{"data":{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:28794464", "kind": "science-record", "revision": 9, "content_hash": "sha256:4d37d93d3e2c316d5c09703850120dd4bf02b08bceb919efa9e1c3650749bc28", "created_at": "2026-11-01T15:40:27Z", "updated_at": "2026-11-01T22:43:04Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Expression changes in pelvic organ prolapse: a systematic review and in silico study.", "doi": "10.1038/s41598-017-08185-6", "pmid": "28794464", "authors": ["Maryam B Khadzhieva", "Dmitry S Kolobkov", "Svetlana V Kamoeva", "Lyubov E Salnikova"], "journal": "Scientific reports", "year": 2017, "abstract": "Pelvic organ prolapse (POP) is a highly disabling condition common for a vast number of women worldwide. To contribute to existing knowledge in POP pathogenesis, we performed a systematic review of expression studies on both specific gene and whole-genome/proteome levels and an in silico analysis of publicly available datasets related to POP development. The most extensively investigated genes in individual studies were related to extracellular matrix (ECM) organization. Three premenopausal and two postmenopausal sets from two Gene Expression Omnibus (GEO) studies (GSE53868 and GSE12852) were analyzed; Gene Ontology (GO) terms related to tissue repair (locomotion, biological adhesion, immune processes and other) were enriched in all five datasets. Co-expression was higher in cases than in controls in three premenopausal sets. The shared between two or more datasets up-regulated genes were enriched with those related to inflammatory bowel disease (IBD) in the NHGRI GWAS Catalog. ECM-related genes were not over-represented among differently expressed genes. Up-regulation of genes related to tissue renewal probably reflects compensatory mechanisms aimed at repair of damaged tissue. Inefficiency of this process may have different origins including age-related deregulation of gene expression.", "claims": [{"id": "claim-method", "statement": "Results of two studies submitted to the repository Gene Expression Omnibus (GEO) were processed with GEO2R – an interactive web tool which exploits Limma R packages from Bioconductor project17 for comparison of user-defined groups of samples under the same experimental conditions (http://www.ncbi.nlm.nih.gov/geo/geo2r/).", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:28794464", "locator": "sections[13] \"Microarray data processing\" paragraph 2", "quote": "Results of two studies submitted to the repository Gene Expression Omnibus (GEO) were processed with GEO2R – an interactive web tool which exploits Limma R packages from Bioconductor project17 for comparison of user-defined groups of samples under the same experimental conditions (http://www.ncbi.nlm.nih.gov/geo/geo2r/)."}], "state": "complete"}, {"id": "claim-data-access", "statement": "Three premenopausal and two postmenopausal sets from two Gene Expression Omnibus (GEO) studies (GSE53868 and GSE12852) were analyzed;", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:28794464", "locator": "sections[0] \"Abstract\" paragraph 1", "quote": "Three premenopausal and two postmenopausal sets from two Gene Expression Omnibus (GEO) studies (GSE53868 and GSE12852) were analyzed;"}], "state": "complete"}, {"id": "claim-target-result", "statement": "The paper combined a systematic review with in silico analysis of two public GEO studies, GSE53868 and GSE12852; GEO2R with Limma was used for microarray comparisons, and KOBAS 3.0 with REVIGO was used for gene-set enrichment analysis and GO-term summarization. No numerical result was reported specifically for this methodological target.", "kind": "qualitative", "target": null, "evidence": [{"asset": "source:pmid:28794464", "locator": "sections[0] \"Abstract\" paragraph 1", "quote": "To contribute to existing knowledge in POP pathogenesis, we performed a systematic review of expression studies on both specific gene and whole-genome/proteome levels and an in silico analysis of publicly available datasets related to POP development."