{"data":{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:34335936", "kind": "science-record", "revision": 8, "content_hash": "sha256:941dae675f0a78fcee5b55626945107613742f4a1347fd17d09754f5b8fc7194", "created_at": "2026-11-01T15:41:46Z", "updated_at": "2026-11-01T22:04:23Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Low expression of CDHR1 is an independent unfavorable prognostic factor in glioma.", "doi": "10.7150/jca.59948", "pmid": "34335936", "authors": ["Haiwei Wang", "Xinrui Wang", "Liangpu Xu", "Yingying Lin", "Ji Zhang", "Hua Cao"], "journal": "Journal of Cancer", "year": 2021, "abstract": "Background: Analysis of the differentially expressed genes between lower grade glioma (LGG) and glioblastoma (GBM) will identify genes involved in a more aggressive phenotype of glioma. Methods: Differentially expressed genes between GBM and LGG were identified using published datasets. Kaplan-Meier estimator was used to determine the overall survival of different groups of glioma patients. The biological functions of CDHR1 in glioma were tested using CCK-8 and trans-well assays. Results: CCDC109B, CD58, CLIC1, EFEMP2, EMP3, LAMC1, LGALS1, PDLIM1 and TNFRSF1A were over-expressed, while, CDHR1 was down-regulated in GBM in The Cancer Genome Atlas (TCGA), Chinese Glioma Genome Atlas (CGGA), GSE4412 and GSE43378 datasets. Compared with normal brain tissues, CDHR1 was down-regulated in glioma tissues. And low expression of CDHR1 was an unfavorable prognostic factor in glioma. Moreover, CDHR1 was lowly expressed in mesenchymal GBM subtype and lower expression of CDHR1 was associated with the worse clinical prognosis of GBM. Furthermore, CDHR1 was down-regulated in astrocytoma LGG subtype and low expression of CDHR1 was a bad prognosis of LGG. CDHR1 expression levels were also associated with IDH mutation. IDH mutant LGG or GBM patients were with higher CDHR1 expression. High expression of CDHR1 was a favorable prognosis in IDH mutant or IDH wild type LGG patients. CHDR1 expression was associated with MGMT methylation and CDHR1 was down-regulated in chemotherapy un-responsive LGG patients. CDHR1 was an independent prognostic factor and negatively associated with EMP3 expression. Glioma patients with low CDHR1 and high EMP3 expression had worse clinical outcomes. At last, we showed that over-expression of CDHR1 could inhibit glioma cell growth and invasion. Conclusion: Low expression of CDHR1 was an independent unfavorable prognostic factor in glioma.", "claims": [{"id": "claim-method", "statement": "The differentially expressed genes between LGG and GBM patients were determined using two tails paired Student's t test in TCGA, CGGA, GSE4412 and GSE43378 datasets.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:34335936", "locator": "sections[4] \"Identification of the differentially expressed genes between GBM and LGG\" paragraph 2", "quote": "The differentially expressed genes between LGG and GBM patients were determined using two tails paired Student's t test in TCGA, CGGA, GSE4412 and GSE43378 datasets."}], "state": "complete"}, {"id": "claim-data-access", "statement": "The gene expression, DNA methylation along with the clinical datasets of TCGA GBMLGG was downloaded from https://tcga.xenahubs.net website.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:34335936", "locator": "sections[3] \"Data collection\" paragraph 2", "quote": "The gene expression, DNA methylation along with the clinical datasets of TCGA GBMLGG was downloaded from https://tcga.xenahubs.net website."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "partial", "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:34335936"], "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:GSE13041"], "outputs": ["the source data with its repository provenance"], "instruments": [], "reagents": []}, {"id": "run_analysis", "order": 3, "name": "Run the published analysis", "kind": "analysis", "state": "blocked", "blocked_on": "method:student_t", "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:GSE13041"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": ["step:run_analysis blocked on method:student_t"]}, "data": {"state": "partial", "assets": [{"id": "source:pmid:34335936", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.7150/jca.59948", "sha256": "sha256:c4125d98679017d773069ffc878eaf4b1e18a0efb79bf9c1a07595e0b4fc8d2d", "bytes": 39091, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.7150/jca.59948", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC8317511", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE13041", "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=GSE13041", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE13041", "version": null, "note": "The gene expression, DNA methylation along with the clinical datasets of TCGA GBMLGG was downloaded from https://tcga.xenahubs.net website.