{"data":{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:31788082", "kind": "science-record", "revision": 5, "content_hash": "sha256:347845451f1a23ea461c6ed19cac34a0772e7d754ebd4a6057e53c8e9a30a7df", "created_at": "2026-11-01T15:40:52Z", "updated_at": "2026-11-01T22:01:03Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Identification of biomarkers and construction of a microRNA-mRNA regulatory network for ependymoma using integrated bioinformatics analysis.", "doi": "10.3892/ol.2019.10941", "pmid": "31788082", "authors": ["Biao Yang", "Jun-Xi Dai", "Yuan-Bo Pan", "Yan-Bin Ma", "Sheng-Hua Chu"], "journal": "Oncology letters", "year": 2019, "abstract": "Ependymomas (EPNs) are one of the most common types of malignant neuroepithelial tumors. In an effort to identify potential biomarkers involved in the pathogenesis of EPN, the mRNA expression profiles of the GSE25604, GSE50161, GSE66354, GSE74195 and GSE86574 datasets, in addition to the microRNA (miRNA/miR) expression profiles of GSE42657 were downloaded from the Gene Expression Omnibus (GEO) database. Differentially expressed genes (DEGs) and differentially expressed miRNAs (DEMs) between EPN and normal brain tissue samples were identified using the Limma package in R and GEO2R, respectively. Functional and pathway enrichment analyses were conducted using the Database for Annotation, Visualization and Integrated Discovery. A protein-protein interaction network was constructed using the Search Tool for Retrieval of Interacting Genes database, which was visualized using Cytoscape. The targeted genes of DEMs were predicted using miRWalk2.0 and a miRNA-mRNA regulatory network was constructed. Following analysis, a total of 948 DEGs and 129 DEMs were identified. Functional enrichment analysis revealed that 609 upregulated DEGs were significantly enriched in 'PI3K-Akt signaling pathway', while 339 downregulated DEGs were primarily involved in 'cell junction' and 'retrograde endocannabinoid signaling'. In addition, 6 hub genes [cyclin dependent kinase 1, CD44 molecule (Indian blood group) (CD44), proliferating cell nuclear antigen (PCNA), MYC, synaptotagmin 1 (SYT1) and kinesin family member 4A] and 6 crucial miRNAs [homo sapiens (hsa)-miR-34a-5p, hsa-miR-449a, hsa-miR-106a-5p, hsa-miR-124-3p, hsa-miR-128-3p and hsa-miR-330-3p] were identified as biomarkers and potential therapeutic targets for EPN. Furthermore, a microRNA-mRNA regulatory network was constructed to highlight the interactions between DEMs and their target DEGs; this included the hsa-miR-449a-SYT1, hsa-miR-34a-5p-SYT1, hsa-miR-330-3p-CD44 and hsa-miR-124-3p-PCNA pairs, whose expression levels were confirmed using reverse transcription-quantitative polymerase chain reaction. In conclusion, the present study may provide important data for the investigation of the molecular mechanisms of EPN pathogenesis.", "claims": [{"id": "claim-method", "statement": "The statistical significance between EPN and normal brain tissues was determined using an independent sample t-test.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:31788082", "locator": "sections[12] \"Statistical analysis\" paragraph 2", "quote": "The statistical significance between EPN and normal brain tissues was determined using an independent sample t-test."}], "state": "complete"}, {"id": "claim-data-access", "statement": "The datasets generated and/or analyzed during the current study are available the GEO database repository (http://www.ncbi.nlm.nih.gov/geo/).", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:31788082", "locator": "sections[26] \"Availability of data and materials\" paragraph 2", "quote": "The datasets generated and/or analyzed during the current study are available the GEO database repository (http://www.ncbi.nlm.nih.gov/geo/)."