{"data":{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:34123594", "kind": "science-record", "revision": 7, "content_hash": "sha256:7e8e15e5aa1ad6c45d459b7a5740d65de6b42208a1f021b629b5937e2e69fb4e", "created_at": "2026-11-01T15:41:38Z", "updated_at": "2026-11-01T22:03:57Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Identification of potential gene signatures associated with osteosarcoma by integrated bioinformatics analysis.", "doi": "10.7717/peerj.11496", "pmid": "34123594", "authors": ["Yutao Jia", "Yang Liu", "Zhihua Han", "Rong Tian"], "journal": "PeerJ", "year": 2021, "abstract": "BACKGROUND: Osteosarcoma (OS) is the most primary malignant bone cancer in children and adolescents with a high mortality rate. This work aims to screen novel potential gene signatures associated with OS by integrated microarray analysis of the Gene Expression Omnibus (GEO) database.\nMATERIAL AND METHODS: The OS microarray datasets were searched and downloaded from GEO database to identify differentially expressed genes (DEGs) between OS and normal samples. Afterwards, the functional enrichment analysis, protein-protein interaction (PPI) network analysis and transcription factor (TF)-target gene regulatory network were applied to uncover the biological function of DEGs. Finally, two published OS datasets (GSE39262 and GSE126209) were obtained from GEO database for evaluating the expression level and diagnostic values of key genes.\nRESULTS: In total 1,059 DEGs (569 up-regulated DEGs and 490 down-regulated DEGs) between OS and normal samples were screened. Functional analysis showed that these DEGs were markedly enriched in 214 GO terms and 54 KEGG pathways such as pathways in cancer. Five genes (CAMP, METTL7A, TCN1, LTF and CXCL12) acted as hub genes in PPI network. Besides, METTL7A, CYP4F3, TCN1, LTF and NETO2 were key genes in TF-gene network. Moreover, Pax-6 regulated four key genes (TCN1, CYP4F3, NETO2 and CXCL12). The expression levels of four genes (METTL7A, TCN1, CXCL12 and NETO2) in GSE39262 set were consistent with our integration analysis. The expression levels of two genes (CXCL12 and NETO2) in GSE126209 set were consistent with our integration analysis. ROC analysis of GSE39262 set revealed that CYP4F3, CXCL12, METTL7A, TCN1 and NETO2 had good diagnostic values for OS patients. ROC analysis of GSE126209 set revealed that CXCL12, METTL7A, TCN1 and NETO2 had good diagnostic values for OS patients.", "claims": [{"id": "claim-method", "statement": "Subsequently, MetaMA (https://cran.r-project.org/web/packages/metaMA/), an R package, was used to combine data from four GEO datasets.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:34123594", "locator": "sections[4] \"Data pre-processing and DEGs identification\" paragraph 2", "quote": "Subsequently, MetaMA (https://cran.r-project.org/web/packages/metaMA/), an R package, was used to combine data from four GEO datasets."}], "state": "complete"}, {"id": "claim-data-access", "statement": "The following information was supplied regarding data availability:The data is available at NCBI GEO: GSE12865, GSE19276, GSE87624, GSE99671, GSE39262, and GSE126209.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:34123594", "locator": "sections[21] \"Data Availability\" paragraph 2", "quote": "The following information was supplied regarding data availability:The data is available at NCBI GEO: GSE12865, GSE19276, GSE87624, GSE99671, GSE39262, and GSE126209."