{"data":{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:29226137", "kind": "science-record", "revision": 8, "content_hash": "sha256:83aeb300716f6500f2847e2dcb849fc602d529683e6649ff1e9187bab275d194", "created_at": "2026-11-01T15:40:30Z", "updated_at": "2026-11-01T21:59:36Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Identification of Key Pathways and Genes in Advanced Coronary Atherosclerosis Using Bioinformatics Analysis.", "doi": "10.1155/2017/4323496", "pmid": "29226137", "authors": ["Xiaowen Tan", "Xiting Zhang", "Lanlan Pan", "Xiaoxuan Tian", "Pengzhi Dong"], "journal": "BioMed research international", "year": 2017, "abstract": "BACKGROUND: Coronary artery atherosclerosis is a chronic inflammatory disease. This study aimed to identify the key changes of gene expression between early and advanced carotid atherosclerotic plaque in human.\nMETHODS: Gene expression dataset GSE28829 was downloaded from Gene Expression Omnibus (GEO), including 16 advanced and 13 early stage atherosclerotic plaque samples from human carotid. Differentially expressed genes (DEGs) were analyzed.\nRESULTS: 42,450 genes were obtained from the dataset. Top 100 up- and downregulated DEGs were listed. Functional enrichment analysis and Kyoto Encyclopedia of Genes and Genomes (KEGG) identification were performed. The result of functional and pathway enrichment analysis indicted that the immune system process played a critical role in the progression of carotid atherosclerotic plaque. Protein-protein interaction (PPI) networks were performed either. Top 10 hub genes were identified from PPI network and top 6 modules were inferred. These genes were mainly involved in chemokine signaling pathway, cell cycle, B cell receptor signaling pathway, focal adhesion, and regulation of actin cytoskeleton.\nCONCLUSION: The present study indicated that analysis of DEGs would make a deeper understanding of the molecular mechanisms of atherosclerosis development and they might be used as molecular targets and diagnostic biomarkers for the treatment of atherosclerosis.", "claims": [{"id": "claim-method", "statement": "DEGs were identified using signal to noise method where a total of 42,450 genes were analyzed and top 100 (top 100 upregulated and top 100 downregulated genes) genes were listed.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:29226137", "locator": "sections[4] \"2.2. Identification of Differentially Expression Genes (DEGs)\" paragraph 2", "quote": "DEGs were identified using signal to noise method where a total of 42,450 genes were analyzed and top 100 (top 100 upregulated and top 100 downregulated genes) genes were listed."}], "state": "complete"}, {"id": "claim-data-access", "statement": "The gene expression profiles of GSE28829 were downloaded from Gene Expression Omnibus (GEO). GSE28829 was performed on GPL570, [HG-U133_Plus_2] Affymetrix Human Genome U133 Plus 2.0 Array. The GSE28829 data set contained 29 samples, including 16 advanced atherosclerotic plaque samples and 13 early atherosclerotic plaque samples.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:29226137", "locator": "sections[3] \"2.1. Microarray Data\" paragraph 2", "quote": "The gene expression profiles of GSE28829 were downloaded from Gene Expression Omnibus (GEO). GSE28829 was performed on GPL570, [HG-U133_Plus_2] Affymetrix Human Genome U133 Plus 2.0 Array. The GSE28829 data set contained 29 samples, including 16 advanced atherosclerotic plaque samples and 13 early atherosclerotic plaque samples."