{"data":{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:39529156", "kind": "science-record", "revision": 2, "content_hash": "sha256:0ec4f41c9b47b55b491f8271dec9b951e1f3de1fb390db808845ba4a9def1395", "created_at": "2026-11-01T20:29:47Z", "updated_at": "2026-11-01T21:34:19Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Comparative meta-analysis of transcriptomic studies in spinal muscular atrophy: comparison between tissues and mouse models.", "doi": "10.1186/s12920-024-02040-0", "pmid": "39529156", "authors": ["Shamini Hemandhar Kumar", "Katharina Brandt", "Peter Claus", "Klaus Jung"], "journal": "BMC medical genomics", "year": 2024, "abstract": "BACKGROUND: Spinal Muscular Atrophy (SMA), a neuromuscular disorder that leads to weakness in the muscles due to degeneration of motor neurons. Mutations in the survival motor neuron 1 (SMN1) gene leads to the deficiency of SMN protein that causes SMA. The molecular alterations associated with SMA extends across the transcriptome and proteome. Although several studies have examined the transcriptomic profile of SMA, the difference in experimental settings across these studies highlight the need for a comparative meta-analysis to better understand these differences.\nMETHODS AND DATA: We conducted a systematic comparative meta-analysis of publicly available gene expression data from six selected studies to elucidate variations in the transcriptomic landscape across different experimental conditions, including tissue types and mouse models. We used both microarray and RNA-seq datasets, retrieved from Gene Expression Omnibus (GEO) and ArrayExpress (AE). Methods included normalization, differential expression analysis, gene-set enrichment analysis (GSEA), network reconstruction and co-expression analysis.\nRESULTS: Differential expression analysis revealed varying numbers of differentially expressed genes ranging between zero and 1,655 across the selected studies. Notably, the Metallothionein gene Mt2 was common in several of the eight comparisons. This highlights its role in oxidative stress and detoxification. Additionally, genes such as Hspb1, St14 and Sult1a1 were among the top ten differentially expressed genes in more than one comparison. The Snrpa1 gene, involved in pre-mRNA splicing, was upregulated in the spinal cord and has a strong correlation with other differentially expressed genes from other comparisons in our network reconstruction analysis. Gene-set enrichment analysis identified significant GO terms such as contractile fibers and myosin complexes in more than one comparison which highlights its significant role in SMA.\nCONCLUSIONS: Our comparative meta-analysis identified only few genes and pathways that were consistently dysregulated in SMA across different tissues and experimental settings. Conversely, many genes and pathways appeared to play a tissue-specific role in SMA. In comparison with the original studies, reproducibility was rather weak.", "claims": [{"id": "claim-method", "statement": "We conducted a systematic comparative meta-analysis of publicly available gene expression data from six selected studies to elucidate variations in the transcriptomic landscape across different experimental conditions, including tissue types and mouse models.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:39529156", "locator": "sections[0] \"Abstract\" paragraph 2", "quote": "We conducted a systematic comparative meta-analysis of publicly available gene expression data from six selected studies to elucidate variations in the transcriptomic landscape across different experimental conditions, including tissue types and mouse models."}], "state": "complete"}, {"id": "claim-data-access", "statement": "The datasets analysed during the current study are available in the Gene Expression Omnibus (GEO) and ArrayExpress (AE) repository,\nhttps://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE207890\nhttps://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE154106\nhttps://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE102204\nhttps://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE56284\nhttps://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSe10224\nhttps://www.ebi.ac.uk/biostudies/arrayexpress/studies/E-MEXP-2428?query=E-MEXP-2428", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:39529156", "locator": "sections[22] \"Data availability\" paragraphs 1-8", "quote": "The datasets analysed during the current study are available in the Gene Expression Omnibus (GEO) and ArrayExpress (AE) repository,\nhttps://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE207890\nhttps://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE154106\nhttps://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE102204\nhttps://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE56284\nhttps://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSe10224\nhttps://www.ebi.ac.uk/biostudies/arrayexpress/studies/E-MEXP-2428?query=E-MEXP-2428"}], "state": "complete"}, {"id": "claim-target-result", "statement": "Differential expression analysis revealed varying numbers of differentially expressed genes ranging between zero and 1,655 across the selected studies.", "kind": "qualitative", "target": null, "evidence": [{"asset": "source:pmid:39529156", "locator": "sections[0] \"Abstract\" paragraph 3", "quote": "Differential expression analysis revealed varying numbers of differentially expressed genes ranging between zero and 1,655 across the selected studies."