}], "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:34123594"], "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:GSE12865"], "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:GSE12865"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:34123594", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.7717/peerj.11496", "sha256": "sha256:e0342019cff475247828b761e80fd4add71f9f71f98e09b6edfab54816bc2307", "bytes": 38550, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.7717/peerj.11496", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC8164836", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE12865", "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=GSE12865", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE12865", "version": null, "note": "The following information was supplied regarding data availability:The data is available at NCBI GEO: GSE12865, GSE19276, GSE87624, GSE99671, GSE39262, and GSE126209.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The following information was supplied regarding data availability:The data is available at NCBI GEO: GSE12865, GSE19276, GSE87624, GSE99671, GSE39262, and GSE126209.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM288005", "GSM288006", "GSM322691", "GSM322692", "GSM322693", "GSM322694", "GSM322695", "GSM322696", "GSM322697", "GSM322698", "GSM322699", "GSM322700", "GSM322701", "GSM322702"], "sample_count": 14, "group_sizes": null, "group_sizes_basis": null, "platform": "6244", "taxon": "Homo sapiens", "title": "Gene expression of human paediatric osteosarcoma tumour samples relative to normal human osteoblasts", "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:GSE19276", "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=GSE19276", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE19276", "version": null, "note": "The following information was supplied regarding data availability:The data is available at NCBI GEO: GSE12865, GSE19276, GSE87624, GSE99671, GSE39262, and GSE126209.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The following information was supplied regarding data availability:The data is available at NCBI GEO: GSE12865, GSE19276, GSE87624, GSE99671, GSE39262, and GSE126209.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM481071", "GSM481072", "GSM481073", "GSM481074", "GSM481075", "GSM481076", "GSM481077", "GSM481078", "GSM481079", "GSM481080", "GSM481081", "GSM481082", "GSM481083", "GSM481084", "GSM481085", "GSM481086", "GSM481087", "GSM481088", "GSM481089", "GSM481090", "GSM481091", "GSM481092", "GSM481093", "GSM481094", "GSM481095", "GSM481096", "GSM481097", "GSM481098", "GSM481099", "GSM481100", "GSM481101", "GSM481102", "GSM481103", "GSM481104", "GSM481105", "GSM481106", "GSM481107", "GSM481108", "GSM481109", "GSM481110", "GSM481111", "GSM481112", "GSM481113", "GSM481114", "GSM481115", "GSM481116", "GSM481117", "GSM481118", "GSM481119"], "sample_count": 49, "group_sizes": null, "group_sizes_basis": null, "platform": "6848", "taxon": "Homo sapiens", "title": "Osteosarcoma is characterized by impaired osteoclastogenesis and antigen presentation compared to normal bone", "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:GSE39262", "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=GSE39262", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE39262", "version": null, "note": "The following information was supplied regarding data availability:The data is available at NCBI GEO: GSE12865, GSE19276, GSE87624, GSE99671, GSE39262, and GSE126209.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The following information was supplied regarding data availability:The data is available at NCBI GEO: GSE12865, GSE19276, GSE87624, GSE99671, GSE39262, and GSE126209.