}, {"asset": "source:pmid:28794464", "locator": "sections[0] \"Abstract\" paragraph 1", "quote": "Three premenopausal and two postmenopausal sets from two Gene Expression Omnibus (GEO) studies (GSE53868 and GSE12852) were analyzed; Gene Ontology (GO) terms related to tissue repair (locomotion, biological adhesion, immune processes and other) were enriched in all five datasets."}, {"asset": "source:pmid:28794464", "locator": "sections[13] \"Microarray data processing\" paragraph 2", "quote": "Results of two studies submitted to the repository Gene Expression Omnibus (GEO) were processed with GEO2R – an interactive web tool which exploits Limma R packages from Bioconductor project17 for comparison of user-defined groups of samples under the same experimental conditions (http://www.ncbi.nlm.nih.gov/geo/geo2r/)."}, {"asset": "source:pmid:28794464", "locator": "sections[14] \"Gene set enrichment analysis\" paragraph 2", "quote": "These gene sets were treated with KOBAS 3.0 resource7 for Gene Ontology (GO) enrichment analysis."}, {"asset": "source:pmid:28794464", "locator": "sections[14] \"Gene set enrichment analysis\" paragraph 2", "quote": "Web server REVIGO was utilized for summarizing GO terms, which was guided by the P-value9."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "complete", "objective": "The paper combined a systematic review with in silico analysis of two public GEO studies, GSE53868 and GSE12852; GEO2R with Limma was used for microarray comparisons, and KOBAS 3.0 with REVIGO was used for gene-set enrichment analysis and GO-term summarization. No numerical result was reported specifically for this methodological target.", "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:28794464"], "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:GSE12852"], "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:GSE12852"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:28794464", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1038/s41598-017-08185-6", "sha256": "sha256:758955f45f1a5f6363bcb77001f490b54cd17ebadee3c1866325e106e5a8c84e", "bytes": 36526, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1038/s41598-017-08185-6", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC5550478", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE12852", "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=GSE12852", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE12852", "version": null, "note": "Three premenopausal and two postmenopausal sets from two Gene Expression Omnibus (GEO) studies (GSE53868 and GSE12852) were analyzed;", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "Three premenopausal and two postmenopausal sets from two Gene Expression Omnibus (GEO) studies (GSE53868 and GSE12852) were analyzed;", "access_statement_kind": "repository_route_statement", "sample_accessions": ["GSM322499", "GSM322500", "GSM322501", "GSM322502", "GSM322503", "GSM322504", "GSM322505", "GSM322506", "GSM322507", "GSM322508", "GSM322509", "GSM322510", "GSM322511", "GSM322512", "GSM322513", "GSM322514", "GSM322515", "GSM322516", "GSM322517", "GSM322518", "GSM322519", "GSM322520", "GSM322521", "GSM322522", "GSM322523", "GSM322524", "GSM322525", "GSM322526", "GSM322527", "GSM322528", "GSM322529", "GSM322530", "GSM322531", "GSM322532"], "sample_count": 34, "group_sizes": null, "group_sizes_basis": null, "platform": "2986", "taxon": "Homo sapiens", "title": "Gene expression profile in pelvic organ prolapse", "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:GSE53868", "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=GSE53868", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE53868", "version": null, "note": "Three premenopausal and two postmenopausal sets from two Gene Expression Omnibus (GEO) studies (GSE53868 