}], "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:31788082"], "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:GSE25604"], "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:GSE25604"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:31788082", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.3892/ol.2019.10941", "sha256": "sha256:ab4e1cc728fa3e8957519bc13067a6fccf7c7e4dfbedf83b62dde2805379e381", "bytes": 41340, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.3892/ol.2019.10941", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC6865127", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE25604", "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=GSE25604", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE25604", "version": null, "note": "The datasets generated and/or analyzed during the current study are available the GEO database repository (http://www.ncbi.nlm.nih.gov/geo/).", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The datasets generated and/or analyzed during the current study are available the GEO database repository (http://www.ncbi.nlm.nih.gov/geo/).", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM629283", "GSM629284", "GSM629285", "GSM629286", "GSM629287", "GSM629288", "GSM629289", "GSM629290", "GSM629291", "GSM629292", "GSM629293", "GSM629294", "GSM629295", "GSM629296", "GSM629297", "GSM629298", "GSM629299", "GSM629300", "GSM629301", "GSM629302", "GSM629303", "GSM629304"], "sample_count": 22, "group_sizes": null, "group_sizes_basis": null, "platform": "571", "taxon": "Homo sapiens", "title": "Gene expression of LMPC cells of infratentorial ependymomas when compared to LMPC ependymal cells", "resolution_checked_at": "2026-11-01T15:39:54Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:GSE42657", "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=GSE42657", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE42657", "version": null, "note": "The datasets generated and/or analyzed during the current study are available the GEO database repository (http://www.ncbi.nlm.nih.gov/geo/).", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The datasets generated and/or analyzed during the current study are available the GEO database repository (http://www.ncbi.nlm.nih.gov/geo/).", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM1047468", "GSM1047469", "GSM1047470", "GSM1047471", "GSM1047472", "GSM1047473", "GSM1047474", "GSM1047475", "GSM1047476", "GSM1047477", "GSM1047478", "GSM1047479", "GSM1047480", "GSM1047481", "GSM1047482", "GSM1047483", "GSM1047484", "GSM1047485", "GSM1047486", "GSM1047487", "GSM1047488", "GSM1047489", "GSM1047490", "GSM1047491", "GSM1047492", "GSM1047493", "GSM1047494", "GSM1047495", "GSM1047496", "GSM1047497", "GSM1047498", "GSM1047499", "GSM1047500", "GSM1047501", "GSM1047502", "GSM1047503", "GSM1047504", "GSM1047505", "GSM1047506", "GSM1047507", "GSM1047508", "GSM1047509", "GSM1047510", "GSM1047511", "GSM1047512", "GSM1047513", "GSM1047514", "GSM1047515", "GSM1047516", "GSM1047517", "GSM1047518", "GSM1047519", "GSM1047520", "GSM1047521", "GSM1047522", "GSM1047523", "GSM1047524", "GSM1047525", "GSM1047526", "GSM1047527", "GSM1047528", "GSM1047529", "GSM1047530", "GSM1047531"], "sample_count": 64, "group_sizes": null, "group_sizes_basis": null, "platform": "8179", "taxon": "Homo sapiens", "title": "MicroRNA expression profiles for paediatric brain tumours", "resolution_checked_at": "2026-11-01T15:39:54Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:GSE50161", "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=GSE50161", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE50161", "version": null, "note": "The datasets generated and/or analyzed during the current study are available the GEO database repository (http://www.ncbi.nlm.nih.gov/geo/).", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The datasets generated and/or analyzed during the current study are available the GEO database repository (http://www.ncbi.nlm.nih.gov/geo/).", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM1214834", "GSM1214835", "GSM1214836", "GSM1214837", "GSM1214838", "GSM1214839", "GSM1214840", "GSM1214841", "GSM1214842", "GSM1214843", "GSM1214844", "GSM1214845", "GSM1214846", "GSM1214847", "GSM1214848", "GSM1214849", "GSM1214850", "GSM1214851", "GSM1214852", "GSM1214853", "GSM1214854", "GSM1214855", "GSM1214856", "GSM1214857", "GSM1214858", "GSM1214859", "GSM1214860", "GSM1214861", "GSM1214862", "GSM1214863", "GSM1214864", "GSM1214865", "GSM1214866", "GSM1214867", "GSM1214868", "GSM1214869", "GSM1214870", "GSM1214871", "GSM1214872", "GSM1214873", "GSM1214874", "GSM1214875", "GSM1214876", "GSM1214877", "GSM1214878", "GSM1214879", "GSM1214880", "GSM1214881", "GSM1214882", "GSM1214883", "GSM1214884", "GSM1214885", "GSM1214886", "GSM1214887", "GSM1214888", "GSM1214889", "GSM1214890", "GSM1214891", "GSM1214892", "GSM1214893", "GSM1214894", "GSM1214895", "GSM1214896", "GSM1214897", "GSM1214898", "GSM1214899", "GSM1214900", "GSM1214901", "GSM1214902", "GSM1214903", "GSM1214904", "GSM1214905", "GSM1214906", "GSM1214907", "GSM1214908", "GSM1214909", "GSM1214910", "GSM1214911", "GSM1214912", "GSM1214913", "GSM1214914", "GSM1214915", "GSM1214916", "GSM1214917", "GSM1214918", "GSM1214919", "GSM1214920", "GSM1214921", "GSM1214922", "GSM1214923", "GSM1214924", "GSM1214925", "GSM1214926", "GSM1214927", "GSM1214928", "GSM1214929", "GSM1214930", "GSM1214931", "GSM1214932", "GSM1214933", "GSM1214934", "GSM1214935", "GSM1214936", "GSM1214937", "GSM1214938", "GSM1214939", "GSM1214940", "GSM1214941", "GSM1214942", "GSM1214943", "GSM1214944", "GSM1214945", "GSM1214946", "GSM1214947", "GSM1214948", "GSM1214949", "GSM1214950", "GSM1214951", "GSM1214952", "GSM1214953", "GSM1214954", "GSM1214955", "GSM1214956", "GSM1214957", "GSM1214958", "GSM1214959", "GSM1214960", "GSM1214961", "GSM1214962", "GSM1214963"], "sample_count": 130, "group_sizes": null, "group_sizes_basis": null, "platform": "570", "taxon": "Homo sapiens", "title": "Expression data from human brain tumors and human normal brain", "resolution_checked_at": "2026-11-01T15:39:54Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:GSE66354", "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=GSE66354", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE66354", "version": null, "note": "The datasets generated and/or analyzed during the current study are available the GEO database repository (http://www.ncbi.nlm.nih.gov/geo/).", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The datasets generated and/or analyzed during the current study are available the GEO database repository (http://www.ncbi.nlm.nih.gov/geo/).", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM1620173", "GSM1620174", "GSM1620175", "GSM1620176", "GSM1620177", "GSM1620178", "GSM1620179", "GSM1620180", "GSM1620181", "GSM1620182", "GSM1620183", "GSM1620184", "GSM1620185", "GSM1620186", "GSM1620187", "GSM1620188", "GSM1620189", "GSM1620190", "GSM1620191", "GSM1620192", "GSM1620193", "GSM1620194", "GSM1620195", "GSM1620196", "GSM1620197", "GSM1620198", "GSM1620199", "GSM1620200", "GSM1620201", "GSM1620202", "GSM1620203", "GSM1620204", "GSM1620205", "GSM1620206", "GSM1620207", "GSM1620208", "GSM1620209", "GSM1620210", "GSM1620211", "GSM1620212", "GSM1620213", "GSM1620214", "GSM1620215", "GSM1620216", "GSM1620217", "GSM1620218", "GSM1620219", "GSM1620220", "GSM1620221", "GSM1620222", "GSM1620223", "GSM1620224", "GSM1620225", "GSM1620226", "GSM1620227", "GSM1620228", "GSM1620229", "GSM1620230", "GSM1620231", "GSM1620232", "GSM1620233", "GSM1620234", "GSM1620235", "GSM1620236", "GSM1620237", "GSM1620238", "GSM1620239", "GSM1620240", "GSM1620241", "GSM1620242", "GSM1620243", "GSM1620244", "GSM1620245", "GSM1620246", "GSM1620247", "GSM1620248", "GSM1620249", "GSM1620250", "GSM1620251", "GSM1620252", "GSM1620253", "GSM1620254", "GSM1620255", "GSM1620256", "GSM1620257", "GSM1620258", "GSM1620259", "GSM1620260", "GSM1620261", "GSM1620262", "GSM1620263", "GSM1620264", "GSM1620265", "GSM1620266", "GSM1620267", "GSM1620268", "GSM1620269", "GSM1620270", "GSM1620271", "GSM1620272", "GSM1620273", "GSM1620274", "GSM1620275", "GSM1620276", "GSM1620277", "GSM1620278", "GSM1620279", "GSM1620280", "GSM1620281", "GSM1620282", "GSM1620283", "GSM1620284", "GSM1620285", "GSM1620286", "GSM1620287", "GSM1620288", "GSM1620289", "GSM1620290", "GSM1620291", "GSM1620292", "GSM1620293", "GSM1620294", "GSM1620295", "GSM1620296", "GSM1620297", "GSM1620298", "GSM1620299", "GSM1620300", "GSM1620301", "GSM1620302", "GSM1620303", "GSM1620304", "GSM1620305", "GSM1620306", "GSM1620307", "GSM1620308", "GSM1620309", "GSM1620310", "GSM1620311", "GSM1620312", "GSM1620313", "GSM1620314", "GSM1620315", "GSM1620316", "GSM1620317", "GSM1620318", "GSM1620319", "GSM1620320", "GSM1620321"], "sample_count": 