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM958993", "GSM958994", "GSM958995", "GSM958996", "GSM958997", "GSM958998", "GSM958999", "GSM959000", "GSM959001", "GSM959002", "GSM959003", "GSM959004", "GSM959005", "GSM959006", "GSM959007", "GSM959008", "GSM959009", "GSM959010", "GSM959011", "GSM959012", "GSM959013", "GSM959014", "GSM959015", "GSM959016", "GSM959017", "GSM959018", "GSM959019", "GSM959020", "GSM959021", "GSM959022", "GSM959023", "GSM959024", "GSM959025", "GSM959026", "GSM959027", "GSM959028", "GSM959029", "GSM959030", "GSM959031", "GSM959032", "GSM959033", "GSM959034", "GSM959035", "GSM959036", "GSM959037", "GSM959038", "GSM959039", "GSM959040", "GSM959041", "GSM959042", "GSM959043"], "sample_count": 51, "group_sizes": null, "group_sizes_basis": null, "platform": "96", "taxon": "Homo sapiens", "title": "Human sarcoma cell lines and untransformed cells", "resolution_checked_at": "2026-11-01T15:39:54Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:GSE87624", "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=GSE87624", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE87624", "version": null, "note": "The following information was supplied regarding data availability:The data is available at NCBI GEO: GSE12865, GSE19276, GSE87624, GSE99671, GSE39262, and GSE126209.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The following information was supplied regarding data availability:The data is available at NCBI GEO: GSE12865, GSE19276, GSE87624, GSE99671, GSE39262, and GSE126209.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM2335686", "GSM2335687", "GSM2335688", "GSM2335689", "GSM2335690", "GSM2335691", "GSM2335692", "GSM2335693", "GSM2335694", "GSM2335695", "GSM2335696", "GSM2335697", "GSM2335698", "GSM2335699", "GSM2335700", "GSM2335701", "GSM2335702", "GSM2335703", "GSM2335704", "GSM2335705", "GSM2335706", "GSM2335707", "GSM2335708", "GSM2335709", "GSM2335710", "GSM2335711", "GSM2335712", "GSM2335713", "GSM2335714", "GSM2335715", "GSM2335716", "GSM2335717", "GSM2335718", "GSM2335719", "GSM2335720", "GSM2335721", "GSM2335722", "GSM2335723", "GSM2335724", "GSM2335725", "GSM2335726", "GSM2335727", "GSM2335728", "GSM2335729", "GSM2335730", "GSM2335731", "GSM2335732", "GSM2335733", "GSM2335734", "GSM2335735", "GSM2335736", "GSM2335737"], "sample_count": 52, "group_sizes": null, "group_sizes_basis": null, "platform": "11154", "taxon": "Homo sapiens", "title": "Next-gen RNA sequencing of human osteosarcoma tumors", "resolution_checked_at": "2026-11-01T15:39:55Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:GSE99671", "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=GSE99671", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE99671", "version": null, "note": "The following information was supplied regarding data availability:The data is available at NCBI GEO: GSE12865, GSE19276, GSE87624, GSE99671, GSE39262, and GSE126209.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The following information was supplied regarding data availability:The data is available at NCBI GEO: GSE12865, GSE19276, GSE87624, GSE99671, GSE39262, and GSE126209.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM2649696", "GSM2649697", "GSM2649698", "GSM2649699", "GSM2649700", "GSM2649701", "GSM2649702", "GSM2649703", "GSM2649704", "GSM2649705", "GSM2649706", "GSM2649707", "GSM2649708", "GSM2649709", "GSM2649710", "GSM2649711", "GSM2649712", "GSM2649713", "GSM2649714", "GSM2649715", "GSM2649716", "GSM2649717", "GSM2649718", "GSM2649719", "GSM2649720", "GSM2649721", "GSM2649722", "GSM2649723", "GSM2649724", "GSM2649725", "GSM2649726", "GSM2649727", "GSM2649728", "GSM2649729", "GSM2649730", "GSM2649731", "GSM2652426", "GSM2652427", "GSM2652428", "GSM2652429", "GSM2652430", "GSM2652431", "GSM2652432", "GSM2652433", "GSM2652434", "GSM2652435", "GSM2652436", "GSM2652437", "GSM2652438", "GSM2652439", "GSM2652440"], "sample_count": 51, "group_sizes": null, "group_sizes_basis": null, "platform": "20148", "taxon": "Homo sapiens", "title": "Whole transcriptome analysis