{"data":{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:31981472", "kind": "science-record", "revision": 8, "content_hash": "sha256:26f7d5c92e0ebbf7aaa21ab1245459c7c3de0d4a138c6bba5cd406363e15b457", "created_at": "2026-11-01T15:40:55Z", "updated_at": "2026-11-01T22:01:13Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Common and distinct features of potentially predictive biomarkers in small cell lung carcinoma and large cell neuroendocrine carcinoma of the lung by systematic and integrated analysis.", "doi": "10.1002/mgg3.1126", "pmid": "31981472", "authors": ["Shenghua Dong", "Jun Liang", "Wenxin Zhai", "Zhuang Yu"], "journal": "Molecular genetics & genomic medicine", "year": 2020, "abstract": "BACKGROUND: Large-cell neuroendocrine carcinoma of the lung (LCNEC) and small-cell lung carcinoma (SCLC) are neuroendocrine neoplasms. However, the underlying mechanisms of common and distinct genetic characteristics between LCNEC and SCLC are currently unclear. Herein, protein expression profiles and possible interactions with miRNAs were provided by integrated bioinformatics analysis, in order to explore core genes associated with tumorigenesis and prognosis in SCLC and LCNEC.\nMETHODS: GSE1037 gene expression profiles were obtained from the Gene Expression Omnibus (GEO) database. Differentially expressed genes (DEGs) in LCNEC and SCLC, as compared with normal lung tissues, were selected using the GEO2R online analyzer and Venn diagram software. Gene ontology (GO) analysis was performed using Database for Annotation, Visualization and Integrated Discovery. The biological pathway analysis was performed using the FunRich database. Subsequently, a protein-protein interaction (PPI) network of DEGs was generated using Search Tool for the Retrieval of Interacting Genes and displayed via Cytoscape software. The PPI network was analyzed by the Molecular Complex Detection app from Cytoscape, and 16 upregulated hub genes were selected. The Oncomine database was used to detect expression patterns of hub genes for validation. Furthermore, the biological pathways of these 16 hub genes were re-analyzed, and potential interactions between these genes and miRNAs were explored via FunRich.\nRESULTS: A total of 384 DEGs were identified. A Venn diagram determined 88 common DEGs. The PPI network was constructed with 48 nodes and 221 protein pairs. Among them, 16 hub genes were extracted, 14 of which were upregulated in SCLC samples, as compared with normal lung specimens, and 10 were correlated with the cell cycle pathway. Furthermore, 57 target miRNAs for 8 hub genes were identified, among which 31 miRNAs were correlated with the progression of carcinoma, drug-resistance, radio-sensitivity, or autophagy in lung cancer.\nCONCLUSION: This study provided effective biomarkers and novel therapeutic targets for diagnosis and prognosis of SCLC and LCNEC.", "claims": [{"id": "claim-data-access", "statement": "Gene expression profiles (http://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE1037) were obtained from the GEO database, based on the GPL962 CHUGAI 41K platform. Data including 18 primary normal lung tissues, 8 primary LCNEC tissues, 15 primary small‐cell lung carcinoma tissues, and 9 small‐cell lung carcinoma cell lines were downloaded.