{"data":{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:32594047", "kind": "science-record", "revision": 6, "content_hash": "sha256:7bcd7778b11e12883d51e5b6ead0cf95aa394a1f6eb2e6fb29cd8b2abb46f708", "created_at": "2026-11-01T15:41:04Z", "updated_at": "2026-11-01T21:23:24Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Hub genes and key pathways of traumatic brain injury: bioinformatics analysis and in vivo validation.", "doi": "10.4103/1673-5374.284996", "pmid": "32594047", "authors": ["Yun-Liang Tang", "Long-Jun Fang", "Ling-Yang Zhong", "Jian Jiang", "Xiao-Yang Dong", "Zhen Feng"], "journal": "Neural regeneration research", "year": 2020, "abstract": "The exact mechanisms associated with secondary brain damage following traumatic brain injury (TBI) remain unclear; therefore, identifying the critical molecular mechanisms involved in TBI is essential. The mRNA expression microarray GSE2871 was downloaded from the Gene Expression Omnibus (GEO) repository. GSE2871 comprises a total of 31 cerebral cortex samples, including two post-TBI time points. The microarray features eight control and seven TBI samples, from 4 hours post-TBI, and eight control and eight TBI samples from 24 hours post-TBI. In this bioinformatics-based study, 109 and 66 differentially expressed genes (DEGs) were identified in a Sprague-Dawley (SD) rat TBI model, 4 and 24 hours post-TBI, respectively. Functional enrichment analysis showed that the identified DEGs were significantly enriched in several terms, such as positive regulation of nuclear factor-κB transcription factor activity, mitogen-activated protein kinase signaling pathway, negative regulation of apoptotic process, and tumor necrosis factor signaling pathway. Moreover, the hub genes with high connectivity degrees were primarily related to inflammatory mediators. To validate the top five hub genes, a rat model of TBI was established using the weight-drop method, and real-time quantitative polymerase chain reaction analysis of the cerebral cortex was performed. The results showed that compared with control rats, Tnf-α, c-Myc, Spp1, Cxcl10, Ptprc, Egf, Mmp9, and Lcn2 were upregulated, and Fn1 was downregulated in TBI rats. Among these hub genes, Fn1, c-Myc, and Ptprc may represent novel biomarkers or therapeutic targets for TBI. These identified pathways and key genes may provide insights into the molecular mechanisms of TBI and provide potential treatment targets for patients with TBI. This study was approved by the Experimental Animal Ethics Committee of the First Affiliated Hospital of Nanchang University, China (approval No. 003) in January 2016.", "claims": [{"id": "claim-method", "statement": "We used GEO2R (http://www.ncbi.nlm.nih.gov/geo/geo2r) to identify DEGs between control and TBI cortical samples at both time points.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:32594047", "locator": "sections[5] \"Data processing\" paragraph 2", "quote": "We used GEO2R (http://www.ncbi.nlm.nih.gov/geo/geo2r) to identify DEGs between control and TBI cortical samples at both time points."}], "state": "complete"}, {"id": "claim-data-access", "statement": "Datasets analyzed during the current study are available from the corresponding author on reasonable request.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:32594047", "locator": "sections[18] \"Footnotes\" paragraph 2", "quote": "Datasets analyzed during the current study are available from the corresponding author on reasonable request."