{"data":{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:39708330", "kind": "science-record", "revision": 3, "content_hash": "sha256:b251679c5a7273c04942efab3266d01e1edc5cdadddfe7a7a378c44421fc4eee", "created_at": "2026-11-01T20:30:01Z", "updated_at": "2026-11-01T22:13:24Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Deciphering the Significance of Platelet-Derived Chloride Ion Channel Gene (BEST3) Through Platelet-Related Subtypes Mining for Non-Small Cell Lung Cancer.", "doi": "10.1111/jcmm.70233", "pmid": "39708330", "authors": ["Hanxiao Ren", "Meng-Ze Du", "Yulin Liao", "Ruiling Zu", "Lubei Rao", "Run Xiang", "Xingmei Zhang", "Shan Liu", "Peiyin Zhang", "Ping Leng", "Ling Qi", "Huaichao Luo"], "journal": "Journal of cellular and molecular medicine", "year": 2024, "abstract": "This study investigates platelet-related subtypes in non-small cell lung cancer (NSCLC) and seeks to identify genes associated with prognosis, focusing on the clinical significance of the chloride ion channel gene BEST3. We utilised sequencing and clinical data from GEO, TCGA and the Xena platform, building a risk model based on genetic features. TCGA and GSE37745 served as training cohorts, while GSE50081, GSE13213, GSE30129 and GSE42127 were validation cohorts. Immunotherapy datasets (GSE135222, TCGA-SKCM) were also analysed. Differentially expressed genes (DEGs) were identified using Limma, subtypes through ConsensusClusterPlus and key prognostic genes using COX regression, Random Forest and LASSO-COX. BEST3 expression was validated by flow cytometry (FCM) and functional assays in A549 cells with lentiviral overexpression evaluated its impact on apoptosis, proliferation and migration. Three platelet-related subtypes were identified, with ten key prognostic genes (including BEST3). Gene Ontology (GO) analysis showed six genes involved in platelet pathways. BEST3 was highly expressed in the platelet subtype 1. Flow cytometry confirmed elevated BEST3 levels in NSCLC (35.9% vs. 27.3% in healthy individuals). Overexpression of BEST3 in NSCLC cells suppressed apoptosis and promoted proliferation and migration. The discovery of three platelet subtypes and the role of BEST3 in promoting tumour growth and migration highlights its potential as a therapeutic target and prognostic marker in NSCLC.", "claims": [{"id": "claim-method", "statement": "Survival analysis curves were plotted with Kaplan–Meier, and log‐rank tests were applied to compare OS differences between groups.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:39708330", "locator": "sections[15] \"Data Analysis and Statistical Methods\" paragraph 2", "quote": "Survival analysis curves were plotted with Kaplan–Meier, and log‐rank tests were applied to compare OS differences between groups."}], "state": "complete"}, {"id": "claim-data-access", "statement": "All data from study are included in this manuscript. Some of the code has been uploaded to GitHub (https://github.com/Huaichao2018/Platelet‐Related‐Subtypes‐Mining‐for‐NSCLC).", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:39708330", "locator": "sections[35] \"Data Availability Statement\" paragraph 2", "quote": "All data from study are included in this manuscript. Some of the code has been uploaded to GitHub (https://github.com/Huaichao2018/Platelet‐Related‐Subtypes‐Mining‐for‐NSCLC)."}], "state": "complete"}, {"id": "claim-target-result", "statement": "The discovery of three platelet subtypes and the role of BEST3 in promoting tumour growth and migration highlights its potential as a therapeutic target and prognostic marker in NSCLC.", "kind": "qualitative", "target": null, "evidence": [{"asset": "source:pmid:39708330", "locator": "sections[0] \"Abstract\" paragraph 1", "quote": "The discovery of three platelet subtypes and the role of BEST3 in promoting tumour growth and migration highlights its potential as a therapeutic target and prognostic marker in NSCLC."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "complete", "objective": "The discovery of three platelet subtypes and the role of BEST3 in promoting tumour growth and migration highlights its potential as a therapeutic target and prognostic marker in NSCLC.", "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:39708330"], "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:GSE13213"], "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:GSE13213"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:39708330", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1111/jcmm.70233", "sha256": "sha256:5616ab333a07d6215d376f25a58b2d59bd69932279b9093677e8182181836cff", "bytes": 52333, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1111/jcmm.70233", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC11662966", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE13213", "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=GSE13213", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE13213", "version": null, "note": "All