{"data":{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:32547947", "kind": "science-record", "revision": 8, "content_hash": "sha256:83486387bb6293a6313cae2d06f890ba14c496259ac85707f2aaf89338d9cdc6", "created_at": "2026-11-01T15:41:03Z", "updated_at": "2026-11-01T22:44:58Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Identification of Potential Key Genes for Pathogenesis and Prognosis in Prostate Cancer by Integrated Analysis of Gene Expression Profiles and the Cancer Genome Atlas.", "doi": "10.3389/fonc.2020.00809", "pmid": "32547947", "authors": ["Shuang Liu", "Wenxin Wang", "Yan Zhao", "Kaige Liang", "Yaojiang Huang"], "journal": "Frontiers in oncology", "year": 2020, "abstract": "Background: Prostate cancer (PCa)is a malignancy of the urinary system with a high incidence, which is the second most common male cancer in the world. There are still huge challenges in the treatment of prostate cancer. It is urgent to screen out potential key biomarkers for the pathogenesis and prognosis of PCa. Methods: Multiple gene differential expression profile datasets of PCa tissues and normal prostate tissues were integrated analysis by R software. Gene Ontology (GO) and Kyoto Encyclopedia of Genes and Genomes (KEGG) pathway analysis of the overlapping Differentially Expressed Genes (DEG) were performed. The STRING online database was used in conjunction with Cytospace software for protein-protein interaction (PPI) network analysis to define hub genes. The relative mRNA expression of hub genes was detected in Gene Expression Profiling Interactive Analysis (GEPIA) database. A prognostic gene signature was identified by Univariate and multivariate Cox regression analysis. Results: Three hundred twelve up-regulated genes and 85 down-regulated genes were identified from three gene expression profiles (GSE69223, GSE3325, GSE55945) and The Cancer Genome Atlas Prostate Adenocarcinoma (TCGA-PRAD) dataset. Seven hub genes (FGF2, FLNA, FLNC, VCL, CAV1, ACTC1, and MYLK) further were detected, which related to the pathogenesis of PCa. Seven prognostic genes (BCO1, BAIAP2L2, C7, AP000844.2, ASB9, MKI67P1, and TMEM272) were screened to construct a prognostic gene signature, which shows good predictive power for survival by the ROC curve analysis. Conclusions: We identified a robust set of new potential key genes in PCa, which would provide reliable biomarkers for early diagnosis and prognosis and would promote molecular targeting therapy for PCa.", "claims": [{"id": "claim-method", "statement": "The DEGs of PCa and normal tissues were detected by limma package of R software (5), P-Val < 0.05 and absolute logFC > 1. Using edgeR package of R software to normalize TCGA datasets and screen DEGs (6), P-Val < 0.05 and absolute logFC >1.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:32547947", "locator": "sections[4] \"Data Preprocessing and Differentially Expressed Genes (DEGs) Screening\" paragraph 2", "quote": "The DEGs of PCa and normal tissues were detected by limma package of R software (5), P-Val < 0.05 and absolute logFC > 1. Using edgeR package of R software to normalize TCGA datasets and screen DEGs (6), P-Val < 0.05 and absolute logFC >1."}], "state": "complete"}, {"id": "claim-data-access", "statement": "Publicly available datasets were analyzed in this study. This data can be found here: http://www.ncbi.nlm.nih.gov/geo/ and http://cancergenome.nih.gov/.