{"data":{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:33551990", "kind": "science-record", "revision": 7, "content_hash": "sha256:3a30c1cde106c826d2d951165c7e44d3c9c13008a2450f7618e483476469a481", "created_at": "2026-11-01T15:41:24Z", "updated_at": "2026-11-01T22:03:03Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Integrative Analyses of Genes Associated With Osteoporosis in CD16+ Monocyte.", "doi": "10.3389/fendo.2020.581878", "pmid": "33551990", "authors": ["Bin Hu", "Xiangan Kong", "Li Li", "Fang Dai", "Qiu Zhang", "Ruifeng Shi"], "journal": "Frontiers in endocrinology", "year": 2020, "abstract": "Background: Osteoporosis is a metabolic bone disease characterized by decreased bone mineral density and abnormal bone quality. Monocytes can secret cytokines for bone resorption, resulting in bone mass loss. However, the mechanism by which monocytes subpopulations lead to osteoporosis remains unclear. The aim of this study was to identify genes associated with osteoporosis in monocytes subsets.\nMethods: Three microarray datasets including GSE7158 (transcription of low/high-peak bone mass), GSE101489 (transcription of CD16+/CD16- monocyte) and GSE93883 (miRNA expression profile of primary osteoporosis) were derived from the Gene Expression Omnibus (GEO) database and analyzed with GEO2R tool to identify differentially expressed genes (DEGs). Functional enrichment was analyzed using Metascape database and GSEA software. STRING was utilized for the Protein-Protein Interaction Network construct. The hub genes were screened out using the Cytoscape software. Related miRNAs were predicted in miRWalk, miRDB, and TargetScan databases.\nResults: Total 368 DEGs from GSE7158 were screened out, which were mostly enriched in signaling, positive regulation of biological process and immune system process. The hub genes were clustered into two modules by PPI network analysis. We identified 15 overlapping DGEs between GSE101489 and GSE7158 microarray datasets. Moreover, all of them were up-regulated genes in both datasets. Then, nine key genes were screened out from above 15 overlapping DEGs using Cytoscape software. It is a remarkable fact that the nine genes were all in one hub gene module of GSE7158. Additionally, 183 target miRNAs were predicted according to the above nine DEGs. After cross-verification with miRNA express profile dataset for osteoporosis (GSE93883), 12 DEmiRNAs were selected. Finally, a miRNA-mRNA network was constructed with the nine key genes and 12 miRNAs, which were involved in osteoporosis.\nConclusion: Our analysis results constructed a gene expression framework in monocyte subsets for osteoporosis. This approach could provide a novel insight into osteoporosis.", "claims": [{"id": "claim-method", "statement": "The online analysis tool GEO2R (https://www.ncbi.nlm.nih.gov/geo/geo2r/) was used to detect the DEGs between HPBM and LPBM samples.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:33551990", "locator": "sections[4] \"Data Processing\" paragraph 2", "quote": "The online analysis tool GEO2R (https://www.ncbi.nlm.nih.gov/geo/geo2r/) was used to detect the DEGs between HPBM and LPBM samples."}], "state": "complete"}, {"id": "claim-data-access", "statement": "The original contributions presented in the study are included in the article/Supplementary Material; further inquiries can be directed to the corresponding authors.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:33551990", "locator": "sections[17] \"Data Availability Statement\" paragraph 2", "quote": "The original contributions presented in the study are included in the article/Supplementary Material; further inquiries can be directed to the corresponding authors."