{"data":{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:34307909", "kind": "science-record", "revision": 8, "content_hash": "sha256:ef222e55cb3c07d411ff5ed2a6bf44f7c8dd6411b27f08e6a4b4d8aa0c6705fd", "created_at": "2026-11-01T15:41:45Z", "updated_at": "2026-11-01T22:04:18Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Analysis of SARS-CoV-2 infection associated cell entry proteins ACE2, CD147, PPIA, and PPIB in datasets from non SARS-CoV-2 infected neuroblastoma patients, as potential prognostic and infection biomarkers in neuroblastoma.", "doi": "10.1016/j.bbrep.2021.101081", "pmid": "34307909", "authors": ["Brandon Bergsneider", "Elise Bailey", "Yusuf Ahmed", "Namrata Gogineni", "Derek Huntley", "Ximena Montano"], "journal": "Biochemistry and biophysics reports", "year": 2021, "abstract": "SARS-CoV-2 viral contagion has given rise to a worldwide pandemic. Although most children experience minor symptoms from SARS-CoV-2 infection, some have severe complications including Multisystem Inflammatory Syndrome in Children. Neuroblastoma patients may be at higher risk of severe infection as treatment requires immunocompromising chemotherapy and SARS-CoV-2 has demonstrated tropism for nervous cells. To date, there is no sufficient epidemiological data on neuroblastoma patients with SARS-CoV-2. Therefore, we evaluated datasets of non-SARS-CoV-2 infected neuroblastoma patients to assess for key genes involved with SARS-CoV-2 infection as possible neuroblastoma prognostic and infection biomarkers. We hypothesized that ACE2, CD147, PPIA and PPIB, which are associated with viral-cell entry, are potential biomarkers for poor prognosis neuroblastoma and SARS-CoV-2 infection. We have analysed three publicly available neuroblastoma gene expression datasets to understand the specific molecular susceptibilities that high-risk neuroblastoma patients have to the virus. Gene Expression Omnibus (GEO) GSE49711 and GEO GSE62564 are the microarray and RNA-Seq data, respectively, from 498 neuroblastoma samples published as part of the Sequencing Quality Control initiative. TARGET, contains microarray data from 249 samples and is part of the Therapeutically Applicable Research to Generate Effective Treatments (TARGET) initiative. ACE2, CD147, PPIA and PPIB were identified through their involvement in both SARS-CoV-2 infection and cancer pathogenesis. In-depth statistical analysis using Kaplan-Meier, differential gene expression, and Cox multivariate regression analysis, demonstrated that overexpression of ACE2, CD147, PPIA and PPIB is significantly associated with poor-prognosis neuroblastoma samples. These results were seen in the presence of amplified MYCN, unfavourable tumour histology and in patients older than 18 months of age. Previously, we have shown that high levels of the nerve growth factor receptor NTRK1 together with low levels of the phosphatase PTPN6 and TP53 are associated with increased relapse-free survival of neuroblastoma patients. Interestingly, low levels of expression of ACE2, CD147, PPIA and PPIB are associated with this NTRK1-PTPN6-TP53 module, suggesting that low expression levels of these genes are associated with good prognosis. These findings have implications for clinical care and therapeutic treatment. The upregulation of ACE2, CD147, PPIA