{"data":{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:30918899", "kind": "science-record", "revision": 6, "content_hash": "sha256:710ba6ff6f0f050df343fcdbe7d448862930be0b28912d7ccb172cbc18f83539", "created_at": "2026-11-01T15:40:43Z", "updated_at": "2026-11-01T22:43:53Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Differential Expression of mRNAs in the Brain Tissues of Patients with Alzheimer's Disease Based on GEO Expression Profile and Its Clinical Significance.", "doi": "10.1155/2019/8179145", "pmid": "30918899", "authors": ["Guowei Ma", "Mingyan Liu", "Ke Du", "Xin Zhong", "Shiqiang Gong", "Linchi Jiao", "Minjie Wei"], "journal": "BioMed research international", "year": 2019, "abstract": "BACKGROUND: Early diagnosis of Alzheimer's disease (AD) is an urgent point for AD prevention and treatment. The biomarkers of AD still remain indefinite. Based on the bioinformatics analysis of mRNA differential expressions in the brain tissues and the peripheral blood samples of Alzheimer's disease (AD) patients, we investigated the target mRNAs that could be used as an AD biomarker and developed a new effective, practical clinical examination program.\nMETHODS: We compared the AD peripheral blood mononuclear cells (PBMCs) expression dataset (GEO accession GSE4226 and GSE18309) with AD brain tissue expression datasets (GEO accessions GSE1297 and GSE5281) from GEO in the present study. The GEO gene database was used to download the appropriate gene expression profiles to analyze the differential mRNA expressions between brain tissue and blood of AD patients and normal elderly. The Venn diagram was used to screen out the differential expression of mRNAs between the brain tissue and blood. The protein-protein interaction network map (PPI) was used to view the correlation between the possible genes. GO (gene ontology) and KEGG (Kyoto Gene and Genomic Encyclopedia) were used for gene enrichment analysis to determine the major affected genes and the function or pathway.\nRESULTS: Bioinformatics analysis revealed that there were differentially expressed genes in peripheral blood and hippocampus of AD patients. There were 4958 differential mRNAs in GSE18309, 577 differential mRNAs in GSE4226 in AD PBMCs sample, 7464 differential mRNAs in GSE5281, and 317 differential mRNAs in GSE129 in AD brain tissues, when comparing between AD patients and healthy elderly. Two mRNAs of RAB7A and ITGB1 coexpressed in hippocampus and peripheral blood were screened. Furthermore, functions of differential genes were enriched by the PPI network map, GO, and KEGG analysis, and finally the chemotaxis, adhesion, and inflammatory reactions were found out, respectively.\nCONCLUSIONS: ITGB1 and RAB7A mRNA expressions were both changed in hippocampus and PBMCs, highly suggested being used as an AD biomarker with AD. Also, according to the results of this analysis, it is indicated that we can test the blood routine of the elderly for 2-3 years at a frequency of 6 months or one year. When a patient continuously detects the inflammatory manifestations, it is indicated as a potentially high-risk AD patient for AD prevention.", "claims": [{"id": "claim-method", "statement": "Difference analysis was performed by GEO2R analysis with P < 0.05 and |logFC| > 1 as cutoff values for screening differentially expressed genes (DEGs).", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:30918899", "locator": "sections[5] \"2.3. Difference Analysis\" paragraph 2", "quote": "Difference analysis was performed by GEO2R analysis with P < 0.05 and |logFC| > 1 as cutoff values for screening differentially expressed genes (DEGs)."}], "state": "complete"}, {"id": "claim-data-access", "statement": "The data used to support the findings of this study are available from the corresponding author upon request.