{"data":{"sci_version": "1.0", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:32973752", "kind": "science-record", "revision": 6, "content_hash": "sha256:18ef65f6a4f72fdfa8fd9ec793b34b841bfa7bf45600556aa370de6e6bf9729c", "created_at": "2026-11-01T15:41:11Z", "updated_at": "2026-11-01T21:23:50Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Multiple Processes May Involve in the IgG4-RD Pathogenesis: An Integrative Study via Proteomic and Transcriptomic Analysis.", "doi": "10.3389/fimmu.2020.01795", "pmid": "32973752", "authors": ["Shaozhe Cai", "Yu Chen", "ShengYan Lin", "Cong Ye", "Fang Zheng", "Lingli Dong"], "journal": "Frontiers in immunology", "year": 2020, "abstract": "Immunoglobulin G4-related disease (IgG4-RD) is a newly defined disease entity, while the exact pathogenesis is still not clear. Identifying the characters of IgG4-RD in proteomic and transcriptomic aspects will be critical to investigate the potential pathogenic mechanisms of IgG4-RD. We performed proteomic analysis realized with iTRAQ technique for serum samples from eight treatment-naive IgG4-RD patients and eight healthy volunteers, and tissue samples from two IgG4-RD patients and two non-IgG4-RD patients. Transcriptomic data (GSE40568 and GSE66465) was obtained from the GEO Dataset for validation. The weighted correlation network analysis (WGCNA) was applied to detect the gene modules correlated with IgG4-RD. KEGG pathway analysis was used to investigate pathways enriched in IgG4-RD samples. As a result, a total of 980 differentially expressed proteins (DEPs) in tissue and 94 DEPs in serum were identified between IgG4-RD and control groups. Three hundred fifty-four and two hundred forty-seven genes that most correlated with IgG4-RD were detected by WGCNA analysis in tissue and PBMC, respectively. We also found that DEPs in IgG4-RD samples were enriched in several immune-related activities including bacterial/viral infections and platelet activation as well as some immune related signaling pathways. In conclusion, we identified multiple processes/factors and several signaling pathways that may involve in the IgG4-RD pathogenesis, and found out some potential therapeutic targets for IgG4-RD.", "claims": [{"id": "claim-method", "statement": "Log2 transformed data were used to calculate the difference of proteins between IgG4-RD and HC samples with “t-test” function in R package (version 3.5.1).", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:32973752", "locator": "sections[10] \"Statistical Analysis\" paragraph 2", "quote": "Log2 transformed data were used to calculate the difference of proteins between IgG4-RD and HC samples with “t-test” function in R package (version 3.5.1)."}], "state": "complete"}, {"id": "claim-data-access", "statement": "Data of GSE40568 and GSE66465 can be downloaded from Gene Expression Omnibus Dataset (GEO Dataset: http://www.ncbi.nlm.nih.gov/geo/). The proteomic data is available from the corresponding author on reasonable request.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:32973752", "locator": "sections[20] \"Data Availability Statement\" paragraph 2", "quote": "Data of GSE40568 and GSE66465 can be downloaded from Gene Expression Omnibus Dataset (GEO Dataset: http://www.ncbi.nlm.nih.gov/geo/). The proteomic data is available from the corresponding author on 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:32973752"], "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:GSE40568"], "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:GSE40568"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:32973752", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.3389/fimmu.2020.01795", "sha256": "sha256:85675686643941753b4f439d041e259ecf0200f119b560d470bdc4ce76533fe1", "bytes": 