{"data":{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:33490151", "kind": "science-record", "revision": 8, "content_hash": "sha256:54d3cd27d352b8661c33149ffd5004c935d3ff444681191cddf18f261365f828", "created_at": "2026-11-01T15:41:23Z", "updated_at": "2026-11-01T22:02:59Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Bioinformatics analysis to determine the prognostic value and prospective pathway signaling of miR-126 in non-small cell lung cancer.", "doi": "10.21037/atm-20-7520", "pmid": "33490151", "authors": ["Zichen Jiao", "Ao Yu", "Xiaofeng He", "Yulong Xuan", "He Zhang", "Guojun Wang", "Minke Shi", "Tao Wang"], "journal": "Annals of translational medicine", "year": 2020, "abstract": "BACKGROUND: MicroRNAs (miRNAs) have been demonstrated to play crucial roles in the initiation and development of non-small cell lung cancer (NSCLC). However, further investigation of the specific role of miR-126 in NSCLC is still required.\nMETHODS: An analysis of miR-126 expression in NSCLC was carried out using the Gene Expression Omnibus (GEO) database, and a literature review was also performed. The differentially expressed genes (DEGs) in three mRNA datasets, GSE18842, GSE19804, and GSE101929, from GEO were identified. Following the prediction of hsa-miR-126-5p target genes by TargetScan, the overlap of miR-126 target genes with DEGs in NSCLC was examined. After that, Gene Ontology enrichment and Kyoto Encyclopedia of Genes and Genomes pathway analyses were performed. Finally, an analysis to identify the impact of hub genes on the prognosis of NSCLC was carried out on the basis of a protein-protein interaction (PPI) network constructed using STRING and Cytoscape.\nRESULTS: The data in the literature review revealed a trend that miR126 was downregulated in NSCLC. The number of both NSCLC-related and miR-126-related DEGs was 187. Dozens of DEGs were significantly enriched in biological regulation, cell membrane binding, and signal receptor binding. In the PPI network analysis, 3 of 10 identified hub genes, namely NCAPG, MELK, and KIAA0101, were obviously related to poor prognosis in NSCLC; the survival rate was low among patients with high expression levels of these genes. Furthermore, through network analysis, TPX2, HMMR, and ANLN were identified as recessive miR-126-related genes that may be involved in NSCLC.\nCONCLUSIONS: MiR-126 plays an essential role in the biological processes of NSCLC through binding to target genes and influences the prognosis of patients with the disease.", "claims": [{"id": "claim-method", "statement": "The Kaplan-Meier method was used to analyze the NSCLC patients’ survival.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:33490151", "locator": "sections[6] \"Survival analysis\" paragraph 2", "quote": "The Kaplan-Meier method was used to analyze the NSCLC patients’ survival."}], "state": "complete"}, {"id": "claim-data-access", "statement": "Three microarray datasets related to the expression of miR-126 in NSCLC tissue samples and adjacent noncancerous lung tissue (ANLT) samples were obtained: GSE101929, GSE18842, and GSE19804.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:33490151", "locator": "sections[3] \"Selection of GEO datasets\" paragraph 2", "quote": "Three microarray datasets related to the expression of miR-126 in NSCLC tissue samples and adjacent noncancerous lung tissue (ANLT) samples were obtained: GSE101929, GSE18842, and GSE19804."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "complete", "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:33490151"], "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:GSE101929"], "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:GSE101929"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:33490151", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.21037/atm-20-7520", "sha256": "sha256:c58edaa4072cce9057878c8fd0d3e97d5ee6c0c0e7cfcc374608dce218d90f2d", "bytes": 31752, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.21037/atm-20-7520", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC7812220", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE101929", "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=GSE101929", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE101929", "version": null, "note": "Three microarray datasets related to the expression of miR-126 in NSCLC tissue samples and adjacent noncancerous lung tissue (ANLT) samples were obtained: GSE101929, GSE18842, and GSE19804.