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "complete", "objective": null, "steps": [{"id": "read_published_estimate", "order": 1, "name": "Read the published estimate from the source", "kind": "other", "state": "complete", "blocked_on": null, "description": "The claim, method and evidence span published with the source article.", "duration_hours": null, "parameters": {}, "inputs": ["source:pmid:32594047"], "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:GSE2871"], "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:GSE2871"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:32594047", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.4103/1673-5374.284996", "sha256": "sha256:6c52a32aae66466a61db6749a5bbdccc5bb13bb14caa80d0b6b850f836309d05", "bytes": 35216, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.4103/1673-5374.284996", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC7749465", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE2871", "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=GSE2871", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE2871", "version": null, "note": "Datasets analyzed during the current study are available from the corresponding author on reasonable request.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "Datasets analyzed during the current study are available from the corresponding author on reasonable request.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM53252", "GSM53253", "GSM53254", "GSM53255", "GSM53256", "GSM53257", "GSM53258", "GSM53259", "GSM53260", "GSM53261", "GSM53262", "GSM53263", "GSM53264", "GSM53265", "GSM53266", "GSM53267", "GSM53268", "GSM53269", "GSM53270", "GSM53271", "GSM53272", "GSM53273", "GSM53274", "GSM53275", "GSM53276", "GSM53277", "GSM53278", "GSM53279", "GSM53280", "GSM53281", "GSM53282", "GSM53283", "GSM53284", "GSM53285", "GSM53286", "GSM53287", "GSM53288", "GSM53289", "GSM53290", "GSM53291", "GSM53292", "GSM53293", "GSM53294", "GSM53295", "GSM53296", "GSM53297", "GSM53298"], "sample_count": 47, "group_sizes": null, "group_sizes_basis": null, "platform": "85", "taxon": "Rattus norvegicus", "title": "giza-affy-rat-84719", "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:32594047:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:c6c7537f9f6e4fdb368c9a278f68ed19d3eb9e0b6772bbfe5e262e96257b883f", "bytes": 1531, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[9]/table-wrap[1]#T1", "version": null, "note": "Primer sequences for polymerase chain reaction amplification", "structure": {"pmcid": "PMC7749465", "section_index": 9, "section_title": "Real-time quantitative PCR", "row_count": 23, "column_count": 3}, "table": {"label": "Table 1", "caption": "Primer sequences for polymerase chain reaction amplification", "rows": [["Gene", "Sequence", "Product size (bp)"], ["Fn1", "Forward: 5′-TAC ACG GTT TCC CAT TAC GC-3′", "224"], ["", "Reverse: 5′-CCT TTC CAT TCC CGA GAC AT-3′", ""], ["Tnf-α", "Forward: 5′-AGA TGT GGA ACT GGC AGA GG-3′", "178"], ["", "Reverse: 5′-CCC ATT TGG GAA CTT CTC CT-3′", ""], ["c-Myc", "Forward: 5′-GGT CAT CCC CAT CAA GAG-3′", "187"], ["", "Reverse: 5′-GAG GAG AAG GCG CAT TAC AG-3′", ""], ["Spp1", "Forward: 5′-GAG GAG AAG GCG CAT TAC AG-3′", "165"], ["", "Reverse:5′-ATG GCT TTC ATT GGA GTT GC-3′", ""], ["Cxcl10", "Forward: 5′-CAC ACC CTC CTT CTC CCT-3′", "88"], ["", "Reverse: 5′-TGC CAT CTC ACC TGG ACT-3′", ""], ["Ptprc", "Forward: 5′-CGA ACA AAT CCT CAG CCT A-3′", "108"], ["", "Reverse: 5′-CCT CCC CTT TCC ATG TG-3′", ""], ["Egf", "Forward: 5′-ACA GGC TTT GTT CTG CTT CCT-3′", "195"], ["", "Reverse: 5′-GCT GCA TCC ACC ATT ATC GGA G-3′", ""], ["Mmp9", "Forward: 5′-GCC GGG AAC GTA TCT GGA AA-3′", "177"], ["", "Reverse: 5′-GGT TGT GGA AAC TCA CAC GC-3′", ""], ["Nox4", "Forward: 5′-GGG CCT AGG ATT GTG TTT GA-3′", "245"], ["", "Reverse: 5′-CTG AGA AGT TCA GGG CGT TC-3′", ""], ["Lcn2", "Forward: 5′-GGC CTC AAG GAT AAC A-3′", "150"], ["", "Reverse: 5′-GGC AAC AGG AAA GAT GGA-3′", ""], ["GAPDH", "Forward: 5′-CCT TCC GTG TCC CCA CT-3′", "100"], ["", "Reverse: 5′-GCC TGC TTC