47408, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.3389/fimmu.2020.01795", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC7468437", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE40568", "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=GSE40568", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE40568", "version": null, "note": "Data of GSE40568 and GSE66465 can be downloaded from Gene Expression Omnibus Dataset (GEO Dataset: http://www.ncbi.nlm.nih.gov/geo/). The proteomic data is available from the corresponding author on reasonable request.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "Data of GSE40568 and GSE66465 can be downloaded from Gene Expression Omnibus Dataset (GEO Dataset: http://www.ncbi.nlm.nih.gov/geo/). The proteomic data is available from the corresponding author on reasonable request.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM1389608", "GSM1389609", "GSM1389610", "GSM1389611", "GSM1389612", "GSM1389613", "GSM1389614", "GSM1389615", "GSM1389616", "GSM1389617", "GSM1389618", "GSM1389619", "GSM1389620"], "sample_count": 13, "group_sizes": null, "group_sizes_basis": null, "platform": "570", "taxon": "Homo sapiens", "title": "DNA microarray analysis of labial salivary glands in IgG4-related disease – comparison with Sjögren’s syndrome", "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:GSE66465", "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=GSE66465", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE66465", "version": null, "note": "Data of GSE40568 and GSE66465 can be downloaded from Gene Expression Omnibus Dataset (GEO Dataset: http://www.ncbi.nlm.nih.gov/geo/). The proteomic data is available from the corresponding author on reasonable request.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "Data of GSE40568 and GSE66465 can be downloaded from Gene Expression Omnibus Dataset (GEO Dataset: http://www.ncbi.nlm.nih.gov/geo/). The proteomic data is available from the corresponding author on reasonable request.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM1622973", "GSM1622974", "GSM1622975", "GSM1622976", "GSM1622977", "GSM1622978", "GSM1622979", "GSM1622980"], "sample_count": 8, "group_sizes": null, "group_sizes_basis": null, "platform": "6244", "taxon": "Homo sapiens", "title": "Gene expression patterns in IgG4-RD before and after steroid treatment and healthy control groups", "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:32973752:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:5e1f279220aff54a418c696d42e9a51cf4c7e9348ccedfb7e4f0121bb6202fbf", "bytes": 840, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[4]/table-wrap[1]#T1", "version": null, "note": "Basic clinical information of IgG4-RD patients in this study.", "structure": {"pmcid": "PMC7468437", "section_index": 4, "section_title": "Patients and Treatment", "row_count": 9, "column_count": 4}, "table": {"label": "Table 1", "caption": "Basic clinical information of IgG4-RD patients in this study.", "rows": [["ID", "Age", "Involved organ", "Sample type"], ["1", "40–50", "Retroperitoneum, pancreas, biliary tract, submandibular glands", "Serum, tissue"], ["2", "40–50", "Submandibular glands, retroperitoneum", "Serum"], ["3", "50–60", "Pancreas, biliary tract, submandibular glands, lymph nodes", "Serum"], ["4", "50–60", "Pancreas, biliary tract, submandibular glands", "Serum, tissue"], ["5", "70–80", "Pancreas, submandibular glands, salivary glands, lymph nodes", "Serum"], ["6", "40–50", "Pancreas, biliary tracts, lymph nodes", "Serum"], ["7", "20–30", "Endocranium, lymph nodes", "Serum"], ["8", "50–60", "Submandibular