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "Three microarray datasets related to the expression of miR-126 in NSCLC tissue samples and adjacent noncancerous lung tissue (ANLT) samples were obtained: GSE101929, GSE18842, and GSE19804.", "access_statement_kind": "repository_route_statement", "sample_accessions": ["GSM2718949", "GSM2718950", "GSM2718951", "GSM2718952", "GSM2718953", "GSM2718954", "GSM2718955", "GSM2718956", "GSM2718957", "GSM2718958", "GSM2718959", "GSM2718960", "GSM2718961", "GSM2718962", "GSM2718963", "GSM2718964", "GSM2718965", "GSM2718966", "GSM2718967", "GSM2718968", "GSM2718969", "GSM2718970", "GSM2718971", "GSM2718972", "GSM2718973", "GSM2718974", "GSM2718975", "GSM2718976", "GSM2718977", "GSM2718978", "GSM2718979", "GSM2718980", "GSM2718981", "GSM2718982", "GSM2718983", "GSM2718984", "GSM2718985", "GSM2718986", "GSM2718987", "GSM2718988", "GSM2718989", "GSM2718990", "GSM2718991", "GSM2718992", "GSM2718993", "GSM2718994", "GSM2718995", "GSM2718996", "GSM2718997", "GSM2718998", "GSM2718999", "GSM2719000", "GSM2719001", "GSM2719002", "GSM2719003", "GSM2719004", "GSM2719005", "GSM2719006", "GSM2719007", "GSM2719008", "GSM2719009", "GSM2719010", "GSM2719011", "GSM2719012", "GSM2719013", "GSM2719014"], "sample_count": 66, "group_sizes": null, "group_sizes_basis": null, "platform": "570", "taxon": "Homo sapiens", "title": "Gene expression data from African Americans and European Americans with non-small cell lung cancer", "resolution_checked_at": "2026-11-01T15:39:54Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:GSE102286", "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=GSE102286", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE102286", "version": null, "note": "Three microarray datasets related to the expression of miR-126 in NSCLC tissue samples and adjacent noncancerous lung tissue (ANLT) samples were obtained: GSE101929, GSE18842, and GSE19804.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "Three microarray datasets related to the expression of miR-126 in NSCLC tissue samples and adjacent noncancerous lung tissue (ANLT) samples were obtained: GSE101929, GSE18842, and GSE19804.", "access_statement_kind": "repository_route_statement", "sample_accessions": ["GSM2732934", "GSM2732935", "GSM2732936", "GSM2732937", "GSM2732938", "GSM2732939", "GSM2732940", "GSM2732941", "GSM2732942", "GSM2732943", "GSM2732944", "GSM2732945", "GSM2732946", "GSM2732947", "GSM2732948", "GSM2732949", "GSM2732950", "GSM2732951", "GSM2732952", "GSM2732953", "GSM2732954", "GSM2732955", "GSM2732956", "GSM2732957", "GSM2732958", "GSM2732959", "GSM2732960", "GSM2732961", "GSM2732962", "GSM2732963", "GSM2732964", "GSM2732965", "GSM2732966", "GSM2732967", "GSM2732968", "GSM2732969", "GSM2732970", "GSM2732971", "GSM2732972", "GSM2732973", "GSM2732974", "GSM2732975", "GSM2732976", "GSM2732977", "GSM2732978", "GSM2732979", "GSM2732980", "GSM2732981", "GSM2732982", "GSM2732983", "GSM2732984", "GSM2732985", "GSM2732986", "GSM2732987", "GSM2732988", "GSM2732989", "GSM2732990", "GSM2732991", "GSM2732992", "GSM2732993", "GSM2732994", "GSM2732995", "GSM2732996", "GSM2732997", "GSM2732998", "GSM2732999", "GSM2733000", "GSM2733001", "GSM2733002", "GSM2733003", "GSM2733004", "GSM2733005", "GSM2733006", "GSM2733007", "GSM2733008", "GSM2733009", "GSM2733010", "GSM2733011", "GSM2733012", "GSM2733013", "GSM2733014", "GSM2733015", "GSM2733016", "GSM2733017", "GSM2733018", "GSM2733019", "GSM2733020", "GSM2733021", "GSM2733022", "GSM2733023", "GSM2733024", "GSM2733025", "GSM2733026", "GSM2733027", "GSM2733028", "GSM2733029", "GSM2733030", "GSM2733031", "GSM2733032", "GSM2733033", "GSM2733034", "GSM2733035", "GSM2733036", "GSM2733037", "GSM2733038", "GSM2733039", "GSM2733040", "GSM2733041", "GSM2733042", "GSM2733043", "GSM2733044", "GSM2733045", "GSM2733046", "GSM2733047", "GSM2733048", "GSM2733049", "GSM2733050", "GSM2733051", "GSM2733052", "GSM2733053", "GSM2733054", "GSM2733055", "GSM2733056", "GSM2733057", "GSM2733058", "GSM2733059", "GSM2733060", "GSM2733061", "GSM2733062", "GSM2733063", "GSM2733064", "GSM2733065", "GSM2733066", "GSM2733067", "GSM2733068", "GSM2733069", "GSM2733070", "GSM2733071", "GSM2733072", "GSM2733073", "GSM2733074", "GSM2733075", "GSM2733076", "GSM2733077", "GSM2733078", "GSM2733079", "GSM2733080", "GSM2733081", "GSM2733082", "GSM2733083", "GSM2733084", "GSM2733085", "GSM2733086", "GSM2733087", "GSM2733088", "GSM2733089", "GSM2733090", "GSM2733091", "GSM2733092", "GSM2733093", "GSM2733094", "GSM2733095", "GSM2733096", "GSM2733097", "GSM2733098", "GSM2733099", "GSM2733100", "GSM2733101", "GSM2733102", "GSM2733103", "GSM2733104", "GSM2733105", "GSM2733106", "GSM2733107", "GSM2733108", "GSM2733109", "GSM2733110", "GSM2733111", "GSM2733112"], "sample_count": 179, "group_sizes": null, "group_sizes_basis": null, "platform": "23871", "taxon": "Homo sapiens", "title": "MicroRNA expression data from African Americans and European Americans with non-small cell lung cancer", "resolution_checked_at": "2026-11-01T15:39:54Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:GSE102287", "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=GSE102287", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE102287", "version": null, "note": "Three microarray datasets related to the expression of miR-126 in NSCLC tissue samples and adjacent noncancerous lung tissue (ANLT) samples were obtained: GSE101929, GSE18842, and GSE19804.