}], "state": "complete"}, {"id": "claim-target-result", "statement": "Using the signal-to-noise method on GSE28829 gene-expression data downloaded from GEO, the study identified C2 as the most significantly upregulated gene (score 1.792) and H2AFV as the most significantly downregulated gene (score −2.249).", "kind": "qualitative", "target": null, "evidence": [{"asset": "source:pmid:29226137", "locator": "sections[0] \"Abstract\" paragraph 2", "quote": "Gene expression dataset GSE28829 was downloaded from Gene Expression Omnibus (GEO), including 16 advanced and 13 early stage atherosclerotic plaque samples from human carotid."}, {"asset": "source:pmid:29226137", "locator": "sections[4] \"2.2. Identification of Differentially Expression Genes (DEGs)\" paragraph 2", "quote": "DEGs were identified using signal to noise method where a total of 42,450 genes were analyzed and top 100 (top 100 upregulated and top 100 downregulated genes) genes were listed."}, {"asset": "source:pmid:29226137", "locator": "sections[9] \"3.1. Identification of Differentially Expressed Genes (DEGs)\" paragraph 2", "quote": "Among the total 42,450 genes, the most significant signal of upregulated gene is C2, and the signal to noise score is 1.792. The most significant signal of downregulated gene is H2AFV where the signal to noise score is −2.249."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "complete", "objective": "Using the signal-to-noise method on GSE28829 gene-expression data downloaded from GEO, the study identified C2 as the most significantly upregulated gene (score 1.792) and H2AFV as the most significantly downregulated gene (score −2.249).", "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:29226137"], "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:GSE28829"], "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:GSE28829"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:29226137", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1155/2017/4323496", "sha256": "sha256:d72f0f5f86e9dca3fe7ed9feb8316c19c4a64e36af134bd54a28d835762b0523", "bytes": 37036, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1155/2017/4323496", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC5684517", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE28829", "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=GSE28829", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE28829", "version": null, "note": "The gene expression profiles of GSE28829 were downloaded from Gene Expression Omnibus (GEO). GSE28829 was performed on GPL570, [HG-U133_Plus_2] Affymetrix Human Genome U133 Plus 2.0 Array. The GSE28829 data set contained 29 samples, including 16 advanced atherosclerotic plaque samples and 13 early atherosclerotic plaque samples.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The gene expression profiles of GSE28829 were downloaded from Gene Expression Omnibus (GEO). GSE28829 was performed on GPL570, [HG-U133_Plus_2] Affymetrix Human Genome U133 Plus 2.0 Array. The GSE28829 data set contained 29 samples, including 16 advanced atherosclerotic plaque samples and 13 early atherosclerotic plaque samples.", "access_statement_kind": "repository_route_statement", "sample_accessions": ["GSM714070", "GSM714071", "GSM714072", "GSM714073", "GSM714074", "GSM714075", "GSM714076", "GSM714077", "GSM714078", "GSM714079", "GSM714080", "GSM714081", "GSM714082", "GSM714083", "GSM714084", "GSM714085", "GSM714086", "GSM714087", "GSM714088", "GSM714089", "GSM714090", "GSM714091", "GSM714092", "GSM714093", "GSM714094", "GSM714095", "GSM714096", "GSM714097", "GSM714098"], "sample_count": 