glands, lymph nodes", "Serum"]], "row_count": 9, "column_count": 4, "numeric_cells": 16, "header_rows": 1, "locator": "section[4]/table-wrap[1]#T1"}}, {"id": "asset:table:pmid:32973752:2", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:e774bd535e2829f490f9d68e06a8d9dc31b1b9ea97fecc00d74f0eaf77f0bd55", "bytes": 2118, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[15]/table-wrap[1]#T2", "version": null, "note": "KEGG terms related to infectious process enriched in IgG4-RD tissue proteomic data.", "structure": {"pmcid": "PMC7468437", "section_index": 15, "section_title": "Potential Infection and Infection-Related Responses May Be the Trigger in IgG4-RD", "row_count": 15, "column_count": 4}, "table": {"label": "Table 2", "caption": "KEGG terms related to infectious process enriched in IgG4-RD tissue proteomic data.", "rows": [["Pathway ID", "KEGG term", "Associated proteins", "P-value"], ["KEGG:05143", "African trypanosomiasis", "FAS, GNAQ, IL18, LAMA4, PLCB1, PLCB2, PRKCB, VCAM1", "0.0010"], ["KEGG:05146", "Amoebiasis", "CASP3, GNA11, GNAQ, LAMA4, LAMB3, PLCB1, PLCB2, PRKACB, PRKCB, RAB5C, SERPINB9, TLR2", "0.0159"], ["KEGG:05100", "Bacterial invasion of epithelial cells", "ARPC1B, ARPC2, ARPC3, ARPC5, CDH1, DNM3, ELMO1, ELMO3, RHOG, SEPT1, WAS", "0.0050"], ["KEGG:05142", "Chagas disease American trypanosomiasis", "C1QB, CD3E, CD3G, FAS, GNA11, GNAO1, GNAQ, PLCB1, PLCB2, PPP2CB, PPP2R1B, TLR2", "0.0331"], ["KEGG:05120", "Epithelial cell signaling in Helicobacter pylori infection", "ADAM17, ATP6V0C, ATP6V1G2, CASP3, CSK, F11R, LYN, NOD1, PLCG2, TJP1", "0.0079"], ["KEGG:05170", "Human immunodeficiency virus 1 infection", "AP1G2, AP1S3, APOBEC3C, APOBEC3F, ATM, CASP3, CD3E, CD3G, CD4, CFL1, CFL2, FAS, GNA11, GNAO1, GNAQ, GNG2, GNG7, HLA-E, LIMK1, MAP2K1, PLCG2, PRKCB, RAC2, RPS6KB2, SAMHD1, TLR2, TRADD, TRIM5", "0.0001"], ["KEGG:05134", "Legionellosis", "CASP3, CR1, HSF1, HSPA6, IL18, PYCARD, RAB1A, TLR2", "0.0177"], ["KEGG:05140", "Leishmaniasis", "CR1, CYBB, HLA-DQA2, HLA-DQB1, HLA-DRA, ITGA4, PRKCB, PTPN6, TLR2", "0.0447"], ["KEGG:05144", "Malaria", "CR1, IL18, ITGAL, SDC2, THBS1, TLR2, VCAM1", "0.0282"], ["KEGG:05130", "Pathogenic Escherichia coli infection", "ARPC1B, ARPC2, ARPC3, ARPC5, CDH1, EZR, KRT18, TUBA4A, TUBAL3, TUBB1, TUBB4B, WAS", "0.0001"], ["KEGG:05132", "Salmonella infection", "ARPC1B, ARPC2, ARPC3, ARPC5, IL18, KLC3, KLC4, PFN1, PKN1, PYCARD, RHOG, TJP1, WAS", "0.0020"], ["KEGG:05131", "Shigellosis", "ARPC1B, ARPC2, ARPC3, ARPC5, ELMO1, ELMO3, NOD1, PFN1, RHOG, UBE2D2, WAS", "0.0018"], ["KEGG:05110", "Vibrio cholerae infection", "ATP6V0C, ATP6V1G2, PLCG2, PRKACB, SLC12A2, TJP1, TJP2", "0.0311"], ["KEGG:05416", "Viral myocarditis", "CASP3, CXADR, DAG1, DMD, HLA-DQA2, HLA-DQB1, HLA-DRA, HLA-E, ITGAL, RAC2", "0.0028"]], "row_count": 15, "column_count": 4, "numeric_cells": 39, "header_rows": 1, "locator": "section[15]/table-wrap[1]#T2"}}, {"id": "asset:table:pmid:32973752:3", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:dfe69839ad1ad96d52360e004b08122b09b70cc79fdb783b167d007cf5ddf43d", "bytes": 727, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[15]/table-wrap[2]#T3", "version": null, "note": "KEGG terms related to infectious process enriched in “turquoise” module in IgG4-RD tissue transcriptomic data.", "structure": {"pmcid": "PMC7468437", "section_index": 15, "section_title": "Potential Infection and Infection-Related Responses May Be the Trigger in IgG4-RD", "row_count": 5, "column_count": 4}, "table": {"label": "Table 3", "caption": "KEGG terms related to infectious process enriched in “turquoise” module in IgG4-RD tissue transcriptomic data.", "rows": [["Pathway ID", "KEGG