{"data":{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:34568491", "kind": "science-record", "revision": 8, "content_hash": "sha256:0807bde4dbfc0b599e19c90327a46dcd515aedae5e2138eeff64b08cfcbcab57", "created_at": "2026-11-01T15:41:54Z", "updated_at": "2026-11-01T22:47:36Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Biodata Mining of Differentially Expressed Genes between Acute Myocardial Infarction and Unstable Angina Based on Integrated Bioinformatics.", "doi": "10.1155/2021/5584681", "pmid": "34568491", "authors": ["Siyu Guo", "Zhihong Huang", "Xinkui Liu", "Jingyuan Zhang", "Peizhi Ye", "Chao Wu", "Shan Lu", "Shanshan Jia", "Xiaomeng Zhang", "Xiuping Chen", "Miaomiao Wang", "Jiarui Wu"], "journal": "BioMed research international", "year": 2021, "abstract": "Acute coronary syndrome (ACS) is a complex syndrome of clinical symptoms. In order to accurately diagnose the type of disease in ACS patients, this study is aimed at exploring the differentially expressed genes (DEGs) and biological pathways between acute myocardial infarction (AMI) and unstable angina (UA). The GSE29111 and GSE60993 datasets containing microarray data from AMI and UA patients were downloaded from the Gene Expression Omnibus (GEO) database. DEG analysis of these 2 datasets is performed using the \"limma\" package in R software. DEGs were also analyzed using protein-protein interaction (PPI), Molecular Complex Detection (MCODE) algorithm, Gene Ontology (GO), and Kyoto Encyclopedia of Genes and Genomes (KEGG) enrichment analysis. Correlation analysis and \"cytoHubba\" were used to analyze the hub genes. A total of 286 DEGs were obtained from GSE29111 and GSE60993, including 132 upregulated genes and 154 downregulated genes. Subsequent comprehensive analysis identified 20 key genes that may be related to the occurrence and development of AMI and UA and were involved in the inflammatory response, interaction of neuroactive ligand-receptor, calcium signaling pathway, inflammatory mediator regulation of TRP channels, viral protein interaction with cytokine and cytokine receptor, human cytomegalovirus infection, and cytokine-cytokine receptor interaction pathway. The integrated bioinformatical analysis could improve our understanding of DEGs between AMI and UA. The results of this study might provide a new perspective and reference for the early diagnosis and treatment of ACS.", "claims": [{"id": "claim-method", "statement": "DEG analysis of these 2 datasets is performed using the “limma” package in R software.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:34568491", "locator": "sections[0] \"Abstract\" paragraph 1", "quote": "DEG analysis of these 2 datasets is performed using the “limma” package in R software."}], "state": "complete"}, {"id": "claim-data-access", "statement": "The raw data supporting the conclusions of this article will be made available by the authors, without undue reservation. All data obtained or analyzed during this study are available from the published article and its supplementary information files. The datasets during the current study are available from the corresponding author upon reasonable request.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:34568491", "locator": "sections[17] \"Data Availability\" paragraph 2", "quote": "The raw data supporting the conclusions of this article will be made available by the authors, without undue reservation. All data obtained or analyzed during this study are available from the published article and its supplementary information files. The datasets during the current study are available from the corresponding author upon reasonable 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:34568491"], "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:GSE29111"], "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:GSE29111"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:34568491", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1155/2021/5584681", "sha256": "sha256:0b40a2456e4ee78aa69f96a29e2751bf6aa96d0b78d9fde029edaff09262f267", "bytes": 56382, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1155/2021/5584681", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC8456013", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE29111", "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=GSE29111", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE29111", "version": null, "note": "The raw data supporting the conclusions of this article will be made available by the authors, without undue reservation. All data obtained or analyzed during this study are available from the published article and its supplementary information files. The datasets during the current study are available from the corresponding author upon reasonable request.