{"data":{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:34335950", "kind": "science-record", "revision": 9, "content_hash": "sha256:9901a7cdc23a692a68695a55a85ec6d3d8f34f48a90711358cf96a9a396b24c5", "created_at": "2026-11-01T15:41:46Z", "updated_at": "2026-11-01T22:47:14Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Dyslipidemia in Chinese Pancreatic Cancer Patients: A Two-Center Retrospective Study.", "doi": "10.7150/jca.60340", "pmid": "34335950", "authors": ["Feiyang Wang", "Li Huang", "Jinyan Zhang", "Junwei Fan", "Heshui Wu", "Junming Xu"], "journal": "Journal of Cancer", "year": 2021, "abstract": "Background: Pancreatic cancer (PC) is one of the most aggressive and lethal malignancies in the world. High cholesterol intake may have a certain association with an elevated risk of PC, though dyslipidemia in PC patients has rarely been reported. In this study, we compared serum lipids levels between PC and non-PC tumor patients and assessed their prognostic value in PC. Methods: 271 patients treated at Wuhan Union Hospital from January 2012 to December 2016 and 204 individuals at Shanghai General Hospital from January 2018 to December 2019 were recruited. Their demographic parameters, laboratory data, pathological information, and clinical outcomes were extracted and analyzed. The mRNA expressions of related lipoprotein, low density lipoprotein receptor (LDLR) and high density lipoprotein binding protein (HDLBP), in PC tissues and paired noncancerous tissues and follow-up information were assessed based on the GEO database (GSE15471 and GSE62165) and TCGA database. Results: A total of 172 non-PC tumor patients and 260 PC patients were finally eligible for our analysis. PC patients exhibited higher levels of serum triglyceride, cholesterol, and low-density lipoprotein (LDL) and a lower serum high-density lipoprotein (HDL) level on admission versus the non-PC tumor group. In PC patients, LDLR mRNA expression was upregulated, and HDLBP mRNA expression was downregulated in cancerous tissues compared to these levels in paired noncancerous tissues. The survival analysis revealed that dyslipidemia had a non-significant association with a poor prognosis, but PC patients with a high LDLR level were at risk of poor survival. Conclusion: Dyslipidemia is detected in PC patients but has a non-significant relation to PC prognosis. However, LDLR may be a potential predictive marker for PC prognosis.", "claims": [{"id": "claim-data-access", "statement": "The mRNA expression data of GSE15471 (39 matched pairs of samples) and GSE62165 (118 PC tissue samples and 13 paracancerous tissue samples) were acquired to identify differential target genes of related lipoprotein in PC.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:34335950", "locator": "sections[4] \"Microarray data collection\" paragraph 2", "quote": "The mRNA expression data of GSE15471 (39 matched pairs of samples) and GSE62165 (118 PC tissue samples and 13 paracancerous tissue samples) were acquired to identify differential target genes of related lipoprotein in PC."}], "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:34335950"], "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:GSE15471"], "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:GSE15471"], "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:34335950", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.7150/jca.60340", "sha256": "sha256:d50b87f937c9eadaf04f869b79f092382ea9bae3d5c891610aa3add3e70ed174", "bytes": 23694, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.7150/jca.60340", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC8317532", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE15471", "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=GSE15471", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE15471", "version": null, "note": "The mRNA expression data of GSE15471 (39 matched pairs of samples) and GSE62165 (118 PC tissue samples and 13 paracancerous tissue samples) were acquired to identify differential target genes of related lipoprotein in PC.