ACC TTC-3′", ""]], "row_count": 23, "column_count": 3, "numeric_cells": 34, "header_rows": 1, "locator": "section[9]/table-wrap[1]#T1"}}, {"id": "asset:table:pmid:32594047:2", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:c00cedb6ff5c90264ea8b29b9cbd851273a440f2eed63a2cd7b824b821cb20da", "bytes": 3971, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[13]/table-wrap[1]#T2", "version": null, "note": "Functional and pathway enrichment analysis of differentially expressed genes", "structure": {"pmcid": "PMC7749465", "section_index": 13, "section_title": "Functional enrichment analysis of identified DEGs in TBI", "row_count": 43, "column_count": 5}, "table": {"label": "Table 2", "caption": "Functional and pathway enrichment analysis of differentially expressed genes", "rows": [["Category", "Term", "Count", "Gene ratio (%)", "P-value"], ["4 h post-traumatic brain injury", "", "", "", ""], ["GOTERM_BP_DIRECT", "GO:0051092~positive regulation of NF-kappaB transcription factor activity", "8", "0.058642428", "3.89E-06"], ["GOTERM_BP_DIRECT", "GO:0009612~response to mechanical stimulus", "7", "0.051312124", "2.55E-05"], ["GOTERM_BP_DIRECT", "GO:0031663~lipopolysaccharide-mediated signaling pathway", "5", "0.036651517", "2.57E-05"], ["GOTERM_BP_DIRECT", "GO:0032496~response to lipopolysaccharide", "10", "0.073303035", "2.70E-05"], ["GOTERM_BP_DIRECT", "GO:0033280~response to vitamin D", "5", "0.036651517", "2.93E-05"], ["GOTERM_CC_DIRECT", "GO:0005615~extracellular space", "26", "0.19058789", "2.12E-08"], ["GOTERM_CC_DIRECT", "GO:0005576~extracellular region", "16", "0.117284856", "6.43E-06"], ["GOTERM_CC_DIRECT", "GO:0072562~blood microparticle", "7", "0.051312124", "4.31E-05"], ["GOTERM_CC_DIRECT", "GO:0005829~cytosol", "19", "0.139275766", "0.001995362"], ["GOTERM_CC_DIRECT", "GO:0048471~perinuclear region of cytoplasm", "11", "0.080633338", "0.002452866"], ["GOTERM_MF_DIRECT", "GO:0005125~cytokine activity", "9", "0.065972731", "2.93E-06"], ["GOTERM_MF_DIRECT", "GO:0002020~protease binding", "7", "0.051312124", "6.58E-05"], ["GOTERM_MF_DIRECT", "GO:0008201~heparin binding", "7", "0.051312124", "1.77E-04"], ["GOTERM_MF_DIRECT", "GO:0008083~growth factor activity", "6", "0.043981821", "0.00125609"], ["GOTERM_MF_DIRECT", "GO:0044183~protein binding involved in protein folding", "3", "0.02199091", "0.00236215"], ["KEGG_PATHWAY", "rno04010:MAPK signaling pathway", "10", "0.073303035", "2.08E-04"], ["KEGG_PATHWAY", "rno04668:TNF signaling pathway", "7", "0.051312124", "2.39E-04"], ["KEGG_PATHWAY", "rno05323:Rheumatoid arthritis", "6", "0.043981821", "7.82E-04"], ["KEGG_PATHWAY", "rno04623:Cytosolic DNA-sensing pathway", "5", "0.036651517", "0.001061882"], ["KEGG_PATHWAY", "rno04620:Toll-like receptor signaling pathway", "6", "0.043981821", "0.001097316"], ["24 h post-traumatic brain injury", "", "", "", ""], ["GOTERM_BP_DIRECT", "GO:0043066~negative regulation of apoptotic process", "11", "0.152417902", "9.12E-06"], ["GOTERM_BP_DIRECT", "GO:0071222~cellular response to lipopolysaccharide", "7", "0.09699321", "2.23E-05"], ["GOTERM_BP_DIRECT", "GO:0045087~innate immune response", "8", "0.110849383", "2.94E-05"], ["GOTERM_BP_DIRECT", "GO:0030593~neutrophil chemotaxis", "5", "0.069280865", "4.58E-05"], ["GOTERM_BP_DIRECT", "GO:0032496~response to lipopolysaccharide", "8", "0.110849383", "4.60E-05"], ["GOTERM_CC_DIRECT", "GO:0005615~extracellular space", "20", "0.277123459", "1.64E-08"], ["GOTERM_CC_DIRECT", "GO:0070062~extracellular exosome", "22", "0.304835804", "4.77E-05"], ["GOTERM_CC_DIRECT", "GO:0005576~extracellular region", "11", "0.152417902", "8.97E-05"], ["GOTERM_CC_DIRECT", "GO:0048471~perinuclear region of cytoplasm", "9", "0.124705556", "0.001041127"], ["GOTERM_CC_DIRECT", "GO:0005737~cytoplasm", "27", "0.374116669", "0.008608494"], ["GOTERM_MF_DIRECT", "GO:0008083~growth