{"data":{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:34046056", "kind": "science-record", "revision": 7, "content_hash": "sha256:b0ec069640c6a7b5c82b56e05ddf5ff2399723b7a244537e838f293074392466", "created_at": "2026-11-01T15:41:37Z", "updated_at": "2026-11-01T22:03:51Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Predicting the Key Genes Involved in Aortic Valve Calcification Through Integrated Bioinformatics Analysis.", "doi": "10.3389/fgene.2021.650213", "pmid": "34046056", "authors": ["Dinghui Wang", "Tianhua Xiong", "Wenlong Yu", "Bin Liu", "Jing Wang", "Kaihu Xiao", "Qiang She"], "journal": "Frontiers in genetics", "year": 2021, "abstract": "Background: Valvular heart disease is obtaining growing attention in the cardiovascular field and it is believed that calcific aortic valve disease (CAVD) is the most common valvular heart disease (VHD) in the world. CAVD does not have a fully effective treatment to delay its progression and the specific molecular mechanism of aortic valve calcification remains unclear. Materials and Methods: We obtained the gene expression datasets GSE12644 and GSE51472 from the public comprehensive free database GEO. Then, a series of bioinformatics methods, such as GO and KEGG analysis, STING online tool, Cytoscape software, were used to identify differentially expressed genes in CAVD and healthy controls, construct a PPI network, and then identify key genes. In addition, immune infiltration analysis was used via CIBERSORT to observe the expression of various immune cells in CAVD. Results: A total of 144 differential expression genes were identified in the CAVD samples in comparison with the control samples, including 49 up-regulated genes and 95 down-regulated genes. GO analysis of DEGs were most observably enriched in the immune response, signal transduction, inflammatory response, proteolysis, innate immune response, and apoptotic process. The KEGG analysis revealed that the enrichment of DEGs in CAVD were remarkably observed in the chemokine signaling pathway, cytokine-cytokine receptor interaction, and PI3K-Akt signaling pathway. Chemokines CXCL13, CCL19, CCL8, CXCL8, CXCL16, MMP9, CCL18, CXCL5, VCAM1, and PPBP were identified as the hub genes of CAVD. It was macrophages that accounted for the maximal proportion among these immune cells. The expression of macrophages M0, B cells memory, and Plasma cells were higher in the CAVD valves than in healthy valves, however, the expression of B cells naïve, NK cells activated, and macrophages M2 were lower. Conclusion: We detected that chemokines CXCL13, CXCL8, CXCL16, and CXCL5, and CCL19, CCL8, and CCL18 are the most important markers of aortic valve disease. The regulatory macrophages M0, plasma cells, B cells memory, B cells naïve, NK cells activated, and macrophages M2 are probably related to the occurrence and the advancement of aortic valve stenosis. These identified chemokines and these immune cells may interact with a subtle adjustment relationship in the development of calcification in CAVD.", "claims": [{"id": "claim-data-access", "statement": "The original contributions presented in the study are included in the article/Supplementary Material, further inquiries can be directed to the corresponding author/s.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:34046056", "locator": "sections[17] \"Data Availability Statement\" paragraph 2", "quote": "The original contributions presented in the study are included in the article/Supplementary Material, further inquiries can be directed to the corresponding author/s."}], "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:34046056"], "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:GSE12644"], "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:GSE12644"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:34046056", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.3389/fgene.2021.650213", "sha256": "sha256:80550d65e402f28849474f9777afd171d6a98837cbbedef795bbc42e4024984e", "bytes": 39430, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.3389/fgene.2021.650213", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC8144713", "source": "europe_pmc_fulltext", "coverage": "whole_body_without_references", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE12644", "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=GSE12644", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE12644", "version": null, "note": "The original contributions presented in the study are included in the article/Supplementary Material, further inquiries can be directed to the corresponding author/s.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The original contributions presented in the study are included in the article/Supplementary Material, further inquiries can be directed to the corresponding author/s.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM317342", "GSM317343", "GSM317344", "GSM317345", "GSM317346", "GSM317347", "GSM317348", "GSM317349", "GSM317350", "GSM317351", "GSM377368", "GSM377369", "GSM377370", "GSM377371", "GSM377372", "GSM377373", "GSM377374", "GSM377375", "GSM377376", "GSM377377"], "sample_count": 20, "group_sizes": null, "group_sizes_basis": null, "platform": "570", "taxon": "Homo sapiens", "title": "Gene expression profile of normal and calcified stenotic human aortic valves", "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:GSE26953", "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=GSE26953", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE26953", "version": null, "note": "The original contributions presented in the study are included in the article/Supplementary Material, further inquiries can be directed to the corresponding author/s.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The original contributions presented in the study are included in the article/Supplementary Material, further inquiries can be directed to the corresponding author/s.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM663526", "GSM663527", "GSM663528", "GSM663529", "GSM663530", "GSM663531", "GSM663532", "GSM663533", "GSM663534", "GSM663535", "GSM663536", "GSM663537", "GSM663538", "GSM663539", "GSM663540", "GSM663541", "GSM663542", "GSM663543", "GSM663544", "GSM663545", "GSM663546", "GSM663547", "GSM663548", "GSM663549", "GSM665514", "GSM665515", "GSM665516", "GSM665517", "GSM665518", "GSM665519", "GSM665520", "GSM665521", "GSM665522", "GSM665523", "GSM665524", "GSM665525", "GSM665526", "GSM665527", "GSM665528", "GSM665529", "GSM665530", "GSM665531", "GSM665532", "GSM665533", "GSM665534", "GSM665535", "GSM665536", "GSM665537"], "sample_count": 48, "group_sizes": null, "group_sizes_basis": null, "platform": "8179;6947", "taxon": "Homo sapiens", "title": "Discovery of Shear- and Side-specific mRNAs and miRNAs in Human Aortic Valvular Endothelial Cells", "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:GSE51472", "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=GSE51472", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE51472", "version": null, "note": "The original contributions presented in the study are included in the article/Supplementary Material, further inquiries can be directed to the corresponding author/s.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The original contributions presented in the study are included in the article/Supplementary Material, further inquiries can be directed to the corresponding author/s.