.ipynb, lines 44–77 · score 0.54 · spatial transcriptomic, manual rotation, UMI, SSI, radius, seq
[7] § Methods › Data preprocessing in SPOmiAlign ↔ Tutorial/Tutorial 1 omic-to-image (spatial transcriptomics to CCF)/spatial transcriptomic section (Slide-seq_29) to Allen Brain Atlas.py, lines 56–75 · score 0.54 · Allen Brain Atlas, Slide seq, UMI, SSI, radius, spots
[8] § Methods › Data preprocessing in SPOmiAlign ↔ SHARP-Track/Analyze_ROIs.m, lines 81–154 · score 0.52 · reference spaces, ROIs, sagittal, coronal, Allen, pixel

Paper

Loaded from Europe PMC by your browser, not stored by OSCR: doi.org · Europe PMC

The paper is loaded when this pane is shown.

The paper is loaded by your browser, with JavaScript: read it at doi.org or on Europe PMC.

The authors' code

Jupyter notebook · 144 lines · 4.8 KB · no license · 3 matches

# %% [markdown]
# # spatial transcriptomic section (Slide-seq_29) to Allen Brain Atlas
#
# This tutorial demonstrates omic-to-image alignment by registering the Slide-seq_29 spatial omics section to the Allen Brain Atlas image reference.
#
# Tutorial 1: spatial omics to CCF (omic-to-image)
# %% [markdown]
# ## 1. Load package and data paths
# %%
from pathlib import Path
import sys
import matplotlib.pyplot as plt
import cv2
try:
START_DIR = Path(__file__).resolve().parent
except NameError:
START_DIR = Path.cwd()
PROJECT_ROOT = next(
candidate for candidate in (START_DIR, *START_DIR.parents)
if (candidate / "SPOmiAlign").is_dir()
)
spomialign_path = PROJECT_ROOT / "SPOmiAlign"
if str(spomialign_path) not in sys.path:
sys.path.insert(0, str(spomialign_path))
from tutorial_utils import (
generate_ssi_visualization,
get_tutorial_paths,
run_omic_to_image_alignment,
read_bgr,
)
DATA_DIR, OUTPUT_ROOT = get_tutorial_paths(PROJECT_ROOT)
SAMPLE_ID = "PUCK29"
SOURCE_OMIC_PATH = "Tutorial 1 spatial omics to CCF (omic-to-image)/Puck_Num_29.h5ad"
TARGET_IMAGE_PATH = "Tutorial 1 spatial omics to CCF (omic-to-image)/CCF_100048576_205.png"
SSI_IMAGE_PATH = None
%matplotlib inline
# %% [markdown]
# ## 2. Parameter settings
#
# | Parameter | Meaning |
# | --- | --- |
# | `SAMPLE_ID` | Output folder name under `output/h5ad_2_img/`. |
# | `SOURCE_OMIC_PATH` | Source spatial omics h5ad path in data. |
# | `TARGET_IMAGE_PATH` | Reference image path in data. |
# | `SSI_IMAGE_PATH` | The path of rendered SSI image. |
# | `manual_rotate` | Clockwise manual rotation applied when rendering the source h5ad into SSI. |
# | `SSI_dpi` | SSI rendering resolution. The default value is 150. |
# | `x_coordinate` / `y_coordinate` | Spot coordinate columns used for SSI rendering. |
# | `SPOT_UMI` | UMI is calculated by default; use this h5ad obs key if available. |
# | `threshold_percentile` | Optional intensity(UMI) percentile filter; `None` keeps all valid spots. |
# | `SPOT` | Spot shape (`square` / `circle`) and visualization radius. |
# | `Alignment_mode` | SPOmiAlign supports three alignment modes: Rigid (`Rigid`), Affine (`Affine`, `Homography`), and Non-Rigid (`bspline`, `affine+bspline`). |
# | `device` | Torch device used by alignment, for example `cuda:0`, `cuda:1`, or `cpu`; `None` keeps automatic selection. |
# %%
SSI_PARAMS = {
"manual_rotate": 180,
"SSI_dpi": 150,
"x_coordinate": "Raw_Slideseq_X",
"y_coordinate": "Raw_Slideseq_Y",
"SPOT_UMI": "nFeature_Spatial",
"threshold_percentile": 80,
"SPOT": {"shape": "circle", "radius": 5},
}
ALIGNMENT_PARAMS = {
"Alignment_mode": "affine+bspline",
"device": "cuda:0",
}
SAMPLE_ID, SOURCE_OMIC_PATH, TARGET_IMAGE_PATH, SSI_IMAGE_PATH, SSI_PARAMS, ALIGNMENT_PARAMS
# %% [markdown]
# ## 3. Generate SSI image
#
# The SSI image is generated from the spatial omics h5ad before alignment. For these Slide-seq examples, spot coordinates are read from `Raw_Slideseq_X` and `Raw_Slideseq_Y`, and spot intensity is read from `nFeature_Spatial`.
# %%
ssi = generate_ssi_visualization(
data_root=DATA_DIR,
output_root=OUTPUT_ROOT,
sample_id=SAMPLE_ID,
source_omic_path=SOURCE_OMIC_PATH,
**SSI_PARAMS,
)
images=[ssi["source_section_visualization"]]
titles=["Generated SSI"]
figsize=(6, 6)
titles = titles or ["" for _ in images]
if figsize is None:
figsize = (5.5 * len(images), 5.5)
fig, axes = plt.subplots(1, len(images), figsize=figsize)
if len(images) == 1:
axes = [axes]
for ax, image_or_path, title in zip(axes, images, titles):
image = read_bgr(image_or_path) if isinstance(image_or_path, (str, Path)) else image_or_path
ax.imshow(cv2.cvtColor(image, cv2.COLOR_BGR2RGB))
ax.set_title(title)
ax.axis("off")
plt.tight_layout()
plt.show()
# %% [markdown]
# ## 4. Run SPOmiAlign
# %%
result = run_omic_to_image_alignment(
data_root=DATA_DIR,
output_root=OUTPUT_ROOT,
sample_id=SAMPLE_ID,
source_omic_path=SOURCE_OMIC_PATH,
target_image_path=TARGET_IMAGE_PATH,
SSI_IMAGE_PATH=SSI_IMAGE_PATH,
**SSI_PARAMS,
**ALIGNMENT_PARAMS,
)
# %% [markdown]
# ## 5. Outputs
# %%
images=[result["source_section_visualization"], result["target_section_visualization"], result["overlay"]]
titles=["Generated SSI", "CCF reference", "Aligned slice overlay"]
figsize=(6, 6)
titles = titles or ["" for _ in images]
if figsize is None:
figsize = (5.5 * len(images), 5.5)
fig, axes = plt.subplots(1, len(images), figsize=figsize)
if len(images) == 1:
axes = [axes]
for ax, image_or_path, title in zip(axes, images, titles):
image = read_bgr(image_or_path) if isinstance(image_or_path, (str, Path)) else image_or_path
ax.imshow(cv2.cvtColor(image, cv2.COLOR_BGR2RGB))
ax.set_title(title)
ax.axis("off")
plt.tight_layout()
plt.show()
print("Save transformed h5ad path to ", result["transformed_h5ad"])

