{"data":{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:33145306", "kind": "science-record", "revision": 6, "content_hash": "sha256:3713bad2dac792de23a5f9a184a05f544b8fbe1de81a1e7ffbef13ce0d2965cf", "created_at": "2026-11-01T15:41:14Z", "updated_at": "2026-11-01T22:02:27Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Investigation of hub genes involved in diabetic nephropathy using biological informatics methods.", "doi": "10.21037/atm-20-5647", "pmid": "33145306", "authors": ["Zhanting Li", "Jianxin Liu", "Weiwei Wang", "Yunchun Zhao", "Dengfeng Yang", "Xiaodong Geng"], "journal": "Annals of translational medicine", "year": 2020, "abstract": "BACKGROUND: The aim of this study was to find genes with significantly aberrant expression in diabetic nephropathy (DN) and determine their underlying mechanisms.\nMETHODS: GSE30528 and GSE1009 were obtained by querying the Gene Expression Omnibus (GEO) database. The difference in target gene expression between normal renal tissues and kidney tissues in patients with DN was screened by using the GEO2R tool. Using the Database for Annotation, Visualization, and Integrated Discovery (DAVID) database, differentially expressed genes (DEGs) were analysed by Gene Ontology (GO) annotation and the Kyoto Encyclopedia of Genes and Genomes (KEGG) pathway enrichment. Then, the protein-protein interactions (PPIs) of DEGs were analyzed by Cytoscape with the Search Tool for the Retrieval of Interacting Genes/Proteins (STRING) database, and the hub genes in this PPI network were recognized by centrality analysis.\nRESULTS: There were 110 genes with significant expression differences between normal and DN tissues. The differences in gene expression involved many functions and expression pathways, such as the formation of the extracellular matrix and the construction of the extracellular domain. The correlation analysis and subgroup analysis of 14 hub genes and the clinical characteristics of DN showed that CTGF, ALB, PDPN, FLT1, IGF1, WT1, GJA1, IGFBP2, FGF9, BMP2, FGF1, BMP7, VEGFA, and TGFBR3 may be involved in the progression of DN.\nCONCLUSIONS: We confirmed the differentially expressed hub genes and other genes which may be the novel biomarker and target candidates in DN.", "claims": [{"id": "claim-method", "statement": "Pearson’s correlation analysis between hub genes, glomerular filtration rate (GFR), and proteinuria in patients with DN was performed using Nephroseq v5 online platform (http://v5.nephroseq.org). Comparisons between two groups were performed using an unpaired Student’s t-test.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:33145306", "locator": "sections[7] \"Statistical analysis\" paragraph 2", "quote": "Pearson’s correlation analysis between hub genes, glomerular filtration rate (GFR), and proteinuria in patients with DN was performed using Nephroseq v5 online platform (http://v5.nephroseq.org). Comparisons between two groups were performed using an unpaired Student’s t-test."}], "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:33145306"], "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:GSE1009"], "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:GSE1009"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:33145306", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.21037/atm-20-5647", "sha256": "sha256:6114168cff361aa04f3b006e03870e7ffaca40ee80f30e879fea267b3d06a9df", "bytes": 29096, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.21037/atm-20-5647", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC7575993", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE1009", "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=GSE1009", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE1009", "version": null, "note": "The GSE30528 microarray data package contained 22 samples of human glomerular tissue. The study samples were taken from healthy human transplant donors, diagnostic renal biopsies, and post-nephrectomy specimens. Further analysis of the specific composition showed that it included 9 DN kidney tissue samples and 13 control group kidney tissue samples.