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:32547947", "locator": "sections[17] \"Data Availability Statement\" paragraph 2", "quote": "Publicly available datasets were analyzed in this study. This data can be found here: http://www.ncbi.nlm.nih.gov/geo/ and http://cancergenome.nih.gov/."}], "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:32547947"], "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:GSE3325"], "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:GSE3325"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:32547947", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.3389/fonc.2020.00809", "sha256": "sha256:17f80bc48c379fa3da6ec95e9f9e887cf1201e9ddbd66909f1b838c809939eb1", "bytes": 30650, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.3389/fonc.2020.00809", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC7277826", "source": "europe_pmc_fulltext", "coverage": "whole_body_without_references", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE3325", "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=GSE3325", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE3325", "version": null, "note": "Publicly available datasets were analyzed in this study. This data can be found here: http://www.ncbi.nlm.nih.gov/geo/ and http://cancergenome.nih.gov/.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "Publicly available datasets were analyzed in this study. This data can be found here: http://www.ncbi.nlm.nih.gov/geo/ and http://cancergenome.nih.gov/.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM74875", "GSM74876", "GSM74877", "GSM74878", "GSM74879", "GSM74880", "GSM74881", "GSM74882", "GSM74883", "GSM74884", "GSM74885", "GSM74886", "GSM74887", "GSM74888", "GSM74889", "GSM74890", "GSM74891", "GSM74892", "GSM74893"], "sample_count": 19, "group_sizes": null, "group_sizes_basis": null, "platform": "570", "taxon": "Homo sapiens", "title": "Integrative Genomic and Proteomic Analysis of Prostate Cancer Reveals Signatures of Metastatic Progression", "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:GSE55945", "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=GSE55945", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE55945", "version": null, "note": "Publicly available datasets were analyzed in this study. This data can be found here: http://www.ncbi.nlm.nih.gov/geo/ and http://cancergenome.nih.gov/.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "Publicly available datasets were analyzed in this study. This data can be found here: http://www.ncbi.nlm.nih.gov/geo/ and http://cancergenome.nih.gov/.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM1348933", "GSM1348934", "GSM1348935", "GSM1348936", "GSM1348937", "GSM1348938", "GSM1348939", "GSM1348940", "GSM1348941", "GSM1348942", "GSM1348943", "GSM1348944", "GSM1348945", "GSM1348946", "GSM1348947", "GSM1348948", "GSM1348949", "GSM1348950", "GSM1348951", "GSM1348952", "GSM1348953"], "sample_count": 21, "group_sizes": null, "group_sizes_basis": null, "platform": "570", "taxon": "Homo sapiens", "title": "Gene Expression Profiling of Prostate Benign and Malignant Tissue", "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:GSE69223", "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=GSE69223", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE69223", "version": null, "note": "Publicly available datasets were analyzed in this study. This data can be found here: http://www.ncbi.nlm.nih.gov/geo/ and http://cancergenome.nih.gov/.