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:30918899", "locator": "sections[11] \"Data Availability\" paragraph 2", "quote": "The data used to support the findings of this study are available from the corresponding author upon 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:30918899"], "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:GSE1297"], "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:GSE1297"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:30918899", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1155/2019/8179145", "sha256": "sha256:3bd5d563d19b2b8e0b45d1e3d0d6814120b1612c97815befae94f1c7f361525d", "bytes": 26642, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1155/2019/8179145", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC6413412", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE1297", "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=GSE1297", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE1297", "version": null, "note": "The data used to support the findings of this study are available from the corresponding author upon request.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The data used to support the findings of this study are available from the corresponding author upon request.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM21203", "GSM21204", "GSM21205", "GSM21206", "GSM21207", "GSM21208", "GSM21209", "GSM21210", "GSM21211", "GSM21212", "GSM21213", "GSM21214", "GSM21215", "GSM21216", "GSM21217", "GSM21218", "GSM21219", "GSM21220", "GSM21221", "GSM21222", "GSM21223", "GSM21224", "GSM21225", "GSM21226", "GSM21227", "GSM21228", "GSM21229", "GSM21230", "GSM21231", "GSM21232", "GSM21233"], "sample_count": 31, "group_sizes": null, "group_sizes_basis": null, "platform": "96", "taxon": "Homo sapiens", "title": "Incipient Alzheimer's Disease: Microarray Correlation Analyses", "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:GSE18309", "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=GSE18309", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE18309", "version": null, "note": "The data used to support the findings of this study are available from the corresponding author upon request.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The data used to support the findings of this study are available from the corresponding author upon request.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM457169", "GSM457170", "GSM457171", "GSM457172", "GSM457173", "GSM457174", "GSM457175", "GSM457176", "GSM457177"], "sample_count": 9, "group_sizes": null, "group_sizes_basis": null, "platform": "570", "taxon": "Homo sapiens", "title": "Transcriptomes in Peripheral Blood Mononuclear Cells of Dementia and Alzheimer Patients", "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:GSE4226", "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=GSE4226", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE4226", "version": null, "note": "The data used to support the findings of this study are available from the corresponding author upon request.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The data used to support the findings of this study are available from the corresponding author upon request.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM96454", "GSM96455", "GSM96456", "GSM96457", "GSM96458", "GSM96459", "GSM96461", "GSM96462", "GSM96463", "GSM96464", "GSM96466", "GSM96467", "GSM96468", "GSM96469", "GSM96470", "GSM96471", "GSM96472", "GSM96473", "GSM96474", "GSM96475", "GSM96476", "GSM96477", "GSM96478", "GSM96479", "GSM96480", "GSM96481", "GSM96482", "GSM96483"], "sample_count": 28, "group_sizes": null, "group_sizes_basis": null, "platform": "1211", "taxon": "Homo sapiens", "title": "Alzheimer Disease peripheral blood mononuclear cell expression", "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:GSE5281", "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=GSE5281", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE5281", "version": null, "note": "The data used to support the findings of this study are available from the corresponding author upon request.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The data used to support the findings of this study are available from the corresponding author upon request.