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:31981472", "locator": "sections[4] \"Gene expression profile data\" paragraph 2", "quote": "Gene expression profiles (http://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE1037) were obtained from the GEO database, based on the GPL962 CHUGAI 41K platform. Data including 18 primary normal lung tissues, 8 primary LCNEC tissues, 15 primary small‐cell lung carcinoma tissues, and 9 small‐cell lung carcinoma cell lines were downloaded."}], "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:31981472"], "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:GSE1037"], "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:GSE1037"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:31981472", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1002/mgg3.1126", "sha256": "sha256:fb7f3b48eb1b331626dbfe0efcbefc8ee5a755a34f2516dd4b919c93672582c6", "bytes": 70667, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1002/mgg3.1126", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC7057089", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE1037", "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=GSE1037", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE1037", "version": null, "note": "Gene expression profiles (http://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE1037) were obtained from the GEO database, based on the GPL962 CHUGAI 41K platform. Data including 18 primary normal lung tissues, 8 primary LCNEC tissues, 15 primary small‐cell lung carcinoma tissues, and 9 small‐cell lung carcinoma cell lines were downloaded.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "Gene expression profiles (http://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE1037) were obtained from the GEO database, based on the GPL962 CHUGAI 41K platform. Data including 18 primary normal lung tissues, 8 primary LCNEC tissues, 15 primary small‐cell lung carcinoma tissues, and 9 small‐cell lung carcinoma cell lines were downloaded.", "access_statement_kind": "repository_route_statement", "sample_accessions": ["GSM16557", "GSM16558", "GSM16559", "GSM16560", "GSM16561", "GSM16562", "GSM16563", "GSM16564", "GSM16565", "GSM16566", "GSM16567", "GSM16568", "GSM17195", "GSM17196", "GSM17287", "GSM17288", "GSM17289", "GSM17290", "GSM17291", "GSM17292", "GSM17293", "GSM17294", "GSM17295", "GSM17296", "GSM17297", "GSM17298", "GSM17299", "GSM17300", "GSM17301", "GSM17302", "GSM17303", "GSM17304", "GSM17305", "GSM17306", "GSM17307", "GSM17308", "GSM17309", "GSM17310", "GSM17311", "GSM17312", "GSM17313", "GSM17314", "GSM17315", "GSM17316", "GSM17317", "GSM17318", "GSM17319", "GSM17320", "GSM17321", "GSM17322", "GSM17323", "GSM17324", "GSM17325", "GSM17326", "GSM17327", "GSM17328", "GSM17329", "GSM17330", "GSM17331", "GSM17332", "GSM17333", "GSM17334", "GSM17335", "GSM17336", "GSM17337", "GSM17338", "GSM17339", "GSM17340", "GSM17341", "GSM17342", "GSM17343", "GSM17344", "GSM17345", "GSM17346", "GSM17347", "GSM17348", "GSM17349", "GSM17350", "GSM17351", "GSM17352", "GSM17353", "GSM17354", "GSM17355", "GSM17356", "GSM18306", "GSM18307", "GSM18308", "GSM18309", "GSM18310", "GSM18311", "GSM18312"], "sample_count": 