{"data":{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:30813939", "kind": "science-record", "revision": 7, "content_hash": "sha256:3c8ae4b6c0bc85bee2e31138976d42d346e899b8035fbc15e58177bfcadcb72d", "created_at": "2026-11-01T15:40:42Z", "updated_at": "2026-11-01T22:00:23Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Comprehensive bioinformatics analysis of acquired progesterone resistance in endometrial cancer cell line.", "doi": "10.1186/s12967-019-1814-6", "pmid": "30813939", "authors": ["Wenzhi Li", "Shufen Wang", "Chunping Qiu", "Zhiming Liu", "Qing Zhou", "Deshui Kong", "Xiaohong Ma", "Jie Jiang"], "journal": "Journal of translational medicine", "year": 2019, "abstract": "BACKGROUND: Progesterone resistance is a problem in endometrial carcinoma, and its underlying molecular mechanisms remain poorly understood. The aim of this study was to elucidate the molecular mechanisms of progesterone resistance and to identify the key genes and pathways mediating progesterone resistance in endometrial cancer using bioinformatics analysis.\nMETHODS: We developed a stable MPA (medroxyprogesterone acetate)-resistant endometrial cancer cell subline named IshikawaPR. Microarray analysis was used to identify differentially expressed genes (DEGs) from triplicate samples of Ishikawa and IshikawaPR cells. PANTHER, DAVID and Metascape were used to perform gene ontology (GO), Kyoto Encyclopedia of Genes and Genomes (KEGG) pathway enrichment analysis, and cBioPortal for progesterone receptor (PGR) coexpression analysis. GEO microarray (GSE17025) was utilized for validation. The protein-protein interaction network (PPI) and modular analyses were performed using Metascape and Cytoscape. Further validation were performed by real-time polymerase chain reaction (RT-PCR).\nRESULTS: In total, 821 DEGs were found and further analyzed by GO, KEGG pathway enrichment and PPI analyses. We found that lipid metabolism, immune system and inflammation, extracellular environment-related processes and pathways accounted for a significant portion of the enriched terms. PGR coexpression analysis revealed 7 PGR coexpressed genes (ANO1, SOX17, CGNL1, DACH1, RUNDC3B, SH3YL1 and CRISPLD1) that were also dramatically changed in IshikawaPR cells. Kaplan-Meier survival statistics revealed clinical significance for 4 out of 7 target genes. Furthermore, 8 hub genes and 4 molecular complex detections (MCODEs) were identified.\nCONCLUSIONS: Using microarray and bioinformatics analyses, we identified DEGs and determined a comprehensive gene network of progesterone resistance. We offered several possible mechanisms of progesterone resistance and identified therapeutic and prognostic targets of progesterone resistance in endometrial cancer.", "claims": [{"id": "claim-method", "statement": "Kaplan–Meier curves for target genes were generated with the online tool Kaplan–Meier Plotter (http://www.kmplot.com/). A total of 542 RNA-seq data samples of uterine corpus endometrial carcinoma were interrogated. The patients were split into 2 groups (high vs. low) based on the expression level.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:30813939", "locator": "sections[5] \"PGR coexpression analysis and validation by bioinformatics\" paragraph 3", "quote": "Kaplan–Meier curves for target genes were generated with the online tool Kaplan–Meier Plotter (http://www.kmplot.com/). A total of 542 RNA-seq data samples of uterine corpus endometrial carcinoma were interrogated. The patients were split into 2 groups (high vs. low) based on the expression level."}], "state": "complete"}, {"id": "claim-data-access", "statement": "The datasets used and/or analyzed during the current study are available from the corresponding author on reasonable request.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:30813939", "locator": "sections[23] \"ack\" paragraph 1", "quote": "The datasets used and/or analyzed during the current study are available from the corresponding author on reasonable request."