data from study are included in this manuscript. Some of the code has been uploaded to GitHub (https://github.com/Huaichao2018/Platelet‐Related‐Subtypes‐Mining‐for‐NSCLC).", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "All data from study are included in this manuscript. Some of the code has been uploaded to GitHub (https://github.com/Huaichao2018/Platelet‐Related‐Subtypes‐Mining‐for‐NSCLC).", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM333673", "GSM333674", "GSM333675", "GSM333676", "GSM333677", "GSM333678", "GSM333679", "GSM333680", "GSM333681", "GSM333682", "GSM333683", "GSM333684", "GSM333685", "GSM333686", "GSM333687", "GSM333688", "GSM333689", "GSM333690", "GSM333691", "GSM333692", "GSM333693", "GSM333694", "GSM333695", "GSM333696", "GSM333697", "GSM333698", "GSM333699", "GSM333700", "GSM333701", "GSM333702", "GSM333703", "GSM333704", "GSM333705", "GSM333706", "GSM333707", "GSM333708", "GSM333709", "GSM333710", "GSM333711", "GSM333712", "GSM333713", "GSM333714", "GSM333715", "GSM333716", "GSM333717", "GSM333718", "GSM333719", "GSM333720", "GSM333721", "GSM333722", "GSM333723", "GSM333724", "GSM333725", "GSM333726", "GSM333727", "GSM333728", "GSM333729", "GSM333730", "GSM333731", "GSM333732", "GSM333733", "GSM333734", "GSM333735", "GSM333736", "GSM333737", "GSM333738", "GSM333739", "GSM333740", "GSM333741", "GSM333742", "GSM333743", "GSM333744", "GSM333745", "GSM333746", "GSM333747", "GSM333748", "GSM333749", "GSM333750", "GSM333751", "GSM333752", "GSM333753", "GSM333754", "GSM333755", "GSM333756", "GSM333757", "GSM333758", "GSM333759", "GSM333760", "GSM333761", "GSM333762", "GSM333763", "GSM333764", "GSM333765", "GSM333766", "GSM333767", "GSM333768", "GSM333769", "GSM333770", "GSM333771", "GSM333772", "GSM333773", "GSM333774", "GSM333775", "GSM333776", "GSM333777", "GSM333778", "GSM333779", "GSM333780", "GSM333781", "GSM333782", "GSM333783", "GSM333784", "GSM333785", "GSM333786", "GSM333787", "GSM333788", "GSM333789"], "sample_count": 117, "group_sizes": null, "group_sizes_basis": null, "platform": "6480", "taxon": "Homo sapiens", "title": "Relapse-related molecular signature in lung adenocarcinomas identifies patients with dismal prognosis", "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:GSE135222", "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=GSE135222", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE135222", "version": null, "note": "All data from study are included in this manuscript. Some of the code has been uploaded to GitHub (https://github.com/Huaichao2018/Platelet‐Related‐Subtypes‐Mining‐for‐NSCLC).", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "All data from study are included in this manuscript. Some of the code has been uploaded to GitHub (https://github.com/Huaichao2018/Platelet‐Related‐Subtypes‐Mining‐for‐NSCLC).", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM3995402", "GSM3995403", "GSM3995404", "GSM3995405", "GSM3995406", "GSM3995407", "GSM3995408", "GSM3995409", "GSM3995410", "GSM3995411", "GSM3995412", "GSM3995413", "GSM3995414", "GSM3995415", "GSM3995416", "GSM3995417", "GSM3995418", "GSM3995419", "GSM3995420", "GSM3995421", "GSM3995422", "GSM3995423", "GSM3995424", "GSM3995425", "GSM3995426", "GSM3995427", "GSM3995428"], "sample_count": 27, "group_sizes": null, "group_sizes_basis": null, "platform": "16791", "taxon": "Homo sapiens", "title": "DNA methylation loss coupled with mitotic cell division promotes immune evasion of tumours with high mutation load [RNA-seq]", "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:GSE30129", "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=GSE30129", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE30129", "version": null, "note": "All data from study are included in this manuscript. Some of the code has been uploaded to GitHub (https://github.com/Huaichao2018/Platelet‐Related‐Subtypes‐Mining‐for‐NSCLC).", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "All data from study are included in this manuscript. Some of the code has been uploaded to GitHub (https://github.com/Huaichao2018/Platelet‐Related‐Subtypes‐Mining‐for‐NSCLC).", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM745922", "GSM745923", "GSM745924", "GSM745925", "GSM745926", "GSM745927", "GSM745928", "GSM745929", "GSM745930", "GSM745931", "GSM745932", "GSM745933"], "sample_count": 12, "group_sizes": null, "group_sizes_basis": null, "platform": "6246", "taxon": "Mus musculus", "title": "AIRE-deficient CD8+CD28low regulatory T lymphocytes fail to control experimental colitis", "resolution_checked_at": "2026-11-01T19:09:46Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:GSE37745", "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=GSE37745", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE37745", "version": null, "note": "All data from study