{"data":{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:33927789", "kind": "science-record", "revision": 7, "content_hash": "sha256:dbe47be8633f32cf45e347017d13b1e2577cdf1572aa55d684ace43024bfb55e", "created_at": "2026-11-01T15:41:34Z", "updated_at": "2026-11-01T22:03:39Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Transcriptome-Wide Gene Expression in a Murine Model of Ventilator-Induced Lung Injury.", "doi": "10.1155/2021/5535890", "pmid": "33927789", "authors": ["Zhao Li", "Guoshao Zhu", "Chen Zhou", "Hui Wang", "Le Yu", "Yunxin Xu", "Li Xu", "Qingxiu Wang"], "journal": "Disease markers", "year": 2021, "abstract": "BACKGROUND: Mechanical ventilation could lead to ventilator-induced lung injury (VILI), but its underlying pathogenesis remains largely unknown. In this study, we aimed to determine the genes which were highly correlated with VILI as well as their expressions and interactions by analyzing the differentially expressed genes (DEGs) between the VILI samples and controls.\nMETHODS: GSE11434 was downloaded from the gene expression omnibus (GEO) database, and DEGs were identified with GEO2R. Gene Ontology (GO) and Kyoto Encyclopedia of Genes and Genomes (KEGG) pathway enrichment analyses were conducted using DAVID. Next, we used the STRING tool to construct protein-protein interaction (PPI) network of the DEGs. Then, the hub genes and related modules were identified with the Cytoscape plugins: cytoHubba and MCODE. qRT-PCR was further used to validate the results in the GSE11434 dataset. We also applied gene set enrichment analysis (GSEA) to discern the gene sets that had a significant difference between the VILI group and the control. Hub genes were also subjected to analyses by CyTargetLinker and NetworkAnalyst to predict associated miRNAs and transcription factors (TFs). Besides, we used CIBERSORT to detect the contributions of different types of immune cells in lung tissues of mice in the VILI group. By using DrugBank, small molecular compounds that could potentially interact with hub genes were identified.\nRESULTS: A total of 141 DEGs between the VILI group and the control were identified in GSE11434. Then, seven hub genes were identified and were validated by using qRT-PCR. Those seven hub genes were largely enriched in TLR and JAK-STAT signaling pathways. GSEA showed that VILI-associated genes were also enriched in NOD, antigen presentation, and chemokine pathways. We predicted the miRNAs and TFs associated with hub genes and constructed miRNA-TF-gene regulatory network. An analysis with CIBERSORT showed that the proportion of M0 macrophages and activated mast cells was higher in the VILI group than in the control. Small molecules, like nadroparin and siltuximab, could act as potential drugs for VILI.\nCONCLUSION: In sum, a number of hub genes associated with VILI were identified and could provide novel insights into the pathogenesis of VILI and potential targets for its treatment.", "claims": [{"id": "claim-data-access", "statement": "All data generated or analyzed during this study were included in this accepted article.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:33927789", "locator": "sections[25] \"Data Availability\" paragraph 2", "quote": "All data generated or analyzed during this study were included in this accepted article."