ASTRO: Automated Spatial-Transcriptome whole RNA Output.

{"sci_version": "1.0", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:41495477", "kind": "science-record", "revision": 2, "content_hash": "sha256:186c8884a76f7322ac2543613cba02f9176845452ae6e85313c40ae2d6ffc913", "created_at": "2026-11-01T20:31:28Z", "updated_at": "2026-11-01T21:36:16Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "ASTRO: Automated Spatial-Transcriptome whole RNA Output.", "doi": "10.1093/bioinformatics/btaf688", "pmid": "41495477", "authors": ["Dingyao Zhang", "Zhiyuan Chu", "Yiran Huo", "Yunzhe Jiang", "Yuhang Chen", "Zhiliang Bai", "Rong Fan", "Jun Lu", "Mark Gerstein"], "journal": "Bioinformatics (Oxford, England)", "year": 2026, "abstract": "MOTIVATION: Despite significant advances in spatial transcriptomics, the analysis of formalin-fixed paraffin-embedded (FFPE) tissues, which constitute most clinically available samples, remains challenging. Additionally, capturing both coding and noncoding RNAs in a spatial context poses significant challenges. We recently introduced Patho-DBiT, a technology designed to address these unmet needs. However, the marked differences between Patho-DBiT and existing spatial transcriptomics protocols necessitate specialized computational tools for comprehensive whole-transcriptome analysis in FFPE samples.\nRESULTS: Here, we present ASTRO, an automated pipeline developed to process spatial transcriptomics data. In addition to supporting standard datasets, ASTRO is optimized for whole-transcriptome analyses of FFPE samples, enabling the detection of various RNA species, including non-coding RNAs such as miRNAs. To compensate for the reduced RNA quality in FFPE tissues, ASTRO incorporates a specialized filtering step and optimizes spatial barcode calling, increasing the mapping rate. These optimizations allow ASTRO to spatially quantify coding and non-coding RNA species in the entire transcriptome and achieve robust performance in FFPE samples.\nAVAILABILITY: Codes are available at GitHub (https://github.com/gersteinlab/ASTRO) and Zenodo (doi: 10.5281/zenodo.17913760).\nSUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.", "claims": [{"id": "claim-method", "statement": "For RNA fragments mapping to multiple overlapping annotations, an “overlap score” was calculated using the formula (Lo−Lno)/La, where Lo denotes the overlapped length between the query RNA fragment and an annotation, Lno represents the non-overlapped length of the query RNA fragment, and La is the total length of the genomic annotation.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:41495477", "locator": "sections[7] \"2.3.2 Assign reads with overlapping annotations\" paragraph 2", "quote": "For RNA fragments mapping to multiple overlapping annotations, an “overlap score” was calculated using the formula (Lo−Lno)/La, where Lo denotes the overlapped length between the query RNA fragment and an annotation, Lno represents the non-overlapped length of the query RNA fragment, and La is the total length of the genomic annotation."}], "state": "complete"}, {"id": "claim-data-access", "statement": "The data underlying this article are available in Gene Expression Omnibus at https://www.ncbi.nlm.nih.gov/geo/, and can be accessed with GSE274641.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:41495477", "locator": "sections[23] \"Data availability\" paragraph 2", "quote": "The data underlying this article are available in Gene Expression Omnibus at https://www.ncbi.nlm.nih.gov/geo/, and can be accessed with GSE274641."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "complete", "objective": "", "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:41495477"], "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:GSE274641"], "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:GSE274641"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:41495477", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1093/bioinformatics/btaf688", "sha256": "sha256:d018c83f2de75b9c481bf765c6167fa21aee971f1be88363a6ec533981cd74ee", "bytes": 33775, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1093/bioinformatics/btaf688", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC12866646", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE274641", "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=GSE274641", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE274641", "version": null, "note": "The data underlying this article are available in Gene Expression Omnibus at https://www.ncbi.nlm.nih.gov/geo/, and can be accessed with GSE274641.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The data underlying this article are available in Gene Expression Omnibus at https://www.ncbi.nlm.nih.gov/geo/, and can be accessed with GSE274641.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM8454077", "GSM8454078", "GSM8454079", "GSM8454080", "GSM8454081", "GSM8454082", "GSM8454083", "GSM8454084", "GSM8454085", "GSM8457351", "GSM8457352"], "sample_count": 11, "group_sizes": null, "group_sizes_basis": null, "platform": "24676;24247", "taxon": "Mus musculus; Homo sapiens", "title": "Spatially exploring RNA biology in archival formalin-fixed paraffin-embedded tissues", "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:GSE274641 not downloaded", "asset:data:geo:GSE274641 licence not read"]}, "analysis": {"state": "partial", "methods": [{"id": "method-1", "family": null, "specific": null, "label": "overlap score", "dsl_operations": [], "missing_operations": [], "expressible": null, "parameters": {}, "data_shapes": [], "evidence": {"score": 1.0, "band": "verbatim", "quote": "For RNA fragments mapping to multiple overlapping annotations, an “overlap score” was calculated using the formula (Lo−Lno)/La, where Lo denotes the overlapped length between the query RNA fragment and an annotation, Lno represents the non-overlapped length of the query RNA fragment, and La is the total length of the genomic annotation."}}], "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": "method", "blocked_on": "method:not_determinable", "axes": {"method": {"tier": "R4", "expressible": false, "required_operations": [], "missing_operations": [], "basis": "The reader quoted the method the paper names (overlap score), but the corpus's method extractor could not map it onto a DSL operation, so the method is published but not expressible."}, "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": ["GSE274641"], "resolved_accessions": ["GSE274641"], "statements": ["The data underlying this article are available in Gene Expression Omnibus at https://www.ncbi.nlm.nih.gov/geo/, and can be accessed with GSE274641."], "basis": "The paper names GSE274641 in Gene Expression Omnibus and the accession resolves in the repository. No dataset was downloaded and no licence was read."}}, "can_run": {"dsl_operations": [], "assets": ["source:pmid:41495477", "data:geo:GSE274641"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE274641"]}, "gaps": ["method:not_determinable"]}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-11-01T20:09:35Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 5, "usage": {"prompt_tokens": 10079, "completion_tokens": 1382, "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:41495477", "type": "paper", "label": "pmid:41495477"}, {"id": "source:pmid:41495477", "type": "manuscript", "label": "PMID 41495477 full text"}, {"id": "data:geo:GSE274641", "type": "dataset", "label": "GEO GSE274641"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:41495477", "type": "paper", "label": "pmid:41495477"}, {"id": "source:pmid:41495477", "type": "manuscript", "label": "PMID 41495477 full text"}, {"id": "data:geo:GSE274641", "type": "dataset", "label": "GEO GSE274641"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-41495477", "type": "extraction", "used": ["source:pmid:41495477"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE274641", "type": "accession_resolution", "used": ["data:geo:GSE274641"], "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:41495477", "parent_hash": "sha256:ede5f2aa9ea72f79a3b2fa17d3024f5512c5d3a853a600bb86067f392a2ef635", "fork_of": null, "generation": 1}, "gaps": ["asset:data:geo:GSE274641 licence not read", "asset:data:geo:GSE274641 not downloaded", "execution.not_run", "method.reader_named_unmapped", "review.human_critique", "review.independent_reader", "review.machine_critique"]}