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "Three microarray datasets related to the expression of miR-126 in NSCLC tissue samples and adjacent noncancerous lung tissue (ANLT) samples were obtained: GSE101929, GSE18842, and GSE19804.", "access_statement_kind": "repository_route_statement", "sample_accessions": ["GSM2718949", "GSM2718950", "GSM2718951", "GSM2718952", "GSM2718953", "GSM2718954", "GSM2718955", "GSM2718956", "GSM2718957", "GSM2718958", "GSM2718959", "GSM2718960", "GSM2718961", "GSM2718962", "GSM2718963", "GSM2718964", "GSM2718965", "GSM2718966", "GSM2718967", "GSM2718968", "GSM2718969", "GSM2718970", "GSM2718971", "GSM2718972", "GSM2718973", "GSM2718974", "GSM2718975", "GSM2718976", "GSM2718977", "GSM2718978", "GSM2718979", "GSM2718980", "GSM2718981", "GSM2718982", "GSM2718983", "GSM2718984", "GSM2718985", "GSM2718986", "GSM2718987", "GSM2718988", "GSM2718989", "GSM2718990", "GSM2718991", "GSM2718992", "GSM2718993", "GSM2718994", "GSM2718995", "GSM2718996", "GSM2718997", "GSM2718998", "GSM2718999", "GSM2719000", "GSM2719001", "GSM2719002", "GSM2719003", "GSM2719004", "GSM2719005", "GSM2719006", "GSM2719007", "GSM2719008", "GSM2719009", "GSM2719010", "GSM2719011", "GSM2719012", "GSM2719013", "GSM2719014", "GSM2732934", "GSM2732935", "GSM2732936", "GSM2732937", "GSM2732938", "GSM2732939", "GSM2732940", "GSM2732941", "GSM2732942", "GSM2732943", "GSM2732944", "GSM2732945", "GSM2732946", "GSM2732947", "GSM2732948", "GSM2732949", "GSM2732950", "GSM2732951", "GSM2732952", "GSM2732953", "GSM2732954", "GSM2732955", "GSM2732956", "GSM2732957", "GSM2732958", "GSM2732959", "GSM2732960", "GSM2732961", "GSM2732962", "GSM2732963", "GSM2732964", "GSM2732965", "GSM2732966", "GSM2732967", "GSM2732968", "GSM2732969", "GSM2732970", "GSM2732971", "GSM2732972", "GSM2732973", "GSM2732974", "GSM2732975", "GSM2732976", "GSM2732977", "GSM2732978", "GSM2732979", "GSM2732980", "GSM2732981", "GSM2732982", "GSM2732983", "GSM2732984", "GSM2732985", "GSM2732986", "GSM2732987", "GSM2732988", "GSM2732989", "GSM2732990", "GSM2732991", "GSM2732992", "GSM2732993", "GSM2732994", "GSM2732995", "GSM2732996", "GSM2732997", "GSM2732998", "GSM2732999", "GSM2733000", "GSM2733001", "GSM2733002", "GSM2733003", "GSM2733004", "GSM2733005", "GSM2733006", "GSM2733007", "GSM2733008", "GSM2733009", "GSM2733010", "GSM2733011", "GSM2733012", "GSM2733013", "GSM2733014", "GSM2733015", "GSM2733016", "GSM2733017", "GSM2733018", "GSM2733019", "GSM2733020", "GSM2733021", "GSM2733022", "GSM2733023", "GSM2733024", "GSM2733025", "GSM2733026", "GSM2733027", "GSM2733028", "GSM2733029", "GSM2733030", "GSM2733031", "GSM2733032", "GSM2733033", "GSM2733034", "GSM2733035", "GSM2733036", "GSM2733037", "GSM2733038", "GSM2733039", "GSM2733040", "GSM2733041", "GSM2733042", "GSM2733043", "GSM2733044", "GSM2733045", "GSM2733046", "GSM2733047", "GSM2733048", "GSM2733049", "GSM2733050", "GSM2733051", "GSM2733052", "GSM2733053", "GSM2733054", "GSM2733055", "GSM2733056", "GSM2733057", "GSM2733058", "GSM2733059", "GSM2733060", "GSM2733061", "GSM2733062", "GSM2733063", "GSM2733064", "GSM2733065", "GSM2733066", "GSM2733067", "GSM2733068", "GSM2733069", "GSM2733070", "GSM2733071", "GSM2733072", "GSM2733073", "GSM2733074", "GSM2733075", "GSM2733076", "GSM2733077", "GSM2733078", "GSM2733079", "GSM2733080", "GSM2733081", "GSM2733082", "GSM2733083", "GSM2733084", "GSM2733085", "GSM2733086", "GSM2733087", "GSM2733088", "GSM2733089", "GSM2733090", "GSM2733091", "GSM2733092", "GSM2733093", "GSM2733094", "GSM2733095", "GSM2733096", "GSM2733097", "GSM2733098", "GSM2733099", "GSM2733100", "GSM2733101", "GSM2733102", "GSM2733103", "GSM2733104", "GSM2733105", "GSM2733106", "GSM2733107", "GSM2733108", "GSM2733109", "GSM2733110", "GSM2733111", "GSM2733112"], "sample_count": 245, "group_sizes": null, "group_sizes_basis": null, "platform": "570;23871", "taxon": "Homo sapiens", "title": "Gene and microRNA expression data from African Americans and European Americans with non-small cell lung cancer", "resolution_checked_at": "2026-11-01T15:39:54Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:GSE18842", "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=GSE18842", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE18842", "version": null, "note": "Three microarray datasets related to the expression of miR-126 in NSCLC tissue samples and adjacent noncancerous lung tissue (ANLT) samples were obtained: GSE101929, GSE18842, and GSE19804.