{"data":{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:28167242", "kind": "science-record", "revision": 7, "content_hash": "sha256:8ccc5adbda0535cccbbf5e4d86c193eb8de3e1c1d213abb73f043ea195d201ce", "created_at": "2026-11-01T15:40:22Z", "updated_at": "2026-11-01T21:59:15Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Epigenome-Wide DNA Methylation Profiling Identifies Differential Methylation Biomarkers in High-Grade Bladder Cancer.", "doi": "10.1016/j.tranon.2017.01.001", "pmid": "28167242", "authors": ["Ekaterina Olkhov-Mitsel", "Andrea J Savio", "Ken J Kron", "Vaijayanti V Pethe", "Thomas Hermanns", "Neil E Fleshner", "Bas W van Rhijn", "Theodorus H van der Kwast", "Alexandre R Zlotta", "Bharati Bapat"], "journal": "Translational oncology", "year": 2017, "abstract": "Epigenetic changes, including CpG island hypermethylation, occur frequently in bladder cancer (BC) and may be exploited for BC detection and distinction between high-grade (HG) and low-grade (LG) disease. Genome-wide methylation analysis was performed using Agilent Human CpG Island Microarrays to determine epigenetic differences between LG and HG cases. Pathway enrichment analysis and functional annotation determined that the most frequently methylated pathways in HG BC were enriched for anterior/posterior pattern specification, embryonic skeletal system development, neuron fate commitment, DNA binding, and transcription factor activity. We identified 990 probes comprising a 32-gene panel that completely distinguished LG from HG based on methylation. Selected genes from this panel, EOMES, GP5, PAX6, TCF4, and ZSCAN12, were selected for quantitative polymerase chain reaction-based validation by MethyLight in an independent series (n=84) of normal bladder samples and LG and HG cases. GP5 and ZSCAN12, two novel methylated genes in BC, were significantly hypermethylated in HG versus LG BC (P≤.03). We validated our data in a second independent cohort of LG and HG BC cases (n=42) from The Cancer Genome Atlas (TCGA). Probes representing our 32-gene panel were significantly differentially methylated in LG versus HG tumors (P≤.04). These results indicate the ability to distinguish normal tissue from cancer, as well as LG from HG, based on methylation and reveal important pathways dysregulated in HG BC. Our findings were corroborated using publicly available data sets from TCGA. Ultimately, the creation of a methylation panel, including GP5 and ZSCAN12, able to distinguish between disease phenotypes will improve disease management and patient outcomes.", "claims": [{"id": "claim-method", "statement": "Comparison of median PMR values between LG, HG, and normal samples and other clinicopathological variables was performed using the Mann-Whitney U test or Kruskal-Wallis test, where appropriate.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:28167242", "locator": "sections[12] \"Statistical Analysis\" paragraph 2", "quote": "Comparison of median PMR values between LG, HG, and normal samples and other clinicopathological variables was performed using the Mann-Whitney U test or Kruskal-Wallis test, where appropriate."}], "state": "complete"}, {"id": "claim-data-access", "statement": "For these 42 total selected cases, level 3 methylation data from Illumina Infinium HumanMethylation450 BeadChip arrays were downloaded from TCGA in March 2016. Methylation data were also downloaded for all 21 benign bladder tissue samples available.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:28167242", "locator": "sections[11] \"The Cancer Genome Atlas (TCGA) Data Set\" paragraph 2", "quote": "For these 42 total selected cases, level 3 methylation data from Illumina Infinium HumanMethylation450 BeadChip arrays were downloaded from TCGA in March 2016. Methylation data were also downloaded for all 21 benign bladder tissue samples available."