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The gene expression, DNA methylation along with the clinical datasets of TCGA GBMLGG was downloaded from https://tcga.xenahubs.net website.", "access_statement_kind": "repository_route_statement", "sample_accessions": ["GSM326661", "GSM326662", "GSM326663", "GSM326664", "GSM326665", "GSM326666", "GSM326667", "GSM326668", "GSM326669", "GSM326670", "GSM326671", "GSM326672", "GSM326673", "GSM326674", "GSM326675", "GSM326676", "GSM326677", "GSM326678", "GSM326679", "GSM326680", "GSM326681", "GSM326682", "GSM326683", "GSM326684", "GSM326685", "GSM326686", "GSM326687", "GSM326688", "GSM326689", "GSM326690", "GSM326691", "GSM326692", "GSM326693", "GSM326694", "GSM326695", "GSM326696", "GSM326697", "GSM326698", "GSM326699", "GSM326700", "GSM326701", "GSM326702", "GSM326703", "GSM326704", "GSM326705", "GSM326706", "GSM326707", "GSM326708", "GSM326709", "GSM326710", "GSM326711", "GSM326712", "GSM326713", "GSM326714", "GSM326715", "GSM326716", "GSM326717", "GSM326718", "GSM326719", "GSM326720", "GSM326721", "GSM326722", "GSM326723", "GSM326724", "GSM326725", "GSM326726", "GSM326727", "GSM326728", "GSM326729", "GSM326730", "GSM326731", "GSM326732", "GSM326733", "GSM326734", "GSM326735", "GSM326736", "GSM326737", "GSM326738", "GSM326739", "GSM326740", "GSM326741", "GSM326742", "GSM326743", "GSM326744", "GSM326745", "GSM326746", "GSM326747", "GSM326748", "GSM326749", "GSM326750", "GSM326751", "GSM326752", "GSM326753", "GSM326754", "GSM326755", "GSM326756", "GSM326757", "GSM326758", "GSM326759", "GSM326760", "GSM326761", "GSM326762", "GSM326763", "GSM326764", "GSM326765", "GSM326766", "GSM326767", "GSM326768", "GSM326769", "GSM326770", "GSM326771", "GSM326772", "GSM326773", "GSM326774", "GSM326775", "GSM326776", "GSM326777", "GSM326778", "GSM326779", "GSM326780", "GSM326781", "GSM326782", "GSM326783", "GSM326784", "GSM326785", "GSM326786", "GSM326787", "GSM326788", "GSM326789", "GSM326790", "GSM326791", "GSM326792", "GSM326793", "GSM326794", "GSM326795", "GSM326796", "GSM326797", "GSM326798", "GSM326799", "GSM326800", "GSM326801", "GSM326802", "GSM326803", "GSM326804", "GSM326805", "GSM326806", "GSM326807", "GSM326808", "GSM326809", "GSM326810", "GSM326811", "GSM326812", "GSM326813", "GSM326814", "GSM326815", "GSM326816", "GSM326817", "GSM326818", "GSM326819", "GSM326820", "GSM326821", "GSM326822", "GSM326823", "GSM326824", "GSM326825", "GSM326826", "GSM326827", "GSM326828", "GSM326829", "GSM326830", "GSM326831", "GSM326832", "GSM326833", "GSM326834", "GSM326835", "GSM326836", "GSM326837", "GSM326838", "GSM326839", "GSM326840", "GSM326841", "GSM326842", "GSM326843", "GSM326844", "GSM326845", "GSM326846", "GSM326847", "GSM326848", "GSM326849", "GSM326850", "GSM326851", "GSM326852", "GSM326853", "GSM326854", "GSM326855", "GSM326856", "GSM326857", "GSM326858", "GSM326859", "GSM326860", "GSM326861", "GSM326862", "GSM326863", "GSM326864", "GSM326865", "GSM326866", "GSM326867", "GSM326868", "GSM326869", "GSM326870", "GSM326871", "GSM326872", "GSM326873", "GSM326874", "GSM326875", "GSM326876", "GSM326877", "GSM326878", "GSM326879", "GSM326880", "GSM326881", "GSM326882", "GSM326883", "GSM326884", "GSM326885", "GSM326886", "GSM326887", "GSM326888", "GSM326889", "GSM326890", "GSM326891", "GSM326892", "GSM326893", "GSM326894", "GSM326895", "GSM326896", "GSM326897", "GSM326898", "GSM326899", "GSM326900", "GSM326901", "GSM326902", "GSM326903", "GSM326904", "GSM326905", "GSM326906", "GSM326907", "GSM326908", "GSM326909", "GSM326910", "GSM326911", "GSM326912", "GSM326913", "GSM326914", "GSM326915", "GSM326916", "GSM326917", "GSM326918", "GSM326919", "GSM326920", "GSM326921", "GSM326922", "GSM326923", "GSM326924", "GSM326925", "GSM326926", "GSM326927"], "sample_count": 267, "group_sizes": null, "group_sizes_basis": null, "platform": "570;8300;96", "taxon": "Homo sapiens", "title": "Gene expression analysis of glioblastomas identifies the major molecular basis for the prognostic benefit of younger age", "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:GSE16011", "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=GSE16011", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE16011", "version": null, "note": "The gene expression, DNA methylation along with the clinical datasets of TCGA GBMLGG was downloaded from https://tcga.xenahubs.net website.