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM119615", "GSM119616", "GSM119617", "GSM119618", "GSM119619", "GSM119620", "GSM119621", "GSM119622", "GSM119623", "GSM119624", "GSM119625", "GSM119626", "GSM119627", "GSM119628", "GSM119629", "GSM119630", "GSM119631", "GSM119632", "GSM119633", "GSM119634", "GSM119635", "GSM119636", "GSM119637", "GSM119638", "GSM119639", "GSM119640", "GSM119641", "GSM119642", "GSM119643", "GSM119644", "GSM119645", "GSM119646", "GSM119647", "GSM119648", "GSM119649", "GSM119650", "GSM119651", "GSM119652", "GSM119653", "GSM119654", "GSM119655", "GSM119656", "GSM119657", "GSM119658", "GSM119659", "GSM119660", "GSM119661", "GSM119662", "GSM119663", "GSM119664", "GSM119665", "GSM119666", "GSM119667", "GSM119668", "GSM119669", "GSM119670", "GSM119671", "GSM119672", "GSM119673", "GSM119674", "GSM119675", "GSM119676", "GSM119677", "GSM119678", "GSM119679", "GSM119680", "GSM119681", "GSM119682", "GSM119683", "GSM119684", "GSM119685", "GSM119686", "GSM119687", "GSM119688", "GSM238763", "GSM238790", "GSM238791", "GSM238792", "GSM238793", "GSM238794", "GSM238795", "GSM238796", "GSM238797", "GSM238798", "GSM238799", "GSM238800", "GSM238801", "GSM238802", "GSM238803", "GSM238804", "GSM238805", "GSM238806", "GSM238807", "GSM238808", "GSM238809", "GSM238810", "GSM238811", "GSM238812", "GSM238813", "GSM238815", "GSM238816", "GSM238817", "GSM238818", "GSM238819", "GSM238820", "GSM238821", "GSM238822", "GSM238823", "GSM238824", "GSM238825", "GSM238826", "GSM238827", "GSM238834", "GSM238835", "GSM238837", "GSM238838", "GSM238839", "GSM238840", "GSM238841", "GSM238842", "GSM238843", "GSM238844", "GSM238845", "GSM238846", "GSM238847", "GSM238848", "GSM238851", "GSM238854", "GSM238855", "GSM238856", "GSM238857", "GSM238858", "GSM238860", "GSM238861", "GSM238862", "GSM238863", "GSM238864", "GSM238865", "GSM238867", "GSM238868", "GSM238870", "GSM238871", "GSM238872", "GSM238873", "GSM238874", "GSM238875", "GSM238877", "GSM238941", "GSM238942", "GSM238943", "GSM238944", "GSM238945", "GSM238946", "GSM238947", "GSM238948", "GSM238949", "GSM238951", "GSM238952", "GSM238953", "GSM238955", "GSM238963"], "sample_count": 161, "group_sizes": null, "group_sizes_basis": null, "platform": "570", "taxon": "Homo sapiens", "title": "Alzheimer's disease and the normal aged brain (steph-affy-human-433773)", "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:30918899:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:90e36c7c6b519459d74ccca3687bdc2a044f69fb218e6675d002aa50fc0fc0a9", "bytes": 2340, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[1]/table-wrap[1]#tab1", "version": null, "note": "Current mainstream detection methods of AD.", "structure": {"pmcid": "PMC6413412", "section_index": 1, "section_title": "1. Introduction", "row_count": 10, "column_count": 4}, "table": {"label": "Table 1", "caption": "Current mainstream detection methods of AD.", "rows": [["Detection method", "Principle", "Advantage", "Disadvantage"], ["MMSE", "The most common scale of intelligence impairment at present. Illiteracy ≤ 17 points, primary school degree ≤ 20 points, middle school degree ≤ 22 points, college degree ≤ 23 points, indicates the impairment of cognitive function.", "Low cost, concise content, less time for measurement, and easy to be accepted by the elderly", "Only screening the patients with moderate-to-severe symptoms"], [""], ["Structural imaging: head CT (thin scan) and MRI (coronal) scanning", "Diagnostic imaging techniques show significant atrophy of the cerebral cortex, especially in the hippocampus and medial temporal lobe, supporting the clinical diagnosis of AD.", "Used to exclude other underlying diseases and to identify specific imaging findings of AD", "Convenience not as good as MMSE, expensive cost, hospital equipment support, low penetration rate"], [""], ["18FDG-PET", "It shows the reduction of glucose metabolism in the dome and upper/posterior temporal region, posterior cingulate cortex, and anterior cranial lobe, revealing specific abnormal changes in AD. In the late period of AD, the frontal lobe metabolism was reduced.", "Improving the reliability of dementia diagnosis and being suitable