}], "state": "complete"}, {"id": "claim-target-result", "statement": "Genome-wide methylation analysis identified a 32-gene methylation panel that completely distinguished low-grade from high-grade bladder cancer and was validated with MethyLight and TCGA data.", "kind": "qualitative", "target": null, "evidence": [{"asset": "source:pmid:28167242", "locator": "sections[0] \"Abstract\" paragraph 1", "quote": "We identified 990 probes comprising a 32-gene panel that completely distinguished LG from HG based on methylation."}, {"asset": "source:pmid:28167242", "locator": "sections[0] \"Abstract\" paragraph 1", "quote": "Selected genes from this panel, EOMES, GP5, PAX6, TCF4, and ZSCAN12, were selected for quantitative polymerase chain reaction–based validation by MethyLight in an independent series (n = 84) of normal bladder samples and LG and HG cases."}, {"asset": "source:pmid:28167242", "locator": "sections[0] \"Abstract\" paragraph 1", "quote": "We validated our data in a second independent cohort of LG and HG BC cases (n = 42) from The Cancer Genome Atlas (TCGA)."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "partial", "objective": "Genome-wide methylation analysis identified a 32-gene methylation panel that completely distinguished low-grade from high-grade bladder cancer and was validated with MethyLight and TCGA data.", "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:28167242"], "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": "blocked", "blocked_on": "data:accession_absent", "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": [], "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:group_comparison_mann_whitney", "description": "Apply the paper's statistical method to the resolved series and compare the result with the published target.", "duration_hours": null, "parameters": {}, "inputs": [], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": ["step:run_analysis blocked on method:group_comparison_mann_whitney", "step:obtain_source_data blocked on data:accession_absent"]}, "data": {"state": "partial", "assets": [{"id": "source:pmid:28167242", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1016/j.tranon.2017.01.001", "sha256": "sha256:50265a52677d6e9ff9816a5743e3e50bdf7e1a8d6e767efe54941d2d37475daf", "bytes": 49077, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1016/j.tranon.2017.01.001", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC5293735", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "asset:table:pmid:28167242:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:87e06c45942931dc922b93972ebbd1731c511449c950525a30f5dcd7a7ab9bcb", "bytes": 2043, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[3]/table-wrap[1]#t0005", "version": null, "note": "Clinicopathological Variables of LG and HG BC Patients of Cohort Used for MethyLight Gene-Specific Methylation Analysis", "structure": {"pmcid": "PMC5293735", "section_index": 3, "section_title": "Patients and Pathology", "row_count": 49, "column_count": 3}, "table": {"label": "Table 1", "caption": "Clinicopathological Variables of LG and HG BC Patients of Cohort Used for MethyLight Gene-Specific Methylation Analysis", "rows": [["Clinicopathological Variable", "LG, N (%)", "HG, N (%)"], ["Gender", "", ""], ["Male", "27 (67.5)", "27 (67.5)"], ["Female", "13 (32.5)", "13 (32.5)"], ["Age group", "", ""], ["< 50", "2 (5.0)", "4 (10.0)"], ["50-59", "9 (22.5)", "8 (20.0)"], ["60-69", "16 (40.0)", "15 (37.5)"], ["70-79", "12 (30.0)", "12 (30.0)"], ["80-89", "1 (2.5)", "1 (2.5)"], ["Grade", "", ""], ["LG", "40 (100.0)", "0 (0.0)"], ["HG", "0 (0.0)", "40 (100.0)"], ["Pathological stage", "", ""], ["Ta", "21 (52.5)", "0 (0.0)"], ["T1", "18 (45.0)", "34 (85.0)"], ["T2a", "0 (0.0)", "1 (2.5)"], ["T2b", "1 (2.5)", "0 (0.0)"], ["T3a", "0 (0.0)", "4 (10.0)"], ["T3b", "0 (0.0)", "1 (2.5)"], ["Surgery", "", ""], ["Transurethral resection of bladder tumor", "16 (40.0)", "33 (82.5)"], ["Radical cystectomy", "7 (17.5)", "7 (17.5)"], ["No data", "17 (42.5)", "0 (0.0)"], ["Recurrence", "", ""], ["No recurrence", "4 (10.0)", "14 (35.0)"], ["Recurrence", "12 (30.0)", "18 (45.0)"], ["No data", "24 (60.0)", "8 (20.0)"], ["FGFR3 mutation", "", ""], ["Wild type", "10 (25.0)", "30 (75.0)"], ["Mutation", "13 (32.5)", "9 (22.5)"], ["No data", "17 (42.5)", "1 (2.5)"], ["FGFR3 expression", "", ""], ["Not expressed", "6 (15.0)", "18 (45.0)"], ["Expressed", "17 (42.5)", "21 (52.5)"], ["No data", "17 (42.5)", "1 (2.5)"], ["P53 expression", "", ""], ["Not expressed", "22 (55.0)", "18 (45.0)"], ["Expressed", "1 (2.5)", "22 (55.0)"], ["No data", "17 (42.5)", "0 (0.0)"], ["P27 expression", "", ""], ["Not expressed", "13 (32.5)", "21 (52.5)"], ["Expressed", "10 (25.0)", "19 (47.5)"], ["No data", "17 (42.5)", "0 (0.0)"], ["EOMES median PMR (range)", "30.2 (0.0-100.0)", "41.8 (1.8-100.0)"], ["GP5 median PMR (range)", "0.0 (0.0-53.7)", "1.6 (0.0-87.6)"], ["PAX6 median PMR (range)", "19.0 (0.0-69.4)", "22.4 (0.0-100.0)"], ["TCF4 median PMR (range)", "0.0 (0.0-37.5)", "0.2 (0.0-37.9)"], ["ZSCAN12 median PMR (range)", "0.0 (0.0-73.56)", "10.9 (0.0-74.9)"]], "row_count": 49, "column_count": 3, "numeric_cells": 84, "header_rows": 1, "locator": "section[3]/table-wrap[1]#t0005"}}, {"id": "asset:table:pmid:28167242:2", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:7600bf94004cd243a521f0a51c4567ec2c1acf926f76dae87e938b68699d9fc2", "bytes": 2743, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[14]/table-wrap[1]#t0010", "version": null, "note": "List of the 19 Most Significantly Hypermethylated and 13 Hypomethylated Genes between LG and HG BC, Comprising a 32-Gene Panel", "structure": {"pmcid": "PMC5293735", "section_index": 14, "section_title": "Genome-Wide Methylation in LG and HG BC", "row_count": 34, "column_count": 5}, "table": {"label": "Table 2", "caption": "List of the 19 Most Significantly Hypermethylated and 13 Hypomethylated Genes between LG and HG BC, Comprising a 32-Gene Panel", "rows": [["Gene Name (Abbreviation)", "Number of Probes", "Fold Change", "P Value"], ["LPE", "Limma"], ["Von Willebrand factor C domain containing 2 (UNQ739)", "1", "66.7", "3.51 × 10−6", "2.16 × 10−5"], ["Uncharacterized LOC389064 (FLJ46347)", "2", "41.3", ".0006", ".0332"], ["Eomesodermin (EOMES)", "3", "36.5", ".0104", ".0016"], ["Glycoprotein V (platelet) (GP5)", "4", "36.3", ".0108", ".0006"], ["Solute carrier family 2 (facilitated glucose transporter), member 2 (SLC2A2)", "2", "36.1", ".0116", ".0002"], ["Glial cell–derived neurotrophic factor (GDNF)", "4", "33.6", ".0033", ".0136"], ["Short stature homeobox (SHOX)", "3", "32.6", ".0156", ".0238"], ["Olfactory receptor, family 10, subfamily AD, member 1 (OR10AD1)", "4", "31.8", ".0013", ".0005"], ["Glutamate receptor, ionotropic, kainate 1 (GRIK1)", "1", "29.4", ".0017", ".0035"], ["Zinc finger protein 418 (ZNF418)", "1", "28.8", "1.13 × 10−5", ".0006"], ["Forkhead box E1 (thyroid transcription factor 2) (FOXE1)", "1", "28.3", ".0005", ".0001"], ["Zinc finger and SCAN domain containing 12 (ZSCAN12/ZNF96)", "6", "26.8", ".0096", ".0062"], ["Homeobox D9 (HOXD9)", "1", "24.4", "7.63 × 10−6", ".0017"], ["Phosphatidylinositol-3,4,5-trisphosphate–dependent Rac exchange factor 1 (PREX1)", "1", "23.4", ".0004", ".0311"], ["Engulfment adaptor PTB domain containing 1 (GULP1)", "6", "23.1", ".0025", ".0069"], ["Myosin binding