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "Three microarray datasets related to the expression of miR-126 in NSCLC tissue samples and adjacent noncancerous lung tissue (ANLT) samples were obtained: GSE101929, GSE18842, and GSE19804.", "access_statement_kind": "repository_route_statement", "sample_accessions": ["GSM466947", "GSM466948", "GSM466949", "GSM466950", "GSM466951", "GSM466952", "GSM466953", "GSM466954", "GSM466955", "GSM466956", "GSM466957", "GSM466958", "GSM466959", "GSM466960", "GSM466961", "GSM466962", "GSM466963", "GSM466964", "GSM466965", "GSM466966", "GSM466967", "GSM466968", "GSM466969", "GSM466970", "GSM466971", "GSM466972", "GSM466973", "GSM466974", "GSM466975", "GSM466976", "GSM466977", "GSM466978", "GSM466979", "GSM466980", "GSM466981", "GSM466982", "GSM466983", "GSM466984", "GSM466985", "GSM466986", "GSM466987", "GSM466988", "GSM466989", "GSM466990", "GSM466991", "GSM466992", "GSM466993", "GSM466994", "GSM466995", "GSM466996", "GSM466997", "GSM466998", "GSM466999", "GSM467000", "GSM467001", "GSM467002", "GSM467003", "GSM467004", "GSM467005", "GSM467006", "GSM467007", "GSM467008", "GSM467009", "GSM467010", "GSM467011", "GSM467012", "GSM467013", "GSM467014", "GSM467015", "GSM467016", "GSM467017", "GSM467018", "GSM467019", "GSM467020", "GSM467021", "GSM467022", "GSM467023", "GSM467024", "GSM467025", "GSM467026", "GSM467027", "GSM467028", "GSM467029", "GSM467030", "GSM467031", "GSM467032", "GSM467033", "GSM467034", "GSM467035", "GSM467036", "GSM467037"], "sample_count": 91, "group_sizes": null, "group_sizes_basis": null, "platform": "570", "taxon": "Homo sapiens", "title": "Gene expression analysis of human lung cancer and control samples", "resolution_checked_at": "2026-11-01T15:39:54Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:GSE19804", "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=GSE19804", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE19804", "version": null, "note": "Three microarray datasets related to the expression of miR-126 in NSCLC tissue samples and adjacent noncancerous lung tissue (ANLT) samples were obtained: GSE101929, GSE18842, and GSE19804.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "Three microarray datasets related to the expression of miR-126 in NSCLC tissue samples and adjacent noncancerous lung tissue (ANLT) samples were obtained: GSE101929, GSE18842, and GSE19804.", "access_statement_kind": "repository_route_statement", "sample_accessions": ["GSM494556", "GSM494557", "GSM494558", "GSM494559", "GSM494560", "GSM494561", "GSM494562", "GSM494563", "GSM494564", "GSM494565", "GSM494566", "GSM494567", "GSM494568", "GSM494569", "GSM494570", "GSM494571", "GSM494572", "GSM494573", "GSM494574", "GSM494575", "GSM494576", "GSM494577", "GSM494578", "GSM494579", "GSM494580", "GSM494581", "GSM494582", "GSM494583", "GSM494584", "GSM494585", "GSM494586", "GSM494587", "GSM494588", "GSM494589", "GSM494590", "GSM494591", "GSM494592", "GSM494593", "GSM494594", "GSM494595", "GSM494596", "GSM494597", "GSM494598", "GSM494599", "GSM494600", "GSM494601", "GSM494602", "GSM494603", "GSM494604", "GSM494605", "GSM494606", "GSM494607", "GSM494608", "GSM494609", "GSM494610", "GSM494611", "GSM494612", "GSM494613", "GSM494614", "GSM494615", "GSM494616", "GSM494617", "GSM494618", "GSM494619", "GSM494620", "GSM494621", "GSM494622", "GSM494623", "GSM494624", "GSM494625", "GSM494626", "GSM494627", "GSM494628", "GSM494629", "GSM494630", "GSM494631", "GSM494632", "GSM494633", "GSM494634", "GSM494635", "GSM494636", "GSM494637", "GSM494638", "GSM494639", "GSM494640", "GSM494641", "GSM494642", "GSM494643", "GSM494644", "GSM494645", "GSM494646", "GSM494647", "GSM494648", "GSM494649", "GSM494650", "GSM494651", "GSM494652", "GSM494653", "GSM494654", "GSM494655", "GSM494656", "GSM494657", "GSM494658", "GSM494659", "GSM494660", "GSM494661", "GSM494662", "GSM494663", "GSM494664", "GSM494665", "GSM494666", "GSM494667", "GSM494668", "GSM494669", "GSM494670", "GSM494671", "GSM494672", "GSM494673", "GSM494674", "GSM494675"], "sample_count": 120, "group_sizes": null, "group_sizes_basis": null, "platform": "570", "taxon": "Homo sapiens", "title": "Genome-wide screening of transcriptional modulation in non-smoking female lung cancer in Taiwan", "resolution_checked_at": "2026-11-01T15:39:54Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:GSE27705", "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=GSE27705", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE27705", "version": null, "note": "Three microarray datasets related to the expression of miR-126 in NSCLC tissue samples and adjacent noncancerous lung tissue (ANLT) samples were obtained: GSE101929, GSE18842, and GSE19804.