are included in this manuscript. Some of the code has been uploaded to GitHub (https://github.com/Huaichao2018/Platelet‐Related‐Subtypes‐Mining‐for‐NSCLC).", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "All data from study are included in this manuscript. Some of the code has been uploaded to GitHub (https://github.com/Huaichao2018/Platelet‐Related‐Subtypes‐Mining‐for‐NSCLC).", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM1019138", "GSM1019139", "GSM1019140", "GSM1019141", "GSM1019142", "GSM1019143", "GSM1019144", "GSM1019145", "GSM1019146", "GSM1019147", "GSM1019148", "GSM1019149", "GSM1019150", "GSM1019151", "GSM1019152", "GSM1019153", "GSM1019154", "GSM1019155", "GSM1019156", "GSM1019157", "GSM1019158", "GSM1019159", "GSM1019160", "GSM1019161", "GSM1019162", "GSM1019163", "GSM1019164", "GSM1019165", "GSM1019166", "GSM1019167", "GSM1019168", "GSM1019169", "GSM1019170", "GSM1019171", "GSM1019172", "GSM1019173", "GSM1019174", "GSM1019175", "GSM1019176", "GSM1019177", "GSM1019178", "GSM1019179", "GSM1019180", "GSM1019181", "GSM1019182", "GSM1019183", "GSM1019184", "GSM1019185", "GSM1019186", "GSM1019187", "GSM1019188", "GSM1019189", "GSM1019190", "GSM1019191", "GSM1019192", "GSM1019193", "GSM1019194", "GSM1019195", "GSM1019196", "GSM1019197", "GSM1019198", "GSM1019199", "GSM1019200", "GSM1019201", "GSM1019202", "GSM1019203", "GSM1019204", "GSM1019205", "GSM1019206", "GSM1019207", "GSM1019208", "GSM1019209", "GSM1019210", "GSM1019211", "GSM1019212", "GSM1019213", "GSM1019214", "GSM1019215", "GSM1019216", "GSM1019217", "GSM1019218", "GSM1019219", "GSM1019220", "GSM1019221", "GSM1019222", "GSM1019223", "GSM1019224", "GSM1019225", "GSM1019226", "GSM1019227", "GSM1019228", "GSM1019229", "GSM1019230", "GSM1019231", "GSM1019232", "GSM1019233", "GSM1019234", "GSM1019235", "GSM1019236", "GSM1019237", "GSM1019238", "GSM1019239", "GSM1019240", "GSM1019241", "GSM1019242", "GSM1019243", "GSM1019244", "GSM1019245", "GSM1019246", "GSM1019247", "GSM1019248", "GSM1019249", "GSM1019250", "GSM1019251", "GSM1019252", "GSM1019253", "GSM1019254", "GSM1019255", "GSM1019256", "GSM1019257", "GSM1019258", "GSM1019259", "GSM1019260", "GSM1019261", "GSM1019262", "GSM1019263", "GSM1019264", "GSM1019265", "GSM1019266", "GSM1019267", "GSM1019268", "GSM1019269", "GSM1019270", "GSM1019271", "GSM1019272", "GSM1019273", "GSM1019274", "GSM1019275", "GSM1019276", "GSM1019277", "GSM1019278", "GSM1019279", "GSM1019280", "GSM1019281", "GSM1019282", "GSM1019283", "GSM1019284", "GSM1019285", "GSM1019286", "GSM1019287", "GSM1019288", "GSM1019289", "GSM1019290", "GSM1019291", "GSM1019292", "GSM1019293", "GSM1019294", "GSM1019295", "GSM1019296", "GSM1019297", "GSM1019298", "GSM1019299", "GSM1019300", "GSM1019301", "GSM1019302", "GSM1019303", "GSM1019304", "GSM1019305", "GSM1019306", "GSM1019307", "GSM1019308", "GSM1019309", "GSM1019310", "GSM1019311", "GSM1019312", "GSM1019313", "GSM1019314", "GSM1019315", "GSM1019316", "GSM1019317", "GSM1019318", "GSM1019319", "GSM1019320", "GSM1019321", "GSM1019322", "GSM1019323", "GSM1019324", "GSM1019325", "GSM1019326", "GSM1019327", "GSM1019328", "GSM1019329", "GSM1019330", "GSM1019331", "GSM1019332", "GSM1019333"], "sample_count": 196, "group_sizes": null, "group_sizes_basis": null, "platform": "570", "taxon": "Homo sapiens", "title": "Biomarker discovery in non-small cell lung cancer: integrating gene expression profiling, meta-analysis and tissue microarray validation", "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:GSE42127", "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=GSE42127", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE42127", "version": null, "note": "All data from study are included in this manuscript. Some of the code has been uploaded to GitHub (https://github.com/Huaichao2018/Platelet‐Related‐Subtypes‐Mining‐for‐NSCLC).", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "All data from study are included in this manuscript. Some of the code has been uploaded to GitHub (https://github.com/Huaichao2018/Platelet‐Related‐Subtypes‐Mining‐for‐NSCLC).", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM1032881", "GSM1032882", "GSM1032883", "GSM1032884", "GSM1032885", "GSM1032886", "GSM1032887", "GSM1032888", "GSM1032889", "GSM1032890", "GSM1032891", "GSM1032892", "GSM1032893", "GSM1032894", "GSM1032895", "GSM1032896", "GSM1032897", "GSM1032898", "GSM1032899", "GSM1032900", "GSM1032901", "GSM1032902", "GSM1032903", "GSM1032904", "GSM1032905", "GSM1032906", "GSM1032907", "GSM1032908", "GSM1032909", "GSM1032910", "GSM1032911", "GSM1032912", "GSM1032913", "GSM1032914", "GSM1032915", "GSM1032916", "GSM1032917", "GSM1032918", "GSM1032919", "GSM1032920", "GSM1032921", "GSM1032922", "GSM1032923", "GSM1032924", "GSM1032925", "GSM1032926", "GSM1032927", "GSM1032928", "GSM1032929", "GSM1032930", "GSM1032931", "GSM1032932", "GSM1032933", "GSM1032934", "GSM1032935", "GSM1032936", "GSM1032937", "