term", "Associated proteins", "P-value"], ["KEGG:05165", "Human papillomavirus infection", "AKT3, COL1A1, COL1A2, COL6A1, COL6A3, EGFR, FN1, FZD7, ITGA9, JAG1, LAMA2, LAMA4, LAMC1, THBS2", "0.0052"], ["KEGG:05100", "Bacterial invasion of epithelial cells", "CAV1, CAV2, FN1, MET, WASF2", "0.0112"], ["KEGG:05146", "Amoebiasis", "COL1A1, COL1A2, COL3A1, FN1, GNAL, LAMA2, LAMA4, LAMC1", "0.0004"], ["KEGG:05144", "Malaria", "CD36, HGF, MET, SDC2, THBS2", "0.0019"]], "row_count": 5, "column_count": 4, "numeric_cells": 9, "header_rows": 1, "locator": "section[15]/table-wrap[2]#T3"}}, {"id": "asset:table:pmid:32973752:4", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:3f95c9ec85e925c50d499e49f162290bf6a610f40bf48feee6ab475179472dcb", "bytes": 2919, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[17]/table-wrap[1]#T4", "version": null, "note": "Signaling pathways and other potential pathogenic processes detected in IgG4-RD tissue transcriptomic data.", "structure": {"pmcid": "PMC7468437", "section_index": 17, "section_title": "Multiple Signaling Pathways May Participate the Pathogenesis of IgG4-RD", "row_count": 18, "column_count": 5}, "table": {"label": "Table 4", "caption": "Signaling pathways and other potential pathogenic processes detected in IgG4-RD tissue transcriptomic data.", "rows": [["Pathway ID", "KEGG term", "Associated proteins/genes", "P-value", "Data origin"], ["KEGG:04350", "TGF-beta signaling pathway", "BMP6, LTBP1, SMAD1, THBS1", "0.0409", "PBMC transcriptomic"], ["KEGG:04217", "Necroptosis", "HIST1H2AB, HIST1H2AE, HIST1H2AH, HIST1H2AI, HIST1H2AJ, HIST1H2AK, HIST1H2AL, HIST1H2AM, TNFAIP3", "0.0009", "PBMC transcriptomic"], ["KEGG:05203", "Viral carcinogenesis", "HIST1H2BB, HIST1H2BC, HIST1H2BG, HIST1H2BH, HIST1H2BI, HIST1H2BJ, HIST1H2BM, HIST1H2BN, HIST1H2BO, HIST1H4D, HIST2H2BE, HIST2H4A", "0.0001", "PBMC transcriptomic"], ["KEGG:05202", "Transcriptional misregulation in cancer", "CD14, HIST1H3A, HIST1H3B, HIST1H3F, HIST1H3H, HIST1H3J, MEIS1, SMAD1", "0.0081", "PBMC transcriptomic"], ["KEGG:04064", "NF-kappa B signaling pathway", "ATM, BTK, LYN, PARP1, PLCG2, PRKCB, TNFRSF11A, TRADD, UBE2I, VCAM1, ZAP70", "0.0471", "Tissue proteomic"], ["KEGG:04015", "Rap1 signaling pathway", "APBB1IP, CDH1, CSF1R, FLT1, FYB1, GNAO1, GNAQ, ITGA2B, ITGAL, MAP2K1, NGFR, PARD3, PDGFA, PDGFC, PDGFRA, PFN1, PLCB1, PLCB2, PRKCB, RAC2, RAP1A, SIPA1, SIPA1L3, THBS1, VASP", "0.0009", "Tissue proteomic"], ["KEGG:04140", "Autophagy", "DAPK1, GABARAPL1, HMGB1, MAP2K1, MTMR14, PIK3R4, PPP2CB, PRKACB, RPS6KB2, RRAGA, RRAGC, STX17, ULK2, WIPI1", "0.0371", "Tissue proteomic"], ["KEGG:04217", "Necroptosis", "CHMP1B, CHMP4C, CYBB, FAS, FTH1, FTL, H2AFX, H2AFY, H2AFY2, HIST2H2AB, HMGB1, PARP1, PYCARD, PYGM, TRADD, TYK2, ZBP1", "0.0289", "Tissue proteomic"], ["KEGG:05219", "Bladder cancer", "CDH1, DAPK1, MAP2K1, RPS6KA5, THBS1, TYMP", "0.0368", "Tissue proteomic"], ["KEGG:04010", "MAPK signaling pathway", "AKT3, EGFR, FGF2, FGF7, HGF, KITLG, MAP3K20, MET, NTRK2, PDGFD, PDGFRA, TGFBR2", "0.0115", "Tissue transcriptomic"], ["KEGG:04015", "Rap1 signaling pathway", "AKT3, DOCK4, EGFR, FGF2, FGF7, HGF, KITLG, MET, PDGFD, PDGFRA, SIPA1L2", "0.0013", "Tissue transcriptomic"], ["KEGG:04151", "PI3K-Akt signaling pathway", "AKT3, COL1A1, COL1A2, COL6A1, COL6A3, EGFR, FGF2, FGF7, FN1, GHR, GNG11, HGF, ITGA9, KITLG, LAMA2, LAMA4, LAMC1, MET, NTRK2, PDGFD, PDGFRA, THBS2", "<0.0001", "Tissue transcriptomic"], ["KEGG:05226", "Gastric cancer", "AKT3, EGFR, FGF2, FGF7, FZD7, HGF, MET, TGFBR2", "0.0059", "Tissue transcriptomic"], ["KEGG:05222", "Small cell lung cancer", "AKT3, FN1, LAMA2, LAMA4, LAMC1", "0.0276", "Tissue transcriptomic"], ["KEGG:05215", "Prostate