factor activity", "5", "0.069280865", "0.001505624"], ["GOTERM_MF_DIRECT", "GO:0016301~kinase activity", "4", "0.055424692", "0.016521332"], ["GOTERM_MF_DIRECT", "GO:0005125~cytokine activity", "4", "0.055424692", "0.01738503"], ["GOTERM_MF_DIRECT", "GO:0016175~superoxide-generating NADPH oxidase activity", "2", "0.027712346", "0.027536173"], ["GOTERM_MF_DIRECT", "GO:0050786~RAGE receptor binding", "2", "0.027712346", "0.034302944"], ["KEGG_PATHWAY", "rno04668:TNF signaling pathway", "4", "0.055050922", "0.013802516"], ["KEGG_PATHWAY", "rno05168:Herpes simplex infection", "5", "0.068813653", "0.017207178"], ["KEGG_PATHWAY", "rno04010:MAPK signaling pathway", "5", "0.068813653", "0.030289942"], ["KEGG_PATHWAY", "rno04925:Aldosterone synthesis and secretion", "3", "0.041288192", "0.057689656"], ["KEGG_PATHWAY", "rno04612:Antigen processing and presentation", "3", "0.041288192", "0.074243304"]], "row_count": 43, "column_count": 5, "numeric_cells": 162, "header_rows": 1, "locator": "section[13]/table-wrap[1]#T2"}}, {"id": "asset:table:pmid:32594047:3", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:246d3168ccb9fbce8c7b68a7f1d6c35045a591c1f9e9ed48427c85cc100ddd0e", "bytes": 1630, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[14]/table-wrap[1]#T3", "version": null, "note": "Functional and pathway enrichment analysis of hub genes", "structure": {"pmcid": "PMC7749465", "section_index": 14, "section_title": "PPI network construction and hub genes analysis", "row_count": 20, "column_count": 5}, "table": {"label": "Table 3", "caption": "Functional and pathway enrichment analysis of hub genes", "rows": [["Category", "Term", "Count", "Gene ratio (%)", "P-value"], ["4 h post-traumatic brain injury", "", "", "", ""], ["GOTERM_BP_DIRECT", "GO:0033280~response to vitamin D", "5", "25", "3.47E-08"], ["GOTERM_BP_DIRECT", "GO:0071222~cellular response to lipopolysaccharide", "6", "30", "7.70E-07"], ["GOTERM_BP_DIRECT", "GO:0042493~response to drug", "8", "40", "7.94E-07"], ["GOTERM_BP_DIRECT", "GO:0000165~MAPK cascade", "5", "25", "3.20E-06"], ["GOTERM_BP_DIRECT", "GO:0031663~lipopolysaccharide-mediated signaling pathway", "4", "20", "4.76E-06"], ["KEGG_PATHWAY", "rno04668:TNF signaling pathway", "5", "25", "7.66E-05"], ["KEGG_PATHWAY", "rno05146:Amoebiasis", "5", "25", "8.51E-05"], ["KEGG_PATHWAY", "rno04010:MAPK signaling pathway", "6", "30", "1.72E-04"], ["KEGG_PATHWAY", "rno05144:Malaria", "4", "20", "2.64E-04"], ["KEGG_PATHWAY", "rno05164:Influenza A", "5", "25", "4.35E-04"], ["24 h post-traumatic brain injury", "", "", "", ""], ["GOTERM_BP_DIRECT", "GO:0001666~response to hypoxia", "6", "30", "8.13E-06"], ["GOTERM_BP_DIRECT", "GO:0043066~negative regulation of apoptotic process", "7", "35", "1.25E-05"], ["GOTERM_BP_DIRECT", "GO:0042493~response to drug", "7", "35", "1.41E-05"], ["GOTERM_BP_DIRECT", "GO:0030593~neutrophil chemotaxis", "4", "20", "3.20E-05"], ["GOTERM_BP_DIRECT", "GO:0000187~activation of MAPK activity", "4", "20", "7.79E-05"], ["KEGG_PATHWAY", "rno04668:TNF signaling pathway", "3", "15", "0.015978393"], ["KEGG_PATHWAY", "rno04062:Chemokine signaling pathway", "3", "15", "0.039429064"]], "row_count": 20, "column_count": 5, "numeric_cells": 70, "header_rows": 1, "locator": "section[14]/table-wrap[1]#T3"}}], "gaps": ["asset:data:geo:GSE2871 not downloaded", "asset:data:geo:GSE2871 licence not read"]}, "analysis": {"state": "partial", "methods": [{"id": "method-1", "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": 0.8, "band": "high", "quote": "GO enrichment"}}, {"id": "method-2", "family": null, "specific": null, "label": "GEO2R", "dsl_operations": [], "missing_operations": [], "expressible": null, "parameters": {}, "data_shapes": [], "evidence": {"score": 1.0, "band": "verbatim", "quote": "We used GEO2R (http://www.ncbi.nlm.nih.gov/geo/geo2r) to identify DEGs between control and TBI cortical samples at both time points."