protein C, slow type (MYBPC1)", "1", "23.0", ".0009", ".0071"], ["Motor neuron and pancreas homeobox 1 (HLXB9)", "1", "22.3", "4.02 × 10−5", ".0003"], ["Glutamate receptor, ionotropic, AMPA 2 (GRIA2)", "2", "22.0", ".0002", ".0003"], ["Paired box 6 (PAX6)", "8", "21.8", ".0063", ".004"], ["small nucleolar RNA, H/ACA box 70 (U70)", "1", "−8.9", ".033", ".011"], ["Protease, serine, 21 (PRSS21)", "1", "−7.8", ".043", ".008"], ["Carbonic anhydrase XIII (CA13)", "1", "−7.7", ".021", ".019"], ["Translocase of outer mitochondrial membrane 40 homolog (TOMM40)", "1", "−6.9", ".029", ".002"], ["Phosphorylase kinase, alpha 1 (PHKA1)", "1", "−6.9", ".047", ".004"], ["DOK2-XPO7", "1", "−6.4", ".043", ".012"], ["Kruppel-like factor 11 (KLF11)", "1", "−6.3", ".018", ".018"], ["BCL2-associated transcription factor 1 (BCLAF1)", "1", "−6.2", ".027", ".024"], ["Single-minded homolog 1 (Drosophila) (SIM1)", "2", "−5.0", ".045", ".006"], ["FLJ43870", "1", "−4.7", ".043", ".028"], ["BMP and activin membrane-bound inhibitor homolog (Xenopus laevis) (BAMBI)", "1", "−4.4", ".044", ".039"], ["Ribosomal protein L31 (RPL31)", "1", "−4.3", ".045", ".011"], ["Homeobox A9 (HOXA9)", "1", "−3.8", ".043", ".002"]], "row_count": 34, "column_count": 5, "numeric_cells": 151, "header_rows": 2, "locator": "section[14]/table-wrap[1]#t0010"}}, {"id": "asset:table:pmid:28167242:3", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:47b57199eb2c53c2d51aed27c2fc061f4bcd72d741a0eba1b2cd901a2d8f658c", "bytes": 2252, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[17]/table-wrap[1]#t0015", "version": null, "note": "Associations between Methylation of Five Genes and Clinicopathological Variables in BC Patients", "structure": {"pmcid": "PMC5293735", "section_index": 17, "section_title": "Gene-Specific Methylation Analysis", "row_count": 60, "column_count": 6}, "table": {"label": "Table 3", "caption": "Associations between Methylation of Five Genes and Clinicopathological Variables in BC Patients", "rows": [["Clinicopathological Variable", "EOMES PMR", "GP5 PMR", "PAX6 PMR", "TCF4 PMR", "ZSCAN12 PMR"], ["Normal vs cancer"], ["Normal", "0.0", "0.0", "3.9", "0.0", "0.9"], ["Cancer", "31.8", "0.0", "20.2", "0.1", "3.1"], ["P value", "1.2 × 10−4", ".22", ".06", ".19", ".29"], [""], ["Normal vs LG vs HG"], ["Normal", "0.0", "0.0", "3.9", "0.0", "0.9"], ["LG", "30.2", "0.0", "19.0", "0.01", "0.0"], ["HG", "41.8", "1.6", "22.4", "0.2", "10.9"], ["P value", ".001", ".008", ".11", ".32", ".04"], [""], ["LG vs HG"], ["LG", "30.2", "0.0", "19.0", "0.01", "0.0"], ["HG", "41.8", "1.6", "22.4", "0.2", "10.9"], ["P value", ".05", ".006", ".34", ".53", ".03"], [""], ["Normal vs LG"], ["Normal", "0.0", "0.0", "3.9", "0.0", "0.9"], ["LG", "30.2", "0.0", "19.0", "0.01", "0.0"], ["P value", ".002", ".43", ".07", ".23", ".66"], [""], ["Normal vs HG"], ["Normal", "0.0", "0.0", "3.9", "0.0", "0.9"], ["HG", "41.8", "1.6", "22.4", "0.2", "10.9"], ["P value", "1.8 × 10−5", ".11", ".06", ".19", ".10"], [""], ["Stage"], ["Ta", "9.7", "0.0", "9.3", "0.01", "0.0"], ["T1", "46.1", "0.0", "26.7", "0.2", "10.9"], ["T2a", "31.0", "16.4", "16.0", "0.0", "0.0"], ["T2b", "15.8", "5.8", "7.4", "4.6", "0.8"], ["T3a", "18.4", "1.7", "3.4", "0.6", "3.4"], ["T3b", "55.7", "62.7", "1.0", "0.0", "12.4"], ["P value", ".047", ".51", "4.6 × 10−4", ".03", ".001"], [""], ["Recurrence"], ["No recurrence", "43.5", "0.0", "22.8", "0.04", "0.3"], ["Recurrence", "46.1", "2.5", "30.7", "0.7", "11.7"], ["P value", ".80", ".17", ".17", ".64", ".23"], [""], ["P53 expression"], ["Not expressed", "21.6", "0.0", "12.9", "0.01", "0.3"], ["Expressed", "41.4", "0.0", "26.3", "0.01", "1.1"], ["P value", ".09", ".02", ".31", ".35", ".39"], [""], ["P27 expression"], ["Not