}], "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:33551990"], "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:GSE101489"], "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:GSE101489"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:33551990", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.3389/fendo.2020.581878", "sha256": "sha256:a0fc95ad22f5c0ab21a95959afbbd8d9dfce860d2b5a9cc44b77a43b6b5ba93d", "bytes": 25079, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.3389/fendo.2020.581878", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC7859337", "source": "europe_pmc_fulltext", "coverage": "whole_body_without_references", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE101489", "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=GSE101489", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE101489", "version": null, "note": "The original contributions presented in the study are included in the article/Supplementary Material; further inquiries can be directed to the corresponding authors.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The original contributions presented in the study are included in the article/Supplementary Material; further inquiries can be directed to the corresponding authors.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM2704854", "GSM2704855", "GSM2704856", "GSM2704857", "GSM2704858", "GSM2704859", "GSM2704860", "GSM2704861", "GSM2704862", "GSM2704863", "GSM2704864", "GSM2704865", "GSM2704866", "GSM2704867", "GSM2704868", "GSM2704869", "GSM2704870", "GSM2704871", "GSM2704872", "GSM2704873", "GSM2704874", "GSM2704875", "GSM2704876"], "sample_count": 23, "group_sizes": null, "group_sizes_basis": null, "platform": "10904", "taxon": "Homo sapiens", "title": "Transcriptome profiling of peripheral blood mononuclear cell subsets", "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:GSE7158", "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=GSE7158", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE7158", "version": null, "note": "The original contributions presented in the study are included in the article/Supplementary Material; further inquiries can be directed to the corresponding authors.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The original contributions presented in the study are included in the article/Supplementary Material; further inquiries can be directed to the corresponding authors.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM172405", "GSM172406", "GSM172407", "GSM172408", "GSM172409", "GSM172410", "GSM172411", "GSM172412", "GSM172413", "GSM172414", "GSM172415", "GSM172416", "GSM172417", "GSM172418", "GSM172419", "GSM172420", "GSM172421", "GSM172422", "GSM172423", "GSM172424", "GSM172425", "GSM172426", "GSM172427", "GSM172428", "GSM172429", "GSM172430"], "sample_count": 26, "group_sizes": null, "group_sizes_basis": null, "platform": "570", "taxon": "Homo sapiens", "title": "Genome Wide Gene Expression Study of Circulating Monocytes in human with extremely high vs. low bone mass", "resolution_checked_at": "2026-11-01T15:39:55Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:GSE93883", "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=GSE93883", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE93883", "version": null, "note": "The original contributions presented in the study are included in the article/Supplementary Material; further inquiries can be directed to the corresponding authors.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The original contributions presented in the study are included in the article/Supplementary Material; further inquiries can be directed to the corresponding authors.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM2464440", "GSM2464441", "GSM2464442", "GSM2464443", "GSM2464444", "GSM2464445", "GSM2464446", "GSM2464447", "GSM2464448", "GSM2464449", "GSM2464450", "GSM2464451", "GSM2464452", "GSM2464453", "GSM2464454", "GSM2464455", "GSM2464456", "GSM2464457"], "sample_count": 18, "group_sizes": null, "group_sizes_basis": null, "platform": "18058", "taxon": "Homo sapiens; Mus musculus; Rattus norvegicus", "title": "Gene expression-based, individualized outcome prediction for osteoporosis with vertebral fracture", "resolution_checked_at": "2026-11-01T15:39:55Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "asset:table:pmid:33551990:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:960edd771350fa13b1103b3f2b92774d8f8bebbd33b76fee2e27b686d3025898", "bytes": 2319, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[9]/table-wrap[1]#T1", "version": null, "note": "Top 