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "Three microarray datasets related to the expression of miR-126 in NSCLC tissue samples and adjacent noncancerous lung tissue (ANLT) samples were obtained: GSE101929, GSE18842, and GSE19804.", "access_statement_kind": "repository_route_statement", "sample_accessions": ["GSM686110", "GSM686111", "GSM686112", "GSM686113", "GSM686114", "GSM686115", "GSM686116", "GSM686117", "GSM686118", "GSM686119", "GSM686120", "GSM686121", "GSM686122", "GSM686123", "GSM686124", "GSM686125", "GSM686126", "GSM686127", "GSM686128", "GSM686129", "GSM686130", "GSM686131", "GSM686132", "GSM686133", "GSM686134", "GSM686135", "GSM686136", "GSM686137", "GSM686138", "GSM686139"], "sample_count": 30, "group_sizes": null, "group_sizes_basis": null, "platform": "11432", "taxon": "Rattus norvegicus; Human alphaherpesvirus 2; JC polyomavirus; Merkel cell polyomavirus; Homo sapiens; Murid gammaherpesvirus 4; Betapolyomavirus hominis; human gammaherpesvirus 4; Human gammaherpesvirus 8; Mus musculus cytomegalovirus 2; Betapolyomavirus macacae; Mus musculus; Human alphaherpesvirus 1; Human betaherpesvirus 5; Human immunodeficiency virus 1", "title": "Signature of MicroRNAs with Impact on Angiogenesis in Non-Small Cell Lung Cancer", "resolution_checked_at": "2026-11-01T15:39:54Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:GSE29248", "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=GSE29248", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE29248", "version": null, "note": "Three microarray datasets related to the expression of miR-126 in NSCLC tissue samples and adjacent noncancerous lung tissue (ANLT) samples were obtained: GSE101929, GSE18842, and GSE19804.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "Three microarray datasets related to the expression of miR-126 in NSCLC tissue samples and adjacent noncancerous lung tissue (ANLT) samples were obtained: GSE101929, GSE18842, and GSE19804.", "access_statement_kind": "repository_route_statement", "sample_accessions": ["GSM723147", "GSM723148", "GSM723149", "GSM723150", "GSM723151", "GSM723152", "GSM723153", "GSM723154", "GSM723155", "GSM723156", "GSM723157", "GSM723158"], "sample_count": 12, "group_sizes": null, "group_sizes_basis": null, "platform": "8179", "taxon": "Homo sapiens", "title": "Genome-wide analysis of  microRNA expression in Non-small Cell Lung Cancer", "resolution_checked_at": "2026-11-01T15:39:54Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:GSE63805", "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=GSE63805", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE63805", "version": null, "note": "Three microarray datasets related to the expression of miR-126 in NSCLC tissue samples and adjacent noncancerous lung tissue (ANLT) samples were obtained: GSE101929, GSE18842, and GSE19804.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "Three microarray datasets related to the expression of miR-126 in NSCLC tissue samples and adjacent noncancerous lung tissue (ANLT) samples were obtained: GSE101929, GSE18842, and GSE19804.", "access_statement_kind": "repository_route_statement", "sample_accessions": ["GSM1557646", "GSM1557647", "GSM1557648", "GSM1557649", "GSM1557650", "GSM1557651", "GSM1557652", "GSM1557653", "GSM1557654", "GSM1557655", "GSM1557656", "GSM1557657", "GSM1557658", "GSM1557659", "GSM1557660", "GSM1557661", "GSM1557662", "GSM1557663", "GSM1557664", "GSM1557665", "GSM1557666", "GSM1557667", "GSM1557668", "GSM1557669", "GSM1557670", "GSM1557671", "GSM1557672", "GSM1557673", "GSM1557674", "GSM1557675", "GSM1557676", "GSM1557677", "GSM1557678", "GSM1557679", "GSM1557680", "GSM1557681", "GSM1557682", "GSM1557683", "GSM1557684", "GSM1557685", "GSM1557686", "GSM1557687", "GSM1557688", "GSM1557689", "GSM1557690", "GSM1557691", "GSM1557692", "GSM1557693", "GSM1557694", "GSM1557695", "GSM1557696", "GSM1557697", "GSM1557698", "GSM1557699", "GSM1557700", "GSM1557701", "GSM1557702", "GSM1557703", "GSM1557704", "GSM1557705", "GSM1557706", "GSM1557707"], "sample_count": 62, "group_sizes": null, "group_sizes_basis": null, "platform": "18410", "taxon": "Homo sapiens", "title": "Multi-platform Characterization of Stage I Lung Adenocarcinoma (miRNA profiling)", "resolution_checked_at": "2026-11-01T15:39:55Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "asset:table:pmid:33490151:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:20decf2b309508c38ba6e43c8c7225afc29683ef2c16cdb0b46cf351407e6e45", "bytes": 708, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[14]/table-wrap[1]#t5", "version": null, "note": "Correlation between hsa-miR-126 and target genes in NSCLC patients (n=62)", "structure": {"pmcid": "PMC7812220", "section_index": 6, "section_title": "Survival analysis", "row_count": 11, "column_count": 4}, "table": {"label": "Table 5", "caption": "Correlation