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM1246204", "GSM1246205", "GSM1246206", "GSM1246207", "GSM1246208", "GSM1246209", "GSM1246210", "GSM1246211", "GSM1246212", "GSM1246213", "GSM1246214", "GSM1246215", "GSM1246216", "GSM1246217", "GSM1246218"], "sample_count": 15, "group_sizes": null, "group_sizes_basis": null, "platform": "570", "taxon": "Homo sapiens", "title": "Expression data of human aortic valve cusps", "resolution_checked_at": "2026-11-01T11:38:18Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:GSE83453", "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=GSE83453", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE83453", "version": null, "note": "The original contributions presented in the study are included in the article/Supplementary Material, further inquiries can be directed to the corresponding author/s.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The original contributions presented in the study are included in the article/Supplementary Material, further inquiries can be directed to the corresponding author/s.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM2203485", "GSM2203486", "GSM2203487", "GSM2203488", "GSM2203489", "GSM2203490", "GSM2203491", "GSM2203492", "GSM2203493", "GSM2203494", "GSM2203495", "GSM2203496", "GSM2203497", "GSM2203498", "GSM2203499", "GSM2203500", "GSM2203501", "GSM2203502", "GSM2203503", "GSM2203504", "GSM2203505", "GSM2203506", "GSM2203507", "GSM2203508", "GSM2203509", "GSM2203510", "GSM2203511"], "sample_count": 27, "group_sizes": null, "group_sizes_basis": null, "platform": "10558", "taxon": "Homo sapiens", "title": "Gene expression profile of calcified bicuspid, tricuspid and normal human aortic valves", "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:34046056:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:10d85eb9a4bd1c2bb20d3097073a8aaf6baaf3df75a6ae6f65bebc286dbc1246", "bytes": 3806, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[11]/table-wrap[1]#T1", "version": null, "note": "The GO functional enrichment analyses of DEGs ranked by count.", "structure": {"pmcid": "PMC8144713", "section_index": 11, "section_title": "GO and KEGG Functional Analysis of DEGs in CAVD", "row_count": 22, "column_count": 4}, "table": {"label": "TABLE 1", "caption": "The GO functional enrichment analyses of DEGs ranked by count.", "rows": [["Term", "Count", "Genes", "P-value"], ["GO-BPs", "", "", ""], ["GO:0006955∼immune response", "23", "ADAMDEC1, CXCL8, GZMA, GPR65, AQP9, C5AR1, PRG4, PPBP, CXCL13, CXCL5, JCHAIN, FCGR3A, FCGR3B, CCL8, IGKC, TRBC1, CTSG, IGLC1, PKHD1L1, CCL19, IL7R, CCL18, and FCGR1B", "1.08E-12"], ["GO:0007165∼signal transduction", "17", "CXCL8, TNFAIP6, C5AR1, TRHDE, RASGRP1, CXCL5, ADRA2A, GREM1, CCL8, PLAU, WIF1, KIT, CLEC5A, NDP, IL7R, CCL18, and S100A9", "0.016322305"], ["GO:0006954∼inflammatory response", "16", "CXCL8, TNFAIP6, C5AR1, LY86, PPBP, CXCL13, CXCL5, CCL8, KIT, SPP1, CHI3L1, CCL19, CCL18, S100A9, SCG2, and S100A8", "2.20E-07"], ["GO:0006508∼proteolysis", "15", "FCN1, CPA3, ADAMDEC1, TPSB2, MMP1, TRHDE, MMP9, MMP12, GZMK, MMP13, RELN, IGKC, PLAU, CTSG, and IGLC1", "3.05E-05"], ["GO:0045087∼innate immune response", "11", "IGHM, C6, FCER1G, IGKC, CLEC5A, LY86, IGLC1, TREM1, S100A9, S100A8, and JCHAIN", "0.001788216"], ["GO:0006915∼apoptotic process", "11", "CD2, SHC4, GREM1, GZMA, GPR65, C5AR1, LY86, GZMB, CHI3L1, S100A9, and S100A8", "0.012113741"], ["GO-CCs", "", "", ""], ["GO:0005886∼plasma membrane", "48", "SHC4, GPM6A, IGHM, GPR65, C5AR1, AQP9, C2ORF88, GPR83, ATP1A2, GPR84, IFI30, TREM1, RASGRP1, CXCL16, FCGR3A, RELN, FCGR3B, IGKC, PRKAR2B, PLAU, LAMP3, TRBC1, CLEC5A, HMOX1, SCN7A, IGLC1, CTSG, FCGR1B, PRIMA1, FCER1G, VCAM1, CD93, ANXA3, LY86, SLC16A10, ADRA2A, VMP1, CD2, VNN2, KIT, GPR160, PCDHB5, PLPP3, IL7R, STEAP1, S100A9, S100A8, and CLEC4G", "8.05E-04"], ["GO:0005576∼extracellular