GSM1032938", "GSM1032939", "GSM1032940", "GSM1032941", "GSM1032942", "GSM1032943", "GSM1032944", "GSM1032945", "GSM1032946", "GSM1032947", "GSM1032948", "GSM1032949", "GSM1032950", "GSM1032951", "GSM1032952", "GSM1032953", "GSM1032954", "GSM1032955", "GSM1032956", "GSM1032957", "GSM1032958", "GSM1032959", "GSM1032960", "GSM1032961", "GSM1032962", "GSM1032963", "GSM1032964", "GSM1032965", "GSM1032966", "GSM1032967", "GSM1032968", "GSM1032969", "GSM1032970", "GSM1032971", "GSM1032972", "GSM1032973", "GSM1032974", "GSM1032975", "GSM1032976", "GSM1032977", "GSM1032978", "GSM1032979", "GSM1032980", "GSM1032981", "GSM1032982", "GSM1032983", "GSM1032984", "GSM1032985", "GSM1032986", "GSM1032987", "GSM1032988", "GSM1032989", "GSM1032990", "GSM1032991", "GSM1032992", "GSM1032993", "GSM1032994", "GSM1032995", "GSM1032996", "GSM1032997", "GSM1032998", "GSM1032999", "GSM1033000", "GSM1033001", "GSM1033002", "GSM1033003", "GSM1033004", "GSM1033005", "GSM1033006", "GSM1033007", "GSM1033008", "GSM1033009", "GSM1033010", "GSM1033011", "GSM1033012", "GSM1033013", "GSM1033014", "GSM1033015", "GSM1033016", "GSM1033017", "GSM1033018", "GSM1033019", "GSM1033020", "GSM1033021", "GSM1033022", "GSM1033023", "GSM1033024", "GSM1033025", "GSM1033026", "GSM1033027", "GSM1033028", "GSM1033029", "GSM1033030", "GSM1033031", "GSM1033032", "GSM1033033", "GSM1033034", "GSM1033035", "GSM1033036", "GSM1033037", "GSM1033038", "GSM1033039", "GSM1033040", "GSM1033041", "GSM1033042", "GSM1033043", "GSM1033044", "GSM1033045", "GSM1033046", "GSM1033047", "GSM1033048", "GSM1033049", "GSM1033050", "GSM1033051", "GSM1033052", "GSM1033053", "GSM1033054", "GSM1033055", "GSM1033056"], "sample_count": 176, "group_sizes": null, "group_sizes_basis": null, "platform": "6884", "taxon": "Homo sapiens", "title": "Expression data for 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:GSE50081", "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=GSE50081", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE50081", "version": null, "note": "All data from study are included in this manuscript. Some of the code has been uploaded to GitHub (https://github.com/Huaichao2018/Platelet‐Related‐Subtypes‐Mining‐for‐NSCLC).", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "All data from study are included in this manuscript. Some of the code has been uploaded to GitHub (https://github.com/Huaichao2018/Platelet‐Related‐Subtypes‐Mining‐for‐NSCLC).", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM1213669", "GSM1213670", "GSM1213671", "GSM1213672", "GSM1213673", "GSM1213674", "GSM1213675", "GSM1213676", "GSM1213677", "GSM1213678", "GSM1213679", "GSM1213680", "GSM1213681", "GSM1213682", "GSM1213683", "GSM1213684", "GSM1213685", "GSM1213686", "GSM1213687", "GSM1213688", "GSM1213689", "GSM1213690", "GSM1213691", "GSM1213692", "GSM1213693", "GSM1213694", "GSM1213695", "GSM1213696", "GSM1213697", "GSM1213698", "GSM1213699", "GSM1213700", "GSM1213701", "GSM1213702", "GSM1213703", "GSM1213704", "GSM1213705", "GSM1213706", "GSM1213707", "GSM1213708", "GSM1213709", "GSM1213710", "GSM1213711", "GSM1213712", "GSM1213713", "GSM1213714", "GSM1213715", "GSM1213716", "GSM1213717", "GSM1213718", "GSM1213719", "GSM1213720", "GSM1213721", "GSM1213722", "GSM1213723", "GSM1213724", "GSM1213725", "GSM1213726", "GSM1213727", "GSM1213728", "GSM1213729", "GSM1213730", "GSM1213731", "GSM1213732", "GSM1213733", "GSM1213734", "GSM1213735", "GSM1213736", "GSM1213737", "GSM1213738", "GSM1213739", "GSM1213740", "GSM1213741", "GSM1213742", "GSM1213743", "GSM1213744", "GSM1213745", "GSM1213746", "GSM1213747", "GSM1213748", "GSM1213749", "GSM1213750", "GSM1213751", "GSM1213752", "GSM1213753", "GSM1213754", "GSM1213755", "GSM1213756", "GSM1213757", "GSM1213758", "GSM1213759", "GSM1213760", "GSM1213761", "GSM1213762", "GSM1213763", "GSM1213764", "GSM1213765", "GSM1213766", "GSM1213767", "GSM1213768", "GSM1213769", "GSM1213770", "GSM1213771", "GSM1213772", "GSM1213773", "GSM1213774", "GSM1213775", "GSM1213776", "GSM1213777", "GSM1213778", "GSM1213779", "GSM1213780", "GSM1213781", "GSM1213782", "GSM1213783", "GSM1213784", "GSM1213785", "GSM1213786", "GSM1213787", "GSM1213788", "GSM1213789", "GSM1213790", "GSM1213791", "GSM1213792", "GSM1213793", "GSM1213794", "GSM1213795", "GSM1213796", "GSM1213797", "GSM1213798", "GSM1213799", "GSM1213800", "GSM1213801", "GSM1213802", "GSM1213803", "GSM1213804", "GSM1213805", "GSM1213806", "GSM1213807", "GSM1213808", "GSM1213809", "GSM1213810", "GSM1213811", "GSM1213812", "GSM1213813", "GSM1213814", "GSM1213815", "GSM1213816", "GSM1213817", "GSM1213818", "GSM1213819", "GSM1213820", "GSM1213821", "GSM1213822", "GSM1213823", "GSM1213824", "GSM1213825", "GSM1213826", "GSM1213827", "GSM1213828", "GSM1213829", "GSM1213830", "GSM1213831", "GSM1213832", "GSM1213833", "GSM1213834", "GSM1213835", "GSM1213836", "GSM1213837", "GSM1213838", "GSM1213839", "GSM1213840", "GSM1213841", "GSM1213842", "GSM1213843", "GSM1213844", "GSM1213845", "GSM1213846", "GSM1213847", "GSM1213848", "GSM1213849"], "sample_count": 