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "complete", "objective": "Differential expression analysis revealed varying numbers of differentially expressed genes ranging between zero and 1,655 across the selected studies.", "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:39529156"], "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:GSE102204"], "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:GSE102204"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:39529156", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1186/s12920-024-02040-0", "sha256": "sha256:5b1657b5ff50824ddfe750de94b695a10f52fd6ffdc0501a927d34f3846b3000", "bytes": 50478, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1186/s12920-024-02040-0", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC11555813", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE102204", "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=GSE102204", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE102204", "version": null, "note": "The datasets analysed during the current study are available in the Gene Expression Omnibus (GEO) and ArrayExpress (AE) repository,\nhttps://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE207890\nhttps://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE154106\nhttps://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE102204\nhttps://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE56284\nhttps://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSe10224\nhttps://www.ebi.ac.uk/biostudies/arrayexpress/studies/E-MEXP-2428?query=E-MEXP-2428", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The datasets analysed during the current study are available in the Gene Expression Omnibus (GEO) and ArrayExpress (AE) repository,\nhttps://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE207890\nhttps://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE154106\nhttps://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE102204\nhttps://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE56284\nhttps://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSe10224\nhttps://www.ebi.ac.uk/biostudies/arrayexpress/studies/E-MEXP-2428?query=E-MEXP-2428", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM2730288", "GSM2730289", "GSM2730290", "GSM2730291", "GSM2730292", "GSM2730293", "GSM2730294", "GSM2730295", "GSM2730296", "GSM2730297", "GSM2730298", "GSM2730299", "GSM2730300", "GSM2730301", "GSM2730302", "GSM2730303", "GSM2730304", "GSM2730305", "GSM2730306", "GSM2730307"], "sample_count": 20, "group_sizes": null, "group_sizes_basis": null, "platform": "13112", "taxon": "Mus musculus", "title": "Transcriptome and translatome profiling from brains of  a mouse model of severe SMA", "resolution_checked_at": "2026-11-01T20:16:08Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:GSE10224", "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=GSE10224", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE10224", "version": null, "note": "The datasets analysed during the current study are available in the Gene Expression Omnibus (GEO) and ArrayExpress (AE) repository,\nhttps://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE207890\nhttps://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE154106\nhttps://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE102204\nhttps://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE56284\nhttps://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSe10224\nhttps://www.ebi.ac.uk/biostudies/arrayexpress/studies/E-MEXP-2428?query=E-MEXP-2428", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The datasets analysed during the current study are available in the Gene Expression Omnibus (GEO) and ArrayExpress (AE) repository,\nhttps://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE207890\nhttps://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE154106\nhttps://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE102204\nhttps://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE56284\nhttps://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSe10224\nhttps://www.ebi.ac.uk/biostudies/arrayexpress/studies/E-MEXP-2428?query=E-MEXP-2428", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM258077", "GSM258078", "GSM258079", "GSM258080", "GSM258081", "GSM258082", "GSM258083", "GSM258084", "GSM258085"], "sample_count": 9, "group_sizes": null, "group_sizes_basis": null, "platform": "339", "taxon": "Mus musculus", "title": "Gene Expression Analysis of laser-microdissected motorneurons in Spinal Muscular Atrophy (SMA)", "resolution_checked_at": "2026-11-01T20:16:08Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:GSE154106", "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=GSE154106", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE154106", "version": null, "note": "The datasets analysed during the current study are available in the Gene Expression Omnibus (GEO) and ArrayExpress (AE) repository,\nhttps://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE207890\nhttps://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE154106\nhttps://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE102204\nhttps://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE56284\nhttps://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSe10224\nhttps://www.ebi.ac.uk/biostudies/arrayexpress/studies/E-MEXP-2428?query=E-MEXP-2428", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The datasets analysed during the current study are available in the Gene Expression Omnibus (GEO) and ArrayExpress (AE) repository,\nhttps://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE207890\nhttps://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE154106\nhttps://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE102204\nhttps://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE56284\nhttps://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSe10224\nhttps://www.ebi.ac.uk/biostudies/arrayexpress/studies/E-MEXP-2428?query=E-MEXP-2428", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM4663991", "GSM4663992", "GSM4663993", "GSM4663994", "GSM4663995", "GSM4663996", "GSM4663997", "GSM4663998"], "sample_count": 8, "group_sizes": null, "group_sizes_basis": null, "platform": "17021", "taxon": "Mus musculus", "title": "Ribosome profiling of SMN-primed ribosomes and active ribosome profiling from brains of a mouse model of severe SMA", "resolution_checked_at": "2026-11-01T20:16:08Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:GSE207890", "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=GSE207890", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE207890", "version": null, "note": "The datasets analysed during the current study are available in the Gene Expression Omnibus (GEO) and ArrayExpress (AE) repository,\nhttps://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE207890\nhttps://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE154106\nhttps://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE102204\nhttps://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE56284\nhttps://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSe10224\nhttps://www.ebi.ac.uk/biostudies/arrayexpress/studies/E-MEXP-2428?query=E-MEXP-2428", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The datasets analysed during the current study are available in the Gene Expression Omnibus (GEO) and ArrayExpress (AE) repository,\nhttps://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE207890\nhttps://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE154106\nhttps://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE102204\nhttps://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE56284\nhttps://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSe10224\nhttps://www.ebi.ac.uk/biostudies/arrayexpress/studies/E-MEXP-2428?query=E-MEXP-2428", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM6322581", "GSM6322582", "GSM6322583", "GSM6322584", "GSM6322585", "GSM6322586", "GSM6322587", "GSM6322588", "GSM6322589", "GSM6322590", "GSM6322591", "GSM6322592", "GSM6322593", "GSM6322594", "GSM6322595", "GSM6322596", "GSM6322597", "GSM6322598", "GSM6322599", "GSM6322600", "GSM6322601", "GSM6322602", "GSM6322603", "GSM6322604", "GSM6322605", "GSM6322606", "GSM6322607"], "sample_count": 27, "group_sizes": null, "group_sizes_basis": null, "platform": "10787", "taxon": "Mus musculus", "title": "Skeletal muscle mitochondrial dysfunction in spinal muscular atrophy", "resolution_checked_at": "2026-11-01T20:16:08Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:GSE56284", "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=GSE56284", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE56284", "version": null, "note": "The datasets analysed during the current study are available in the Gene Expression Omnibus (GEO) and ArrayExpress (AE) repository,\nhttps://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE207890\nhttps://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE154106\nhttps://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE102204\nhttps://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE56284\nhttps://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSe10224\nhttps://www.ebi.ac.uk/biostudies/arrayexpress/studies/E-MEXP-2428?query=E-MEXP-2428", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The datasets analysed during the current study are available in the Gene Expression Omnibus (GEO) and ArrayExpress (AE) repository,\nhttps://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE207890\nhttps://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE154106\nhttps://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE102204\nhttps://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE56284\nhttps://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSe10224\nhttps://www.ebi.ac.uk/biostudies/arrayexpress/studies/E-MEXP-2428?query=E-MEXP-2428", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM1358335", "GSM1358336", "GSM1358337", "GSM1358338", "GSM1358339", "GSM1358340"], "sample_count": 6, "group_sizes": null, "group_sizes_basis": null, "platform": "17021", "taxon": "Mus musculus", "title": "Transcriptome profiling of severe spinal muscular atrophy mouse embryonic stem cell-derived motor