and PPIB in poor-prognosis neuroblastoma samples suggests that these patients may be at higher risk of severe SARS-CoV-2 infection. Importantly, our findings reveal ACE2, CD147, PPIA and PPIB as potential biomarkers and therapeutic targets for neuroblastoma.", "claims": [{"id": "claim-data-access", "statement": "Gene Expression Omnibus (GEO) database, accession number GSE49711, 498 samples of Agilent customized 4 × 44K oligonucleotide microarray data were downloaded, of which 492 have event free survival (EFS) data and MYCN amplification status, were analysed.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:34307909", "locator": "sections[3] \"Datasets\" paragraph 2", "quote": "Gene Expression Omnibus (GEO) database, accession number GSE49711, 498 samples of Agilent customized 4 × 44K oligonucleotide microarray data were downloaded, of which 492 have event free survival (EFS) data and MYCN amplification status, were analysed."}], "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:34307909"], "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:GSE49711"], "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:GSE49711"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:34307909", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1016/j.bbrep.2021.101081", "sha256": "sha256:90123c2fc8a57dbf4d8003253fcc9816335cef9bf635478b75c311cf8133dd8c", "bytes": 32823, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1016/j.bbrep.2021.101081", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC8286873", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE49711", "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=GSE49711", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE49711", "version": null, "note": "Gene Expression Omnibus (GEO) database, accession number GSE49711, 498 samples of Agilent customized 4 × 44K oligonucleotide microarray data were downloaded, of which 492 have event free survival (EFS) data and MYCN amplification status, were analysed.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "Gene Expression Omnibus (GEO) database, accession number GSE49711, 498 samples of Agilent customized 4 × 44K oligonucleotide microarray data were downloaded, of which 492 have event free survival (EFS) data and MYCN amplification status, were analysed.", "access_statement_kind": "repository_route_statement", "sample_accessions": ["GSM1205736", "GSM1205737", "GSM1205738", "GSM1205739", "GSM1205740", "GSM1205741", "GSM1205742", "GSM1205743", "GSM1205744", "GSM1205745", "GSM1205746", "GSM1205747", "GSM1205748", "GSM1205749", "GSM1205750", "GSM1205751", "GSM1205752", "GSM1205753", "GSM1205754", "GSM1205755", "GSM1205756", "GSM1205757", "GSM1205758", "GSM1205759", "GSM1205760", "GSM1205761", "GSM1205762", "GSM1205763", "GSM1205764", "GSM1205765", "GSM1205766", "GSM1205767", "GSM1205768", "GSM1205769", "GSM1205770", "GSM1205771", "GSM1205772", "GSM1205773", "GSM1205774", "GSM1205775", "GSM1205776", "GSM1205777", "GSM1205778", "GSM1205779", "GSM1205780", "GSM1205781", "GSM1205782", "GSM1205783", "GSM1205784", "GSM1205785", "GSM1205786", "GSM1205787", "GSM1205788", "GSM1205789", "GSM1205790", "GSM1205791", "GSM1205792", "GSM1205793", "GSM1205794", "GSM1205795", "GSM1205796", "GSM1205797", "GSM1205798", "GSM1205799", "GSM1205800", "GSM1205801