181, "group_sizes": null, "group_sizes_basis": null, "platform": "570", "taxon": "Homo sapiens", "title": "Validation of a histology-independent prognostic gene signature for early stage, non-small cell lung cancer including stage IA patients", "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:GSE89843", "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=GSE89843", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE89843", "version": null, "note": "All data from study are included in this manuscript. Some of the code has been uploaded to GitHub (https://github.com/Huaichao2018/Platelet‐Related‐Subtypes‐Mining‐for‐NSCLC).", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "All data from study are included in this manuscript. Some of the code has been uploaded to GitHub (https://github.com/Huaichao2018/Platelet‐Related‐Subtypes‐Mining‐for‐NSCLC).", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM2390709", "GSM2390710", "GSM2390711", "GSM2390712", "GSM2390713", "GSM2390714", "GSM2390715", "GSM2390716", "GSM2390717", "GSM2390718", "GSM2390719", "GSM2390720", "GSM2390721", "GSM2390722", "GSM2390723", "GSM2390724", "GSM2390725", "GSM2390726", "GSM2390727", "GSM2390728", "GSM2390729", "GSM2390730", "GSM2390731", "GSM2390732", "GSM2390733", "GSM2390734", "GSM2390735", "GSM2390736", "GSM2390737", "GSM2390738", "GSM2390739", "GSM2390740", "GSM2390741", "GSM2390742", "GSM2390744", "GSM2390745", "GSM2390746", "GSM2390747", "GSM2390748", "GSM2390749", "GSM2390750", "GSM2390751", "GSM2390752", "GSM2390753", "GSM2390754", "GSM2390755", "GSM2390756", "GSM2390757", "GSM2390758", "GSM2390759", "GSM2390760", "GSM2390761", "GSM2390762", "GSM2390763", "GSM2390764", "GSM2390765", "GSM2390766", "GSM2390767", "GSM2390768", "GSM2390769", "GSM2390770", "GSM2390771", "GSM2390772", "GSM2390773", "GSM2390774", "GSM2390775", "GSM2390776", "GSM2390777", "GSM2390778", "GSM2390779", "GSM2390780", "GSM2390781", "GSM2390782", "GSM2390783", "GSM2390784", "GSM2390785", "GSM2390786", "GSM2390787", "GSM2390788", "GSM2390789", "GSM2390790", "GSM2390791", "GSM2390792", "GSM2390793", "GSM2390794", "GSM2390795", "GSM2390796", "GSM2390797", "GSM2390798", "GSM2390799", "GSM2390800", "GSM2390801", "GSM2390802", "GSM2390803", "GSM2390804", "GSM2390805", "GSM2390806", "GSM2390807", "GSM2390808", "GSM2390809", "GSM2390810", "GSM2390811", "GSM2390812", "GSM2390813", "GSM2390814", "GSM2390815", "GSM2390816", "GSM2390817", "GSM2390818", "GSM2390819", "GSM2390820", "GSM2390821", "GSM2390822", "GSM2390823", "GSM2390824", "GSM2390825", "GSM2390826", "GSM2390827", "GSM2390828", "GSM2390829", "GSM2390830", "GSM2390831", "GSM2390832", "GSM2390833", "GSM2390834", "GSM2390835", "GSM2390836", "GSM2390837", "GSM2390838", "GSM2390839", "GSM2390840", "GSM2390841", "GSM2390842", "GSM2390843", "GSM2390844", "GSM2390845", "GSM2390846", "GSM2390847", "GSM2390848", "GSM2390849", "GSM2390850", "GSM2390851", "GSM2390852", "GSM2390853", "GSM2390854", "GSM2390855", "GSM2390856", "GSM2390857", "GSM2390858", "GSM2390859", "GSM2390860", "GSM2390861", "GSM2390862", "GSM2390863", "GSM2390864", "GSM2390865", "GSM2390866", "GSM2390867", "GSM2390868", "GSM2390869", "GSM2390870", "GSM2390871", "GSM2390872", "GSM2390873", "GSM2390874", "GSM2390875", "GSM2390876", "GSM2390877", "GSM2390878", "GSM2390879", "GSM2390880", "GSM2390881", "GSM2390882", "GSM2390883", "GSM2390884", "GSM2390885", "GSM2390886", "GSM2390887", "GSM2390888", "GSM2390889", "GSM2390890", "GSM2390891", "GSM2390892", "GSM2390893", "GSM2390894", "GSM2390895", "GSM2390896", "GSM2390897", "GSM2390898", "GSM2390899", "GSM2390900", "GSM2390901", "GSM2390902", "GSM2390903", "GSM2390904", "GSM2390905", "GSM2390906", "GSM2390907", "GSM2390908", "GSM2390909", "GSM2390910", "GSM2390911", "GSM2390912", "GSM2390913", "GSM2390914", "GSM2390915", "GSM2390916", "GSM2390917", "GSM2390918", "GSM2390919", "GSM2390920", "GSM2390921", "GSM2390922", "GSM2390923", "GSM2390924", "GSM2390925", "GSM2390926", "GSM2390927", "GSM2390928", "GSM2390929", "GSM2390930", "GSM2390931", "GSM2390932", "GSM2390933", "GSM2390934", "GSM2390935", "GSM2390936", "GSM2390937", "GSM2390938", "GSM2390939", "GSM2390940", "GSM2390941", "GSM2390942", "GSM2390943", "GSM2390944", "GSM2390945", "GSM2390946", "GSM2390947", "GSM2390948", "GSM2390949", "GSM2390950", "GSM2390951", "GSM2390952", "GSM2390953", "GSM2390954", "GSM2390955", "GSM2390956", "GSM2390957", "GSM2390958", "GSM2390959", "GSM2390960", "GSM2390961", "GSM2390962", "GSM2390963", "GSM2390964", "GSM2390965", "GSM2390966", "GSM2390967", "GSM2390968", "GSM2390969", "GSM2390970", "GSM2390971", "GSM2390972", "GSM2390973", "GSM2390974", "GSM2390975", "GSM2390976", "GSM2390977", "GSM2390978", "GSM2390979", "GSM2390980", "GSM2390981", "GSM2390982", "GSM2390983", "GSM2390984", "GSM2390985", "GSM2390986", "