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The mRNA expression data of GSE15471 (39 matched pairs of samples) and GSE62165 (118 PC tissue samples and 13 paracancerous tissue samples) were acquired to identify differential target genes of related lipoprotein in PC.", "access_statement_kind": "repository_route_statement", "sample_accessions": ["GSM388076", "GSM388077", "GSM388078", "GSM388079", "GSM388080", "GSM388081", "GSM388082", "GSM388083", "GSM388084", "GSM388085", "GSM388086", "GSM388087", "GSM388088", "GSM388089", "GSM388090", "GSM388091", "GSM388092", "GSM388093", "GSM388094", "GSM388095", "GSM388096", "GSM388097", "GSM388098", "GSM388099", "GSM388100", "GSM388101", "GSM388102", "GSM388103", "GSM388104", "GSM388105", "GSM388106", "GSM388107", "GSM388108", "GSM388109", "GSM388110", "GSM388111", "GSM388112", "GSM388113", "GSM388114", "GSM388115", "GSM388116", "GSM388117", "GSM388118", "GSM388119", "GSM388120", "GSM388121", "GSM388122", "GSM388123", "GSM388124", "GSM388125", "GSM388126", "GSM388127", "GSM388128", "GSM388129", "GSM388130", "GSM388131", "GSM388132", "GSM388133", "GSM388134", "GSM388135", "GSM388136", "GSM388137", "GSM388138", "GSM388139", "GSM388140", "GSM388141", "GSM388142", "GSM388143", "GSM388144", "GSM388145", "GSM388146", "GSM388147", "GSM388148", "GSM388149", "GSM388150", "GSM388151", "GSM388152", "GSM388153"], "sample_count": 78, "group_sizes": null, "group_sizes_basis": null, "platform": "570", "taxon": "Homo sapiens", "title": "Whole-Tissue Gene Expression Study of Pancreatic Ductal Adenocarcinoma", "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:GSE62165", "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=GSE62165", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE62165", "version": null, "note": "The mRNA expression data of GSE15471 (39 matched pairs of samples) and GSE62165 (118 PC tissue samples and 13 paracancerous tissue samples) were acquired to identify differential target genes of related lipoprotein in PC.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The mRNA expression data of GSE15471 (39 matched pairs of samples) and GSE62165 (118 PC tissue samples and 13 paracancerous tissue samples) were acquired to identify differential target genes of related lipoprotein in PC.", "access_statement_kind": "repository_route_statement", "sample_accessions": ["GSM1520738", "GSM1520739", "GSM1520740", "GSM1520741", "GSM1520742", "GSM1520743", "GSM1520744", "GSM1520745", "GSM1520746", "GSM1520747", "GSM1520748", "GSM1520749", "GSM1520750", "GSM1520751", "GSM1520752", "GSM1520753", "GSM1520754", "GSM1520755", "GSM1520756", "GSM1520757", "GSM1520758", "GSM1520759", "GSM1520760", "GSM1520761", "GSM1520762", "GSM1520763", "GSM1520764", "GSM1520765", "GSM1520766", "GSM1520767", "GSM1520768", "GSM1520769", "GSM1520770", "GSM1520771", "GSM1520772", "GSM1520773", "GSM1520774", "GSM1520775", "GSM1520776", "GSM1520777", "GSM1520778", "GSM1520779", "GSM1520780", "GSM1520781", "GSM1520782", "GSM1520783", "GSM1520784", "GSM1520785", "GSM1520786", "GSM1520787", "GSM1520788", "GSM1520789", "GSM1520790", "GSM1520791", "GSM1520792", "GSM1520793", "GSM1520794", "GSM1520795", "GSM1520796", "GSM1520797", "GSM1520798", "GSM1520799", "GSM1520800", "GSM1520801", "GSM1520802", "GSM1520803", "GSM1520804", "GSM1520805", "GSM1520806", "GSM1520807", "GSM1520808", "GSM1520809", "GSM1520810", "GSM1520811", "GSM1520812", "GSM1520813", "GSM1520814", "GSM1520815", "GSM1520816", "GSM1520817", "GSM1520818", "GSM1520819", "GSM1520820", "GSM1520821", "GSM1520822", "GSM1520823", "GSM1520824", "GSM1520825", "GSM1520826", "GSM1520827", "GSM1520828", "GSM1520829", "GSM1520830", "GSM1520831", "GSM1520832", "GSM1520833", "GSM1520834", "GSM1520835", "GSM1520836", "GSM1520837", "GSM1520838", "GSM1520839", "GSM1520840", "GSM1520841", "GSM1520842", "GSM1520843", "GSM1520844", "GSM1520845", "GSM1520846", "GSM1520847", "GSM1520848", "GSM1520849", "GSM1520850", "GSM1520851", "GSM1520852", "GSM1520853", "GSM1520854", "GSM1520855", "GSM1520856", "GSM1520857", "GSM1520858", "GSM1520859", "GSM1520860", "GSM1520861", "GSM1520862", "GSM1520863", "GSM1520864", "GSM1520865", "GSM1520866", "GSM1520867", "GSM1520868"], "sample_count": 