}], "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:33927789"], "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:GSE11434"], "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:GSE11434"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:33927789", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1155/2021/5535890", "sha256": "sha256:30dc06eb8a0a36a84da610eeb91570b860dcfd4e7520b8628fd95b6c15048d63", "bytes": 39600, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1155/2021/5535890", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC8049808", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE11434", "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=GSE11434", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE11434", "version": null, "note": "All data generated or analyzed during this study were included in this accepted article.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "All data generated or analyzed during this study were included in this accepted article.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM288398", "GSM288399", "GSM288400", "GSM288401", "GSM288402", "GSM288403", "GSM288404", "GSM288405", "GSM288406", "GSM288407"], "sample_count": 10, "group_sizes": null, "group_sizes_basis": null, "platform": "1261", "taxon": "Mus musculus", "title": "Ventilator-induced lung injury in C57BL\\6 mice", "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:33927789:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:3310a13db8555c643242cd3893f8843479cb5e9ac86c71d4b27e2de9172d12b7", "bytes": 1853, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[15]/table-wrap[1]#tab1", "version": null, "note": "GO analysis of the most significant clustering module in PPI networks.", "structure": {"pmcid": "PMC8049808", "section_index": 15, "section_title": "3.2. PPI Network and Module Analysis of DEGs", "row_count": 18, "column_count": 3}, "table": {"label": "Table 1", "caption": "GO analysis of the most significant clustering module in PPI networks.", "rows": [["Category", "Term", "p value"], ["GOTERM_BP_DIRECT", "GO:0006351~transcription, DNA-templated", "1.19E − 04"], ["GOTERM_BP_DIRECT", "GO:0045893~positive regulation of transcription, DNA-templated", "7.52E − 04"], ["GOTERM_BP_DIRECT", "GO:0006357~regulation of transcription from RNA polymerase II promoter", "7.63E − 04"], ["GOTERM_BP_DIRECT", "GO:0006954~inflammatory response", "0.013427"], ["GOTERM_BP_DIRECT", "GO:0043066~negative regulation of apoptotic process", "0.014684"], ["GOTERM_BP_DIRECT", "GO:0035914~skeletal muscle cell differentiation", "0.024883"], ["GOTERM_BP_DIRECT", "GO:0051091~positive regulation of sequence-specific DNA binding transcription factor activity", "0.048278"], ["GOTERM_BP_DIRECT", "GO:0006355~regulation of transcription, DNA-templated", "0.048792"], ["GOTERM_CC_DIRECT", "GO:0005634~nucleus", "3.27E − 06"], ["GOTERM_CC_DIRECT", "GO:0005654~nucleoplasm", "0.039133"], ["GOTERM_MF_DIRECT", "GO:0003700~transcription factor activity, sequence-specific DNA binding", "1.82E − 06"], ["GOTERM_MF_DIRECT", "GO:0003677~DNA binding", "8.51E − 05"], ["GOTERM_MF_DIRECT", "GO:0000978~RNA polymerase II core promoter proximal region sequence-specific DNA binding", "0.001059"], ["GOTERM_MF_DIRECT", "GO:0043565~sequence-specific DNA binding", "0.002782"], ["GOTERM_MF_DIRECT", "GO:0001077~transcriptional activator activity, RNA polymerase II core promoter proximal region sequence-specific binding", "0.009683"], ["GOTERM_MF_DIRECT", "GO:0000982~transcription factor activity, RNA polymerase II core promoter proximal region sequence-specific binding", "0.014036"], ["GOTERM_MF_DIRECT", "GO:0046983~protein dimerization activity", "0.015108"]], "row_count": 18, "column_count": 3, "numeric_cells": 34, "header_rows": 1, "locator": "section[15]/table-wrap[1]#tab1"}}, {"id": "asset:table:pmid:33927789:2", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:507dd28ba9633d156805b58b376539654fc8be6b9e95ba36e7debd6a63fea6c3", "bytes": 1013, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[15]/table-wrap[2]#tab2", "version": null, "note": "KEGG