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The raw data supporting the conclusions of this article will be made available by the authors, without undue reservation. All data obtained or analyzed during this study are available from the published article and its supplementary information files. The datasets during the current study are available from the corresponding author upon reasonable request.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM720972", "GSM720973", "GSM720974", "GSM720975", "GSM720976", "GSM720977", "GSM720978", "GSM720979", "GSM720980", "GSM720981", "GSM720982", "GSM720983", "GSM720984", "GSM720985", "GSM720986", "GSM720987", "GSM720988", "GSM720989", "GSM720990", "GSM720991", "GSM720992", "GSM720993", "GSM720994", "GSM720995", "GSM720996", "GSM720997", "GSM720998", "GSM720999", "GSM721000", "GSM721001", "GSM721002", "GSM721003", "GSM721004", "GSM721005", "GSM721006", "GSM721007", "GSM721008", "GSM721009", "GSM721010", "GSM721011", "GSM721012", "GSM721013", "GSM721014", "GSM721015", "GSM721016", "GSM721017", "GSM721018", "GSM721019", "GSM721020", "GSM721021", "GSM721022", "GSM721023"], "sample_count": 52, "group_sizes": null, "group_sizes_basis": null, "platform": "570", "taxon": "Homo sapiens", "title": "Characterisation of Myocardial Infarction and Unstable Angina with mRNA Profiles from Whole Blood of individual 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:GSE60993", "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=GSE60993", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE60993", "version": null, "note": "The raw data supporting the conclusions of this article will be made available by the authors, without undue reservation. All data obtained or analyzed during this study are available from the published article and its supplementary information files. The datasets during the current study are available from the corresponding author upon reasonable request.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The raw data supporting the conclusions of this article will be made available by the authors, without undue reservation. All data obtained or analyzed during this study are available from the published article and its supplementary information files. The datasets during the current study are available from the corresponding author upon reasonable request.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM1495313", "GSM1495314", "GSM1495315", "GSM1495316", "GSM1495317", "GSM1495318", "GSM1495319", "GSM1495320", "GSM1495321", "GSM1495322", "GSM1495323", "GSM1495324", "GSM1495325", "GSM1495326", "GSM1495327", "GSM1495328", "GSM1495329", "GSM1495330", "GSM1495331", "GSM1495332", "GSM1495333", "GSM1495334", "GSM1495335", "GSM1495336", "GSM1495337", "GSM1495338", "GSM1495339", "GSM1495340", "GSM1495341", "GSM1495342", "GSM1495343", "GSM1495344", "GSM1495345"], "sample_count": 33, "group_sizes": null, "group_sizes_basis": null, "platform": "6884", "taxon": "Homo sapiens", "title": "Assessment and Diagnostic Relevance of Novel Serum Biomarkers for Early Decision of ST-elevation Myocardial Infarction", "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:34568491:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:6b5b4cb2f0903af07959dcaef9dddc0d90478a11df711e38a98439d738af8abf", "bytes": 442, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[9]/table-wrap[1]#tab1", "version": null, "note": "Information of 2 microarray datasets of acute myocardial infarction and unstable angina.", "structure": {"pmcid": "PMC8456013", "section_index": 9, "section_title": "3.1. Screening of Differentially Expressed Genes", "row_count": 3, "column_count": 3}, "table": {"label": "Table 1", "caption": "Information of 2 microarray datasets of acute myocardial infarction and unstable angina.", "rows": [["Dataset", "Platform", "Sample (AMI/UA)"], ["GSE29111", "GPL570 [HG-U133_Plus_2] Affymetrix Human Genome U133 Plus 2.0 Array", "36/16"], ["GSE60993", "GPL6884 Illumina HumanWG-6 v3.0 expression beadchip", "17/9"]], "row_count": 3, "column_count": 3, "numeric_cells": 6, "header_rows": 1, "locator": "section[9]/table-wrap[1]#tab1"}}, {"id": "asset:table:pmid:34568491:2", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:9fa8219fc4674a1fb72249cdcd8ecc64a5eaf0dade171b20d1493c8f9c44b03f", "bytes": 750, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[10]/table-wrap[1]#tab2", "version": null, "note": "Information of key genes in PPI network of GSE29111.", "structure": {"pmcid": "PMC8456013", "section_index": 10, "section_title": "3.2. Protein Interaction Analysis and Module Analysis of DEGs", "row_count": 11, "column_count": 5}, "table": {"label": "Table 2", "caption": "Information of key genes in PPI network of GSE29111.", "rows": [["Gene", "UniProt ID", "Degree", "Expression level", "Module"], ["BDKRB2", "P30411", "8", "Upregulation", "Module 1"], ["HRH1", "P35367", "6", "Upregulation", "Module 1"], ["KISS1", "Q15726", "6", "Upregulation", "Module 1"], ["GRPR", "P30550", "6", "Downregulation", "Module 1"], ["TACR3", "P29371", "6", "Downregulation", "Module 1"], ["HTR2B", "P41595", "6", "Downregulation", "Module 1"], ["CCL25", "O15444", "3", "Upregulation", "—"], ["NPBWR1", "P48145", "3", "Upregulation", "—"], ["BDKRB1", "P46663", "8", "Upregulation", "Module 1"], ["ORM1", "P02763", "2", "Downregulation", "Module 1"]], "row_count": 11, "column_count": 5, "numeric_cells": 29, "header_rows": 1, "locator": "section[10]/table-wrap[1]#tab2"}}, {"id": "asset:table:pmid:34568491:3", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:be80a5a257efbbe85626ce7325ccfa73a42c4b7e109d5e47589204d8ab26c915", "bytes": 738, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[10]/table-wrap[2]#tab3", "version": null, "note": "Information of key genes in protein interaction network of GSE60993.", "structure": {"pmcid": "PMC8456013", "section_index": 10, "section_title": "3.2. Protein Interaction Analysis and Module Analysis of DEGs", "row_count": 11, "column_count": 5}, "table": {"label": "Table 3", "caption": "Information of key genes in protein interaction network of GSE60993.", "rows": [["Gene", "UniProt ID", "Degree", "Expression level", "Module"], ["IFI44", "Q8TCB0", "3", "Downregulation", "Module 1"], ["FFAR2", "O15552", "2", "Downregulation", "—"], ["GNG10", "P50151", "3", "Downregulation", "—"], ["CXCR2", "P25025", "2", "—", "—"], ["MCEMP1", "Q8IX19", "2", "Downregulation", "—"], ["FPR2", "P25090", "5", "—", "—"], ["CLEC4D", "Q8WXI8", "2", "Downregulation", "—"], ["IFIT3", "O14879", "3", "Downregulation", "Module 1"], ["RSAD2", "Q8WXG1", "3", "Downregulation", "Module 1"], ["PLSCR1", "O15162", "3", "Downregulation", "Module 1"]], "row_count": 11, "column_count": 5, "numeric_cells": 23, "header_rows": 1, "locator": "section[10]/table-wrap[2]#tab3"}}, {"id": "asset:table:pmid:34568491:4", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:6a0d78c7cff502d8f5295537c5c10ef5ba138c8f36c8cfb9ad8c89b8321b9016", "bytes": 518, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[11]/table-wrap[1]#tab4", "version": null, "note": "Information on GO entries enriched by differentially expressed genes in GSE29111.", "structure": {"pmcid": "PMC8456013", "section_index": 11, "section_title": "3.3. Enrichment Analysis of DEGs", "row_count": 5, "column_count": 4}, "table": {"label": "Table 4", "caption": "Information on GO entries enriched by differentially expressed genes in GSE29111.", "rows": [["Category", "ID", "Item", "FDR"], ["BP", "GO:0006954", "Inflammatory response", "6.67E − 04"], ["BP", "GO:0007186", "G-protein-coupled receptor signaling pathway", "0.004568"], ["CC", "GO:0005887", "Integral component of plasma membrane", "0.003999"], ["CC", "GO:0005886", "Plasma membrane", "0.012242"]], "row_count": 5, "column_count": 4, "numeric_cells": 8, "header_rows": 1, "locator": "section[11]/table-wrap[1]#tab4"}}, {"id": "asset:table:pmid:34568491:5", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:f5f00e70d77c544d75c93dbdd288ac8805b59764ec0ab6d4b2c126eecb2c258a", "bytes": 3913, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[11]/table-wrap[2]#tab5", "version": null, "note": "Information on GO entries enriched by differentially expressed genes in GSE60993.", "structure": {"pmcid": "PMC8456013", "section_index": 11, "section_title": "3.3. Enrichment Analysis of DEGs", "row_count": 53, "column_count": 4}, "table": {"label": "Table 5", "caption": "Information on GO entries enriched by differentially expressed genes in GSE60993.", "rows": [["Category", "ID", "Item", "P adjust"], ["BP", "GO:0042119", "Neutrophil activation", "1.41E − 05"], ["BP", "GO:0045088", "Regulation of innate immune response", "6.17E − 05"], ["BP", "GO:0043312", "Neutrophil degranulation", "6.17E − 05"], ["BP", "GO:0002283", "Neutrophil activation involved