131, "group_sizes": null, "group_sizes_basis": null, "platform": "13667", "taxon": "Homo sapiens", "title": "Prognostic relevance of molecular subtypes and master regulators in pancreatic ductal adenocarcinoma", "resolution_checked_at": "2026-11-01T15:39:55Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "asset:table:pmid:34335950:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:9f8c8d63f6a282a2dc2a4427efeb6b598ab46a40fa5d30da237fd4ac9a0271df", "bytes": 2821, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[7]/table-wrap[1]#T1", "version": null, "note": "Demographic characteristics and laboratory data of patients with PC and non-PC tumor", "structure": {"pmcid": "PMC8317532", "section_index": 7, "section_title": "Clinical features, laboratory data, and serum lipids levels between PC versus non-PC tumors", "row_count": 37, "column_count": 6}, "table": {"label": "Table 1", "caption": "Demographic characteristics and laboratory data of patients with PC and non-PC tumor", "rows": [["Characteristics", "", "Pancreatic cancer", "", "non-PC tumor", "P-value"], ["Age, years", "Σ260", "60.48±10.77", "Σ172", "53.29±14.41", "<0.001"], ["Gender, male", "Σ260", "167 (64.2%)", "Σ172", "87 (50.6%)", "0.005"], ["Smoke", "Σ260", "62 (23.8%)", "Σ172", "34 (19.8%)", "0.319"], ["Alcohol", "Σ260", "51 (19.6%)", "Σ172", "18 (10.5%)", "0.011"], ["BMI index, kg/m2", "Σ260", "22.17±3.23", "Σ172", "22.32±3.03", "0.639"], ["Comorbidities", "", "", "", "", "0.545"], ["Circulatory system diseases", "Σ260", "69 (26.5%)", "Σ172", "41 (23.8%)", ""], ["Metablolic diseases", "Σ260", "53 (20.4%)", "Σ172", "24 (14.0%)", ""], ["Chornic inflammation", "Σ260", "18 (6.9%)", "Σ172", "17 (9.9%)", ""], ["Other malignant tumor", "Σ260", "8 (3.1%)", "Σ172", "4 (2.3%)", ""], ["Symptom", "", "", "", "", "<0.001"], ["Abdominal pain", "Σ260", "146 (56.2%)", "Σ172", "60 (34.9%)", ""], ["Jaundice", "Σ260", "95 (36.5%)", "Σ172", "8 (4.7%)", ""], ["Asymptomatic", "Σ260", "31 (11.9%)", "Σ172", "90 (52.3%)", ""], ["Others", "Σ260", "18 (6.9%)", "Σ172", "17 (9.9%)", ""], ["Laboratory data", "", "", "", "", ""], ["White cell count, ×109/L", "Σ255", "5.62±1.62", "Σ172", "5.86±1.93", "0.168"], ["Hemoglobin, g/L", "Σ255", "123.97±17.20", "Σ172", "129.39±17.58", "0.002"], ["Platelet count, ×109/L", "Σ255", "214.12±74.61", "Σ172", "208.09±75.13", "0.414"], ["Total bilirubin, μmol/L", "Σ255", "102.54±118.77", "Σ171", "22.38±49.9", "<0.001"], ["Alanine aminotransferase, U/L", "Σ254", "140.89±176.78", "Σ171", "42.90±85.03", "<0.001"], ["Albumin, g/L", "Σ255", "39.21±5.21", "Σ170", "41.05±5.24", "<0.001"], ["Creatinine, μmol/L", "Σ255", "62.38±15.50", "Σ171", "61.68±16.38", "0.657"], ["Serum glucose, mmol/L", "Σ250", "6.72±2.69", "Σ165", "5.61±1.90", "<0.001"], ["Prothrombin time, s", "Σ252", "12.38±1.54", "Σ170", "12.12±1.54", "0.085"], ["Activated partial thromboplastin time, s", "Σ251", "33.91±6.80", "Σ169", "32.36±6.41", "0.020"], ["CA199, U/ml", "Σ238", "450.23±493.76", "Σ163", "32.19±107.84", "<0.001"], ["Serum lipids level", "", "", "", "", ""], ["Triglyceride, mmol/L", "Σ242", "1.82±1.37", "Σ157", "1.41±1.01", "0.001"], ["Cholesterol, mmol/L", "Σ242", "4.93±2.35", "Σ158", "4.36±1.18", "0.005"], ["High density lipoprotein, mmol/L", "Σ231", "0.98±0.49", "Σ147", "1.17±0.39", "<0.001"], ["Low density lipoprotein, mmol/L", "Σ229", "2.97±1.67", "Σ146", "2.50±1.09", "0.003"], ["Lipoprotein a, mmol/L", "Σ82", "207.22±361.98", "Σ80", "264.99±444.73", "0.365"], ["Apolipoprotein