{"data":{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:41021615", "kind": "science-record", "revision": 4, "content_hash": "sha256:f2fd69aebf317c2c4241a8817c385248e8fafe918c0a3c1c591b76194b065508", "created_at": "2026-11-01T20:31:05Z", "updated_at": "2026-11-01T22:57:13Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Uncovering biomarkers and molecular pathways linking NAFLD and AIS: Insights from bioinformatic analysis and experiment.", "doi": "10.1371/journal.pone.0333719", "pmid": "41021615", "authors": ["Junjie Su", "Fenglei Sun"], "journal": "PloS one", "year": 2025, "abstract": "BACKGROUND: Non-alcoholic fatty liver disease (NAFLD) and acute ischemic stroke (AIS) are both closely related to chronic inflammation and metabolic disorders, but the molecular mechanisms between them are not yet clear. This study aims to explore the common molecular characteristics between NAFLD and AIS using bioinformatics methods.\nMETHODS: We integrated transcriptomic data from GEO (GSE89632 for NAFLD and GSE16561 for AIS) to identify shared molecular signatures. Differentially expressed genes (DEGs) were screened using the limma package, and co-expression modules were identified via WGCNA. Functional enrichment and immune infiltration analyses were conducted using standard bioinformatics tools. Key genes were selected through LASSO and random forest algorithms, and candidate drugs were predicted using the CMap database. Experimental validation included qPCR, immunohistochemistry, and drug intervention in HepG2 and HMC3 cell models, as well as a high-fat diet-induced NAFLD mouse model.\nRESULTS: Through differential expression analysis, 65 common DEGs were identified in both NAFLD and AIS. Functional enrichment analysis showed that these genes mainly involve signal pathways related to immune regulation and inflammatory responses. Immune infiltration analysis showed a significant increase in monocytes, B cells, and plasma cells in NAFLD patients. Ultimately, four potential biomarkers were screened out using LASSO regression and random forest algorithms: CEBPD, SOCS2, THBS1, and IFIT2. Using cMAP, 10 candidate therapeutic drugs, including lamotrigine, were identified. Expression of CEBPD and SOCS2 was consistently upregulated in NAFLD clinical datasets, FFA-treated HepG2 cells, and liver tissues of HFD-induced NAFLD mice, but not in AIS datasets or OGD-treated microglial cells. Furthermore, lamotrigine, cinnarizine, and lenvatinib significantly suppressed FFA-induced CEBPD and SOCS2 expression in HepG2 cells (p < 0.05), supporting their potential regulatory effects.\nCONCLUSIONS: This study identified common DEGs between NAFLD and AIS and experimentally validated CEBPD as a potential marker, revealing possible common molecular mechanisms between the two diseases, providing new directions for future diagnosis and treatment.", "claims": [{"id": "claim-method", "statement": "Using the limma package in RStudio, differential analysis was performed with the lmFit and eBayes functions.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:41021615", "locator": "sections[4] \"2.2 Differential expression gene analysis\" paragraph 2", "quote": "Using the limma package in RStudio, differential analysis was performed with the lmFit and eBayes functions."}], "state": "complete"}, {"id": "claim-data-access", "statement": "All datasets files are available from the GEO (https://www.ncbi.nlm.nih.gov/geo/) database (accession numbers GSE89632, GSE16561,GSE58979,GSE63067,GSE22255).", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:41021615", "locator": "sections[30] \"Data Availability\" paragraph 2", "quote": "All datasets files are available from the GEO (https://www.ncbi.nlm.nih.gov/geo/) database (accession numbers GSE89632, GSE16561,GSE58979,GSE63067,GSE22255)."}], "state": "complete"}, {"id": "claim-target-result", "statement": "The study identified 65 common differentially expressed genes between NAFLD and AIS.", "kind": "qualitative", "target": null, "evidence": [{"asset": "source:pmid:41021615", "locator": "sections[0] \"Abstract\" paragraph 3", "quote": "Through differential expression analysis, 65 common DEGs were identified in both NAFLD and AIS."