{"data":{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:35371305", "kind": "science-record", "revision": 3, "content_hash": "sha256:f55a946a5a21467b9b96ba4189c647895165665b55d4f142f6803d95c90e23fa", "created_at": "2026-11-01T18:14:11Z", "updated_at": "2026-11-01T21:27:34Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Identification and analysis of a prognostic ferroptosis and iron-metabolism signature for esophageal squamous cell carcinoma.", "doi": "10.7150/jca.68568", "pmid": "35371305", "authors": ["Mengnan Zhao", "Ming Li", "Yuansheng Zheng", "Zhengyang Hu", "Jiaqi Liang", "Guoshu Bi", "Yunyi Bian", "Qihai Sui", "Cheng Zhan", "Miao Lin", "Qun Wang"], "journal": "Journal of Cancer", "year": 2022, "abstract": "Background: The role of ferroptosis in esophageal squamous cell carcinoma (ESCC) is still unclear. Methods: The association of iron metabolism and ferroptosis-related genes with the prognosis, copy number variation (CNV), TMB, and immune cell infiltration of ESCC was explored using data from the GEO and TCGA database and validated by immunofluorescence in 112 ESCC patients from our center. The potential anti-cancer drugs and compounds from the GDSC and the Connectivity Map database were also screened. Results: A total of 117 iron metabolism and ferroptosis-related genes were identified. We found the expressions of PRNP, SLC3A2, SLC39A8, and SLC39A14 negatively related to the prognosis of ESCC patients, while ATP6V0A1 and LCN2 were opposite, which was validated in 112 ESCC samples from our center. And a prognostic signature was constructed based on their expressions and Cox regression coefficient (β). The low-score group exhibited a significantly worse OS. Besides, analysis of 179 ESCC samples from GSE53625 revealed that patients of poorly differentiation, more than 60 years, T4 stage, advanced N stage, advanced stage, and adjuvant therapy also exhibited a significantly shorter OS, based on which a nomogram to predict the OS was established. Moreover, the low-score group exhibited significantly higher CNV and TMB and more frequent mutations of TP53, MUC16, and NOTCH1. Higher proportion of Macrophages M2, and lower proportion of T cells follicular helper were observed in the low-score group. We discovered that AZD7762, Sunitinib, Cytarabine, Docetaxel, Vinblastine, and Elesclomol exhibited lower IC50 in the low-score group. And 20 potential compounds were identified from the CMap database. Conclusions: Six iron metabolism and ferroptosis-related genes were associated with the prognosis, CNV, TMB, and immune cell infiltration of ESCC. Some potential anti-cancer drugs and compounds may be helpful for OS.", "claims": [{"id": "claim-method", "statement": "The relation of the expression of DEGs to the prognosis of ESCC patients was analyzed with multivariate Cox regression, based on which a prognostic signature was constructed.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:35371305", "locator": "sections[6] \"Construction and functional analysis of iron metabolism and ferroptosis-related prognostic signature\" paragraph 2", "quote": "The relation of the expression of DEGs to the prognosis of ESCC patients was analyzed with multivariate Cox regression, based on which a prognostic signature was constructed."}], "state": "complete"}, {"id": "claim-data-access", "statement": "The expression data of ESCC and normal esophageal tissues were extracted from the GSE20347, GSE67269, and GSE38129 datasets.