91, "group_sizes": null, "group_sizes_basis": null, "platform": "962", "taxon": "Homo sapiens", "title": "Lung cancer", "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:31981472:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:9786397856b13a122a79357fa9dc5a8e5fa2019cb1b822a8125dd9b8aeb01513", "bytes": 908, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[12]/table-wrap[1]#mgg31126-tbl-0001", "version": null, "note": "Commonly DEGs in the SCLC and LCNEC samples", "structure": {"pmcid": "PMC7057089", "section_index": 12, "section_title": "Identification of DEGs", "row_count": 3, "column_count": 2}, "table": {"label": "Table 1", "caption": "Commonly DEGs in the SCLC and LCNEC samples", "rows": [["DEGs", "Genes name"], ["Upregulated", "ZNF829 BCCIP PTTG1 CENPA FAM123A SESN2 CSE1L LOC256676///CDCA5 PBK UBE2TC5orf13 ZNF587 UNQ353///CSNK1G1///KIAA0101 HMGB3 SOX4 FARP1 C1orf215///STMN1 MLF1IP AURKA MYBL2 ZWINTAS///ZWINT UBE2C EZH2 RFC4 CDCA8 SLC2A1 LOC253012 TPX2 TTKCDCA7 TOP2A NUF2"], ["Downregulated", "ADH1B CAV1 WIF1 SFTPC FMO2 TSHZ2///ADAMTS8 USP42 MFAP4 SCGB1A1 IGSF10 TIMP3 CLDN18 OGN CAV2 MAOA FABP4 ZNF521 SVEP1 EPAS1 TPSB2///TPSAB1 FHL1 FAT4 CAB39L ADH1C PI4KAP1 C2orf34 AGER LOC144571///PZP///A2M AQP4 FAM75A1 SFTPH AQP1 CAMP HBE1 EMCN HNRNPH1 SLC39A8 SUSD2 FLJ44379 LIMCH1 SLPI CYBRD1 HOPX C13orf15 LOC100131277///TACC1 LYVE1 GPR116 MAOB SELENBP1 PGM5 EMP2 PMP22 S1PR1 ABCA8 ANGPTL1 RGS2"]], "row_count": 3, "column_count": 2, "numeric_cells": 2, "header_rows": 1, "locator": "section[12]/table-wrap[1]#mgg31126-tbl-0001"}}, {"id": "asset:table:pmid:31981472:2", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:b82744efdde33404a5809029f9f0d7e40ef5ade12d670f791c0a9ef31492a14e", "bytes": 5525, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[13]/table-wrap[1]#mgg31126-tbl-0002", "version": null, "note": "Enriched Go terms of the DEGs", "structure": {"pmcid": "PMC7057089", "section_index": 13, "section_title": "Enrichment analysis", "row_count": 52, "column_count": 7}, "table": {"label": "Table 2", "caption": "Enriched Go terms of the DEGs", "rows": [["", "Category", "Term", "Count", "%", "p‐Value", "FDR"], ["Up regulated", "GOTERM_BP_DIRECT", "GO:0051301~cell division", "6", "0.142993327", "4.04E‐06", "0.004971483"], ["GOTERM_BP_DIRECT", "GO:0006355~regulation of transcription DNA‐templated", "7", "0.166825548", "3.53E‐04", "0.432578524"], ["GOTERM_BP_DIRECT", "GO:0006281~DNA repair", "4", "0.095328885", "8.15E‐04", "0.997007591"], ["GOTERM_BP_DIRECT", "GO:0045143~homologous chromosome segregation", "2", "0.047664442", ".006639221", "7.86341138"], ["GOTERM_BP_DIRECT", "GO:0031536~positive regulation of exit from mitosis", "2", "0.047664442", ".008292426", "9.731016783"], ["GOTERM_BP_DIRECT", "GO:0007067~mitotic nuclear division", "3", "0.071496663", ".013030094", "14.89218414"], ["GOTERM_BP_DIRECT", "GO:0046323~glucose import", "2", "0.047664442", ".018156528", "20.17047326"], ["GOTERM_BP_DIRECT", "GO:0051276~chromosome