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "complete", "objective": null, "steps": [{"id": "read_published_estimate", "order": 1, "name": "Read the published estimate from the source", "kind": "other", "state": "complete", "blocked_on": null, "description": "The claim, method and evidence span published with the source article.", "duration_hours": null, "parameters": {}, "inputs": ["source:pmid:30813939"], "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:GSE121367"], "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:GSE121367"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:30813939", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1186/s12967-019-1814-6", "sha256": "sha256:0dc636c96c6dd0fdd92e7c68ae6cfb9353e4eb6bee6ef85aca78ed57272324e8", "bytes": 41657, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1186/s12967-019-1814-6", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC6391799", "source": "europe_pmc_fulltext", "coverage": "whole_body_without_references", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE121367", "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=GSE121367", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE121367", "version": null, "note": "The datasets used and/or analyzed during the current study are available from the corresponding author on reasonable request.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The datasets used and/or analyzed during the current study are available from the corresponding author on reasonable request.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM3433342", "GSM3433343", "GSM3433344", "GSM3433345", "GSM3433346", "GSM3433347"], "sample_count": 6, "group_sizes": null, "group_sizes_basis": null, "platform": "13497", "taxon": "Homo sapiens", "title": "Endometrial cancer cell line with acquired resistance to medroxyprogesterone acetate", "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:GSE17025", "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=GSE17025", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE17025", "version": null, "note": "The datasets used and/or analyzed during the current study are available from the corresponding author on reasonable request.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The datasets used and/or analyzed during the current study are available from the corresponding author on reasonable request.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM425837", "GSM425838", "GSM425839", "GSM425840", "GSM425841", "GSM425842", "GSM425843", "GSM425844", "GSM425845", "GSM425846", "GSM425847", "GSM425848", "GSM425849", "GSM425850", "GSM425851", "GSM425852", "GSM425853", "GSM425854", "GSM425855", "GSM425856", "GSM425857", "GSM425858", "GSM425859", "GSM425860", "GSM425861", "GSM425862", "GSM425863", "GSM425864", "GSM425865", "GSM425866", "GSM425867", "GSM425868", "GSM425869", "GSM425870", "GSM425871", "GSM425872", "GSM425873", "GSM425874", "GSM425875", "GSM425876", "GSM425877", "GSM425878", "GSM425879", "GSM425880", "GSM425881", "GSM425882", "GSM425883", "GSM425884", "GSM425885", "GSM425886", "GSM425887", "GSM425888", "GSM425889", "GSM425890", "GSM425891", "GSM425892", "GSM425893", "GSM425894", "GSM425895", "GSM425896", "GSM425897", "GSM425898", "GSM425899", "GSM425900", "GSM425901", "GSM425902", "GSM425903", "GSM425904", "GSM425905", "GSM425906", "GSM425907", "GSM425908", "GSM425909", "GSM425910", "GSM425911", "GSM425912", "GSM425913", "GSM425914", "GSM425915", "GSM425916", "GSM425917", "GSM425918", "GSM425919", "GSM425920", "GSM425921", "GSM425922", "GSM425923", "GSM425924", "GSM425925", "GSM425926", "GSM425927", "GSM425928", "GSM425929", "GSM425930", "GSM425931", "GSM425932", "GSM425933", "GSM425934", "GSM425935", "GSM425936", "GSM425937", "GSM425938", "GSM425939"], "sample_count": 103, "group_sizes": null, "group_sizes_basis": null, "platform": "570", "taxon": "Homo sapiens", "title": "Gene Expression Analysis of Stage I Endometrial Cancers", "resolution_checked_at": "2026-11-01T15:39:54Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "asset:table:pmid:30813939:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:e148435da6c475bae03d769f94e9fe3fc5d5a2d44b8f5853a4a1555b3f2c2297", "bytes": 1668, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[10]/table-wrap[1]#Tab1", "version": null, "note": "Top 10 GO enrichment analyses of up-regulated and down-regulated DEGs", "structure": {"pmcid": "PMC6391799", "section_index": 10, "section_title": "Gene ontology analysis of DEGs", "row_count": 