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The gene expression, DNA methylation along with the clinical datasets of TCGA GBMLGG was downloaded from https://tcga.xenahubs.net website.", "access_statement_kind": "repository_route_statement", "sample_accessions": ["GSM405200", "GSM405201", "GSM405202", "GSM405203", "GSM405204", "GSM405205", "GSM405206", "GSM405207", "GSM405208", "GSM405209", "GSM405210", "GSM405211", "GSM405212", "GSM405213", "GSM405214", "GSM405215", "GSM405216", "GSM405217", "GSM405218", "GSM405219", "GSM405220", "GSM405221", "GSM405222", "GSM405223", "GSM405224", "GSM405225", "GSM405226", "GSM405227", "GSM405228", "GSM405229", "GSM405230", "GSM405231", "GSM405232", "GSM405233", "GSM405234", "GSM405235", "GSM405236", "GSM405237", "GSM405238", "GSM405239", "GSM405240", "GSM405241", "GSM405242", "GSM405243", "GSM405244", "GSM405245", "GSM405246", "GSM405247", "GSM405248", "GSM405249", "GSM405250", "GSM405251", "GSM405252", "GSM405253", "GSM405254", "GSM405255", "GSM405256", "GSM405257", "GSM405258", "GSM405259", "GSM405260", "GSM405261", "GSM405262", "GSM405263", "GSM405264", "GSM405265", "GSM405266", "GSM405267", "GSM405268", "GSM405269", "GSM405270", "GSM405271", "GSM405272", "GSM405273", "GSM405274", "GSM405275", "GSM405276", "GSM405277", "GSM405278", "GSM405279", "GSM405280", "GSM405281", "GSM405282", "GSM405283", "GSM405284", "GSM405285", "GSM405286", "GSM405287", "GSM405288", "GSM405289", "GSM405290", "GSM405291", "GSM405292", "GSM405293", "GSM405294", "GSM405295", "GSM405296", "GSM405297", "GSM405298", "GSM405299", "GSM405300", "GSM405301", "GSM405302", "GSM405303", "GSM405304", "GSM405305", "GSM405306", "GSM405307", "GSM405308", "GSM405309", "GSM405310", "GSM405311", "GSM405312", "GSM405313", "GSM405314", "GSM405315", "GSM405316", "GSM405317", "GSM405318", "GSM405319", "GSM405320", "GSM405321", "GSM405322", "GSM405323", "GSM405324", "GSM405325", "GSM405326", "GSM405327", "GSM405328", "GSM405329", "GSM405330", "GSM405331", "GSM405332", "GSM405333", "GSM405334", "GSM405335", "GSM405336", "GSM405337", "GSM405338", "GSM405339", "GSM405340", "GSM405341", "GSM405342", "GSM405343", "GSM405344", "GSM405345", "GSM405346", "GSM405347", "GSM405348", "GSM405349", "GSM405350", "GSM405351", "GSM405352", "GSM405353", "GSM405354", "GSM405355", "GSM405356", "GSM405357", "GSM405358", "GSM405359", "GSM405360", "GSM405361", "GSM405362", "GSM405363", "GSM405364", "GSM405365", "GSM405366", "GSM405367", "GSM405368", "GSM405369", "GSM405370", "GSM405371", "GSM405372", "GSM405373", "GSM405374", "GSM405375", "GSM405376", "GSM405377", "GSM405378", "GSM405379", "GSM405380", "GSM405381", "GSM405382", "GSM405383", "GSM405384", "GSM405385", "GSM405386", "GSM405387", "GSM405388", "GSM405389", "GSM405390", "GSM405391", "GSM405392", "GSM405393", "GSM405394", "GSM405395", "GSM405396", "GSM405397", "GSM405398", "GSM405399", "GSM405400", "GSM405401", "GSM405402", "GSM405403", "GSM405404", "GSM405405", "GSM405406", "GSM405407", "GSM405408", "GSM405409", "GSM405410", "GSM405411", "GSM405412", "GSM405413", "GSM405414", "GSM405415", "GSM405416", "GSM405417", "GSM405418", "GSM405419", "GSM405420", "GSM405421", "GSM405422", "GSM405423", "GSM405424", "GSM405425", "GSM405426", "GSM405427", "GSM405428", "GSM405429", "GSM405430", "GSM405431", "GSM405432", "GSM405433", "GSM405434", "GSM405435", "GSM405436", "GSM405437", "GSM405438", "GSM405439", "GSM405440", "GSM405441", "GSM405442", "GSM405443", "GSM405444", "GSM405445", "GSM405446", "GSM405447", "GSM405448", "GSM405449", "GSM405450", "GSM405451", "GSM405452", "GSM405453", "GSM405454", "GSM405455", "GSM405456", "GSM405457", "GSM405458", "GSM405459", "GSM405460", "GSM405461", "GSM405462", "GSM405463", "GSM405464", "GSM405465", "GSM405466", "GSM405467", "GSM405468", "GSM405469", "GSM405470", "GSM405471", "GSM405472", "GSM405473", "GSM405474", "GSM405475", "GSM405476", "GSM405477", "GSM405478", "GSM405479", "GSM405480", "GSM405481", "GSM405482", "GSM405483"], "sample_count": 284, "group_sizes": null, "group_sizes_basis": null, "platform": "8542", "taxon": "Homo sapiens", "title": "Intrinsic Gene Expression Profiles of Gliomas are a Better Predictor of Survival than Histology", "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:GSE43378", "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=GSE43378", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE43378", "version": null, "note": "The gene expression, DNA methylation along with the clinical datasets of TCGA GBMLGG was downloaded from https://tcga.xenahubs.net website.