spatial transcriptomic section (Slide-seq_29) to Allen Brain Atlas.ipynb at commit c7f8b7a, no license · at the source

Overview

Authors: Yi Wang^1,2, Zihang He³, Yunjie Yan⁴

ORCID iDs: Yi Wang, Zihang He

Liangzhu Laboratory, Zhejiang University School of Medicine, No. 1369 Wenyi West Road, Yuhang District, Hangzhou, Zhejiang Province 311113, China
Zhejiang Key Laboratory of Multi-Omics in Infection and Immunity, Center for Infectious Disease Research, School of Medicine, Westlake University, No. 18 Shilongshan Street, Zhuantang Subdistrict, Xihu District, Hangzhou, Zhejiang Province 310024, China
Zhejiang University-University of Edinburgh Institute (ZJE), Zhejiang University School of Medicine, Zhejiang University, 718 East Haizhou Road, Haining, 314400, China
Sir Run Run Shaw Hospital, School of Medicine, Zhejiang University, 3 East Qingchun Road, Hangzhou, 310016, China

Institutions: Zhejiang University-University of Edinburgh Institute (China); Sir Run Run Shaw Hospital (China); Zhejiang University (China)

Journal: Briefings in bioinformatics, volume 27, issue 3, article bbag331

Dates: received 21 February 2026; accepted 24 May 2026; published online 21 June 2026; in print May 2026

Type: Research article · Language: English

License: CC BY

Identifiers: DOI 10.1093/bib/bbag331 · PMID 42323879 · PMCID PMC13283438 · OpenAlex W7165478251

Open access: gold, a free copy (OpenAlex)

Status: code verified

Categories: genetics / omics (modality), mouse (organism), methods / tools (subfield)

Methods: Statistics, Smoothing, state filtering, decompositions, Connectivity, Machine learning, fMRI & imaging, Spectral & time-frequency

Keywords: spatial multimodal alignment, feature matching, foundation model, common coordinate framework, spatial multi-omics integration

MeSH: Computational Biology*, Proteomics*, Software*, Algorithms, Animals, Brain, Metabolomics, Mice, Multiomics, Spatial Transcriptomics (* major topic)

Topic: Single-cell and spatial transcriptomics (Molecular Biology, Biochemistry, Genetics and Molecular Biology), according to OpenAlex

Funding: National Key Research and Development Program of China (2024YFA1306600); Yuhang District Postdoctoral Research Funding Program