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The GSE30528 microarray data package contained 22 samples of human glomerular tissue. The study samples were taken from healthy human transplant donors, diagnostic renal biopsies, and post-nephrectomy specimens. Further analysis of the specific composition showed that it included 9 DN kidney tissue samples and 13 control group kidney tissue samples.", "access_statement_kind": "repository_route_statement", "sample_accessions": ["GSM15965", "GSM15966", "GSM15967", "GSM15968", "GSM15969", "GSM15970"], "sample_count": 6, "group_sizes": null, "group_sizes_basis": null, "platform": "8300", "taxon": "Homo sapiens", "title": "Diabetic nephropathy", "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:GSE30528", "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=GSE30528", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE30528", "version": null, "note": "The GSE30528 microarray data package contained 22 samples of human glomerular tissue. The study samples were taken from healthy human transplant donors, diagnostic renal biopsies, and post-nephrectomy specimens. Further analysis of the specific composition showed that it included 9 DN kidney tissue samples and 13 control group kidney tissue samples.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The GSE30528 microarray data package contained 22 samples of human glomerular tissue. The study samples were taken from healthy human transplant donors, diagnostic renal biopsies, and post-nephrectomy specimens. Further analysis of the specific composition showed that it included 9 DN kidney tissue samples and 13 control group kidney tissue samples.", "access_statement_kind": "repository_route_statement", "sample_accessions": ["GSM756992", "GSM756993", "GSM756994", "GSM756995", "GSM756996", "GSM756997", "GSM756998", "GSM756999", "GSM757000", "GSM757001", "GSM757002", "GSM757003", "GSM757004", "GSM757005", "GSM757006", "GSM757007", "GSM757008", "GSM757009", "GSM757010", "GSM757011", "GSM757012", "GSM757013"], "sample_count": 22, "group_sizes": null, "group_sizes_basis": null, "platform": "571", "taxon": "Homo sapiens", "title": "Transcriptome Analysis of Human Diabetic Kidney Disease (DKD Glomeruli vs. Control Glomeruli)", "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:33145306:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:a5815c6c163578289e95d0ddf4315d55c208abeb1ba502e01d6b54665722f8c2", "bytes": 1124, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[9]/table-wrap[1]#t1", "version": null, "note": "110 differentially expressed genes (DEGs) were identified from two profile datasets", "structure": {"pmcid": "PMC7575993", "section_index": 9, "section_title": "Identification of DEGs in DN", "row_count": 3, "column_count": 2}, "table": {"label": "Table 1", "caption": "110 differentially expressed genes (DEGs) were identified from two profile datasets", "rows": [["DGEs", "Genes name"], ["Upregulated", "ALOX5, FRY, CCL19, GRIK2, C1orf21, TAC1, CORO1A, IGLC1, THBS2, IL7R, UMOD, TDO2, TRBC1, IGK///IGKC"], ["Downregulated", "PLCE1, MYO1B, IGF1, KLK6, SEPT11, COL4A5, CXADR, GJA1, CDC14A, PALLD, GRK5, GHR, EVI2A, FOXC1, MGAT5, PARVA, CDC42EP3, WT1-AS, FGF1, CHI3L1, CORO2B, NEBL, PLA2R1, COL4A3, NPHS1, WT1, TCF21, TRAM2, KCND3, ST3GAL6, TNNT2, BMP7, DUSP1, KBTBD11, GALC, GPRC5A, CD200, IGFBP2, MEGF9, BMP2, CLIC5, CAND2, HPGD, VEGFA, MME, TYRO3, AIF1SRGAP2C///SRGAP2B///SRGAP2, MIR6872///SEMA3B, CTGF, CMAHP, DPP6, PTGER4, CR1, PDPN, PRKAR2B, FLT1, PTPRD, NFASC, PTGDS, CTNNBIP1, KLK7, USP46, THSD7A, MAGI2, EXPH5, LOC101930416///LOC101929792///LOC100996724///PDE4DIP, FGF9, SPOCK2, PAMR1, DDN, APOD, F2R, HTRA1, CACNB2, NTNG1, PDE4B, CTDSPL, PTPRO, CDKN1C, GAS1, ZNF185, MAP1B, LOX, SULF1, MYL9, TGFBR3, LPL, F5, MCM6, SEMA5A, ALB, F3, ITGB5, DPYSL3, SPOCK1"]], "row_count": 3, "column_count": 2, "numeric_cells": 2, "header_rows": 1, "locator": "section[9]/table-wrap[1]#t1"}}, {"id": "asset:table:pmid:33145306:2", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:394d7b26ffc01e4c914deb11d1d7c8945517fcb13bb6c519890481e9d93a0a65", "bytes": 2672, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[10]/table-wrap[1]#t2", "version": null, "note": "GO enrichment analysis of DEGs in DN", "structure": {"pmcid": "PMC7575993", "section_index": 10, "section_title": "DEG GO analysis in DN", "row_count": 31, "column_count": 4}, "table": {"label": "Table 2", "caption": "GO enrichment analysis of DEGs in DN", "rows": [["Category", "Term", "Count", "P value"], ["GOTERM_BP_DIRECT", "GO:0030154~cell