{"data":{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:34250093", "kind": "science-record", "revision": 5, "content_hash": "sha256:6fae8fa253aed46feacf95c504f7fe78a93ce851bf4e6adcbdec6043f44dd997", "created_at": "2026-11-01T15:41:42Z", "updated_at": "2026-11-01T22:04:11Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Identification of Macrophage Polarization-Related Genes as Biomarkers of Chronic Obstructive Pulmonary Disease Based on Bioinformatics Analyses.", "doi": "10.1155/2021/9921012", "pmid": "34250093", "authors": ["Yalin Zhao", "Meihua Li", "Yanxia Yang", "Tao Wu", "Qingyuan Huang", "Qinghua Wu", "Chaofeng Ren"], "journal": "BioMed research international", "year": 2021, "abstract": "OBJECTIVES: Chronic obstructive pulmonary disease (COPD) is characterized by lung inflammation and remodeling. Macrophage polarization is associated with inflammation and tissue remodeling, as well as immunity. Therefore, this study attempts to investigate the diagnostic value and regulatory mechanism of macrophage polarization-related genes for COPD by bioinformatics analysis and to provide a new theoretical basis for experimental research.\nMETHODS: The raw gene expression profile dataset (GSE124180) was collected from the Gene Expression Omnibus (GEO) database. Next, a weighted gene coexpression network analysis (WGCNA) was conducted to screen macrophage polarization-related genes. The differentially expressed genes (DEGs) between the COPD and normal samples were generated using DESeq2 v3.11 and overlapped with the macrophage polarization-related genes. Moreover, functional annotations of overlapped genes were conducted by Database for Annotation, Visualization and Integrated Discovery (DAVID) Bioinformatics Resource. The immune-related genes were selected, and their correlation with the differential immune cells was analyzed by Pearson. Finally, receiver operating characteristic (ROC) curves were used to verify the diagnostic value of genes.\nRESULTS: A total of 4922 coexpressed genes related to macrophage polarization were overlapped with the 203 DEGs between the COPD and normal samples, obtaining 25 genes related to COPD and macrophage polarization. GEM, S100B, and GZMA of them participated in the immune response, which were considered the candidate biomarkers. GEM and S100B were significantly correlated with marker genes of B cells which had a significant difference between the COPD and normal samples. Moreover, GEM was highly associated with the genes in the PI3K/Akt/GSK3β signaling pathway, regulation of actin cytoskeleton, and calcium signaling pathway based on a Pearson correlation analysis of the candidate genes and the genes in the B cell receptor signaling pathway. PPI network analysis also indicated that GEM might participate in the regulation of the PI3K/Akt/GSK3β signaling pathway. The ROC curve showed that GEM possessed an excellent accuracy in distinguishing COPD from normal samples.\nCONCLUSIONS: The data provide a transcriptome-based evidence that GEM is related to COPD and macrophage polarization likely contributes to COPD diagnosis. At the same time, it is hoped that in-depth functional mining can provide new ideas for exploring the COPD pathogenesis.", "claims": [{"id": "claim-method", "statement": "Pearson analysis was used to investigate the correlation of the candidate genes and the differential immune cells between the COPD and normal samples, as well as marker genes and pathways of differential immune cells.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:34250093", "locator": "sections[6] \"2.4. The Functional Annotations and Correlation Analysis of the Candidate Genes\" paragraph 2", "quote": "Pearson analysis was used to investigate the correlation of the candidate genes and the differential immune cells between the COPD and normal samples, as well as marker genes and pathways of differential immune cells."}], "state": "complete"}, {"id": "claim-data-access", "statement": "The GSE124180 dataset analyzed in this study was available in the GEO database.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:34250093", "locator": "sections[20] \"Data Availability\" paragraph 2", "quote": "The GSE124180 dataset analyzed in this study was available in the GEO database."}], "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:34250093"], "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:GSE124180"], "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:GSE124180"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:34250093", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1155/2021/9921012", "sha256": "sha256:dfb104fe7ed9687932e637ec013e24311f6797dc66709050b51e900f49549dc1", "bytes": 45799, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1155/2021/9921012", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC8238569", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE124180", "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=GSE124180", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE124180", "version": null, "note": "The GSE124180 dataset analyzed in this study was available in the GEO database.