in immune response", "6.17E − 05"], ["BP", "GO:0002446", "Neutrophil mediated immunity", "6.17E − 05"], ["BP", "GO:0035743", "CD4-positive, alpha-beta T cell cytokine production", "0.000114"], ["BP", "GO:0045089", "Positive regulation of innate immune response", "0.000148"], ["BP", "GO:0002367", "Cytokine production involved in immune response", "0.000235"], ["BP", "GO:0098542", "Defense response to other organisms", "0.000496"], ["BP", "GO:0002369", "T cell cytokine production", "0.000501"], ["BP", "GO:0002720", "Positive regulation of cytokine production involved in immune response", "0.001009"], ["BP", "GO:0030595", "Leukocyte chemotaxis", "0.001785"], ["BP", "GO:0002440", "Production of molecular mediator of immune response", "0.001785"], ["BP", "GO:0002699", "Positive regulation of immune effector process", "0.001886"], ["BP", "GO:0070673", "Response to interleukin-18", "0.001886"], ["BP", "GO:0002526", "Acute inflammatory response", "0.002469"], ["BP", "GO:0002690", "Positive regulation of leukocyte chemotaxis", "0.002469"], ["BP", "GO:0002718", "Regulation of cytokine production involved in immune response", "0.002508"], ["BP", "GO:0002456", "T cell mediated immunity", "0.002638"], ["BP", "GO:0002708", "Positive regulation of lymphocyte mediated immunity", "0.002638"], ["BP", "GO:0060337", "Type I interferon signaling pathway", "0.002638"], ["BP", "GO:0071357", "Cellular response to type I interferon", "0.002638"], ["BP", "GO:0042742", "Defense response to bacterium", "0.002638"], ["BP", "GO:0002702", "Positive regulation of production of molecular mediator of immune response", "0.002638"], ["BP", "GO:0034340", "Response to type I interferon", "0.002648"], ["BP", "GO:0060326", "Cell chemotaxis", "0.002648"], ["BP", "GO:0002726", "Positive regulation of T cell cytokine production", "0.003238"], ["BP", "GO:0002688", "Regulation of leukocyte chemotaxis", "0.003238"], ["BP", "GO:0002705", "Positive regulation of leukocyte mediated immunity", "0.004302"], ["BP", "GO:0002687", "Positive regulation of leukocyte migration", "0.00459"], ["BP", "GO:0032103", "Positive regulation of response to external stimulus", "0.005129"], ["BP", "GO:0050921", "Positive regulation of chemotaxis", "0.005298"], ["BP", "GO:0009615", "Response to virus", "0.005298"], ["BP", "GO:0002706", "Regulation of lymphocyte mediated immunity", "0.005706"], ["BP", "GO:0002700", "Regulation of production of molecular mediator of immune response", "0.005732"], ["BP", "GO:0070102", "Interleukin-6-mediated signaling pathway", "0.005732"], ["BP", "GO:0002724", "Regulation of T cell cytokine production", "0.006379"], ["BP", "GO:0002251", "Organ or tissue specific immune response", "0.008387"], ["BP", "GO:0002711", "Positive regulation of T cell mediated immunity", "0.009107"], ["BP", "GO:0097529", "Myeloid leukocyte migration", "0.009288"], ["BP", "GO:0019835", "Cytolysis", "0.009599"], ["CC", "GO:0042581", "Specific granule", "1.44E − 05"], ["CC", "GO:0070820", "Tertiary granule", "1.44E − 05"], ["CC", "GO:0030667", "Secretory granule membrane", "0.000164"], ["CC", "GO:0070821", "Tertiary granule membrane", "0.000654"], ["CC", "GO:0035579", "Specific granule membrane", "0.001009"], ["CC", "GO:0098802", "Plasma membrane receptor complex", "0.003883"], ["CC", "GO:1904724", "Tertiary granule lumen", "0.009249"], ["CC", "GO:0101003", "Ficolin-1-rich granule membrane", "0.009249"], ["CC", "GO:0035580", "Specific granule lumen", "0.009249"], ["MF", "GO:0004896", "Cytokine receptor activity", "6.26E − 05"], ["MF", "GO:0019955", "Cytokine binding", "0.003951"]], "row_count": 53, "column_count": 4, "numeric_cells": 107, "header_rows": 1, "locator": "section[11]/table-wrap[2]#tab5"}}], "gaps": ["asset:data:geo:GSE29111 not downloaded", "asset:data:geo:GSE29111 licence not read", "asset:data:geo:GSE60993 not downloaded", "asset:data:geo:GSE60993 licence not read"]}, "analysis": {"state": "complete", "methods": [{"id": "method-1", "family": "differential_expression", "specific": "limma_voom", "label": "Differential expression analysis", "dsl_operations": ["normalise_counts", "differential_expression_fit", "fdr_bh"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["count_matrix_with_condition"], "evidence": {"score": 1.0, "band": "verbatim", "quote": "DEG analysis of these 2 datasets is performed using the “limma” package in R software."