between hsa-miR-126 and target genes in NSCLC patients (n=62)", "rows": [["miRNA", "Target gene", "r", "P value"], ["hsa-miR-126", "ANLN", "−0.2886", "0.0229"], ["hsa-miR-126", "HMMR", "−0.2737", "0.0314"], ["hsa-miR-126", "KIF15", "−0.1640", "0.2029"], ["hsa-miR-126", "MELK", "−0.2202", "0.0855"], ["hsa-miR-126", "NCAPG", "−0.2256", "0.0780"], ["hsa-miR-126", "NUF2", "−0.2328", "0.0686"], ["hsa-miR-126", "TPX2", "−0.2602", "0.0411"], ["hsa-miR-126", "BUB1B", "−0.2408", "0.0594"], ["hsa-miR-126", "KIAA0101", "−0.2454", "0.0545"], ["hsa-miR-126", "CCNB1", "−0.2158", "0.0921"]], "row_count": 11, "column_count": 4, "numeric_cells": 32, "header_rows": 1, "locator": "section[14]/table-wrap[1]#t5"}}, {"id": "asset:table:pmid:33490151:2", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:771b928a309598104cd9a7fc73f5647391660e7521af1de2716e5c6f76460f3d", "bytes": 655, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[9]/table-wrap[1]#t1", "version": null, "note": "Characteristics of the Gene Expression Omnibus (GEO) datasets", "structure": {"pmcid": "PMC7812220", "section_index": 9, "section_title": "miR-126 expression in NSCLC based on GEO", "row_count": 7, "column_count": 10}, "table": {"label": "Table 1", "caption": "Characteristics of the Gene Expression Omnibus (GEO) datasets", "rows": [["Dataset", "NSCLC", "", "Normal control", "t", "P"], ["Mean", "SD", "n", "Mean", "SD", "n"], ["GSE27705", "0.45", "0.22", "20", "", "2.07", "1.27", "10", "4.00", "0.003"], ["GSE63805", "13.79", "1.19", "31", "", "14.15", "1.09", "31", "1.24", "0.220"], ["GSE29248", "13.18", "0.23", "6", "", "13.58", "0.19", "6", "3.31", "0.008"], ["GSE102286", "12.59", "0.72", "90", "", "14.34", "0.71", "89", "16.29", "0.000"], ["Total", "SMD =−1.69 (95% CI: −2.97 to −0.41), P=0.009, I2=93.3%, P=0.000"]], "row_count": 7, "column_count": 10, "numeric_cells": 37, "header_rows": 2, "locator": "section[9]/table-wrap[1]#t1"}}, {"id": "asset:table:pmid:33490151:3", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:b76fac77fcf35594ce9b1fb8bf756603841ef8f0c28eb9b1e8a8aec61ead1e7e", "bytes": 792, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[10]/table-wrap[1]#t2", "version": null, "note": "Studies included from the literature", "structure": {"pmcid": "PMC7812220", "section_index": 10, "section_title": "Expression profiles of miR-126 in NSCLC and ANLT in the literature", "row_count": 8, "column_count": 10}, "table": {"label": "Table 2", "caption": "Studies included from the literature", "rows": [["Author", "Year", "Country", "Case", "", "Control", "Result", "Detection methods"], ["Source name", "n", "Source name", "n"], ["Yang JY", "2012", "China", "NSCLC", "167", "", "ANLT", "167", "Down-regulation", "qRT-PCR"], ["Kim", "2014", "Korea", "NSCLC", "72", "", "BLT", "30", "Down-regulation", "qRT-PCR"], ["Li XG", "2014", "China", "NSCLC", "49", "", "ANLT", "49", "Down-regulation", "qRT-PCR"], ["Chen SW", "2015", "China", "NSCLC", "113", "", "ANLT", "113", "Down-regulation", "qRT-PCR"], ["Begum", "2015", "USA", "NSCLC", "18", "", "ANLT", "18", "Down-regulation", "qRT-PCR"], ["Switlik", "2017", "Poland", "NSCLC", "50", "", "ANLT", "50", "Down-regulation", "qRT-PCR"]], "row_count": 8, "column_count": 10, "numeric_cells": 18, "header_rows": 2, "locator": "section[10]/table-wrap[1]#t2"}}, {"id": "asset:table:pmid:33490151:4", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:8bb6d80e27ca300f3a8928492ee76ec9f55852f47ce784b0db52d6ac2632f257", "bytes": 1318, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[11]/table-wrap[1]#t3", "version": null, "note": "Top 10 differentially expressed genes related to hsa-miR-126-5p in NSCLC based on data from Gene Expression Omnibus (GSE101929)", "structure": {"pmcid": "PMC7812220", "section_index": 11, "section_title": "miR-126 target prediction and bioinformatics analysis, data preprocessing and screening of DEGs", "row_count": 23, "column_count": 4}, "table": {"label": "Table 3", "caption": "Top 10 differentially expressed genes related to hsa-miR-126-5p in NSCLC based on data from Gene Expression Omnibus (GSE101929)", "rows": [["DEG", "logFC", "P value", "adj. P value"], ["Up-regulated genes"], ["COL11A1", "4.422953836", "2.39E-19", "6.08E-17"], ["TMPRSS4", "4.221629522", "4.37E-10", "8.69E-09"], ["TPX2", "3.807505294", "9.78E-12", "3.07E-10"], ["GJB2", "3.796664393", "2.78E-14", "1.66E-12"], ["ADAMDEC1", "3.708366029", "5.52E-09", "8.22E-08"], ["GCNT3", "3.685815147", "6.40E-10", "1.22E-08"], ["MELK", "3.59921375", "9.24E-17", "1.04E-14"], ["ANLN", "3.459272472", "5.15E-11", "1.31E-09"], ["GINS1", "3.379747077", "1.33E-15", "1.12E-13"], ["LGSN", "3.311053254", "5.50E-07", "4.85E-06"], ["Down-regulated