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The GSE124180 dataset analyzed in this study was available in the GEO database.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM3523461", "GSM3523462", "GSM3523463", "GSM3523464", "GSM3523465", "GSM3523466", "GSM3523467", "GSM3523468", "GSM3523469", "GSM3523470", "GSM3523471", "GSM3523472", "GSM3523473", "GSM3523474", "GSM3523475", "GSM3523476", "GSM3523477", "GSM3523478", "GSM3523479", "GSM3523480", "GSM3523481", "GSM3523482", "GSM3523483", "GSM3523484", "GSM3523485", "GSM3523486", "GSM3523487", "GSM3523488", "GSM3523489", "GSM3523490", "GSM3523491", "GSM3523492", "GSM3523493", "GSM3523494", "GSM3523495", "GSM3523496", "GSM3523497", "GSM3523498", "GSM3523499", "GSM3523500", "GSM3523501", "GSM3523502", "GSM3523503", "GSM3523504", "GSM3523505", "GSM3523506", "GSM3523507", "GSM3523508", "GSM3523509", "GSM3523510", "GSM3523511", "GSM3523512", "GSM3523513", "GSM3523514", "GSM3523515", "GSM3523516", "GSM3523517", "GSM3523518", "GSM3523519", "GSM3523520", "GSM3523521", "GSM3523522", "GSM3523523"], "sample_count": 63, "group_sizes": null, "group_sizes_basis": null, "platform": "16791", "taxon": "Homo sapiens", "title": "RNA-sequencing across three matched tissues highlights gene expression signatures in COPD", "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:34250093:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:d48ffd9dc17df6ee5934f52fac7853c517df871b32e399dd968c79fe3b60cf0a", "bytes": 8190, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[11]/table-wrap[1]#tab1", "version": null, "note": "The results of GO functional annotation and KEGG pathways for the 25 candidate genes.", "structure": {"pmcid": "PMC8238569", "section_index": 11, "section_title": "3.3. Functional Annotations of the Candidate Genes", "row_count": 19, "column_count": 3}, "table": {"label": "Table 1", "caption": "The results of GO functional annotation and KEGG pathways for the 25 candidate genes.", "rows": [["ID", "Biological process", "KEGG pathway"], ["CBR3", "GO:0042376 ~ phylloquinone catabolic process, GO:0050890 ~ cognition, GO:0055114 ~ oxidation-reduction process", "hsa00590: arachidonic acid metabolism, hsa00980: metabolism of xenobiotics by cytochrome P450, hsa01100: metabolic pathways"], ["FZD6", "GO:0001736 ~ establishment of planar polarity, GO:0001843 ~ neural tube closure, GO:0001942 ~ hair follicle development, GO:0007186 ~ G-protein coupled receptor signaling pathway, GO:0007223 ~ Wnt signaling pathway, calcium modulating pathway, GO:0007275 ~ multicellular organism development, GO:0030168 ~ platelet activation, GO:0033278 ~ cell proliferation in midbrain, GO:0035567 ~ non-canonical Wnt signaling pathway, GO:0035880 ~ embryonic nail plate morphogenesis, GO:0042472 ~ inner ear morphogenesis, GO:0043433 ~ negative regulation of sequence-specific DNA binding transcription factor activity, GO:0060071 ~ Wnt signaling pathway, planar cell polarity pathway, GO:0090090 ~ negative regulation of canonical Wnt signaling pathway, GO:1904693 ~ midbrain morphogenesis", "hsa04310: Wnt signaling pathway, hsa04390: Hippo signaling pathway, hsa04550: signaling pathways regulating pluripotency of stem cells, hsa04916: melanogenesis, hsa05166:HTLV-I infection, hsa05200: pathways in cancer, hsa05205: proteoglycans in cancer, hsa05217: basal cell carcinoma"], ["NEFL", "GO:0000165 ~ MAPK cascade, GO:0000226 ~ microtubule cytoskeleton organization, GO:0008089 ~ anterograde axonal transport, GO:0008090 ~ retrograde axonal transport, GO:0009636 ~ response to toxic substance, GO:0014012 ~ peripheral nervous system axon regeneration, GO:0019896 ~ axonal transport of mitochondrion, GO:0021510 ~ spinal cord development, GO:0021766 ~ hippocampus development, GO:0021987 ~ cerebral cortex development, GO:0031133 ~ regulation of axon diameter, GO:0033693 ~ neurofilament bundle assembly, GO:0040011 ~ locomotion, GO:0043434 ~ response to peptide hormone, GO:0043524 ~ negative regulation of neuron apoptotic process, GO:0043547 ~ positive regulation of GTPase activity, GO:0045105 ~ intermediate filament polymerization or depolymerization, GO:0045109 ~ intermediate filament organization, GO:0048812 ~ neuron projection morphogenesis, GO:0050772 ~ positive regulation of axonogenesis, GO:0050885 ~ neuromuscular process controlling balance, GO:0051258 ~ protein polymerization, GO:0051412 ~ response to corticosterone, GO:0061564 ~ axon development, GO:1903935 ~ response to sodium arsenite, GO:1903937 ~ response to acrylamide", "hsa05014: amyotrophic lateral sclerosis (ALS),"], ["ZNF676", "GO:0006351 ~ transcription, DNA-templated, GO:0006355 ~ regulation of transcription, DNA-templated", ""], ["PROX2", "GO:0000122 ~ negative regulation of transcription from RNA polymerase II promoter, GO:0006351 ~ transcription, DNA-templated, GO:0030182 ~ neuron differentiation, GO:0045944 ~ positive regulation of transcription from RNA polymerase II promoter, GO:0055007 ~ cardiac muscle cell differentiation", ""], ["HMMR", "GO:0000086 ~ G2/M transition of mitotic cell cycle, GO:0030214 ~ hyaluronan catabolic process", "hsa04512: ECM-receptor interaction"], ["GEM", "GO:0006955 ~ immune response, GO:0007067 ~ mitotic nuclear division, GO:0007165 ~ signal transduction, GO:0007166 ~ cell surface receptor signaling pathway, GO:0007264 ~ small GTPase mediated signal transduction, GO:0051276 ~ chromosome organization, GO:0051310 ~ metaphase plate congression", ""], ["HESX1", "GO:0006351 ~ transcription, DNA-templated, GO:0007420 ~ brain development,GO:0030916 ~ otic vesicle formation, GO:0043584 ~ nose development, GO:0045892 ~ negative regulation of transcription, DNA-templated, GO:0048853 ~ forebrain morphogenesis,", "hsa04550: signaling pathways regulating pluripotency of stem cells"], ["PRDM6", "GO:0006351 ~ transcription, DNA-templated, GO:0022008 ~ neurogenesis, GO:0034968 ~ histone lysine methylation, GO:0045892 ~ negative regulation of transcription, DNA-templated, GO:0051151 ~ negative regulation of smooth muscle cell differentiation", ""], ["RUNDC3B", "", ""], ["S100B", "GO:0007409 ~ axonogenesis, GO:0007417 ~ central nervous system development, GO:0007611 ~ learning or memory, GO:0007613 ~ memory, GO:0008283 ~ cell proliferation, GO:0008284 ~ positive regulation of cell proliferation, GO:0008360 ~ regulation of cell shape, GO:0043065 ~ positive regulation of apoptotic process, GO:0043123 ~ positive regulation of I-kappaB kinase/NF-kappaB signaling, GO:0045087 ~ innate immune response, GO:0048168 ~ regulation of neuronal synaptic plasticity, GO:0048708 ~ astrocyte differentiation, GO:0051384 ~ response to glucocorticoid, GO:0051597 ~ response to methylmercury, GO:0060291 ~ long-term synaptic potentiation, GO:0071456 ~ cellular response to hypoxia, GO:2001015 ~ negative regulation of skeletal muscle cell differentiation", ""], ["CENPS", "GO:0000712 ~ resolution of meiotic recombination intermediates, GO:0006281 ~ DNA repair, GO:0006312 ~ mitotic recombination, GO:0006974 ~ cellular response to DNA damage stimulus, GO:0007062 ~ sister chromatid cohesion, GO:0007067 ~ mitotic nuclear division, GO:0031297 ~ replication fork processing, GO:0031398 ~ positive regulation of protein ubiquitination, GO:0034080 ~ CENP-A containing nucleosome assembly, GO:0036297 ~ interstrand cross-link repair, GO:0051301 ~ cell division, GO:0051382 ~ kinetochore assembly", "hsa03460: Fanconi anemia pathway"], ["C10orf105", "", ""], ["GZMA", "GO:0006915 ~ apoptotic process, GO:0006955 ~ immune response, GO:0019835 ~ cytolysis, GO:0032078 ~ negative regulation of endodeoxyribonuclease activity, GO:0043065 ~ positive regulation of apoptotic process, GO:0043392 ~ negative regulation of DNA binding, GO:0051354 ~ negative regulation of oxidoreductase activity, GO:0051603 ~ proteolysis involved in cellular protein catabolic process", "hsa04080: neuroactive ligand-receptor interaction"], ["NEBL", "GO:0071691 ~ cardiac muscle thin filament assembly", ""], ["RNF43", "GO:0016055 ~ Wnt signaling pathway, GO:0016567 ~ protein ubiquitination, GO:0030178 ~ negative regulation of Wnt signaling pathway, GO:0038018 ~ Wnt receptor catabolic process, GO:0042787 ~ protein ubiquitination involved in ubiquitin-dependent protein catabolic process, GO:0072089 ~ stem cell proliferation,", ""], ["SPINK2", "GO:0002176 ~ male germ cell proliferation, GO:0007286 ~ spermatid development, GO:0009566 ~ fertilization, GO:0043065 ~ positive regulation of apoptotic process, GO:0060046 ~ regulation of acrosome reaction, GO:0072520 ~ seminiferous tubule development, GO:1900004 ~ negative regulation of serine-type endopeptidase activity", ""], ["UTS2", "GO:0001666 ~ response to hypoxia, GO:0003105 ~ negative regulation of glomerular filtration, GO:0006936 ~ muscle contraction, GO:0007204 ~ positive regulation of cytosolic calcium ion concentration, GO:0007268 ~ chemical synaptic transmission, GO:0008217 ~ regulation of blood pressure, GO:0010459 ~ negative regulation of heart rate, GO:0010460 ~ positive regulation of heart rate, GO:0010763 ~ positive regulation of fibroblast migration, GO:0010841 ~ positive regulation of circadian