29, "group_sizes": null, "group_sizes_basis": null, "platform": "570", "taxon": "Homo sapiens", "title": "Gene Expression in early and advanced atherosclerotic plaque from human carotid", "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:29226137:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:1fed78a873ac5f751d59a34f4b91016a9de6652c58db37e905484c69e44e6b60", "bytes": 882, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[10]/table-wrap[1]#tab1", "version": null, "note": "Cellular component (GO) enrichment analysis in networks.", "structure": {"pmcid": "PMC5684517", "section_index": 10, "section_title": "3.2. Gene Ontology and Pathway Enrichment Analysis", "row_count": 12, "column_count": 5}, "table": {"label": "Table 1", "caption": "Cellular component (GO) enrichment analysis in networks.", "rows": [["Expression", "#Pathway ID", "Pathway description", "Observed gene count", "False discovery rate"], ["Upregulated", "GO.0005764", "Lysosome", "103", "1.02E − 25"], ["GO.0005773", "Vacuole", "112", "1.32E − 25"], ["GO.0005886", "Plasma membrane", "441", "1.46E − 25"], ["GO.0071944", "Cell periphery", "446", "1.46E − 25"], ["GO.0044459", "Plasma membrane part", "268", "1.30E − 24"], [""], ["Downregulated", "GO.0005737", "Cytoplasm", "807", "9.90E − 37"], ["GO.0043229", "Intracellular organelle", "838", "1.42E − 26"], ["GO.0044422", "Organelle part", "639", "3.03E − 26"], ["GO.0044444", "Cytoplasmic part", "611", "3.03E − 26"], ["GO.0044446", "Intracellular organelle part", "628", "3.03E − 26"]], "row_count": 12, "column_count": 5, "numeric_cells": 30, "header_rows": 1, "locator": "section[10]/table-wrap[1]#tab1"}}, {"id": "asset:table:pmid:29226137:2", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:eff5eccfec84feefcd780d0162a433c468b90fd6dabe8ef1e696beeda02c7d38", "bytes": 894, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[10]/table-wrap[2]#tab2", "version": null, "note": "Molecular function (GO) enrichment analysis in networks.", "structure": {"pmcid": "PMC5684517", "section_index": 10, "section_title": "3.2. Gene Ontology and Pathway Enrichment Analysis", "row_count": 12, "column_count": 5}, "table": {"label": "Table 2", "caption": "Molecular function (GO) enrichment analysis in networks.", "rows": [["Expression", "#Pathway ID", "Pathway description", "Observed gene count", "False discovery rate"], ["Upregulated", "GO.0005515", "Protein binding", "445", "7.57E − 24"], ["GO.0005102", "Receptor binding", "148", "1.76E − 16"], ["GO.0060089", "Molecular transducer activity", "194", "1.39E − 14"], ["GO.0003674", "Molecular_function", "889", "4.21E − 12"], ["GO.0005488", "Binding", "761", "4.21E − 12"], [""], ["Downregulated", "GO.0005515", "Protein binding", "426", "8.46E − 22"], ["GO.0005488", "Binding", "740", "3.00E − 12"], ["GO.0008092", "Cytoskeletal protein binding", "79", "7.43E − 12"], ["GO.0019899", "Enzyme binding", "151", "7.43E − 12"], ["GO.0000166", "Nucleotide binding", "218", "1.07E − 08"]], "row_count": 12, "column_count": 5, "numeric_cells": 30, "header_rows": 1, "locator": "section[10]/table-wrap[2]#tab2"}}, {"id": "asset:table:pmid:29226137:3", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:21244b63d9cfb9db6c876e804b50ddebab22277c0a52a850112e09d4e7fcb9e9", "bytes": 1029, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[10]/table-wrap[3]#tab3", "version": null, "note": "Biological process (GO) enrichment analysis in networks.", "structure": {"pmcid": "PMC5684517", "section_index": 10, "section_title": "3.2. Gene Ontology and Pathway Enrichment