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:35371305", "locator": "sections[5] \"Identifying differentially expressed iron metabolism and ferroptosis-related genes (DEGs) between ESCC and normal esophageal tissues\" paragraph 2", "quote": "The expression data of ESCC and normal esophageal tissues were extracted from the GSE20347, GSE67269, and GSE38129 datasets."}], "state": "complete"}, {"id": "claim-target-result", "statement": "Six iron metabolism and ferroptosis-related genes were associated with the prognosis, CNV, TMB, and immune cell infiltration of ESCC.", "kind": "qualitative", "target": null, "evidence": [{"asset": "source:pmid:35371305", "locator": "sections[0] \"Abstract\" paragraph 4", "quote": "Conclusions: Six iron metabolism and ferroptosis-related genes were associated with the prognosis, CNV, TMB, and immune cell infiltration of ESCC."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "complete", "objective": "Six iron metabolism and ferroptosis-related genes were associated with the prognosis, CNV, TMB, and immune cell infiltration of ESCC.", "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:35371305"], "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:GSE20347"], "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:GSE20347"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:35371305", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.7150/jca.68568", "sha256": "sha256:0c22a4ae01ca0bee2fca1bcf12b693ba591cca233ab0cd02fbc418e3b94f982a", "bytes": 28564, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.7150/jca.68568", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC8965120", "source": "europe_pmc_fulltext", "coverage": "whole_body_without_references", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE20347", "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=GSE20347", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE20347", "version": null, "note": "The expression data of ESCC and normal esophageal tissues were extracted from the GSE20347, GSE67269, and GSE38129 datasets.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The expression data of ESCC and normal esophageal tissues were extracted from the GSE20347, GSE67269, and GSE38129 datasets.", "access_statement_kind": "repository_route_statement", "sample_accessions": ["GSM509787", "GSM509788", "GSM509789", "GSM509790", "GSM509791", "GSM509792", "GSM509793", "GSM509794", "GSM509795", "GSM509796", "GSM509797", "GSM509798", "GSM509799", "GSM509800", "GSM509801", "GSM509802", "GSM509803", "GSM509804", "GSM509805", "GSM509806", "GSM509807", "GSM509808", "GSM509809", "GSM509810", "GSM509811", "GSM509812", "GSM509813", "GSM509814", "GSM509815", "GSM509816", "GSM509817", "GSM509818", "GSM509819", "GSM509820"], "sample_count": 34, "group_sizes": null, "group_sizes_basis": null, "platform": "571", "taxon": "Homo sapiens", "title": "Analysis of gene expression in esophageal squamous cell carcinoma (ESCC)", "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:GSE38129", "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=GSE38129", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE38129", "version": null, "note": "The expression data of ESCC and normal esophageal tissues were extracted from the GSE20347, GSE67269, and GSE38129 datasets.