23, "column_count": 4}, "table": {"label": "Table 1", "caption": "Top 10 GO enrichment analyses of up-regulated and down-regulated DEGs", "rows": [["Category", "Term", "Count", "p-value"], ["Up-regulated"], ["BP", "GO:0009952 ~ anterior/posterior pattern specification", "14", "1.65E−08"], ["CC", "GO:0005615 ~ extracellular space", "56", "3.21E−07"], ["MF", "GO:0043565 ~ sequence-specific DNA binding", "30", "2.32E−06"], ["BP", "GO:0032526 ~ response to retinoic acid", "8", "2.57E−05"], ["CC", "GO:0005576 ~ extracellular region", "57", "3.21E−05"], ["CC", "GO:0005578 ~ proteinaceous extracellular matrix", "17", "1.07E−04"], ["BP", "GO:0048704 ~ embryonic skeletal system morphogenesis", "7", "1.80E−04"], ["CC", "GO:0009986 ~ cell surface", "25", "2.58E−04"], ["BP", "GO:0030198 ~ extracellular matrix organization", "14", "3.68E−04"], ["BP", "GO:0002474 ~ antigen processing and presentation of peptide antigen via MHC class I", "6", "4.30E−04"], ["Down-regulated"], ["BP", "GO:0042472 ~ inner ear morphogenesis", "6", "0.001957"], ["BP", "GO:0060021 ~ palate development", "7", "0.001967"], ["BP", "GO:0070830 ~ bicellular tight junction assembly", "5", "0.002114"], ["BP", "GO:0030198 ~ extracellular matrix organization", "11", "0.002153"], ["CC", "GO:0016328 ~ lateral plasma membrane", "6", "0.002206"], ["CC", "GO:0032587 ~ ruffle membrane", "7", "0.003009"], ["CC", "GO:0005923 ~ bicellular tight junction", "8", "0.003557"], ["BP", "GO:0001525 ~ angiogenesis", "11", "0.005387"], ["BP", "GO:0007165 ~ signal transduction", "33", "0.005738"], ["BP", "GO:0007156 ~ homophilic cell adhesion via plasma membrane adhesion molecules", "9", "0.0061"]], "row_count": 23, "column_count": 4, "numeric_cells": 60, "header_rows": 1, "locator": "section[10]/table-wrap[1]#Tab1"}}, {"id": "asset:table:pmid:30813939:2", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:647092373014820ebfdda4eaa7fd1f78f76d5f8cae73b7941ec9f0b1b289fa8a", "bytes": 938, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[11]/table-wrap[1]#Tab2", "version": null, "note": "Top 5 KEGG pathway enrichment of up-regulated and down-regulated DEGs sorted by p-value and count of hit-genes", "structure": {"pmcid": "PMC6391799", "section_index": 11, "section_title": "Encoded protein class and KEGG pathway enrichment analysis of DEGs", "row_count": 13, "column_count": 4}, "table": {"label": "Table 2", "caption": "Top 5 KEGG pathway enrichment of up-regulated and down-regulated DEGs sorted by p-value and count of hit-genes", "rows": [["Term", "Description", "p-value", "Count"], ["Up-regulated"], ["hsa04610", "Complement and coagulation cascades", "1.40E−04", "9"], ["hsa04550", "Signaling pathways regulating pluripotency of stem cells", "0.001138056", "11"], ["hsa05134", "Legionellosis", "0.001227629", "7"], ["hsa05150", "Staphylococcus aureus infection", "0.001227629", "7"], ["hsa05133", "Pertussis", "0.006513616", "7"], ["Down-regulated"], ["hsa05202", "Transcriptional misregulation in cancer", "0.003670966", "9"], ["hsa04015", "Rap1 signaling pathway", "0.004207876", "10"], ["hsa05200", "Pathways in cancer", "0.014545204", "13"], ["hsa04918", "Thyroid hormone synthesis", "0.020795767", "5"], ["hsa05146", "Amoebiasis", "0.021449539", "6"]], "row_count": 13, "column_count": 4, "numeric_cells": 30, "header_rows": 1, "locator": "section[11]/table-wrap[1]#Tab2"}}, {"id": "asset:table:pmid:30813939:3", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:f81e9d6a22c47c6798c14ab92415aba2683eaa00e52c92092ec8a767cdc8290c", "bytes": 984, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[12]/table-wrap[1]#Tab3", "version": null, "note": "Distinguishing and validation of 7 PGR co-expressed genes among DEGs", "structure": {"pmcid": "PMC6391799", "section_index": 12, "section_title": "PGR coexpression analysis and validation", "row_count": 10, "column_count": 9}, "table": {"label": "Table 3", "caption": "Distinguishing and validation of 7 PGR co-expressed genes among DEGs", "rows": [["Gene symbol", "PGR co-expression(548 EC tissues)", "Microarray analysis", "GSE17025", "Survival curve(542 EC tissues)"], ["Pearson score"], ["Pearson score", "Spearman score", "LogFC", "−Log(p-value)", "r", "p-value", "HR", "LogRank p-value"], ["ANO1", "0.66", "0.72", "− 