{"data":{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:32696819", "kind": "science-record", "revision": 6, "content_hash": "sha256:56dacbddaee7062d1a150d6aa392b36fbc1555685a3dc0d0e74571b6f620dd66", "created_at": "2026-11-01T15:41:06Z", "updated_at": "2026-11-01T22:01:56Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Identification of potential molecular mechanisms and small molecule drugs in myocardial ischemia/reperfusion injury.", "doi": "10.1590/1414-431x20209717", "pmid": "32696819", "authors": ["Tao Jiang", "Yingcun Liu", "Biao Chen", "Liangyi Si"], "journal": "Brazilian journal of medical and biological research = Revista brasileira de pesquisas medicas e biologica", "year": 2020, "abstract": "Myocardial ischemia/reperfusion (MI/R) injury is a complex phenomenon that causes severe damage to the myocardium. However, the potential molecular mechanisms of MI/R injury have not been fully clarified. We identified potential molecular mechanisms and therapeutic targets in MI/R injury through analysis of Gene Expression Omnibus (GEO) database. Differentially expressed genes (DEGs) were found between MI/R injury and normal samples, and overlapping DEGs were found between GSE61592 and GSE67308. Gene Ontology (GO) and pathway analysis were performed for overlapping DEGs by Database for Annotation, Visualization and Integration Discovery (DAVID). Then, a network of protein-protein interaction (PPI) was constructed through the Search Tool for the Retrieval of Interacting Genes (STRING) database. Potential microRNAs (miRNAs) and therapeutic small molecules were screened out using microRNA.org database and the Comparative Toxicogenomics database (CTD), respectively. Finally, we identified 21 overlapping DEGs related to MI/R injury. These DEGs were significantly enriched in IL-17 signaling pathway, cytosolic DNA-sensing pathway, chemokine signaling, and cytokine-cytokine receptor interaction pathway. According to the degree in the PPI network, CCL2, LCN2, HP, CCL7, HMOX1, CCL4, and S100A8 were found to be hub genes. Furthermore, we identified potential miRNAs (miR-24-3p, miR-26b-5p, miR-2861, miR-217, miR-4251, and miR-124-3p) and therapeutic small molecules like ozone, troglitazone, rosiglitazone, and n-3 polyunsaturated fatty acids for MI/R injury. These results identified hub genes and potential small molecule drugs, which could contribute to the understanding of molecular mechanisms and treatment for MI/R injury.", "claims": [{"id": "claim-method", "statement": "After data preprocessing, the fold change (FC) of gene expression and the false discovery rate (FDR) was calculated between MI/R and normal samples. DEGs were identified with a |log FC| ≥2 and an FDR <0.05.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:32696819", "locator": "sections[4] \"Identification of overlapping DEGs and enrichment analysis\" paragraph 2", "quote": "After data preprocessing, the fold change (FC) of gene expression and the false discovery rate (FDR) was calculated between MI/R and normal samples. DEGs were identified with a |log FC| ≥2 and an FDR <0.05."}], "state": "complete"}, {"id": "claim-data-access", "statement": "The GSE61592 and GSE67308 datasets were downloaded from the GEO database (http://www.ncbi.nlm.nih.gov/geo/). The GSE61592 dataset included three normal heart samples and three MI/R injury samples. The MI/R injury samples of two datasets were obtained from mice subjected to I/R involving left anterior descending coronary artery occlusion followed by reperfusion.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:32696819", "locator": "sections[3] \"Datasets and data preprocessing\" paragraph 2", "quote": "The GSE61592 and GSE67308 datasets were downloaded from the GEO database (http://www.ncbi.nlm.nih.gov/geo/)."}, {"asset": "source:pmid:32696819", "locator": "sections[3] \"Datasets and data preprocessing\" paragraph 2", "quote": "The GSE61592 dataset included three normal heart samples and three MI/R injury samples."}, {"asset": "source:pmid:32696819", "locator": "sections[3] \"Datasets and data preprocessing\" paragraph 2", "quote": "The MI/R injury samples of two datasets were obtained from mice subjected to I/R involving left anterior descending coronary artery occlusion followed by reperfusion."