expressed", "31.0", "0.0", "23.9", "0.0", "4.6"], ["Expressed", "22.8", "0.0", "12.9", "0.02", "0.0"], ["P value", ".91", ".001", ".80", ".88", ".36"], [""], ["FGFR3 mutation"], ["Wild-type", "28.5", "0.0", "16.6", "0.0", "2.1"], ["Mutated", "36.4", "0.0", "23.9", "0.2", "0.0"], ["P value", ".09", ".11", ".81", ".37", ".005"], [""], ["FGFR3 expression"], ["Not expressed", "30.0", "0.0", "14.6", "0.02", "0.5"], ["Expressed", "27.9", "0.0", "23.8", "0.01", "0.3"], ["P value", ".30", ".002", ".29", ".34", ".005"]], "row_count": 60, "column_count": 6, "numeric_cells": 193, "header_rows": 1, "locator": "section[17]/table-wrap[1]#t0015"}}, {"id": "asset:table:pmid:28167242:4", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:176fc5f881518a0ec48a313c0f2357afae0a2503c947d29dcc2092fd7dae6e20", "bytes": 1572, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[18]/table-wrap[1]#t0020", "version": null, "note": "Associations between Methylation of a Five-Gene Panel and Grade in BC Patients from TCGA", "structure": {"pmcid": "PMC5293735", "section_index": 18, "section_title": "Gene-Specific Validation in TCGA Data Set", "row_count": 28, "column_count": 6}, "table": {"label": "Table 4", "caption": "Associations between Methylation of a Five-Gene Panel and Grade in BC Patients from TCGA", "rows": [["Gene", "EOMES", "GP5", "PAX6", "TCF4", "ZSCAN12"], ["Probe ID", "cg21473142", "cg18780769", "cg24701575", "cg23482397", "cg20271532"], ["Benign vs cancer", "", "", "", "", ""], ["Benign", "0.261", "0.137", "0.137", "0.022", "0.072"], ["Cancer", "0.606", "0.129", "0.281", "0.028", "0.098"], ["P value", ".003", ".94", ".02", "1.9 × 10−4", ".31"], ["Benign vs LG vs HG", "", "", "", "", ""], ["Benign", "0.261", "0.137", "0.137", "0.022", "0.072"], ["LG", "0.314", "0.092", "0.156", "0.026", "0.056"], ["HG", "0.753", "0.232", "0.465", "0.046", "0.225"], ["P value", "2.7 × 10−5", "2.9 × 10−4", "1.3 × 10−4", "1.7 × 10−4", ".02"], ["LG vs HG", "", "", "", "", ""], ["LG", "0.314", "0.092", "0.156", "0.046", "0.225"], ["HG", "0.753", "0.232", "0.565", "0.026", "0.056"], ["P value", ".003", ".001", ".001", ".04", ".02"], ["Benign vs LG", "", "", "", "", ""], ["Benign", "0.261", "0.137", "0.137", "0.022", "0.072"], ["LG", "0.314", "0.092", "0.156", "0.026", "0.056"], ["P value", ".77", ".009", ".97", ".01", ".46"], ["Benign vs HG", "", "", "", "", ""], ["Benign", "0.246", "0.137", "0.137", "0.022", "0.072"], ["HG", "0.753", "0.232", "0.565", "0.046", "0.225"], ["P value", "2.3 × 10−6", ".01", "5.5 × 10−5", "9.3 × 10−5", ".01"], ["Stage", "", "", "", "", ""], ["T2", "0.321", "0.125", "0.226", "0.027", "0.079"], ["T3", "0.671", "0.098", "0.280", "0.046", "0.070"], ["T4", "0.732", "0.195", "0.347", "0.027", "0.429"], ["P value", ".12", ".39", ".77", ".59", ".44"]], "row_count": 28, "column_count": 6, "numeric_cells": 106, "header_rows": 1, "locator": "section[18]/table-wrap[1]#t0020"}}], "gaps": []}, "analysis": {"state": "partial", "methods": [{"id": "method-1", "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": 1.0, "band": "verbatim", "quote": "Comparison of median PMR values between LG, HG, and normal samples and other clinicopathological variables was performed using the Mann-Whitney U test or Kruskal-Wallis test, where appropriate."