and GSE12852) were analyzed;", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "Three premenopausal and two postmenopausal sets from two Gene Expression Omnibus (GEO) studies (GSE53868 and GSE12852) were analyzed;", "access_statement_kind": "repository_route_statement", "sample_accessions": ["GSM1302316", "GSM1302317", "GSM1302318", "GSM1302319", "GSM1302320", "GSM1302321", "GSM1302322", "GSM1302323", "GSM1302324", "GSM1302325", "GSM1302326", "GSM1302327", "GSM1302328", "GSM1302329", "GSM1302330", "GSM1302331", "GSM1302332", "GSM1302333", "GSM1302334", "GSM1302335", "GSM1302336", "GSM1302337", "GSM1302338", "GSM1302339"], "sample_count": 24, "group_sizes": null, "group_sizes_basis": null, "platform": "18142", "taxon": "Homo sapiens", "title": "Micro-array analysis of the anterior vaginal wall from premenopausal patients with Pelvic Organ Prolapse (POP)", "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:28794464:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:f468591ba24e0beb26a8e7b3243025f703f1cfad1c0bd864348f86e51c70c8e8", "bytes": 4416, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[4]/table-wrap[1]#Tab1", "version": null, "note": "Characteristics of the whole genome/proteome studies of POP.", "structure": {"pmcid": "PMC5550478", "section_index": 4, "section_title": "Overview of whole genome/proteome studies of POP", "row_count": 8, "column_count": 7}, "table": {"label": "Table 1", "caption": "Characteristics of the whole genome/proteome studies of POP.", "rows": [["Dataset", "Number of samples (age/MP status)", "Analysis", "DEG (DEP)", "Main findingsa", "Confirmation of whole genome/proteome data", "Reference"], ["Pubococcygeus muscle in Caucasian POP patients and mixed ethnicity controls", "5 cases (58.9 ± 5.5); 5 controls (45.5 ± 11.4)", "Microarray gene expression", "Down-regulation in POP patients: FC > 2.0, 257 genes; FC > 5, 20 genes; FC > 10, 3 genes. Up-regulation in POP patients: FC > 2.0, 479 genes; FC > 5, 18 genes; FC > 10, 2 genes.", "The genes MYBPH (FC 24.7), MYH3 (FC 17.4) and COMP (FC 6.0) were down-regulated, while smooth muscle myosin heavy chain (FC 11.8), MLCK (FC 5.77) and TNC (FC 5.1) genes were up-regulated in POP patients in comparison with controls.", "No", "10"], ["Full-thickness vaginal wall biopsies from patients with POP and age-, parity -, and body mass index -matched controlsb", "5 PrM cases, 5 PrM controls", "Microarray gene expression", "Upregulated genes (n = 50) comprised those involved in smooth muscle contraction, proteolysis, response to oxidative stress, transcriptional regulation, cytoskeletal organization, and lipid catabolism.", "The PPP1R12A and ADAMTS1 genes were up-regulated 2.4 and 4-fold in cases compared to controls.", "mRNA analysis for 4 matched pairs of POP/control tissues", "12"], ["USLs and RLs from mixed ethnicity patients with uterine prolapse (POP-Q stage ≥ 2) and controls", "8 POP patients (5 PrM and 3 PM); 9 controls (6 PrM and 3 PM)", "Microarray gene expression", "In a combined analysis of expression changes in USLs and RLs, 1521 genes were up-regulated and 1193 genes were down-regulated with FC change 1.5. 249 up-regulated gene probes met FDR criteria ≤ 5.18.", "After FDR correction for multiple testing, genes enriched for ‘immunity and defense’ were up-regulated in POP patients.", "qRT-PCR Up-regulation in POP patients: IL-6 (FC 9.8), ATF3 (FC 2.6), THBS1 (FC 3.5) and PTGS2 (FC 2.4)", "13"], ["Pubocervical fascia from females with POP and SUI and from asymptomatic controlsb", "4 cases (PM); 3 controls (PM)", "Proteomic analysis (two-dimensional electrophoresis and matrix-assisted laser desorption/ionization time-of-flight mass spectrometry)", "7 proteins with an expression FC more than two (3.8 ─ 54.3-fold).", "The expression levels of transgelin (FC 54.3), smooth muscle gamma-actin (FC 6.3), myosin light polypeptide 6 (FC 4.4), and alpha-1 antitrypsin precursor (FC 