region", "46", "FCN1, ADAMDEC1, TPSB2, CXCL8, COL11A1, TNC, NDNF, CXCL13, IFI30, THBS2, TREM1, PLA2G7, CHRDL1, CXCL5, CXCL16, JCHAIN, APELA, C6, IBSP, IGKC, PLAU, WIF1, SPP1, COL10A1, IGLC1, CTSG, CCL19, PLTP, CPA3, CHST9, MMP1, GZMA, ADIPOQ, PRG4, PPBP, MMP9, MFAP5, CD2, MMP12, GZMK, IGSF10, MMP13, COL6A6, IL7R, S100A9, and S100A8", "1.19E-15"], ["GO:0005615∼extracellular space", "41", "IGHM, CXCL8, TNFAIP6, TNC, CXCL13, CHRDL2, CXCL5, CXCL16, JCHAIN, APELA, RELN, CCL8, IBSP, IGKC, PLAU, SPP1, HMOX1, IGLC1, CTSG, NDP, CCL19, CCL18, PLTP, TIMP4, CTHRC1, CPA3, VCAM1, MYOC, ADIPOQ, LY86, PPBP, MMP9, GREM1, MMP13, KIT, CHI3L1, PKHD1L1, S100A9, SCG2, S100A8, and ANGPTL1", "1.04E-14"], ["GO:0070062∼extracellular exosome", "31", "GPM6A, IGHM, ITLN1, TRHDE, COCH, JCHAIN, FCGR3A, C6, FCGR3B, ALDH2, IGKC, TSPAN8, PRKAR2B, PLAU, SPP1, ACP5, IGLC1, CTSG, VCAM1, MYOC, ANXA3, ADIPOQ, MMP9, KRT18, KRT14, CHI3L1, MNDA, PLPP3, S100A9, S100A8, and ANGPTL1", "0.022687598"], ["GO:0005887∼integral component of plasma membrane", "17", "CD52, FCER1G, SCARA5, GPR65, AQP9, C5AR1, LAPTM5, GPR83, SLC16A10, GPR84, TRHDE, ADRA2A, CD2, TSPAN8, CLEC5A, PLPP3, and STEAP1", "0.059028895"], ["GO:0005578∼proteinaceous extracellular matrix", "14", "MYOC, MMP1, COL11A1, NDNF, MMP9, COCH, MMP12, MMP13, RELN, COL10A1, CHI3L1, COL6A6, TIMP4, and CTHRC1", "9.98E-08"], ["GO-MFs", "", "", ""], ["GO:0004252∼serine-type endopeptidase activity", "13", "FCN1, TPSB2, MMP1, GZMA, GZMB, MMP9, MMP12, GZMK, MMP13, IGKC, PLAU, CTSG, and IGLC1", "3.25E-07"], ["GO:0042803∼protein homodimerization activity", "11", "CD2, BCL2A1, GZMA, ID1, KIT, ADIPOQ, HMOX1, NDP, RASGRP1, ADRA2A, and JCHAIN", "0.038761584"], ["GO:0005509∼calcium ion binding", "10", "MMP12, MMP13, CD93, ANXA3, MMP1, PCDHB5, THBS2, S100A9, RASGRP1, and S100A8", "0.075449087"], ["GO:0008009∼chemokine activity", "8", "CCL8, CXCL8, PPBP, CCL19, CXCL13, CCL18, CXCL5, and CXCL16", "5.78E-08"], ["GO:0003823∼antigen binding", "5", "IGHM, IGKC, IGLC1, IL7R, and JCHAIN", "0.006624345"], ["GO:0004222∼metalloendopeptidase activity", "5", "MMP12, ADAMDEC1, MMP13, MMP1, and MMP9", "0.009131648"]], "row_count": 22, "column_count": 4, "numeric_cells": 70, "header_rows": 1, "locator": "section[11]/table-wrap[1]#T1"}}, {"id": "asset:table:pmid:34046056:2", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:b7c902c1563aca90a8548d1f04b65fee973bfea9f4a1ae035cd11c9d98c917ec", "bytes": 1436, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[11]/table-wrap[2]#T2", "version": null, "note": "The KEGG pathway analysis of DEGs ranked by count.", "structure": {"pmcid": "PMC8144713", "section_index": 11, "section_title": "GO and KEGG Functional Analysis of DEGs in CAVD", "row_count": 13, "column_count": 4}, "table": {"label": "TABLE 2", "caption": "The KEGG pathway analysis of DEGs ranked by count.", "rows": [["Term", "Count", "Genes", "P-value"], ["KEGG_PATHWAY", "", "", ""], ["hsa04062:Chemokine signaling pathway", "9", "SHC4, CCL8, CXCL8, PPBP, CCL19, CXCL13, CCL18, CXCL5, and CXCL16", "2.12E-04"], ["hsa04060:Cytokine-cytokine receptor interaction", "9", "CCL8, CXCL8, PPBP, CCL19, CXCL13, IL7R, CCL18, CXCL5, and CXCL16", "0.001258766"], ["hsa04151:PI3K-Akt signaling pathway", "9", "RELN, IBSP, COL11A1, KIT, SPP1, TNC, COL6A6, THBS2, and IL7R", "0.010615579"], ["hsa04510:Focal adhesion", "8", "SHC4, RELN, IBSP, COL11A1, SPP1, TNC, COL6A6, and THBS2", "0.002157992"], ["hsa04512:ECM-receptor interaction", "7", "RELN, IBSP, COL11A1, SPP1, TNC, COL6A6, and THBS2", "1.09E-04"], ["hsa04974:Protein digestion and absorption", "6", "CPA3, COL11A1, COL10A1, COL6A6, ATP1A2, and SLC16A10", "0.001034968"], ["hsa03320:PPAR signaling pathway", "5", "ACADL, MMP1, ADIPOQ, PLIN1, and PLTP", "0.002827573"], ["hsa04064:NF-kappa B signaling pathway", "5", "VCAM1, CXCL8, BCL2A1, PLAU, and CCL19", "0.007200464"], ["hsa04650:Natural