20 enriched terms for differentially expressed genes in monocytes of low peak bone mass (LPBM).", "structure": {"pmcid": "PMC7859337", "section_index": 9, "section_title": "Identification and Enrichment of Differentially Expressed Genes in Low-Peak Bone Mass Monocytes", "row_count": 21, "column_count": 7}, "table": {"label": "Table 1", "caption": "Top 20 enriched terms for differentially expressed genes in monocytes of low peak bone mass (LPBM).", "rows": [["GO", "Category", "Description", "Count", "%", "Log10(P)", "Log10(q)"], ["GO:0070528", "GO Biological Processes", "protein kinase C signaling", "7", "1.98", "–6.5", "–2.14"], ["GO:0002385", "GO Biological Processes", "mucosal immune response", "6", "1.69", "–4.92", "–1.21"], ["GO:0001906", "GO Biological Processes", "cell killing", "11", "3.11", "–4.23", "–0.82"], ["GO:0098552", "GO Cellular Components", "side of membrane", "22", "6.21", "–4.13", "–0.77"], ["GO:0031225", "GO Cellular Components", "anchored component of membrane", "10", "2.82", "–3.76", "–0.58"], ["GO:0043025", "GO Cellular Components", "neuronal cell body", "19", "5.37", "–3.72", "–0.57"], ["GO:0043114", "GO Biological Processes", "regulation of vascular permeability", "5", "1.41", "–3.67", "–0.54"], ["GO:0010810", "GO Biological Processes", "regulation of cell-substrate adhesion", "11", "3.11", "–3.48", "–0.5"], ["GO:0048762", "GO Biological Processes", "mesenchymal cell differentiation", "11", "3.11", "–3.43", "–0.5"], ["GO:0002068", "GO Biological Processes", "glandular epithelial cell development", "4", "1.13", "–3.29", "–0.47"], ["GO:0003678", "GO Molecular Functions", "DNA helicase activity", "6", "1.69", "–2.99", "–0.2"], ["GO:0051216", "GO Biological Processes", "cartilage development", "10", "2.82", "–2.95", "–0.18"], ["GO:1901611", "GO Molecular Functions", "phosphatidylglycerol binding", "3", "0.85", "–2.92", "–0.16"], ["GO:0042623", "GO Molecular Functions", "ATPase activity, coupled", "12", "3.39", "–2.9", "-0.16"], ["GO:0030011", "GO Biological Processes", "maintenance of cell polarity", "3", "0.85", "–2.75", "-0.04"], ["GO:0071634", "GO Biological Processes", "regulation of transforming growth factor beta production", "4", "1.13", "–2.75", "–0.04"], ["GO:0005938", "GO Cellular Components", "cell cortex", "12", "3.39", "–2.58", "0"], ["GO:0060541", "GO Biological Processes", "respiratory system development", "9", "2.54", "–2.55", "0"], ["GO:0061640", "GO Biological Processes", "cytoskeleton-dependent cytokinesis", "6", "1.69", "–2.49", "0"], ["GO:0016853", "GO Molecular Functions", "isomerase activity", "8", "2.26", "–2.49", "0"]], "row_count": 21, "column_count": 7, "numeric_cells": 102, "header_rows": 1, "locator": "section[9]/table-wrap[1]#T1"}}, {"id": "asset:table:pmid:33551990:2", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:86051115b05d703a16388b3260feff1ce318dc6dac9d92a176387347512b1b40", "bytes": 741, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[11]/table-wrap[1]#T2", "version": null, "note": "The hub genes for DEGs in monocytes of LPBM.", "structure": {"pmcid": "PMC7859337", "section_index": 11, "section_title": "Protein–Protein Interaction Network Analysis and Hub Gene Identification of Differentially Expressed Genes in Low-Peak Bone Mass Monocytes", "row_count": 11, "column_count": 4}, "table": {"label": "Table 2", "caption": "The hub genes for DEGs in monocytes of LPBM.", "rows": [["Rank", "Gene Symbol", "Gene Name", "MMC Score"], ["1", "RHOH", "Ras homolog family member H", "104"], ["2", "RHOJ", "Ras Homolog Family Member J", "102"], ["2", "RHOBTB2", "Rho Related BTB Domain Containing 2", "102"], ["4", "FN1", "Fibronectin 1", "68"], ["5", "PRF1", "Perforin 1", "67"], ["6", "CFL1", "Cofilin 1", "58"], ["7", "KLRD1", "Killer Cell Lectin Like Receptor D1", "56"], ["8", "DOCK1", "Dedicator of Cytokinesis 1", "51"], ["9", "NCR1", "Natural Cytotoxicity Triggering Receptor 1", "43"], ["10", "SLAMF1", "Signaling Lymphocytic Activation Molecule Family Member 1", "38"]], "row_count": 11, "column_count": 4, "numeric_cells": 27, "header_rows": 