{"data":{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:30393234", "kind": "science-record", "revision": 7, "content_hash": "sha256:d973b1b04929bdec0cf7d962e22ec92308b7994a3e60b964b7f466ec3cb33889", "created_at": "2026-11-01T15:40:38Z", "updated_at": "2026-11-01T22:00:08Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Gene expression profiles analysis identifies a novel two-gene signature to predict overall survival in diffuse large B-cell lymphoma.", "doi": "10.1042/BSR20181293", "pmid": "30393234", "authors": ["Chengtao Sun", "Xianfeng Cheng", "Chaoyu Wang", "Xi Wang", "Bing Xia", "Yizhuo Zhang"], "journal": "Bioscience reports", "year": 2019, "abstract": "Diffuse large B-cell lymphoma (DLBCL) is the most common hematologic malignancy, however, specific tumor-associated genes and signaling pathways are yet to be deciphered. Differentially expressed genes (DEGs) were computed based on gene expression profiles from GSE32018, GSE56315, and The Cancer Genome Atlas (TCGA) DLBC. Overlapping DEGs were then evaluated for gene ontology (GO), pathways enrichment, DNA methylation, protein-protein interaction (PPI) network analysis as well as survival analysis. Seventy-four up-regulated and 79 down-regulated DEGs were identified. From PPI network analysis, majority of the DEGs were involved in cell cycle, oocyte meiosis, and epithelial-to-mesenchymal transition (EMT) pathways. Six hub genes including CDC20, MELK, PBK, prostaglandin D2 synthase (PTGDS), PCNA, and CDK1 were selected using the Molecular Complex Detection (MCODE). CDC20 and PTGDS were able to predict overall survival (OS) in TCGA DLBC and in an additional independent cohort GSE31312. Furthermore, CDC20 DNA methylation negatively regulated CDC20 expression and was able to predict OS in DLBCL. A two-gene panel consisting of CDC20 and PTGDS had a better prognostic value compared with CDC20 or PTGDS alone in the TCGA cohort (P=0.026 and 0.039). Overall, the present study identified a set of novel genes and pathways that may play a significant role in the initiation and progression of DLBCL. In addition, CDC20 and PTGDS will provide useful guidance for therapeutic applications.", "claims": [{"id": "claim-method", "statement": "The receiver operating characteristic (ROC) curve was used to assess the diagnostic effectiveness of the identified hub genes between DLBCL and normal tissue, and was based on the GSE56315 dataset.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:30393234", "locator": "sections[6] \"Validation of the diagnostic effectiveness of the identified hub genes for DLBCL\" paragraph 2", "quote": "The receiver operating characteristic (ROC) curve was used to assess the diagnostic effectiveness of the identified hub genes between DLBCL and normal tissue, and was based on the GSE56315 dataset."}], "state": "complete"}, {"id": "claim-data-access", "statement": "All data were extracted from previously published freely available datasets.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:30393234", "locator": "sections[19] \"Data availability\" paragraph 2", "quote": "All data were extracted from previously published freely available datasets."}], "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:30393234"], "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:GSE31312"], "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:GSE31312"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:30393234", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1042/BSR20181293", "sha256": "sha256:b60f7cc1db470cdd8bb57480738a696298de8b01cd3a4715c9d2a2d36876ae86", "bytes": 37456, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1042/BSR20181293", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC6328866", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE31312", "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=GSE31312", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE31312", "version": null, "note": "All data were extracted from previously published freely available datasets.