Analysis", "row_count": 12, "column_count": 5}, "table": {"label": "Table 3", "caption": "Biological process (GO) enrichment analysis in networks.", "rows": [["Expression", "#Pathway ID", "Pathway description", "Observed gene count", "False discovery rate"], ["Upregulated", "GO.0002376", "Immune system process", "321", "7.44E − 63"], ["GO.0006952", "Defense response", "252", "5.46E − 56"], ["GO.0002682", "Regulation of immune system process", "246", "8.58E − 56"], ["GO.0006955", "Immune response", "241", "2.11E − 55"], ["GO.0050776", "Regulation of immune response", "175", "4.95E − 49"], [""], ["Downregulated", "GO.0007010", "Cytoskeleton organization", "109", "2.81E − 12"], ["GO.0016043", "Cellular component organization", "386", "2.81E − 12"], ["GO.0048522", "Positive regulation of cellular process", "362", "2.81E − 12"], ["GO.0051128", "Regulation of cellular component organization", "211", "6.71E − 12"], ["GO.0071840", "Cellular component organization or biogenesis", "390", "1.02E − 11"]], "row_count": 12, "column_count": 5, "numeric_cells": 30, "header_rows": 1, "locator": "section[10]/table-wrap[3]#tab3"}}, {"id": "asset:table:pmid:29226137:4", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:a621ea75f8b3d7f05d3b3c8761c300a2e3400f872fdbdd349f1486ea004493b5", "bytes": 2112, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[11]/table-wrap[1]#tab5", "version": null, "note": "Top 6 modules from protein-protein interaction network.", "structure": {"pmcid": "PMC5684517", "section_index": 11, "section_title": "3.3. Module Screening from the Protein-Protein Interaction (PPI) Network", "row_count": 12, "column_count": 3}, "table": {"label": "Table 5", "caption": "Top 6 modules from protein-protein interaction network.", "rows": [["Gene set", "MCODE score", "Nodes"], ["Chemokine signaling pathway", "31.419", "CCL20, PNOC, PENK, LPAR5, C5AR1, CCR1, RGS1, ADRA2A, CXCL3, CXCL2, CCL21, CCR7, CCL19, FPR3, CCR5, CCL5, CXCL16, ADCY3, P2RY13, ADORA3, CCL16, IL8, RGS10, RGS19, CXCL1, C3, CCR2, C3AR1, CXCL12, GPR18, CXCR4, ADCY4"], [""], ["Cell cycle", "10.303", "KIF20A, PTTG1, HLA-B, CDK1, CASC5, IRF8, IRF4, CIITA, CKS2, IRF5, IRF1, IRF7, CCL4, UBE2C, KIF4A, CCNA2, AURKA, ZWINT, TOP2A, HLA-A, PTAFR, TYMS, CENPK, CCNB1, MLF1IP, HLA-C, NUSAP1, KNTC1, SGOL2, MCM4, PML, RCC2, CCNB2, TTK"], [""], ["B cell receptor signaling pathway", "9.762", "VWF, NCF4, SH3KBP1, PLEK, CD14, TNFSF13B, CD79A, BLNK, CD72, SPI1, PTPRC, KLRG1, IL2RB, PIK3CD, SYK, VAV3, CASP1, CDH5, PLCG2, FCER1G, SDC1, NCF1, INPP5D, PIK3R5, RAC2, CD22, NCF2, LYN, ACE, CYBA, DAPP1, ITGAL, HCLS1, MYD88, PRKCH, PAG1, ANPEP, CD36, THY1, SHC2, NOD2, HCK, CD2"], [""], ["Focal adhesion", "8.852", "TNS1, DLG1, NDE1, PPM1B, WDR1, RRAS, ITGB3, CNN1, SRSF1, CCND2, HNRNPD, IGF1R, TPM1, TPM2, EGFR, RHEB, TLN2, HNRNPU, PDS5B, SKA2, NUDC, PAFAH1B1, RHOQ, ABL1, CAP2, ACTG2, PPP3CB, TUBA4A, CORO1C, PAPOLA, RAF1, LAMA5, SF3B2, LAMC1, MAPRE1, ILKAP, RHOA, NDEL1, SRRM1, SRSF3, PPM1A, PPP2R5A, PPP1R12A, PPP1CB, ACTR3B, HNRNPA3, CYCS, ENAH, CLIP1, CLASP2, PPP2CB, RANBP2, PPP2R5C, VCL, ACTR3"], [""], ["Focal adhesion", "7.414", "YWHAZ, ITGA11, GNB5, KALRN, ROCK1, DNAJB4, SMAD4, S1PR3, DNAJC10, ITGB1, DNAJB6, ITGA8, ERBB2, FGF13, PDE4D, GNAS, PRKAR1A, CYFIP2, FRK, DNAJB5, CCND1, CASK, CRK, ADCY9, DLG3, HSPA4, HSPA4L, ADCY5, H2AFV, PDE3A, YAP1, PGR, MPP7, ITGA9, ROCK2, PDE8B, PCM1, PARVA, ADCY2, RAP1A, KAT7, ITGA7, DNAJA4, MAPK9, ACTN2, ZAK, CEP70, CEP63, PPM1K, MAP3K7, MPP6, COL4A5, HSP90AB1, SUGT1, STK11, PTGER3, FGFR1, ACTA2, ROR1"], [""], ["Regulation of actin