10.78", "8.69", "0.611", "< 0.01", "0.38", "3.00E−06"], ["CGNL1", "0.39", "0.45", "− 7.19", "3.38", "0.438", "< 0.01", "0.48", "0.00046"], ["DACH1", "0.33", "0.39", "− 6.67", "4.60", "0.285", "< 0.01", "0.79", "0.27"], ["SH3YL1", "0.58", "0.54", "− 4.40", "6.41", "0.416", "< 0.01", "0.53", "0.0027"], ["RUNDC3B", "0.43", "0.46", "− 4.23", "4.64", "0.235", "< 0.1", "0.73", "0.21"], ["CRISPLD1", "0.39", "0.39", "− 4.09", "4.42", "0.434", "< 0.01", "0.64", "0.038"], ["SOX17", "0.46", "0.59", "− 4.03", "5.83", "0.444", "< 0.01", "0.46", "0.00021"]], "row_count": 10, "column_count": 9, "numeric_cells": 60, "header_rows": 3, "locator": "section[12]/table-wrap[1]#Tab3"}}, {"id": "asset:table:pmid:30813939:4", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:e311c392d02b2732c9db5e70dac51aae1b2dc103b0fcc123ee602f994890f645", "bytes": 760, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[13]/table-wrap[1]#Tab4", "version": null, "note": "8 hub genes (degree ≥ 15) selected from PPI network according to degree", "structure": {"pmcid": "PMC6391799", "section_index": 13, "section_title": "Protein-protein interaction network (PPI) and modular analysis", "row_count": 9, "column_count": 6}, "table": {"label": "Table 4", "caption": "8 hub genes (degree ≥ 15) selected from PPI network according to degree", "rows": [["Gene symbol", "Eccentricity", "Closeness", "Betweenness", "Degree", "Stress"], ["HSPA1A", "0.1667", "0.0011", "26,447.0664", "30.0", "65,244.0"], ["EEF1A2", "0.1429", "0.0010", "13,663.9556", "26.0", "38,054.0"], ["AR", "0.1667", "0.0011", "15,814.7167", "20.0", "49,698.0"], ["POU5F1", "0.1429", "0.0010", "14,493.2442", "19.0", "42,006.0"], ["C3", "0.1429", "0.0009", "5703.5021", "18.0", "14,084.0"], ["SYK", "0.1429", "0.0010", "12,162.3216", "16.0", "34,430.0"], ["LPAR1", "0.1250", "0.0008", "996.2218", "15.0", "3726.0"], ["NMU", "0.1250", "0.0008", "1251.3925", "15.0", "3778.0"]], "row_count": 9, "column_count": 6, "numeric_cells": 40, "header_rows": 1, "locator": "section[13]/table-wrap[1]#Tab4"}}, {"id": "asset:table:pmid:30813939:5", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:1a79fb273754dff36a09d478be744bf99adacbe70a9ff454fcf855df594eb42f", "bytes": 1150, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[13]/table-wrap[2]#Tab5", "version": null, "note": "Top 15 GO enrichments of the 4 MCODEs related genes", "structure": {"pmcid": "PMC6391799", "section_index": 13, "section_title": "Protein-protein interaction network (PPI) and modular analysis", "row_count": 16, "column_count": 3}, "table": {"label": "Table 5", "caption": "Top 15 GO enrichments of the 4 MCODEs related genes", "rows": [["GO term", "Description", "−Log10(p)"], ["GO:0002474", "Antigen processing and presentation of peptide antigen via MHC class I", "6.60"], ["GO:0006955", "Immune response", "3.98"], ["GO:0002480", "Antigen processing and presentation of exogenous peptide antigen via MHC class I, TAP-independent", "3.93"], ["GO:0006954", "Inflammatory response", "3.22"], ["GO:0090023", "Positive regulation of neutrophil chemotaxis", "3.13"], ["GO:0007218", "Neuropeptide signaling pathway", "3.08"], ["GO:0007186", "G-protein coupled receptor signaling pathway", "2.98"], ["GO:000693", "Chemotaxis", "2.84"], ["GO:0042612", "MHC class I protein complex", "3.82"], ["GO:0005622", "Intracellular", "3.57"], ["GO:0005887", "Integral component of plasma membrane", "3.38"], ["GO:0031090", "Organelle membrane", "3.37"], ["GO:0071556", "Integral component of lumenal side of endoplasmic reticulum membrane", "2.96"], ["GO:0008395", "Steroid hydroxylase activity", "4.85"], ["GO:0020037", "Heme binding", "3.96"]], "row_count": 16, "column_count": 3, "numeric_cells": 31, "header_rows": 1, "locator": "section[13]/table-wrap[2]#Tab5"}}, {"id": "asset:table:pmid:30813939:6", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:c0c41e51a5366de2646382e76d8b9bb042f088deab21f7e6327e6501cd5b1a13", "bytes": 779, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[13]/table-wrap[3]#Tab6", "version": null, "note": "Top 10 KEGG pathway enrichment of the 4 MCODEs related genes", "structure": {"pmcid": "PMC6391799", "section_index": 13, "section_title": "Protein-protein interaction network (PPI) and modular analysis", "row_count": 11, "column_count": 