identifies differentially regulated networks between osteosarcoma and normal bone samples", "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:34123594:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:a910ebcbdd9154619c5af66f725b51f5a06aa8f74c9dda39b980cd5fcdec772f", "bytes": 2684, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[10]/table-wrap[1]#table-1", "version": null, "note": "The list of top 20 up-regulated and down-regulated differentially expressed genes.", "structure": {"pmcid": "PMC8164836", "section_index": 10, "section_title": "Identification of DEGs", "row_count": 41, "column_count": 5}, "table": {"label": "Table 1", "caption": "The list of top 20 up-regulated and down-regulated differentially expressed genes.", "rows": [["Gene symbol", "Combined.ES", "P_value", "FDR", "Up/Down-regulation"], ["NETO2", "1.773", "5.48E−10", "1.16E−07", "Up-regulation"], ["RTKN", "1.664", "3.90E−09", "6.57E−07", "Up-regulation"], ["TMEM65", "1.669", "1.08E−08", "1.54E−06", "Up-regulation"], ["MLLT11", "1.507", "1.41E−08", "1.84E−06", "Up-regulation"], ["LAPTM4B", "1.499", "1.78E−08", "2.21E−06", "Up-regulation"], ["ZC3H8", "1.563", "1.97E−08", "2.41E−06", "Up-regulation"], ["SLC35F2", "1.570", "3.46E−08", "3.90E−06", "Up-regulation"], ["IRX2", "1.534", "5.03E−08", "5.19E−06", "Up-regulation"], ["ZNF593", "1.404", "7.11E−08", "6.78E−06", "Up-regulation"], ["FLAD1", "1.451", "7.54E−08", "7.10E−06", "Up-regulation"], ["KCNG1", "1.456", "1.32E−07", "1.16E−05", "Up-regulation"], ["FGD1", "1.304", "2.59E−07", "2.04E−05", "Up-regulation"], ["RPAP2", "1.480", "2.63E−07", "2.06E−05", "Up-regulation"], ["DYRK4", "1.405", "2.83E−07", "2.20E−05", "Up-regulation"], ["EDARADD", "1.360", "3.06E−07", "2.33E−05", "Up-regulation"], ["PDCD5", "1.285", "3.77E−07", "2.80E−05", "Up-regulation"], ["TMEM97", "1.349", "4.04E−07", "2.95E−05", "Up-regulation"], ["GNL2", "1.311", "4.14E−07", "3.01E−05", "Up-regulation"], ["HOXB6", "1.527", "4.47E−07", "3.17E−05", "Up-regulation"], ["ZZZ3", "1.504", "5.79E−07", "3.99E−05", "Up-regulation"], ["CAMP", "−4.158", "0", "0", "Down-regulation"], ["AHSP", "−3.156", "0", "0", "Down-regulation"], ["OLFM4", "−3.108", "0", "0", "Down-regulation"], ["LTF", "−3.006", "0", "0", "Down-regulation"], ["ADH1C", "−2.814", "0", "0", "Down-regulation"], ["CXCL12", "−2.746", "0", "0", "Down-regulation"], ["BPI", "−2.556", "0", "0", "Down-regulation"], ["HBD", "−2.615", "8.88E−16", "5.32E−13", "Down-regulation"], ["TCN1", "−2.522", "1.11E−15", "6.40E−13", "Down-regulation"], ["FABP4", "−2.296", "7.77E−15", "4.31E−12", "Down-regulation"], ["RAB37", "−2.279", "2.02E−14", "1.08E−11", "Down-regulation"], ["FCN1", "−2.320", "2.95E−14", "1.53E−11", "Down-regulation"], ["TMEM154", "−2.279", "3.13E−14", "1.55E−11", "Down-regulation"], ["METTL7A", "−2.181", "5.44E−14", "2.47E−11", "Down-regulation"], ["CYP4F3", "−2.304", "6.66E−14", "2.94E−11", "Down-regulation"], ["CAT", "−2.109", "3.44E−13", "1.43E−10", "Down-regulation"], ["CHL1", "−1.974", "5.51E−13", "2.17E−10", "Down-regulation"], ["TMEM132C", "−1.860", "5.19E−12", "1.85E−09", "Down-regulation"], ["SERPINB2", "−3.082", "5.64E−12", "1.97E−09", "Down-regulation"], ["SLC28A3", "−2.118", "8.26E−12", "2.69E−09", "Down-regulation"]], "row_count": 41, "column_count": 5, "numeric_cells": 130, "header_rows": 1, "locator": "section[10]/table-wrap[1]#table-1"}}, {"id": "asset:table:pmid:34123594:2", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:530ff1dd5ceafeb25ec5573210cbad15fd20bfb0c686851d59d8bff1de9c7d54", "bytes": 3885, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[11]/table-wrap[1]#table-2", "version": null, "note": "The top 20 significantly enriched KEGG pathways.", "structure": {"pmcid": "PMC8164836", "section_index": 