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The gene expression, DNA methylation along with the clinical datasets of TCGA GBMLGG was downloaded from https://tcga.xenahubs.net website.", "access_statement_kind": "repository_route_statement", "sample_accessions": ["GSM1061661", "GSM1061662", "GSM1061663", "GSM1061664", "GSM1061665", "GSM1061666", "GSM1061667", "GSM1061668", "GSM1061669", "GSM1061670", "GSM1061671", "GSM1061672", "GSM1061673", "GSM1061674", "GSM1061675", "GSM1061676", "GSM1061677", "GSM1061678", "GSM1061679", "GSM1061680", "GSM1061681", "GSM1061682", "GSM1061683", "GSM1061684", "GSM1061685", "GSM1061686", "GSM1061687", "GSM1061688", "GSM1061689", "GSM1061690", "GSM1061691", "GSM1061692", "GSM1061693", "GSM1061694", "GSM1061695", "GSM1061696", "GSM1061697", "GSM1061698", "GSM1061699", "GSM1061700", "GSM1061701", "GSM1061702", "GSM1061703", "GSM1061704", "GSM1061705", "GSM1061706", "GSM1061707", "GSM1061708", "GSM1061709", "GSM1061710"], "sample_count": 50, "group_sizes": null, "group_sizes_basis": null, "platform": "570", "taxon": "Homo sapiens", "title": "Expression data from glioma 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:GSE4412", "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=GSE4412", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE4412", "version": null, "note": "The gene expression, DNA methylation along with the clinical datasets of TCGA GBMLGG was downloaded from https://tcga.xenahubs.net website.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The gene expression, DNA methylation along with the clinical datasets of TCGA GBMLGG was downloaded from https://tcga.xenahubs.net website.", "access_statement_kind": "repository_route_statement", "sample_accessions": ["GSM99432", "GSM99433", "GSM99434", "GSM99435", "GSM99436", "GSM99437", "GSM99438", "GSM99439", "GSM99440", "GSM99441", "GSM99442", "GSM99443", "GSM99444", "GSM99445", "GSM99446", "GSM99447", "GSM99448", "GSM99449", "GSM99450", "GSM99451", "GSM99452", "GSM99453", "GSM99454", "GSM99455", "GSM99456", "GSM99457", "GSM99458", "GSM99459", "GSM99460", "GSM99461", "GSM99462", "GSM99463", "GSM99464", "GSM99465", "GSM99466", "GSM99467", "GSM99468", "GSM99469", "GSM99470", "GSM99471", "GSM99472", "GSM99473", "GSM99474", "GSM99475", "GSM99476", "GSM99477", "GSM99478", "GSM99479", "GSM99480", "GSM99481", "GSM99482", "GSM99483", "GSM99484", "GSM99485", "GSM99486", "GSM99487", "GSM99488", "GSM99489", "GSM99490", "GSM99491", "GSM99492", "GSM99493", "GSM99494", "GSM99495", "GSM99496", "GSM99497", "GSM99498", "GSM99499", "GSM99500", "GSM99501", "GSM99502", "GSM99503", "GSM99504", "GSM99505", "GSM99506", "GSM99507", "GSM99508", "GSM99509", "GSM99510", "GSM99511", "GSM99512", "GSM99513", "GSM99514", "GSM99515", "GSM99516", "GSM99517", "GSM99518", "GSM99519", "GSM99520", "GSM99521", "GSM99522", "GSM99523", "GSM99524", "GSM99525", "GSM99526", "GSM99527", "GSM99528", "GSM99529", "GSM99530", "GSM99531", "GSM99532", "GSM99533", "GSM99534", "GSM99535", "GSM99536", "GSM99537", "GSM99538", "GSM99539", "GSM99540", "GSM99541", "GSM99542", "GSM99543", "GSM99544", "GSM99545", "GSM99546", "GSM99547", "GSM99548", "GSM99549", "GSM99550", "GSM99551", "GSM99552", "GSM99553", "GSM99554", "GSM99555", "GSM99556", "GSM99557", "GSM99558", "GSM99559", "GSM99560", "GSM99561", "GSM99562", "GSM99563", "GSM99564", "GSM99565", "GSM99566", "GSM99567", "GSM99568", "GSM99569", "GSM99570", "GSM99571", "GSM99572", "GSM99573", "GSM99574", "GSM99575", "GSM99576", "GSM99577", "GSM99578", "GSM99579", "GSM99580", "GSM99581", "GSM99582", "GSM99583", "GSM99584", "GSM99585", "GSM99586", "GSM99587", "GSM99588", "GSM99589", "GSM99590", "GSM99591", "GSM99592", "GSM99593", "GSM99594", "GSM99595", "GSM99596", "GSM99597", "GSM99598", "GSM99599", "GSM99600", "GSM99601"], "sample_count": 170, "group_sizes": null, "group_sizes_basis": null, "platform": "96;97", "taxon": "Homo sapiens", "title": "freij-affy-human-91666", "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:GSE44971", "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=GSE44971", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE44971", "version": null, "note": "The gene expression, DNA methylation along with the clinical datasets of TCGA GBMLGG was downloaded from https://tcga.xenahubs.net website.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The gene expression, DNA methylation along with the clinical datasets of TCGA GBMLGG was downloaded from https://tcga.xenahubs.net website.", "access_statement_kind": "repository_route_statement", "sample_accessions": ["GSM1094814", "GSM1094815", "GSM1094816", "GSM1094817", "GSM1094818", "GSM1094819", "GSM1094820", "GSM1094821", "GSM1094822", "GSM1094823", "GSM1094824", "GSM1094825", "GSM1094826", "GSM1094827", "GSM1094828", "GSM1094829", "GSM1094830", "GSM1094831", "GSM1094832", "GSM1094833", "GSM1094834", "GSM1094835", "GSM1094836", "GSM1094837", "GSM1094838", "GSM1094839", "GSM1094840", "GSM1094841", "GSM1094842", "GSM1094843", "GSM1094844", "GSM1094845", "GSM1094846", "GSM1094847", "GSM1094848", "GSM1094849", "GSM1094850", "GSM1094851", "GSM1094852", "GSM1094853", "GSM1094854", "GSM1094855", "GSM1094856", "GSM1094857", "GSM1094858", "GSM1094859", "GSM1094860", "GSM1094861", "GSM1094862", "GSM1094863", "GSM1094864", "GSM1094865", "GSM1094866", "GSM1094867", "GSM1094868", "GSM1094869", "GSM1094870", "GSM1094871"], "sample_count": 