Spage2vec: Unsupervised representation of localized spatial gene expression signatures.

{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:32976679", "kind": "science-record", "revision": 7, "content_hash": "sha256:6eb0a8ce81424064ce8d46577c0c281a0027ccaf400b55cba3ab32909c0740e9", "created_at": "2026-11-01T15:41:11Z", "updated_at": "2026-11-01T22:02:14Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Spage2vec: Unsupervised representation of localized spatial gene expression signatures.", "doi": "10.1111/febs.15572", "pmid": "32976679", "authors": ["Gabriele Partel", "Carolina Wählby"], "journal": "The FEBS journal", "year": 2021, "abstract": "Investigations of spatial cellular composition of tissue architectures revealed by multiplexed in situ RNA detection often rely on inaccurate cell segmentation or prior biological knowledge from complementary single-cell sequencing experiments. Here, we present spage2vec, an unsupervised segmentation-free approach for decrypting the spatial transcriptomic heterogeneity of complex tissues at subcellular resolution. Spage2vec represents the spatial transcriptomic landscape of tissue samples as a graph and leverages a powerful machine learning graph representation technique to create a lower dimensional representation of local spatial gene expression. We apply spage2vec to mouse brain data from three different in situ transcriptomic assays and to a spatial gene expression dataset consisting of hundreds of individual cells. We show that learned representations encode meaningful biological spatial information of re-occurring localized gene expression signatures involved in cellular and subcellular processes. DATABASE: Spatial gene expression data are available in Zenodo database at https://doi.org/10.5281/zenodo.3897401. Source code for reproducing analysis results and figures is available in Zenodo database at http://www.doi.org/10.5281/zenodo.4030404.", "claims": [{"id": "claim-method", "statement": "We therefore cluster the 50‐dimensional spage2vec output using the Leiden clustering algorithm [35, 36] followed by column‐wise Z‐score normalization of the cluster expression matrix (genes x clusters).", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:32976679", "locator": "sections[20] \"Identification of localized gene expression signatures\" paragraph 2", "quote": "We therefore cluster the 50‐dimensional spage2vec output using the Leiden clustering algorithm [35, 36] followed by column‐wise Z‐score normalization of the cluster expression matrix (genes x clusters)."}], "state": "complete"}, {"id": "claim-data-access", "statement": "Spatial gene expression data are available in Zenodo database at https://doi.org/10.5281/zenodo.3897401. Source code for reproducing analysis results and figures is available in Zenodo database at http://www.doi.org/10.5281/zenodo.4030404.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:32976679", "locator": "sections[0] \"Abstract\" paragraph 4", "quote": "Spatial gene expression data are available in Zenodo database at https://doi.org/10.5281/zenodo.3897401. Source code for reproducing analysis results and figures is available in Zenodo database at http://www.doi.org/10.5281/zenodo.4030404."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "partial", "objective": null, "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:32976679"], "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": "blocked", "blocked_on": "data:accession_absent", "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": [], "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": [], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": ["step:obtain_source_data blocked on data:accession_absent"]}, "data": {"state": "partial", "assets": [{"id": "source:pmid:32976679", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1111/febs.15572", "sha256": "sha256:e1593c8ad9f0bfc7cd281d4ba82eed704f4665691f2314ae0b84f6d229ab0542", "bytes": 40155, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1111/febs.15572", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC7983892", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}], "gaps": []}, "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": 0.7, "band": "medium", "quote": "segmentation"}}, {"id": "method-2", "family": null, "specific": null, "label": "Leiden clustering algorithm", "dsl_operations": [], "missing_operations": [], "expressible": null, "parameters": {}, "data_shapes": [], "evidence": {"score": 1.0, "band": "verbatim", "quote": "We therefore cluster the 50‐dimensional spage2vec output using the Leiden clustering algorithm [35, 36] followed by column‐wise Z‐score normalization of the cluster expression matrix (genes x clusters)."}}], "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": "blocked", "tier": "R4", "blocking_axis": "data", "blocked_on": "data:accession_absent", "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": "R4", "reachable": false, "accessions": [], "resolved_accessions": [], "statements": ["Spatial gene expression data are available in Zenodo database at https://doi.org/10.5281/zenodo.3897401. Source code for reproducing analysis results and figures is available in Zenodo database at http://www.doi.org/10.5281/zenodo.4030404."], "basis": "The paper names no accession to its source data, so the data has to come from the authors."}}, "can_run": {"dsl_operations": ["segment_objects", "quantify_intensity"], "assets": ["source:pmid:32976679"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:None"]}, "gaps": ["data:accession_absent"]}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-10-31T18:22:47Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 3, "usage": {"prompt_tokens": 29992, "completion_tokens": 2493, "cached_tokens": 528}}, "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:32976679", "type": "paper", "label": "pmid:32976679"}, {"id": "source:pmid:32976679", "type": "manuscript", "label": "PMID 32976679 full text"}, {"id": "data:geo:None", "type": "dataset", "label": "GEO None"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:32976679", "type": "paper", "label": "pmid:32976679"}, {"id": "source:pmid:32976679", "type": "manuscript", "label": "PMID 32976679 full text"}, {"id": "data:geo:None", "type": "dataset", "label": "GEO None"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-32976679", "type": "extraction", "used": ["source:pmid:32976679"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-None", "type": "accession_resolution", "used": ["data:geo:None"], "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:32976679", "parent_hash": "sha256:21da7f87486d195888195f049983af8ecd81fc5aa1cd454a95cb014c8f4b896c", "fork_of": null, "generation": 6}, "gaps": ["execution.not_run", "method.reader_named_unmapped", "review.human_critique", "review.independent_reader", "review.machine_critique", "step:obtain_source_data blocked on data:accession_absent"], "assays": [{"role": "data_generation", "definition_id": "animal_model", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.99, "evidence": ["atial gene expression. We apply spage2vec to mouse brain data from three different in situ tran", "Spage2vec for in situ sequencing analysis of mouse hippocampal area CA1 We first analyzed publi", "d published in situ sequencing (ISS) data of mouse hippocampal area CA1 [11], where transcripts", "ge2vec model trained on the right hemisphere mouse hippocampal area CA1 to predict the node emb"], "order_basis": "paper_text_order:722", "id": "assay:1"}, {"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": 0.7, "evidence": ["segmentation"], "order_basis": "consumes_earlier_output", "id": "assay:2"}]}