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The expression data of ESCC and normal esophageal tissues were extracted from the GSE20347, GSE67269, and GSE38129 datasets.", "access_statement_kind": "repository_route_statement", "sample_accessions": ["GSM935144", "GSM935145", "GSM935146", "GSM935147", "GSM935148", "GSM935149", "GSM935150", "GSM935151", "GSM935152", "GSM935153", "GSM935154", "GSM935155", "GSM935156", "GSM935157", "GSM935158", "GSM935159", "GSM935160", "GSM935161", "GSM935162", "GSM935163", "GSM935164", "GSM935165", "GSM935166", "GSM935167", "GSM935168", "GSM935169", "GSM935170", "GSM935171", "GSM935172", "GSM935173", "GSM935174", "GSM935175", "GSM935176", "GSM935177", "GSM935178", "GSM935179", "GSM935180", "GSM935181", "GSM935182", "GSM935183", "GSM935184", "GSM935185", "GSM935186", "GSM935187", "GSM935188", "GSM935189", "GSM935190", "GSM935191", "GSM935192", "GSM935193", "GSM935194", "GSM935195", "GSM935196", "GSM935197", "GSM935198", "GSM935199", "GSM935200", "GSM935201", "GSM935202", "GSM935203"], "sample_count": 60, "group_sizes": null, "group_sizes_basis": null, "platform": "571", "taxon": "Homo sapiens", "title": "A pilot study of integrative genomics analysis of genes with biallelic loss and its relation to the expression of mRNA and micro-RNA in esophageal squamous cell cancer", "resolution_checked_at": "2026-11-01T15:39:54Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:GSE53625", "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=GSE53625", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE53625", "version": null, "note": "The expression data of ESCC and normal esophageal tissues were extracted from the GSE20347, GSE67269, and GSE38129 datasets.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The expression data of ESCC and normal esophageal tissues were extracted from the GSE20347, GSE67269, and GSE38129 datasets.", "access_statement_kind": "repository_route_statement", "sample_accessions": ["GSM1296956", "GSM1296957", "GSM1296958", "GSM1296959", "GSM1296960", "GSM1296961", "GSM1296962", "GSM1296963", "GSM1296964", "GSM1296965", "GSM1296966", "GSM1296967", "GSM1296968", "GSM1296969", "GSM1296970", "GSM1296971", "GSM1296972", "GSM1296973", "GSM1296974", "GSM1296975", "GSM1296976", "GSM1296977", "GSM1296978", "GSM1296979", "GSM1296980", "GSM1296981", "GSM1296982", "GSM1296983", "GSM1296984", "GSM1296985", "GSM1296986", "GSM1296987", "GSM1296988", "GSM1296989", "GSM1296990", "GSM1296991", "GSM1296992", "GSM1296993", "GSM1296994", "GSM1296995", "GSM1296996", "GSM1296997", "GSM1296998", "GSM1296999", "GSM1297000", "GSM1297001", "GSM1297002", "GSM1297003", "GSM1297004", "GSM1297005", "GSM1297006", "GSM1297007", "GSM1297008", "GSM1297009", "GSM1297010", "GSM1297011", "GSM1297012", "GSM1297013", "GSM1297014", "GSM1297015", "GSM1297016", "GSM1297017", "GSM1297018", "GSM1297019", "GSM1297020", "GSM1297021", "GSM1297022", "GSM1297023", "GSM1297024", "GSM1297025", "GSM1297026", "GSM1297027", "GSM1297028", "GSM1297029", "GSM1297030", "GSM1297031", "GSM1297032", "GSM1297033", "GSM1297034", "GSM1297035", "GSM1297036", "GSM1297037", "GSM1297038", "GSM1297039", "GSM1297040", "GSM1297041", "GSM1297042", "GSM1297043", "GSM1297044", "GSM1297045", "GSM1297046", "GSM1297047", "GSM1297048", "GSM1297049", "GSM1297050", "GSM1297051", "GSM1297052", "GSM1297053", "GSM1297054", "GSM1297055", "GSM1297056", "GSM1297057", "GSM1297058", "GSM1297059", "GSM1297060", "GSM1297061", "GSM1297062", "GSM1297063", "GSM1297064", "GSM1297065", "GSM1297066", "GSM1297067", "GSM1297068", "GSM1297069", "GSM1297070", "GSM1297071", "GSM1297072", "GSM1297073", "GSM1297074", "GSM1297075", "GSM1297076", "GSM1297077", "GSM1297078", "GSM1297079", "GSM1297080", "GSM1297081", "GSM1297082", "GSM1297083", "GSM1297084", "GSM1297085", "GSM1297086", "GSM1297087", "GSM1297088", "GSM1297089", "GSM1297090", "GSM1297091", "GSM1297092", "GSM1297093", "GSM1297094", "GSM1297095", "GSM1297096", "GSM1297097", "GSM1297098", "GSM1297099", "GSM1297100", "GSM1297101", "GSM1297102", "GSM1297103", "GSM1297104", "GSM1297105", "GSM1297106", "GSM1297107", "GSM1297108", "GSM1297109", "GSM1297110", "GSM1297111", "GSM1297112", "GSM1297113", "GSM1297114", "GSM1297115", "GSM1297116", "GSM1297117", "GSM1297118", "GSM1297119", "GSM1297120", "GSM1297121", "GSM1297122", "GSM1297123", "GSM1297124", "GSM1297125", "GSM1297126", "GSM1297127", "GSM1297128", "GSM1297129", "GSM1297130", "GSM1297131", "GSM1297132", "GSM1297133", "GSM1297134", "GSM1297135", "GSM1297136", "GSM1297137", "GSM1297138", "GSM1297139", "GSM1297140", "GSM1297141", "GSM1297142", "GSM1297143", "GSM1297144", "GSM1297145", "GSM1297146", "GSM1297147", "GSM1297148", "GSM1297149", "GSM1297150", "GSM1297151", "GSM1297152", "GSM1297153", "GSM1297154", "GSM1297155", "GSM1297156", "GSM1297157", "GSM1297158", "GSM1297159", "GSM1297160", "GSM1297161", "GSM1297162", "GSM1297163", "GSM1297164", "GSM1297165", "GSM1297166", "GSM1297167", "GSM1297168", "GSM1297169", "GSM1297170", "GSM1297171", "GSM1297172", "GSM1297173", "GSM1297174", "GSM1297175", "GSM1297176", "GSM1297177", "GSM1297178", "GSM1297179", "GSM1297180", "GSM1297181", "GSM1297182", "GSM1297183", "GSM1297184", "GSM1297185", "GSM1297186", "GSM1297187", "GSM1297188", "GSM1297189", "GSM1297190", "GSM1297191", "GSM1297192", "GSM1297193", "GSM1297194", "GSM1297195", "GSM1297196", "GSM1297197", "GSM1297198", "GSM1297199", "GSM1297200", "GSM1297201", "GSM1297202", "GSM1297203", "GSM1297204", "GSM1297205", "GSM1297206", "GSM1297207", "GSM1297208", "GSM1297209", "GSM1297210", "GSM1297211", "GSM1297212", "GSM1297213", "GSM1297214", "GSM1297215", "GSM1297216", "GSM1297217", "GSM1297218", "GSM1297219", "GSM1297220", "GSM1297221", "GSM1297222", "GSM1297223", "GSM1297224", "GSM1297225", "GSM1297226", "GSM1297227", "GSM1297228", "GSM1297229", "GSM1297230", "GSM1297231", "GSM1297232", "GSM1297233", "GSM1297234", "GSM1297235", "GSM1297236", "GSM1297237", "GSM1297238", "GSM1297239", "GSM1297240", "GSM1297241", "GSM1297242", "GSM1297243", "GSM1297244", "GSM1297245", "GSM1297246", "GSM1297247", "GSM1297248", "GSM1297249", "GSM1297250", "GSM1297251", "GSM1297252", "GSM1297253", "GSM1297254", "GSM1297255", "GSM1297256", "GSM1297257", "GSM1297258", "GSM1297259", "GSM1297260", "GSM1297261", "GSM1297262", "GSM1297263", "GSM1297264", "GSM1297265", "GSM1297266", "GSM1297267", "GSM1297268", "GSM1297269", "GSM1297270", "GSM1297271", "GSM1297272", "GSM1297273", "GSM1297274", "GSM1297275", "GSM1297276", "GSM1297277", "GSM1297278", "GSM1297279", "GSM1297280", "GSM1297281", "GSM1297282", "GSM1297283", "GSM1297284", "GSM1297285", "GSM1297286", "GSM1297287", "GSM1297288", "GSM1297289", "GSM1297290", "GSM1297291", "GSM1297292", "GSM1297293", "GSM1297294", "GSM1297295", "GSM1297296", "GSM1297297", "GSM1297298", "GSM1297299", "GSM1297300", "GSM1297301", "GSM1297302", "GSM1297303", "GSM1297304", "GSM1297305", "GSM1297306", "GSM1297307", "GSM1297308", "GSM1297309", "GSM1297310", "GSM1297311", "GSM1297312", "GSM1297313"], "sample_count": 358, "group_sizes": null, "group_sizes_basis": null, "platform": "18109", "taxon": "Homo sapiens", "title": "LncRNA profile study reveals a three-lncRNA signature associated with the survival of esophageal squamous cell carcinoma 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:GSE67269", "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=GSE67269", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE67269", "version": null, "note": "The expression data of ESCC and normal esophageal tissues were extracted from the GSE20347, GSE67269, and GSE38129 datasets.