}}], "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": ["pathway_enrich"], "missing_operations": [], "basis": "The paper names the method it used and the corpus's method extractor maps it onto the DSL catalogue: pathway_enrichment."}, "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": ["GSE2871"], "resolved_accessions": ["GSE2871"], "statements": ["Datasets analyzed during the current study are available from the corresponding author on reasonable request."], "basis": "The paper names GSE2871 in Gene Expression Omnibus (GEO) repository and the accession resolves in the repository. No dataset was downloaded and no licence was read."}}, "can_run": {"dsl_operations": ["pathway_enrich"], "assets": ["source:pmid:32594047", "data:geo:GSE2871", "asset:table:pmid:32594047:1", "asset:table:pmid:32594047:2", "asset:table:pmid:32594047:3"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE2871"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-10-31T18:20:41Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 3, "usage": {"prompt_tokens": 28499, "completion_tokens": 1127, "cached_tokens": 779}}, "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:32594047", "type": "paper", "label": "pmid:32594047"}, {"id": "source:pmid:32594047", "type": "manuscript", "label": "PMID 32594047 full text"}, {"id": "data:geo:GSE2871", "type": "dataset", "label": "GEO GSE2871"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:32594047", "type": "paper", "label": "pmid:32594047"}, {"id": "source:pmid:32594047", "type": "manuscript", "label": "PMID 32594047 full text"}, {"id": "data:geo:GSE2871", "type": "dataset", "label": "GEO GSE2871"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-32594047", "type": "extraction", "used": ["source:pmid:32594047"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE2871", "type": "accession_resolution", "used": ["data:geo:GSE2871"], "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:32594047", "parent_hash": "sha256:04a3c410ea4be404e021837c55251ac41881ccccac5aab1bb855ecbc56b88ca4", "fork_of": null, "generation": 5}, "gaps": ["asset:data:geo:GSE2871 licence not read", "asset:data:geo:GSE2871 not downloaded", "execution.not_run", "method.reader_named_unmapped", "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": ["ic brain injury: bioinformatics analysis and in vivo validation.", "Gs) were identified in a Sprague-Dawley (SD) rat TBI model, 4 and 24 hours post-TBI, respecti", "ators. To validate the top five hub genes, a rat model of TBI was established using the weigh", "he results showed that compared with control rats, Tnf-α, c-Myc, Spp1, Cxcl10, Ptprc, Egf, Mmp"], "order_basis": "paper_text_order:37", "id": "assay:1"}, {"role": "data_generation", "definition_id": "microarray", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.99, "evidence": ["ved in TBI is essential. The mRNA expression microarray GSE2871 was downloaded from the Gene Express", "les, including two post-TBI time points. The microarray features eight control and seven TBI samples"], "order_basis": "paper_text_order:279", "id": "assay:2"}, {"role": "analysis", "definition_id": "network_analysis", "definition_version": "f2132e96ae6c7a4e", "definition_digest": null, "required_operations": ["pathway_enrich"], "support_state": "supported", "source_hashes": {"dsl_catalogue": "f2132e96ae6c7a4e"}, "confidence": 0.8, "evidence": ["GO enrichment"], "order_basis": "consumes_earlier_output", "id": "assay:3"}]},"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":"2026-11-04T01:22:59+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}}}