1, "locator": "section[11]/table-wrap[1]#T2"}}, {"id": "asset:table:pmid:33551990:3", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:6097ad7ec12db6783fed770b757768b7467afcda055be4398bdc9ba2c08ffc93", "bytes": 2368, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[12]/table-wrap[1]#T3", "version": null, "note": "Top 20 enriched terms for differentially expressed genes in CD16+ monocytes.", "structure": {"pmcid": "PMC7859337", "section_index": 12, "section_title": "Identification and Enrichment of Differentially Expressed Genes in CD16+ Monocytes", "row_count": 21, "column_count": 7}, "table": {"label": "Table 3", "caption": "Top 20 enriched terms for differentially expressed genes in CD16+ monocytes.", "rows": [["GO", "Category", "Description", "Count", "%", "Log10(P)", "Log10(q)"], ["GO:0002228", "GO Biological Processes", "natural killer cell mediated immunity", "12", "6.63", "–13.17", "–9.08"], ["hsa04650", "KEGG Pathway", "Natural killer cell mediated cytotoxicity", "15", "8.29", "–13.14", "–9.08"], ["GO:0006968", "GO Biological Processes", "cellular defense response", "10", "5.52", "–11.23", "–7.35"], ["GO:0046649", "GO Biological Processes", "lymphocyte activation", "27", "14.92", "–10.95", "–7.22"], ["GO:0002250", "GO Biological Processes", "adaptive immune response", "26", "14.36", "–10.88", "–7.22"], ["GO:0001772", "GO Cellular Components", "immunological synapse", "7", "3.87", "–8.02", "–4.87"], ["GO:0032609", "GO Biological Processes", "interferon-gamma production", "10", "5.52", "–7.89", "–4.79"], ["GO:0023024", "GO Molecular Functions", "MHC class I protein complex binding", "4", "2.21", "–7.36", "–4.4"], ["GO:0043152", "GO Biological Processes", "induction of bacterial agglutination", "4", "2.21", "–6.99", "–4.11"], ["GO:0006935", "GO Biological Processes", "chemotaxis", "19", "10.5", "–6.39", "–3.64"], ["hsa04660", "KEGG Pathway", "T cell receptor signaling pathway", "8", "4.42", "–5.99", "–3.31"], ["GO:0002366", "GO Biological Processes", "leukocyte activation involved in immune response", "19", "10.5", "–5.8", "–3.14"], ["GO:0019835", "GO Biological Processes", "cytolysis", "5", "2.76", "–5.74", "–3.1"], ["GO:0048015", "GO Biological Processes", "phosphatidylinositol-mediated signaling", "10", "5.52", "–5.74", "–3.1"], ["GO:0043235", "GO Cellular Components", "receptor complex", "16", "8.84", "–5.72", "–3.09"], ["GO:0030246", "GO Molecular Functions", "carbohydrate binding", "11", "6.08", "–5.33", "–2.78"], ["GO:0060191", "GO Biological Processes", "regulation of lipase activity", "7", "3.87", "–5.03", "–2.54"], ["GO:0051092", "GO Biological Processes", "positive regulation of NF-kappaB transcription factor activity", "8", "4.42", "–4.71", "–2.26"], ["GO:0032393", "GO Molecular Functions", "MHC class I receptor activity", "3", "1.66", "–4.48", "–2.11"], ["GO:0009897", "GO Cellular Components", "external side of plasma membrane", "12", "6.63", "–4.3", "–1.94"]], "row_count": 21, "column_count": 7, "numeric_cells": 102, "header_rows": 1, "locator": "section[12]/table-wrap[1]#T3"}}, {"id": "asset:table:pmid:33551990:4", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:59b63824f264832c4e7223f033a284e996ff40f408431e05259a4430dd0a8ed6", "bytes": 648, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[14]/table-wrap[1]#T4", "version": null, "note": "The enriched terms for 15 overlapping genes.", "structure": {"pmcid": "PMC7859337", "section_index": 14, "section_title": "Identification and Cluster Analysis of Overlapping Genes", "row_count": 5, "column_count": 7}, "table": {"label": "Table 4", "caption": "The enriched terms for 15 overlapping genes.", "rows": [["GO", "Category", "Description", "Count", "%", "Log10(P)", "Log10(q)"], ["hsa04650", "KEGG Pathway", "Natural killer cell mediated cytotoxicity", "4", "44.44", "–6.98", "–2.62"], ["GO:0002228", "GO Biological Processes", "natural killer cell mediated immunity", "3", "33.33", "–5.8", "–1.92"], ["GO:0030246", "GO Molecular Functions", "carbohydrate binding", "3", "33.33", "–4", "–0.34"], ["GO:0000323", "GO Cellular Components", "lytic vacuole", "3", "33.33", "–2.76", "0"]], "row_count": 5, "column_count": 7, "numeric_cells": 22, "header_rows": 