Citations: not cited yet (Europe PMC); 47 references in the paper

Abstract

Multimodal spatial omics enables systematic characterization of tissue organization by jointly profiling transcriptomic, proteomic, metabolomic, and other spatially resolved modalities within their spatial context. A central challenge in realizing this potential is achieving robust spatial alignment across modalities and sections. Although numerous alignment methods have been developed, most are designed for single-modality sections or specific modality combinations, with few enabling modality-agnostic alignment. Cross-modal alignment remains difficult due to the absence of shared molecular features, partial spatial overlap, and nonrigid tissue deformations. To address these challenges, we introduce SPOmiAlign, a modality-agnostic framework for spatial multimodal alignment, enabled by a feature-matching foundation model that serves as a general computational primitive for spatial multi-omics alignment. The framework enables accurate cross-modal spatial alignment without manual intervention or modality-specific tuning. Across diverse multimodal benchmarks, SPOmiAlign consistently achieves higher alignment accuracy than existing methods. We further demonstrate its utility through automated registration to a common coordinate framework, enabling standardized anatomical annotation. Finally, applying SPOmiAlign to integrate spatial transcriptomic, proteomic, and metabolomic data in mouse brain facilitates the identification of spatial domains that were difficult to resolve with less accurate registration, highlighting its utility for multi-omic integration and biological interpretation.

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 8 matches between paragraphs and lines of code.

cortex-lab/allenccf

License: none: the authors keep all their rights

State: the link answers, verified on 27 September 2026

Evidence: files inventoried

Commit: e5a57fe7e1c9fb333fec51c29a8471131c233a76, 15 July 2025

Languages: MATLAB (61)

Size: 75 files, 61 scripts

Software Heritage: not archived

Found in: “Data availability”

Holds: README

Not found: license file, CITATION.cff, environment file, tests, continuous integration, documentation

Tools: Image Processing Toolbox (7 files), Statistics and Machine Learning Toolbox (1 file)

Availability: 1 check, the latest on 27 September 2026: the link answers

27 September 2026: the link answers

62 files

Browsing Functions/AtlasTransformBrowser.m, MATLAB, 1,196 lines
Browsing Functions/CCF_to_FP.m, MATLAB, 66 lines
Browsing Functions/addAllenCtxOutlines.m, MATLAB, 51 lines
Browsing Functions/aggregateAcr.m, MATLAB, 146 lines
Browsing Functions/allenAtlasBrowser.m, MATLAB, 658 lines
Browsing Functions/allenAtlasBrowser_original.m, MATLAB, 262 lines
Browsing Functions/allenCCFbregma.m, MATLAB, 8 lines
Browsing Functions/allenTilt.m, MATLAB, 172 lines
Browsing Functions/allen_ccf_2pi.m, MATLAB, 780 lines
Browsing Functions/allen_ccf_colormap.m, MATLAB, 10 lines
Browsing Functions/allen_ccf_npx.m, MATLAB, 1,087 lines
Browsing Functions/allen_ccf_npx_4shank.m, MATLAB, 931 lines
Browsing Functions/allen_ccf_npx_4shank_spherical.m, MATLAB, 987 lines
Browsing Functions/best_fit_line.m, MATLAB, 28 lines
Browsing Functions/customVectorSlice.m, MATLAB, 38 lines
Browsing Functions/distinguishable_colors.m, MATLAB, 152 lines
Browsing Functions/get_offset_map.m, MATLAB, 41 lines
Browsing Functions/gridIn3D.m, MATLAB, 80 lines
Browsing Functions/hierarchicalSelect.m, MATLAB, 130 lines
Browsing Functions/idRegionByAcr.m, MATLAB, 27 lines
Browsing Functions/isAreaOrContains.m, MATLAB, 31 lines
Browsing Functions/loadCCFtoFP.m, MATLAB, 17 lines
Browsing Functions/loadFPtable.m, MATLAB, 16 lines
Browsing Functions/loadStructureTree.m, MATLAB, 48 lines
Browsing Functions/makeSTtree.m, MATLAB, 45 lines
Browsing Functions/makeSmoothCoords.m, MATLAB, 23 lines
Browsing Functions/natsort.m, MATLAB, 330 lines
Browsing Functions/natsortfiles.m, MATLAB, 169 lines
Browsing Functions/plotAVoverlay.m, MATLAB, 28 lines
Browsing Functions/plotAVslice.m, MATLAB, 13 lines
Browsing Functions/plotAsProbe.m, MATLAB, 37 lines
Browsing Functions/plotBrainGrid.m, MATLAB, 35 lines
Browsing Functions/plotBrainOutlinesByAxis.m, MATLAB, 23 lines
Browsing Functions/plotDistToNearest.m, MATLAB, 123 lines
Browsing Functions/plotDistToNearestToTip.m, MATLAB, 252 lines
Browsing Functions/plotLabelsAsProbe.m, MATLAB, 110 lines
Browsing Functions/plotNeuronOnSliceFromCoord.m, MATLAB, 20 lines
Browsing Functions/plotTVslice.m, MATLAB, 12 lines
Browsing Functions/plotTopDownOutlines.m, MATLAB, 100 lines
Browsing Functions/sagittalSlices.m, MATLAB, 50 lines
Browsing Functions/sanitizeStructureTree.m, MATLAB, 31 lines
Browsing Functions/script_sliceMovie.m, MATLAB, 66 lines
Browsing Functions/selectStructure.m, MATLAB, 264 lines
Browsing Functions/sliceBrowser.m, MATLAB, 142 lines
Browsing Functions/sliceByVector.m, MATLAB, 55 lines
Browsing Functions/sliceOutlineWithRegion.m, MATLAB, 38 lines
Browsing Functions/sliceOutlineWithRegionVec.m, MATLAB, 74 lines
Browsing Functions/transformed_sliceBrowser.m, MATLAB, 171 lines
Histology Functions/HistologyBrowser.m, MATLAB, 161 lines
Histology Functions/HistologyCropper.m, MATLAB, 105 lines
Histology Functions/SliceFlipper.m, MATLAB, 177 lines
Histology Functions/natsort.m, MATLAB, 330 lines
Histology Functions/natsortfiles.m, MATLAB, 169 lines
SHARP-Track/Analyze_Clicked_Points.m, MATLAB, 131 lines
SHARP-Track/Analyze_ROIs.m, MATLAB, 158 lines, 1 match
SHARP-Track/Convert_CCF_Coords_to_FP_Regions.m, MATLAB, 117 lines, 1 match
SHARP-Track/Convert_Clicked_Points_to_FP_coords.m, MATLAB, 145 lines
SHARP-Track/Display_Probe_Track.m, MATLAB, 229 lines
SHARP-Track/Navigate_Atlas_and_Register_Slices.m, MATLAB, 66 lines
SHARP-Track/Process_Histology.m, MATLAB, 133 lines
setup_utils.m, MATLAB, 47 lines
README.md, Text, 72 lines