for the differential diagnosis of AD and other dementia", "Convenience not as good as MMSE, expensive cost, specific equipment support needed, penetration rate"], [""], ["EEG", "The EEG of AD is characterized by a decrease in alpha wave, an increase in theta wave, and a decrease in the average frequency.", "Used for the differential diagnosis of AD, providing early evidence of prion disease or other brain diseases", "33% of patients with early AD are normal without change in EEG and low penetration rate"], [""], ["Biological markers", "Dynamically observing the progression of the disease by using proteins or miRNAs in body fluids such as peripheral blood, cerebrospinal fluid, and urine biology as markers to increase the specificity of the diagnosis.", "Noninvasive, simple and inexpensive, and of low price", "Low repeatability, problems with accuracy and specificity, lack of standards"]], "row_count": 10, "column_count": 4, "numeric_cells": 3, "header_rows": 1, "locator": "section[1]/table-wrap[1]#tab1"}}, {"id": "asset:table:pmid:30918899:2", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:d728d7fa07f5ad1171d3f97ffef02ba41a53e90666770e98708b323ae393b432", "bytes": 611, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[6]/table-wrap[1]#tab2", "version": null, "note": "GEO microarray datasets.", "structure": {"pmcid": "PMC6413412", "section_index": 6, "section_title": "3. Results", "row_count": 8, "column_count": 5}, "table": {"label": "Table 2", "caption": "GEO microarray datasets.", "rows": [["Chip serial number", "Elderly sample", "AD sample", "Resource", "Platform"], ["GSE1297", "9", "22", "Hippocampus", "GPL1211 NIA MGC, Mammalian Genome Collection"], [""], ["GSE5281", "13", "10", "Hippocampus", "GPL1211 NIA MGC, Mammalian Genome Collection"], [""], ["GSE18309", "3", "6", "PBMCs", "GPL570 [HG-U133_Plus_2] Affymetrix Human Genome U133 Plus 2.0 Array"], [""], ["GSE4226", "14", "14", "PBMCs", "GPL96 [HG-U133A] Affymetrix Human Genome U133A Array"]], "row_count": 8, "column_count": 5, "numeric_cells": 16, "header_rows": 1, "locator": "section[6]/table-wrap[1]#tab2"}}, {"id": "asset:table:pmid:30918899:3", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:7df060693a77bb630ce93f426b14c73f6f004cdc21d77dcd56a9aa8b1f90622f", "bytes": 2111, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[6]/table-wrap[2]#tab3", "version": null, "note": "TOP lowest term P value corrected with Bonferroni step-down of RAB7A and ITGB1.", "structure": {"pmcid": "PMC6413412", "section_index": 6, "section_title": "3. Results", "row_count": 24, "column_count": 7}, "table": {"label": "Table 3", "caption": "TOP lowest term P value corrected with Bonferroni step-down of RAB7A and ITGB1.", "rows": [["CHIP", "GOID", "GO Term", "Number of Genes", "Associated genes (%)", "Term P value", "Term P value corrected with Bonferroni step-down"], ["GSE4226", "GO:0044403", "Symbiosis, encompassing mutualism through parasitism", "113", "10.53122", "5.98E-33", "1.23E-30"], ["GO:0016032", "Viral process", "109", "10.62378", "4.57E-32", "9.32E-30"], ["GO:0019058", "Viral life cycle", "74", "15.16394", "1.85E-31", "3.76E-29"], ["GO:0009056", "Catabolic process", "146", "5.968929", "4.54E-17", "8.63E-15"], ["GO:0034613", "Cellular protein localization", "121", "6.547619", "6.10E-17", "1.15E-14"], [""], ["GSE18309", "GO:0006955", "Immune response", "314", "14.47672", "1.25E-08", "8.10E-06"], ["GO:0040011", "Locomotion", "443", "24.7072", "8.99E-11", "6.07E-08"], ["GO:0032879", "Regulation of localization", "601", "22.68781", "8.00E-08", "5.08E-05"], ["GO:0045321", "Leukocyte activation", "178", "13.69231", "3.53E-07", "2.20E-04"], ["GO:0023052", "Signaling", "1386", "20.76716", "4.25E-07", "2.64E-04"], [""], ["GSE1297", "GO:0044699", "Single-organism process", "248", "1.814856", "1.08E-07", "1.16E-05"], ["GO:0044763", "Single-organism cellular process", "213", "1.933551", "1.77E-07", "1.86E-05"], ["GO:0048522", "Positive regulation of cellular process", "117", "2.322811", "7.89E-07", "8.13E-05"], ["GO:0048518", "Positive regulation of biological