{"data":{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:33313152", "kind": "science-record", "revision": 7, "content_hash": "sha256:521bb38a641b290e17fec890af86a594c79f9e42ba39eb50ffbfbacc7f105a76", "created_at": "2026-11-01T15:41:19Z", "updated_at": "2026-11-01T22:02:43Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Identification and validation of key genes mediating intracranial aneurysm rupture by weighted correlation network analysis.", "doi": "10.21037/atm-20-4083", "pmid": "33313152", "authors": ["Siliang Chen", "Dan Yang", "Bao Liu", "Lei Wang", "Yuexin Chen", "Wei Ye", "Changwei Liu", "Leng Ni", "Xiaobo Zhang", "Yuehong Zheng"], "journal": "Annals of translational medicine", "year": 2020, "abstract": "BACKGROUND: Rupture of intracranial aneurysm (IA) is the leading cause of subarachnoid hemorrhage. However, there are few pharmacological therapies available for the prevention of IA rupture. Therefore, exploring the molecular mechanisms which underlie IA rupture and identifying the potential molecular targets for preventing the rupture of IA is of vital importance.\nMETHODS: We used the Gene Expression Omnibus (GEO) datasets GSE13353, GSE15629, and GSE54083 in our study. The 3 datasets were merged and normalized. Differentially expressed gene (DEG) screening and weighted correlation network analysis (WGCNA) were conducted. The co-expression patterns between ruptured IA samples and unruptured IA samples were compared. Then, the DEGs were mapped into the whole co-expression network of ruptured IA samples, and a DEG co-expression network was generated. Molecular Complex Detection (MCODE) (http://baderlab.org/Software/MCODE) was used to identify key genes based on the DEG co-expression network. Finally, key genes were validated using another GEO dataset (GSE122897), and their potential diagnostic values were shown using receiver operating characteristic (ROC) analysis.\nRESULTS: In our study, 49 DEGs were screened while 8 and 6 gene modules were detected based on ruptured IA samples and unruptured IA samples, respectively. Pathways associated with inflammation and immune response were clustered in the salmon module of ruptured IA samples. The DEG co-expression network with 35 nodes and 168 edges was generated, and 14 key genes were identified based on this DEG co-expression network. The gene with the highest degree in the key gene cluster was CXCR4. All key genes were validated using GSE122897, and they all showed the potential diagnostic value in predicting IA rupture.\nCONCLUSIONS: Using a weighted gene co-expression network approach, we identified 8 and 6 modules for ruptured IA and unruptured IA, respectively. After that, we identified the hub genes for each module and key genes based on the DEG co-expression network. All these key genes were validated by another GEO dataset and might serve as potential targets for pharmacological therapies and diagnostic markers in predicting IA rupture. Further studies are needed to elucidate the detailed molecular mechanisms and biological functions of these key genes which underlie the rupture of IA.", "claims": [{"id": "claim-data-access", "statement": "The raw datasets were available from the GEO database (http://www.ncbi.nlm.nih.gov/geo/; GSE13353, GSE15629, GSE54083 and GSE122897).", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:33313152", "locator": "sections[3] \"Medical ethics\" paragraph 2", "quote": "The raw datasets were available from the GEO database (http://www.ncbi.nlm.nih.gov/geo/; GSE13353, GSE15629, GSE54083 and GSE122897)."