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "complete", "objective": "The study identified 65 common differentially expressed genes between NAFLD and AIS.", "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:41021615"], "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:GSE115469"], "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:GSE115469"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:41021615", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1371/journal.pone.0333719", "sha256": "sha256:714b245cb1ee1e62227a43ce52d6187c39aeaa4023b55903fcea889fc7298902", "bytes": 49294, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1371/journal.pone.0333719", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC12478928", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE115469", "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=GSE115469", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE115469", "version": null, "note": "All datasets files are available from the GEO (https://www.ncbi.nlm.nih.gov/geo/) database (accession numbers GSE89632, GSE16561,GSE58979,GSE63067,GSE22255).", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "All datasets files are available from the GEO (https://www.ncbi.nlm.nih.gov/geo/) database (accession numbers GSE89632, GSE16561,GSE58979,GSE63067,GSE22255).", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM3178782", "GSM3178783", "GSM3178784", "GSM3178785", "GSM3178786"], "sample_count": 5, "group_sizes": null, "group_sizes_basis": null, "platform": "16791", "taxon": "Homo sapiens", "title": "Dissecting the human liver cellular landscape by single cell RNA-seq reveals novel intrahepatic monocyte/ macrophage populations", "resolution_checked_at": "2026-11-01T20:16:08Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:GSE16561", "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=GSE16561", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE16561", "version": null, "note": "All datasets files are available from the GEO (https://www.ncbi.nlm.nih.gov/geo/) database (accession numbers GSE89632, GSE16561,GSE58979,GSE63067,GSE22255).", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "All datasets files are available from the GEO (https://www.ncbi.nlm.nih.gov/geo/) database (accession numbers GSE89632, GSE16561,GSE58979,GSE63067,GSE22255).", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM416528", "GSM416529", "GSM416530", "GSM416531", "GSM416532", "GSM416533", "GSM416534", "GSM416535", "GSM416536", "GSM416537", "GSM416538", "GSM416539", "GSM416540", "GSM416541", "GSM416542", "GSM416543", "GSM416544", "GSM416545", "GSM416546", "GSM416547", "GSM416548", "GSM416549", "GSM416550", "GSM416551", "GSM416552", "GSM416553", "GSM416554", "GSM416555", "GSM416556", "GSM416557", "GSM416558", "GSM416559", "GSM416560", "GSM416561", "GSM416562", "GSM416563", "GSM416564", "GSM416565", "GSM416566", "GSM416567", "GSM416568", "GSM416569", "GSM416570", "GSM416571", "GSM416572", "GSM416573", "GSM416574", "GSM416575", "GSM416576", "GSM416577", "GSM416578", "GSM416579", "GSM416580", "GSM416581", "GSM416582", "GSM416583", "GSM416584", "GSM416585", "GSM416586", "GSM416587", "GSM416588", "GSM416589", "GSM416590"], "sample_count": 63, "group_sizes": null, "group_sizes_basis": null, "platform": "6883", "taxon": "Homo sapiens", "title": "Gene expression analysis of peripheral whole blood RNA following ischemic stroke", "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:GSE22255", "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=GSE22255", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE22255", "version": null, "note": "All datasets files are available from the GEO (https://www.ncbi.nlm.nih.gov/geo/) database (accession numbers GSE89632, GSE16561,GSE58979,GSE63067,GSE22255).", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "All datasets files are available from the GEO (https://www.ncbi.nlm.nih.gov/geo/) database (accession numbers GSE89632, GSE16561,GSE58979,GSE63067,GSE22255).", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM554014", "GSM554015", "GSM554016", "GSM554017", "GSM554018", "GSM554019", "GSM554020", "GSM554021", "GSM554022", "GSM554023", "GSM554024", "GSM554025", "GSM554026", "GSM554027", "GSM554028", "GSM554029", "GSM554030", "GSM554031", "GSM554032", "GSM554033", "GSM554034", "GSM554035", "GSM554036", "GSM554037", "GSM554038", "GSM554039", "GSM554040", "GSM554041", "GSM554042", "GSM554043", "GSM554044", "GSM554045", "GSM554046", "GSM554047", "GSM554048", "GSM554049", "GSM554050", "GSM554051", "GSM554052", "GSM554053"], "sample_count": 