neurons", "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:GSE102204 not downloaded", "asset:data:geo:GSE102204 licence not read", "asset:data:geo:GSE10224 not downloaded", "asset:data:geo:GSE10224 licence not read", "asset:data:geo:GSE154106 not downloaded", "asset:data:geo:GSE154106 licence not read", "asset:data:geo:GSE207890 not downloaded", "asset:data:geo:GSE207890 licence not read", "asset:data:geo:GSE56284 not downloaded", "asset:data:geo:GSE56284 licence not read"]}, "analysis": {"state": "partial", "methods": [{"id": "method-1", "family": null, "specific": null, "label": "systematic comparative meta-analysis", "dsl_operations": [], "missing_operations": [], "expressible": null, "parameters": {}, "data_shapes": [], "evidence": {"score": 1.0, "band": "verbatim", "quote": "We conducted a systematic comparative meta-analysis of publicly available gene expression data from six selected studies to elucidate variations in the transcriptomic landscape across different experimental conditions, including tissue types and mouse models."}}], "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 (systematic comparative meta-analysis), 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": ["GSE207890", "GSE154106", "GSE102204", "GSE56284", "GSE10224"], "resolved_accessions": ["GSE207890", "GSE154106", "GSE102204", "GSE56284", "GSE10224"], "statements": ["The datasets analysed during the current study are available in the Gene Expression Omnibus (GEO) and ArrayExpress (AE) repository,\nhttps://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE207890\nhttps://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE154106\nhttps://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE102204\nhttps://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE56284\nhttps://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSe10224\nhttps://www.ebi.ac.uk/biostudies/arrayexpress/studies/E-MEXP-2428?query=E-MEXP-2428"], "basis": "The paper names GSE207890, GSE154106, GSE102204, GSE56284, GSE10224 in Gene Expression Omnibus (GEO) and the accession resolves in the repository. No dataset was downloaded and no licence was read."}}, "can_run": {"dsl_operations": [], "assets": ["source:pmid:39529156", "data:geo:GSE102204"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE102204"]}, "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": "2026-11-01T19:38:29Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 5, "usage": {"prompt_tokens": 13974, "completion_tokens": 2638, "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:39529156", "type": "paper", "label": "pmid:39529156"}, {"id": "source:pmid:39529156", "type": "manuscript", "label": "PMID 39529156 full text"}, {"id": "data:geo:GSE102204", "type": "dataset", "label": "GEO GSE102204"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:39529156", "type": "paper", "label": "pmid:39529156"}, {"id": "source:pmid:39529156", "type": "manuscript", "label": "PMID 39529156 full text"}, {"id": "data:geo:GSE102204", "type": "dataset", "label": "GEO GSE102204"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-39529156", "type": "extraction", "used": ["source:pmid:39529156"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE102204", "type": "accession_resolution", "used": ["data:geo:GSE102204"], "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:39529156", "parent_hash": "sha256:72a6f1351ecb85273fa717a582071b00930bb1d0cfc45266435ee268d595718e", "fork_of": null, "generation": 1}, "gaps": ["asset:data:geo:GSE102204 licence not read", "asset:data:geo:GSE102204 not downloaded", "asset:data:geo:GSE10224 licence not read", "asset:data:geo:GSE10224 not downloaded", "asset:data:geo:GSE154106 licence not read", "asset:data:geo:GSE154106 not downloaded", "asset:data:geo:GSE207890 licence not read", "asset:data:geo:GSE207890 not downloaded", "asset:data:geo:GSE56284 licence not read", "asset:data:geo:GSE56284 not downloaded", "execution.not_run", "method.reader_named_unmapped", "review.human_critique", "review.independent_reader", "review.machine_critique"], "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": 0.93, "evidence": ["ular atrophy: comparison between tissues and mouse models.", "ental conditions, including tissue types and mouse models. We used both microarray and RNA-seq"], "order_basis": "paper_text_order:66", "id": "assay:1"}, {"role": "data_generation", "definition_id": "microarray", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.93, "evidence": ["tissue types and mouse models. We used both microarray and RNA-seq datasets, retrieved from Gene Ex"], "order_basis": "paper_text_order:944", "id": "assay:2"}]},"meta":{"api_version":"v1","automation_ladder_snapshot":"ba34b49490d9bfaf","automation_ladder_caveats":["Method extraction is rule-based and has no hand-judged accuracy sample. Evidence bands order textual support; method agreement intervals are null (n=0), never probabilities. Work-type validation does not validate methods.","Operation coverage describes only explicitly named methods. It does not prove a complete protocol, compatible parameters, successful compilation or re-execution. Unrecognised or ambiguous methods require review.","Data reachability is a textual accession or public-data statement. No dataset was downloaded or checked