58, "group_sizes": null, "group_sizes_basis": null, "platform": "570", "taxon": "Homo sapiens", "title": "Gene expression data from pilocytic astrocytoma tumour samples and normal cerebellum controls", "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:GSE68848", "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=GSE68848", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE68848", "version": null, "note": "The gene expression, DNA methylation along with the clinical datasets of TCGA GBMLGG was downloaded from https://tcga.xenahubs.net website.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The gene expression, DNA methylation along with the clinical datasets of TCGA GBMLGG was downloaded from https://tcga.xenahubs.net website.", "access_statement_kind": "repository_route_statement", "sample_accessions": ["GSM1683515", "GSM1683516", "GSM1683517", "GSM1683518", "GSM1683519", "GSM1683520", "GSM1683521", "GSM1683522", "GSM1683523", "GSM1683524", "GSM1683525", "GSM1683526", "GSM1683527", "GSM1683528", "GSM1683529", "GSM1683530", "GSM1683531", "GSM1683532", "GSM1683533", "GSM1683534", "GSM1683535", "GSM1683536", "GSM1683537", "GSM1683538", "GSM1683539", "GSM1683540", "GSM1683541", "GSM1683542", "GSM1683543", "GSM1683544", "GSM1683545", "GSM1683546", "GSM1683547", "GSM1683548", "GSM1683549", "GSM1683550", "GSM1683551", "GSM1683552", "GSM1683553", "GSM1683554", "GSM1683555", "GSM1683556", "GSM1683557", "GSM1683558", "GSM1683559", "GSM1683560", "GSM1683561", "GSM1683562", "GSM1683563", "GSM1683564", "GSM1683565", "GSM1683566", "GSM1683567", "GSM1683568", "GSM1683569", "GSM1683570", "GSM1683571", "GSM1683572", "GSM1683573", "GSM1683574", "GSM1683575", "GSM1683576", "GSM1683577", "GSM1683578", "GSM1683579", "GSM1683580", "GSM1683581", "GSM1683582", "GSM1683583", "GSM1683584", "GSM1683585", "GSM1683586", "GSM1683587", "GSM1683588", "GSM1683589", "GSM1683590", "GSM1683591", "GSM1683592", "GSM1683593", "GSM1683594", "GSM1683595", "GSM1683596", "GSM1683597", "GSM1683598", "GSM1683599", "GSM1683600", "GSM1683601", "GSM1683602", "GSM1683603", "GSM1683604", "GSM1683605", "GSM1683606", "GSM1683607", "GSM1683608", "GSM1683609", "GSM1683610", "GSM1683611", "GSM1683612", "GSM1683613", "GSM1683614", "GSM1683615", "GSM1683616", "GSM1683617", "GSM1683618", "GSM1683619", "GSM1683620", "GSM1683621", "GSM1683622", "GSM1683623", "GSM1683624", "GSM1683625", "GSM1683626", "GSM1683627", "GSM1683628", "GSM1683629", "GSM1683630", "GSM1683631", "GSM1683632", "GSM1683633", "GSM1683634", "GSM1683635", "GSM1683636", "GSM1683637", "GSM1683638", "GSM1683639", "GSM1683640", "GSM1683641", "GSM1683642", "GSM1683643", "GSM1683644", "GSM1683645", "GSM1683646", "GSM1683647", "GSM1683648", "GSM1683649", "GSM1683650", "GSM1683651", "GSM1683652", "GSM1683653", "GSM1683654", "GSM1683655", "GSM1683656", "GSM1683657", "GSM1683658", "GSM1683659", "GSM1683660", "GSM1683661", "GSM1683662", "GSM1683663", "GSM1683664", "GSM1683665", "GSM1683666", "GSM1683667", "GSM1683668", "GSM1683669", "GSM1683670", "GSM1683671", "GSM1683672", "GSM1683673", "GSM1683674", "GSM1683675", "GSM1683676", "GSM1683677", "GSM1683678", "GSM1683679", "GSM1683680", "GSM1683681", "GSM1683682", "GSM1683683", "GSM1683684", "GSM1683685", "GSM1683686", "GSM1683687", "GSM1683688", "GSM1683689", "GSM1683690", "GSM1683691", "GSM1683692", "GSM1683693", "GSM1683694", "GSM1683695", "GSM1683696", "GSM1683697", "GSM1683698", "GSM1683699", "GSM1683700", "GSM1683701", "GSM1683702", "GSM1683703", "GSM1683704", "GSM1683705", "GSM1683706", "GSM1683707", "GSM1683708", "GSM1683709", "GSM1683710", "GSM1683711", "GSM1683712", "GSM1683713", "GSM1683714", "GSM1683715", "GSM1683716", "GSM1683717", "GSM1683718", "GSM1683719", "GSM1683720", "GSM1683721", "GSM1683722", "GSM1683723", "GSM1683724", "GSM1683725", "GSM1683726", "GSM1683727", "GSM1683728", "GSM1683729", "GSM1683730", "GSM1683731", "GSM1683732", "GSM1683733", "GSM1683734", "GSM1683735", "GSM1683736", "GSM1683737", "GSM1683738", "GSM1683739", "GSM1683740", "GSM1683741", "GSM1683742", "GSM1683743", "GSM1683744", "GSM1683745", "GSM1683746", "GSM1683747", "GSM1683748", "GSM1683749", "GSM1683750", "GSM1683751", "GSM1683752", "GSM1683753", "GSM1683754", "GSM1683755", "GSM1683756", "GSM1683757", "GSM1683758", "GSM1683759", "GSM1683760", "GSM1683761", "GSM1683762", "GSM1683763", "GSM1683764", "GSM1683765", "GSM1683766", "GSM1683767", "GSM1683768", "GSM1683769", "GSM1683770", "GSM1683771", "GSM1683772", "GSM1683773", "GSM1683774", "GSM1683775", "GSM1683776", "GSM1683777", "GSM1683778", "GSM1683779", "GSM1683780", "GSM1683781", "