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "All data were extracted from previously published freely available datasets.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM775979", "GSM775980", "GSM775981", "GSM775982", "GSM775983", "GSM775984", "GSM775985", "GSM775986", "GSM775987", "GSM775988", "GSM775989", "GSM775990", "GSM775991", "GSM775992", "GSM775993", "GSM775994", "GSM775995", "GSM775996", "GSM775997", "GSM775998", "GSM775999", "GSM776000", "GSM776001", "GSM776002", "GSM776003", "GSM776004", "GSM776005", "GSM776006", "GSM776007", "GSM776008", "GSM776009", "GSM776010", "GSM776011", "GSM776012", "GSM776013", "GSM776014", "GSM776015", "GSM776016", "GSM776017", "GSM776018", "GSM776019", "GSM776020", "GSM776021", "GSM776022", "GSM776023", "GSM776024", "GSM776025", "GSM776026", "GSM776027", "GSM776028", "GSM776029", "GSM776030", "GSM776031", "GSM776032", "GSM776033", "GSM776034", "GSM776035", "GSM776036", "GSM776037", "GSM776038", "GSM776039", "GSM776040", "GSM776041", "GSM776042", "GSM776043", "GSM776044", "GSM776045", "GSM776046", "GSM776047", "GSM776048", "GSM776049", "GSM776050", "GSM776051", "GSM776052", "GSM776053", "GSM776054", "GSM776055", "GSM776056", "GSM776057", "GSM776058", "GSM776059", "GSM776060", "GSM776061", "GSM776062", "GSM776063", "GSM776064", "GSM776065", "GSM776066", "GSM776067", "GSM776068", "GSM776069", "GSM776070", "GSM776071", "GSM776072", "GSM776073", "GSM776074", "GSM776075", "GSM776076", "GSM776077", "GSM776078", "GSM776079", "GSM776080", "GSM776081", "GSM776082", "GSM776083", "GSM776084", "GSM776085", "GSM776086", "GSM776087", "GSM776088", "GSM776089", "GSM776090", "GSM776091", "GSM776092", "GSM776093", "GSM776094", "GSM776095", "GSM776096", "GSM776097", "GSM776098", "GSM776099", "GSM776100", "GSM776101", "GSM776102", "GSM776103", "GSM776104", "GSM776105", "GSM776106", "GSM776107", "GSM776108", "GSM776109", "GSM776110", "GSM776111", "GSM776112", "GSM776113", "GSM776114", "GSM776115", "GSM776116", "GSM776117", "GSM776118", "GSM776119", "GSM776120", "GSM776121", "GSM776122", "GSM776123", "GSM776124", "GSM776125", "GSM776126", "GSM776127", "GSM776128", "GSM776129", "GSM776130", "GSM776131", "GSM776132", "GSM776133", "GSM776134", "GSM776135", "GSM776136", "GSM776137", "GSM776138", "GSM776139", "GSM776140", "GSM776141", "GSM776142", "GSM776143", "GSM776144", "GSM776145", "GSM776146", "GSM776147", "GSM776148", "GSM776149", "GSM776150", "GSM776151", "GSM776152", "GSM776153", "GSM776154", "GSM776155", "GSM776156", "GSM776157", "GSM776158", "GSM776159", "GSM776160", "GSM776161", "GSM776162", "GSM776163", "GSM776164", "GSM776165", "GSM776166", "GSM776167", "GSM776168", "GSM776169", "GSM776170", "GSM776171", "GSM776172", "GSM776173", "GSM776174", "GSM776175", "GSM776176", "GSM776177", "GSM776178", "GSM776179", "GSM776180", "GSM776181", "GSM776182", "GSM776183", "GSM776184", "GSM776185", "GSM776186", "GSM776187", "GSM776188", "GSM776189", "GSM776190", "GSM776191", "GSM776192", "GSM776193", "GSM776194", "GSM776195", "GSM776196", "GSM776197", "GSM776198", "GSM776199", "GSM776200", "GSM776201", "GSM776202", "GSM776203", "GSM776204", "GSM776205", "GSM776206", "GSM776207", "GSM776208", "GSM776209", "GSM776210", "GSM776211", "GSM776212", "GSM776213", "GSM776214", "GSM776215", "GSM776216", "GSM776217", "GSM776218", "GSM776219", "GSM776220", "GSM776221", "GSM776222", "GSM776223", "GSM776224", "GSM776225", "GSM776226", "GSM776227", "GSM776228", "GSM776229", "GSM776230", "GSM776231", "GSM776232", "GSM776233", "GSM776234", "GSM776235", "GSM776236", "GSM776237", "GSM776238", "GSM776239", "GSM776240", "GSM776241", "GSM776242", "GSM776243", "GSM776244", "GSM776245", "GSM776246", "GSM776247", "GSM776248", "GSM776249", "GSM776250", "GSM776251", "GSM776252", "GSM776253", "GSM776254", "GSM776255", "GSM776256", "GSM776257", "GSM776258", "GSM776259", "GSM776260", "GSM776261", "GSM776262", "GSM776263", "GSM776264", "GSM776265", "GSM776266", "GSM776267", "GSM776268", "GSM776269", "GSM776270", "GSM776271", "GSM776272", "GSM776273", "GSM776274", "GSM776275", "GSM776276", "GSM776277", "GSM776278", "GSM776279", "GSM776280", "GSM776281", "GSM776282", "GSM776283", "GSM776284", "GSM776285", "GSM776286", "GSM776287", "GSM776288", "GSM776289", "GSM776290", "GSM776291", "GSM776292", "GSM776293", "GSM776294", "GSM776295", "GSM776296", "GSM776297", "GSM776298", "GSM776299", "GSM776300", "GSM776301", "GSM776302", "GSM776303", "GSM776304", "GSM776305", "GSM776306", "GSM776307", "GSM776308", "GSM776309", "GSM776310", "GSM776311", "GSM776312", "GSM776313", "GSM776314", "GSM776315", "GSM776316", "GSM776317", "GSM776318", "GSM776319", "GSM776320", "GSM776321", "GSM776322", "GSM776323", "GSM776324", "GSM776325", "GSM776326", "GSM776327", "GSM776328", "GSM776329", "GSM776330", "GSM776331", "GSM776332", "GSM776333", "GSM776334", "GSM776335", "GSM776336", "GSM776337", "GSM776338", "GSM776339", "GSM776340", "GSM776341", "GSM776342", "GSM776343", "GSM776344", "GSM776345", "GSM776346", "GSM776347", "GSM776348", "GSM776349", "GSM776350", "GSM776351", "GSM776352", "GSM776353", "GSM776354", "GSM776355", "GSM776356", "GSM776357", "GSM776358", "GSM776359", "GSM776360", "GSM776361", "GSM776362", "GSM776363", "GSM776364", "GSM776365", "GSM776366", "GSM776367", "GSM776368", "GSM776369", "GSM776370", "GSM776371", "GSM776372", "GSM776373", "GSM776374", "GSM776375", "GSM776376", "GSM776377", "GSM776378", "GSM776379", "GSM776380", "GSM776381", "GSM776382", "GSM776383", "GSM776384", "GSM776385", "GSM776386", "GSM776387", "GSM776388", "GSM776389", "GSM776390", "GSM776391", "GSM776392", "GSM776393", "GSM776394", "GSM776395", "GSM776396", "GSM776397", "GSM776398", "GSM776399", "GSM776400", "GSM776401", "GSM776402", "GSM776403", "GSM776404", "GSM776405", "GSM776406", "GSM776407", "GSM776408", "GSM776409", "GSM776410", "GSM776411", "GSM776412", "GSM776413", "GSM776414", "GSM776415", "GSM776416", "GSM776417", "GSM776418", "GSM776419", "GSM776420", "GSM776421", "GSM776422", "GSM776423", "GSM776424", "GSM776425", "GSM776426", "GSM776427", "GSM776428", "GSM776429", "GSM776430", "GSM776431", "GSM776432", "GSM776433", "GSM776434", "GSM776435", "GSM776436", "GSM776437", "GSM776438", "GSM776439", "GSM776440", "GSM776441", "GSM776442", "GSM776443", "GSM776444", "GSM776445", "GSM776446", "GSM776447", "GSM776448", "GSM776449", "GSM776450", "GSM776451", "GSM776452", "GSM776453", "GSM776454", "GSM776455", "GSM776456", "GSM776457", "GSM776458", "GSM776459", "GSM776460", "GSM776461", "GSM776462", "GSM776463", "GSM776464", "GSM776465", "GSM776466", "GSM776467", "GSM776468", "GSM776469", "GSM776470", "GSM776471", "GSM776472", "GSM776473", "GSM776474", "GSM776475", "GSM776476"], "sample_count": 498, "group_sizes": null, "group_sizes_basis": null, "platform": "570", "taxon": "Homo sapiens", "title": "Development and application of a new immunophenotypic algorithm for molecular subtype classification of Diffuse Large B-Cell Lymphoma (DLBCL): Report from an International DLBCL Rituximab-CHOP Consortium Program Study", "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:GSE32018", "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=GSE32018", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE32018", "version": null, "note": "All data were extracted from previously published freely available datasets.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "All data were extracted from previously published freely available datasets.