SpatialRNA: a Python package for easy application of Graph Neural Network models on single-molecule spatial transcriptomics dataset.

{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:41390915", "kind": "science-record", "revision": 3, "content_hash": "sha256:d2ef983e40981c62f5d84697ac531cc7380857ad47b436f63ebd555396db667a", "created_at": "2026-11-01T20:31:24Z", "updated_at": "2026-11-01T22:15:10Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "SpatialRNA: a Python package for easy application of Graph Neural Network models on single-molecule spatial transcriptomics dataset.", "doi": "10.1093/bioinformatics/btaf659", "pmid": "41390915", "authors": ["Ruqian Lyu", "Annika Vannan", "Jonathan A Kropski", "Nicholas E Banovich", "Davis J McCarthy"], "journal": "Bioinformatics (Oxford, England)", "year": 2026, "abstract": "SUMMARY: Image-based spatial transcriptomics (iST) deliver gene expression measurements of RNA transcripts in tissue slices with single-molecule resolution and spatial context preserved. Modern Graph Neural Network (GNN) models are promising methods for capturing the complex molecular and cellular phenotypes in tissues at single-transcript and single-cell levels. A key application of GNNs is the detection of spatial domains or niches, that is, groups of molecules and/or cells that collaboratively work together to produce complex phenotypes. Due to the vast number of detected transcripts in (iST) dataset, applying GNNs on RNA molecule graphs is not trivial. We present a Python package, SpatialRNA, for easy (sub)graph generation from tissue samples and provide comprehensive tutorials for convenient and efficient application of Graph Neural Network models under the PyG framework. This highly scalable tool comprehensively segments tissue into spatial domains, aiding in biological interpretation of iST data and its underlying molecular microenvironments.\nAVAILABILITY AND IMPLEMENTATION: The SpatialRNA package is freely accessible from online repository https://github.com/ruqianl/spatialrna and can be installed via pip. Comprehensive tutorials, guidance on parameter selection, and complete workflows of case studies are available from the documentation website https://ruqianl.github.io/spatialrna_docs/, and uploaded on Zenodo with a DOI 10.5281/zenodo.17339575.", "claims": [{"id": "claim-method", "statement": "We found that the SpatialRNA-workflow recovered true cell types robustly with different numbers of sampled edges across radius 1 and 3 [adjusted rand index (ARI) score > 0.9; Fig. 12, available as supplementary data at Bioinformatics online], which was on par with FICTURE (Si et al. 2024).", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:41390915", "locator": "sections[10] \"4 Comparing workflow variations and other methods on simulation data\" paragraph 2", "quote": "We found that the SpatialRNA-workflow recovered true cell types robustly with different numbers of sampled edges across radius 1 and 3 [adjusted rand index (ARI) score > 0.9; Fig. 12, available as supplementary data at Bioinformatics online], which was on par with FICTURE (Si et al. 2024)."}], "state": "complete"}, {"id": "claim-data-access", "statement": "Supplementary data is available at Bioinformatics online.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:41390915", "locator": "sections[15] \"Supplementary data\" paragraph 2", "quote": "Supplementary data is available at Bioinformatics online."}], "state": "complete"}, {"id": "claim-target-result", "statement": "We present a Python package, SpatialRNA, for easy (sub)graph generation from tissue samples and provide comprehensive tutorials for convenient and efficient application of Graph Neural Network models under the PyG framework.", "kind": "qualitative", "target": null, "evidence": [{"asset": "source:pmid:41390915", "locator": "sections[0] \"Abstract\" paragraph 1", "quote": "We present a Python package, SpatialRNA, for easy (sub)graph generation from tissue samples and provide comprehensive tutorials for convenient and efficient application of Graph Neural Network models under the PyG framework."