cytoskeleton", "6.25", "CALD1, PLS3, FGF2, TAGLN, RHOB, CFL2, MYLK, ITGB5, WASL, JAK2, LMOD1, DSTN, PFN2, MYH11, ACTN1, PTPN11, SORBS1"]], "row_count": 12, "column_count": 3, "numeric_cells": 12, "header_rows": 1, "locator": "section[11]/table-wrap[1]#tab5"}}, {"id": "asset:table:pmid:29226137:5", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:4d29e467aee22d84ede73d092e8de942f7c4b486902de598ed9b1c40fcaaf686", "bytes": 1675, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[12]/table-wrap[1]#tab6", "version": null, "note": "KEGG analysis based on module A.", "structure": {"pmcid": "PMC5684517", "section_index": 12, "section_title": "3.4. Pathways Interrelation Analysis", "row_count": 20, "column_count": 6}, "table": {"label": "Table 6", "caption": "KEGG analysis based on module A.", "rows": [["GOID", "GO term", "Ontology source", "Term P value", "Nr. genes", "Associated genes found"], ["GO:0004064", "NF-kappa B signaling pathway", "KEGG_01.03.2017", "19.0E − 6", "5.00", "[CCL19, CCL21, CXCL12, CXCL2, CXCL8]"], [""], ["GO:0005150", "Staphylococcus aureus infection", "KEGG_01.03.2017", "43.0E − 6", "4.00", "[C3, C3AR1, C5AR1, FPR3]"], [""], ["GO:0004060", "Cytokine-cytokine receptor interaction", "KEGG_01.03.2017", "37.0E − 18", "16.00", "[CCL16, CCL19, CCL20, CCL21, CCL5, CCR1, CCR2, CCR5, CCR7, CXCL1, CXCL12, CXCL16, CXCL2, CXCL3, CXCL8, CXCR4]"], [""], ["GO:0004062", "Chemokine signaling pathway", "KEGG_01.03.2017", "10.0E − 24", "18.00", "[ADCY3, ADCY4, CCL16, CCL19, CCL20, CCL21, CCL5, CCR1, CCR2, CCR5, CCR7, CXCL1, CXCL12, CXCL16, CXCL2, CXCL3, CXCL8, CXCR4]"], [""], ["GO:0004657", "IL-17 signaling pathway", "KEGG_01.03.2017", "17.0E − 6", "5.00", "[CCL20, CXCL1, CXCL2, CXCL3, CXCL8]"], [""], ["GO:0004668", "TNF signaling pathway", "KEGG_01.03.2017", "35.0E − 6", "5.00", "[CCL20, CCL5, CXCL1, CXCL2, CXCL3]"], [""], ["GO:0005120", "Epithelial cell signaling in Helicobacter pylori infection", "KEGG_01.03.2017", "1.7E − 3", "3.00", "[CCL5, CXCL1, CXCL8]"], [""], ["GO:0005132", "Salmonella infection", "KEGG_01.03.2017", "230.0E − 6", "4.00", "[CXCL1, CXCL2, CXCL3, CXCL8]"], [""], ["GO:0005134", "Legionellosis", "KEGG_01.03.2017", "1.2E − 6", "5.00", "[C3, CXCL1, CXCL2, CXCL3, CXCL8]"], [""], ["GO:0005323", "Rheumatoid arthritis", "KEGG_01.03.2017", "14.0E − 6", "5.00", "[CCL20, CCL5, CXCL1, CXCL12, CXCL8]"]], "row_count": 20, "column_count": 6, "numeric_cells": 47, "header_rows": 1, "locator": "section[12]/table-wrap[1]#tab6"}}, {"id": "asset:table:pmid:29226137:6", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:81733fc44f474872cae8e9576f379c4346bd392cf1da9fb9684fd8d858dfab3f", "bytes": 3079, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[12]/table-wrap[2]#tab7", "version": null, "note": "KEGG analysis based on module D.", "structure": {"pmcid": "PMC5684517", "section_index": 12, "section_title": "3.4. Pathways Interrelation Analysis", "row_count": 46, "column_count": 6}, "table": {"label": "Table 7", "caption": "KEGG analysis based on module D.", "rows": [["GOID", "GO term", "Ontology source", "Term P value", "Nr. genes", "Associated genes found"], ["GO:0005130", "Pathogenic Escherichia coli infection", "KEGG_01.03.2017", "3.6E − 3", "3.00", "[ABL1, RHOA, TUBA4A]"], [""], ["GO:0004071", "Sphingolipid signaling pathway", "KEGG_01.03.2017", "500.0E − 6", "5.00", "[PPP2CB, PPP2R5A, PPP2R5C, RAF1, RHOA]"], [""], ["GO:0004270", "Vascular smooth muscle contraction", "KEGG_01.03.2017", "570.0E − 6", "5.00", "[ACTG2, PPP1CB, PPP1R12A, RAF1, RHOA]"], [""], ["GO:0005210", "Colorectal cancer", "KEGG_01.03.2017", "4.6E − 