At the source: github.com/cortex-lab/allenCCF/blob/master/structure_tree_safe_2017.csv

gpenglab/misar-seq

License: none: the authors keep all their rights

State: the link answers, verified on 27 September 2026

Evidence: files inventoried

Commit: 6fdceee0aa05e85473bbde84eeafdee5af7f8a9f, 4 September 2026

Languages: R (5), Python (4), Shell (1)

Size: 26 files, 10 scripts

Software Heritage: not checked

Found in: “Data availability”

Holds: README

Not found: license file, CITATION.cff, environment file, tests, continuous integration, documentation

Tools: tidyverse (4 files), Biopython (2 files), clusterProfiler (2 files), igraph (2 files), NumPy (2 files), patchwork (2 files), reticulate (2 files), Seurat (2 files), deepTools (1 file), Matplotlib (1 file), Numba (1 file), OpenCV (1 file), pandas (1 file), Scanpy (1 file), SciPy (1 file)

Availability: 1 check, the latest on 27 September 2026: the link answers

27 September 2026: the link answers

11 files

MISAR-seq.R, R, 304 lines
MISAR-seq.sh, Shell, 58 lines
MISAR-seq_new.R, R, 383 lines
Python/Grid_filter.py, Python, 50 lines
Python/MISAR_Split_BC_ATAC.py, Python, 31 lines
Python/MISAR_Split_BC_RNA.py, Python, 30 lines
Python/utils.py, Python, 52 lines
R/DER.R, R, 447 lines
R/function.R, R, 767 lines
R/function_new.R, R, 921 lines
README.md, Text, 25 lines

At the source: github.com/gpenglab/MISAR-seq/blob/main/Data/Download

bioinfo-biols/flow2spatial

License: GPL-3.0

State: the link answers, verified on 27 September 2026

Evidence: files inventoried

Commit: 4ce25791e904dafb677ae93fa052b0acfb75ac91, 16 May 2025

Languages: Python (11)

Size: 36 files, 11 scripts

Software Heritage: not archived

Found in: “Data availability”

Holds: README, license file, environment (setup.py, docs/requirements.txt), documentation

Not found: CITATION.cff, tests, continuous integration

Tools: NumPy (4 files), pandas (4 files), anndata (2 files), Matplotlib (2 files), SciPy (2 files), PyTorch (1 file), scikit-image (1 file)