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM793379", "GSM793380", "GSM793381", "GSM793382", "GSM793383", "GSM793384", "GSM793385", "GSM793386", "GSM793387", "GSM793388", "GSM793389", "GSM793390", "GSM793391", "GSM793392", "GSM793393", "GSM793394", "GSM793395", "GSM793396", "GSM793397", "GSM793398", "GSM793399", "GSM793400", "GSM793401", "GSM793402", "GSM793403", "GSM793404", "GSM793405", "GSM793406", "GSM793407", "GSM793408", "GSM793409", "GSM793410", "GSM793411", "GSM793412", "GSM793413", "GSM793414", "GSM793415", "GSM793416", "GSM793417", "GSM793418", "GSM793419", "GSM793420", "GSM793421", "GSM793422", "GSM793423", "GSM793424", "GSM793425", "GSM793426", "GSM793427", "GSM793428", "GSM793429", "GSM793430", "GSM793431", "GSM793432", "GSM793433", "GSM793434", "GSM793435", "GSM793436", "GSM793437", "GSM793438", "GSM793439", "GSM793440", "GSM793441", "GSM793442", "GSM793443", "GSM793444", "GSM793445", "GSM793446", "GSM793447", "GSM793448", "GSM793449", "GSM793450", "GSM793451", "GSM793452", "GSM793453", "GSM793454", "GSM793455", "GSM793456", "GSM793457", "GSM793458", "GSM793459", "GSM793460", "GSM793461", "GSM793462", "GSM793463", "GSM793464", "GSM793465", "GSM793466", "GSM793467", "GSM793468", "GSM793469", "GSM793470", "GSM793471", "GSM793472", "GSM793473", "GSM793474", "GSM793475", "GSM793476", "GSM793477", "GSM793478", "GSM793479", "GSM793480", "GSM793481", "GSM793482", "GSM793483", "GSM793484", "GSM793485", "GSM793486", "GSM793487", "GSM793488", "GSM793489", "GSM793490", "GSM793491", "GSM793492", "GSM793493", "GSM793494", "GSM793495", "GSM793496", "GSM793497", "GSM793498", "GSM793499", "GSM793500", "GSM793501", "GSM793502", "GSM793503", "GSM793504", "GSM793505"], "sample_count": 127, "group_sizes": null, "group_sizes_basis": null, "platform": "6480", "taxon": "Homo sapiens", "title": "Gene-expression profile in a series of  non-Hodgkin lymphoma (NHL) patients", "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:GSE56315", "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=GSE56315", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE56315", "version": null, "note": "All data were extracted from previously published freely available datasets.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "All data were extracted from previously published freely available datasets.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM1358939", "GSM1358940", "GSM1358941", "GSM1358942", "GSM1358943", "GSM1358944", "GSM1358945", "GSM1358946", "GSM1358947", "GSM1358948", "GSM1358949", "GSM1358950", "GSM1358951", "GSM1358952", "GSM1358953", "GSM1358954", "GSM1358955", "GSM1358958", "GSM1358959", "GSM1358960", "GSM1358962", "GSM1358963", "GSM1358966", "GSM1358969", "GSM1358972", "GSM1358975", "GSM1358976", "GSM1358977", "GSM1358980", "GSM1358982", "GSM1358983", "GSM1358984", "GSM1358985", "GSM1358986", "GSM1358987", "GSM1358988", "GSM1358989", "GSM1358992", "GSM1358994", "GSM1358995", "GSM1358996", "GSM1358997", "GSM1358998", "GSM1358999", "GSM1359000", "GSM1359001", "GSM1359002", "GSM1359003", "GSM1359004", "GSM1359005", "GSM1359006", "GSM1359007", "GSM1359008", "GSM1359009", "GSM1359018", "GSM1359028", "GSM1359029", "GSM1359030", "GSM1359031", "GSM1359032", "GSM1359033", "GSM1359034", "GSM1359035", "GSM1359036", "GSM1359037", "GSM1359038", "GSM1359039", "GSM1359040", "GSM1359041", "GSM1359042", "GSM1359043", "GSM1359044", "GSM1359045", "GSM1359046", "GSM1359047", "GSM1359048", "GSM1359049", "GSM1359050", "GSM1359051", "GSM1359052", "GSM1359053", "GSM1359054", "GSM1359055", "GSM1359056", "GSM1359057", "GSM1359058", "GSM1359059", "GSM1359060"], "sample_count": 88, "group_sizes": null, "group_sizes_basis": null, "platform": "570", "taxon": "Homo sapiens", "title": "Diffuse Large B-Cell Lymphoma Classification System That Associates Normal B-Cell Subset Phenotypes With Prognosis", "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:30393234:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:a3cc75fcdc6f68af5ee5c75555703baf640161c530b24b439b2a0235d66c3e6d", "bytes": 1462, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[11]/table-wrap[1]#T1", "version": null, "note": "GO