genes"], ["SCN4B", "−3.966201158", "2.47E-18", "4.37E-16"], ["PGC", "−4.101979531", "1.07E-08", "1.46E-07"], ["TCF21", "−4.1755375", "3.80E-21", "1.98E-18"], ["CYP4B1", "−4.188821121", "1.11E-12", "4.46E-11"], ["IGSF10", "−4.295135221", "8.70E-21", "3.70E-18"], ["MAMDC2", "−4.641650221", "4.93E-16", "4.54E-14"], ["GKN2", "−4.84796114", "6.20E-15", "4.38E-13"], ["SOSTDC1", "−5.507636397", "9.25E-21", "3.85E-18"], ["TMEM100", "−5.954176691", "6.04E-21", "2.86E-18"], ["SLC6A4", "−6.365475914", "2.88E-25", "8.40E-22"]], "row_count": 23, "column_count": 4, "numeric_cells": 64, "header_rows": 1, "locator": "section[11]/table-wrap[1]#t3"}}, {"id": "asset:table:pmid:33490151:5", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:d16653449bb35b314df849e9127e1a3595a898b2da268ed83c07350972fc23d7", "bytes": 931, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[12]/table-wrap[1]#t4", "version": null, "note": "GO and KEGG enrichment analysis of differentially expressed genes related to hsa-miR-126-5p in NSCLC", "structure": {"pmcid": "PMC7812220", "section_index": 12, "section_title": "Functional analysis of miR-126-related DEGs in NSCLC", "row_count": 15, "column_count": 4}, "table": {"label": "Table 4", "caption": "GO and KEGG enrichment analysis of differentially expressed genes related to hsa-miR-126-5p in NSCLC", "rows": [["Term", "Description", "Count", "FDR"], ["Biological processes", "", ""], ["GO:0050896", "Response to stimulus", "101", "0.0043"], ["GO:0065007", "Biological regulation", "133", "0.0276"], ["GO:0009987", "Cellular process", "157", "0.0408"], ["Molecular function (GO)", "", ""], ["GO:1901681", "Sulfur compound binding", "10", "0.0221"], ["GO:0005539", "Glycosaminoglycan binding", "11", "0.0073"], ["GO:0005102", "Signaling receptor binding", "30", "0.0221"], ["Cellular component", "", ""], ["GO:0005886", "Plasma membrane", "86", "1.58E-06"], ["GO:0071944", "Cell periphery", "88", "1.38E-06"], ["GO:0016020", "Membrane", "107", "0.0024"], ["KEGG pathway", "", "", ""], ["hsa04974", "Protein digestion and absorption", "7", "0.0061"]], "row_count": 15, "column_count": 4, "numeric_cells": 30, "header_rows": 2, "locator": "section[12]/table-wrap[1]#t4"}}, {"id": "asset:table:pmid:33490151:6", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:20decf2b309508c38ba6e43c8c7225afc29683ef2c16cdb0b46cf351407e6e45", "bytes": 708, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[14]/table-wrap[1]#t5", "version": null, "note": "Correlation between hsa-miR-126 and target genes in NSCLC patients (n=62)", "structure": {"pmcid": "PMC7812220", "section_index": 14, "section_title": "Survival analysis", "row_count": 11, "column_count": 4}, "table": {"label": "Table 5", "caption": "Correlation between hsa-miR-126 and target genes in NSCLC patients (n=62)", "rows": [["miRNA", "Target gene", "r", "P value"], ["hsa-miR-126", "ANLN", "−0.2886", "0.0229"], ["hsa-miR-126", "HMMR", "−0.2737", "0.0314"], ["hsa-miR-126", "KIF15", "−0.1640", "0.2029"], ["hsa-miR-126", "MELK", "−0.2202", "0.0855"], ["hsa-miR-126", "NCAPG", "−0.2256", "0.0780"], ["hsa-miR-126", "NUF2", "−0.2328", "0.0686"], ["hsa-miR-126", "TPX2", "−0.2602", "0.0411"], ["hsa-miR-126", "BUB1B", "−0.2408", "0.0594"], ["hsa-miR-126", "KIAA0101", "−0.2454", "0.0545"], ["hsa-miR-126", "CCNB1", "−0.2158", "0.0921"]], "row_count": 11, "column_count": 4, "numeric_cells": 32, "header_rows": 1, "locator": "section[14]/table-wrap[1]#t5"}}], "gaps": ["asset:data:geo:GSE101929 not downloaded", "asset:data:geo:GSE101929 licence not read", "asset:data:geo:GSE102286 not downloaded", "asset:data:geo:GSE102286 licence not read", "asset:data:geo:GSE102287 not downloaded", "asset:data:geo:GSE102287 licence not read", "asset:data:geo:GSE18842 not downloaded", "asset:data:geo:GSE18842 licence not read", "asset:data:geo:GSE19804 not downloaded", "asset:data:geo:GSE19804 licence not read", "asset:data:geo:GSE27705 not downloaded", "asset:data:geo:GSE27705 licence not read", "asset:data:geo:GSE29248 not downloaded", "asset:data:geo:GSE29248 licence not read", "asset:data:geo:GSE63805 not downloaded", "asset:data:geo:GSE63805 licence not read"]}, "analysis": {"state": "complete", "methods": [{"id": "method-1", "family": "survival_analysis", "specific": "kaplan_meier", "label": "Survival analysis", "dsl_operations": ["survival_km"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["time_to_event_with_censoring"], "evidence": {"score": 1.0, "band": "verbatim", "quote": "The Kaplan-Meier method was used to analyze the NSCLC patients’ survival."