Availability: 1 check, the latest on 27 September 2026: the link answers

27 September 2026: the link answers

13 files

Flow2Spatial/__init__.py, Python, 9 lines
Flow2Spatial/generator/__init__.py, Python, 8 lines
Flow2Spatial/generator/design_utils.py, Python, 239 lines
Flow2Spatial/generator/generators.py, Python, 138 lines
Flow2Spatial/generator/utils.py, Python, 526 lines
Flow2Spatial/main.py, Python, 11 lines
Flow2Spatial/model/__init__.py, Python, 8 lines
Flow2Spatial/model/dnn_utils.py, Python, 316 lines
Flow2Spatial/model/utils.py, Python, 273 lines, 1 match
docs/conf.py, Python, 66 lines
setup.py, Python, 39 lines
LICENSE, License, 674 lines
README.md, Text, 32 lines

At the source: github.com/bioinfo-biols/Flow2Spatial/tree/main/datasets

wangyiyuyang/SPOmiAlign

License: none: the authors keep all their rights

State: the link answers, verified on 27 September 2026

Evidence: files inventoried

Commit: c7f8b7adeddcbd9c67683e6f9edfd40153b2ea5b, 15 May 2026

Languages: Python (70), Jupyter (4), C++ (1), CUDA (1)

Size: 132 files, 76 scripts

Software Heritage: not checked

Found in: “Data availability”

Holds: README, environment (SPOmiAlign/software/Roma/pyproject.toml, SPOmiAlign/software/Roma/requirements.txt, SPOmiAlign/software/Roma/uv.lock, SPOmiAlign/software/fused-local-corr-master/fused-local-corr-master/pyproject.toml, SPOmiAlign/software/fused-local-corr-master/fused-local-corr-master/requirements.txt, SPOmiAlign/software/fused-local-corr-master/fused-local-corr-master/setup.py), tests, documentation, 4 notebooks

Not found: license file, CITATION.cff, continuous integration

Tools: PyTorch (47 files), NumPy (23 files), Pillow (19 files), OpenCV (18 files), Matplotlib (14 files), Scanpy (5 files), pandas (4 files), SciPy (4 files), h5py (2 files), anndata (1 file), scikit-image (1 file), SimpleITK (1 file)