analysis of DEGs associated with DLBCL", "structure": {"pmcid": "PMC6328866", "section_index": 11, "section_title": "Functional enrichment analysis of DEGs in DLBCL", "row_count": 25, "column_count": 4}, "table": {"label": "Table 1", "caption": "GO analysis of DEGs associated with DLBCL", "rows": [["Term", "Description", "Count", "P-value"], ["Up-regulated"], ["GO:0022403", "Cell cycle phase", "21", "2.69E-15"], ["GO:0000279", "M phase", "19", "9.84E-15"], ["GO:0000278", "Mitotic cell cycle", "19", "7.50E-14"], ["GO:0022402", "Cell cycle process", "22", "8.22E-14"], ["GO:0003777", "Microtubule motor activity", "5", "3.33E-04"], ["GO:0005524", "ATP binding", "17", "3.58E-04"], ["GO:0032559", "Adenyl ribonucleotide binding", "17", "4.17E-04"], ["GO:0001883", "Purine nucleoside binding", "17", "8.80E-04"], ["GO:0001882", "Nucleoside binding", "17", "9.49E-04"], ["GO:0005819", "Spindle", "14", "2.04E-14"], ["GO:0015630", "Microtubule cytoskeleton", "16", "3.56E-09"], ["GO:0000793", "Condensed chromosome", "9", "5.24E-08"], ["GO:0044430", "Cytoskeletal part", "17", "8.49E-07"], ["GO:0000776", "Kinetochore", "7", "7.19E-07"], ["GO:0005874", "Microtubule", "8", "1.28E-04"], ["Down-regulated"], ["GO:0006163", "Purine nucleotide metabolic process", "4", "0.023786"], ["GO:0008285", "Negative regulation of cell proliferation", "5", "0.031481"], ["GO:0051252", "Regulation of RNA metabolic process", "12", "0.032176"], ["GO:0006350", "Transcription", "13", "0.038040"], ["GO:0003700", "Transcription factor activity", "9", "0.022489"], ["GO:0003677", "DNA binding", "15", "0.032567"], ["GO:0030528", "Transcription regulator activity", "11", "0.041292"]], "row_count": 25, "column_count": 4, "numeric_cells": 66, "header_rows": 1, "locator": "section[11]/table-wrap[1]#T1"}}, {"id": "asset:table:pmid:30393234:2", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:6474e028d788c17a9e1484fd48469ea1a960b748fb500431b9fb18c4808565c0", "bytes": 1164, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[11]/table-wrap[2]#T2", "version": null, "note": "Signaling pathway enrichment analysis of DEGs associated with DLBCL", "structure": {"pmcid": "PMC6328866", "section_index": 11, "section_title": "Functional enrichment analysis of DEGs in DLBCL", "row_count": 11, "column_count": 5}, "table": {"label": "Table 2", "caption": "Signaling pathway enrichment analysis of DEGs associated with DLBCL", "rows": [["Pathway", "Name", "Gene count", "P-value", "Genes"], ["Up-regulated DEG", "", "", "", ""], ["REACTOME: REACT_152", "Cell cycle, mitotic", "16", "5.20E-08", "GINS1, KIF23, CDK1, SGOL2, DBF4, NUF2, CDC20, MCM10, KIF2C, CDCA8, MAD2L1, ZWINT, RRM2, PCNA, BUB1B, SKA1"], ["KEGG: hsa04110", "Cell cycle", "7", "2.36E-05", "CDK1, MAD2L1, DBF4, PCNA, BUB1B, TTK, CDC20"], ["REACTOME: REACT_1538", "Cell cycle checkpoints", "6", "0.004610", "CDK1, MAD2L1, DBF4, BUB1B, CDC20, MCM10"], ["KEGG: hsa04114", "Oocyte meiosis", "3", "0.010084", "CDK1, MAD2L1, CDC20"], ["REACTOME: REACT_8017", "APC-Cdc20-mediated degradation of Nek2A", "3", "0.021560", "MAD2L1, BUB1B, CDC20"], ["REACTOME: REACT_6850", "Cdc20:p-APC/C-mediated degradation of Cyclin A", "4", "0.027276", "CDK1, MAD2L1, BUB1B, CDC20"], ["KEGG: hsa00010", "Glycolysis/gluconeogenesis", "3", "0.034518", "LDHA, PGAM1, GAPDH"], ["Down-regulated DEG", "", "", "", ""], ["FUNRICH biological pathway", "EMT", "4", "0.007158", "PTGDS, FCER2, TPO, IL11RA"]], "row_count": 11, "column_count": 5, "numeric_cells": 32, "header_rows": 1, "locator": "section[11]/table-wrap[2]#T2"}}, {"id": "asset:table:pmid:30393234:3", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:ec7670667f649171bc599362b23311dde9ae47f7c0008a2270b461bb26b6a045", "bytes": 409, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[12]/table-wrap[1]#T3", "version": null, "note": "Pathway enrichment analysis of the most significant gene function