3", "3.00", "[CYCS, RAF1, RHOA]"], [""], ["GO:0004270", "Vascular smooth muscle contraction", "KEGG_01.03.2017", "570.0E − 6", "5.00", "[ACTG2, PPP1CB, PPP1R12A, RAF1, RHOA]"], [""], ["GO:0004510", "Focal adhesion", "KEGG_01.03.2017", "560.0E − 12", "12.00", "[CCND2, EGFR, IGF1R, ITGB3, LAMA5, LAMC1, PPP1CB, PPP1R12A, RAF1, RHOA, TLN2, VCL]"], [""], ["GO:0004611", "Platelet activation", "KEGG_01.03.2017", "610.0E − 6", "5.00", "[ITGB3, PPP1CB, PPP1R12A, RHOA, TLN2]"], [""], ["GO:0004720", "Long-term potentiation", "KEGG_01.03.2017", "6.3E − 3", "3.00", "[PPP1CB, PPP3CB, RAF1]"], [""], ["GO:0004810", "Regulation of actin cytoskeleton", "KEGG_01.03.2017", "2.1E − 6", "9.00", "[EGFR, ENAH, ITGB3, PPP1CB, PPP1R12A, RAF1, RHOA, RRAS, VCL]"], [""], ["GO:0005210", "Colorectal cancer", "KEGG_01.03.2017", "4.6E − 3", "3.00", "[CYCS, RAF1, RHOA]"], [""], ["GO:0004071", "Sphingolipid signaling pathway", "KEGG_01.03.2017", "500.0E − 6", "5.00", "[PPP2CB, PPP2R5A, PPP2R5C, RAF1, RHOA]"], [""], ["GO:0004152", "AMPK signaling pathway", "KEGG_01.03.2017", "570.0E − 6", "5.00", "[IGF1R, PPP2CB, PPP2R5A, PPP2R5C, RHEB]"], [""], ["GO:0004520", "Adherens junction", "KEGG_01.03.2017", "700.0E − 6", "4.00", "[EGFR, IGF1R, RHOA, VCL]"], [""], ["GO:0004730", "Long-term depression", "KEGG_01.03.2017", "4.6E − 3", "3.00", "[IGF1R, PPP2CB, RAF1]"], [""], ["GO:0005214", "Glioma", "KEGG_01.03.2017", "5.6E − 3", "3.00", "[EGFR, IGF1R, RAF1]"], [""], ["GO:0005218", "Melanoma", "KEGG_01.03.2017", "6.9E − 3", "3.00", "[EGFR, IGF1R, RAF1]"], [""], ["GO:0003015", "mRNA surveillance pathway", "KEGG_01.03.2017", "10.0E − 6", "6.00", "[PAPOLA, PPP1CB, PPP2CB, PPP2R5A, PPP2R5C, SRRM1]"], [""], ["GO:0004071", "Sphingolipid signaling pathway", "KEGG_01.03.2017", "500.0E − 6", "5.00", "[PPP2CB, PPP2R5A, PPP2R5C, RAF1, RHOA]"], [""], ["GO:0004114", "Oocyte meiosis", "KEGG_01.03.2017", "63.0E − 6", "6.00", "[IGF1R, PPP1CB, PPP2CB, PPP2R5A, PPP2R5C, PPP3CB]"], [""], ["GO:0004152", "AMPK signaling pathway", "KEGG_01.03.2017", "570.0E − 6", "5.00", "[IGF1R, PPP2CB, PPP2R5A, PPP2R5C, RHEB]"], [""], ["GO:0004261", "Adrenergic signaling in cardiomyocytes", "KEGG_01.03.2017", "140.0E − 6", "6.00", "[PPP1CB, PPP2CB, PPP2R5A, PPP2R5C, TPM1, TPM2]"], [""], ["GO:0004730", "Long-term depression", "KEGG_01.03.2017", "4.6E − 3", "3.00", "[IGF1R, PPP2CB, RAF1]"], [""], ["GO:0005210", "Colorectal cancer", "KEGG_01.03.2017", "4.6E − 3", "3.00", "[CYCS, RAF1, RHOA]"]], "row_count": 46, "column_count": 6, "numeric_cells": 97, "header_rows": 1, "locator": "section[12]/table-wrap[2]#tab7"}}, {"id": "asset:table:pmid:29226137:7", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:ca8c1dcb63a4001e98f3e6b25e8d37cfc8cfff2c2cb9564b10cb5f0222da7602", "bytes": 930, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[13]/table-wrap[1]#tab4", "version": null, "note": "KEGG pathways enrichment analysis in networks.", "structure": {"pmcid": "PMC5684517", "section_index": 13, "section_title": "4. Discussion", "row_count": 12, "column_count": 5}, "table": {"label": "Table 4", "caption": "KEGG pathways enrichment analysis in networks.", "rows": [["Expression", "#Pathway ID", "Pathway description", "Observed gene count", "False discovery rate"], ["Upregulated", "4380", "Osteoclast differentiation", "47", "6.30E − 22"], ["4060", "Cytokine-cytokine receptor interaction", "63", "6.90E − 18"], ["4062", "Chemokine signaling pathway", "51", "6.91E − 18"], ["4142", "Lysosome", "41", "1.75E − 17"], ["5150", "Staphylococcus aureus infection", "27", "2.52E − 17"], [""], ["Downregulated", "4510", "Focal