", "GSM1205802", "GSM1205803", "GSM1205804", "GSM1205805", "GSM1205806", "GSM1205807", "GSM1205808", "GSM1205809", "GSM1205810", "GSM1205811", "GSM1205812", "GSM1205813", "GSM1205814", "GSM1205815", "GSM1205816", "GSM1205817", "GSM1205818", "GSM1205819", "GSM1205820", "GSM1205821", "GSM1205822", "GSM1205823", "GSM1205824", "GSM1205825", "GSM1205826", "GSM1205827", "GSM1205828", "GSM1205829", "GSM1205830", "GSM1205831", "GSM1205832", "GSM1205833", "GSM1205834", "GSM1205835", "GSM1205836", "GSM1205837", "GSM1205838", "GSM1205839", "GSM1205840", "GSM1205841", "GSM1205842", "GSM1205843", "GSM1205844", "GSM1205845", "GSM1205846", "GSM1205847", "GSM1205848", "GSM1205849", "GSM1205850", "GSM1205851", "GSM1205852", "GSM1205853", "GSM1205854", "GSM1205855", "GSM1205856", "GSM1205857", "GSM1205858", "GSM1205859", "GSM1205860", "GSM1205861", "GSM1205862", "GSM1205863", "GSM1205864", "GSM1205865", "GSM1205866", "GSM1205867", "GSM1205868", "GSM1205869", "GSM1205870", "GSM1205871", "GSM1205872", "GSM1205873", "GSM1205874", "GSM1205875", "GSM1205876", "GSM1205877", "GSM1205878", "GSM1205879", "GSM1205880", "GSM1205881", "GSM1205882", "GSM1205883", "GSM1205884", "GSM1205885", "GSM1205886", "GSM1205887", "GSM1205888", "GSM1205889", "GSM1205890", "GSM1205891", "GSM1205892", "GSM1205893", "GSM1205894", "GSM1205895", "GSM1205896", "GSM1205897", "GSM1205898", "GSM1205899", "GSM1205900", "GSM1205901", "GSM1205902", "GSM1205903", "GSM1205904", "GSM1205905", "GSM1205906", "GSM1205907", "GSM1205908", "GSM1205909", "GSM1205910", "GSM1205911", "GSM1205912", "GSM1205913", "GSM1205914", "GSM1205915", "GSM1205916", "GSM1205917", "GSM1205918", "GSM1205919", "GSM1205920", "GSM1205921", "GSM1205922", "GSM1205923", "GSM1205924", "GSM1205925", "GSM1205926", "GSM1205927", "GSM1205928", "GSM1205929", "GSM1205930", "GSM1205931", "GSM1205932", "GSM1205933", "GSM1205934", "GSM1205935", "GSM1205936", "GSM1205937", "GSM1205938", "GSM1205939", "GSM1205940", "GSM1205941", "GSM1205942", "GSM1205943", "GSM1205944", "GSM1205945", "GSM1205946", "GSM1205947", "GSM1205948", "GSM1205949", "GSM1205950", "GSM1205951", "GSM1205952", "GSM1205953", "GSM1205954", "GSM1205955", "GSM1205956", "GSM1205957", "GSM1205958", "GSM1205959", "GSM1205960", "GSM1205961", "GSM1205962", "GSM1205963", "GSM1205964", "GSM1205965", "GSM1205966", "GSM1205967", "GSM1205968", "GSM1205969", "GSM1205970", "GSM1205971", "GSM1205972", "GSM1205973", "GSM1205974", "GSM1205975", "GSM1205976", "GSM1205977", "GSM1205978", "GSM1205979", "GSM1205980", "GSM1205981", "GSM1205982", "GSM1205983", "GSM1205984", "GSM1205985", "GSM1205986", "GSM1205987", "GSM1205988", "GSM1205989", "GSM1205990", "GSM1205991", "GSM1205992", "GSM1205993", "GSM1205994", "GSM1205995", "GSM1205996", "GSM1205997", "GSM1205998", "GSM1205999", "GSM1206000", "GSM1206001", "GSM1206002", "GSM1206003", "GSM1206004", "GSM1206005", "GSM1206006", "GSM1206007", "GSM1206008", "GSM1206009", "GSM1206010", "GSM1206011", "GSM1206012", "GSM1206013", "GSM1206014", "GSM1206015", "GSM1206016", "GSM1206017", "GSM1206018", "GSM1206019", "GSM1206020", "GSM1206021", "GSM1206022", "GSM1206023", "GSM1206024", "GSM1206025", "GSM1206026", "GSM1206027", "GSM1206028", "GSM1206029", "GSM1206030", "GSM1206031", "GSM1206032", "GSM1206033", "GSM1206034", "GSM1206035", "GSM1206036", "GSM1206037", "GSM1206038", "GSM1206039", "GSM1206040", "GSM1206041", "GSM1206042", "GSM1206043", "GSM1206044", "GSM1206045", "GSM1206046", "GSM1206047", "GSM1206048", "GSM1206049", "GSM1206050", "GSM1206051", "GSM1206052", "GSM1206053", "GSM1206054", "GSM1206055", "GSM1206056", "GSM1206057", "GSM1206058", "GSM1206059", "GSM1206060", "GSM1206061", "GSM1206062", "GSM1206063", "GSM1206064", "GSM1206065", "GSM1206066", "GSM1206067", "GSM1206068", "GSM1206069", "GSM1206070", "GSM1206071", "GSM1206072", "GSM1206073", "GSM1206074", "GSM1206075", "GSM1206076", "GSM1206077", "GSM1206078", "GSM1206079", "GSM1206080", "GSM1206081", "GSM1206082", "GSM1206083", "GSM1206084", "GSM1206085", "GSM1206086", "GSM1206087", "GSM1206088", "GSM1206089", "GSM1206090", "GSM1206091", "GSM1206092", "GSM1206093", "GSM1206094", "GSM1206095", "GSM1206096", "GSM1206097", "GSM1206098", "GSM1206099", "GSM1206100", "GSM1206101", "GSM1206102", "GSM1206103", "GSM1206104", "GSM1206105", "GSM1206106", "GSM1206107", "GSM1206108", "GSM1206109", "GSM1206110", "GSM1206111", "GSM1206112", "GSM1206113", "GSM1206114", "GSM1206115", "GSM1206116", "GSM1206117", "GSM1206118", "GSM1206119", "GSM1206120", "GSM1206121", "GSM1206122", "GSM1206123", "GSM1206124", "GSM1206125", "GSM1206126", "GSM1206127", "GSM1206128", "GSM1206129", "GSM1206130", "GSM1206131", "GSM1206132", "GSM1206133", "GSM1206134", "GSM1206135", "GSM1206136", "GSM1206137", "GSM1206138", "GSM1206139", "GSM1206140", "GSM1206141", "GSM1206142", "GSM1206143", "GSM1206144", "GSM1206145", "GSM1206146", "GSM1206147", "GSM1206148", "GSM1206149", "GSM1206150", "GSM1206151", "GSM1206152", "GSM1206153", "GSM1206154", "GSM1206155", "GSM1206156", "GSM1206157", "GSM1206158", "GSM1206159", "GSM1206160", "GSM1206161", "GSM1206162", "GSM1206163", "GSM1206164", "GSM1206165", "GSM1206166", "GSM1206167", "GSM1206168", "GSM1206169", "GSM1206170", "GSM1206171", "GSM1206172", "GSM1206173", "GSM1206174", "GSM1206175", "GSM1206176", "GSM1206177", "GSM1206178", "GSM1206179", "GSM1206180", "GSM1206181", "GSM1206182", "GSM1206183", "GSM1206184", "GSM1206185", "GSM1206186", "GSM1206187", "GSM1206188", "GSM1206189", "GSM1206190", "GSM1206191", "GSM1206192", "GSM1206193", "GSM1206194", "GSM1206195", "GSM1206196", "GSM1206197", "GSM1206198", "GSM1206199", "GSM1206200", "GSM1206201", "GSM1206202", "GSM1206203", "GSM1206204", "GSM1206205", "GSM1206206", "GSM1206207", "GSM1206208", "GSM1206209", "GSM1206210", "GSM1206211", "GSM1206212", "GSM1206213", "GSM1206214", "GSM1206215", "GSM1206216", "GSM1206217", "GSM1206218", "GSM1206219", "GSM1206220", "GSM1206221", "GSM1206222", "GSM1206223", "GSM1206224", "GSM1206225", "GSM1206226", "GSM1206227", "GSM1206228", "GSM1206229", "GSM1206230", "GSM1206231", "GSM1206232", "GSM1206233"], "sample_count": 498, "group_sizes": null, "group_sizes_basis": null, "platform": "17553", "taxon": "Homo sapiens", "title": "RNA-Seq reveals an unprecedented complexity of the neuroblastoma transcriptome and is suitable for clinical endpoint prediction [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:GSE62564", "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=GSE62564", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE62564", "version": null, "note": "Gene Expression Omnibus (GEO) database, accession number GSE49711, 498 samples of Agilent customized 4 × 44K oligonucleotide microarray data were downloaded, of which 492 have event free survival (EFS) data and MYCN amplification status, were analysed.