for access, completeness or licence.","Capabilities are planning states seeded from the dated equipment register. No bench ownership, completed quote or partner booking is inferred. Procurement counts are dependencies, not guaranteed replications or financial returns.","Tier and blocker counts are deterministic assessments of this corpus, not measured agreement. R3 is reserved for procurement; unresolved methods and data require human work (R4). The most restrictive axis wins, with capability, method, data as tie-breaks. Resolving one blocker can leave another at the same tier."],"engine":"corpus_engine","engine_provider":"rule_based_v1+lex99e1195c7d6f","run_id":"run-20261023T122449232913","source":"esearch","source_detail":"PubMed mirror biomed_pubmed (read-only)","run_status":"complete","imported_at":"2026-11-03T20:16:52+00:00","generated_at":"2026-11-04T02:52:03+00:00","total_papers":5529,"total_assays_tracked":29,"automatable_assay_families":6,"validated":true,"caveat_count":9,"blocking_caveats":5,"caveats":[{"code":"low_evidence_dominates","basis":["4,152 of 5,529 classifications (75.1%) matched no cue evidence and sit at the 0.05 floor.","34 of 230 data_only calls (14.8%) are in that group."],"claim":"Work type and confidence bands","gloss":"Most records were classified from their title and framing alone, with assay-cue coverage at zero.","detail":"Most classifications in this run rest on no matched evidence at all. At the evidence floor the work type comes from title framing and a fixed prior, not from anything in the paper, so the published work-type split should be read as a rough triage signal rather than a measured distribution. The impact is bounded but not removed: since 2026-10-23 the engine excludes floor-confidence records from the shortlist entirely and publishes them separately as held out, so the recommendation is unaffected even though the census is.","status":"unverified","severity":"high"},{"code":"runtime_is_modelled","basis":["Runtime is summed from published per-assay hour figures. Timing awaits the first executed replication.","4,407 of 5,529 records (79.7%) model to 0.00 hours because no assay was matched, which the ranking then reads as \"cheapest\".","0 of 10 shortlisted records carry a 0.00-hour estimate."],"claim":"Estimated replication runtime","gloss":"The hour figures are estimates built from assay mentions; timing awaits the first executed replication.","detail":"The hour figures are a cost model derived from the bench steps implied by each matched assay family. The first executed replication will supply measured timing. Records without an assay match currently receive a zero-hour model value.","status":"unverified","severity":"high"},{"code":"signal_score_without_citations","basis":["5,529 of 5,529 records (100.0%) have no citation count from the source metadata."],"claim":"Signal score","gloss":"The signal score uses publication-type weight because the mirror supplied zero citation counts.","detail":"The source supplied no citation counts for any record in this run, so the signal score is publication-type weight only. The citation term of the ranking is inert here, and the shortlist is ordered by publication type alone.","status":"unverified","severity":"high"},{"code":"abstract_absent","basis":["1,667 of 5,529 records (30.2%) carry no abstract at all."],"claim":"Evidence base for classification","gloss":"Some records contain a title and publication type only, defining the available classification evidence.","detail":"Where the mirror contains a title and publication types only, those fields define the classifier evidence. A methods section is required for fuller automated and human review.","status":"unverified","severity":"medium"},{"code":"classifier_agreement_measured","basis":["Published two-way decision agreement 77.7% (310 of 399 decidable records) from a stratified hand-check of 438 real records.","Three-way diagnostic agreement 73.9% (288 of 390 decidable records).","data_only agreement 75.2% (100 of 133 decidable).","48 record(s) could not be decided from title and abstract and were excluded from the denominator.","56 analysis-only records were published under another work type, so the data_only share is not an upper bound."],"claim":"Published automatable decision","gloss":"This figure has been checked against a human reading the same papers, so we know how often it is right.","detail":"The published automatable / not-automatable distribution comes from a rule-based classifier that was hand-checked against a fixed ground-truth definition. The agreement rates below are measured, not estimated. The three-way work type remains a diagnostic and is reported separately.","status":"measured","severity":"high"},{"code":"llm_comparison_not_measured","basis":["rule_based_v1+lex99e1195c7d6f produced 5,529 of 5,529 classifications.","Measured on 438 labelled records; these are RULE-BASED figures, not model results."],"claim":"Rule-based versus LLM agreement","gloss":"Every number here is the rule engine’s own. Model comparison begins when a working API credential is connected and measured.","detail":"The published two-way decision agreed with a human reading on 310 of 399 decidable records (77.7%). The diagnostic three-way label agreed on 288 of 390 