}}, {"id": "method-2", "family": "correlation_analysis", "specific": "pearson", "label": "Correlation analysis", "dsl_operations": ["pearson_r"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["paired_numeric_columns"], "evidence": {"score": 0.8, "band": "high", "quote": "Pearson correlation"}}, {"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": "protein-protein interaction"}}, {"id": "method-4", "family": "network_analysis", "specific": "pathway_enrichment", "label": "Network / pathway analysis", "dsl_operations": ["pathway_enrich"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["edge_list"], "evidence": {"score": 0.8, "band": "high", "quote": "pathway enrichment"}}, {"id": "method-5", "family": "network_analysis", "specific": "centrality", "label": "Network / pathway analysis", "dsl_operations": ["build_graph", "centrality_scores", "pathway_enrich"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["edge_list"], "evidence": {"score": 0.8, "band": "high", "quote": "Centrality"}}], "targets": [], "gaps": []}, "capability": {"state": "complete", "requirements": [{"capability_id": "capability:computational_analysis", "label": "Computational analysis platform", "assay_families": ["meta_analysis", "machine_learning", "survival_analysis", "statistical_regression", "pca", "molecular_docking", "network_analysis", "differential_expression", "gwas"], "availability_state": "owned", "tier_unlocked": "R1", "candidate": "Automated Assays Laravel application and simulated adapters"}], "gaps": []}, "readiness": {"state": "complete", "tier": "R1", "blocking_axis": "none", "blocked_on": "nothing:replicable_now", "axes": {"method": {"tier": "R1", "expressible": true, "required_operations": ["normalise_counts", "differential_expression_fit", "fdr_bh"], "missing_operations": [], "basis": "The paper names the method it used and the corpus's method extractor maps it onto the DSL catalogue: limma_voom."}, "capability": {"tier": "R1", "capability_id": "capability:computational_analysis", "availability_state": "owned", "basis": "The computational analysis is owned. The physical bench the paper used is not, so a physical validation cannot be run here."}, "data": {"tier": "R1", "reachable": true, "accessions": ["GSE29111", "GSE60993"], "resolved_accessions": ["GSE29111", "GSE60993"], "statements": ["The raw data supporting the conclusions of this article will be made available by the authors, without undue reservation. All data obtained or analyzed during this study are available from the published article and its supplementary information files. The datasets during the current study are available from the corresponding author upon reasonable request."], "basis": "The paper names GSE29111, GSE60993 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:34568491", "data:geo:GSE29111", "asset:table:pmid:34568491:1", "asset:table:pmid:34568491:2", "asset:table:pmid:34568491:3", "asset:table:pmid:34568491:4", "asset:table:pmid:34568491:5"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE29111"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-10-31T18:35:14Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 3, "usage": {"prompt_tokens": 45945, "completion_tokens": 1072, "cached_tokens": 785}}, "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:34568491", "type": "paper", "label": "pmid:34568491"}, {"id": "source:pmid:34568491", "type": "manuscript", "label": "PMID 34568491 full text"}, {"id": "data:geo:GSE29111", "type": "dataset", "label": "GEO GSE29111"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:34568491", "type": "paper", "label": "pmid:34568491"}, {"id": "source:pmid:34568491", "type": "manuscript", "label": "PMID 34568491 full text"}, {"id": "data:geo:GSE29111", "type": "dataset", "label": "GEO GSE29111"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-34568491", "type": "extraction", "used": ["source:pmid:34568491"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE29111", "type": "accession_resolution", "used": ["data:geo:GSE29111"], "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:34568491", "parent_hash": "sha256:f22108cac868932036295a307c32659be427f5b073e2d076e075e880fcad8161", "fork_of": null, "generation": 7}, "gaps": ["asset:data:geo:GSE29111 licence not read", "asset:data:geo:GSE29111 not downloaded", "asset:data:geo:GSE60993 licence not read", "asset:data:geo:GSE60993 not downloaded", "execution.not_run", "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": ["DEG analysis of these 2 datasets is performed using the “limma” package in R software."], "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":"2026-11-04T03:15:55+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}}}