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "Gene Expression Omnibus (GEO) database, accession number GSE49711, 498 samples of Agilent customized 4 × 44K oligonucleotide microarray data were downloaded, of which 492 have event free survival (EFS) data and MYCN amplification status, were analysed.", "access_statement_kind": "repository_route_statement", "sample_accessions": ["GSM1528894", "GSM1528895", "GSM1528896", "GSM1528897", "GSM1528898", "GSM1528899", "GSM1528900", "GSM1528901", "GSM1528902", "GSM1528903", "GSM1528904", "GSM1528905", "GSM1528906", "GSM1528907", "GSM1528908", "GSM1528909", "GSM1528910", "GSM1528911", "GSM1528912", "GSM1528913", "GSM1528914", "GSM1528915", "GSM1528916", "GSM1528917", "GSM1528918", "GSM1528919", "GSM1528920", "GSM1528921", "GSM1528922", "GSM1528923", "GSM1528924", "GSM1528925", "GSM1528926", "GSM1528927", "GSM1528928", "GSM1528929", "GSM1528930", "GSM1528931", "GSM1528932", "GSM1528933", "GSM1528934", "GSM1528935", "GSM1528936", "GSM1528937", "GSM1528938", "GSM1528939", "GSM1528940", "GSM1528941", "GSM1528942", "GSM1528943", "GSM1528944", "GSM1528945", "GSM1528946", "GSM1528947", "GSM1528948", "GSM1528949", "GSM1528950", "GSM1528951", "GSM1528952", "GSM1528953", "GSM1528954", "GSM1528955", "GSM1528956", "GSM1528957", "GSM1528958", "GSM1528959", "GSM1528960", "GSM1528961", "GSM1528962", "GSM1528963", "GSM1528964", "GSM1528965", "GSM1528966", "GSM1528967", "GSM1528968", "GSM1528969", "GSM1528970", "GSM1528971", "GSM1528972", "GSM1528973", "GSM1528974", "GSM1528975", "GSM1528976", "GSM1528977", "GSM1528978", "GSM1528979", "GSM1528980", "GSM1528981", "GSM1528982", "GSM1528983", "GSM1528984", "GSM1528985", "GSM1528986", "GSM1528987", "GSM1528988", "GSM1528989", "GSM1528990", "GSM1528991", "GSM1528992", "GSM1528993", "GSM1528994", "GSM1528995", "GSM1528996", "GSM1528997", "GSM1528998", "GSM1528999", "GSM1529000", "GSM1529001", "GSM1529002", "GSM1529003", "GSM1529004", "GSM1529005", "GSM1529006", "GSM1529007", "GSM1529008", "GSM1529009", "GSM1529010", "GSM1529011", "GSM1529012", "GSM1529013", "GSM1529014", "GSM1529015", "GSM1529016", "GSM1529017", "GSM1529018", "GSM1529019", "GSM1529020", "GSM1529021", "GSM1529022", "GSM1529023", "GSM1529024", "GSM1529025", "GSM1529026", "GSM1529027", "GSM1529028", "GSM1529029", "GSM1529030", "GSM1529031", "GSM1529032", "GSM1529033", "GSM1529034", "GSM1529035", "GSM1529036", "GSM1529037", "GSM1529038", "GSM1529039", "GSM1529040", "GSM1529041", "GSM1529042", "GSM1529043", "GSM1529044", "GSM1529045", "GSM1529046", "GSM1529047", "GSM1529048", "GSM1529049", "GSM1529050", "GSM1529051", "GSM1529052", "GSM1529053", "GSM1529054", "GSM1529055", "GSM1529056", "GSM1529057", "GSM1529058", "GSM1529059", "GSM1529060", "GSM1529061", "GSM1529062", "GSM1529063", "GSM1529064", "GSM1529065", "GSM1529066", "GSM1529067", "GSM1529068", "GSM1529069", "GSM1529070", "GSM1529071", "GSM1529072", "GSM1529073", "GSM1529074", "GSM1529075", "GSM1529076", "GSM1529077", "GSM1529078", "GSM1529079", "GSM1529080", "GSM1529081", "GSM1529082", "GSM1529083", "GSM1529084", "GSM1529085", "GSM1529086", "GSM1529087", "GSM1529088", "GSM1529089", "GSM1529090", "GSM1529091