4.3) were higher in patients than in controls.", "2-DE western blot analysis for transgelin", "11"], ["USLs from Asian women with POP-Q stage 3-4 (cases) or 0-1 (controls)", "12 cases (PM), 5 controls (PM)", "Microarray gene expression", "143 genes were up-regulated and 87 genes were down-regulated with FC > 1.5 (P < 0.05).", "The expression levels of ESRRA (FC 0.434) decreased, while the expression levels of DAPK2 (FC 2.013), IL15 (FC 2.1) and STAP2 (FC 2.392) increased in POP patients compared with controls.", "qRT-PCR for the genes ESRRA, DAPK2, IL15, STAP2", "14"], ["USLs from patients with uterine prolapse and controlsb", "16 POP patients (15 patients PM); 9 controls (7 females PM)", "Microarray gene expression", "21 up-regulated and 7 down-regulated genes with FC > 2.0 were found in patients with POP compared to the control group.", "Down-regulation in POP patients compared with controls after FDR correction for multiple testing: NKX2-3 (FC 2.6) in the whole set; KIF11 (FC 1.3) in patients with ≥ 3 deliveries compared to patients with < 3 deliveries; UGT1A1 (FC 1.4), SCARB1 (FC 3.2) and NKX2-3 (FC 6.2) in PrM patients compared to PrM controls; UGT1A1 (FC 1.1) in PM patients compared to PM controls.", "No", "15"], ["USL samples of patients with stage II to stage IV POP (mean age 61 years) and normal controls (mean age 55 years)b", "No data", "RNA-seq (a HiSeqTM 2500 platform (Illumina))", "After FDR-correction, a total of 81 genes had different expression patterns in POP patients and controls. Sixty-six DEGs did not differ between the POP samples with different stages", "Canonical Wnt receptor signaling pathway was the most significantly enriched GO term (P- value = 3.33E-07), and neuroactive ligand-receptor interaction was the most significantly enriched pathway (P- value = 1.24E-03).", "No", "16"]], "row_count": 8, "column_count": 7, "numeric_cells": 34, "header_rows": 1, "locator": "section[4]/table-wrap[1]#Tab1"}}, {"id": "asset:table:pmid:28794464:2", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:71e3f09f8eb7be849725e011a58681f7171648345caa0c967677c35b6b7b3f55", "bytes": 1220, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[5]/table-wrap[1]#Tab2", "version": null, "note": "Characteristics of the POP datasets in the Gene Expression Omnibus (GEO) database repository.", "structure": {"pmcid": "PMC5550478", "section_index": 5, "section_title": "Overview of available GEO datasets for POP", "row_count": 10, "column_count": 7}, "table": {"label": "Table 2", "caption": "Characteristics of the POP datasets in the Gene Expression Omnibus (GEO) database repository.", "rows": [["Dataset", "Reference", "Tissue", "Number of samples", "GEO accession no; Platform", "Number of DEGa with FDR-corrected P - value < 0.05", "Number of DEGa with FC ≥ 2.0 and P - value < 0.05 (uncorrected for multiplicity)"], ["PrM Caucasian women (cystocele POP-Q stage ≥ 2), n = 12", "Citation missing", "AVW (POP site) versus precervical AVW (non POP site)", "12 women (24 samples)", "GSE53868; GPL18142 Agilent-014850 WHGM 4 × 44K G4112F", "50 (↑ 31; ↓ 19)", "74 (↑ 58; ↓16)"], ["PrM POP women, n = 5b", "Brizzolara et al.13", "RLs", "5", "GSE12852; GPL2986 ABI Human Genome Survey Microarray Version 2", "PrM_RLs set 0", "PrM_RLs set 287 (↑ 246; ↓ 41)"], ["USLs", "5"], ["PrM controls, n = 6b", "RLs", "6", "PrM_USLs set 0", "PrM_USLs set 972 (↑ 949; ↓23)"], ["USL", "6"], ["PM POP women, n = 3b", "RL", "3", "PM_RLs set 0", "PM_RLs set 485 (↑ 345; ↓ 140)"], ["USL", "3"], ["PM controls, n = 3b", "RL", "3", "PM_USLs set 2 (↑ 2; ↓ 0)", "PM_USLs set 494(↑ 263; ↓ 231)"], ["USL", "3"]], "row_count": 10, "column_count": 7, "numeric_cells": 29, "header_rows": 1, "locator": "section[5]/table-wrap[1]#Tab2"}}, {"id": "asset:table:pmid:28794464:3", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:79797698d2e0a2d8d38f62d4cfbc5ce2c116241beb93e1e810450ef79f26eb53", "bytes": 