40, "group_sizes": null, "group_sizes_basis": null, "platform": "570", "taxon": "Homo sapiens", "title": "Blood genomic expression profile for ischemic stroke (IS)", "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:GSE58979", "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=GSE58979", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE58979", "version": null, "note": "All datasets files are available from the GEO (https://www.ncbi.nlm.nih.gov/geo/) database (accession numbers GSE89632, GSE16561,GSE58979,GSE63067,GSE22255).", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "All datasets files are available from the GEO (https://www.ncbi.nlm.nih.gov/geo/) database (accession numbers GSE89632, GSE16561,GSE58979,GSE63067,GSE22255).", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM1423267", "GSM1423268", "GSM1423269", "GSM1423270", "GSM1423271", "GSM1423272", "GSM1423273", "GSM1423274", "GSM1423275", "GSM1423276", "GSM1423277", "GSM1423278", "GSM1423279", "GSM1423280", "GSM1423281", "GSM1423282", "GSM1423283", "GSM1423284", "GSM1423285", "GSM1423286", "GSM1423287", "GSM1423288", "GSM1423289", "GSM1423290", "GSM1423291", "GSM1423292", "GSM1423293", "GSM1423294", "GSM1423295", "GSM1423296", "GSM1423297", "GSM1423298", "GSM1423299", "GSM1423300", "GSM1423301", "GSM1423302", "GSM1423303", "GSM1423304", "GSM1423305", "GSM1423306", "GSM1423307", "GSM1423308", "GSM1423309", "GSM1423310", "GSM1423311", "GSM1423312", "GSM1423313", "GSM1423314", "GSM1423315", "GSM1423316", "GSM1423317", "GSM1423318", "GSM1423319"], "sample_count": 53, "group_sizes": null, "group_sizes_basis": null, "platform": "15207", "taxon": "Homo sapiens", "title": "Gene expression in subcutaneous and visceral fat predicts liver histology in morbidly obese patients", "resolution_checked_at": "2026-11-01T15:39:54Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:GSE63067", "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=GSE63067", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE63067", "version": null, "note": "All datasets files are available from the GEO (https://www.ncbi.nlm.nih.gov/geo/) database (accession numbers GSE89632, GSE16561,GSE58979,GSE63067,GSE22255).", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "All datasets files are available from the GEO (https://www.ncbi.nlm.nih.gov/geo/) database (accession numbers GSE89632, GSE16561,GSE58979,GSE63067,GSE22255).", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM1539877", "GSM1539878", "GSM1539879", "GSM1539880", "GSM1539881", "GSM1539882", "GSM1539883", "GSM1539884", "GSM1539885", "GSM1539886", "GSM1539887", "GSM1539888", "GSM1539889", "GSM1539890", "GSM1539891", "GSM1539892", "GSM1539893", "GSM1539894"], "sample_count": 18, "group_sizes": null, "group_sizes_basis": null, "platform": "570", "taxon": "Homo sapiens", "title": "Expression data from human non-alcoholic fatty liver disease stages", "resolution_checked_at": "2026-11-01T15:39:55Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:GSE89632", "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=GSE89632", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE89632", "version": null, "note": "All datasets files are available from the GEO (https://www.ncbi.nlm.nih.gov/geo/) database (accession numbers GSE89632, GSE16561,GSE58979,GSE63067,GSE22255).", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "All datasets files are available from the GEO (https://www.ncbi.nlm.nih.gov/geo/) database (accession numbers GSE89632, GSE16561,GSE58979,GSE63067,GSE22255).", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM2385720", "GSM2385721", "GSM2385722", "GSM2385723", "GSM2385724", "GSM2385725", "GSM2385726", "GSM2385727", "GSM2385728", "GSM2385729", "GSM2385730", "GSM2385731", "GSM2385732", "GSM2385733", "GSM2385734", "GSM2385735", "GSM2385736", "GSM2385737", "GSM2385738", "GSM2385739", "GSM2385740", "GSM2385741", "GSM2385742", "GSM2385743", "GSM2385744", "GSM2385745", "GSM2385746", "GSM2385747", "GSM2385748", "GSM2385749", "GSM2385750", "GSM2385751", "GSM2385752", "GSM2385753", "GSM2385754", "GSM2385755", "GSM2385756", "GSM2385757", "GSM2385758", "GSM2385759", "GSM2385760", "GSM2385761", "GSM2385762", "GSM2385763", "GSM2385764", "GSM2385765", "GSM2385766", "GSM2385767", "GSM2385768", "GSM2385769", "GSM2385770", "GSM2385771", "GSM2385772", "GSM2385773", "GSM2385774", "GSM2385775", "GSM2385776", "GSM2385777", "GSM2385778", "GSM2385779", "GSM2385780", "GSM2385781", "GSM2385782"], "sample_count": 