3}, "table": {"label": "Table 6", "caption": "Top 10 KEGG pathway enrichment of the 4 MCODEs related genes", "rows": [["KEGG pathway term", "Count", "−Log(p-value)"], ["hsa04612:Antigen processing and presentation", "5", "4.241909"], ["hsa04145:Phagosome", "6", "4.228601"], ["hsa05168:Herpes simplex infection", "6", "3.858941"], ["hsa04080:Neuroactive ligand-receptor interaction", "6", "3.025758"], ["hsa05332:Graft-versus-host disease", "3", "2.399844"], ["hsa05330:Allograft rejection", "3", "2.302013"], ["hsa04940:Type I diabetes mellitus", "3", "2.194244"], ["hsa05320:Autoimmune thyroid disease", "3", "2.014217"], ["hsa05134:Legionellosis", "3", "1.982622"], ["hsa05416:Viral myocarditis", "3", "1.93748"]], "row_count": 11, "column_count": 3, "numeric_cells": 30, "header_rows": 1, "locator": "section[13]/table-wrap[3]#Tab6"}}], "gaps": ["asset:data:geo:GSE121367 not downloaded", "asset:data:geo:GSE121367 licence not read", "asset:data:geo:GSE17025 not downloaded", "asset:data:geo:GSE17025 licence not read"]}, "analysis": {"state": "partial", "methods": [{"id": "method-1", "family": "survival_analysis", "specific": "kaplan_meier", "label": "Survival analysis", "dsl_operations": ["survival_km"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["time_to_event_with_censoring"], "evidence": {"score": 0.7, "band": "medium", "quote": "Kaplan-Meier"}}, {"id": "method-2", "family": "network_analysis", "specific": "ppi_network", "label": "Network / pathway analysis", "dsl_operations": ["build_graph", "centrality_scores", "pathway_enrich"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["edge_list"], "evidence": {"score": 0.7, "band": "medium", "quote": "protein-protein interaction"}}, {"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"}}, {"id": "method-4", "family": null, "specific": null, "label": "Kaplan–Meier survival analysis", "dsl_operations": [], "missing_operations": [], "expressible": null, "parameters": {}, "data_shapes": [], "evidence": {"score": 1.0, "band": "verbatim", "quote": "Kaplan–Meier curves for target genes were generated with the online tool Kaplan–Meier Plotter (http://www.kmplot.com/). A total of 542 RNA-seq data samples of uterine corpus endometrial carcinoma were interrogated. The patients were split into 2 groups (high vs. low) based on the expression level."}}], "targets": [], "gaps": ["method.reader_named_unmapped"]}, "capability": {"state": "complete", "requirements": [{"capability_id": "capability:computational_analysis", "label": "Computational analysis platform", "assay_families": ["meta_analysis", "machine_learning", "survival_analysis", "statistical_regression", "pca", "molecular_docking", "network_analysis", "differential_expression", "gwas"], "availability_state": "owned", "tier_unlocked": "R1", "candidate": "Automated Assays Laravel application and simulated adapters"}], "gaps": []}, "readiness": {"state": "complete", "tier": "R1", "blocking_axis": "none", "blocked_on": "nothing:replicable_now", "axes": {"method": {"tier": "R1", "expressible": true, "required_operations": ["survival_km"], "missing_operations": [], "basis": "The paper names the method it used and the corpus's method extractor maps it onto the DSL catalogue: kaplan_meier."}, "capability": {"tier": "R1", "capability_id": "capability:computational_analysis", "availability_state": "owned", "basis": "The computational analysis is owned. The physical bench the paper used is not, so a physical validation cannot be run here."}, "data": {"tier": "R1", "reachable": true, "accessions": ["GSE121367", "GSE17025"], "resolved_accessions": ["GSE121367", "GSE17025"], "statements": ["The datasets used and/or analyzed during the current study are available from the corresponding author on reasonable request."], "basis": "The paper names GSE121367, GSE17025 in Gene Expression Omnibus (GEO) and the accession resolves in the repository. No dataset was downloaded and no licence was read."