}], "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:32696819"], "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:GSE61592"], "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:GSE61592"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:32696819", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1590/1414-431x20209717", "sha256": "sha256:36f3597d6046b9b62f3f9c489c0af93483fe202910da935e2b613b72d556e8fe", "bytes": 33575, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1590/1414-431x20209717", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC7372942", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE61592", "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=GSE61592", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE61592", "version": null, "note": "The GSE61592 and GSE67308 datasets were downloaded from the GEO database (http://www.ncbi.nlm.nih.gov/geo/). The GSE61592 dataset included three normal heart samples and three MI/R injury samples. The MI/R injury samples of two datasets were obtained from mice subjected to I/R involving left anterior descending coronary artery occlusion followed by reperfusion.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The GSE61592 and GSE67308 datasets were downloaded from the GEO database (http://www.ncbi.nlm.nih.gov/geo/). The GSE61592 dataset included three normal heart samples and three MI/R injury samples. The MI/R injury samples of two datasets were obtained from mice subjected to I/R involving left anterior descending coronary artery occlusion followed by reperfusion.", "access_statement_kind": "repository_route_statement", "sample_accessions": ["GSM1508996", "GSM1508997", "GSM1508998", "GSM1508999", "GSM1509000", "GSM1509001"], "sample_count": 6, "group_sizes": null, "group_sizes_basis": null, "platform": "6887", "taxon": "Mus musculus", "title": "IGF-1 degradation by mast cell chymase promotes delayed cell death in post-ischemic hearts", "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:GSE67308", "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=GSE67308", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE67308", "version": null, "note": "The GSE61592 and GSE67308 datasets were downloaded from the GEO database (http://www.ncbi.nlm.nih.gov/geo/). The GSE61592 dataset included three normal heart samples and three MI/R injury samples. The MI/R injury samples of two datasets were obtained from mice subjected to I/R involving left anterior descending coronary artery occlusion followed by reperfusion.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The GSE61592 and GSE67308 datasets were downloaded from the GEO database (http://www.ncbi.nlm.nih.gov/geo/). The GSE61592 dataset included three normal heart samples and three MI/R injury samples. The MI/R injury samples of two datasets were obtained from mice subjected to I/R involving left anterior descending coronary artery occlusion followed by reperfusion.", "access_statement_kind": "repository_route_statement", "sample_accessions": ["GSM1644168", "GSM1644169", "GSM1644170", "GSM1644171", "GSM1644172", "GSM1644173", "GSM1644174", "GSM1644175", "GSM1644176", "GSM1644177", "GSM1644178", "GSM1644179", "GSM1644180", "GSM1644181", "GSM1644182", "GSM1644183"], "sample_count": 16, "group_sizes": null, "group_sizes_basis": null, "platform": "7202", "taxon": "Mus musculus", "title": "Hif2a-cardiomyocyte deficient mice response to myocardial ischemia and reperfusion", "resolution_checked_at": "2026-11-01T15:39:55Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "asset:table:pmid:32696819:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:7f7f1c0d1d4d14b8c9a40baf02679a8ff43179263117d03b6a2ad26727ce4a9f", "bytes": 552, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[9]/table-wrap[1]#t01", "version": null, "note": "Kyoto Encyclopedia of Genes and Genomes pathway enrichment analysis of overlapping DEGs.", "structure": {"pmcid": "PMC7372942", "section_index": 9, "section_title": "GO functional annotation and pathway enrichment analysis in overlapping DEGs", "row_count": 5, "column_count": 4}, "table": {"label": "Table 1", "caption": "Kyoto Encyclopedia of Genes and