11, "section_title": "GO and KEGG enrichment analysis of DEGs", "row_count": 21, "column_count": 5}, "table": {"label": "Table 2", "caption": "The top 20 significantly enriched KEGG pathways.", "rows": [["ID", "Term", "P_value", "Count", "Gene Symbols"], ["hsa04923", "Regulation of lipolysis in adipocytes", "0.0001", "10", "ADRB2, FABP4, PDE3B, PIK3CD, PLIN1, PTGER3, IRS2, ABHD5, PNPLA2, ADCY4"], ["hsa04141", "Protein processing in endoplasmic reticulum", "0.0001", "19", "BAG1, EIF2S1, HSPA2, LMAN1, MAN1A1, MAP3K5, P4HB, EIF2AK2, RPN2, RRBP1, SSR2, PREB, SEC24A, SEC61G, UBQLN2, DNAJB11, UBQLN4, DNAJC1, UBE2J2"], ["hsa05200", "Pathways in cancer", "0.0002", "34", "BCL2L1, CASP8, CDKN2A, CEBPA, CKS1B, COL4A1, DVL1, E2F1, EPAS1, FGF7, FGF13, FLT3, MTOR, GLI2, GLI3, GNAQ, PIK3CD, PTEN, PTGER2, PTGER3, RARB, RXRA, CXCL12, SKP2, STAT5A, TGFB3, TGFBR2, VEGFA, NCOA4, FGF16, PIAS2, ARHGEF11, LEF1, ADCY4, SHC1, CALM1, CHEK1, ELK1, FDPS, GPS2, MSX2, RANBP1, TLN1, VCAM1, TLN2"], ["hsa01230", "Biosynthesis of amino acids", "0.0004", "11", "CTH, ENO1, GAPDH, PC, SHMT1, TALDO1, TKT, TPI1, SDS, RPIA, AADAT, CAT, MDH2, ME1, MCEE"], ["hsa04974", "Protein digestion and absorption", "0.0019", "11", "COL2A1, COL4A1, COL5A2, COL10A1, COL11A1, COL17A1, CPA3, SLC7A8, COL18A1, COL27A1, SLC16A10"], ["hsa04722", "Neurotrophin signaling pathway", "0.0022", "13", "CALM1, MAPK14, MAP3K5, NFKBIE, NTF3, NTRK2, PIK3CD, PRKCD, RPS6KA2, SHC1, MAGED1, PRDM4, IRAK3"], ["hsa04152", "AMPK signaling pathway", "0.0023", "13", "CPT1A, ELAVL1, MTOR, LEP, PIK3CD, PPP2R5A, PPP2R5D, PRKAB2, IRS2, CREB5, CAMKK2, STRADB, CREB3L1, PRKCD, PRKCE, PTEN, RPS6KA2, TBC1D4, JAK2, NFKBIE, RXRA, SOCS2, CAT, ADCY4, CALM1, ELK1, FLOT2, PDE3B, PRKAR2B, SHC1, INPP5K, HSPA2"], ["M00007", "Pentose phosphate pathway, non-oxidative phase, fructose 6P =>ribose 5P", "0.0026", "3", "TALDO1, TKT, RPIA"], ["hsa03060", "Protein export", "0.0028", "5", "OXA1L, SRP54, SRP72, SEC61G, SRPRB"], ["hsa04933", "AGE-RAGE signaling pathway in diabetic complications", "0.0041", "11", "COL4A1, MAPK14, JAK2, PIK3CD, PRKCD, PRKCE, STAT5A, TGFB3, TGFBR2, VCAM1, VEGFA, CD247, MTOR, NFKBIE, RXRA, STAT6, IL27RA, LHB, SHC1, SOCS2, AOX1, BCL2L1, IL5RA, LEP, PIAS2"], ["hsa04360", "Axon guidance", "0.0045", "16", "EFNA1, EFNA3, EFNA5, EFNB1, EPHA3, EPHB2, EPHB6, FES, PIK3CD, CXCL12, SEMA7A, SEMA3A, RHOD, SEMA4C, NTNG2, PLXNA4"], ["hsa04015", "Rap1 signaling pathway", "0.0053", "18", "CALM1, MAPK14, EFNA1, EFNA3, EFNA5, FGF7, FGF13, GNAQ, ITGB3, PFN2, PIK3CD, TLN1, VEGFA, FGF16, RAPGEF3, APBB1IP, TLN2, ADCY4, BCL2L1, COL2A1, COL4A1, MTOR, ITGA7, JAK2, PPP2R5A, PPP2R5D, PTEN, RXRA, TLR4, CREB5, CREB3L1, THEM4"], ["hsa00590", "Arachidonic acid metabolism", "0.0055", "8", "ALOX15, GGT5, GPX3, GPX7, LTA4H, CYP4F3, PLA2G5, PTGES, GSTA4, GSTM3, SRM, GGCT"], ["hsa04932", "Non-alcoholic fatty liver disease (NAFLD)", "0.0060", "14", "CASP8, CEBPA, EIF2S1, LEP, MAP3K5, NDUFB9, NDUFS5, PIK3CD, PRKAB2, RXRA, UQCRH, IRS2, NDUFB11, NDUFA4L2"], ["hsa00620", "Pyruvate metabolism", "0.0066", "6", "GLO1, HAGH, MDH2, ME1, PC, LDHD"], ["hsa04924", "Renin secretion", "0.0073", "8", "ADRB2, CALM1, GNAQ, PDE1A, PDE1C, PDE3B, PTGER2, CLCA4"], ["hsa04750", "Inflammatory mediator regulation of TRP channels", "0.0101", "10", "CALM1, MAPK14, GNAQ, PIK3CD, PRKCD, PRKCE, PTGER2, TRPA1, TRPV4, ADCY4, ADRB2, ATP2B4, PPP2R5A, PPP2R5D, CREB5, RAPGEF3, CACNG7, CREB3L1, HSPA2, SHC1, PLA2G5, PTGIR, ARHGEF11, PPP1R14A, MYL6B, GPX3, GPX7, SLC26A4, ELK1, GNRH2, LHB"], ["hsa01524", "Platinum drug resistance", "0.0144", "8", "BCL2L1, CASP8, CDKN2A, GSTA4, GSTM3, MAP3K5, PIK3CD, PMAIP1, BCL2A1, DFFA, DFFB, EIF2S1, PARP2, DIABLO, DAB2IP, MAPK14, VCAM1, CREB5, CREB3L1, MLKL, CALM1, ITGB3, PLAT, VEGFA, TRPV4"], ["hsa04071", "Sphingolipid