}], "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:33313152"], "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:GSE122897"], "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:GSE122897"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:33313152", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.21037/atm-20-4083", "sha256": "sha256:788757f21982619ff4d8c44d46e074a6997a3b2499f2c3aefdf62b976a2df0f6", "bytes": 35600, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.21037/atm-20-4083", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC7723540", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE122897", "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=GSE122897", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE122897", "version": null, "note": "The raw datasets were available from the GEO database (http://www.ncbi.nlm.nih.gov/geo/; GSE13353, GSE15629, GSE54083 and GSE122897).", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The raw datasets were available from the GEO database (http://www.ncbi.nlm.nih.gov/geo/; GSE13353, GSE15629, GSE54083 and GSE122897).", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM3487837", "GSM3487838", "GSM3487839", "GSM3487840", "GSM3487841", "GSM3487842", "GSM3487843", "GSM3487844", "GSM3487845", "GSM3487846", "GSM3487847", "GSM3487848", "GSM3487849", "GSM3487850", "GSM3487851", "GSM3487852", "GSM3487853", "GSM3487854", "GSM3487855", "GSM3487856", "GSM3487857", "GSM3487858", "GSM3487859", "GSM3487860", "GSM3487861", "GSM3487862", "GSM3487863", "GSM3487864", "GSM3487865", "GSM3487866", "GSM3487867", "GSM3487868", "GSM3487869", "GSM3487870", "GSM3487871", "GSM3487872", "GSM3487873", "GSM3487874", "GSM3487875", "GSM3487876", "GSM3487877", "GSM3487878", "GSM3487879", "GSM3487880", "GSM3487881", "GSM3487882", "GSM3487883", "GSM3487884", "GSM3487885", "GSM3487886", "GSM3487887", "GSM3487888", "GSM3487889", "GSM3487890", "GSM3487891", "GSM3487892", "GSM3487893", "GSM3487894", "GSM3487895", "GSM3487896"], "sample_count": 60, "group_sizes": null, "group_sizes_basis": null, "platform": "16791", "taxon": "Homo sapiens", "title": "RNA Sequencing Analysis of Intracranial Aneurysm Walls Reveals Involvement of Lysosomes and Immunoglobulins in Rupture", "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:GSE13353", "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=GSE13353", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE13353", "version": null, "note": "The raw datasets were available from the GEO database (http://www.ncbi.nlm.nih.gov/geo/; GSE13353, GSE15629, GSE54083 and GSE122897).", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The raw datasets were available from the GEO database (http://www.ncbi.nlm.nih.gov/geo/; GSE13353, GSE15629, GSE54083 and GSE122897).", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM337102", "GSM337103", "GSM337104", "GSM337105", "GSM337106", "GSM337107", "GSM337108", "GSM337109", "GSM337110", "GSM337111", "GSM337112", "GSM337113", "GSM337114", "GSM337115", "GSM337116", "GSM337117", "GSM337118", "GSM337119", "GSM337120"], "sample_count": 19, "group_sizes": null, "group_sizes_basis": null, "platform": "570", "taxon": "Homo sapiens", "title": "Comparison of gene expression between ruptured and unruptured human intracranial aneurysms", "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:GSE15629", "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=GSE15629", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE15629", "version": null, "note": "The raw datasets were available from the GEO database (http://www.ncbi.nlm.nih.gov/geo/; GSE13353, GSE15629, GSE54083 and GSE122897).", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The raw datasets were available from the GEO database (http://www.ncbi.nlm.nih.gov/geo/; GSE13353, GSE15629, GSE54083 and GSE122897).", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM391277", "GSM391278", "GSM391279", "GSM391280", "GSM391281", "GSM391282", "GSM391283", "GSM391284", "GSM391285", "GSM391286", "GSM391287", "GSM391288", "GSM391289", "GSM391290", "GSM391291", "GSM391292", "GSM391293", "GSM391294", "GSM391295"], "sample_count": 