A1, g/L", "Σ82", "1.11±0.38", "Σ81", "1.29±0.29", "0.001"], ["Apolipoprotein B, g/L", "Σ82", "0.88±0.35", "Σ81", "0.76±0.22", "0.007"], ["Apolipoprotein E, mg/L", "Σ82", "64.21±58.59", "Σ81", "35.62±23.89", "<0.001"]], "row_count": 37, "column_count": 6, "numeric_cells": 157, "header_rows": 1, "locator": "section[7]/table-wrap[1]#T1"}}, {"id": "asset:table:pmid:34335950:2", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:d50bf1f575c5c31bd6b436d1efeb0137125fc7817000ecd490a0e1a3ff438273", "bytes": 1280, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[8]/table-wrap[1]#T2", "version": null, "note": "Logistic regression analysis of risk factors for PC", "structure": {"pmcid": "PMC8317532", "section_index": 8, "section_title": "Logistic regression analysis of risk factors for PC", "row_count": 16, "column_count": 5}, "table": {"label": "Table 2", "caption": "Logistic regression analysis of risk factors for PC", "rows": [["", "Univariable analysis", "Multivariable analysis"], ["Odd ratio (95% CI)", "P value", "Odd ratio (95% CI)", "P value"], ["Sex, male", "0.57 (0.39, 0.84)", "0.005", "", ""], ["Age, ≥60 years", "1.89 (1.27, 2.82)", "0.002", "", ""], ["Alcohol", "2.09 (1.17, 3.72)", "0.012", "", ""], ["Hemoglobin, <120 g/L", "1.91 (1.23, 2.97)", "0.004", "", ""], ["Total bilirubin, >17.1 μmol/L", "8.30 (5.05, 13.64)", "<0.001", "2.88 (1.39, 5.97)", "0.004"], ["Alanine aminotransferase, >50 U/L", "6.58 (4.21, 10.29)", "<0.001", "3.46 (1.55, 7.69)", "0.002"], ["Albumin, <35 g/L", "1.27 (0.72, 2.24)", "0.417", "", ""], ["Serum glucose, >7.0 mmol/L", "2.45 (1.47, 4.08)", "0.001", "", ""], ["Activated partial thromboplastin time, >40 s", "1.21 (0.68, 2.14)", "0.521", "", ""], ["CA199, >25 U/ml", "18.78 (11.30, 31.22)", "<0.001", "10.87 (5.97, 19.80)", "<0.001"], ["Triglyceride, >1.7 mmol/L", "1.82 (1.18, 2.81)", "0.007", "", ""], ["Cholesterol, >5.18 mmol/L", "2.10 (1.28, 3.45)", "0.003", "", ""], ["High density lipoprotein, <1.16 mmol/L", "1.74 (1.13, 2.67)", "0.012", "", ""], ["Low density lipoprotein, >4.14 mmol/L", "3.10 (1.25, 7.69)", "0.015", "", ""]], "row_count": 16, "column_count": 5, "numeric_cells": 48, "header_rows": 2, "locator": "section[8]/table-wrap[1]#T2"}}, {"id": "asset:table:pmid:34335950:3", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:0ac533140f049f2821bbbbd4801d84573696f107654d3a6e94d8170e154952df", "bytes": 2681, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[9]/table-wrap[1]#T3", "version": null, "note": "Clinicopathological and follow-up information of PC patients in different lipid level", "structure": {"pmcid": "PMC8317532", "section_index": 9, "section_title": "Clinicopathological features and survival analysis between PC patients with different lipid levels", "row_count": 21, "column_count": 13}, "table": {"label": "Table 3", "caption": "Clinicopathological and follow-up information of PC patients in different lipid level", "rows": [["", "High CHOL", "Low CHOL", "P value", "High TG", "Low TG", "P value", "Low HDL", "High HDL", "P value", "High LDL", "Low LDL", "P value"], ["Tumor size, cm", "73", "164", "<0.001", "96", "141", "0.057", "158", "69", "0.869", "27", "201", "<0.001"], ["", "2.91±1.04", "3.63±1.48", "", "3.20±1.24", "3.55±1.47", "", "3.37±1.41", "3.40±1.38", "", "3.50±1.40", "2.55±1.00", ""], ["Operation type", "73", "169", "0.143", "97", "145", "0.102", "162", "69", "0.124", "27", "202", "0.218"], ["Radical resection", "71 (97.3%)", "156 (92.3%)", "", "94 (96.9%)", "133 (91.7%)", "", "152 (93.8%)", "68 (98.6%)", "", "27 (100.0%)", "191 (94.6%)", ""], ["Palliative resection", "2 (2.7%)", "13 (7.7%)", "", "3 (3.1%)", "12 (8.3%)", "", "10 (6.2%)", "1 (1.4%)", "", "0 (0.0%)", "11 (5.4%)", ""], ["AJCC stage", "73", "169", "0.055", "97", "145", "0.074", "162", "69", "0.246", "27", "202", "0.961"], ["Stage I, II", "56 (76.7%)", "113 (66.9%)", "", "74 (76.3%)", "95 (65.5%)", "", "118 (72.8%)", "45 (65.2%)", "", "20 (74.1%)", "141 (69.8%)", ""], ["Stage III, IV", "17 (23.3%)", "56 (33.1%)", "", "23 (23.7%)", "50 (34.5%)", "", "44 (27.2%)", "24 (34.8%)", "", "7 (25.9%)", "61 (30.2%)", ""], ["Differentiation degree", "67", "143", "0.601", "86", "128", "0.394", "146", "62", "0.186", "25", "178", "0.417"], ["Well", "13 (19.4%)", "27 (18.9%)", "", "15 (17.4%)", "25 (19.5%)", "", "27 (18.5%)", "12 (19.4%)", "", "7 (28.0%)", "31 (17.4%)", ""], ["Moderate", "36 (53.7%)", "71 (49.7%)", "", "41 (47.7%)", "66 (51.6%)", "", "68 (46.6%)", "36 (58.1%)", "", "11 (44.0%)", "93 (52.2%)", ""], ["Poor", "18 (26.9%)", "45 (31.5%)", "", "30 (34.9%)", "37 (28.9%)", "", "51 (34.9%)", "14 (22.6%)", "", "7 (28.0%)", "54 (30.3%)", ""], ["Nerve invasion", "67", "148", "0.574", "89", "126", "0.664", "142", "66", "0.977", "26", "180", "0.269"], ["", "37 (55.2%)", "80 (54.1%)", "", "50 (56.2%)", "67 (53.2%)", "", "75 (52.8%)", "35 (53.0%)", "", "13 (50.0%)", "96 (53.3%)", ""], ["Vascular invasion", "68", "148", "0.874", "90", "126", "0.977", "143", "66", "0.140", "26", "181", "0.753"], ["", "12 (17.6%)", "31 (20.9%)", "", "18 (20.0%)", "25 (19.8%)", "", "32 (22.4%)", "9 (13.6%)", "", "3 (11.5%)", "37 (20.4%)", ""], ["Follow-up, months", "73", "169", "0.083", "97", "145", "0.846", "162", "69", "0.065", "27", "202", "0.009"], ["", "80.99±69.65", "64.86±64.57", "", "70.74±63.92", "69.04±68.24", "", "66.57±62.13", "84.38±76.74", "", "102.67±67.72", "67.98±66.36", ""], ["Disease related death", "73", "169", "0.959", "97", "145", "0.774", "162", "69", "0.397", "27", "202", "0.991"], ["", "40 (54.8%)", "92 (54.4%)", "", "54 (55.7%)", "78 (53.8%)", "", "92 (56.8%)", "35 (50.7%)", "", "15 (55.6%)", "112 (55.4%)", ""]], "row_count": 21, "column_count": 13, "numeric_cells": 192, "header_rows": 1, "locator": "section[9]/table-wrap[1]#T3"}}], "gaps": ["asset:data:geo:GSE15471 not downloaded", "asset:data:geo:GSE15471 licence not read", "asset:data:geo:GSE62165 not downloaded", "asset:data:geo:GSE62165 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": "reordered", "quote": "\"Normally distributed continuous variables were compared by using Student's t-test, and differences in categorical variables were analyzed using the chi-square or Fisher's exact test.\" \"The Mann-Whitney U test was used for comparisons in nonnormally distributed variables.\" \"A logistic regression analysis model was used to identify risk factors of PC.\" \"Patient overall survival (OS) was obtained using the Kaplan-Meier method.\" \"Demographic characteristics, laboratory results, serum lipids levels, surgical and pathological data were collected through electronic medical records and paper charts.\""}}, {"id": "method-2", "family": "group_comparison", "specific": "mann_whitney", "label": "Group comparison", "dsl_operations": [], "missing_operations": ["group_comparison_mann_whitney"], "expressible": false, "parameters": {}, "data_shapes": ["two_or_more_groups_continuous"], "evidence": {"score": 0.8, "band": "high", "quote": "Mann-Whitney"}}, {"id": "method-3", "family": "survival_analysis", "specific": "kaplan_meier", "label": "Survival analysis", "dsl_operations": ["survival_km"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["time_to_event_with_censoring"], "evidence": {"score": 0.8, "band": "high", "quote": "Kaplan-Meier"}}, {"id": "method-4", "family": "regression_modelling", "specific": "logistic", "label": "Regression modelling", "dsl_operations": ["glm_logit_fit"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["predictors_and_outcome"], "evidence": {"score": 0.8, "band": "high", "quote": "logistic regression"}}, {"id": "method-5", "family": "contingency_analysis", "specific": "chi_square", "label": "Categorical (contingency table) analysis", "dsl_operations": ["chi_square_test"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["categorical_cross_tabulation"], "evidence": {"score": 