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The expression data of ESCC and normal esophageal tissues were extracted from the GSE20347, GSE67269, and GSE38129 datasets.", "access_statement_kind": "repository_route_statement", "sample_accessions": ["GSM1076726", "GSM1076727", "GSM1076728", "GSM1076729", "GSM1076730", "GSM1076731", "GSM1076732", "GSM1076733", "GSM1076734", "GSM1076735", "GSM1076736", "GSM1076737", "GSM1076738", "GSM1076739", "GSM1076740", "GSM1076741", "GSM1076742", "GSM1076743", "GSM1076744", "GSM1076745", "GSM1076746", "GSM1076747", "GSM1076748", "GSM1076749", "GSM1076750", "GSM1076751", "GSM1076752", "GSM1076753", "GSM1076754", "GSM1076755", "GSM1076756", "GSM1076757", "GSM1076758", "GSM1076759", "GSM1076760", "GSM1076761", "GSM1076762", "GSM1076763", "GSM1076764", "GSM1076765", "GSM1076766", "GSM1076767", "GSM1076768", "GSM1076769", "GSM1076770", "GSM1076771", "GSM1076772", "GSM1076773", "GSM1076774", "GSM1076775", "GSM1076776", "GSM1076777", "GSM1076778", "GSM1076779", "GSM1076780", "GSM1076781", "GSM1076782", "GSM1076783", "GSM1076784", "GSM1076785", "GSM1076786", "GSM1076787", "GSM1076788", "GSM1076789", "GSM1076790", "GSM1076791", "GSM1076792", "GSM1076793", "GSM1076794", "GSM1076795", "GSM1076796", "GSM1076797", "GSM1076798", "GSM1076799", "GSM1076800", "GSM1076801", "GSM1076802", "GSM1076803", "GSM1076804", "GSM1076805", "GSM1076806", "GSM1076807", "GSM1076808", "GSM1076809", "GSM1076810", "GSM1076811", "GSM1076812", "GSM1076813", "GSM1076814", "GSM1076815", "GSM1076816", "GSM1076817", "GSM1076818", "GSM1076819", "GSM1076820", "GSM1076821", "GSM1076822", "GSM1076823", "GSM1076824", "GSM1076825", "GSM1076826", "GSM1076827", "GSM1076828", "GSM1076829", "GSM1076830", "GSM1076831", "GSM1076832", "GSM1076833", "GSM1076834", "GSM1076835", "GSM1076836", "GSM1076837", "GSM1076838", "GSM1076839", "GSM1076840", "GSM1076841", "GSM1076842", "GSM1076843", "GSM1076844", "GSM1076845", "GSM1076846", "GSM1076847", "GSM1076848", "GSM1076849", "GSM1076850", "GSM1076851", "GSM1076852", "GSM1076853", "GSM1076854", "GSM1076855", "GSM1076856", "GSM1076857", "GSM1076858", "GSM1076859", "GSM1076860", "GSM1076861", "GSM1076862", "GSM1076863", "GSM1076864", "GSM1076865", "GSM1076866", "GSM1076867", "GSM1076868", "GSM1076869", "GSM1076870", "GSM1076871", "GSM1076872", "GSM1076873", "GSM1076874", "GSM1076875", "GSM1076876", "GSM1076877", "GSM1076878", "GSM1076879", "GSM1076880", "GSM1076881", "GSM1076882", "GSM1076883", "GSM1076884", "GSM1076885", "GSM1076886", "GSM1076887", "GSM1076888", "GSM1076889", "GSM1076890", "GSM1076891", "GSM1076892", "GSM1076893", "GSM1076894", "GSM1076895", "GSM1076896", "GSM1076897", "GSM1076898", "GSM1076899", "GSM1076900", "GSM1076901", "GSM1076902", "GSM1076903", "GSM1076904", "GSM1076905", "GSM1076906", "GSM1076907", "GSM1076908", "GSM1076909", "GSM1076910", "GSM1076911", "GSM1076912", "GSM1076913", "GSM1076914", "GSM1076915", "GSM1076916", "GSM1076917", "GSM1076918", "GSM1076919", "GSM1076920", "GSM1076921", "GSM1076922", "GSM1076923", "GSM1076924", "GSM1076925", "GSM1076926", "GSM1076927", "GSM1076928", "GSM1076929", "GSM1076930", "GSM1076931", "GSM1076932", "GSM1076933", "GSM1076934", "GSM1076935", "GSM1076936", "GSM1076937", "GSM1076938", "GSM1076939", "GSM1076940", "GSM1076941", "GSM1076942", "GSM1076943", "GSM1076944", "GSM1076945", "GSM1076946", "GSM1076947", "GSM1076948", "GSM1076949", "GSM1076950", "GSM1076951", "GSM1643294", "GSM1643295", "GSM1643296", "GSM1643297", "GSM1643298", "GSM1643299", "GSM1643300", "GSM1643301", "GSM1643302", "GSM1643303", "GSM1643304", "GSM1643305", "GSM1643306", "GSM1643307", "GSM1643308", "GSM1643309", "GSM1643310", "GSM1643311", "GSM1643312", "GSM1643313", "GSM1643314", "GSM1643315", "GSM1643316", "GSM1643317", "GSM1643318", "GSM1643319", "GSM1643320", "GSM1643321", "GSM1643322", "GSM1643323", "GSM1643324", "GSM1643325", "GSM1643326", "GSM1643327", "GSM1643328", "GSM1643329", "GSM1643330", "GSM1643331", "GSM1643332", "GSM1643333", "GSM1643334", "GSM1643335", "GSM1643336", "GSM1643337", "GSM1643338", "GSM1643339", "GSM1643340", "GSM1643341", "GSM1643342", "GSM1643343", "GSM1643344", "GSM1643345", "GSM1643346", "GSM1643347", "GSM1643348", "GSM1643349", "GSM1643350", "GSM1643351", "GSM1643352", "GSM1643353", "GSM1643354", "GSM1643355", "GSM1643356", "GSM1643357", "GSM1643358", "GSM1643359", "GSM1643360", "GSM1643361", "GSM1643362", "GSM1643363", "GSM1643364", "GSM1643365", "GSM1643366", "GSM1643367", "GSM1643368", "GSM1643369", "GSM1643370", "GSM1643371", "GSM1643372", "GSM1643373", "GSM1643374", "GSM1643375", "GSM1643376", "GSM1643377", "GSM1643378", "GSM1643379", "GSM1643380", "GSM1643381", "GSM1643382", "GSM1643383", "GSM1643384", "GSM1643385", "GSM1643386", "GSM1643387", "GSM1643388", "GSM1643389", "GSM1643390", "GSM1643391", "GSM1643392", "GSM1643393", "GSM1643394", "GSM1643395", "GSM1643396", "GSM1643397", "GSM1643398", "GSM1643399", "GSM1643400", "GSM1643401", "GSM1643402", "GSM1643403", "GSM1643404", "GSM1643405", "GSM1643406", "GSM1643407", "GSM1643408", "GSM1643409", "GSM1643410", "GSM1643411", "GSM1643412", "GSM1643413", "GSM1643414", "GSM1643415", "GSM1643416", "GSM1643417", "GSM1643418", "GSM1643419", "GSM1643420", "GSM1643421", "GSM1643422", "GSM1643423", "GSM1643424", "GSM1643425", "GSM1643426", "GSM1643427", "GSM1643428", "GSM1643429", "GSM1643430", "GSM1643431", "GSM1643432", "GSM1643433", "GSM1643434", "GSM1643435", "GSM1643436", "GSM1643437", "GSM1643438", "GSM1643439", "GSM1643440", "GSM1643441", "GSM1643442", "GSM1643443", "GSM1643444", "GSM1643445", "GSM1643446", "GSM1643447", "GSM1643448", "GSM1643449", "GSM1643450", "GSM1643451", "GSM1643452", "GSM1643453", "GSM1643454", "GSM1643455", "GSM1643456", "GSM1643457", "GSM1643458", "GSM1643459", "GSM1643460", "GSM1643461", "GSM1643462", "GSM1643463", "GSM1643464", "GSM1643465", "GSM1643466", "GSM1643467", "GSM1643468", "GSM1643469", "GSM1643470", "GSM1643471", "GSM1643472", "GSM1643473", "GSM1643474", "GSM1643475", "GSM1643476", "GSM1643477", "GSM1643478", "GSM1643479", "GSM1643480", "GSM1643481", "GSM1643482", "GSM1643483", "GSM1643484", "GSM1643485", "GSM1643486", "GSM1643487", "GSM1643488", "GSM1643489", "GSM1643490", "GSM1643491", "GSM1643492", "GSM1643493", "GSM1643494", "GSM1643495", "GSM1643496", "GSM1643497", "GSM1643498", "GSM1643499", "GSM1643500", "GSM1643501", "GSM1643502", "GSM1643503", "GSM1643504", "GSM1643505", "GSM1643506", "GSM1643507", "GSM1643508", "GSM1643509", "GSM1643510", "GSM1643511", "GSM1643512", "GSM1643513", "GSM1643514", "GSM1643515", "GSM1643516", "GSM1643517", "GSM1643518", "GSM1643519"], "sample_count": 