149, "group_sizes": null, "group_sizes_basis": null, "platform": "570", "taxon": "Homo sapiens", "title": "Investigation of the mechansim underlying the inflammatory phenotype in Group A ependymoma", "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:GSE74195", "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=GSE74195", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE74195", "version": null, "note": "The datasets generated and/or analyzed during the current study are available the GEO database repository (http://www.ncbi.nlm.nih.gov/geo/).", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The datasets generated and/or analyzed during the current study are available the GEO database repository (http://www.ncbi.nlm.nih.gov/geo/).", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM1914320", "GSM1914321", "GSM1914322", "GSM1914323", "GSM1914324", "GSM1914325", "GSM1914326", "GSM1914327", "GSM1914328", "GSM1914329", "GSM1914330", "GSM1914331", "GSM1914332", "GSM1914333", "GSM1914334", "GSM1914335", "GSM1914336", "GSM1914337", "GSM1914338", "GSM1914339", "GSM1914340", "GSM1914341", "GSM1914342", "GSM1914343", "GSM1914344", "GSM1914345", "GSM1914346", "GSM1914347", "GSM1914348", "GSM1914349", "GSM1914350", "GSM1914351", "GSM1914352", "GSM1914353", "GSM1914354", "GSM1914355", "GSM1914356", "GSM1914357", "GSM1914358", "GSM1914359", "GSM1914360", "GSM1914361", "GSM1914362", "GSM1914363", "GSM1914364", "GSM1914365", "GSM1914366", "GSM1914367", "GSM1914368", "GSM1914369", "GSM1914370"], "sample_count": 51, "group_sizes": null, "group_sizes_basis": null, "platform": "570", "taxon": "Homo sapiens", "title": "Differential expression and prognostic significant of SOX genes in pediatric medulloblastoma and ependymoma identified by microarray analysis", "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:GSE86574", "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=GSE86574", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE86574", "version": null, "note": "The datasets generated and/or analyzed during the current study are available the GEO database repository (http://www.ncbi.nlm.nih.gov/geo/).", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The datasets generated and/or analyzed during the current study are available the GEO database repository (http://www.ncbi.nlm.nih.gov/geo/).", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM2306094", "GSM2306095", "GSM2306096", "GSM2306097", "GSM2306098", "GSM2306099", "GSM2306100", "GSM2306101", "GSM2306102", "GSM2306103", "GSM2306104", "GSM2306105", "GSM2306106", "GSM2306107", "GSM2306108", "GSM2306109", "GSM2306110", "GSM2306111", "GSM2306112", "GSM2306113", "GSM2306114", "GSM2306115", "GSM2306116", "GSM2306117", "GSM2306118", "GSM2306119", "GSM2306120", "GSM2306121", "GSM2306122", "GSM2306123", "GSM2306124", "GSM2306125", "GSM2306126", "GSM2306127", "GSM2306128", "GSM2306129", "GSM2306130", "GSM2306131", "GSM2306132", "GSM2306133", "GSM2306134", "GSM2306135", "GSM2306136", "GSM2306137", "GSM2306138", "GSM2306139", "GSM2306140", "GSM2306141", "GSM2306142", "GSM2306143", "GSM2306144", "GSM2306145", "GSM2306146", "GSM2306147", "GSM2306148", "GSM2306149", "GSM2306150", "GSM2306151", "GSM2306152", "GSM2306153", "GSM2306154", "GSM2306155", "GSM2306156", "GSM2306157", "GSM2306158", "GSM2306159", "GSM2306160", "GSM2306161", "GSM2306162", "GSM2306163", "GSM2306164", "GSM2306165", "GSM2306166", "GSM2306167", "GSM2306168", "GSM2306169", "GSM2306170", "GSM2306171", "GSM2306172", "GSM2306173", "GSM2306174", "GSM2306175", "GSM2306176", "GSM2306177", "GSM2306178", "GSM2306179", "GSM2306180", "GSM2306181", "GSM2306182", "GSM2306183", "GSM2306184", "GSM2306185", "GSM2306186", "GSM2306187", "GSM2306188", "GSM2306189", "GSM2306190", "GSM2306191", "GSM2306192", "GSM2306193", "GSM2306194", "GSM2306195", "GSM2306196", "GSM2306197", "GSM2306198", "GSM2306199", "GSM2306200", "GSM2306201", "GSM2306202", "GSM2306203"], "sample_count": 110, "group_sizes": null, "group_sizes_basis": null, "platform": "570", "taxon": "Homo sapiens", "title": "Characterization of Two Novel Ependymoma Cell Lines with Chromosome 1q gain derived from Posterior Fossa