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "Publicly available datasets were analyzed in this study. This data can be found here: http://www.ncbi.nlm.nih.gov/geo/ and http://cancergenome.nih.gov/.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM1695583", "GSM1695584", "GSM1695585", "GSM1695586", "GSM1695587", "GSM1695588", "GSM1695589", "GSM1695590", "GSM1695591", "GSM1695592", "GSM1695593", "GSM1695594", "GSM1695595", "GSM1695596", "GSM1695597", "GSM1695598", "GSM1695599", "GSM1695600", "GSM1695601", "GSM1695602", "GSM1695603", "GSM1695604", "GSM1695605", "GSM1695606", "GSM1695607", "GSM1695608", "GSM1695609", "GSM1695610", "GSM1695611", "GSM1695612"], "sample_count": 30, "group_sizes": null, "group_sizes_basis": null, "platform": "570", "taxon": "Homo sapiens", "title": "Genome-wide analysis of gene expression patterns in human prostate cancer (PCa)", "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:32547947:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:699e88bf38a7e466d27c6f849c5ced9156191ba609665fac6cc3913a7472d834", "bytes": 954, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[14]/table-wrap[1]#T4", "version": null, "note": "Prognostic value of the seven genes in the PCa patients of the TCGA cohort.", "structure": {"pmcid": "PMC7277826", "section_index": 8, "section_title": "Survival Analysis", "row_count": 9, "column_count": 6}, "table": {"label": "Table 4", "caption": "Prognostic value of the seven genes in the PCa patients of the TCGA cohort.", "rows": [["Gene symbol", "Univariate analysis", "Multivariate analysis", ""], ["", "Hazard ratio (95% CI)", "p-value", "Hazard ratio (95% CI)", "p-value", "Coefficient"], ["BCO1", "2.619(1.438–4.768)", "0.002", "1.023(1.006–1.040)", "0.007", "0.022"], ["BAIAP2L2", "1.644(1.187–2.278)", "0.003", "0.999 (0.997–1.000)", "0.037", "−0.002"], ["C7", "0.657(0.491–0.879)", "0.005", "0.999 (0.999–1.000)", "0.074", "−0.001"], ["AP000844.2", "1.743(1.2151–2.499)", "0.003", "1.004 (1.002–1.004)", "<0.001", "0.004"], ["ASB9", "1.828(1.315–2.541)", "<0.001", "1.002(1.002–1.006)", "0.039", "0.001"], ["MKI67P1", "5.033(1.977–12.804)", "0.001", "2.288(1.307–4.005)", "0.004", "0.828"], ["TMEM272", "2.545(1.479–4.380)", "0.001", "1.05(0.989–1.123)", "0.106", "0.053"]], "row_count": 9, "column_count": 6, "numeric_cells": 40, "header_rows": 2, "locator": "section[14]/table-wrap[1]#T4"}}, {"id": "asset:table:pmid:32547947:2", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:ecffca0d05f7bc68e3513e921ca318777161762c3776ee70f5bd45244fcd7df2", "bytes": 565, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[10]/table-wrap[1]#T1", "version": null, "note": "Information of the three GEO datasets.", "structure": {"pmcid": "PMC7277826", "section_index": 10, "section_title": "Results", "row_count": 4, "column_count": 5}, "table": {"label": "Table 1", "caption": "Information of the three GEO datasets.", "rows": [["Dataset", "References", "Platform", "Tumor", "Normal"], ["GSE69223", "Meller et al. (17)", "[HG-U133_Plus_2] Affymetrix Human Genome U133 Plus 2.0 Array", "15", "15"], ["GSE3325", "Varambally et al. (18)", "[HG-U133_Plus_2] Affymetrix Human Genome U133 Plus 2.0 Array", "13", "6"], ["GSE55945", "Arredouani et al. (19)", "[HG-U133_Plus_2] Affymetrix Human Genome U133 Plus 2.0 Array", "13", "8"]], "row_count": 4, "column_count": 