cancer", "AKT3, EGFR, PDGFD, PDGFRA, PLAT", "0.0323", "Tissue transcriptomic"], ["KEGG:05205", "Proteoglycans in cancer", "AKT3, ANK2, CAV1, CAV2, COL21A1, DCN, EGFR, FGF2, FN1, FZD7, GPC3, HGF, LUM, MET, SDC2, TIMP3", "<0.0001", "Tissue transcriptomic"], ["KEGG:05218", "Melanoma", "AKT3, EGFR, FGF2, FGF7, HGF, MET, PDGFD, PDGFRA", "<0.0001", "Tissue transcriptomic"]], "row_count": 18, "column_count": 5, "numeric_cells": 40, "header_rows": 1, "locator": "section[17]/table-wrap[1]#T4"}}, {"id": "asset:table:pmid:32973752:5", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:9c0111502c82e77597113019c24136cb583ea3c781212d5ab1892190f55ffb04", "bytes": 2467, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[18]/table-wrap[1]#T5", "version": null, "note": "Potential therapeutic targets and targeted drugs for IgG4-RD.", "structure": {"pmcid": "PMC7468437", "section_index": 18, "section_title": "Potential Therapeutic Target Identified by Tissue DEPs Related Biological Processes", "row_count": 20, "column_count": 4}, "table": {"label": "Table 5", "caption": "Potential therapeutic targets and targeted drugs for IgG4-RD.", "rows": [["Gene symbol", "Name", "Drugs (target type)", "Disease application"], ["Targets identified from KEGG terms"], ["RAC1", "Ras-related C3 botulinum toxin substrate 1", "EHT-1864 (Literature-reported target)", "Alzheimer disease"], ["ITGB1", "Integrin beta-1", "131I-radretumab (Clinical trial target)", "Non-small-cell lung cancer; Macular degeneration"], ["", "", "ATN-161(Clinical trial Target) *Target: Integrin alpha-5/beta-1", "Non-small-cell lung cancer; Renal cell carcinoma"], ["MAPK1", "Extracellular signal-regulated kinase 2", "CI-1040 (Clinical trial target)", "Artery stenosis; Pancreatic cancer"], ["MAPK3", "Extracellular signal-regulated kinase 1", "BVD-523 (Clinical trial Target)", "Solid tumor/cancer; Artery stenosis"], ["PRKCB", "Protein kinase C beta", "Enzastaurin (Clinical trial target)", "Diffuse large B-cell lymphoma; Lymphoma"], ["PRKCA", "Protein kinase C alpha", "Sodium phenylbutyrate (Successful target)", "Spinal muscular atrophy; Renal transplantation;"], ["PIK3CA", "Phosphatidylinositol 3-kinase catalytic subunit alpha", "BAY 80-6946 (Successful target)", "Follicular lymphoma; Non-hodgkin lymphoma"], ["PIK3CB", "Phosphatidylinositol 3-kinase catalytic subunit beta", "Buparlisib (Clinical trial target)", "Breast cancer; Pain"], ["PIK3CD", "Phosphatidylinositol 3-kinase catalytic subunit delta", "Idelalisib (Successful target)", "Follicular lymphoma; Small lymphocytic lymphoma"], ["PRKCG", "Protein kinase C gamma", "Midostaurin (Successful target)", "Acute myeloid leukemia; Systemic mastocytosis"], ["SRC", "Proto-oncogene tyrosine-protein kinase Src", "Herbimycin A (Successful target)", "Breast cancer; Ischemia"], ["Targets identified from GO Biological process terms"], ["NCK1", "NCK adaptor protein", "AX-024 (Clinical trial target)", "Multiple sclerosis"], ["PRKCD", "Protein kinase C delta", "KAI-9803 (Clinical trial target)", "Acute myocardial infarction; Human immunodeficiency virus infection"], ["PTPRC", "Receptor-type tyrosine-protein phosphatase C", "Iomab-B (Clinical trial target)", "Bone marrow transplantation; Acute myeloid leukemia"], ["RAC1", "Ras-related C3 botulinum toxin substrate 1", "EHT-1864(Literature-reported target)", "Alzheimer disease"], ["ABL1", "Tyrosine-protein kinase ABL1", "Adenosine triphosphate (Successful target)", "Breast cancer; Ischemia"]], "row_count": 20, "column_count": 4, "numeric_cells": 17, "header_rows": 1, "locator": "section[18]/table-wrap[1]#T5"}}], "gaps": ["asset:data:geo:GSE40568 not downloaded", "asset:data:geo:GSE40568 licence not read", "asset:data:geo:GSE66465 not downloaded", "asset:data:geo:GSE66465 licence not read"]}, "analysis": {"state": "partial", "methods": [{"id": "method-1", "family": null, "specific": null, "label": "t-test", "dsl_operations": [], "missing_operations": [], "expressible": null, "parameters": {}, "data_shapes": [], "evidence": {"score": 1.0, "band": "verbatim", "quote": "Log2 transformed data were used to calculate the difference of proteins between IgG4-RD and HC samples with “t-test” function in R package (version 3.5.1)."