GSM1683782", "GSM1683783", "GSM1683784", "GSM1683785", "GSM1683786", "GSM1683787", "GSM1683788", "GSM1683789", "GSM1683790", "GSM1683791", "GSM1683792", "GSM1683793", "GSM1683794", "GSM1683795", "GSM1683796", "GSM1683797", "GSM1683798", "GSM1683799", "GSM1683800", "GSM1683801", "GSM1683802", "GSM1683803", "GSM1683804", "GSM1683805", "GSM1683806", "GSM1683807", "GSM1683808", "GSM1683809", "GSM1683810", "GSM1683811", "GSM1683812", "GSM1683813", "GSM1683814", "GSM1683815", "GSM1683816", "GSM1683817", "GSM1683818", "GSM1683819", "GSM1683820", "GSM1683821", "GSM1683822", "GSM1683823", "GSM1683824", "GSM1683825", "GSM1683826", "GSM1683827", "GSM1683828", "GSM1683829", "GSM1683830", "GSM1683831", "GSM1683832", "GSM1683833", "GSM1683834", "GSM1683835", "GSM1683836", "GSM1683837", "GSM1683838", "GSM1683839", "GSM1683840", "GSM1683841", "GSM1683842", "GSM1683843", "GSM1683844", "GSM1683845", "GSM1683846", "GSM1683847", "GSM1683848", "GSM1683849", "GSM1683850", "GSM1683851", "GSM1683852", "GSM1683853", "GSM1683854", "GSM1683855", "GSM1683856", "GSM1683857", "GSM1683858", "GSM1683859", "GSM1683860", "GSM1683861", "GSM1683862", "GSM1683863", "GSM1683864", "GSM1683865", "GSM1683866", "GSM1683867", "GSM1683868", "GSM1683869", "GSM1683870", "GSM1683871", "GSM1683872", "GSM1683873", "GSM1683874", "GSM1683875", "GSM1683876", "GSM1683877", "GSM1683878", "GSM1683879", "GSM1683880", "GSM1683881", "GSM1683882", "GSM1683883", "GSM1683884", "GSM1683885", "GSM1683886", "GSM1683887", "GSM1683888", "GSM1683889", "GSM1683890", "GSM1683891", "GSM1683892", "GSM1683893", "GSM1683894", "GSM1683895", "GSM1683896", "GSM1683897", "GSM1683898", "GSM1683899", "GSM1683900", "GSM1683901", "GSM1683902", "GSM1683903", "GSM1683904", "GSM1683905", "GSM1683906", "GSM1683907", "GSM1683908", "GSM1683909", "GSM1683910", "GSM1683911", "GSM1683912", "GSM1683913", "GSM1683914", "GSM1683915", "GSM1683916", "GSM1683917", "GSM1683918", "GSM1683919", "GSM1683920", "GSM1683921", "GSM1683922", "GSM1683923", "GSM1683924", "GSM1683925", "GSM1683926", "GSM1683927", "GSM1683928", "GSM1683929", "GSM1683930", "GSM1683931", "GSM1683932", "GSM1683933", "GSM1683934", "GSM1683935", "GSM1683936", "GSM1683937", "GSM1683938", "GSM1683939", "GSM1683940", "GSM1683941", "GSM1683942", "GSM1683943", "GSM1683944", "GSM1683945", "GSM1683946", "GSM1683947", "GSM1683948", "GSM1683949", "GSM1683950", "GSM1683951", "GSM1683952", "GSM1683953", "GSM1683954", "GSM1683955", "GSM1683956", "GSM1683957", "GSM1683958", "GSM1683959", "GSM1683960", "GSM1683961", "GSM1683962", "GSM1683963", "GSM1683964", "GSM1683965", "GSM1683966", "GSM1683967", "GSM1683968", "GSM1683969", "GSM1683970", "GSM1683971", "GSM1683972", "GSM1683973", "GSM1683974", "GSM1683975", "GSM1683976", "GSM1683977", "GSM1683978", "GSM1683979", "GSM1683980", "GSM1683981", "GSM1683982", "GSM1683983", "GSM1683984", "GSM1683985", "GSM1683986", "GSM1683987", "GSM1683988", "GSM1683989", "GSM1683990", "GSM1683991", "GSM1683992", "GSM1683993", "GSM1683994", "GSM1683995", "GSM1683996", "GSM1683997", "GSM1683998", "GSM1683999", "GSM1684000", "GSM1684001", "GSM1684002", "GSM1684003", "GSM1684004", "GSM1684005", "GSM1684006", "GSM1684007", "GSM1684008", "GSM1684009", "GSM1684010", "GSM1684011", "GSM1684012", "GSM1684013", "GSM1684014", "GSM1684015", "GSM1684016", "GSM1684017", "GSM1684018", "GSM1684019", "GSM1684020", "GSM1684021", "GSM1684022", "GSM1684023", "GSM1684024", "GSM1684025", "GSM1684026", "GSM1684027", "GSM1684028", "GSM1684029", "GSM1684030", "GSM1684031", "GSM1684032", "GSM1684033", "GSM1684034", "GSM1684035", "GSM1684036", "GSM1684037", "GSM1684038", "GSM1684039", "GSM1684040", "GSM1684041", "GSM1684042", "GSM1684043", "GSM1684044", "GSM1684045", "GSM1684046", "GSM1684047", "GSM1684048", "GSM1684049", "GSM1684050", "GSM1684051", "GSM1684052", "GSM1684053", "GSM1684054", "GSM1684055", "GSM1684056", "GSM1684057", "GSM1684058", "GSM1684059", "GSM1684060", "GSM1684061", "GSM1684062", "GSM1684063", "GSM1684064", "GSM1684065", "GSM1684066", "GSM1684067", "GSM1684068", "GSM1684069", "GSM1684070", "GSM1684071", "GSM1684072", "GSM1684073", "GSM1684074", "GSM1684075", "GSM1684076", "GSM1684077", "GSM1684078", "GSM1684079", "GSM1684080", "GSM1684081", "GSM1684082", "GSM1684083", "GSM1684084", "GSM1684085", "GSM1684086", "GSM1684087", "GSM1684088", "GSM1684089", "GSM1684090", "GSM1684091", "GSM1684092", "GSM1684093", "GSM1684094"], "sample_count": 580, "group_sizes": null, "group_sizes_basis": null, "platform": "570", "taxon": "Homo sapiens", "title": "caArray_fine-00037: Rembrandt_GeneExpression", "resolution_checked_at": "2026-11-01T15:39:55Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:GSE74187", "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=GSE74187", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE74187", "version": null, "note": "The gene expression, DNA methylation along with the clinical datasets of TCGA GBMLGG was downloaded from https://tcga.xenahubs.net website.