19, "group_sizes": null, "group_sizes_basis": null, "platform": "6244", "taxon": "Homo sapiens", "title": "Global expression profiling of ruptured and unruptured human intracranial aneurysms", "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:GSE54083", "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=GSE54083", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE54083", "version": null, "note": "The raw datasets were available from the GEO database (http://www.ncbi.nlm.nih.gov/geo/; GSE13353, GSE15629, GSE54083 and GSE122897).", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The raw datasets were available from the GEO database (http://www.ncbi.nlm.nih.gov/geo/; GSE13353, GSE15629, GSE54083 and GSE122897).", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM1306885", "GSM1306886", "GSM1306887", "GSM1306888", "GSM1306889", "GSM1306890", "GSM1306891", "GSM1306892", "GSM1306893", "GSM1306894", "GSM1306895", "GSM1306896", "GSM1306897", "GSM1306898", "GSM1306899", "GSM1306900", "GSM1306901", "GSM1306902", "GSM1306903", "GSM1306904", "GSM1306905", "GSM1306906", "GSM1306907"], "sample_count": 23, "group_sizes": null, "group_sizes_basis": null, "platform": "4133", "taxon": "Homo sapiens", "title": "Gene expression profiling of intracranial aneurysms", "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:33313152:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:e7908ce11a760971e02b9a85b2cff7d0ba668ed2cd51e9fef400414ecd32f3a7", "bytes": 1378, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[13]/table-wrap[1]#t1", "version": null, "note": "DEGs with top-10 fold-change (ruptured IA/unruptured IA)", "structure": {"pmcid": "PMC7723540", "section_index": 13, "section_title": "DEG screening", "row_count": 23, "column_count": 3}, "table": {"label": "Table 1", "caption": "DEGs with top-10 fold-change (ruptured IA/unruptured IA)", "rows": [["Gene symbol", "Official full name", "Log2(fold-change)"], ["Up-regulated", "", ""], ["PPBP", "Pro-platelet basic protein", "1.67"], ["PF4", "Platelet factor 4", "1.19"], ["S100A8", "S100 calcium binding protein A8", "1.09"], ["FPR1", "Formyl peptide receptor 1", "1.01"], ["C15orf48", "Chromosome 15 open reading frame 48", "0.91"], ["NCF2", "Neutrophil cytosolic factor 2", "0.91"], ["RGS18", "Regulator of G protein signaling 18", "0.90"], ["UPP1", "Uridine phosphorylase 1", "0.89"], ["CXCR4", "C-X-C motif chemokine receptor 4", "0.88"], ["SLA", "Src like adaptor", "0.87"], ["Down-regulated", "", ""], ["NR1D2", "Nuclear receptor subfamily 1 group D member 2", "−1.05"], ["ATP1A2", "ATPase Na+/K+ transporting subunit alpha 2", "−0.95"], ["FMO2", "Flavin containing dimethylaniline monoxygenase 2", "−0.89"], ["SLC6A1", "Solute carrier family 6 member 1", "−0.77"], ["CYP4X1", "Cytochrome P450 family 4 subfamily X member 1", "−0.76"], ["NTRK3", "Neurotrophic receptor tyrosine kinase 3", "−0.73"], ["PER3", "Period circadian regulator 3", "−0.66"], ["ZIC1", "Zic family member 1", "−0.63"], ["OPCML", "Opioid binding protein/cell adhesion molecule like", "−0.63"], ["ZMAT1", "Zinc finger matrin-type 1", "−0.61"]], "row_count": 23, "column_count": 3, "numeric_cells": 40, "header_rows": 1, "locator": "section[13]/table-wrap[1]#t1"}}, {"id": "asset:table:pmid:33313152:2", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:10480c01a8b36a17f670c42e1700444562a9904a379589c043f356173efcb813", "bytes": 961, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[15]/table-wrap[1]#t2", "version": null, "note": "GO-BP terms and KEGG pathways with top-10 count number for ruptured IA", "structure": {"pmcid": "PMC7723540", "section_index": 15, "section_title": "Co-expression pattern