analysis of the most significant clustering module in PPI networks.", "structure": {"pmcid": "PMC8049808", "section_index": 15, "section_title": "3.2. PPI Network and Module Analysis of DEGs", "row_count": 13, "column_count": 3}, "table": {"label": "Table 2", "caption": "KEGG analysis of the most significant clustering module in PPI networks.", "rows": [["Category", "Term", "p value"], ["KEGG_PATHWAY", "ssc04668:TNF signaling pathway", "1.84E − 08"], ["KEGG_PATHWAY", "ssc05166:HTLV-I infection", "2.59E − 06"], ["KEGG_PATHWAY", "ssc05202:transcriptional misregulation in cancer", "1.31E − 04"], ["KEGG_PATHWAY", "ssc05200:pathways in cancer", "4.31E − 04"], ["KEGG_PATHWAY", "ssc04380:osteoclast differentiation", "0.001668"], ["KEGG_PATHWAY", "ssc04630:JAK-STAT signaling pathway", "0.001932"], ["KEGG_PATHWAY", "ssc05161:hepatitis B", "0.0024"], ["KEGG_PATHWAY", "ssc04917:prolactin signaling pathway", "0.006385"], ["KEGG_PATHWAY", "ssc04931:insulin resistance", "0.017635"], ["KEGG_PATHWAY", "ssc05169:Epstein-Barr virus infection", "0.018235"], ["KEGG_PATHWAY", "ssc05152:tuberculosis", "0.040023"], ["KEGG_PATHWAY", "ssc05168:herpes simplex infection", "0.043435"]], "row_count": 13, "column_count": 3, "numeric_cells": 24, "header_rows": 1, "locator": "section[15]/table-wrap[2]#tab2"}}, {"id": "asset:table:pmid:33927789:3", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:8c6660e756e23ce21d8d1bf85a9e153c170d3338c33d1086dd53db62813418ee", "bytes": 1887, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[16]/table-wrap[1]#tab3", "version": null, "note": "GO enrichment analysis of hub genes.", "structure": {"pmcid": "PMC8049808", "section_index": 16, "section_title": "3.3. The Identification and Validation of Hub Genes", "row_count": 20, "column_count": 3}, "table": {"label": "Table 3", "caption": "GO enrichment analysis of hub genes.", "rows": [["Category", "Term", "p value"], ["GOTERM_BP_DIRECT", "GO:0035914~skeletal muscle cell differentiation", "2.15E − 04"], ["GOTERM_BP_DIRECT", "GO:0045944~positive regulation of transcription from RNA polymerase II promoter", "0.002266"], ["GOTERM_BP_DIRECT", "GO:0006351~transcription, DNA-templated", "0.002534"], ["GOTERM_BP_DIRECT", "GO:0070102~interleukin-6-mediated signaling pathway", "0.00354"], ["GOTERM_BP_DIRECT", "GO:0043066~negative regulation of apoptotic process", "0.006244"], ["GOTERM_BP_DIRECT", "GO:0050679~positive regulation of epithelial cell proliferation", "0.018091"], ["GOTERM_BP_DIRECT", "GO:0006355~regulation of transcription, DNA-templated", "0.034263"], ["GOTERM_BP_DIRECT", "GO:0042493~response to drug", "0.034428"], ["GOTERM_BP_DIRECT", "GO:0042593~glucose homeostasis", "0.042752"], ["GOTERM_CC_DIRECT", "GO:0005654~nucleoplasm", "0.016377"], ["GOTERM_CC_DIRECT", "GO:0005634~nucleus", "0.02582"], ["GOTERM_MF_DIRECT", "GO:0005125~cytokine activity", "0.001928"], ["GOTERM_MF_DIRECT", "GO:0001077~transcriptional activator activity, RNA polymerase II core promoter proximal region sequence-specific binding", "0.004063"], ["GOTERM_MF_DIRECT", "GO:0000978~RNA polymerase II core promoter proximal region sequence-specific DNA binding", "0.008486"], ["GOTERM_MF_DIRECT", "GO:0000982~transcription factor activity, RNA polymerase II core promoter proximal region sequence-specific binding", "0.011174"], ["GOTERM_MF_DIRECT", "GO:0046983~protein dimerization activity", "0.017511"], ["GOTERM_MF_DIRECT", "GO:0003700~transcription factor activity, sequence-specific DNA binding", "0.022809"], ["GOTERM_MF_DIRECT", "GO:0008134~transcription factor binding", "0.039418"], ["GOTERM_MF_DIRECT", "GO:0003677~DNA binding", "0.042522"]], "row_count": 20, "column_count": 3, "numeric_cells": 38, "header_rows": 