killer cell mediated cytotoxicity", "5", "SHC4, FCGR3A, FCGR3B, FCER1G, and GZMB", "0.022607194"], ["hsa05323:Rheumatoid arthritis", "4", "CXCL8, MMP1, ACP5, and CXCL5", "0.042784539"], ["hsa00380:Tryptophan metabolism", "3", "TDO2, ALDH2, and MAOA", "0.048643268"]], "row_count": 13, "column_count": 4, "numeric_cells": 40, "header_rows": 1, "locator": "section[11]/table-wrap[2]#T2"}}, {"id": "asset:table:pmid:34046056:3", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:595ee946cbcd114053eebca3262837acf5faaf967fedd66a1610628f9183a904", "bytes": 6565, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[12]/table-wrap[1]#T3", "version": null, "note": "Summary of the function of 10 hub genes.", "structure": {"pmcid": "PMC8144713", "section_index": 12, "section_title": "Establishment of PPI Network and Module Analysis", "row_count": 12, "column_count": 3}, "table": {"label": "TABLE 3", "caption": "Summary of the function of 10 hub genes.", "rows": [["Top 10 in network string_interactions.tsv_MCC_top10 ranked by MCC method"], ["Gene symbol", "Full name", "Function"], ["CXCL13", "C-X-C motif chemokine ligand 13", "B lymphocyte chemoattractant, independently cloned and named Angie, is an antimicrobial peptide and CXC chemokine strongly expressed in the follicles of the spleen, lymph nodes, and Peyer’s patches. It preferentially promotes the migration of B lymphocytes (compared to T cells and macrophages), apparently by stimulating calcium influx into, and chemotaxis of, cells expressing Burkitt’s lymphoma receptor 1 (BLR-1). It may therefore function in the homing of B lymphocytes to follicles"], ["CCL19", "C-C motif chemokine ligand 19", "One of several CC cytokine genes clustered on the p-arm of chromosome 9. Cytokines are a family of secreted proteins involved in immunoregulatory and inflammatory processes. The CC cytokines are proteins characterized by two adjacent cysteines. The cytokine encoded by this gene may play a role in normal lymphocyte recirculation and homing. It also plays an important role in trafficking of T cells in thymus, and in T cell and B cell migration to secondary lymphoid organs. It specifically binds to chemokine receptor CCR"], ["CCL8", "C-C motif chemokine ligand 8", "One of several chemokine genes clustered on the q-arm of chromosome 17. Chemokines form a superfamily of secreted proteins involved in immunoregulatory and inflammatory processes. The superfamily is divided into four subfamilies based on the arrangement of N-terminal cysteine residues of the mature peptide. This chemokine is a member of the CC subfamily which is characterized by two adjacent cysteine residues. This cytokine displays chemotactic activity for monocytes, lymphocytes, basophils, and eosinophils"], ["CXCL8", "C-X-C motif chemokine ligand 8", "A member of the CXC chemokine family and is a major mediator of the inflammatory response. The encoded protein is commonly referred to as interleukin-8 (IL-8). IL-8 is secreted by mononuclear macrophages, neutrophils, and eosinophils, T lymphocytes, epithelial cells, and fibroblasts. It functions as a chemotactic factor by guiding the neutrophils to the site of infection. Bacterial and viral products rapidly induce IL-8 expression. IL-8 also participates with other cytokines in the proinflammatory signaling cascade and plays a role in systemic inflammatory response syndrome (SIRS). This gene is believed to play a role in the pathogenesis of the lower respiratory tract infection bronchiolitis, a common respiratory tract disease caused by the respiratory syncytial virus (RSV). The overproduction of this proinflammatory protein is thought to cause the lung inflammation associated with csytic fibrosis. This proinflammatory protein is also suspected of playing a role in coronary