organization", "2", "0.047664442", ".023053317", "24.9298377"], ["GOTERM_BP_DIRECT", "GO:0070979~protein K11‐linked ubiquitination", "2", "0.047664442", ".037603917", "37.57710332"], ["GOTERM_BP_DIRECT", "GO:0007052~mitotic spindle organization", "2", "0.047664442", ".037603917", "37.57710332"], ["GOTERM_BP_DIRECT", "GO:0090307~mitotic spindle assembly", "2", "0.047664442", ".045597774", "43.66110836"], ["GOTERM_CC_DIRECT", "GO:0005737~cytoplasm", "15", "0.357483317", "2.21E‐05", "0.022280174"], ["GOTERM_CC_DIRECT", "GO:0005634~nucleus", "14", "0.333651096", "5.40E‐05", "0.054460588"], ["GOTERM_CC_DIRECT", "GO:0043203~axon hillock", "2", "0.047664442", ".00741693", "7.237425098"], ["GOTERM_CC_DIRECT", "GO:0032133~chromosome passenger complex", "2", "0.047664442", ".00741693", "7.237425098"], ["GOTERM_CC_DIRECT", "GO:0005654~nucleoplasm", "7", "0.166825548", ".010502317", "10.10650713"], ["GOTERM_CC_DIRECT", "GO:0045120~pronucleus", "2", "0.047664442", ".013312558", "12.64989615"], ["GOTERM_CC_DIRECT", "GO:0051233~spindle midzone", "2", "0.047664442", ".022093237", "20.18460143"], ["GOTERM_MF_DIRECT", "GO:0031625~ubiquitin protein ligase binding", "3", "0.076628352", ".011662791", "10.93819391"], ["GOTERM_MF_DIRECT", "GO:0008301~DNA binding bending", "2", "0.051085568", ".015851015", "14.59560577"], ["GOTERM_MF_DIRECT", "GO:0005524~ATP binding", "6", "0.153256705", ".027091606", "23.75384229"], ["GOTERM_MF_DIRECT", "GO:0030414~peptidase inhibitor activity", "2", "0.051085568", ".030054212", "26.01571812"], ["GOTERM_MF_DIRECT", "GO:0061631~ubiquitin conjugating enzyme activity", "2", "0.051085568", ".038482685", "32.12464677"], ["Down regulated", "GOTERM_BP_DIRECT", "GO:0070836~caveola assembly", "3", "0.046260601", "6.99E−05", "0.098559412"], ["GOTERM_BP_DIRECT", "GO:0007155~cell adhesion", "6", "0.092521203", ".007419687", "9.977332032"], ["GOTERM_BP_DIRECT", "GO:0019065~receptor‐mediated endocytosis of virus by host cell", "2", "0.030840401", ".008018493", "10.74080337"], ["GOTERM_BP_DIRECT", "GO:0042420~dopamine catabolic process", "2", "0.030840401", ".013329193", "17.25342044"], ["GOTERM_BP_DIRECT", "GO:0042135~neurotransmitter catabolic process", "2", "0.030840401", ".021243157", "26.14357095"], ["GOTERM_BP_DIRECT", "GO:0050891~multicellular organismal water homeostasis", "2", "0.030840401", ".021243157", "26.14357095"], ["GOTERM_BP_DIRECT", "GO:0001525~angiogenesis", "4", "0.061680802", ".021777665", "26.71078904"], ["GOTERM_BP_DIRECT", "GO:0032060~bleb assembly", "2", "0.030840401", ".026484616", "31.53390357"], ["GOTERM_BP_DIRECT", "GO:0006069~ethanol oxidation", "2", "0.030840401", ".031698626", "36.53140253"], ["GOTERM_BP_DIRECT", "GO:0015793~glycerol transport", "2", "0.030840401", ".034295382", "38.89185575"], ["GOTERM_BP_DIRECT", "GO:0009992~cellular water homeostasis", "2", "0.030840401", ".034295382", "38.89185575"], ["GOTERM_CC_DIRECT", "GO:0070062~extracellular exosome", "16", "0.246723207", ".001317986", "1.408901211"], ["GOTERM_CC_DIRECT", "GO:0005886~plasma membrane", "19", "0.292983809", ".003743762", "3.955034143"], ["GOTERM_CC_DIRECT", "GO:0005901~caveola", "3", "0.046260601", ".010295194", "10.53630766"], ["GOTERM_CC_DIRECT", "GO:0005576~extracellular