5, "numeric_cells": 15, "header_rows": 1, "locator": "section[10]/table-wrap[1]#T1"}}, {"id": "asset:table:pmid:32547947:3", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:936f484349a622a08013e47e884952a52d95f6bc34eff037803a99fd58fcb1c3", "bytes": 859, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[10]/table-wrap[2]#T2", "version": null, "note": "The overlapping upregulated DEGs between GSE69223, GSE3325, GSE55945, and TCGA PRAD dataset.", "structure": {"pmcid": "PMC7277826", "section_index": 10, "section_title": "Results", "row_count": 11, "column_count": 1}, "table": {"label": "Table 2", "caption": "The overlapping upregulated DEGs between GSE69223, GSE3325, GSE55945, and TCGA PRAD dataset.", "rows": [["Upregulated DEGs names"], ["HPN,FRMPD3,FOXD3-AS1,DNAH5,PYCR1,POPDC3,DBNDD1,PCA3,DUS1L,"], ["STX19,DLX1, HOXC4,HOXC6,ELL3,HIST1,H2AM,SMIM22,MARCKSL1,"], ["SLC7A11,APOF,RAB17,LUZP2,CGREF1,SIM2,EPCAM,TLCD1,TDRD1,FEV,"], ["OR51E2,MS4A8,FAM222A,TGM3,AMACR,MELK,NEK5,ACSM1,THBS4,B3GAT1,"], ["DLX6-AS1,GCNT1,ADAM2,GDF15,TRPM4,FOXD1,PPM1E,NKAIN1,PRAC1,"], ["TWIST1,BICD1,CTHRC1,GJB1,FFAR2,ZIC2,ATP8A2,PCAT18,TMEM178A,"], ["ELAVL2,KCNH8,PTPRT,VSTM2L,HMMR,HIST1H2AE,MYO6,GPR160,"], ["TOX3,BUB1B,INSM1,C12orf56,MMP26,RRM2,NETO2,EZH2,SDK1,TFF3,ERG,"], ["C15orf48,TMEM45B,PLA2G7,FOLH1B,ABCC4,COL2A1,DNASE2B,PRR16,"], ["FABP5,MIPEP,OR51E1"]], "row_count": 11, "column_count": 1, "numeric_cells": 9, "header_rows": 1, "locator": "section[10]/table-wrap[2]#T2"}}, {"id": "asset:table:pmid:32547947:4", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:b86cc175f0d66e4e781c41d43b4f5e84677d3783cbdf78cb0605b18d6344728b", "bytes": 2387, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[10]/table-wrap[3]#T3", "version": null, "note": "The overlapping downregulated DEGs between GSE69223, GSE3325, GSE55945, and TCGA PRAD dataset.", "structure": {"pmcid": "PMC7277826", "section_index": 10, "section_title": "Results", "row_count": 34, "column_count": 1}, "table": {"label": "Table 3", "caption": "The overlapping downregulated DEGs between GSE69223, GSE3325, GSE55945, and TCGA PRAD dataset.", "rows": [["Downregulated DEGs names"], ["TSLP,NUDT10,KCNJ3,FAT4,RAB40A,SBSPON,CCND2,GLIS3,ITIH5,RBMS3,"], ["KCNAB1,ATRNL1,HOXD13,SPOCK3,NRK,SLC8A1,TBX4,SPON1,JAZF1,SGCB,"], ["C1QTNF7,TWIST2,AFAP1L2,ANGPTL1,RNF180,HS3ST3A1,PLAC9,DAAM2,"], ["SNAI2,NELL2COL4A6,C2orf88,VCL,CFD,ME1,NHS,SEMA5A,AJUBA,OLFML1,"], ["CCDC8,PEG3,MAMDC2,ANGPT1,RBP4,FAM162B,C8orf88,RNF175,FBXO17,"], ["FERMT2,MAP1B,PLCL1,TRPC1,ANO5,TIMP3,PENK,ASPA,FXYD6,CLIC6,"], ["CCDC136,GSTM5,NT5E,C5orf34,EDNRB,PTGS1,LINGO2,PHYHIP,NDNF,FGF2,"], ["ZNF516,DKK3,CLIP4,BMP5,CCDC80,PCDH9,DCN,LPAR1,SLMAP,PRICKLE2,"], ["TPM2,MSRB3,SRD5A2,EID3,RNF112,ADAMTS5,ITGB1BP2,PALLD,CLU,"], ["GPM6B,MAMLD1,CAV2,LRRN3,TRIM6,PCDH10,ITGA1,RASL12,TSHZ3,"], ["DAB1,RND3,LGR6,EFEMP1,DUOXA1,LMOD1,TCEAL2,PTGIS,ZNF423,GSTM3,"], ["TCF7L1,ID4,FZD7,SCARA3,CAV1,SCN7A,SGCA,MYLK,TMEM200B,ACSS3,"], ["HCG11,RAB9B,SMOC1,RGS7BP,AHNAK2,TIMP4,ATP1A2,SLC2A5,DNAJB4,"], ["TSPAN18,S100A6,FBXL22,ST8SIA1,DZIP1,CDC42EP3,LINC01082,VWA5A,"], ["MLC1,RGS9,MXRA7,PTGER2,PNMA1,NDP,PLBD1,TGFBR3,TBX5,FHOD3,"], ["STARD4,FRMD6,PGM5,HLF,POPDC2,STAC,GSTM1,EFEMP2,MBNL1AS1,"], ["MYOCD,RBFOX3,FAM107A,CFL2,DNAJB5,BDNF,AOX1,ANO4,EPHA7,SLC14A1,"], ["RBPMS2,SYNC,SLC16A5,FLNA,DDR2,C3orf70,INMT,MRVI1,DOCK3,"], ["PPP1R14A,CCDC69,HSPB8,PPP1R1A,TMEM47,DPT,GPR87,TCEAL7,SGCG,"], ["SNX7,KLHL13,TRHDE,CYP3A5,GJA1,MAL,WFDC1,FLNC,B3GALT2,FOXF2,"], ["RRAS,CPNE5,MEIS1,CXCL13,PABPC4L,IGSF1,FILIP1L,MYOF,EPB41L3,"], ["GPRASP1,VIT,PDGFC,C2orf40,DSC3,C12orf75,EPHA2,GPX8,SLC24A3,"], ["CD200,C7,CRYAB,ZNF204P,SLC47A1,SCGB3A1,EPHB1,RCAN2,FHL1,ASB2,"], ["SLITRK6,CHRDL1,BCL11A,IL33,PRIMA1,GATA3,NEXN,SNHG18,PPP1R3C,"], ["LSAMP,UBXN10AS1,TMEM158,TENM2,PTGDS,FOXQ1,GPM6A,FOXF1,TGFB1I1,"], ["ACOX2,PARM1,HOXD10,RGN,KRT23,SYNDIG1,PGMAS1,WIF1,HSPB6,KCNJ8,"], ["HSPB3,EFS,PRTFDC1,SCGB1A1,AOC3,GSTP1,ZNF536,EDNRA,MIR100HG,"], ["SOWAHA,GSTM2,NSG1,MYH11,ROR2,SMR3B,NEURL1B,LINC00844,"], ["TMEM100,ID3,ACTC1,LAMB3,OGN,MYL9,LRCH2,IER3,SERPINF1,SYNPO2,"], ["DDIT4L,KIAA1210,PLN,PDZRN4,HSD11B1,IGDCC4,MEIS2,PYGM,PLA2G4A,"], ["DKK1,IP6K3,SMTNL2,SLC18A2,KRT14,CNN1,MYH6,JAKMIP1,CCK,ID1,"], ["KRT5,FLRT3,MME,SNX31,CYP4B1,LINC00261,MIR205HG,SLC39A2,UPK1A,"], ["BEX1,PTGS2,KRT13,TRG-AS1,TGM4,CD177,NEFH,SERPINB11"]], "row_count": 34, "column_count": 1, "numeric_cells": 30, "header_rows": 1, "locator": "section[10]/table-wrap[3]#T3"}}, {"id": "asset:table:pmid:32547947:5", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:699e88bf38a7e466d27c6f849c5ced9156191ba609665fac6cc3913a7472d834", "bytes": 954, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[14]/table-wrap[1]#T4", "version": null, "note": "Prognostic value of the seven genes in the PCa patients of the TCGA cohort.", "structure": {"pmcid": "PMC7277826", "section_index": 14, "section_title": "Survival Analysis", "row_count": 9, "column_count": 6}, "table": {"label": "Table 4", "caption": "Prognostic value of the seven genes in the PCa patients of the TCGA cohort.", "rows": [["Gene symbol", "Univariate analysis", "Multivariate analysis", ""], ["", "Hazard ratio (95% CI)", "p-value", "Hazard ratio (95% CI)", "p-value", "Coefficient"], ["BCO1", "2.619(1.438–4.768)", "0.002", "1.023(1.006–1.040)", "0.007", "0.022"], ["BAIAP2L2", "1.644(1.187–2.278)", "0.003", "0.999 (0.997–1.000)", "0.037", "−0.002"], ["C7", "0.657(0.491–0.879)", "0.005", "0.999 (0.999–1.000)", "0.074", "−0.001"], ["AP000844.2", "1.743(1.2151–2.499)", "0.003", "1.004 (1.002–1.004)", "<0.001", "0.004"], ["ASB9", "1.828(1.315–2.541)", "<0.001", "1.002(1.002–1.006)", "0.039", "0.001"], ["MKI67P1", "5.033(1.977–12.804)", "0.001", "2.288(1.307–4.005)", "0.004", "0.828"], ["TMEM272", "2.545(1.479–4.380)", "0.001", "1.05(0.989–1.123)", "0.106", "0.053"]], "row_count": 9, "column_count": 6, "numeric_cells": 40, "header_rows": 2, "locator": "section[14]/table-wrap[1]#T4"}}], "gaps": ["asset:data:geo:GSE3325 not downloaded", "asset:data:geo:GSE3325 licence not read", "asset:data:geo:GSE55945 not downloaded", "asset:data:geo:GSE55945 licence not read", "asset:data:geo:GSE69223 not downloaded", "asset:data:geo:GSE69223 licence not read"]}, "analysis": {"state": "partial", "methods": [{"id": "method-1", "family": "differential_expression", "specific": "edger", "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": 1.0, "band": "verbatim", "quote": "The DEGs of PCa and normal tissues were detected by limma package of R software (5), P-Val < 0.05 and absolute logFC > 1. Using edgeR package of R software to normalize TCGA datasets and screen DEGs (6), P-Val < 0.05 and absolute logFC >1."