452, "group_sizes": null, "group_sizes_basis": null, "platform": "571;96;19823;570", "taxon": "Homo sapiens", "title": "Integrative analysis of miRNAs and matched gene expression in ESCC", "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:GSE20347 not downloaded", "asset:data:geo:GSE20347 licence not read", "asset:data:geo:GSE38129 not downloaded", "asset:data:geo:GSE38129 licence not read", "asset:data:geo:GSE53625 not downloaded", "asset:data:geo:GSE53625 licence not read", "asset:data:geo:GSE67269 not downloaded", "asset:data:geo:GSE67269 licence not read"]}, "analysis": {"state": "complete", "methods": [{"id": "method-1", "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": 1.0, "band": "verbatim", "quote": "The relation of the expression of DEGs to the prognosis of ESCC patients was analyzed with multivariate Cox regression, based on which a prognostic signature was constructed."}}], "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": ["cox_ph"], "missing_operations": [], "basis": "The paper names the method it used and the corpus's method extractor maps it onto the DSL catalogue: cox_proportional_hazards."}, "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": ["GSE20347", "GSE67269", "GSE38129", "GSE53625"], "resolved_accessions": ["GSE20347", "GSE67269", "GSE38129", "GSE53625"], "statements": ["The expression data of ESCC and normal esophageal tissues were extracted from the GSE20347, GSE67269, and GSE38129 datasets."], "basis": "The paper names GSE20347, GSE67269, GSE38129, GSE53625 in Gene Expression Omnibus (GEO) database and the accession resolves in the repository. No dataset was downloaded and no licence was read."}}, "can_run": {"dsl_operations": ["cox_ph"], "assets": ["source:pmid:35371305", "data:geo:GSE20347"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE20347"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-11-01T17:40:42Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": null}, "calls": 5, "usage": {"prompt_tokens": 8773, "completion_tokens": 2618, "cached_tokens": 128}}, "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:35371305", "type": "paper", "label": "pmid:35371305"}, {"id": "source:pmid:35371305", "type": "manuscript", "label": "PMID 35371305 full text"}, {"id": "data:geo:GSE20347", "type": "dataset", "label": "GEO GSE20347"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:35371305", "type": "paper", "label": "pmid:35371305"}, {"id": "source:pmid:35371305", "type": "manuscript", "label": "PMID 35371305 full text"}, {"id": "data:geo:GSE20347", "type": "dataset", "label": "GEO GSE20347"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-35371305", "type": "extraction", "used": ["source:pmid:35371305"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE20347", "type": "accession_resolution", "used": ["data:geo:GSE20347"], "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:35371305", "parent_hash": "sha256:8fb0ffb36f5e054580fff65166b7835cc28597233e0deaa5e2902eb1cdcac7eb", "fork_of": null, "generation": 2}, "gaps": ["asset:data:geo:GSE20347 licence not read", "asset:data:geo:GSE20347 not downloaded", "asset:data:geo:GSE38129 licence not read", "asset:data:geo:GSE38129 not downloaded", "asset:data:geo:GSE53625 licence not read", "asset:data:geo:GSE53625 not downloaded", "asset:data:geo:GSE67269 licence not read", "asset:data:geo:GSE67269 