1, "locator": "section[16]/table-wrap[1]#tab3"}}, {"id": "asset:table:pmid:33927789:4", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:b0b8f5c4b486adb54de0683069f1dbffcb7069ff4d02b7855379777abe9fb607", "bytes": 1483, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[16]/table-wrap[2]#tab4", "version": null, "note": "KEGG enrichment analysis of hub genes.", "structure": {"pmcid": "PMC8049808", "section_index": 16, "section_title": "3.3. The Identification and Validation of Hub Genes", "row_count": 21, "column_count": 3}, "table": {"label": "Table 4", "caption": "KEGG enrichment analysis of hub genes.", "rows": [["Category", "Term", "p value"], ["KEGG_PATHWAY", "bta05161:hepatitis B", "4.74E − 06"], ["KEGG_PATHWAY", "bta05166:HTLV-I infection", "4.92E − 05"], ["KEGG_PATHWAY", "bta04620:toll-like receptor signaling pathway", "8.79E − 05"], ["KEGG_PATHWAY", "bta05142:Chagas disease (American trypanosomiasis)", "1.12E − 04"], ["KEGG_PATHWAY", "bta05162:measles", "2.07E − 04"], ["KEGG_PATHWAY", "bta04630:JAK-STAT signaling pathway", "2.59E − 04"], ["KEGG_PATHWAY", "bta05020:prion diseases", "3.61E − 04"], ["KEGG_PATHWAY", "bta05168:herpes simplex infection", "5.10E − 04"], ["KEGG_PATHWAY", "bta04623:cytosolic DNA-sensing pathway", "0.001314"], ["KEGG_PATHWAY", "bta05321:inflammatory bowel disease (IBD)", "0.001727"], ["KEGG_PATHWAY", "bta05133:pertussis", "0.002086"], ["KEGG_PATHWAY", "bta05132:Salmonella infection", "0.002419"], ["KEGG_PATHWAY", "bta05323:rheumatoid arthritis", "0.003158"], ["KEGG_PATHWAY", "bta04668:TNF signaling pathway", "0.004063"], ["KEGG_PATHWAY", "bta05200:pathways in cancer", "0.00434"], ["KEGG_PATHWAY", "bta04380:osteoclast differentiation", "0.006194"], ["KEGG_PATHWAY", "bta05164:influenza A", "0.010163"], ["KEGG_PATHWAY", "bta05152:tuberculosis", "0.011088"], ["KEGG_PATHWAY", "bta04060:cytokine-cytokine receptor interaction", "0.015837"], ["KEGG_PATHWAY", "bta04010:MAPK signaling pathway", "0.021328"]], "row_count": 21, "column_count": 3, "numeric_cells": 40, "header_rows": 1, "locator": "section[16]/table-wrap[2]#tab4"}}, {"id": "asset:table:pmid:33927789:5", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:4076aad1ec5f01d9a501e780a55ecdfa68a61e7be4a485155bd51342083cc152", "bytes": 781, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[20]/table-wrap[1]#tab5", "version": null, "note": "Potential drugs that target hub genes derived from DrugBank.", "structure": {"pmcid": "PMC8049808", "section_index": 20, "section_title": "3.7. Drug Prediction for Hub Genes", "row_count": 8, "column_count": 5}, "table": {"label": "Table 5", "caption": "Potential drugs that target hub genes derived from DrugBank.", "rows": [["Gene", "Drug", "Accession number", "Groups", "Interaction type"], ["FOS", "Nadroparin", "DB08813", "Approved, investigational", "Inhibitor"], ["MYC", "Nadroparin", "DB08813", "Approved, investigational", "Inhibitor"], ["IL-6", "Siltuximab", "DB09036", "Approved, investigational", "Antagonist"], ["IL-6", "Ginseng", "DB01404", "Approved, investigational, nutraceutical", "Antagonist"], ["IL-1B", "Donepezil", "DB00843", "Approved", "Inhibitor"], ["IL-1B", "Minocycline", "DB01017", "Approved, investigational", "Modulator"], ["IL-1B", "Gallium nitrate", "DB05260", "Approved, investigational", "Antagonist"]], "row_count": 8, "column_count": 5, "numeric_cells": 12, "header_rows": 1, "locator": "section[20]/table-wrap[1]#tab5"}}], "gaps": ["asset:data:geo:GSE11434 not downloaded", "asset:data:geo:GSE11434 licence not read"]}, "analysis": {"state": "complete", "methods": [{"id": "method-1", "family": "network_analysis", "specific": "ppi_network", "label": "Network / pathway