Availability: 1 check, the latest on 27 September 2026: the link answers

27 September 2026: the link answers

77 files

SPOmiAlign/align_h5ad_to_h5ad_square.py, Python, 944 lines
SPOmiAlign/data_preprocessing.py, Python, 913 lines
SPOmiAlign/reassignment.py, Python, 766 lines
SPOmiAlign/roma.py, Python, 794 lines
SPOmiAlign/software/Roma/demo/demo_3D_effect.py, Python, 47 lines
SPOmiAlign/software/Roma/demo/demo_fundamental.py, Python, 34 lines
SPOmiAlign/software/Roma/demo/demo_match.py, Python, 50 lines
SPOmiAlign/software/Roma/demo/demo_match_opencv_sift.py, Python, 43 lines
SPOmiAlign/software/Roma/demo/demo_match_tiny.py, Python, 77 lines
SPOmiAlign/software/Roma/experiments/eval_roma_outdoor.py, Python, 57 lines
SPOmiAlign/software/Roma/experiments/eval_tiny_roma_v1_outdoor.py, Python, 84 lines
SPOmiAlign/software/Roma/experiments/roma_indoor.py, Python, 322 lines
SPOmiAlign/software/Roma/experiments/train_roma_outdoor.py, Python, 308 lines
SPOmiAlign/software/Roma/experiments/train_tiny_roma_v1_outdoor.py, Python, 498 lines
SPOmiAlign/software/Roma/romatch/__init__.py, Python, 8 lines
SPOmiAlign/software/Roma/romatch/benchmarks/__init__.py, Python, 6 lines
SPOmiAlign/software/Roma/romatch/benchmarks/hpatches_sequences_homog_benchmark.py, Python, 113 lines
SPOmiAlign/software/Roma/romatch/benchmarks/megadepth_dense_benchmark.py, Python, 105 lines
SPOmiAlign/software/Roma/romatch/benchmarks/megadepth_pose_estimation_benchmark.py, Python, 116 lines
SPOmiAlign/software/Roma/romatch/benchmarks/megadepth_pose_estimation_benchmark_poselib.py, Python, 116 lines
SPOmiAlign/software/Roma/romatch/benchmarks/scannet_benchmark.py, Python, 143 lines
SPOmiAlign/software/Roma/romatch/checkpointing/__init__.py, Python, 1 line
SPOmiAlign/software/Roma/romatch/checkpointing/checkpoint.py, Python, 60 lines
SPOmiAlign/software/Roma/romatch/datasets/__init__.py, Python, 2 lines
SPOmiAlign/software/Roma/romatch/datasets/megadepth.py, Python, 232 lines
SPOmiAlign/software/Roma/romatch/datasets/scannet.py, Python, 160 lines
SPOmiAlign/software/Roma/romatch/losses/__init__.py, Python, 1 line
SPOmiAlign/software/Roma/romatch/losses/robust_loss.py, Python, 161 lines
SPOmiAlign/software/Roma/romatch/losses/robust_loss_tiny_roma.py, Python, 160 lines
SPOmiAlign/software/Roma/romatch/models/__init__.py, Python, 1 line
SPOmiAlign/software/Roma/romatch/models/encoders.py, Python, 68 lines
SPOmiAlign/software/Roma/romatch/models/matcher.py, Python, 1,099 lines
SPOmiAlign/software/Roma/romatch/models/model_zoo/__init__.py, Python, 94 lines
SPOmiAlign/software/Roma/romatch/models/model_zoo/roma_models.py, Python, 205 lines
SPOmiAlign/software/Roma/romatch/models/tiny.py, Python, 304 lines
SPOmiAlign/software/Roma/romatch/models/transformer/__init__.py, Python, 48 lines
SPOmiAlign/software/Roma/romatch/models/transformer/dinov2.py, Python, 359 lines
SPOmiAlign/software/Roma/romatch/models/transformer/layers/__init__.py, Python, 12 lines
SPOmiAlign/software/Roma/romatch/models/transformer/layers/attention.py, Python, 96 lines
SPOmiAlign/software/Roma/romatch/models/transformer/layers/block.py, Python, 252 lines
SPOmiAlign/software/Roma/romatch/models/transformer/layers/dino_head.py, Python, 59 lines
SPOmiAlign/software/Roma/romatch/models/transformer/layers/drop_path.py, Python, 35 lines
SPOmiAlign/software/Roma/romatch/models/transformer/layers/layer_scale.py, Python, 28 lines
SPOmiAlign/software/Roma/romatch/models/transformer/layers/mlp.py, Python, 41 lines
SPOmiAlign/software/Roma/romatch/models/transformer/layers/patch_embed.py, Python, 89 lines
SPOmiAlign/software/Roma/romatch/models/transformer/layers/swiglu_ffn.py, Python, 63 lines
SPOmiAlign/software/Roma/romatch/train/__init__.py, Python, 1 line
SPOmiAlign/software/Roma/romatch/train/train.py, Python, 102 lines
SPOmiAlign/software/Roma/romatch/utils/__init__.py, Python, 16 lines
SPOmiAlign/software/Roma/romatch/utils/kde.py, Python, 13 lines
SPOmiAlign/software/Roma/romatch/utils/local_correlation.py, Python, 143 lines
SPOmiAlign/software/Roma/romatch/utils/transforms.py, Python, 118 lines
SPOmiAlign/software/Roma/romatch/utils/utils.py, Python, 661 lines
SPOmiAlign/software/Roma/tests/smoke_test.py, Python, 12 lines
SPOmiAlign/software/Roma/tests/test_match_modes.py, Python, 75 lines
SPOmiAlign/software/Roma/tests/test_mega1500.py, Python, 22 lines
SPOmiAlign/software/Roma/tests/test_mega1500_poselib.py, Python, 14 lines
SPOmiAlign/software/Roma/tests/test_mega_dense.py, Python, 21 lines
SPOmiAlign/software/Roma/tests/test_roma_coarse_inference_time.py, Python, 32 lines
SPOmiAlign/software/Roma/tests/test_roma_coarse_inference_time_cpu.py, Python, 29 lines
SPOmiAlign/software/Roma/tests/test_roma_upsample_inference_time.py, Python, 47 lines
SPOmiAlign/software/fused-local-corr-master/fused-local-corr-master/local_corr/__init__.py, Python, 3 lines
SPOmiAlign/software/fused-local-corr-master/fused-local-corr-master/local_corr/csrc/corr.cpp, C++, 245 lines
SPOmiAlign/software/fused-local-corr-master/fused-local-corr-master/local_corr/csrc/cuda/corr.cu, CUDA, 286 lines
SPOmiAlign/software/fused-local-corr-master/fused-local-corr-master/local_corr/ops.py, Python, 102 lines
SPOmiAlign/software/fused-local-corr-master/fused-local-corr-master/setup.py, Python, 76 lines
SPOmiAlign/software/fused-local-corr-master/fused-local-corr-master/test/test_local_corr.py, Python, 261 lines
SPOmiAlign/tutorial_utils.py, Python, 1,476 lines
Tutorial/Tutorial 1 omic-to-image (spatial transcriptomics to CCF)/spatial transcriptomic section (Slide-seq_29) to Allen Brain Atlas.ipynb, Jupyter, 144 lines, 3 matches
Tutorial/Tutorial 1 omic-to-image (spatial transcriptomics to CCF)/spatial transcriptomic section (Slide-seq_29) to Allen Brain Atlas.py, Python, 136 lines, 2 matches
Tutorial/Tutorial 2 omic-to-omic (spatial multi-omics alignment without paired images)/spatial multi-omics alignment for kidney sections.ipynb, Jupyter, 209 lines
Tutorial/Tutorial 2 omic-to-omic (spatial multi-omics alignment without paired images)/spatial multi-omics alignment for kidney sections.py, Python, 201 lines
Tutorial/Tutorial 2 omic-to-omic (spatial multi-omics alignment without paired images)/spatial multi-omics alignment for mouse brain sections.ipynb, Jupyter, 217 lines
Tutorial/Tutorial 2 omic-to-omic (spatial multi-omics alignment without paired images)/spatial multi-omics alignment for mouse brain sections.py, Python, 199 lines
Tutorial/Tutorial 3 image-to-image (spatial multi-omics alignment with paired images)/spatial multi-omics alignment with paired images.ipynb, Jupyter, 117 lines
Tutorial/Tutorial 3 image-to-image (spatial multi-omics alignment with paired images)/spatial multi-omics alignment with paired images.py, Python, 106 lines
README.md, Text, 74 lines