artery disease and endothelial dysfunction. This protein is also secreted by tumor cells and promotes tumor migration, invasion, angiogenesis and metastasis."], ["CXCL16", "C-X-C motif chemokine ligand 16", "CXCL16 (C-X-C Motif Chemokine Ligand 16) is a Protein Coding gene. Diseases associated with CXCL16 include Xanthogranulomatous Cholecystitis and Systemic Lupus Erythematosus. Among its related pathways are Signaling by GPCR and PEDF Induced Signaling. Gene Ontology (GO) annotations related to this gene include chemokine activity and low-density lipoprotein particle receptor activity."], ["MMP9", "Matrix metallopeptidase 9", "The matrix metalloproteinase (MMP) family are involved in the breakdown of extracellular matrix in normal physiological processes, such as embryonic development, reproduction, and tissue remodeling, as well as in disease processes, such as arthritis and metastasis. Most MMP’s are secreted as inactive proproteins which are activated when cleaved by extracellular proteinases. The enzyme encoded by this gene degrades type IV and V collagens. Studies in rhesus monkeys suggest that the enzyme is involved in IL-8-induced mobilization of hematopoietic progenitor cells from bone marrow, and murine studies suggest a role in tumor-associated tissue remodeling"], ["CCL18", "C-C motif chemokine ligand 18", "One of several Cys-Cys (CC) cytokine genes clustered on the q arm of chromosome 17. Cytokines are a family of secreted proteins involved in immunoregulatory and inflammatory processes. The CC cytokines are proteins characterized by two adjacent cysteines. The cytokine encoded by this gene displays chemotactic activity for naive T cells, CD4+ and CD8+ T cells and nonactivated lymphocytes, but not for monocytes or granulocytes. This chemokine attracts naive T lymphocytes toward dendritic cells and activated macrophages in lymph nodes. It may play a role in both humoral and cell-mediated immunity responses"], ["CXCL5", "C-X-C motif chemokine ligand 5", "This gene encodes a protein that is a member of the CXC subfamily of chemokines. Chemokines, which recruit and activate leukocytes, are classified by function (inflammatory or homeostatic) or by structure. This protein is proposed to bind the G-protein coupled receptor chemokine (C-X-C motif) receptor 2 to recruit neutrophils, to promote angiogenesis and to remodel connective tissues. This protein is thought to play a role in cancer cell proliferation, migration, and invasion"], ["VCAM1", "Vascular cell adhesion molecule 1", "A member of the Ig superfamily and encodes a cell surface sialoglycoprotein expressed by cytokine-activated endothelium. This type I membrane protein mediates leukocyte-endothelial cell adhesion and signal transduction, and may play a role in the development of artherosclerosis and rheumatoid arthritis. Three alternatively spliced transcripts encoding different isoforms have been described for this gene."], ["PPBP", "Pro-platelet basic protein", "The protein encoded by this gene is a platelet-derived growth factor that belongs to the CXC chemokine family. This growth factor is a potent chemoattractant and activator of neutrophils. It has been shown to stimulate various cellular processes including DNA synthesis, mitosis, glycolysis, intracellular cAMP accumulation, prostaglandin E2 secretion, and synthesis of hyaluronic acid and sulfated glycosaminoglycan. It also stimulates the formation and secretion of plasminogen activator by synovial cells. The protein also is an antimicrobial protein with bactericidal and antifungal activity"]], "row_count": 12, "column_count": 3, "numeric_cells": 22, "header_rows": 2, "locator": "section[12]/table-wrap[1]#T3"}}], "gaps": ["asset:data:geo:GSE12644 not downloaded", "asset:data:geo:GSE12644 licence not