}}], "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": "blocked", "tier": "R4", "blocking_axis": "method", "blocked_on": "method:not_determinable", "axes": {"method": {"tier": "R4", "expressible": false, "required_operations": [], "missing_operations": [], "basis": "The reader quoted the method the paper names (t-test), but the corpus's method extractor could not map it onto a DSL operation, so the method is published but not expressible."}, "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": ["GSE40568", "GSE66465"], "resolved_accessions": ["GSE40568", "GSE66465"], "statements": ["Data of GSE40568 and GSE66465 can be downloaded from Gene Expression Omnibus Dataset (GEO Dataset: http://www.ncbi.nlm.nih.gov/geo/). The proteomic data is available from the corresponding author on reasonable request."], "basis": "The paper names GSE40568, GSE66465 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": [], "assets": ["source:pmid:32973752", "data:geo:GSE40568", "asset:table:pmid:32973752:1", "asset:table:pmid:32973752:2", "asset:table:pmid:32973752:3", "asset:table:pmid:32973752:4", "asset:table:pmid:32973752:5"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE40568"]}, "gaps": ["method:not_determinable"]}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-10-31T18:22:42Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 3, "usage": {"prompt_tokens": 38401, "completion_tokens": 1429, "cached_tokens": 784}}, "human_critique": null, "stages": [{"id": "extraction", "state": "complete", "reader": "MiniMax-M3.1-Flash", "provider": "minimax"}], "gaps": ["review.independent_reader", "review.machine_critique", "review.human_critique"]}, "execution": {"state": "absent", "status": "not_run", "mode": null, "runs": [], "gaps": ["execution.not_run"]}, "provenance": {"entities": [{"id": "pmid:32973752", "type": "paper", "label": "pmid:32973752"}, {"id": "source:pmid:32973752", "type": "manuscript", "label": "PMID 32973752 full text"}, {"id": "data:geo:GSE40568", "type": "dataset", "label": "GEO GSE40568"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:32973752", "type": "paper", "label": "pmid:32973752"}, {"id": "source:pmid:32973752", "type": "manuscript", "label": "PMID 32973752 full text"}, {"id": "data:geo:GSE40568", "type": "dataset", "label": "GEO GSE40568"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-32973752", "type": "extraction", "used": ["source:pmid:32973752"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE40568", "type": "accession_resolution", "used": ["data:geo:GSE40568"], "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:32973752", "parent_hash": "sha256:81692e779cc4537e1ba7188b9a8429a7f74c1df9b59f7aff64d5d0a4b2b50a06", "fork_of": null, "generation": 5}, "gaps": ["asset:data:geo:GSE40568 licence not read", "asset:data:geo:GSE40568 not downloaded", "asset:data:geo:GSE66465 licence not read", "asset:data:geo:GSE66465 not downloaded", "execution.not_run", "method.reader_named_unmapped", "review.human_critique", "review.independent_reader", "review.machine_critique"]},"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":"2026-11-04T02:12:08+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}}}