GSM2390987", "GSM2390988", "GSM2390989", "GSM2390990", "GSM2390991", "GSM2390992", "GSM2390993", "GSM2390994", "GSM2390995", "GSM2390996", "GSM2390997", "GSM2390998", "GSM2390999", "GSM2391000", "GSM2391001", "GSM2391002", "GSM2391003", "GSM2391004", "GSM2391005", "GSM2391006", "GSM2391007", "GSM2391008", "GSM2391009", "GSM2391010", "GSM2391011", "GSM2391012", "GSM2391013", "GSM2391014", "GSM2391015", "GSM2391016", "GSM2391017", "GSM2391018", "GSM2391019", "GSM2391020", "GSM2391021", "GSM2391022", "GSM2391023", "GSM2391024", "GSM2391025", "GSM2391026", "GSM2391027", "GSM2391028", "GSM2391029", "GSM2391030", "GSM2391031", "GSM2391032", "GSM2391033", "GSM2391034", "GSM2391035", "GSM2391036", "GSM2391037", "GSM2391038", "GSM2391039", "GSM2391040", "GSM2391041", "GSM2391042", "GSM2391043", "GSM2391044", "GSM2391045", "GSM2391046", "GSM2391047", "GSM2391048", "GSM2391049", "GSM2391050", "GSM2391051", "GSM2391052", "GSM2391053", "GSM2391054", "GSM2391055", "GSM2391056", "GSM2391057", "GSM2391058", "GSM2391059", "GSM2391060", "GSM2391061", "GSM2391062", "GSM2391063", "GSM2391064", "GSM2391065", "GSM2391066", "GSM2391067", "GSM2391068", "GSM2391069", "GSM2391070", "GSM2391071", "GSM2391072", "GSM2391073", "GSM2391074", "GSM2391075", "GSM2391076", "GSM2391077", "GSM2391078", "GSM2391079", "GSM2391080", "GSM2391081", "GSM2391082", "GSM2391083", "GSM2391084", "GSM2391085", "GSM2391086", "GSM2391087", "GSM2391088", "GSM2391089", "GSM2391090", "GSM2391091", "GSM2391092", "GSM2391093", "GSM2391094", "GSM2391095", "GSM2391096", "GSM2391097", "GSM2391098", "GSM2391099", "GSM2391100", "GSM2391101", "GSM2391102", "GSM2391103", "GSM2391104", "GSM2391105", "GSM2391106", "GSM2391107", "GSM2391108", "GSM2391109", "GSM2391110", "GSM2391111", "GSM2391112", "GSM2391113", "GSM2391114", "GSM2391115", "GSM2391116", "GSM2391117", "GSM2391118", "GSM2391119", "GSM2391120", "GSM2391121", "GSM2391122", "GSM2391123", "GSM2391124", "GSM2391125", "GSM2391126", "GSM2391127", "GSM2391128", "GSM2391129", "GSM2391130", "GSM2391131", "GSM2391132", "GSM2391133", "GSM2391134", "GSM2391135", "GSM2391136", "GSM2391137", "GSM2391138", "GSM2391139", "GSM2391140", "GSM2391141", "GSM2391142", "GSM2391143", "GSM2391144", "GSM2391145", "GSM2391146", "GSM2391147", "GSM2391148", "GSM2391149", "GSM2391150", "GSM2391151", "GSM2391152", "GSM2391153", "GSM2391154", "GSM2391155", "GSM2391156", "GSM2391157", "GSM2391158", "GSM2391159", "GSM2391160", "GSM2391161", "GSM2391162", "GSM2391163", "GSM2391164", "GSM2391165", "GSM2391166", "GSM2391167", "GSM2391168", "GSM2391169", "GSM2391170", "GSM2391171", "GSM2391172", "GSM2391173", "GSM2391174", "GSM2391175", "GSM2391176", "GSM2391177", "GSM2391178", "GSM2391179", "GSM2391180", "GSM2391181", "GSM2391182", "GSM2391183", "GSM2391184", "GSM2391185", "GSM2391186", "GSM2391187", "GSM2391188", "GSM2391189", "GSM2391190", "GSM2391191", "GSM2391192", "GSM2391193", "GSM2391194", "GSM2391195", "GSM2391196", "GSM2391197", "GSM2391198", "GSM2391199", "GSM2391200", "GSM2391201", "GSM2391202", "GSM2391203", "GSM2391204", "GSM2391205", "GSM2391206", "GSM2391207", "GSM2391208", "GSM2391209", "GSM2391210", "GSM2391211", "GSM2391212", "GSM2391213", "GSM2391214", "GSM2391215", "GSM2391216", "GSM2391217", "GSM2391218", "GSM2391219", "GSM2391220", "GSM2391221", "GSM2391222", "GSM2391223", "GSM2391224", "GSM2391225", "GSM2391226", "GSM2391227", "GSM2391228", "GSM2391229", "GSM2391230", "GSM2391231", "GSM2391232", "GSM2391233", "GSM2391234", "GSM2391235", "GSM2391236", "GSM2391237", "GSM2391238", "GSM2391239", "GSM2391240", "GSM2391241", "GSM2391242", "GSM2391243", "GSM2391244", "GSM2391245", "GSM2391246", "GSM2391247", "GSM2391248", "GSM2391249", "GSM2391250", "GSM2391251", "GSM2391252", "GSM2391253", "GSM2391254", "GSM2391255", "GSM2391256", "GSM2391257", "GSM2391258", "GSM2391259", "GSM2391260", "GSM2391261", "GSM2391262", "GSM2391263", "GSM2391264", "GSM2391265", "GSM2391266", "GSM2391267", "GSM2391268", "GSM2391269", "GSM2391270", "GSM2391271", "GSM2391272", "GSM2391273", "GSM2391274", "GSM2391275", "GSM2391276", "GSM2391277", "GSM2391278", "GSM2391279", "GSM2391280", "GSM2391281", "GSM2391282", "GSM2391283", "GSM2391284", "GSM2391285", "GSM2391286", "GSM2391287", "GSM2391288", "GSM2391289", "GSM2391290", "GSM2391291", "GSM2391292", "GSM2391293", "GSM2391294", "GSM2391295", "GSM2391296", "GSM2391297", "GSM2391298", "GSM2391299", "GSM2391300", "GSM2391301", "GSM2391302", "GSM2391303", "GSM2391304", "GSM2391305", "GSM2391306", "GSM2391307", "GSM2391308", "GSM2391309", "GSM2391310", "GSM2391311", "GSM2391312", "GSM2391313", "GSM2391314", "GSM2391315", "GSM2391316", "GSM2391317", "GSM2391318", "GSM2391319", "GSM2391320", "GSM2391321", "GSM2391322", "GSM2391323", "GSM2391324", "GSM2391325", "GSM2391326", "GSM2391327", "GSM2391328", "GSM2391329", "GSM2391330", "GSM2391331", "GSM2391332", "GSM2391333", "GSM2391334", "GSM2391335", "GSM2391336", "GSM2391337", "GSM2391