Tumors of Childhood", "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:31788082:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:b9e69b96ef53c245ffac76068a18d6f890ecfb6a1e2b04b739495b2419c94ccb", "bytes": 556, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[18]/table-wrap[1]#tI-ol-0-0-10941", "version": null, "note": "miRNA-target pairs of top 3 miRNAs and hub genes from the miRNA-mRNA regulatory network.", "structure": {"pmcid": "PMC6865127", "section_index": 18, "section_title": "Construction of a negative miRNA-gene regulatory network", "row_count": 5, "column_count": 5}, "table": {"label": "Table I.", "caption": "miRNA-target pairs of top 3 miRNAs and hub genes from the miRNA-mRNA regulatory network.", "rows": [["Mature miRNA", "Precursor miRNA", "Expression", "Hub gene", "Expression"], ["hsa-miR-449a", "hsa-miR-449a", "Up", "SYT1", "Down"], ["hsa-miR-34a-5p", "hsa-miR-34a*; hsa-miR-34a", "Up", "SYT1", "Down"], ["hsa-miR-330-3p", "hsa-miR-330", "Down", "CD44", "Up"], ["hsa-miR-124-3p", "hsa-miR-124*, hsa-miR-124", "Down", "PCNA", "Up"]], "row_count": 5, "column_count": 5, "numeric_cells": 9, "header_rows": 1, "locator": "section[18]/table-wrap[1]#tI-ol-0-0-10941"}}], "gaps": ["asset:data:geo:GSE25604 not downloaded", "asset:data:geo:GSE25604 licence not read", "asset:data:geo:GSE42657 not downloaded", "asset:data:geo:GSE42657 licence not read", "asset:data:geo:GSE50161 not downloaded", "asset:data:geo:GSE50161 licence not read", "asset:data:geo:GSE66354 not downloaded", "asset:data:geo:GSE66354 licence not read", "asset:data:geo:GSE74195 not downloaded", "asset:data:geo:GSE74195 licence not read", "asset:data:geo:GSE86574 not downloaded", "asset:data:geo:GSE86574 licence not read"]}, "analysis": {"state": "partial", "methods": [{"id": "method-1", "family": "differential_expression", "specific": "limma_voom", "label": "Differential expression analysis", "dsl_operations": ["normalise_counts", "differential_expression_fit", "fdr_bh"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["count_matrix_with_condition"], "evidence": {"score": 0.7, "band": "medium", "quote": "Limma"}}, {"id": "method-2", "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-3", "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-4", "family": null, "specific": null, "label": "Independent sample t-test", "dsl_operations": [], "missing_operations": [], "expressible": null, "parameters": {}, "data_shapes": [], "evidence": {"score": 1.0, "band": "verbatim", "quote": "The statistical significance between EPN and normal brain tissues was determined using an independent sample t-test."}}], "targets": [], "gaps": ["method.reader_named_unmapped"]}, "capability": {"state": "complete", "requirements": [{"capability_id": "capability:computational_analysis", "label": "Computational analysis platform", "assay_families": ["meta_analysis", "machine_learning", "survival_analysis", "statistical_regression", "pca", "molecular_docking", "network_analysis", "differential_expression", "gwas"], "availability_state": "owned", "tier_unlocked": "R1", "candidate": "Automated Assays Laravel application and simulated adapters"}], "gaps": []}, "readiness": {"state": "complete", "tier": "R1", "blocking_axis": "none", "blocked_on": "nothing:replicable_now", "axes": {"method": {"tier": "R1", "expressible": true, "required_operations": ["normalise_counts", "differential_expression_fit", "fdr_bh"], "missing_operations": [], "basis": "The paper names the method it used and the corpus's method extractor maps it onto the DSL catalogue: limma_voom."}, "capability": {"tier": "R1", "capability_id": "capability:computational_analysis", "availability_state": "owned", "basis": "The computational analysis is owned. The physical bench the paper used is not, so a physical validation cannot be run here."