Genomes pathway enrichment analysis of overlapping DEGs.", "rows": [["Pathway", "FDR", "Gene count", "Genes"], ["IL-17 signaling pathway", "9.18E-07", "5", "CCL2, CCL7, LCN2, S100A8, S100A9"], ["Chemokine signaling pathway", "0.0112", "3", "CCL2, CCL4, CCL7"], ["Cytokine-cytokine receptor interaction", "0.0184", "3", "CCL2, CCL4, CCL7"], ["Cytosolic DNA-sensing pathway", "0.0184", "2", "CCL4, IL33"]], "row_count": 5, "column_count": 4, "numeric_cells": 11, "header_rows": 1, "locator": "section[9]/table-wrap[1]#t01"}}, {"id": "asset:table:pmid:32696819:2", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:c55de5cc8d92209cb8c655626c4c2e4d2fdfcc5bec2394857705f7d9203583b9", "bytes": 399, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[10]/table-wrap[1]#t02", "version": null, "note": "Protein-protein interaction network degree of identified hub genes.", "structure": {"pmcid": "PMC7372942", "section_index": 10, "section_title": "Construction of PPI network and identification of hub genes", "row_count": 8, "column_count": 3}, "table": {"label": "Table 2", "caption": "Protein-protein interaction network degree of identified hub genes.", "rows": [["Genes", "Degree", "Up/down"], ["CCL2", "7.911", "Up"], ["LCN2", "5.207", "Up"], ["HP", "3.833", "Up"], ["CCL7", "3.611", "Up"], ["HMOX1", "3.419", "Up"], ["CCL4", "3.120", "Up"], ["S100A8", "3.018", "Up"]], "row_count": 8, "column_count": 3, "numeric_cells": 8, "header_rows": 1, "locator": "section[10]/table-wrap[1]#t02"}}, {"id": "asset:table:pmid:32696819:3", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:e55c0030bf68f892e0da38cfc1fcf4605f53791908eb24a1ceebd801be7386c7", "bytes": 581, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[11]/table-wrap[1]#t03", "version": null, "note": "Potential microRNAs of overlapping DEGs.", "structure": {"pmcid": "PMC7372942", "section_index": 11, "section_title": "Potential miRNAs and small molecules associated with MI/R injury", "row_count": 7, "column_count": 4}, "table": {"label": "Table 3", "caption": "Potential microRNAs of overlapping DEGs.", "rows": [["microRNA", "FDR", "Gene count", "Target genes"], ["miR-24-3p", "1.93E-02", "4", "S100A8, CCL2, CCL4, HMOX1"], ["miR-26b-5p", "1.93E-02", "5", "CCL2, CCL7, PLAC8, HMOX1, CH25H"], ["miR-2861", "2.91E-02", "3", "AIF1, ANGPTL4, LCN2"], ["miR-217", "3.60E-02", "4", "CLEC4D, CYP1B1, CCL4, HMOX1"], ["miR-4251", "3.61E-02", "4", "CLEC4D, CCL7, PLAC8, LCN2"], ["miR-124-3p", "3.85E-02", "4", "CYP1B1, CCL2, ANGPTL4, HMOX1"]], "row_count": 7, "column_count": 4, "numeric_cells": 20, "header_rows": 1, "locator": "section[11]/table-wrap[1]#t03"}}, {"id": "asset:table:pmid:32696819:4", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:5a18c8ab4d88cf53939355650afcd553d7cffb8c5109c2f345707a574bc4e3a6", "bytes": 2056, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[11]/table-wrap[2]#t04", "version": null, "note": "Top 20 potential small molecules of the overlapping DEGs.", "structure": {"pmcid": "PMC7372942", "section_index": 11, "section_title": "Potential miRNAs and small molecules associated with MI/R injury", "row_count": 20, "column_count": 4}, "table": {"label": "Table 4", "caption": "Top 20 potential small molecules of the overlapping DEGs.", "rows": [["Molecule in CTD", "FDR", "Gene count", "Target gene"], ["Quartz", "4.99E-10", "7", "S100A9, HP, CCL2, CCL7, HMOX1, LCN2, CH25H"], ["Pregnenolone carbonitrile", "4.99E-10", "13", "CLEC4D, S100A8, AIF1, S100A9, HP, CYP1B1, CCL2, IL33, G0S2, ANGPTL4, HMOX1, LCN2, CH25H"], ["Ozone", "2.40E-09", "12", "S100A8, S100A9, CYP1B1, CCL2, CCL4, IL33, CCL7, G0S2, ANGPTL4, HMOX1, LCN2, CH25H"], ["Muraglitazar", "5.64E-09", "9", "AIF1, CCL2, CCL4, IL33, CCL7, G0S2, ANGPTL4, LCN2, CH25H"], ["Hexachlorobenzene", "2.78E-08", "7", "S100A8, AIF1, S100A9, HP, CYP1B1, HMOX1, LCN2"], ["Dimethylnitrosamine", "4.03E-08", "10", "AIF1, S100A9, HP, CCL2, IL33, CCL7, PLAC8, G0S2, HMOX1, LCN2"], ["Doxorubicin", "5.77E-08", "12", "S100A8, AIF1, S100A9, CYP1B1, CCL2, CCL4, CCL7, PLAC8, G0S2, HMOX1, LCN2, CH25H"], ["Troglitazone", "7.00E-08", "11", "HP, CYP1B1, CCL2, CCL4, IL33, CCL7, G0S2, ANGPTL4, HMOX1, LCN2, CH25H"], ["Naphthalene", "8.36E-08", "8", "S100A8, S100A9, CYP1B1, CCL2, CCL7, ANGPTL4, HMOX1, CH25H"], ["Isoproterenol", "1.26E-07", "10", "CLEC4D, S100A8, AIF1, S100A9, CYP1B1, CCL2, CCL7, HMOX1, LCN2, CH25H"], ["Cobalt", "2.36E-07", "7", "CYP1B1, CCL2, CCL4, CCL7, G0S2, ANGPTL4, HMOX1"], ["Rosiglitazone", "2.92E-07", "11", "AIF1, HP, CYP1B1, CCL2, CCL4, CCL7, G0S2, ANGPTL4, HMOX1, LCN2, CH25H"], ["Tesaglitazar", "3.13E-07", "8", "AIF1, CCL2, CCL4, IL33, G0S2, ANGPTL4, HMOX1, CH25H"], ["1-Naphthylisothiocyanate", "6.76E-07", "9", "S100A8, AIF1, S100A9, CCL2, IL33, PLAC8, G0S2, HMOX1, LCN2"], ["CI 