region", "10", "0.154202005", ".01150877", "11.70950819"], ["GOTERM_CC_DIRECT", "GO:0045121~membrane raft", "4", "0.061680802", ".012603718", "12.75603307"], ["GOTERM_CC_DIRECT", "GO:0045177~apical part of cell", "3", "0.046260601", ".013532583", "13.63498448"], ["GOTERM_CC_DIRECT", "GO:0016021~integral component of membrane", "20", "0.308404009", ".018955008", "18.60768595"], ["GOTERM_CC_DIRECT", "GO:0031012~extracellular matrix", "4", "0.061680802", ".032469722", "29.89178143"], ["GOTERM_CC_DIRECT", "GO:0005615~extracellular space", "8", "0.123361604", ".036771948", "33.17391345"], ["GOTERM_CC_DIRECT", "GO:0002080~acrosomal membrane", "2", "0.030840401", ".043912815", "38.31524409"], ["GOTERM_MF_DIRECT", "GO:0016491~oxidoreductase activity", "4", "0.061680802", ".014279333", "14.99791487"], ["GOTERM_MF_DIRECT", "GO:0005215~transporter activity", "4", "0.061680802", ".014662761", "15.37073704"], ["GOTERM_MF_DIRECT", "GO:0004024~alcohol dehydrogenase activity zinc‐dependent", "2", "0.030840401", ".015188693", "15.87969632"], ["GOTERM_MF_DIRECT", "GO:0005372~water transmembrane transporter activity", "2", "0.030840401", ".015188693", "15.87969632"], ["GOTERM_MF_DIRECT", "GO:0008131~primary amine oxidase activity", "2", "0.030840401", ".015188693", "15.87969632"], ["GOTERM_MF_DIRECT", "GO:0015254~glycerol channel activity", "2", "0.030840401", ".030151975", "29.24210187"], ["GOTERM_MF_DIRECT", "GO:0015250~water channel activity", "2", "0.030840401", ".040003884", "36.95130237"]], "row_count": 52, "column_count": 7, "numeric_cells": 255, "header_rows": 1, "locator": "section[13]/table-wrap[1]#mgg31126-tbl-0002"}}, {"id": "asset:table:pmid:31981472:3", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:3581cf5f8d32afc3aa40cd62d3b39fe23a861884a472e25273b5004ed772775b", "bytes": 1601, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[17]/table-wrap[1]#mgg31126-tbl-0003", "version": null, "note": "Hub genes and corresponded target miRNAs", "structure": {"pmcid": "PMC7057089", "section_index": 17, "section_title": "Prediction of target miRNAs for hub genes", "row_count": 9, "column_count": 2}, "table": {"label": "Table 3", "caption": "Hub genes and corresponded target miRNAs", "rows": [["Gene", "miRNA"], ["TTK", "hsa‐miR‐101‐3p hsa‐miR‐212‐3p hsa‐miR‐132‐3p hsa‐miR‐140‐5p hsa‐miR‐455‐3p hsa‐miR‐582‐5p"], ["PTTG1", "hsa‐miR‐655‐3p hsa‐miR‐374c‐5p"], ["MYBL2", "hsa‐miR‐29a‐3p hsa‐miR‐29b‐3p hsa‐miR‐30c‐5p hsa‐miR‐30a‐5p hsa‐miR‐30b‐5p hsa‐miR‐30d‐5p hsa‐miR‐29c‐3p hsa‐miR‐30e‐5p hsa‐miR‐423‐5p hsa‐miR‐3184‐5p"], ["EZH2", "hsa‐miR‐101‐3p hsa‐miR‐124‐3p hsa‐miR‐137 hsa‐miR‐138‐5p"], ["CENPA", "hsa‐miR‐873‐5p"], ["CDCA8", "hsa‐let‐7a‐5p hsa‐let‐7b‐5p hsa‐let‐7c‐5p hsa‐let‐7d‐5p hsa‐let‐7e‐5p hsa‐let‐7f‐5p hsa‐miR‐98‐5p hsa‐let‐7g‐5p hsa‐let‐7i‐5p hsa‐miR‐133a‐3p hsa‐miR‐133b hsa‐miR‐4458 hsa‐miR‐4500"], ["CDCA7", "hsa‐miR‐30a‐5p hsa‐miR‐30b‐5p hsa‐miR‐30c‐5p hsa‐miR‐30d‐5p hsa‐miR‐30e‐5p hsa‐miR‐302a‐3p hsa‐miR‐302‐3p hsa‐miR‐302c‐3p hsa‐miR‐302d‐3p hsa‐miR‐372‐3p hsa‐miR‐373‐3p hsa‐miR‐520e hsa‐miR‐520b