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The gene expression, DNA methylation along with the clinical datasets of TCGA GBMLGG was downloaded from https://tcga.xenahubs.net website.", "access_statement_kind": "repository_route_statement", "sample_accessions": ["GSM1912920", "GSM1912921", "GSM1912922", "GSM1912923", "GSM1912924", "GSM1912925", "GSM1912926", "GSM1912927", "GSM1912928", "GSM1912929", "GSM1912930", "GSM1912931", "GSM1912932", "GSM1912933", "GSM1912934", "GSM1912935", "GSM1912936", "GSM1912937", "GSM1912938", "GSM1912939", "GSM1912940", "GSM1912941", "GSM1912942", "GSM1912943", "GSM1912944", "GSM1912945", "GSM1912946", "GSM1912947", "GSM1912948", "GSM1912949", "GSM1912950", "GSM1912951", "GSM1912952", "GSM1912953", "GSM1912954", "GSM1912955", "GSM1912956", "GSM1912957", "GSM1912958", "GSM1912959", "GSM1912960", "GSM1912961", "GSM1912962", "GSM1912963", "GSM1912964", "GSM1912965", "GSM1912966", "GSM1912967", "GSM1912968", "GSM1912969", "GSM1912970", "GSM1912971", "GSM1912972", "GSM1912973", "GSM1912974", "GSM1912975", "GSM1912976", "GSM1912977", "GSM1912978", "GSM1912979"], "sample_count": 60, "group_sizes": null, "group_sizes_basis": null, "platform": "6480", "taxon": "Homo sapiens", "title": "Sixty Glioblastoma Multiforme (GBM) samples obtained from surgical excision with OS and PFS", "resolution_checked_at": "2026-11-01T15:39:55Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:GSE83300", "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=GSE83300", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE83300", "version": null, "note": "The gene expression, DNA methylation along with the clinical datasets of TCGA GBMLGG was downloaded from https://tcga.xenahubs.net website.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The gene expression, DNA methylation along with the clinical datasets of TCGA GBMLGG was downloaded from https://tcga.xenahubs.net website.", "access_statement_kind": "repository_route_statement", "sample_accessions": ["GSM2198606", "GSM2198607", "GSM2198608", "GSM2198609", "GSM2198610", "GSM2198611", "GSM2198612", "GSM2198613", "GSM2198614", "GSM2198615", "GSM2198616", "GSM2198617", "GSM2198618", "GSM2198619", "GSM2198620", "GSM2198621", "GSM2198622", "GSM2198623", "GSM2198624", "GSM2198625", "GSM2198626", "GSM2198627", "GSM2198628", "GSM2198629", "GSM2198630", "GSM2198631", "GSM2198632", "GSM2198633", "GSM2198634", "GSM2198635", "GSM2198636", "GSM2198637", "GSM2198638", "GSM2198639", "GSM2198640", "GSM2198641", "GSM2198642", "GSM2198643", "GSM2198644", "GSM2198645", "GSM2198646", "GSM2198647", "GSM2198648", "GSM2198649", "GSM2198650", "GSM2198651", "GSM2198652", "GSM2198653", "GSM2198654", "GSM2198655"], "sample_count": 50, "group_sizes": null, "group_sizes_basis": null, "platform": "6480", "taxon": "Homo sapiens", "title": "Gene expression profiling of 50 glioblastoma multiforme tissue samples", "resolution_checked_at": "2026-11-01T15:39:55Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}], "gaps": ["asset:data:geo:GSE13041 not downloaded", "asset:data:geo:GSE13041 licence not read", "asset:data:geo:GSE16011 not downloaded", "asset:data:geo:GSE16011 licence not read", "asset:data:geo:GSE43378 not downloaded", "asset:data:geo:GSE43378 licence not read", "asset:data:geo:GSE4412 not downloaded", "asset:data:geo:GSE4412 licence not read", "asset:data:geo:GSE44971 not downloaded", "asset:data:geo:GSE44971 licence not read", "asset:data:geo:GSE68848 not downloaded", "asset:data:geo:GSE68848 licence not read", "asset:data:geo:GSE74187 not downloaded", "asset:data:geo:GSE74187 licence not read", "asset:data:geo:GSE83300 not downloaded", "asset:data:geo:GSE83300 licence not read"]}, "analysis": {"state": "partial", "methods": [{"id": "method-1", "family": "group_comparison", "specific": "student_t_test", "label": "Group comparison", "dsl_operations": [], "missing_operations": ["student_t"], "expressible": false, "parameters": {}, "data_shapes": ["two_or_more_groups_continuous"], "evidence": {"score": 1.0, "band": "verbatim", "quote": "The differentially expressed genes between LGG and GBM patients were determined using two tails paired Student's t test in TCGA, CGGA, GSE4412 and GSE43378 datasets."