}, "data": {"tier": "R1", "reachable": true, "accessions": ["GSE25604", "GSE50161", "GSE66354", "GSE74195", "GSE86574", "GSE42657"], "resolved_accessions": ["GSE25604", "GSE50161", "GSE66354", "GSE74195", "GSE86574", "GSE42657"], "statements": ["The datasets generated and/or analyzed during the current study are available the GEO database repository (http://www.ncbi.nlm.nih.gov/geo/)."], "basis": "The paper names GSE25604, GSE50161, GSE66354, GSE74195, GSE86574, GSE42657 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": ["normalise_counts", "differential_expression_fit", "fdr_bh"], "assets": ["source:pmid:31788082", "data:geo:GSE25604", "asset:table:pmid:31788082:1"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE25604"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-10-31T18:17:21Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 3, "usage": {"prompt_tokens": 35916, "completion_tokens": 2495, "cached_tokens": 784}}, "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:31788082", "type": "paper", "label": "pmid:31788082"}, {"id": "source:pmid:31788082", "type": "manuscript", "label": "PMID 31788082 full text"}, {"id": "data:geo:GSE25604", "type": "dataset", "label": "GEO GSE25604"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:31788082", "type": "paper", "label": "pmid:31788082"}, {"id": "source:pmid:31788082", "type": "manuscript", "label": "PMID 31788082 full text"}, {"id": "data:geo:GSE25604", "type": "dataset", "label": "GEO GSE25604"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-31788082", "type": "extraction", "used": ["source:pmid:31788082"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE25604", "type": "accession_resolution", "used": ["data:geo:GSE25604"], "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:31788082", "parent_hash": "sha256:0dff439edd5b3cc0cfe42c15454beeb4265d8f7566d0261e941f65c9e033d9cb", "fork_of": null, "generation": 4}, "gaps": ["asset:data:geo:GSE25604 licence not read", "asset:data:geo:GSE25604 not downloaded", "asset:data:geo:GSE42657 licence not read", "asset:data:geo:GSE42657 not downloaded", "asset:data:geo:GSE50161 licence not read", "asset:data:geo:GSE50161 not downloaded", "asset:data:geo:GSE66354 licence not read", "asset:data:geo:GSE66354 not downloaded", "asset:data:geo:GSE74195 licence not read", "asset:data:geo:GSE74195 not downloaded", "asset:data:geo:GSE86574 licence not read", "asset:data:geo:GSE86574 not downloaded", "execution.not_run", "method.reader_named_unmapped", "review.human_critique", "review.independent_reader", "review.machine_critique"], "assays": [{"role": "analysis", "definition_id": "differential_expression", "definition_version": "f2132e96ae6c7a4e", "definition_digest": null, "required_operations": ["normalise_counts", "differential_expression_fit", "fdr_bh"], "support_state": "supported", "source_hashes": {"dsl_catalogue": "f2132e96ae6c7a4e"}, "confidence": 0.7, "evidence": ["Limma"], "order_basis": "analysis_only", "id": "assay:1"}]},"meta":{"api_version":"v1","automation_ladder_snapshot":"ba34b49490d9bfaf","automation_ladder_caveats":["Method extraction is rule-based and has no hand-judged accuracy sample. Evidence bands order textual support; method agreement intervals are null (n=0), never probabilities. Work-type validation does not validate methods.","Operation coverage describes only explicitly named methods. It does not prove a complete protocol, compatible parameters, successful compilation or re-execution. Unrecognised or ambiguous methods require review.","Data reachability is a textual accession or public-data statement. No dataset was downloaded or checked for access, completeness or licence.","Capabilities are planning states seeded from the dated equipment register. No bench ownership, completed quote or partner booking is inferred. Procurement counts are dependencies, not guaranteed replications or financial returns.","Tier and blocker counts are deterministic assessments of this corpus, not measured agreement. R3 is reserved for procurement; unresolved methods and data require human work (R4). The most restrictive axis wins, with capability, method, data as tie-breaks. Resolving one blocker can leave another at the same tier."],"engine":"corpus_engine","engine_provider":"rule_based_v1+lex99e1195c7d6f","run_id":"run-20261023T122449232913","source":"esearch","source_detail":"PubMed mirror biomed_pubmed (read-only)","run_status":"complete","imported_at":"2026-11-03T20:16:52+00:00","generated_at":"2026-11-04T01:48:45+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}}}