hsa‐miR‐520f‐3p hsa‐miR‐520a‐3p hsa‐miR‐520d‐3p hsa‐miR‐520c‐3p hsa‐miR‐499a‐5p hsa‐miR‐302e"], ["AURKA", "hsa‐miR‐25‐3p hsa‐miR‐92a‐3p hsa‐miR‐363‐3p hsa‐miR‐367‐3p hsa‐miR‐490‐3p hsa‐miR‐92b‐3p hsa‐miR‐421 hsa‐miR‐32‐5p"]], "row_count": 9, "column_count": 2, "numeric_cells": 8, "header_rows": 1, "locator": "section[17]/table-wrap[1]#mgg31126-tbl-0003"}}, {"id": "asset:table:pmid:31981472:4", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:18caefba689141877e0022338719ab5a1962a335c1e5a76734b7ee0962d571e9", "bytes": 1595, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[17]/table-wrap[2]#mgg31126-tbl-0004", "version": null, "note": "Functions of miRNAs in lung cancer", "structure": {"pmcid": "PMC7057089", "section_index": 17, "section_title": "Prediction of target miRNAs for hub genes", "row_count": 9, "column_count": 2}, "table": {"label": "Table 4", "caption": "Functions of miRNAs in lung cancer", "rows": [["Gene", "miRNA"], ["TTK", "hsa‐miR‐101‐3p hsa‐miR‐212‐3p hsa‐miR‐132‐3p hsa‐miR‐140‐5p hsa‐miR‐455‐3p hsa‐miR‐582‐5p"], ["PTTG1", "hsa‐miR‐655‐3p hsa‐miR‐374c‐5p"], ["MYBL2", "hsa‐miR‐29a‐3p hsa‐miR‐29b‐3p hsa‐miR‐30c‐5p hsa‐miR‐30a‐5p hsa‐miR‐30b‐5p hsa‐miR‐30d‐5p hsa‐miR‐29c‐3p hsa‐miR‐30e‐5p hsa‐miR‐423‐5p hsa‐miR‐3184‐5p"], ["EZH2", "hsa‐miR‐101‐3p hsa‐miR‐124‐3p hsa‐miR‐137 hsa‐miR‐138‐5p"], ["CENPA", "hsa‐miR‐873‐5p"], ["CDCA8", "hsa‐let‐7a‐5p hsa‐let‐7b‐5p hsa‐let‐7c‐5p hsa‐let‐7d‐5p hsa‐let‐7e‐5p hsa‐let‐7f‐5p hsa‐miR‐98‐5p hsa‐let‐7g‐5p hsa‐let‐7i‐5p hsa‐miR‐133a‐3p hsa‐miR‐133b hsa‐miR‐4458 hsa‐miR‐4500"], ["CDCA7", "hsa‐miR‐30a‐5p hsa‐miR‐30b‐5p hsa‐miR‐30c‐5p hsa‐miR‐30d‐5p hsa‐miR‐30e‐5p hsa‐miR‐302a‐3p hsa‐miR‐302‐3p hsa‐miR‐302c‐3p hsa‐miR‐302d‐3p hsa‐miR‐372‐3p hsa‐miR‐373‐3p hsa‐miR‐520e hsa‐miR‐520b hsa‐miR‐520f‐3p hsa‐miR‐520a‐3p hsa‐miR‐520d‐3p hsa‐miR‐520c‐3p hsa‐miR‐499a‐5p hsa‐miR‐302e"], ["AURKA", "hsa‐miR‐25‐3p hsa‐miR‐92a‐3p hsa‐miR‐363‐3p hsa‐miR‐367‐3p hsa‐miR‐490‐3p hsa‐miR‐92b‐3p hsa‐miR‐421 hsa‐miR‐32‐5p"]], "row_count": 9, "column_count": 2, "numeric_cells": 8, "header_rows": 1, "locator": "section[17]/table-wrap[2]#mgg31126-tbl-0004"}}], "gaps": ["asset:data:geo:GSE1037 not downloaded", "asset:data:geo:GSE1037 licence not read"]}, "analysis": {"state": "complete", "methods": [{"id": "method-1", "family": "network_analysis", "specific": "ppi_network", "label": "Network / pathway analysis", "dsl_operations": ["build_graph", "centrality_scores", "pathway_enrich"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["edge_list"], "evidence": {"score": 0.7, "band": "medium", "quote": "protein-protein interaction"}}, {"id": "method-2", "family": "network_analysis", "specific": "pathway_enrichment", "label": "Network / pathway analysis", "dsl_operations": ["pathway_enrich"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["edge_list"], "evidence": {"score": 0.8, "band": "high", "quote": "pathway enrichment"}}], "targets": [], "gaps": []}, "capability": {"state": "complete", "requirements": [{"capability_id": "capability:computational_analysis", "label": "Computational analysis