signaling pathway", "0.0146", "11", "MAPK14, MS4A2, GNAQ, MAP3K5, PIK3CD, PPP2R5A, PPP2R5D, PRKCE, PTEN, SPTLC2, SGMS1"], ["hsa00983", "Drug metabolism-other enzymes", "0.0147", "6", "CDA, CES1, DPYD, UCK2, CES2, UCKL1"]], "row_count": 21, "column_count": 5, "numeric_cells": 74, "header_rows": 1, "locator": "section[11]/table-wrap[1]#table-2"}}, {"id": "asset:table:pmid:34123594:3", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:0fc6031ce801f02a51ab922ac9d0fa897dd04d46a4b99bc203ec21990eceaff3", "bytes": 1153, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[13]/table-wrap[1]#table-3", "version": null, "note": "The top 6 TF that has the most downstream genes.", "structure": {"pmcid": "PMC8164836", "section_index": 13, "section_title": "TF-target network analysis", "row_count": 7, "column_count": 3}, "table": {"label": "Table 3", "caption": "The top 6 TF that has the most downstream genes.", "rows": [["TF", "Number∗", "Gene Symbol"], ["Pax-4", "31", "FLAD1, ZZZ3, GNL2, EDARADD, RTKN, LTF, CAMP, CHL1, ADH1C, TMEM154, IRX2, FABP4, LAPTM4B, SLC28A3, FGD1, CXCL12, HBD, TCN1, CAT, SLC35F2, DYRK4, METTL7A, OLFM4, AHSP, RAB37, TMEM97, SERPINB2, CYP4F3, PDCD5, BPI, KCNG1"], ["1-Oct", "22", "FLAD1, GNL2, RPAP2, EDARADD, ZC3H8, CHL1, CAMP, IRX2, FABP4, TMEM65, SLC28A3, HBD, TCN1, CAT, TMEM132C, DYRK4, METTL7A, TMEM97, HOXB6, SERPINB2, BPI, KCNG1"], ["Nkx2-5", "19", "FLAD1, MLLT11, RPAP2, EDARADD, CAMP, CHL1, TMEM154, LAPTM4B, TMEM65, SLC28A3, FGD1, TCN1, SLC35F2, DYRK4, AHSP, SERPINB2, CYP4F3, KCNG1, BPI"], ["HNF-4", "16", "ZZZ3, ZNF593, GNL2, LTF, CHL1, CAMP, LAPTM4B, SLC28A3, FGD1, CXCL12, HBD, SLC35F2, METTL7A, RAB37, CYP4F3, KCNG1"], ["FOXD3", "14", "GNL2, RPAP2, EDARADD, ZC3H8, CHL1, LTF, FABP4, FGD1, HBD, DYRK4, METTL7A, OLFM4, NETO2, RAB37"], ["Pax-6", "13", "EDARADD, GNL2, CHL1, TMEM65, SLC28A3, CXCL12, HBD, TCN1, DYRK4, NETO2, SERPINB2, CYP4F3, KCNG1"]], "row_count": 7, "column_count": 3, "numeric_cells": 17, "header_rows": 1, "locator": "section[13]/table-wrap[1]#table-3"}}], "gaps": ["asset:data:geo:GSE12865 not downloaded", "asset:data:geo:GSE12865 licence not read", "asset:data:geo:GSE19276 not downloaded", "asset:data:geo:GSE19276 licence not read", "asset:data:geo:GSE39262 not downloaded", "asset:data:geo:GSE39262 licence not read", "asset:data:geo:GSE87624 not downloaded", "asset:data:geo:GSE87624 licence not read", "asset:data:geo:GSE99671 not downloaded", "asset:data:geo:GSE99671 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": "GO 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": 0.7, "band": "medium", "quote": "ROC analysis"}}, {"id": "method-4", "family": null, "specific": null, "label": "MetaMA meta-analysis of four GEO datasets", "dsl_operations": [], "missing_operations": [], "expressible": null, "parameters": {}, "data_shapes": [], "evidence": {"score": 1.0, "band": "verbatim", "quote": "Subsequently, MetaMA (https://cran.r-project.org/web/packages/metaMA/), an R package, was used to combine data from four GEO datasets."}}], "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": ["GSE12865", "GSE19276", "GSE87624", "GSE99671", "GSE39262", "and GSE126209"], "resolved_accessions": ["GSE12865", "GSE19276", "GSE87624", "GSE99671", "GSE39262"], "statements": ["The following information was supplied regarding data availability:The data is available at NCBI GEO: GSE12865, GSE19276, GSE87624, GSE99671, GSE39262, and GSE126209."], "basis": "The paper names GSE12865, GSE19276, GSE87624, GSE99671, GSE39262 in NCBI 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:34123594", "data:geo:GSE12865", "asset:table:pmid:34123594:1", "asset:table:pmid:34123594:2", "asset:table:pmid:34123594:3"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE12865"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-10-31T18:30:54Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 