process", "125", "2.214349", "3.47E-06", "3.51E-04"], ["GO:0007154", "Cell communication", "139", "2.078039", "2.60E-05", "0.002369"], [""], ["GSE5281", "GO:0010604", "Positive regulation of macromolecule metabolic process", "1215", "39.69291", "4.13E-28", "4.28E-25"], ["GO:0009893", "Positive regulation of metabolic process", "1299", "39.23286", "8.40E-28", "8.72E-25"], ["GO:0006996", "Organelle organization", "1460", "38.04065", "1.36E-24", "1.40E-21"], ["GO:0048523", "Negative regulation of cellular process", "1681", "36.92882", "6.16E-22", "6.32E-19"], ["GO:0009966", "Regulation of signal transduction", "1131", "38.67989", "3.85E-21", "3.94E-18"]], "row_count": 24, "column_count": 7, "numeric_cells": 104, "header_rows": 1, "locator": "section[6]/table-wrap[2]#tab3"}}], "gaps": ["asset:data:geo:GSE1297 not downloaded", "asset:data:geo:GSE1297 licence not read", "asset:data:geo:GSE18309 not downloaded", "asset:data:geo:GSE18309 licence not read", "asset:data:geo:GSE4226 not downloaded", "asset:data:geo:GSE4226 licence not read", "asset:data:geo:GSE5281 not downloaded", "asset:data:geo:GSE5281 licence not read"]}, "analysis": {"state": "partial", "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": "Difference analysis was performed by GEO2R analysis with P < 0.05 and |logFC| > 1 as cutoff values for screening differentially expressed genes (DEGs)."}}, {"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"}}], "targets": [], "gaps": ["method.reader_differs_from_extractor"]}, "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": ["GSE4226", "GSE18309", "GSE1297", "GSE5281"], "resolved_accessions": ["GSE4226", "GSE18309", "GSE1297", "GSE5281"], "statements": ["The data used to support the findings of this study are available from the corresponding author upon request."], "basis": "The paper names GSE4226, GSE18309, GSE1297, GSE5281 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:30918899", "data:geo:GSE1297", "asset:table:pmid:30918899:1", "asset:table:pmid:30918899:2", "asset:table:pmid:30918899:3"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE1297"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-10-31T18:14:15Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 3, "usage": {"prompt_tokens": 21385, "completion_tokens": 1465, "cached_tokens": 656}}, "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:30918899", "type": "paper", "label": "pmid:30918899"}, {"id": "source:pmid:30918899", "type": "manuscript", "label": "PMID 30918899 full text"}, {"id": "data:geo:GSE1297", "type": "dataset", "label": "GEO GSE1297"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:30918899", "type": "paper", "label": "pmid:30918899"}, {"id": "source:pmid:30918899", "type": "manuscript", "label": "PMID 30918899 full text"}, {"id": "data:geo:GSE1297", "type": "dataset", "label": "GEO GSE1297"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-30918899", "type": "extraction", "used": ["source:pmid:30918899"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE1297", "type": "accession_resolution", "used": ["data:geo:GSE1297"], "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:30918899", "parent_hash": "sha256:65b642c7ae4f2d374c7ea56ee8d26783d10aa4588030839e9a258c65116afd97", "fork_of": null, "generation": 5}, "gaps": ["asset:data:geo:GSE1297 licence not read", "asset:data:geo:GSE1297 not downloaded", "asset:data:geo:GSE18309 licence not read", "asset:data:geo:GSE18309 not downloaded", "asset:data:geo:GSE4226 licence not read", "asset:data:geo:GSE4226 not downloaded", "asset:data:geo:GSE5281 licence not read", "asset:data:geo:GSE5281 not downloaded", "execution.not_run", "method.reader_differs_from_extractor", "review.human_critique", "review.independent_reader", "review.machine_critique"], "assays": [{"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": ["Difference analysis was performed by GEO2R analysis with P < 0.05 and |logFC| > 1 as cutoff values for screening differentially expressed genes (DEGs)."], "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":"2026-11-04T01:43:39+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}}}