}}, {"id": "method-2", "family": "meta_analysis", "specific": "random_effects", "label": "Meta-analysis / evidence synthesis", "dsl_operations": ["random_effects_pool"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["study_level_effect_estimates"], "evidence": {"score": 0.8, "band": "high", "quote": "random-effects"}}, {"id": "method-3", "family": "meta_analysis", "specific": "fixed_effects", "label": "Meta-analysis / evidence synthesis", "dsl_operations": [], "missing_operations": ["fixed_effects_pool"], "expressible": false, "parameters": {}, "data_shapes": ["study_level_effect_estimates"], "evidence": {"score": 0.8, "band": "high", "quote": "fixed-effects"}}, {"id": "method-4", "family": "network_analysis", "specific": "ppi_network", "label": "Network / pathway analysis", "dsl_operations": ["build_graph", "centrality_scores", "pathway_enrich"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["edge_list"], "evidence": {"score": 0.7, "band": "medium", "quote": "protein-protein interaction"}}, {"id": "method-5", "family": "network_analysis", "specific": "pathway_enrichment", "label": "Network / pathway analysis", "dsl_operations": ["pathway_enrich"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["edge_list"], "evidence": {"score": 0.8, "band": "high", "quote": "GO enrichment"}}], "targets": [], "gaps": []}, "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": ["survival_km"], "missing_operations": [], "basis": "The paper names the method it used and the corpus's method extractor maps it onto the DSL catalogue: kaplan_meier."}, "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": ["GSE101929", "GSE18842", "GSE19804", "GSE102286", "GSE29248", "GSE63805", "GSE27705", "GSE102287"], "resolved_accessions": ["GSE101929", "GSE18842", "GSE19804", "GSE102286", "GSE29248", "GSE63805", "GSE27705", "GSE102287"], "statements": ["Three microarray datasets related to the expression of miR-126 in NSCLC tissue samples and adjacent noncancerous lung tissue (ANLT) samples were obtained: GSE101929, GSE18842, and GSE19804."], "basis": "The paper names GSE101929, GSE18842, GSE19804, GSE102286, GSE29248, GSE63805, GSE27705, GSE102287 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": ["survival_km"], "assets": ["source:pmid:33490151", "data:geo:GSE101929", "asset:table:pmid:33490151:1", "asset:table:pmid:33490151:2", "asset:table:pmid:33490151:3", "asset:table:pmid:33490151:4", "asset:table:pmid:33490151:5", "asset:table:pmid:33490151:6"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE101929"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-10-31T18:26:39Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": null}, "calls": 3, "usage": {"prompt_tokens": 26330, "completion_tokens": 1986, "cached_tokens": 776}}, "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:33490151", "type": "paper", "label": "pmid:33490151"}, {"id": "source:pmid:33490151", "type": "manuscript", "label": "PMID 33490151 full text"}, {"id": "data:geo:GSE101929", "type": "dataset", "label": "GEO GSE101929"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:33490151", "type": "paper", "label": "pmid:33490151"}, {"id": "source:pmid:33490151", "type": "manuscript", "label": "PMID 33490151 full text"}, {"id": "data:geo:GSE101929", "type": "dataset", "label": "GEO GSE101929"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-33490151", "type": "extraction", "used": ["source:pmid:33490151"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE101929", "type": "accession_resolution", "used": ["data:geo:GSE101929"], "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:33490151", "parent_hash": "sha256:c1ec8bd56f8dab5182847a188cfbe9253bf8fbb8b6739e83a9c14ea9118b9eeb", "fork_of": null, "generation": 7}, "gaps": ["asset:data:geo:GSE101929 licence not read", "asset:data:geo:GSE101929 not downloaded", "asset:data:geo:GSE102286 licence not read", "asset:data:geo:GSE102286 not downloaded", "asset:data:geo:GSE102287 licence not read", "asset:data:geo:GSE102287 not downloaded", "asset:data:geo:GSE18842 licence not read", "asset:data:geo:GSE18842 not downloaded", "asset:data:geo:GSE19804 licence not read", "asset:data:geo:GSE19804 not downloaded", "asset:data:geo:GSE27705 licence not read", "asset:data:geo:GSE27705 not downloaded", "asset:data:geo:GSE29248 licence not read", "asset:data:geo:GSE29248 not downloaded", "asset:data:geo:GSE63805 licence not read", "asset:data:geo:GSE63805 not downloaded", "execution.not_run", "review.human_critique", "review.independent_reader", "review.machine_critique"], "assays": [{"role": "analysis", "definition_id": "survival_analysis", "definition_version": "f2132e96ae6c7a4e", "definition_digest": null, "required_operations": ["survival_km"], "support_state": "supported", "source_hashes": {"dsl_catalogue": "f2132e96ae6c7a4e"}, "confidence": 1.0, "evidence": ["The Kaplan-Meier method was used to analyze the NSCLC patients’ survival."], "order_basis": "analysis_only", "id": "assay:1"}]},"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":"2026-11-04T02:51:12+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}}}