modules", "structure": {"pmcid": "PMC6328866", "section_index": 12, "section_title": "Hub genes and pathway identification with PPI network and modular analysis", "row_count": 4, "column_count": 4}, "table": {"label": "Table 3", "caption": "Pathway enrichment analysis of the most significant gene function modules", "rows": [["Term", "Description", "Count", "P-value"], ["KEGG cfa04110", "Cell cycle", "7", "5.36E-09"], ["FUNRICH biological pathway", "EMT", "5", "0.007158"], ["KEGG cfa04114", "Oocyte meiosis", "3", "0.012116"]], "row_count": 4, "column_count": 4, "numeric_cells": 8, "header_rows": 1, "locator": "section[12]/table-wrap[1]#T3"}}, {"id": "asset:table:pmid:30393234:4", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:67e9d2aaed6eb88363ee7ab4f23436afea1c61270dd8b3d9088e97fc1b91d39a", "bytes": 485, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[13]/table-wrap[1]#T4", "version": null, "note": "AUC of the six hub genes based on the GSE56315 dataset", "structure": {"pmcid": "PMC6328866", "section_index": 13, "section_title": "Validation of the diagnostic effectiveness of the six hub genes using GSE56315", "row_count": 7, "column_count": 4}, "table": {"label": "Table 4", "caption": "AUC of the six hub genes based on the GSE56315 dataset", "rows": [["Gene", "AUC", "95% CI", "P-value"], ["CDC20", "0.999", "0.997–1.000", "<0.01"], ["MELK", "0.895", "0.832–0.958", "<0.001"], ["PBK", "0.786", "0.676–0.896", "<0.001"], ["PTGDS", "1.000", "1.000–1.000", "<0.01"], ["PCNA", "0.995", "0.987–1.000", "<0.01"], ["CDK1", "0.861", "0.784–0.939", "<0.01"]], "row_count": 7, "column_count": 4, "numeric_cells": 20, "header_rows": 1, "locator": "section[13]/table-wrap[1]#T4"}}], "gaps": ["asset:data:geo:GSE31312 not downloaded", "asset:data:geo:GSE31312 licence not read", "asset:data:geo:GSE32018 not downloaded", "asset:data:geo:GSE32018 licence not read", "asset:data:geo:GSE56315 not downloaded", "asset:data:geo:GSE56315 licence not read"]}, "analysis": {"state": "partial", "methods": [{"id": "method-1", "family": "network_analysis", "specific": "ppi_network", "label": "Network / pathway analysis", "dsl_operations": ["build_graph", "centrality_scores", "pathway_enrich"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["edge_list"], "evidence": {"score": 0.7, "band": "medium", "quote": "protein-protein interaction"}}, {"id": "method-2", "family": "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"}}, {"id": "method-3", "family": "diagnostic_evaluation", "specific": "roc", "label": "Diagnostic test evaluation", "dsl_operations": ["confusion_counts", "roc_curve", "sensitivity_specificity", "solve_confusion_matrix", "classification_metrics", "published_precision_envelope"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["reference_standard_and_test"], "evidence": {"score": 0.8, "band": "high", "quote": "ROC analysis"}}, {"id": "method-4", "family": null, "specific": null, "label": "receiver operating characteristic (ROC) curve", "dsl_operations": [], "missing_operations": [], "expressible": null, "parameters": {}, "data_shapes": [], "evidence": {"score": 1.0, "band": "verbatim", "quote": "The receiver operating characteristic (ROC) curve was used to assess the diagnostic effectiveness of the identified hub genes between DLBCL and normal tissue, and was based on the GSE56315 dataset."}}], "targets": [], "gaps": ["method.reader_named_unmapped"]}, "capability": {"state": "complete", "requirements": [{"capability_id": "capability:computational_analysis", "label": "Computational analysis platform", "assay_families": ["meta_analysis", "machine_learning", "survival_analysis", "statistical_regression", "pca", "molecular_docking", "network_analysis", "differential_expression", "gwas"], "availability_state": "owned", "tier_unlocked": "R1", "candidate": "Automated Assays Laravel application and simulated adapters"}], "gaps": []}, "readiness": {"state": "complete", "tier": "R1", "blocking_axis": "none", "blocked_on": "nothing:replicable_now", "axes": {"method": {"tier": "R1", "expressible": true, "required_operations": ["build_graph", "centrality_scores", "pathway_enrich"], "missing_operations": [], "basis": "The paper names the method it used and the corpus's method extractor maps it onto the DSL catalogue: ppi_network."