sleep/wake cycle, wakefulness, GO:0032224 ~ positive regulation of synaptic transmission, cholinergic, GO:0032967 ~ positive regulation of collagen biosynthetic process, GO:0033574 ~ response to testosterone, GO:0035811 ~ negative regulation of urine volume, GO:0035814 ~ negative regulation of renal sodium excretion, GO:0042312 ~ regulation of vasodilation, GO:0042493 ~ response to drug, GO:0045597 ~ positive regulation of cell differentiation, GO:0045766 ~ positive regulation of angiogenesis,GO:0045776 ~ negative regulation of blood pressure, GO:0045777 ~ positive regulation of blood pressure, GO:0045909 ~ positive regulation of vasodilation, GO:0046005 ~ positive regulation of circadian sleep/wake cycle, REM sleep,GO:0046676 ~ negative regulation of insulin secretion,GO:0048146 ~ positive regulation of fibroblast proliferation,", ""]], "row_count": 19, "column_count": 3, "numeric_cells": 27, "header_rows": 1, "locator": "section[11]/table-wrap[1]#tab1"}}], "gaps": ["asset:data:geo:GSE124180 not downloaded", "asset:data:geo:GSE124180 licence not read"]}, "analysis": {"state": "partial", "methods": [{"id": "method-1", "family": "correlation_analysis", "specific": "pearson", "label": "Correlation analysis", "dsl_operations": ["pearson_r"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["paired_numeric_columns"], "evidence": {"score": 1.0, "band": "verbatim", "quote": "Pearson analysis was used to investigate the correlation of the candidate genes and the differential immune cells between the COPD and normal samples, as well as marker genes and pathways of differential immune cells."}}, {"id": "method-2", "family": "differential_expression", "specific": "deseq2", "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": 0.7, "band": "medium", "quote": "DESeq2"}}, {"id": "method-3", "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": "PPI"}}, {"id": "method-4", "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": 0.7, "band": "medium", "quote": "ROC curve"}}], "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": ["pearson_r"], "missing_operations": [], "basis": "The paper names the method it used and the corpus's method extractor maps it onto the DSL catalogue: pearson."}, "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": ["GSE124180"], "resolved_accessions": ["GSE124180"], "statements": ["The GSE124180 dataset analyzed in this study was available in the GEO database."], "basis": "The paper names GSE124180 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": ["pearson_r"], "assets": ["source:pmid:34250093", "data:geo:GSE124180", "asset:table:pmid:34250093:1"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE124180"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-10-31T18:32:03Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 3, "usage": {"prompt_tokens": 36045, "completion_tokens": 1070, "cached_tokens": 784}}, "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:34250093", "type": "paper", "label": "pmid:34250093"}, {"id": "source:pmid:34250093", "type": "manuscript", "label": "PMID 34250093 full text"}, {"id": "data:geo:GSE124180", "type": "dataset", "label": "GEO GSE124180"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:34250093", "type": "paper", "label": "pmid:34250093"}, {"id": "source:pmid:34250093", "type": "manuscript", "label": "PMID 34250093 full text"}, {"id": "data:geo:GSE124180", "type": "dataset", "label": "GEO GSE124180"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-34250093", "type": "extraction", "used": ["source:pmid:34250093"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE124180", "type": "accession_resolution", "used": ["data:geo:GSE124180"], "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:34250093", "parent_hash": "sha256:15f23e02b3723dcba8a5d21bb0b122b295d8c1e025aa57e07671c80f7c29da17", "fork_of": null, "generation": 4}, "gaps": ["asset:data:geo:GSE124180 licence not read", "asset:data:geo:GSE124180 not downloaded", "execution.not_run", "method.reader_differs_from_extractor", "review.human_critique", "review.independent_reader", "review.machine_critique"], "assays": [{"role": "analysis", "definition_id": "correlation_analysis", "definition_version": "f2132e96ae6c7a4e", "definition_digest": null, "required_operations": ["pearson_r"], "support_state": "supported", "source_hashes": {"dsl_catalogue": "f2132e96ae6c7a4e"}, "confidence": 1.0, "evidence": ["Pearson analysis was used to investigate the correlation of the candidate genes and the differential immune cells between the COPD and normal samples, as well as marker genes and pathways of differential immune cells."], "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":"2026-11-04T01:22:28+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}}}