platform", "assay_families": ["meta_analysis", "machine_learning", "survival_analysis", "statistical_regression", "pca", "molecular_docking", "network_analysis", "differential_expression", "gwas"], "availability_state": "owned", "tier_unlocked": "R1", "candidate": "Automated Assays Laravel application and simulated adapters"}], "gaps": []}, "readiness": {"state": "complete", "tier": "R1", "blocking_axis": "none", "blocked_on": "nothing:replicable_now", "axes": {"method": {"tier": "R1", "expressible": true, "required_operations": ["build_graph", "centrality_scores", "pathway_enrich"], "missing_operations": [], "basis": "The paper names the method it used and the corpus's method extractor maps it onto the DSL catalogue: ppi_network."}, "capability": {"tier": "R1", "capability_id": "capability:computational_analysis", "availability_state": "owned", "basis": "The computational analysis is owned. The physical bench the paper used is not, so a physical validation cannot be run here."}, "data": {"tier": "R1", "reachable": true, "accessions": ["GSE1037"], "resolved_accessions": ["GSE1037"], "statements": ["Gene expression profiles (http://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE1037) were obtained from the GEO database, based on the GPL962 CHUGAI 41K platform. Data including 18 primary normal lung tissues, 8 primary LCNEC tissues, 15 primary small‐cell lung carcinoma tissues, and 9 small‐cell lung carcinoma cell lines were downloaded."], "basis": "The paper names GSE1037 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:31981472", "data:geo:GSE1037", "asset:table:pmid:31981472:1", "asset:table:pmid:31981472:2", "asset:table:pmid:31981472:3", "asset:table:pmid:31981472:4"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE1037"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-10-31T18:55:55Z", "independence": "single_reader"}, "evidence_check": {"method": null, "availability": null}, "calls": 3, "usage": {"prompt_tokens": 43845, "completion_tokens": 1380, "cached_tokens": 520}}, "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:31981472", "type": "paper", "label": "pmid:31981472"}, {"id": "source:pmid:31981472", "type": "manuscript", "label": "PMID 31981472 full text"}, {"id": "data:geo:GSE1037", "type": "dataset", "label": "GEO GSE1037"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:31981472", "type": "paper", "label": "pmid:31981472"}, {"id": "source:pmid:31981472", "type": "manuscript", "label": "PMID 31981472 full text"}, {"id": "data:geo:GSE1037", "type": "dataset", "label": "GEO GSE1037"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-31981472", "type": "extraction", "used": ["source:pmid:31981472"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE1037", "type": "accession_resolution", "used": ["data:geo:GSE1037"], "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:31981472", "parent_hash": "sha256:6b8383e36cb08aaad02ce753290a39e240b5010ba5da8c3ae9cfb4a589f000be", "fork_of": null, "generation": 7}, "gaps": ["asset:data:geo:GSE1037 licence not read", "asset:data:geo:GSE1037 not downloaded", "execution.not_run", "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":"2026-11-04T03:34:13+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}}}