decidable records (73.9%). Every percentage in this run belongs to the rule engine. Model comparison begins when a working API credential is connected and measured.","status":"not_measured","severity":"high"},{"code":"confidence_is_a_band","basis":["low band: 135 of 210 hand-judged records were correct, 64.3% [57.6, 70.5] (95% CI).","medium band: 80 of 104 hand-judged records were correct, 76.9% [68.0, 84.0] (95% CI).","high band: 73 of 76 hand-judged records were correct, 96.0% [89.0, 98.7] (95% CI).","A fitted calibrated probability was built, measured and withdrawn: it overstated held-out accuracy and reorders nothing."],"claim":"Confidence band and evidence score","gloss":"The confidence band carries a measured accuracy interval; 0.85 represents relative rank strength.","detail":"Confidence on this run is a BAND plus its measured accuracy interval. The number stored alongside each record is a monotone evidence score that orders records; 0.85 represents relative rank strength. A fitted probability was withdrawn after it overstated held-out accuracy. Threshold on the band.","status":"measured","severity":"medium"},{"code":"three_way_split_is_diagnostic","basis":["The corpus is published at the two-way decision: automatable or not-automatable. The three-way split (data_only / physical / mixed) is published as a diagnostic with its measured reliability attached, not as a claim, because the rule engine's `mixed` call cannot be defended.","The engine called 22 record(s) mixed; 10 matched the human judgement (45.5%, 95% CI 26.9-65.3).","The engine's `mixed` call is right on 10/22 hand-judged records (45.5%, 95% CI 26.9%-65.3%); a constant `physical` guess scores 36.4%.","The engine's `mixed` call does not reliably beat a constant `physical` guess on the hand-judged records it labels mixed.","The sign of that difference flips between two independent samples, so the three-way refinement is not demonstrably informative.","The mixed stratum contributes a disproportionate share of errors relative to its size.","At title-only depth the physical/mixed split collapses: a title says that work was done, not whether it was also analysed."],"claim":"The published decision is two-way","gloss":"The three-way split is shown for diagnosis only. The published split is two ways.","detail":"Count and filter the corpus on automatable versus not-automatable. The data_only / physical / mixed split remains an internal engine diagnostic because the mixed call has lower measured reliability.","status":"measured","severity":"medium"},{"code":"automatable_flag_unproven","basis":["6 of 29 assay families are marked automatable now: meta_analysis, machine_learning, survival_analysis, pca, molecular_docking, differential_expression.","The flag is a rule over assay family and work type; validation begins with the first executed replication.","It inherits the 75.2% data_only agreement rate, because the flag requires the record to be analysis-only."],"claim":"Automatable now","gloss":"This flag marks assay families the rules classify as data-only. The first executed replication will validate it.","detail":"This flag marks families the rules consider replicable from data alone. Its validity depends on the analysis-only classification and will be measured through an executed replication.","status":"unverified","severity":"medium"}],"confidence_policy":"band_with_measured_interval","confidence_contract":{"policy":"band_with_measured_interval","summary":"Confidence is reported as a BAND with a measured accuracy interval. The raw evidence score supplies monotone ordering. A fitted point estimate was withdrawn after it overstated held-out accuracy.","evidence_score":"A monotone evidence score in [0,1] built from cue mass, axis separation and text coverage. Use it to order records. Interpret 0.85 as relative rank strength.","confidence_band":"low | medium | high. Consumers threshold on this value.","band_accuracy":"Wilson 95% interval on the measured agreement of the hand-judged records in this band.","calibrated_confidence":"WITHDRAWN. Reintroduction requires held-out evidence demonstrating reliable estimates across every bin."},"band_accuracy":{"low":{"n":210,"low":0.576,"band":"low","high":0.7046,"agree":135,"accuracy":0.6429},"high":{"n":76,"low":0.8903,"band":"high","high":0.9865,"agree":73,"accuracy":0.9605},"medium":{"n":104,"low":0.6795,"band":"medium","high":0.8397,"agree":80,"accuracy":0.7692}},"provider":"rule_based_v1+lex99e1195c7d6f","lexicon_id":"99e1195c7d6f","contract_published_at":"2026-10-23T12:25:29.022232+00:00","confidence_is_band":true,"confidence_is_probability":false,"decision_taxonomy":"two_way","decidable_fraction_two_way":0.8854,"decidable_fraction_two_way_low":0.8565,"decidable_fraction_two_way_high":0.9143,"decidable_fraction_three_way":0.8586,"decidable_fraction_three_way_low":0.8287,"decidable_fraction_three_way_high":0.8884,"decidable_population":5529,"validation_sample_size":438,"three_way_cost_fraction":0.0268,"three_way_cost_records":148,"decision_counts":{"automatable":230,"not_automatable":5299},"decision_split":{"automatable":{"count":230,"share":0.04159884246699222},"not_automatable":{"count":5299,"share":0.9584011575330078}},"diagnostic_work_type_counts":{"mixed":24,"physical":5275,"data_only":230}}}