", "GSM1529092", "GSM1529093", "GSM1529094", "GSM1529095", "GSM1529096", "GSM1529097", "GSM1529098", "GSM1529099", "GSM1529100", "GSM1529101", "GSM1529102", "GSM1529103", "GSM1529104", "GSM1529105", "GSM1529106", "GSM1529107", "GSM1529108", "GSM1529109", "GSM1529110", "GSM1529111", "GSM1529112", "GSM1529113", "GSM1529114", "GSM1529115", "GSM1529116", "GSM1529117", "GSM1529118", "GSM1529119", "GSM1529120", "GSM1529121", "GSM1529122", "GSM1529123", "GSM1529124", "GSM1529125", "GSM1529126", "GSM1529127", "GSM1529128", "GSM1529129", "GSM1529130", "GSM1529131", "GSM1529132", "GSM1529133", "GSM1529134", "GSM1529135", "GSM1529136", "GSM1529137", "GSM1529138", "GSM1529139", "GSM1529140", "GSM1529141", "GSM1529142", "GSM1529143", "GSM1529144", "GSM1529145", "GSM1529146", "GSM1529147", "GSM1529148", "GSM1529149", "GSM1529150", "GSM1529151", "GSM1529152", "GSM1529153", "GSM1529154", "GSM1529155", "GSM1529156", "GSM1529157", "GSM1529158", "GSM1529159", "GSM1529160", "GSM1529161", "GSM1529162", "GSM1529163", "GSM1529164", "GSM1529165", "GSM1529166", "GSM1529167", "GSM1529168", "GSM1529169", "GSM1529170", "GSM1529171", "GSM1529172", "GSM1529173", "GSM1529174", "GSM1529175", "GSM1529176", "GSM1529177", "GSM1529178", "GSM1529179", "GSM1529180", "GSM1529181", "GSM1529182", "GSM1529183", "GSM1529184", "GSM1529185", "GSM1529186", "GSM1529187", "GSM1529188", "GSM1529189", "GSM1529190", "GSM1529191", "GSM1529192", "GSM1529193", "GSM1529194", "GSM1529195", "GSM1529196", "GSM1529197", "GSM1529198", "GSM1529199", "GSM1529200", "GSM1529201", "GSM1529202", "GSM1529203", "GSM1529204", "GSM1529205", "GSM1529206", "GSM1529207", "GSM1529208", "GSM1529209", "GSM1529210", "GSM1529211", "GSM1529212", "GSM1529213", "GSM1529214", "GSM1529215", "GSM1529216", "GSM1529217", "GSM1529218", "GSM1529219", "GSM1529220", "GSM1529221", "GSM1529222", "GSM1529223", "GSM1529224", "GSM1529225", "GSM1529226", "GSM1529227", "GSM1529228", "GSM1529229", "GSM1529230", "GSM1529231", "GSM1529232", "GSM1529233", "GSM1529234", "GSM1529235", "GSM1529236", "GSM1529237", "GSM1529238", "GSM1529239", "GSM1529240", "GSM1529241", "GSM1529242", "GSM1529243", "GSM1529244", "GSM1529245", "GSM1529246", "GSM1529247", "GSM1529248", "GSM1529249", "GSM1529250", "GSM1529251", "GSM1529252", "GSM1529253", "GSM1529254", "GSM1529255", "GSM1529256", "GSM1529257", "GSM1529258", "GSM1529259", "GSM1529260", "GSM1529261", "GSM1529262", "GSM1529263", "GSM1529264", "GSM1529265", "GSM1529266", "GSM1529267", "GSM1529268", "GSM1529270", "GSM1529271", "GSM1529272", "GSM1529274", "GSM1529275", "GSM1529276", "GSM1529277", "GSM1529278", "GSM1529279", "GSM1529280", "GSM1529281", "GSM1529282", "GSM1529283", "GSM1529284", "GSM1529285", "GSM1529286", "GSM1529287", "GSM1529288", "GSM1529289", "GSM1529290", "GSM1529291", "GSM1529292", "GSM1529293", "GSM1529294", "GSM1529295", "GSM1529296", "GSM1529297", "GSM1529298", "GSM1529299", "GSM1529300", "GSM1529301", "GSM1529302", "GSM1529303", "GSM1529304", "GSM1529305", "GSM1529306", "GSM1529307", "GSM1529308", "GSM1529309", "GSM1529310", "GSM1529311", "GSM1529312", "GSM1529313", "GSM1529314", "GSM1529315", "GSM1529316", "GSM1529317", "GSM1529318", "GSM1529319", "GSM1529320", "GSM1529321", "GSM1529322", "GSM1529323", "GSM1529324", "GSM1529325", "GSM1529326", "GSM1529327", "GSM1529328", "GSM1529329", "GSM1529330", "GSM1529331", "GSM1529332", "GSM1529333", "GSM1529334", "GSM1529335", "GSM1529336", "GSM1529337", "GSM1529338", "GSM1529339", "GSM1529340", "GSM1529341", "GSM1529342", "GSM1529343", "GSM1529344", "GSM1529345", "GSM1529346", "GSM1529347", "GSM1529348", "GSM1529349", "GSM1529350", "GSM1529351", "GSM1529352", "GSM1529353", "GSM1529354", "GSM1529355", "GSM1529356", "GSM1529357", "GSM1529358", "GSM1529359", "GSM1529360", "GSM1529361", "GSM1529362", "GSM1529363", "GSM1529364", "GSM1529365", "GSM1529366", "GSM1529367", "GSM1529368", "GSM1529369", "GSM1529370", "GSM1529371", "GSM1529372", "GSM1529373", "GSM1529374", "GSM1529375", "GSM1529376", "GSM1529377", "GSM1529378", "GSM1529379", "GSM1529380", "GSM1529381", "GSM1529382", "GSM1529383", "GSM1529384", "GSM1529385", "GSM1529386", "GSM1529387", "GSM1529388", "GSM1529389", "GSM1529390", "GSM1529391", "GSM1529392", "GSM1529393"], "sample_count": 498, "group_sizes": null, "group_sizes_basis": null, "platform": "11154", "taxon": "Homo sapiens", "title": "An Investigation of Biomarkers Derived from Legacy Microarray Data for Their Utility in the RNA-Seq Era", "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:34307909:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:5f94b8628b6c28b525c2c0b52f18dcf78e994a45a0829e85bb7b309653f3f108", "bytes": 580, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[6]/table-wrap[1]#tbl1", "version": null, "note": "Multivariate analysis a of 492 neuroblastoma samples expressing ACE2, CD147, PPIA and PPIB (GSE49711).", "structure": {"pmcid": "PMC8286873", "section_index": 6, "section_title": "ACE2, CD147, PPIA and PPIB expression and association with event free survival", "row_count": 17, "column_count": 3}, "table": {"label": "Table 1", "caption": "Multivariate analysis a of 492 neuroblastoma samples expressing ACE2, CD147, PPIA and PPIB (GSE49711).", "rows": [["Variable", "Hazard ratio", "Pb"], ["ACE2"], ["Low", "1", ""], ["Moderate", "1.58", ".03"], ["High", "1.48", ".05"], ["CD147"], ["Low", "1", ""], ["Moderate", "1.46", ".10"], ["High", "2.13", "<.005"], ["PPIA"], ["Low", "1", ""], ["Moderate", "2.01", "<.005"], ["High", "2.74", "<.005"], ["PPIB"], ["Low", "1", ""], ["Moderate", "0.85", ".46"], ["High", "1.29", ".28"]], "row_count": 17, "column_count": 3, "numeric_cells": 21, "header_rows": 1, "locator": "section[6]/table-wrap[1]#tbl1"}}, {"id": "asset:table:pmid:34307909:2", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:5ea9696b8aa7d2633a16a19ceffd31545c054c7161413e3304e5ce2e2d526e3f", "bytes": 694, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[7]/table-wrap[1]#tbl2", "version": null, "note": "Multivariate analysis a of 492 neuroblastoma samples expressing ACE2, CD147, PPIA and PPIB adjusted for the NTRK1-PTPN6-TP53 module (GSE49711).", "structure": {"pmcid": "PMC8286873", "section_index": 7, "section_title": "ACE2, CD147, PPIA and PPIB expression and association with NTRK1-PTPN6-TP53", "row_count": 20, "column_count": 3}, "table": {"label": "Table 2", "caption": "Multivariate analysis a of 492 neuroblastoma samples expressing ACE2, CD147, PPIA and PPIB adjusted for the NTRK1-PTPN6-TP53 module (GSE49711).", "rows": [["Variable", "Hazard ratio", "Pb"], ["NTRK1-PTPN6-TP53 