adhesion", "38", "3.66E − 07"], ["4810", "Regulation of actin cytoskeleton", "37", "1.46E − 06"], ["5412", "Arrhythmogenic right ventricular cardiomyopathy (ARVC)", "20", "1.52E − 06"], ["4921", "Oxytocin signaling pathway", "30", "1.58E − 06"], ["4022", "cGMP-PKG signaling pathway", "30", "1.95E − 06"]], "row_count": 12, "column_count": 5, "numeric_cells": 30, "header_rows": 1, "locator": "section[13]/table-wrap[1]#tab4"}}], "gaps": ["asset:data:geo:GSE28829 not downloaded", "asset:data:geo:GSE28829 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": "network_analysis", "specific": "pathway_enrichment", "label": "Network / pathway analysis", "dsl_operations": ["pathway_enrich"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["edge_list"], "evidence": {"score": 0.7, "band": "medium", "quote": "pathway enrichment"}}, {"id": "method-3", "family": null, "specific": null, "label": "signal to noise method", "dsl_operations": [], "missing_operations": [], "expressible": null, "parameters": {}, "data_shapes": [], "evidence": {"score": 1.0, "band": "verbatim", "quote": "DEGs were identified using signal to noise method where a total of 42,450 genes were analyzed and top 100 (top 100 upregulated and top 100 downregulated genes) genes were listed."}}], "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": ["GSE28829"], "resolved_accessions": ["GSE28829"], "statements": ["The gene expression profiles of GSE28829 were downloaded from Gene Expression Omnibus (GEO). GSE28829 was performed on GPL570, [HG-U133_Plus_2] Affymetrix Human Genome U133 Plus 2.0 Array. The GSE28829 data set contained 29 samples, including 16 advanced atherosclerotic plaque samples and 13 early atherosclerotic plaque samples."], "basis": "The paper names GSE28829 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:29226137", "data:geo:GSE28829", "asset:table:pmid:29226137:1", "asset:table:pmid:29226137:2", "asset:table:pmid:29226137:3", "asset:table:pmid:29226137:4", "asset:table:pmid:29226137:5", "asset:table:pmid:29226137:6", "asset:table:pmid:29226137:7"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE28829"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-10-31T18:33:00Z", "independence": "same_provider"}, "evidence_check": {"method": "verbatim", "availability": null}, "calls": 8, "usage": {"prompt_tokens": 81275, "completion_tokens": 2704, "cached_tokens": 2064}}, "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:29226137", "type": "paper", "label": "pmid:29226137"}, {"id": "source:pmid:29226137", "type": "manuscript", "label": "PMID 29226137 full text"}, {"id": "data:geo:GSE28829", "type": "dataset", "label": "GEO GSE28829"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:29226137", "type": "paper", "label": "pmid:29226137"}, {"id": "source:pmid:29226137", "type": "manuscript", "label": "PMID 29226137 full text"}, {"id": "data:geo:GSE28829", "type": "dataset", "label": "GEO GSE28829"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-29226137", "type": "extraction", "used": ["source:pmid:29226137"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE28829", "type": "accession_resolution", "used": ["data:geo:GSE28829"], "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:29226137", "parent_hash": "sha256:f7294b575b035a00ff1dbc09ad549d301ba4bc6328e520fcf554918b9186b2f9", "fork_of": null, "generation": 7}, "gaps": ["asset:data:geo:GSE28829 licence not read", "asset:data:geo:GSE28829 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":"2026-11-04T01:41:57+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}}}