1, "locator": "section[14]/table-wrap[1]#T4"}}], "gaps": ["asset:data:geo:GSE101489 not downloaded", "asset:data:geo:GSE101489 licence not read", "asset:data:geo:GSE7158 not downloaded", "asset:data:geo:GSE7158 licence not read", "asset:data:geo:GSE93883 not downloaded", "asset:data:geo:GSE93883 licence not read"]}, "analysis": {"state": "partial", "methods": [{"id": "method-1", "family": "network_analysis", "specific": "ppi_network", "label": "Network / pathway analysis", "dsl_operations": ["build_graph", "centrality_scores", "pathway_enrich"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["edge_list"], "evidence": {"score": 0.7, "band": "medium", "quote": "Protein-Protein Interaction"}}, {"id": "method-2", "family": null, "specific": null, "label": "GEO2R", "dsl_operations": [], "missing_operations": [], "expressible": null, "parameters": {}, "data_shapes": [], "evidence": {"score": 1.0, "band": "verbatim", "quote": "The online analysis tool GEO2R (https://www.ncbi.nlm.nih.gov/geo/geo2r/) was used to detect the DEGs between HPBM and LPBM samples."}}], "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": ["build_graph", "centrality_scores", "pathway_enrich"], "missing_operations": [], "basis": "The paper names the method it used and the corpus's method extractor maps it onto the DSL catalogue: ppi_network."}, "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": ["GSE7158", "GSE101489", "GSE93883"], "resolved_accessions": ["GSE7158", "GSE101489", "GSE93883"], "statements": ["The original contributions presented in the study are included in the article/Supplementary Material; further inquiries can be directed to the corresponding authors."], "basis": "The paper names GSE7158, GSE101489, GSE93883 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": ["build_graph", "centrality_scores", "pathway_enrich"], "assets": ["source:pmid:33551990", "data:geo:GSE101489", "asset:table:pmid:33551990:1", "asset:table:pmid:33551990:2", "asset:table:pmid:33551990:3", "asset:table:pmid:33551990:4"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE101489"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-10-31T18:26:48Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 3, "usage": {"prompt_tokens": 18410, "completion_tokens": 1639, "cached_tokens": 793}}, "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:33551990", "type": "paper", "label": "pmid:33551990"}, {"id": "source:pmid:33551990", "type": "manuscript", "label": "PMID 33551990 full text"}, {"id": "data:geo:GSE101489", "type": "dataset", "label": "GEO GSE101489"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:33551990", "type": "paper", "label": "pmid:33551990"}, {"id": "source:pmid:33551990", "type": "manuscript", "label": "PMID 33551990 full text"}, {"id": "data:geo:GSE101489", "type": "dataset", "label": "GEO GSE101489"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-33551990", "type": "extraction", "used": ["source:pmid:33551990"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE101489", "type": "accession_resolution", "used": ["data:geo:GSE101489"], "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:33551990", "parent_hash": "sha256:e7be6df4974648198ce79ced17ffd8aa480c8af4749f36906c4cb97ed28c395d", "fork_of": null, "generation": 6}, "gaps": ["asset:data:geo:GSE101489 licence not read", "asset:data:geo:GSE101489 not downloaded", "asset:data:geo:GSE7158 licence not read", "asset:data:geo:GSE7158 not downloaded", "asset:data:geo:GSE93883 licence not read", "asset:data:geo:GSE93883 not downloaded", "execution.not_run", "method.reader_named_unmapped", "review.human_critique", "review.independent_reader", "review.machine_critique"], "assays": [{"role": "analysis", "definition_id": "network_analysis", "definition_version": "f2132e96ae6c7a4e", "definition_digest": null, "required_operations": ["build_graph", "centrality_scores", "pathway_enrich"], "support_state": "supported", "source_hashes": {"dsl_catalogue": "f2132e96ae6c7a4e"}, "confidence": 0.7, "evidence": ["Protein-Protein Interaction"], "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":"2026-11-04T01:18:33+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}}}