2134, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[8]/table-wrap[1]#Tab3", "version": null, "note": "The results of gene set enrichment analysis for shared genes up-regulated in POP tissues.", "structure": {"pmcid": "PMC5550478", "section_index": 8, "section_title": "Enrichment analysis (GO, KEGG, GWAS Catalog) for the shared gene set", "row_count": 19, "column_count": 6}, "table": {"label": "Table 3", "caption": "The results of gene set enrichment analysis for shared genes up-regulated in POP tissues.", "rows": [["Term", "Input number", "Background number", "P - value", "Corrected P - value", "Genes"], ["KEGG Pathway"], ["Malaria (hsa05144)", "7", "49", "1,25E-09", "1,93E-07", "COMP, ICAM1, IL6, CXCL8, CCL2, THBS1, THBS4"], ["Influenza A (hsa05164)", "8", "176", "3,48E-07", "2,69E-05", "NLRP3, ICAM1, IL6, CXCL8, NXF3, CCL2, SOCS3, RSAD2"], ["Rheumatoid arthritis (hsa05323)", "5", "91", "2,51E-05", "1,19E-03", "CTSK, ICAM1, IL6, CXCL8, CCL2"], ["PI3K-Akt signaling pathway (hsa04151)", "8", "342", "3,91E-05", "1,19E-03", "CDKN1A, COMP, GNGT1, IL6, MCL1, PPP2R2C, THBS1, THBS4"], ["AGE-RAGE signaling pathway in diabetic complications (hsa04933)", "5", "101", "4,04E-05", "1,19E-03", "ICAM1, IL6, CXCL8, SERPINE1, CCL2"], ["Chagas disease (American trypanosomiasis)", "5", "104", "4,62E-05", "1,19E-03", "IL6, CXCL8, SERPINE1, PPP2R2C, CCL2"], ["Hepatitis C (hsa05142)", "5", "133", "1,41E-04", "2,43E-03", "CDKN1A, CXCL8, LDLR, PPP2R2C, SOCS3"], ["Hepatitis B (hsa05161)", "5", "146", "2,15E-04", "3,32E-03", "CDKN1A, EGR2, EGR3, IL6, CXCL8"], ["Phagosome (hsa04145)", "5", "155", "2,80E-04", "3,95E-03", "COMP, FCAR, THBS1, THBS4, COLEC11"], ["HTLV-I infection (hsa05166)", "6", "259", "3,90E-04", "4,91E-03", "CDKN1A, EGR2, ICAM1, IL6, ATF3, IL1R2"], ["Transcriptional misregulation in cancer (hsa05202)", "5", "180", "5,44E-04", "5,63E-03", "CDKN1A, IL6, CXCL8, IL1R2, NR4A3"], ["Herpes simplex infection (hsa05168)", "5", "186", "6,29E-04", "6,09E-03", "IL6, NXF3, CCL2, TNFSF14, SOCS3"], ["Cytokine-cytokine receptor interaction (hsa04060)", "5", "265", "2,89E-03", "2,03E-02", "IL6, CXCL8, CCL2, IL1R2, TNFSF14"], ["Pathways in cancer (hsa05200)", "6", "397", "3,31E-03", "2,13E-02", "CDKN1A, CKS2, GNGT1, IL6, CXCL8, BDKRB1"], ["The NHGRI GWAS Catalog"], ["Inflammatory bowel disease", "9", "271", "8,03E-07", "1,26E-04", "BORCS5, CCL2, CXCL8, ICAM1, IL1R2, NFIL3, PTPRC, SLC11A1, SLC22A4"], ["Crohn’s disease", "6", "256", "3,68E-04", "1,15E-02", "SLC22A4, ICAM1, CCL2, TAGAP, PTPRC, CNNM1"]], "row_count": 19, "column_count": 6, "numeric_cells": 82, "header_rows": 1, "locator": "section[8]/table-wrap[1]#Tab3"}}], "gaps": ["asset:data:geo:GSE12852 not downloaded", "asset:data:geo:GSE12852 licence not read", "asset:data:geo:GSE53868 not downloaded", "asset:data:geo:GSE53868 licence not read"]}, "analysis": {"state": "complete", "methods": [{"id": "method-1", "family": "differential_expression", "specific": "limma_voom", "label": "Differential expression analysis", "dsl_operations": ["normalise_counts", "differential_expression_fit", "fdr_bh"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["count_matrix_with_condition"], "evidence": {"score": 1.0, "band": "verbatim", "quote": "Results of two studies submitted to the repository Gene Expression Omnibus (GEO) were processed with GEO2R – an interactive web tool which exploits Limma R packages from Bioconductor project17 for comparison of user-defined groups of samples under the same experimental conditions (http://www.ncbi.nlm.nih.gov/geo/geo2r/)."