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "complete", "objective": "We present a Python package, SpatialRNA, for easy (sub)graph generation from tissue samples and provide comprehensive tutorials for convenient and efficient application of Graph Neural Network models under the PyG framework.", "steps": [{"id": "read_published_estimate", "order": 1, "name": "Read the published estimate from the source", "kind": "other", "state": "complete", "blocked_on": null, "description": "The claim, method and evidence span published with the source article.", "duration_hours": null, "parameters": {}, "inputs": ["source:pmid:41390915"], "outputs": ["the published estimate and its evidence"], "instruments": [], "reagents": []}, {"id": "obtain_source_data", "order": 2, "name": "Obtain the source data from the named repository", "kind": "data-preparation", "state": "complete", "blocked_on": null, "description": "The GEO series accession resolves and its sample accessions are listed. This lane did not download the dataset or read its licence.", "duration_hours": null, "parameters": {}, "inputs": ["data:geo:GSE250346"], "outputs": ["the source data with its repository provenance"], "instruments": [], "reagents": []}, {"id": "run_analysis", "order": 3, "name": "Run the published analysis", "kind": "analysis", "state": "complete", "blocked_on": null, "description": "Apply the paper's statistical method to the resolved series and compare the result with the published target.", "duration_hours": null, "parameters": {}, "inputs": ["data:geo:GSE250346"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:41390915", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1093/bioinformatics/btaf659", "sha256": "sha256:0a4b973ac3e60e4a5206461111cb3255ebda708cec06b7d9306b41988922a2e7", "bytes": 28423, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1093/bioinformatics/btaf659", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC12777972", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE250346", "role": "raw", "format": "geo-series", "media_type": "application/vnd.ncbi.geo-series+json", "uri": "https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE250346", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE250346", "version": null, "note": "Supplementary data is available at Bioinformatics online.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "Supplementary data is available at Bioinformatics online.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM7990532", "GSM7990533", "GSM7990534", "GSM7990535", "GSM7990536", "GSM7990537", "GSM7990538", "GSM7990539", "GSM7990540", "GSM7990541", "GSM7990542", "GSM7990543", "GSM7990544", "GSM7990545", "GSM7990546", "GSM7990547", "GSM7990548", "GSM7990549", "GSM7990550", "GSM7990551", "GSM7990552", "GSM7990553", "GSM7990554", "GSM7990555", "GSM7990556", "GSM7990557", "GSM7990558", "GSM7990559", "GSM8505448", "GSM8505449", "GSM8505450", "GSM8505451", "GSM8505452", "GSM8505453", "GSM8505454", "GSM8505455", "GSM8505456", "GSM8505457", "GSM8505458", "GSM8505459", "GSM8505460", "GSM8505461", "GSM8505462", "GSM8505463", "GSM8505464"], "sample_count": 45, "group_sizes": null, "group_sizes_basis": null, "platform": "33762", "taxon": "Homo sapiens", "title": "Image-based spatial transcriptomics identifies molecular niche dysregulation associated with distal lung remodeling in pulmonary fibrosis [Xenium]", "resolution_checked_at": "2026-11-01T20:16:08Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}], "gaps": ["asset:data:geo:GSE250346 not downloaded", "asset:data:geo:GSE250346 licence not read"]}, "analysis": {"state": "partial", "methods": [{"id": "method-1", "family": "image_quantification", "specific": "segmentation", "label": "Image analysis / quantification", "dsl_operations": ["segment_objects", "quantify_intensity"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["image_stack"], "evidence": {"score": 0.8, "band": "high", "quote": "segmentation"}}, {"id": "method-2", "family": null, "specific": null, "label": "adjusted rand index (ARI) score", "dsl_operations": [], "missing_operations": [], "expressible": null, "parameters": {}, "data_shapes": [], "evidence": {"score": 1.0, "band": "verbatim", "quote": "We found that the SpatialRNA-workflow recovered true cell types robustly with different numbers of sampled edges across radius 1 and 3 [adjusted rand index (ARI) score > 0.9; Fig. 12, available as supplementary data at Bioinformatics online], which was on par with FICTURE (Si et al. 2024)."