1044", "6.76E-07", "5", "S100A8, S100A9, CYP1B1, HMOX1, LCN2"], ["Trimethyltin", "6.76E-07", "5", "AIF1, CCL2, CCL4, HMOX1, LCN2"], ["Chloroprene", "1.22E-06", "10", "S100A8, AIF1, S100A9, CYP1B1, IL33, PLAC8, G0S2, ANGPTL4, HMOX1, CH25H"], ["Trinitrobenzenesulfonic acid", "1.69E-06", "7", "S100A8, S100A9, CCL2, CCL4, CCL7, HMOX1, LCN2"], ["n-3 Polyunsaturated fatty acids", "2.09E-06", "5", "HP, CYP1B1, CCL2, CCL7, HMOX1"]], "row_count": 20, "column_count": 4, "numeric_cells": 57, "header_rows": 1, "locator": "section[11]/table-wrap[2]#t04"}}], "gaps": ["asset:data:geo:GSE61592 not downloaded", "asset:data:geo:GSE61592 licence not read", "asset:data:geo:GSE67308 not downloaded", "asset:data:geo:GSE67308 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": "protein-protein interaction"}}, {"id": "method-2", "family": null, "specific": null, "label": "Fold-change filtering with false discovery rate (FDR) control", "dsl_operations": [], "missing_operations": [], "expressible": null, "parameters": {}, "data_shapes": [], "evidence": {"score": 1.0, "band": "verbatim", "quote": "After data preprocessing, the fold change (FC) of gene expression and the false discovery rate (FDR) was calculated between MI/R and normal samples. DEGs were identified with a |log FC| ≥2 and an FDR <0.05."}}], "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": ["GSE61592", "GSE67308"], "resolved_accessions": ["GSE61592", "GSE67308"], "statements": ["The GSE61592 and GSE67308 datasets were downloaded from the GEO database (http://www.ncbi.nlm.nih.gov/geo/). The GSE61592 dataset included three normal heart samples and three MI/R injury samples. The MI/R injury samples of two datasets were obtained from mice subjected to I/R involving left anterior descending coronary artery occlusion followed by reperfusion."], "basis": "The paper names GSE61592, GSE67308 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:32696819", "data:geo:GSE61592", "asset:table:pmid:32696819:1", "asset:table:pmid:32696819:2", "asset:table:pmid:32696819:3", "asset:table:pmid:32696819:4"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE61592"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-10-31T18:21:12Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": null}, "calls": 3, "usage": {"prompt_tokens": 27064, "completion_tokens": 1047, "cached_tokens": 8960}}, "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:32696819", "type": "paper", "label": "pmid:32696819"}, {"id": "source:pmid:32696819", "type": "manuscript", "label": "PMID 32696819 full text"}, {"id": "data:geo:GSE61592", "type": "dataset", "label": "GEO GSE61592"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:32696819", "type": "paper", "label": "pmid:32696819"}, {"id": "source:pmid:32696819", "type": "manuscript", "label": "PMID 32696819 full text"}, {"id": "data:geo:GSE61592", "type": "dataset", "label": "GEO GSE61592"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-32696819", "type": "extraction", "used": ["source:pmid:32696819"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE61592", "type": "accession_resolution", "used": ["data:geo:GSE61592"], "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:32696819", "parent_hash": "sha256:33633a2395a6d504d41736c911984ff2c537695df8a3e40f5a53c20d67139acf", "fork_of": null, "generation": 5}, "gaps": ["asset:data:geo:GSE61592 licence not read", "asset:data:geo:GSE61592 not downloaded", "asset:data:geo:GSE67308 licence not read", "asset:data:geo:GSE67308 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": ["protein-protein interaction"], "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":"2026-11-04T02:50:55+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}}}