differentiation", "3", "3.88E-02"], ["GOTERM_BP_DIRECT", "GO:0014068~positive regulation of phosphatidylinositol 3-kinase signaling", "3", "3.88E-02"], ["GOTERM_BP_DIRECT", "GO:0006693~prostaglandin metabolic process", "2", "3.42E-02"], ["GOTERM_BP_DIRECT", "GO:0045669~positive regulation of osteoblast differentiation", "3", "3.13E-02"], ["GOTERM_BP_DIRECT", "GO:0016525~negative regulation of angiogenesis", "3", "3.13E-02"], ["GOTERM_BP_DIRECT", "GO:0070374~positive regulation of ERK1 and ERK2 cascade", "4", "2.98E-02"], ["GOTERM_BP_DIRECT", "GO:0000187~activation of MAPK activity", "3", "2.85E-02"], ["GOTERM_BP_DIRECT", "GO:0007217~tachykinin receptor signaling pathway", "2", "2.75E-02"], ["GOTERM_BP_DIRECT", "GO:0060686~negative regulation of prostatic bud formation", "2", "2.75E-02"], ["GOTERM_BP_DIRECT", "GO:0006919~activation of cysteine-type endopeptidase activity involved in apoptotic process", "3", "2.71E-02"], ["GOTERM_BP_DIRECT", "GO:0001525~angiogenesis", "4", "2.52E-02"], ["GOTERM_BP_DIRECT", "GO:0050679~positive regulation of epithelial cell proliferation", "3", "2.44E-02"], ["GOTERM_BP_DIRECT", "GO:0030335~positive regulation of cell migration", "4", "2.25E-02"], ["GOTERM_BP_DIRECT", "GO:0034695~response to prostaglandin E", "2", "2.07E-02"], ["GOTERM_BP_DIRECT", "GO:0008543~fibroblast growth factor receptor signaling pathway", "3", "1.82E-02"], ["GOTERM_BP_DIRECT", "GO:0030324~lung development", "4", "4.44E-03"], ["GOTERM_BP_DIRECT", "GO:0045766~positive regulation of angiogenesis", "5", "1.39E-03"], ["GOTERM_BP_DIRECT", "GO:0032836~glomerular basement membrane development", "3", "9.76E-04"], ["GOTERM_MF_DIRECT", "GO:0004725~protein tyrosine phosphatase activity", "4", "1.07E-02"], ["GOTERM_MF_DIRECT", "GO:0008201~heparin binding", "5", "1.11E-03"], ["GOTERM_CC_DIRECT", "GO:0031965~nuclear membrane", "4", "3.73E-02"], ["GOTERM_CC_DIRECT", "GO:0005587~collagen type IV trimer", "2", "3.08E-02"], ["GOTERM_CC_DIRECT", "GO:0030027~lamellipodium", "4", "2.32E-02"], ["GOTERM_CC_DIRECT", "GO:0014069~postsynaptic density", "3", "2.11E-02"], ["GOTERM_CC_DIRECT", "GO:0005884~actin filament", "3", "1.59E-02"], ["GOTERM_CC_DIRECT", "GO:0005925~focal adhesion", "7", "7.97E-03"], ["GOTERM_CC_DIRECT", "GO:0005578~proteinaceous extracellular matrix", "5", "6.46E-03"], ["GOTERM_CC_DIRECT", "GO:0005576~extracellular region", "8", "5.65E-03"], ["GOTERM_CC_DIRECT", "GO:0070062~extracellular exosome", "28", "4.23E-05"], ["GOTERM_CC_DIRECT", "GO:0005615~extracellular space", "18", "5.89E-07"]], "row_count": 31, "column_count": 4, "numeric_cells": 90, "header_rows": 1, "locator": "section[10]/table-wrap[1]#t2"}}, {"id": "asset:table:pmid:33145306:3", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:80910a53a287be65637a1b30ccd36c94a72fb5e2686856185f2ee515f2871f32", "bytes": 675, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[11]/table-wrap[1]#t3", "version": null, "note": "KEGG pathway enrichment analysis of DEGs in DN", "structure": {"pmcid": "PMC7575993", "section_index": 11, "section_title": "Signalling pathway enrichment analysis", "row_count": 10, "column_count": 3}, "table": {"label": "Table 3", "caption": "KEGG pathway enrichment analysis of DEGs in DN", "rows": [["Term", "Count", "P value"], ["has04810: regulation of actin cytoskeleton", "5", "4.84E-02"], ["has04512: ECM-receptor interaction", "4", "2.13E-02"], ["has05414: dilated cardiomyopathy", "4", "1.66E-02"], ["has05410: HCM", "4", "1.56E-02"], ["has04014: Ras signaling pathway", "6", "1.53E-02"], ["has05200: pathways in cancer", "9", "3.93E-03"], ["has04015: Rap1 signaling pathway", "8", "3.91E-04"], ["has04510: focal adhesion", "9", "6.26E-05"], ["has04151: PI3K-Akt signaling pathway", "12", "1.38E-05"]], "row_count": 10, "column_count": 3, "numeric_cells": 27, "header_rows": 1, "locator": "section[11]/table-wrap[1]#t3"}}, {"id": "asset:table:pmid:33145306:4", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:f41064109983af0cf92172e2d429e5bc702bf53ed43e2614e759e2e58df0c677", "bytes": 789, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[13]/table-wrap[1]#t4", "version": null, "note": "Gene symbol and full name of 14 hub genes in diabetic nephropathy", "structure": {"pmcid": "PMC7575993", "section_index": 13, "section_title": "Association between the hub genes and clinical features of DN", "row_count": 15, "column_count": 