module"], ["Absent", "1", ""], ["Present", "0.47", "<.005"], ["ACE2"], ["Low", "1", ""], ["Moderate", "1.50", ".05"], ["High", "1.36", ".13"], ["CD147"], ["Low", "1", ""], ["Moderate", "1.41", ".14"], ["High", "2.17", "<.005"], ["PPIA"], ["Low", "1", ""], ["Moderate", "1.98", "<.005"], ["High", "2.61", "<.005"], ["PPIB"], ["Low", "1", ""], ["Moderate", "0.81", ".31"], ["High", "1.14", ".57"]], "row_count": 20, "column_count": 3, "numeric_cells": 25, "header_rows": 1, "locator": "section[7]/table-wrap[1]#tbl2"}}], "gaps": ["asset:data:geo:GSE49711 not downloaded", "asset:data:geo:GSE49711 licence not read", "asset:data:geo:GSE62564 not downloaded", "asset:data:geo:GSE62564 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": 0.7, "band": "medium", "quote": "Kaplan-Meier"}}, {"id": "method-2", "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": 0.8, "band": "high", "quote": "Cox regression"}}, {"id": "method-3", "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": 0.8, "band": "high", "quote": "log-rank"}}, {"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": "PPI"}}], "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": ["GSE49711", "GSE62564"], "resolved_accessions": ["GSE49711", "GSE62564"], "statements": ["Gene Expression Omnibus (GEO) database, accession number GSE49711, 498 samples of Agilent customized 4 × 44K oligonucleotide microarray data were downloaded, of which 492 have event free survival (EFS) data and MYCN amplification status, were analysed."], "basis": "The paper names GSE49711, GSE62564 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:34307909", "data:geo:GSE49711", "asset:table:pmid:34307909:1", "asset:table:pmid:34307909:2"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE49711"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-10-31T19:42:57Z", "independence": "single_reader"}, "evidence_check": {"method": "absent", "availability": null}, "calls": 3, "usage": {"prompt_tokens": 27777, "completion_tokens": 1638, "cached_tokens": 784}}, "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:34307909", "type": "paper", "label": "pmid:34307909"}, {"id": "source:pmid:34307909", "type": "manuscript", "label": "PMID 34307909 full text"}, {"id": "data:geo:GSE49711", "type": "dataset", "label": "GEO GSE49711"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:34307909", "type": "paper", "label": "pmid:34307909"}, {"id": "source:pmid:34307909", "type": "manuscript", "label": "PMID 34307909 full text"}, {"id": "data:geo:GSE49711", "type": "dataset", "label": "GEO GSE49711"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-34307909", "type": "extraction", "used": ["source:pmid:34307909"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE49711", "type": "accession_resolution", "used": ["data:geo:GSE49711"], "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:34307909", "parent_hash": "sha256:703d6dd3dcd01cbfd0f8dd9d57b7b29cf6e0085d45bee0b1c94ed21942f26846", "fork_of": null, "generation": 7}, "gaps": ["asset:data:geo:GSE49711 licence not read", "asset:data:geo:GSE49711 not downloaded", "asset:data:geo:GSE62564 licence not read", "asset:data:geo:GSE62564 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": 0.7, "evidence": ["Kaplan-Meier"], "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":"2026-11-04T04:13:49+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}}}