At the source: github.com/wangyiyuyang/SPOmiAlign

The paper's code and data availability statement is in the Data section.

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:

4 repositories of the authors' code, each at its verified commit, with its license and how the link was found in the paper;
158 scripts, each with its path and the digest of its content;
8 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

alleninstitute.github.io/abc_atlas_access, at alleninstitute.github.io; found in “Data availability”
zenodo:14986870, at Zenodo; found in “Data availability”

Data availability

All datasets used in this study are publicly available. The Slide-seq dataset, a high-throughput sequencing-based spatial transcriptomics technology with near-cellular resolution comprising 101 adult mouse brain coronal sections that span the entire anteroposterior axis, was obtained from an online resource at https://docs.braincelldata.org/downloads/index.html/Slide-seq_Data. The MERFISH dataset, a high-throughput imaging-based spatial transcriptomics technology with single-cell resolution consisting of 25 adult mouse brain sagittal sections, was obtained from the Allen Brain Cell Atlas at https://alleninstitute.github.io/abc_atlas_access/descriptions/Zhuang-ABCA-3.html. The Allen Common Coordinate Framework (CCF) and the corresponding brain region annotations were obtained from the Allen Brain Atlas. Nissl-stained reference images of the adult mouse brain CCF used for alignment are publicly available for coronal views at https://mouse.brain-map.org/experiment/thumbnails/100048576?image_type=atlas and sagittal views at https://mouse.brain-map.org/experiment/thumbnails/100042147?image_type=atlas. Brain region annotations corresponding to the 25 m resolution CCF were downloaded from the file annotation_25.nrrd at https://download.alleninstitute.org/informatics-archive/current-release/mouse_ccf/annotation/ccf_2017/annotation_25.nrrd. The correspondence between the brain region identifiers and the anatomical labels was obtained from structure _tree _safe _2017.csv, available at https://github.com/cortex-lab/allenCCF/blob/master/structure_tree_safe_2017.csv. The MISAR-seq dataset, a spatial multiomic profiling dataset of the mouse brain that jointly measures chromatin accessibility and gene expression, was obtained from a public repository at https://github.com/gpenglab/MISAR-seq/blob/main/Data/Download. The cRCC R114 dataset used in this study, including the spatial transcriptomics and MALDI imaging mass spectrometry-based metabolomics data, was obtained from a public repository at https://zenodo.org/records/14986870. The spatial multiomic mouse brain dataset that integrates MALDI imaging mass spectrometry-based metabolomics, MAGIC-seq spatial transcriptomics, and PLATO spatial proteomics was obtained from a public repository at https://github.com/bioinfo-biols/Flow2Spatial/tree/main/datasets. Source data are provided with this paper. The code for the SPOmiAlign program is available on GitHub at https://github.com/wangyiyuyang/SPOmiAlign. All source code will be released publicly once the manuscript is published.

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, 3 authors, 5 keywords, 10 MeSH terms, 2 funders, 42 references.

Cite

This paper

Wang, Y., He, Z., & Yan, Y. (2026). SPOmiAlign: a modality-agnostic computational framework for multimodal spatial omics alignment enabled by a feature matching foundation model. Briefings in bioinformatics, 27(3), bbag331. https://doi.org/10.1093/bib/bbag331

BibTeX

@article{wang2026spomialign, author = {Wang, Yi and He, Zihang and Yan, Yunjie}, title = {{SPOmiAlign: a modality-agnostic computational framework for multimodal spatial omics alignment enabled by a feature matching foundation model}}, journal = {Briefings in bioinformatics}, year = {2026}, month = may, volume = {27}, number = {3}, pages = {bbag331}, publisher = {Oxford University Press}, issn = {1467-5463}, doi = {10.1093/bib/bbag331}, url = {https://doi.org/10.1093/bib/bbag331}, pmid = {42323879}, pmcid = {PMC13283438} }