2}, "table": {"label": "Table 4", "caption": "Gene symbol and full name of 14 hub genes in diabetic nephropathy", "rows": [["Gene symbol", "Full name"], ["CTGF", "Connective tissue growth factor"], ["ALB", "Albumin"], ["PDPN", "Podoplanin"], ["FLT1", "Fms-related tyrosine kinase 1"], ["IGF1", "Insulin-like growth factor 1"], ["WT1", "Wilms tumor 1"], ["GJA1", "Gap junction protein alpha 1"], ["IGFBP2", "Insulin-like growth factor binding protein 2"], ["FGF9", "Fibroblast growth factor 9"], ["FGF1", "Fibroblast growth factor 1"], ["BMP2", "Bone morphogenetic protein 2"], ["BMP7", "Bone morphogenetic protein 7"], ["VEGFA", "Vascular endothelial growth factor A"], ["TGFBR3", "Transforming growth factor beta receptor 3"]], "row_count": 15, "column_count": 2, "numeric_cells": 10, "header_rows": 1, "locator": "section[13]/table-wrap[1]#t4"}}], "gaps": ["asset:data:geo:GSE1009 not downloaded", "asset:data:geo:GSE1009 licence not read", "asset:data:geo:GSE30528 not downloaded", "asset:data:geo:GSE30528 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": "PPI"}}, {"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": "network_analysis", "specific": "centrality", "label": "Network / pathway analysis", "dsl_operations": ["build_graph", "centrality_scores", "pathway_enrich"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["edge_list"], "evidence": {"score": 0.7, "band": "medium", "quote": "centrality"}}, {"id": "method-4", "family": null, "specific": null, "label": "Pearson’s correlation analysis; unpaired Student’s t-test", "dsl_operations": [], "missing_operations": [], "expressible": null, "parameters": {}, "data_shapes": [], "evidence": {"score": 1.0, "band": "verbatim", "quote": "Pearson’s correlation analysis between hub genes, glomerular filtration rate (GFR), and proteinuria in patients with DN was performed using Nephroseq v5 online platform (http://v5.nephroseq.org). Comparisons between two groups were performed using an unpaired Student’s t-test."}}], "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": ["GSE30528", "GSE1009"], "resolved_accessions": ["GSE30528", "GSE1009"], "statements": ["The GSE30528 microarray data package contained 22 samples of human glomerular tissue. The study samples were taken from healthy human transplant donors, diagnostic renal biopsies, and post-nephrectomy specimens. Further analysis of the specific composition showed that it included 9 DN kidney tissue samples and 13 control group kidney tissue samples."], "basis": "The paper names GSE30528, GSE1009 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:33145306", "data:geo:GSE1009", "asset:table:pmid:33145306:1", "asset:table:pmid:33145306:2", "asset:table:pmid:33145306:3", "asset:table:pmid:33145306:4"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE1009"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-10-31T18:23:51Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": null}, "calls": 3, "usage": {"prompt_tokens": 22733, "completion_tokens": 1506, "cached_tokens": 7680}}, "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:33145306", "type": "paper", "label": "pmid:33145306"}, {"id": "source:pmid:33145306", "type": "manuscript", "label": "PMID 33145306 full text"}, {"id": "data:geo:GSE1009", "type": "dataset", "label": "GEO GSE1009"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:33145306", "type": "paper", "label": "pmid:33145306"}, {"id": "source:pmid:33145306", "type": "manuscript", "label": "PMID 33145306 full text"}, {"id": "data:geo:GSE1009", "type": "dataset", "label": "GEO GSE1009"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-33145306", "type": "extraction", "used": ["source:pmid:33145306"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE1009", "type": "accession_resolution", "used": ["data:geo:GSE1009"], "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:33145306", "parent_hash": "sha256:440e60dd774059d8832b9848023a6c23edf53fe387dc43cecea8c4b01f2dbbc8", "fork_of": null, "generation": 5}, "gaps": ["asset:data:geo:GSE1009 licence not read", "asset:data:geo:GSE1009 not downloaded", "asset:data:geo:GSE30528 licence not read", "asset:data:geo:GSE30528 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": ["PPI"], "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":"2026-11-04T01:20:43+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}}}