338", "GSM2391339", "GSM2391340", "GSM2391341", "GSM2391342", "GSM2391343", "GSM2391344", "GSM2391345", "GSM2391346", "GSM2391347", "GSM2391348", "GSM2391349", "GSM2391350", "GSM2391351", "GSM2391352", "GSM2391353", "GSM2391354", "GSM2391355", "GSM2391356", "GSM2391357", "GSM2391358", "GSM2391359", "GSM2391360", "GSM2391361", "GSM2391362", "GSM2391363", "GSM2391364", "GSM2391365", "GSM2391366", "GSM2391367", "GSM2391368", "GSM2391369", "GSM2391370", "GSM2391371", "GSM2391372", "GSM2391373", "GSM2391374", "GSM2391375", "GSM2391376", "GSM2391377", "GSM2391378", "GSM2391379", "GSM2391380", "GSM2391381", "GSM2391382", "GSM2391383", "GSM2391384", "GSM2391385", "GSM2391386", "GSM2391387", "GSM2391388", "GSM2391389", "GSM2391390", "GSM2391391", "GSM2391392", "GSM2391393", "GSM2391394", "GSM2391395", "GSM2391396", "GSM2391397", "GSM2391398", "GSM2391399", "GSM2391400", "GSM2391401", "GSM2391402", "GSM2391403", "GSM2391404", "GSM2391405", "GSM2391406", "GSM2391407", "GSM2391408", "GSM2391409", "GSM2391410", "GSM2391411", "GSM2391412", "GSM2391413", "GSM2391414", "GSM2391415", "GSM2391416", "GSM2391417", "GSM2391418", "GSM2391419", "GSM2391420", "GSM2391421", "GSM2391422", "GSM2391423", "GSM2391424", "GSM2391425", "GSM2391426", "GSM2391427", "GSM2391428", "GSM2391429", "GSM2402608", "GSM2402609", "GSM2402610", "GSM2627390", "GSM2627391", "GSM2627392", "GSM2627393", "GSM2627394", "GSM2627395", "GSM2627396", "GSM2627397", "GSM2627398", "GSM2627399", "GSM2627400", "GSM2627401", "GSM2627402", "GSM2627403", "GSM2627404", "GSM2627405", "GSM2627406", "GSM2627407", "GSM2627408", "GSM2627409", "GSM2627410", "GSM2627411", "GSM2627412", "GSM2627413", "GSM2627414", "GSM2627415", "GSM2627416", "GSM2627417", "GSM2627418", "GSM2627419", "GSM2627420", "GSM2627421", "GSM2627422", "GSM2627423", "GSM2627424", "GSM2627425", "GSM2627426", "GSM2627427", "GSM2627428", "GSM2627429", "GSM2627430", "GSM2627431", "GSM2627432", "GSM2627433", "GSM2627434", "GSM2627435", "GSM2627436", "GSM2627437", "GSM2627438", "GSM2627439", "GSM2627440", "GSM2627441", "GSM2627442", "GSM2627443", "GSM2627444", "GSM2627445"], "sample_count": 779, "group_sizes": null, "group_sizes_basis": null, "platform": "16791", "taxon": "Homo sapiens", "title": "Swarm intelligence-enhanced detection of non-small cell lung cancer using tumor-educated platelets", "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:GSE13213 not downloaded", "asset:data:geo:GSE13213 licence not read", "asset:data:geo:GSE135222 not downloaded", "asset:data:geo:GSE135222 licence not read", "asset:data:geo:GSE30129 not downloaded", "asset:data:geo:GSE30129 licence not read", "asset:data:geo:GSE37745 not downloaded", "asset:data:geo:GSE37745 licence not read", "asset:data:geo:GSE42127 not downloaded", "asset:data:geo:GSE42127 licence not read", "asset:data:geo:GSE50081 not downloaded", "asset:data:geo:GSE50081 licence not read", "asset:data:geo:GSE89843 not downloaded", "asset:data:geo:GSE89843 licence not read"]}, "analysis": {"state": "partial", "methods": [{"id": "method-1", "family": "survival_analysis", "specific": "log_rank_test", "label": "Survival analysis", "dsl_operations": ["logrank_test"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["time_to_event_with_censoring"], "evidence": {"score": 1.0, "band": "verbatim", "quote": "Survival analysis curves were plotted with Kaplan–Meier, and log‐rank tests were applied to compare OS differences between groups."}}, {"id": "method-2", "family": "group_comparison", "specific": "wilcoxon", "label": "Group comparison", "dsl_operations": [], "missing_operations": ["group_comparison_wilcoxon"], "expressible": false, "parameters": {}, "data_shapes": ["two_or_more_groups_continuous"], "evidence": {"score": 0.8, "band": "high", "quote": "Wilcoxon"}}, {"id": "method-3", "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": 0.8, "band": "high", "quote": "KM"}}, {"id": "method-4", "family": "survival_analysis", "specific": "cox_proportional_hazards", "label": "Survival analysis", "dsl_operations": ["cox_ph"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["time_to_event_with_censoring"], "evidence": {"score": 0.7, "band": "medium", "quote": "COX regression"}}, {"id": "method-5", "family": "differential_expression", "specific": "limma_voom", "label": "Differential expression analysis", "dsl_operations": ["normalise_counts", "differential_expression_fit", "fdr_bh"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["count_matrix_with_condition"], "evidence": {"score": 0.7, "band": "medium", "quote": "Limma"}}, {"id": "method-6", "family": "machine_learning", "specific": "random_forest", "label": "Machine learning", "dsl_operations": [], "missing_operations": ["machine_learning_random_forest"], "expressible": false, "parameters": {}, "data_shapes": ["labelled_feature_matrix"], "evidence": {"score": 0.7, "band": "medium", "quote": "Random Forest"}}], "targets": [], "gaps": ["method.reader_differs_from_extractor"]}, "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": ["logrank_test"], "missing_operations": [], "basis": "The paper names the method it used and the corpus's method extractor maps it onto the DSL catalogue: log_rank_test."