0.8, "band": "high", "quote": "chi-square"}}, {"id": "method-6", "family": "contingency_analysis", "specific": "fisher_exact", "label": "Categorical (contingency table) analysis", "dsl_operations": ["contingency_table", "chi_square_test"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["categorical_cross_tabulation"], "evidence": {"score": 0.8, "band": "high", "quote": "Fisher's exact"}}], "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": ["GSE15471", "GSE62165"], "resolved_accessions": ["GSE15471", "GSE62165"], "statements": ["The mRNA expression data of GSE15471 (39 matched pairs of samples) and GSE62165 (118 PC tissue samples and 13 paracancerous tissue samples) were acquired to identify differential target genes of related lipoprotein in PC."], "basis": "The paper names GSE15471, GSE62165 in GEO (Gene Expression Omnibus) and the accession resolves in the repository. No dataset was downloaded and no licence was read."}}, "can_run": {"dsl_operations": [], "assets": ["source:pmid:34335950", "data:geo:GSE15471", "asset:table:pmid:34335950:1", "asset:table:pmid:34335950:2", "asset:table:pmid:34335950:3"], "steps": []}, "must_build": {"dsl_operations": [{"operation": "student_t", "unlocks_papers": null, "priority": null}], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE15471"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-10-31T18:33:19Z", "independence": "single_reader"}, "evidence_check": {"method": "reordered", "availability": null}, "calls": 3, "usage": {"prompt_tokens": 18938, "completion_tokens": 1461, "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:34335950", "type": "paper", "label": "pmid:34335950"}, {"id": "source:pmid:34335950", "type": "manuscript", "label": "PMID 34335950 full text"}, {"id": "data:geo:GSE15471", "type": "dataset", "label": "GEO GSE15471"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:34335950", "type": "paper", "label": "pmid:34335950"}, {"id": "source:pmid:34335950", "type": "manuscript", "label": "PMID 34335950 full text"}, {"id": "data:geo:GSE15471", "type": "dataset", "label": "GEO GSE15471"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-34335950", "type": "extraction", "used": ["source:pmid:34335950"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE15471", "type": "accession_resolution", "used": ["data:geo:GSE15471"], "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:34335950", "parent_hash": "sha256:a0276460cc1ffc616a3a234dea9420ffec77d31a32a8d8134e28703e9f936cd2", "fork_of": null, "generation": 8}, "gaps": ["asset:data:geo:GSE15471 licence not read", "asset:data:geo:GSE15471 not downloaded", "asset:data:geo:GSE62165 licence not read", "asset:data:geo:GSE62165 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": "clinical_trial", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.93, "evidence": ["rding to an LDL cutoff of 4.14 mmol/L, 27 PC patients were assigned to the high-LDL group versus 201 patients in"], "order_basis": "paper_text_order:6800", "id": "assay:1"}, {"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": ["\"Normally distributed continuous variables were compared by using Student's t-test, and differences in categorical variables were analyzed using the chi-square or Fisher's exact test.\" \"The Mann-Whitney U test was used for comparisons in nonnormally distributed variables.\" \"A logistic regression analysis model was used to identify risk factors of PC.\" \"Patient overall survival (OS) was obtained using the Kaplan-Meier method.\" \"Demographic characteristics, laboratory results, serum lipids levels, surgical and pathological data were collected through electronic medical records and paper charts.\""], "order_basis": "consumes_earlier_output", "id": "assay:2"}]},"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":"2026-11-04T03:12:33+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}}}