63, "group_sizes": null, "group_sizes_basis": null, "platform": "14951", "taxon": "Homo sapiens", "title": "Genome-wide analysis of hepatic gene expression in patients with non-alcoholic fatty liver disease  and in healthy donors in relation to hepatic fatty acid composition and other nutritional factors", "resolution_checked_at": "2026-11-01T15:39:55Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}], "gaps": ["asset:data:geo:GSE115469 not downloaded", "asset:data:geo:GSE115469 licence not read", "asset:data:geo:GSE16561 not downloaded", "asset:data:geo:GSE16561 licence not read", "asset:data:geo:GSE22255 not downloaded", "asset:data:geo:GSE22255 licence not read", "asset:data:geo:GSE58979 not downloaded", "asset:data:geo:GSE58979 licence not read", "asset:data:geo:GSE63067 not downloaded", "asset:data:geo:GSE63067 licence not read", "asset:data:geo:GSE89632 not downloaded", "asset:data:geo:GSE89632 licence not read"]}, "analysis": {"state": "complete", "methods": [{"id": "method-1", "family": "differential_expression", "specific": "limma_voom", "label": "Differential expression analysis", "dsl_operations": ["normalise_counts", "differential_expression_fit", "fdr_bh"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["count_matrix_with_condition"], "evidence": {"score": 1.0, "band": "verbatim", "quote": "Using the limma package in RStudio, differential analysis was performed with the lmFit and eBayes functions."}}, {"id": "method-2", "family": "machine_learning", "specific": "random_forest", "label": "Machine learning", "dsl_operations": [], "missing_operations": ["machine_learning_random_forest"], "expressible": false, "parameters": {}, "data_shapes": ["labelled_feature_matrix"], "evidence": {"score": 0.7, "band": "medium", "quote": "random forest"}}], "targets": [], "gaps": []}, "capability": {"state": "complete", "requirements": [{"capability_id": "capability:computational_analysis", "label": "Computational analysis platform", "assay_families": ["meta_analysis", "machine_learning", "survival_analysis", "statistical_regression", "pca", "molecular_docking", "network_analysis", "differential_expression", "gwas"], "availability_state": "owned", "tier_unlocked": "R1", "candidate": "Automated Assays Laravel application and simulated adapters"}], "gaps": []}, "readiness": {"state": "complete", "tier": "R1", "blocking_axis": "none", "blocked_on": "nothing:replicable_now", "axes": {"method": {"tier": "R1", "expressible": true, "required_operations": ["normalise_counts", "differential_expression_fit", "fdr_bh"], "missing_operations": [], "basis": "The paper names the method it used and the corpus's method extractor maps it onto the DSL catalogue: limma_voom."}, "capability": {"tier": "R1", "capability_id": "capability:computational_analysis", "availability_state": "owned", "basis": "The computational analysis is owned. The physical bench the paper used is not, so a physical validation cannot be run here."}, "data": {"tier": "R1", "reachable": true, "accessions": ["GSE89632", "GSE16561", "GSE58979", "GSE63067", "GSE22255", "GSE115469"], "resolved_accessions": ["GSE89632", "GSE16561", "GSE58979", "GSE63067", "GSE22255", "GSE115469"], "statements": ["All datasets files are available from the GEO (https://www.ncbi.nlm.nih.gov/geo/) database (accession numbers GSE89632, GSE16561,GSE58979,GSE63067,GSE22255)."], "basis": "The paper names GSE89632, GSE16561, GSE58979, GSE63067, GSE22255, GSE115469 in GEO and the accession resolves in the repository. No dataset was downloaded and no licence was read."}}, "can_run": {"dsl_operations": ["normalise_counts", "differential_expression_fit", "fdr_bh"], "assets": ["source:pmid:41021615", "data:geo:GSE115469"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE115469"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-11-01T20:02:11Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 5, "usage": {"prompt_tokens": 13911, "completion_tokens": 1764, "cached_tokens": 256}}, "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:41021615", "type": "paper", "label": "pmid:41021615"}, {"id": "source:pmid:41021615", "type": "manuscript", "label": "PMID 41021615 full text"}, {"id": "data:geo:GSE115469", "type": "dataset", "label": "GEO GSE115469"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:41021615", "type": "paper", "label": "pmid:41021615"}, {"id": "source:pmid:41021615", "type": "manuscript", "label": "PMID 