analysis", "dsl_operations": ["build_graph", "centrality_scores", "pathway_enrich"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["edge_list"], "evidence": {"score": 0.7, "band": "medium", "quote": "protein-protein interaction"}}, {"id": "method-2", "family": "network_analysis", "specific": "pathway_enrichment", "label": "Network / pathway analysis", "dsl_operations": ["pathway_enrich"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["edge_list"], "evidence": {"score": 0.7, "band": "medium", "quote": "pathway enrichment"}}, {"id": "method-3", "family": "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": 0.8, "band": "high", "quote": "centrality"}}], "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": ["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": ["GSE11434"], "resolved_accessions": ["GSE11434"], "statements": ["All data generated or analyzed during this study were included in this accepted article."], "basis": "The paper names GSE11434 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:33927789", "data:geo:GSE11434", "asset:table:pmid:33927789:1", "asset:table:pmid:33927789:2", "asset:table:pmid:33927789:3", "asset:table:pmid:33927789:4", "asset:table:pmid:33927789:5"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE11434"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-10-31T19:32:51Z", "independence": "single_reader"}, "evidence_check": {"method": null, "availability": "verbatim"}, "calls": 3, "usage": {"prompt_tokens": 31715, "completion_tokens": 958, "cached_tokens": 793}}, "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:33927789", "type": "paper", "label": "pmid:33927789"}, {"id": "source:pmid:33927789", "type": "manuscript", "label": "PMID 33927789 full text"}, {"id": "data:geo:GSE11434", "type": "dataset", "label": "GEO GSE11434"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:33927789", "type": "paper", "label": "pmid:33927789"}, {"id": "source:pmid:33927789", "type": "manuscript", "label": "PMID 33927789 full text"}, {"id": "data:geo:GSE11434", "type": "dataset", "label": "GEO GSE11434"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-33927789", "type": "extraction", "used": ["source:pmid:33927789"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE11434", "type": "accession_resolution", "used": ["data:geo:GSE11434"], "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:33927789", "parent_hash": "sha256:c7266d6d7b1433a11bfdc8a958cbc77c5445b01675c72a261cafcc848e6ec00f", "fork_of": null, "generation": 6}, "gaps": ["asset:data:geo:GSE11434 licence not read", "asset:data:geo:GSE11434 not downloaded", "execution.not_run", "review.human_critique", "review.independent_reader", "review.machine_critique"], "assays": [{"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": ["Transcriptome-Wide Gene Expression in a Murine Model of Ventilator-Induced Lung Injury.", "breathed without any mechanical assistance). Mice were abstained from food 4 hours prior to anesthe", "ly. After 4 h of mechanical ventilation, the mice were euthanized, and then, lung tissues were harv", "NA targets. In this study, we downloaded the murine gene datasets and selected miRTarBase, Micro"], "order_basis": "paper_text_order:0", "id": "assay:1"}, {"role": "analysis", "definition_id": "network_analysis", "definition_version": "f2132e96ae6c7a4e", "definition_digest": null, "required_operations": ["build_graph", "centrality_scores", "pathway_enrich"], "support_state": "supported", "source_hashes": {"dsl_catalogue": "f2132e96ae6c7a4e"}, "confidence": 0.7, "evidence": ["protein-protein interaction"], "order_basis": "consumes_earlier_output", "id": "assay:2"}]},"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":"2026-11-04T00:47:23+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}}}