3, "usage": {"prompt_tokens": 32746, "completion_tokens": 1227, "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:34123594", "type": "paper", "label": "pmid:34123594"}, {"id": "source:pmid:34123594", "type": "manuscript", "label": "PMID 34123594 full text"}, {"id": "data:geo:GSE12865", "type": "dataset", "label": "GEO GSE12865"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:34123594", "type": "paper", "label": "pmid:34123594"}, {"id": "source:pmid:34123594", "type": "manuscript", "label": "PMID 34123594 full text"}, {"id": "data:geo:GSE12865", "type": "dataset", "label": "GEO GSE12865"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-34123594", "type": "extraction", "used": ["source:pmid:34123594"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE12865", "type": "accession_resolution", "used": ["data:geo:GSE12865"], "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:34123594", "parent_hash": "sha256:d127ea05e228fe959b40651942d6292e91496f77be70a9da3636ad3a92f906fa", "fork_of": null, "generation": 6}, "gaps": ["asset:data:geo:GSE12865 licence not read", "asset:data:geo:GSE12865 not downloaded", "asset:data:geo:GSE19276 licence not read", "asset:data:geo:GSE19276 not downloaded", "asset:data:geo:GSE39262 licence not read", "asset:data:geo:GSE39262 not downloaded", "asset:data:geo:GSE87624 licence not read", "asset:data:geo:GSE87624 not downloaded", "asset:data:geo:GSE99671 licence not read", "asset:data:geo:GSE99671 not downloaded", "execution.not_run", "method.reader_named_unmapped", "review.human_critique", "review.independent_reader", "review.machine_critique"], "assays": [{"role": "data_generation", "definition_id": "microarray", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.99, "evidence": ["signatures associated with OS by integrated microarray analysis of the Gene Expression Omnibus (GEO", "(GEO) database. MATERIAL AND METHODS: The OS microarray datasets were searched and downloaded from G"], "order_basis": "paper_text_order:286", "id": "assay:1"}, {"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:2"}]},"meta":{"api_version":"v1","automation_ladder_snapshot":"ba34b49490d9bfaf","automation_ladder_caveats":["Method extraction is rule-based and has no hand-judged accuracy sample. Evidence bands order textual support; method agreement intervals are null (n=0), never probabilities. Work-type validation does not validate methods.","Operation coverage describes only explicitly named methods. It does not prove a complete protocol, compatible parameters, successful compilation or re-execution. Unrecognised or ambiguous methods require review.","Data reachability is a textual accession or public-data statement. No dataset was downloaded or checked for access, completeness or licence.","Capabilities are planning states seeded from the dated equipment register. No bench ownership, completed quote or partner booking is inferred. Procurement counts are dependencies, not guaranteed replications or financial returns.","Tier and blocker counts are deterministic assessments of this corpus, not measured agreement. R3 is reserved for procurement; unresolved methods and data require human work (R4). The most restrictive axis wins, with capability, method, data as tie-breaks. Resolving one blocker can leave another at the same tier."],"engine":"corpus_engine","engine_provider":"rule_based_v1+lex99e1195c7d6f","run_id":"run-20261023T122449232913","source":"esearch","source_detail":"PubMed mirror biomed_pubmed (read-only)","run_status":"complete","imported_at":"2026-11-03T20:16:52+00:00","generated_at":"2026-11-04T01:47:39+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}}}