}}, {"id": "method-2", "family": "survival_analysis", "specific": "cox_proportional_hazards", "label": "Survival analysis", "dsl_operations": ["cox_ph"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["time_to_event_with_censoring"], "evidence": {"score": 0.7, "band": "medium", "quote": "Cox regression"}}, {"id": "method-3", "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": 0.8, "band": "high", "quote": "limma"}}, {"id": "method-4", "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-5", "family": "network_analysis", "specific": "pathway_enrichment", "label": "Network / pathway analysis", "dsl_operations": ["pathway_enrich"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["edge_list"], "evidence": {"score": 0.8, "band": "high", "quote": "GO enrichment"}}, {"id": "method-6", "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": 0.7, "band": "medium", "quote": "ROC curve"}}], "targets": [], "gaps": ["method.reader_differs_from_extractor"]}, "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: edger."}, "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": ["GSE69223", "GSE3325", "GSE55945"], "resolved_accessions": ["GSE69223", "GSE3325", "GSE55945"], "statements": ["Publicly available datasets were analyzed in this study. This data can be found here: http://www.ncbi.nlm.nih.gov/geo/ and http://cancergenome.nih.gov/."], "basis": "The paper names GSE69223, GSE3325, GSE55945 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:32547947", "data:geo:GSE3325", "asset:table:pmid:32547947:1", "asset:table:pmid:32547947:2", "asset:table:pmid:32547947:3", "asset:table:pmid:32547947:4", "asset:table:pmid:32547947:5"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE3325"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-10-31T18:20:22Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 3, "usage": {"prompt_tokens": 22347, "completion_tokens": 1146, "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:32547947", "type": "paper", "label": "pmid:32547947"}, {"id": "source:pmid:32547947", "type": "manuscript", "label": "PMID 32547947 full text"}, {"id": "data:geo:GSE3325", "type": "dataset", "label": "GEO GSE3325"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:32547947", "type": "paper", "label": "pmid:32547947"}, {"id": "source:pmid:32547947", "type": "manuscript", "label": "PMID 32547947 full text"}, {"id": "data:geo:GSE3325", "type": "dataset", "label": "GEO GSE3325"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-32547947", "type": "extraction", "used": ["source:pmid:32547947"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE3325", "type": "accession_resolution", "used": ["data:geo:GSE3325"], "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:32547947", "parent_hash": "sha256:dc36b26c316c2eb31f1bf7788094d88b242e5afe68d7280bf05436517c919470", "fork_of": null, "generation": 7}, "gaps": ["asset:data:geo:GSE3325 licence not read", "asset:data:geo:GSE3325 not downloaded", "asset:data:geo:GSE55945 licence not read", "asset:data:geo:GSE55945 not downloaded", "asset:data:geo:GSE69223 licence not read", "asset:data:geo:GSE69223 not downloaded", "execution.not_run", "method.reader_differs_from_extractor", "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": 1.0, "evidence": ["The DEGs of PCa and normal tissues were detected by limma package of R software (5), P-Val < 0.05 and absolute logFC > 1. Using edgeR package of R software to normalize TCGA datasets and screen DEGs (6), P-Val < 0.05 and absolute logFC >1."], "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":"2026-11-04T03:48:53+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}}}