}}, {"id": "method-2", "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-3", "family": "diagnostic_evaluation", "specific": "roc", "label": "Diagnostic test evaluation", "dsl_operations": ["confusion_counts", "roc_curve", "sensitivity_specificity", "solve_confusion_matrix", "classification_metrics", "published_precision_envelope"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["reference_standard_and_test"], "evidence": {"score": 0.8, "band": "high", "quote": "ROC analysis"}}], "targets": [], "gaps": ["method.student_t"]}, "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": false, "required_operations": [], "missing_operations": ["student_t"], "basis": "The paper names the method it used and the corpus's method extractor maps it onto the DSL catalogue: student_t_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": ["GSE4412", "GSE43378", "GSE13041", "GSE44971", "GSE68848", "GSE74187", "GSE83300", "GSE16011"], "resolved_accessions": ["GSE4412", "GSE43378", "GSE13041", "GSE44971", "GSE68848", "GSE74187", "GSE83300", "GSE16011"], "statements": ["The gene expression, DNA methylation along with the clinical datasets of TCGA GBMLGG was downloaded from https://tcga.xenahubs.net website."], "basis": "The paper names GSE4412, GSE43378, GSE13041, GSE44971, GSE68848, GSE74187, GSE83300, GSE16011 in Gene Expression Omnibus (GEO) and the accession resolves in the repository. No dataset was downloaded and no licence was read."}}, "can_run": {"dsl_operations": [], "assets": ["source:pmid:34335936", "data:geo:GSE13041"], "steps": []}, "must_build": {"dsl_operations": [{"operation": "student_t", "unlocks_papers": null, "priority": null}], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE13041"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-10-31T18:33:10Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": null}, "calls": 3, "usage": {"prompt_tokens": 33561, "completion_tokens": 2571, "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:34335936", "type": "paper", "label": "pmid:34335936"}, {"id": "source:pmid:34335936", "type": "manuscript", "label": "PMID 34335936 full text"}, {"id": "data:geo:GSE13041", "type": "dataset", "label": "GEO GSE13041"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:34335936", "type": "paper", "label": "pmid:34335936"}, {"id": "source:pmid:34335936", "type": "manuscript", "label": "PMID 34335936 full text"}, {"id": "data:geo:GSE13041", "type": "dataset", "label": "GEO GSE13041"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-34335936", "type": "extraction", "used": ["source:pmid:34335936"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE13041", "type": "accession_resolution", "used": ["data:geo:GSE13041"], "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:34335936", "parent_hash": "sha256:984b05223d1bf11410c8a0658dbae7222daead15b14ae6f778b306aca730e06a", "fork_of": null, "generation": 7}, "gaps": ["asset:data:geo:GSE13041 licence not read", "asset:data:geo:GSE13041 not downloaded", "asset:data:geo:GSE16011 licence not read", "asset:data:geo:GSE16011 not downloaded", "asset:data:geo:GSE43378 licence not read", "asset:data:geo:GSE43378 not downloaded", "asset:data:geo:GSE4412 licence not read", "asset:data:geo:GSE4412 not downloaded", "asset:data:geo:GSE44971 licence not read", "asset:data:geo:GSE44971 not downloaded", "asset:data:geo:GSE68848 licence not read", "asset:data:geo:GSE68848 not downloaded", "asset:data:geo:GSE74187 licence not read", "asset:data:geo:GSE74187 not downloaded", "asset:data:geo:GSE83300 licence not read", "asset:data:geo:GSE83300 not downloaded", "execution.not_run", "method.student_t", "review.human_critique", "review.independent_reader", "review.machine_critique", "step:run_analysis blocked on method:student_t"], "assays": [{"role": "data_generation", "definition_id": "apoptosis_assay", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.99, "evidence": ["nctions of CDHR1 in glioma were tested using CCK-8 and trans-well assays. Results: CCDC109B, CD", "CO2. The cell proliferation was detected by CCK-8 assay. Briefly, A172 and U87 cells were seed", "ells were seeded in 96-well plate with 10 µL CCK-8 per well. The cell growth rate (OD450) was m"], "order_basis": "paper_text_order:494", "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": 0.77, "evidence": ["n Glioma cancer cell lines A172 and U87 were cultured in MEM medium (invitrogen) supplemented with 10"], "order_basis": "paper_text_order:2015", "id": "assay:2"}, {"role": "analysis", "definition_id": "group_comparison", "definition_version": "f2132e96ae6c7a4e", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"dsl_catalogue": "f2132e96ae6c7a4e"}, "confidence": 1.0, "evidence": ["The differentially expressed genes between LGG and GBM patients were determined using two tails paired Student's t test in TCGA, CGGA, GSE4412 and GSE43378 datasets."], "order_basis": "consumes_earlier_output", "id": "assay:3"}]},"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":"2026-11-04T01:36:22+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}}}