}}], "targets": [], "gaps": ["method.reader_named_unmapped"]}, "capability": {"state": "complete", "requirements": [{"capability_id": "capability:computational_analysis", "label": "Computational analysis platform", "assay_families": ["meta_analysis", "machine_learning", "survival_analysis", "statistical_regression", "pca", "molecular_docking", "network_analysis", "differential_expression", "gwas"], "availability_state": "owned", "tier_unlocked": "R1", "candidate": "Automated Assays Laravel application and simulated adapters"}], "gaps": []}, "readiness": {"state": "complete", "tier": "R1", "blocking_axis": "none", "blocked_on": "nothing:replicable_now", "axes": {"method": {"tier": "R1", "expressible": true, "required_operations": ["segment_objects", "quantify_intensity"], "missing_operations": [], "basis": "The paper names the method it used and the corpus's method extractor maps it onto the DSL catalogue: segmentation."}, "capability": {"tier": "R1", "capability_id": "capability:computational_analysis", "availability_state": "owned", "basis": "The computational analysis is owned. The physical bench the paper used is not, so a physical validation cannot be run here."}, "data": {"tier": "R1", "reachable": true, "accessions": ["GSE250346"], "resolved_accessions": ["GSE250346"], "statements": ["Supplementary data is available at Bioinformatics online."], "basis": "The paper names GSE250346 in GEO and the accession resolves in the repository. No dataset was downloaded and no licence was read."}}, "can_run": {"dsl_operations": ["segment_objects", "quantify_intensity"], "assets": ["source:pmid:41390915", "data:geo:GSE250346"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE250346"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-11-01T20:08:18Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 5, "usage": {"prompt_tokens": 8240, "completion_tokens": 1547, "cached_tokens": 264}}, "human_critique": null, "stages": [{"id": "extraction", "state": "complete", "reader": "MiniMax-M3.1-Flash", "provider": "minimax"}], "gaps": ["review.independent_reader", "review.machine_critique", "review.human_critique"]}, "execution": {"state": "absent", "status": "not_run", "mode": null, "runs": [], "gaps": ["execution.not_run"]}, "provenance": {"entities": [{"id": "pmid:41390915", "type": "paper", "label": "pmid:41390915"}, {"id": "source:pmid:41390915", "type": "manuscript", "label": "PMID 41390915 full text"}, {"id": "data:geo:GSE250346", "type": "dataset", "label": "GEO GSE250346"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:41390915", "type": "paper", "label": "pmid:41390915"}, {"id": "source:pmid:41390915", "type": "manuscript", "label": "PMID 41390915 full text"}, {"id": "data:geo:GSE250346", "type": "dataset", "label": "GEO GSE250346"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-41390915", "type": "extraction", "used": ["source:pmid:41390915"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE250346", "type": "accession_resolution", "used": ["data:geo:GSE250346"], "agent": "agent:corpus-assay-engine"}], "agents": [{"id": "agent:corpus-assay-engine", "type": "software", "label": "Corpus assay engine"}, {"id": "agent:minimax-reader", "type": "software", "label": "MiniMax literature reader"}], "source_run_id": "reading-sci-2026-11-01", "dsl_catalogue_fingerprint": "343fb30756ba6ec3", "capability_table_fingerprint": "2cb3e42f047d2ecf", "snapshot_id": "ba34b49490d9bfaf"}, "lineage": {"parent_id": "pmid:41390915", "parent_hash": "sha256:0c71dfd7ec1dd8ff29e61a9c9660b56fd2a4df557f6e42ef1844b70309db9e62", "fork_of": null, "generation": 2}, "gaps": ["asset:data:geo:GSE250346 licence not read", "asset:data:geo:GSE250346 not downloaded", "execution.not_run", "method.reader_named_unmapped", "review.human_critique", "review.independent_reader", "review.machine_critique"], "assays": [{"role": "analysis", "definition_id": "image_quantification", "definition_version": "f2132e96ae6c7a4e", "definition_digest": null, "required_operations": ["segment_objects", "quantify_intensity"], "support_state": "supported", "source_hashes": {"dsl_catalogue": "f2132e96ae6c7a4e"}, "confidence": 0.8, "evidence": ["segmentation"], "order_basis": "analysis_only", "id": "assay:1"}]}