not downloaded", "execution.not_run", "review.human_critique", "review.independent_reader", "review.machine_critique"], "assays": [{"role": "data_generation", "definition_id": "clinical_cohort", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.99, "evidence": ["he \"survminer\" R package, based on which the patients were divided into low- and high-score group 10. T", "al cut-off score, based on which the 96 ESCC patients were divided into high- and low-score group. The"], "order_basis": "paper_text_order:2766", "id": "assay:1"}, {"role": "data_generation", "definition_id": "transfection", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.99, "evidence": ["g/gsea/index.jsp) 11. Cell culture and siRNA transfection Two ESCC cell lines (KYSE150 and ECA109) wer", "uangzhou, China) (Table S1). The siRNAs were transfected into cells with Lipo8000 transfect reagent (", "essions of the above 6 prognostic genes were knock-down with 2 diiferent small interfering RNAs (siR", "gdb.org/gsea/index.jsp) 11. Cell culture and siRNA transfection Two ESCC cell lines (KYSE150 an"], "order_basis": "paper_text_order:3191", "id": "assay:2"}, {"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": ["the Chinese Academy of Science Cell Bank and cultured with Dulbecco's Modified Eagle's Medium (Hyclone,"], "order_basis": "paper_text_order:3316", "id": "assay:3"}, {"role": "analysis", "definition_id": "survival_analysis", "definition_version": "f2132e96ae6c7a4e", "definition_digest": null, "required_operations": ["cox_ph"], "support_state": "supported", "source_hashes": {"dsl_catalogue": "f2132e96ae6c7a4e"}, "confidence": 1.0, "evidence": ["The relation of the expression of DEGs to the prognosis of ESCC patients was analyzed with multivariate Cox regression, based on which a prognostic signature was constructed."], "order_basis": "consumes_earlier_output", "id": "assay:4"}]},"meta":{"api_version":"v1","automation_ladder_snapshot":"ba34b49490d9bfaf","automation_ladder_caveats":["Method extraction is rule-based and has no hand-judged accuracy sample. Evidence bands order textual support; method agreement intervals are null (n=0), never probabilities. Work-type validation does not validate methods.","Operation coverage describes only explicitly named methods. It does not prove a complete protocol, compatible parameters, successful compilation or re-execution. Unrecognised or ambiguous methods require review.","Data reachability is a textual accession or public-data statement. No dataset was downloaded or checked for access, completeness or licence.","Capabilities are planning states seeded from the dated equipment register. No bench ownership, completed quote or partner booking is inferred. Procurement counts are dependencies, not guaranteed replications or financial returns.","Tier and blocker counts are deterministic assessments of this corpus, not measured agreement. R3 is reserved for procurement; unresolved methods and data require human work (R4). The most restrictive axis wins, with capability, method, data as tie-breaks. Resolving one blocker can leave another at the same tier."],"engine":"corpus_engine","engine_provider":"rule_based_v1+lex99e1195c7d6f","run_id":"run-20261023T122449232913","source":"esearch","source_detail":"PubMed mirror biomed_pubmed (read-only)","run_status":"complete","imported_at":"2026-11-03T20:16:52+00:00","generated_at":"2026-11-04T02:38:44+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}}}