}, "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": ["GSE89843", "GSE37745", "GSE50081", "GSE13213", "GSE30129", "GSE42127", "GSE135222"], "resolved_accessions": ["GSE89843", "GSE37745", "GSE50081", "GSE13213", "GSE30129", "GSE42127", "GSE135222"], "statements": ["All data from study are included in this manuscript. Some of the code has been uploaded to GitHub (https://github.com/Huaichao2018/Platelet‐Related‐Subtypes‐Mining‐for‐NSCLC)."], "basis": "The paper names GSE89843, GSE37745, GSE50081, GSE13213, GSE30129, GSE42127, GSE135222 in GEO and the accession resolves in the repository. No dataset was downloaded and no licence was read."}}, "can_run": {"dsl_operations": ["logrank_test"], "assets": ["source:pmid:39708330", "data:geo:GSE13213"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE13213"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-11-01T19:43:01Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 5, "usage": {"prompt_tokens": 14021, "completion_tokens": 2810, "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:39708330", "type": "paper", "label": "pmid:39708330"}, {"id": "source:pmid:39708330", "type": "manuscript", "label": "PMID 39708330 full text"}, {"id": "data:geo:GSE13213", "type": "dataset", "label": "GEO GSE13213"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:39708330", "type": "paper", "label": "pmid:39708330"}, {"id": "source:pmid:39708330", "type": "manuscript", "label": "PMID 39708330 full text"}, {"id": "data:geo:GSE13213", "type": "dataset", "label": "GEO GSE13213"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-39708330", "type": "extraction", "used": ["source:pmid:39708330"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE13213", "type": "accession_resolution", "used": ["data:geo:GSE13213"], "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:39708330", "parent_hash": "sha256:663b52c406117df5890009a98a225cf00a48a43fb3707eb0e3ca95febb171a8f", "fork_of": null, "generation": 2}, "gaps": ["asset:data:geo:GSE13213 licence not read", "asset:data:geo:GSE13213 not downloaded", "asset:data:geo:GSE135222 licence not read", "asset:data:geo:GSE135222 not downloaded", "asset:data:geo:GSE30129 licence not read", "asset:data:geo:GSE30129 not downloaded", "asset:data:geo:GSE37745 licence not read", "asset:data:geo:GSE37745 not downloaded", "asset:data:geo:GSE42127 licence not read", "asset:data:geo:GSE42127 not downloaded", "asset:data:geo:GSE50081 licence not read", "asset:data:geo:GSE50081 not downloaded", "asset:data:geo:GSE89843 licence not read", "asset:data:geo:GSE89843 not downloaded", "execution.not_run", "method.reader_differs_from_extractor", "review.human_critique", "review.independent_reader", "review.machine_critique"], "assays": [{"role": "data_generation", "definition_id": "flow_cytometry", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.99, "evidence": ["LASSO-COX. BEST3 expression was validated by flow cytometry (FCM) and functional assays in A549 cells wi", "highly expressed in the platelet subtype 1. Flow cytometry confirmed elevated BEST3 levels in NSCLC (35"], "order_basis": "paper_text_order:860", "id": "assay:1"}, {"role": "data_generation", "definition_id": "cell_culture", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.99, "evidence": ["low cytometry (FCM) and functional assays in A549 cells with lentiviral overexpression evaluat", "rmo Fisher Scientific). Cells were routinely cultured in DMEM (Gibco, #C11995500BT) or 1640 medium (V", "Materials and Methods Cell Culture A549 cells were maintained at 37°C in a 5% CO₂ in"], "order_basis": "paper_text_order:906", "id": "assay:2"}, {"role": "data_generation", "definition_id": "apoptosis_assay", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.93, "evidence": ["viral overexpression evaluated its impact on apoptosis, proliferation and migration. Three platelet", "xpression of BEST3 in NSCLC cells suppressed apoptosis and promoted proliferation and migration. Th"], "order_basis": "paper_text_order:972", "id": "assay:3"}, {"role": "analysis", "definition_id": "survival_analysis", "definition_version": "f2132e96ae6c7a4e", "definition_digest": null, "required_operations": ["logrank_test"], "support_state": "supported", "source_hashes": {"dsl_catalogue": "f2132e96ae6c7a4e"}, "confidence": 1.0, "evidence": ["Survival analysis curves were plotted with Kaplan–Meier, and log‐rank tests were applied to compare OS differences between groups."], "order_basis": "consumes_earlier_output", "id": "assay:4"}]},"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":"2026-11-04T01:47:18+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}}}