read", "asset:data:geo:GSE26953 not downloaded", "asset:data:geo:GSE26953 licence not read", "asset:data:geo:GSE51472 not downloaded", "asset:data:geo:GSE51472 licence not read", "asset:data:geo:GSE83453 not downloaded", "asset:data:geo:GSE83453 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": "reordered", "quote": "“Pearson correlation analysis shows that CCL8, CCL18, CCL19, CXCL16, and VCAM1 are positively correlated with fatty acid synthase (FAS) gene and hydroxymethylglutaryl coenzyme A reductase (HMGCR) gene among the 10 hub genes (Figures 7A,B), yet CXCL13, CXCL5, and CXCL8 have a strong negative correlation with the lecithin cholesterol acyltransferase (CAT) gene (Figure 7C).”"}}, {"id": "method-2", "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": 0.8, "band": "high", "quote": "limma"}}, {"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": "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": "GO Enrichment"}}], "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": ["GSE12644", "GSE51472", "GSE83453", "GSE26953"], "resolved_accessions": ["GSE12644", "GSE51472", "GSE83453", "GSE26953"], "statements": ["The original contributions presented in the study are included in the article/Supplementary Material, further inquiries can be directed to the corresponding author/s."], "basis": "The paper names GSE12644, GSE51472, GSE83453, GSE26953 in Expression Omnibus Gene (GEO) database 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:34046056", "data:geo:GSE12644", "asset:table:pmid:34046056:1", "asset:table:pmid:34046056:2", "asset:table:pmid:34046056:3"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE12644"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-10-31T18:30:31Z", "independence": "single_reader"}, "evidence_check": {"method": "reordered", "availability": "verbatim"}, "calls": 3, "usage": {"prompt_tokens": 27944, "completion_tokens": 2506, "cached_tokens": 776}}, "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:34046056", "type": "paper", "label": "pmid:34046056"}, {"id": "source:pmid:34046056", "type": "manuscript", "label": "PMID 34046056 full text"}, {"id": "data:geo:GSE12644", "type": "dataset", "label": "GEO GSE12644"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:34046056", "type": "paper", "label": "pmid:34046056"}, {"id": "source:pmid:34046056", "type": "manuscript", "label": "PMID 34046056 full text"}, {"id": "data:geo:GSE12644", "type": "dataset", "label": "GEO GSE12644"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-34046056", "type": "extraction", "used": ["source:pmid:34046056"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE12644", "type": "accession_resolution", "used": ["data:geo:GSE12644"], "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:34046056", "parent_hash": "sha256:a9dff4fc3184bd2da900b0da534a53a83c9f107e74baa4f3045f8f4811fa5257", "fork_of": null, "generation": 6}, "gaps": ["asset:data:geo:GSE12644 licence not read", "asset:data:geo:GSE12644 not downloaded", "asset:data:geo:GSE26953 licence not read", "asset:data:geo:GSE26953 not downloaded", "asset:data:geo:GSE51472 licence not read", "asset:data:geo:GSE51472 not downloaded", "asset:data:geo:GSE83453 licence not read", "asset:data:geo:GSE83453 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 correlation analysis shows that CCL8, CCL18, CCL19, CXCL16, and VCAM1 are positively correlated with fatty acid synthase (FAS) gene and hydroxymethylglutaryl coenzyme A reductase (HMGCR) gene among the 10 hub genes (Figures 7A,B), yet CXCL13, CXCL5, and CXCL8 have a strong negative correlation with the lecithin cholesterol acyltransferase (CAT) gene (Figure 7C).”"], "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":"2026-11-04T03:32:58+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}}}