}}, {"id": "method-2", "family": "genetic_association", "specific": "gwas", "label": "Genetic association (GWAS / linkage / MR)", "dsl_operations": ["gwas_locus_scan"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["genotype_phenotype_table"], "evidence": {"score": 0.7, "band": "medium", "quote": "GWAS"}}], "targets": [], "gaps": []}, "capability": {"state": "complete", "requirements": [{"capability_id": "capability:computational_analysis", "label": "Computational analysis platform", "assay_families": ["meta_analysis", "machine_learning", "survival_analysis", "statistical_regression", "pca", "molecular_docking", "network_analysis", "differential_expression", "gwas"], "availability_state": "owned", "tier_unlocked": "R1", "candidate": "Automated Assays Laravel application and simulated adapters"}], "gaps": []}, "readiness": {"state": "complete", "tier": "R1", "blocking_axis": "none", "blocked_on": "nothing:replicable_now", "axes": {"method": {"tier": "R1", "expressible": true, "required_operations": ["normalise_counts", "differential_expression_fit", "fdr_bh"], "missing_operations": [], "basis": "The paper names the method it used and the corpus's method extractor maps it onto the DSL catalogue: limma_voom."}, "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": ["GSE53868", "GSE12852"], "resolved_accessions": ["GSE53868", "GSE12852"], "statements": ["Three premenopausal and two postmenopausal sets from two Gene Expression Omnibus (GEO) studies (GSE53868 and GSE12852) were analyzed;"], "basis": "The paper names GSE53868, GSE12852 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": ["normalise_counts", "differential_expression_fit", "fdr_bh"], "assets": ["source:pmid:28794464", "data:geo:GSE12852", "asset:table:pmid:28794464:1", "asset:table:pmid:28794464:2", "asset:table:pmid:28794464:3"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE12852"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-10-31T18:31:51Z", "independence": "same_provider"}, "evidence_check": {"method": "verbatim", "availability": null}, "calls": 8, "usage": {"prompt_tokens": 75973, "completion_tokens": 4539, "cached_tokens": 19993}}, "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:28794464", "type": "paper", "label": "pmid:28794464"}, {"id": "source:pmid:28794464", "type": "manuscript", "label": "PMID 28794464 full text"}, {"id": "data:geo:GSE12852", "type": "dataset", "label": "GEO GSE12852"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:28794464", "type": "paper", "label": "pmid:28794464"}, {"id": "source:pmid:28794464", "type": "manuscript", "label": "PMID 28794464 full text"}, {"id": "data:geo:GSE12852", "type": "dataset", "label": "GEO GSE12852"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-28794464", "type": "extraction", "used": ["source:pmid:28794464"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE12852", "type": "accession_resolution", "used": ["data:geo:GSE12852"], "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:28794464", "parent_hash": "sha256:1fe660b681d8295f81e7398d67343b884a5c7a2c4d23af2bf2e20a0b3eb3fd28", "fork_of": null, "generation": 8}, "gaps": ["asset:data:geo:GSE12852 licence not read", "asset:data:geo:GSE12852 not downloaded", "asset:data:geo:GSE53868 licence not read", "asset:data:geo:GSE53868 not downloaded", "execution.not_run", "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": 0.93, "evidence": ["Materials and Methods Microarray data processing Results of two studies submi"], "order_basis": "paper_text_order:1395", "id": "assay:1"}, {"role": "analysis", "definition_id": "differential_expression", "definition_version": "f2132e96ae6c7a4e", "definition_digest": null, "required_operations": ["normalise_counts", "differential_expression_fit", "fdr_bh"], "support_state": "supported", "source_hashes": {"dsl_catalogue": "f2132e96ae6c7a4e"}, "confidence": 1.0, "evidence": ["Results of two studies submitted to the repository Gene Expression Omnibus (GEO) were processed with GEO2R – an interactive web tool which exploits Limma R packages from Bioconductor project17 for comparison of user-defined groups of samples under the same experimental conditions (http://www.ncbi.nlm.nih.gov/geo/geo2r/)."], "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":"2026-11-04T03:13:17+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}}}