comparison", "row_count": 15, "column_count": 4}, "table": {"label": "Table 2", "caption": "GO-BP terms and KEGG pathways with top-10 count number for ruptured IA", "rows": [["ID", "Terms", "Count", "-logP"], ["GO-BP", "", "", ""], ["GO:0007165", "Signal transduction", "13", "1.94"], ["GO:0006954", "Inflammatory response", "11", "4.77"], ["GO:0006955", "Immune response", "10", "3.64"], ["GO:0045087", "Innate immune response", "9", "2.89"], ["GO:0042742", "Defense response to bacterium", "7", "4.09"], ["GO:0007155", "Cell adhesion", "7", "1.58"], ["GO:0002576", "Platelet degranulation", "6", "3.81"], ["GO:0051092", "Positive regulation of NF-kappaB transcription factor activity", "6", "3.29"], ["GO:0032496", "Response to lipopolysaccharide", "6", "2.88"], ["GO:0030593", "Neutrophil chemotaxis", "5", "3.50"], ["KEGG pathway", "", "", ""], ["hsa04060", "Cytokine-cytokine receptor interaction", "8", "2.93"], ["hsa04062", "Chemokine signaling pathway", "5", "1.43"]], "row_count": 15, "column_count": 4, "numeric_cells": 36, "header_rows": 1, "locator": "section[15]/table-wrap[1]#t2"}}, {"id": "asset:table:pmid:33313152:3", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:e42d06b2a6a0343402ab29987ab4e87b9b42a464edfbc67a88d4da07fd58a455", "bytes": 924, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[16]/table-wrap[1]#t3", "version": null, "note": "Key genes mediating rupture of IA", "structure": {"pmcid": "PMC7723540", "section_index": 16, "section_title": "Hub gene and key gene mining", "row_count": 15, "column_count": 3}, "table": {"label": "Table 3", "caption": "Key genes mediating rupture of IA", "rows": [["Gene ID", "Gene symbol", "Official full name"], ["84419", "C15orf48", "Chromosome 15 open reading frame 48"], ["366", "AQP9", "Aquaporin 9"], ["6503", "SLA", "Src like adaptor"], ["4354", "MPP1", "Membrane palmitoylated protein 1"], ["23024", "PDZRN3", "PDZ domain containing ring finger 3"], ["284", "ANGPT1", "Angiopoietin 1"], ["2357", "FPR1", "Formyl peptide receptor 1"], ["290", "ANPEP", "Alanyl aminopeptidase, membrane"], ["5552", "SRGN", "Serglycin"], ["4688", "NCF2", "Neutrophil cytosolic factor 2"], ["128346", "C1orf162", "Chromosome 1 open reading frame 162"], ["10312", "TCIRG1", "T cell immune regulator 1, ATPase H+ transporting V0 subunit a3"], ["7852", "CXCR4", "C-X-C motif chemokine receptor 4"], ["2268", "FGR", "FGR proto-oncogene, Src family tyrosine kinase"]], "row_count": 15, "column_count": 3, "numeric_cells": 26, "header_rows": 1, "locator": "section[16]/table-wrap[1]#t3"}}], "gaps": ["asset:data:geo:GSE122897 not downloaded", "asset:data:geo:GSE122897 licence not read", "asset:data:geo:GSE13353 not downloaded", "asset:data:geo:GSE13353 licence not read", "asset:data:geo:GSE15629 not downloaded", "asset:data:geo:GSE15629 licence not read", "asset:data:geo:GSE54083 not downloaded", "asset:data:geo:GSE54083 licence not read"]}, "analysis": {"state": "partial", "methods": [{"id": "method-1", "family": "diagnostic_evaluation", "specific": "roc", "label": "Diagnostic test evaluation", "dsl_operations": ["confusion_counts", "roc_curve", "sensitivity_specificity", "solve_confusion_matrix", "classification_metrics", "published_precision_envelope"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["reference_standard_and_test"], "evidence": {"score": 0.8, "band": "high", "quote": "ROC analysis"}}, {"id": "method-2", "family": null, "specific": null, "label": "Weighted correlation network analysis (WGCNA) using the WGCNA R package; source data were obtained from GEO datasets GSE13353, GSE15629, and GSE54083.", "dsl_operations": [], "missing_operations": [], "expressible": null, "parameters": {}, "data_shapes": [], "evidence": {"score": 1.0, "band": "reordered", "quote": "“The WGCNA R package was used to construct the co-expression networks of ruptured IA samples and unruptured IA samples.” “The datasets GSE13353, GSE15629, and GSE54083 were selected from the GEO database.”"