}}, {"id": "method-2", "family": "group_comparison", "specific": "wilcoxon", "label": "Group comparison", "dsl_operations": [], "missing_operations": ["group_comparison_wilcoxon"], "expressible": false, "parameters": {}, "data_shapes": ["two_or_more_groups_continuous"], "evidence": {"score": 0.8, "band": "high", "quote": "Wilcoxon"}}, {"id": "method-3", "family": "network_analysis", "specific": "pathway_enrichment", "label": "Network / pathway analysis", "dsl_operations": ["pathway_enrich"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["edge_list"], "evidence": {"score": 0.7, "band": "medium", "quote": "Pathway enrichment"}}], "targets": [], "gaps": ["method.group_comparison_mann_whitney"]}, "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": "blocked", "tier": "R4", "blocking_axis": "data", "blocked_on": "data:accession_absent", "axes": {"method": {"tier": "R1", "expressible": false, "required_operations": [], "missing_operations": ["group_comparison_mann_whitney"], "basis": "The paper names the method it used and the corpus's method extractor maps it onto the DSL catalogue: mann_whitney."}, "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": "R4", "reachable": false, "accessions": [], "resolved_accessions": [], "statements": ["For these 42 total selected cases, level 3 methylation data from Illumina Infinium HumanMethylation450 BeadChip arrays were downloaded from TCGA in March 2016. Methylation data were also downloaded for all 21 benign bladder tissue samples available."], "basis": "The paper names no accession to its source data, so the data has to come from the authors."}}, "can_run": {"dsl_operations": [], "assets": ["source:pmid:28167242", "asset:table:pmid:28167242:1", "asset:table:pmid:28167242:2", "asset:table:pmid:28167242:3", "asset:table:pmid:28167242:4"], "steps": []}, "must_build": {"dsl_operations": [{"operation": "group_comparison_mann_whitney", "unlocks_papers": null, "priority": null}], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:None"]}, "gaps": ["data:accession_absent"]}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-10-31T18:30:25Z", "independence": "same_provider"}, "evidence_check": {"method": "verbatim", "availability": null}, "calls": 8, "usage": {"prompt_tokens": 104789, "completion_tokens": 3624, "cached_tokens": 2107}}, "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:28167242", "type": "paper", "label": "pmid:28167242"}, {"id": "source:pmid:28167242", "type": "manuscript", "label": "PMID 28167242 full text"}, {"id": "data:geo:None", "type": "dataset", "label": "GEO None"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:28167242", "type": "paper", "label": "pmid:28167242"}, {"id": "source:pmid:28167242", "type": "manuscript", "label": "PMID 28167242 full text"}, {"id": "data:geo:None", "type": "dataset", "label": "GEO None"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-28167242", "type": "extraction", "used": ["source:pmid:28167242"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-None", "type": "accession_resolution", "used": ["data:geo:None"], "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:28167242", "parent_hash": "sha256:edc084713cad56ee94f49eaf5ada974ed7bf87ec160a106f389c5987aafc8c88", "fork_of": null, "generation": 6}, "gaps": ["execution.not_run", "method.group_comparison_mann_whitney", "review.human_critique", "review.independent_reader", "review.machine_critique", "step:obtain_source_data blocked on data:accession_absent", "step:run_analysis blocked on method:group_comparison_mann_whitney"], "assays": [{"role": "data_generation", "definition_id": "qpcr", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.93, "evidence": ["by a quantitative polymerase chain reaction (qPCR)–based methylation detection assay, MethyLig"], "order_basis": "paper_text_order:2311", "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": ["Comparison of median PMR values between LG, HG, and normal samples and other clinicopathological variables was performed using the Mann-Whitney U test or Kruskal-Wallis test, where appropriate."], "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":"2026-11-04T01:42:16+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}}}