RIS

TY - JOUR AU - Wang, Yi AU - He, Zihang AU - Yan, Yunjie TI - SPOmiAlign: a modality-agnostic computational framework for multimodal spatial omics alignment enabled by a feature matching foundation model T2 - Briefings in bioinformatics J2 - Brief Bioinform PY - 2026 DA - 2026/05/01 VL - 27 IS - 3 SP - bbag331 SN - 1467-5463 PB - Oxford University Press DO - 10.1093/bib/bbag331 UR - https://doi.org/10.1093/bib/bbag331 LA - en ER -

CSL-JSON

{ "id": "10.1093/bib/bbag331", "type": "article-journal", "title": "SPOmiAlign: a modality-agnostic computational framework for multimodal spatial omics alignment enabled by a feature matching foundation model", "container-title": "Briefings in bioinformatics", "author": [ { "family": "Wang", "given": "Yi" }, { "family": "He", "given": "Zihang" }, { "family": "Yan", "given": "Yunjie" } ], "container-title-short": "Brief Bioinform", "volume": "27", "issue": "3", "page": "bbag331", "DOI": "10.1093/bib/bbag331", "PMID": "42323879", "PMCID": "PMC13283438", "ISSN": "1467-5463", "publisher": "Oxford University Press", "URL": "https://doi.org/10.1093/bib/bbag331", "language": "en", "issued": { "date-parts": [ [ 2026, 5, 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:10.1038/s42003-026-10957-8 [code]: Brain defence by the extracellular matrix protein Cochlin.
Journal: Communications biology
In common: Biopython, reticulate, igraph, 14 other tools, mouse
[2] doi:10.1016/j.xcrm.2026.102766 [code]: A longitudinal single-cell and spatial multiomic atlas of pediatric high-grade glioma.
Journal: Cell reports. Medicine
In common: anndata, igraph, Numba, 13 other tools, genetics / omics, 1 reference
[3] doi:10.1093/bioinformatics/btag220 [code]: Riemannian metric learning for alignment of spatial multiomics.
Journal: Bioinformatics (Oxford, England)
In common: anndata, Scanpy, PyTorch, 3 other tools, Zenodo 14986870, methods / tools, genetics / omics, mouse, 5 references
[4] doi:10.1038/s41592-026-03194-8 [code]: Beyond benchmarking: an expert-guided consensus approach to spatially aware clustering.
Journal: Nature methods
In common: anndata, igraph, Scanpy, 8 other tools, alleninstitute.github.io/abc_atlas_access, methods / tools, genetics / omics, 2 references
[5] doi:10.1038/s41467-026-71803-3 [code]: Charting the transition from in vitro gliogenesis to the in vivo maturation of human glial progenitor cells transplanted into the hypomyelinated mouse brain.
Journal: Nature communications
In common: deepTools, reticulate, anndata, 11 other tools, genetics / omics, mouse, 1 reference
[6] doi:10.1002/imt2.70163 [code]: Spatial multi-omics unveils sphingolipid metabolic reprogramming within the retinal pathological niche.
Journal: iMeta
In common: anndata, igraph, clusterProfiler, 11 other tools, genetics / omics, mouse, 1 reference
[7] doi:10.1038/s44318-026-00818-9 [code]: FAM134B-mediated ER-phagy degrades APP and suppresses Alzheimer's disease pathology.
Journal: The EMBO journal
In common: Biopython, reticulate, anndata, 11 other tools, mouse
[8] doi:10.1038/s41592-026-03211-w [code]: Spatial isoform sequencing at single-cell resolution reveals cell-type-specific spatial isoform variability in multiple brain cell types.
Journal: Nature methods
In common: Biopython, Numba, clusterProfiler, 9 other tools, genetics / omics, mouse, 2 references
[9] doi:10.1093/bib/bbag175 [code]: Uncovering causal relationships in single-cell omic studies with causarray.
Journal: Briefings in bioinformatics
In common: reticulate, anndata, igraph, 11 other tools, mouse
[10] doi:10.1038/s44320-026-00208-7 [code]: Interpretable deep generative ensemble learning for single-cell omics with Hydra.
Journal: Molecular systems biology
In common: reticulate, anndata, igraph, 11 other tools, 1 reference

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.

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: questions and error reports about this paper and its code, from signed-in readers and its authors. It opens with sign-in.

Reproductions: reports from readers who ran the authors' code: what they reproduced, with which environment, commit and data. It opens with sign-in.

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

SPOmiAlign: a modality-agnostic computational framework for multimodal spatial omics alignment enabled by a feature matching foundation model.

Code ↔ Paper

Paper

The authors' code

Overview

Abstract

Repositories

cortex-lab/allenccf

gpenglab/misar-seq

bioinfo-biols/flow2spatial

wangyiyuyang/SPOmiAlign

Tracing map

Data

Datasets cited

Data availability

Versions

Version 1, 27 September 2026: the first record

Cite

This paper

Similar papers

Contribute

Claim this paper

Correct its record

Validate its tracing map

Add the badge to its README

Request its removal

Discussion, reproductions, activity