}}], "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": ["confusion_counts", "roc_curve", "sensitivity_specificity", "solve_confusion_matrix", "classification_metrics", "published_precision_envelope"], "missing_operations": [], "basis": "The paper names the method it used and the corpus's method extractor maps it onto the DSL catalogue: roc."}, "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": ["GSE13353", "GSE15629", "GSE54083", "GSE122897"], "resolved_accessions": ["GSE13353", "GSE15629", "GSE54083", "GSE122897"], "statements": ["The raw datasets were available from the GEO database (http://www.ncbi.nlm.nih.gov/geo/; GSE13353, GSE15629, GSE54083 and GSE122897)."], "basis": "The paper names GSE13353, GSE15629, GSE54083, GSE122897 in Gene Expression Omnibus (GEO) database and the accession resolves in the repository. No dataset was downloaded and no licence was read."}}, "can_run": {"dsl_operations": ["confusion_counts", "roc_curve", "sensitivity_specificity", "solve_confusion_matrix", "classification_metrics", "published_precision_envelope"], "assets": ["source:pmid:33313152", "data:geo:GSE122897", "asset:table:pmid:33313152:1", "asset:table:pmid:33313152:2", "asset:table:pmid:33313152:3"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE122897"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-10-31T18:25:05Z", "independence": "single_reader"}, "evidence_check": {"method": "reordered", "availability": "verbatim"}, "calls": 3, "usage": {"prompt_tokens": 28144, "completion_tokens": 1750, "cached_tokens": 792}}, "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:33313152", "type": "paper", "label": "pmid:33313152"}, {"id": "source:pmid:33313152", "type": "manuscript", "label": "PMID 33313152 full text"}, {"id": "data:geo:GSE122897", "type": "dataset", "label": "GEO GSE122897"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:33313152", "type": "paper", "label": "pmid:33313152"}, {"id": "source:pmid:33313152", "type": "manuscript", "label": "PMID 33313152 full text"}, {"id": "data:geo:GSE122897", "type": "dataset", "label": "GEO GSE122897"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-33313152", "type": "extraction", "used": ["source:pmid:33313152"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE122897", "type": "accession_resolution", "used": ["data:geo:GSE122897"], "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:33313152", "parent_hash": "sha256:b3fe1966e32588180bd9a7fc6fc93d9968496833a0a1db5b4ec7ea751fd6972c", "fork_of": null, "generation": 6}, "gaps": ["asset:data:geo:GSE122897 licence not read", "asset:data:geo:GSE122897 not downloaded", "asset:data:geo:GSE13353 licence not read", "asset:data:geo:GSE13353 not downloaded", "asset:data:geo:GSE15629 licence not read", "asset:data:geo:GSE15629 not downloaded", "asset:data:geo:GSE54083 licence not read", "asset:data:geo:GSE54083 not downloaded", "execution.not_run", "method.reader_named_unmapped", "review.human_critique", "review.independent_reader", "review.machine_critique"], "assays": [{"role": "analysis", "definition_id": "diagnostic_evaluation", "definition_version": "f2132e96ae6c7a4e", "definition_digest": null, "required_operations": ["confusion_counts", "roc_curve", "sensitivity_specificity", "solve_confusion_matrix", "classification_metrics", "published_precision_envelope"], "support_state": "supported", "source_hashes": {"dsl_catalogue": "f2132e96ae6c7a4e"}, "confidence": 0.8, "evidence": ["ROC analysis"], "order_basis": "analysis_only", "id": "assay:1"}]},"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":"2026-11-04T02:16:25+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}}}