}, "capability": {"tier": "R1", "capability_id": "capability:computational_analysis", "availability_state": "owned", "basis": "The computational analysis is owned. The physical bench the paper used is not, so a physical validation cannot be run here."}, "data": {"tier": "R1", "reachable": true, "accessions": ["GSE32018", "GSE56315", "GSE31312"], "resolved_accessions": ["GSE32018", "GSE56315", "GSE31312"], "statements": ["All data were extracted from previously published freely available datasets."], "basis": "The paper names GSE32018, GSE56315, GSE31312 in NCBI 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:30393234", "data:geo:GSE31312", "asset:table:pmid:30393234:1", "asset:table:pmid:30393234:2", "asset:table:pmid:30393234:3", "asset:table:pmid:30393234:4"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE31312"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-10-31T18:12:53Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 3, "usage": {"prompt_tokens": 29950, "completion_tokens": 2403, "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:30393234", "type": "paper", "label": "pmid:30393234"}, {"id": "source:pmid:30393234", "type": "manuscript", "label": "PMID 30393234 full text"}, {"id": "data:geo:GSE31312", "type": "dataset", "label": "GEO GSE31312"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:30393234", "type": "paper", "label": "pmid:30393234"}, {"id": "source:pmid:30393234", "type": "manuscript", "label": "PMID 30393234 full text"}, {"id": "data:geo:GSE31312", "type": "dataset", "label": "GEO GSE31312"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-30393234", "type": "extraction", "used": ["source:pmid:30393234"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE31312", "type": "accession_resolution", "used": ["data:geo:GSE31312"], "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:30393234", "parent_hash": "sha256:a43da0f6720aec6ea4c8901fd54c9b02cde2d42cabbd4cd40ea2c4f12000b12b", "fork_of": null, "generation": 6}, "gaps": ["asset:data:geo:GSE31312 licence not read", "asset:data:geo:GSE31312 not downloaded", "asset:data:geo:GSE32018 licence not read", "asset:data:geo:GSE32018 not downloaded", "asset:data:geo:GSE56315 licence not read", "asset:data:geo:GSE56315 not downloaded", "execution.not_run", "method.reader_named_unmapped", "review.human_critique", "review.independent_reader", "review.machine_critique"], "assays": [{"role": "data_generation", "definition_id": "rna_seq", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.93, "evidence": ["d PTGDS methylation and OS in DLBCL patients RNA-seq and Illumina 450 K methylation array dataset"], "order_basis": "paper_text_order:2879", "id": "assay:1"}, {"role": "data_generation", "definition_id": "methylation_array", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.93, "evidence": ["in DLBCL patients RNA-seq and Illumina 450 K methylation array datasets were downloaded using the UCSC Xena"], "order_basis": "paper_text_order:2906", "id": "assay:2"}, {"role": "analysis", "definition_id": "network_analysis", "definition_version": "f2132e96ae6c7a4e", "definition_digest": null, "required_operations": ["build_graph", "centrality_scores", "pathway_enrich"], "support_state": "supported", "source_hashes": {"dsl_catalogue": "f2132e96ae6c7a4e"}, "confidence": 0.7, "evidence": ["protein-protein interaction"], "order_basis": "consumes_earlier_output", "id": "assay: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":"2026-11-04T00:40:39+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}}}