41021615 full text"}, {"id": "data:geo:GSE115469", "type": "dataset", "label": "GEO GSE115469"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-41021615", "type": "extraction", "used": ["source:pmid:41021615"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE115469", "type": "accession_resolution", "used": ["data:geo:GSE115469"], "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:41021615", "parent_hash": "sha256:a5cf4623bc41095da4ad5def31025e3ed4af07373a11ee33980e28da1349d7b5", "fork_of": null, "generation": 3}, "gaps": ["asset:data:geo:GSE115469 licence not read", "asset:data:geo:GSE115469 not downloaded", "asset:data:geo:GSE16561 licence not read", "asset:data:geo:GSE16561 not downloaded", "asset:data:geo:GSE22255 licence not read", "asset:data:geo:GSE22255 not downloaded", "asset:data:geo:GSE58979 licence not read", "asset:data:geo:GSE58979 not downloaded", "asset:data:geo:GSE63067 licence not read", "asset:data:geo:GSE63067 not downloaded", "asset:data:geo:GSE89632 licence not read", "asset:data:geo:GSE89632 not downloaded", "execution.not_run", "review.human_critique", "review.independent_reader", "review.machine_critique"], "assays": [{"role": "data_generation", "definition_id": "qpcr", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.99, "evidence": ["p database. Experimental validation included qPCR, immunohistochemistry, and drug intervention", "nd IFIT2) across different liver cell types. qPCR Validation and Western blot analysis showed", "del. (D) Drug validation. (E) The results of qPCR. (F,G) Western blot analysis of CEBPD and SO"], "order_basis": "paper_text_order:946", "id": "assay:1"}, {"role": "data_generation", "definition_id": "ihc", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.99, "evidence": ["base. Experimental validation included qPCR, immunohistochemistry, and drug intervention in HepG2 and HMC3 cel", ". (B) OGD-induced HMC3 microglial cells. (C) IHC analysis in NAFLD mouse model. (D) Drug vali", "er confirmed in our NAFLD mouse model, where IHC analysis revealed significantly elevated pro"], "order_basis": "paper_text_order:952", "id": "assay:2"}, {"role": "data_generation", "definition_id": "cell_culture", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.99, "evidence": ["munohistochemistry, and drug intervention in HepG2 and HMC3 cell models, as well as a high-fat", "ated in NAFLD clinical datasets, FFA-treated HepG2 cells, and liver tissues of HFD-induced NAFL", "ed FFA-induced CEBPD and SOCS2 expression in HepG2 cells (p < 0.05), supporting their potential", "lture and drug intervention HepG2 cells were cultured in Dulbecco’s Modified Eagle Medium (DMEM) supp"], "order_basis": "paper_text_order:999", "id": "assay:3"}, {"role": "data_generation", "definition_id": "animal_model", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.99, "evidence": ["ls, as well as a high-fat diet-induced NAFLD mouse model. RESULTS: Through differential expression an", "ls, as well as a high-fat diet-induced NAFLD mouse model. RESULTS: Through differential express", "microglial cells. (C) IHC analysis in NAFLD mouse model. (D) Drug validation. (E) The results of qPC", "findings was further confirmed in our NAFLD mouse model, where IHC analysis revealed significantly e"], "order_basis": "paper_text_order:1068", "id": "assay:4"}, {"role": "data_generation", "definition_id": "western_blot", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.99, "evidence": ["ferent liver cell types. qPCR Validation and Western blot analysis showed that the expression levels o", "g validation. (E) The results of qPCR. (F,G) Western blot analysis of CEBPD and SOCS2 expression in co"], "order_basis": "paper_text_order:6806", "id": "assay:5"}, {"role": "analysis", "definition_id": "differential_expression", "definition_version": "f2132e96ae6c7a4e", "definition_digest": null, "required_operations": ["normalise_counts", "differential_expression_fit", "fdr_bh"], "support_state": "supported", "source_hashes": {"dsl_catalogue": "f2132e96ae6c7a4e"}, "confidence": 1.0, "evidence": ["Using the limma package in RStudio, differential analysis was performed with the lmFit and eBayes functions."], "order_basis": "consumes_earlier_output", "id": "assay:6"}]},"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":"2026-11-04T01:45:49+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}}}