}}, "can_run": {"dsl_operations": ["survival_km"], "assets": ["source:pmid:30813939", "data:geo:GSE121367", "asset:table:pmid:30813939:1", "asset:table:pmid:30813939:2", "asset:table:pmid:30813939:3", "asset:table:pmid:30813939:4", "asset:table:pmid:30813939:5", "asset:table:pmid:30813939:6"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE121367"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-10-31T18:14:06Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 3, "usage": {"prompt_tokens": 30191, "completion_tokens": 1614, "cached_tokens": 648}}, "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:30813939", "type": "paper", "label": "pmid:30813939"}, {"id": "source:pmid:30813939", "type": "manuscript", "label": "PMID 30813939 full text"}, {"id": "data:geo:GSE121367", "type": "dataset", "label": "GEO GSE121367"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:30813939", "type": "paper", "label": "pmid:30813939"}, {"id": "source:pmid:30813939", "type": "manuscript", "label": "PMID 30813939 full text"}, {"id": "data:geo:GSE121367", "type": "dataset", "label": "GEO GSE121367"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-30813939", "type": "extraction", "used": ["source:pmid:30813939"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE121367", "type": "accession_resolution", "used": ["data:geo:GSE121367"], "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:30813939", "parent_hash": "sha256:5051fc84aca475d0d51eea29bf2fa01f94ca15945b86bcc426cc5b8869ab6bf7", "fork_of": null, "generation": 6}, "gaps": ["asset:data:geo:GSE121367 licence not read", "asset:data:geo:GSE121367 not downloaded", "asset:data:geo:GSE17025 licence not read", "asset:data:geo:GSE17025 not downloaded", "execution.not_run", "method.reader_named_unmapped", "review.human_critique", "review.independent_reader", "review.machine_critique"], "assays": [{"role": "data_generation", "definition_id": "microarray", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.99, "evidence": ["etrial cancer cell subline named IshikawaPR. Microarray analysis was used to identify differentially", "ne receptor (PGR) coexpression analysis. GEO microarray (GSE17025) was utilized for validation. The", "(MCODEs) were identified. CONCLUSIONS: Using microarray and bioinformatics analyses, we identified D"], "order_basis": "paper_text_order:549", "id": "assay:1"}, {"role": "data_generation", "definition_id": "cell_culture", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.77, "evidence": ["ed atmosphere. IshikawaPR cell was routinely cultured in 10 μM MPA to maintain resistance. Gene ontol"], "order_basis": "paper_text_order:2526", "id": "assay:2"}, {"role": "analysis", "definition_id": "survival_analysis", "definition_version": "f2132e96ae6c7a4e", "definition_digest": null, "required_operations": ["survival_km"], "support_state": "supported", "source_hashes": {"dsl_catalogue": "f2132e96ae6c7a4e"}, "confidence": 0.7, "evidence": ["Kaplan-Meier"], "order_basis": "consumes_earlier_output", "id": "assay:3"}]},"meta":{"api_version":"v1","automation_ladder_snapshot":"ba34b49490d9bfaf","automation_ladder_caveats":["Method extraction is rule-based and has no hand-judged accuracy sample. Evidence bands order textual support; method agreement intervals are null (n=0), never probabilities. Work-type validation does not validate methods.","Operation coverage describes only explicitly named methods. It does not prove a complete protocol, compatible parameters, successful compilation or re-execution. Unrecognised or ambiguous methods require review.","Data reachability is a textual accession or public-data statement. No dataset was downloaded or checked for access, completeness or licence.","Capabilities are planning states seeded from the dated equipment register. No bench ownership, completed quote or partner booking is inferred. Procurement counts are dependencies, not guaranteed replications or financial returns.","Tier and blocker counts are deterministic assessments of this corpus, not measured agreement. R3 is reserved for procurement; unresolved methods and data require human work (R4). The most restrictive axis wins, with capability, method, data as tie-breaks. Resolving one blocker can leave another at the same tier."],"engine":"corpus_engine","engine_provider":"rule_based_v1+lex99e1195c7d6f","run_id":"run-20261023T122449232913","source":"esearch","source_detail":"PubMed mirror biomed_pubmed (read-only)","run_status":"complete","imported_at":"2026-11-03T20:16:52+00:00","generated_at":"2026-11-04T02:47:02+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}}}