{"data":{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:33777260", "kind": "science-record", "revision": 7, "content_hash": "sha256:2668ac8b38e9a1774682153af311f4a12030a55aab7e5e88890b2df500f5cd54", "created_at": "2026-11-01T15:41:30Z", "updated_at": "2026-11-01T22:03:25Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "The Genetic and Epigenetic Mechanisms Involved in Irreversible Pulp Neural Inflammation.", "doi": "10.1155/2021/8831948", "pmid": "33777260", "authors": ["Xiaoxi Xi", "Yihong Ma", "Yuzhen Xu", "Anthony Chukwunonso Ogbuehi", "Xiangqiong Liu", "Yupei Deng", "Junming Xi", "Haitong Pan", "Qian Lin", "Bo Li", "Wanchen Ning", "Xiao Jiang", "Hanluo Li", "Simin Li", "Xianda Hu"], "journal": "Disease markers", "year": 2021, "abstract": "AIM: To identify the critical genetic and epigenetic biomarkers by constructing the long noncoding RNA- (lncRNA-) related competing endogenous RNA (ceRNA) network involved in irreversible pulp neural inflammation (pulpitis).\nMATERIALS AND METHODS: The public datasets regarding irreversible pulpitis were downloaded from the gene expression omnibus (GEO) database. The differential expression analysis was performed to identify the differentially expressed genes (DEGs) and DElncRNAs. Functional enrichment analysis was performed to explore the biological processes and signaling pathways enriched by DEGs. By performing a weighted gene coexpression network analysis (WGCNA), the significant gene modules in each dataset were identified. Most importantly, DElncRNA-DEmRNA regulatory network and DElncRNA-associated ceRNA network were constructed. A transcription factor- (TF-) DEmRNA network was built to identify the critical TFs involved in pulpitis.\nRESULT: Two datasets (GSE92681 and GSE77459) were selected for analysis. DEGs involved in pulpitis were significantly enriched in seven signaling pathways (i.e., NOD-like receptor (NLR), Toll-like receptor (TLR), NF-kappa B, tumor necrosis factor (TNF), cell adhesion molecules (CAMs), chemokine, and cytokine-cytokine receptor interaction pathways). The ceRNA regulatory relationships were established consisting of three genes (i.e., LCP1, EZH2, and NR4A1), five miRNAs (i.e., miR-340-5p, miR-4731-5p, miR-27a-3p, miR-34a-5p, and miR-766-5p), and three lncRNAs (i.e., XIST, MIR155HG, and LINC00630). Six transcription factors (i.e., GATA2, ETS1, FOXP3, STAT1, FOS, and JUN) were identified to play pivotal roles in pulpitis.\nCONCLUSION: This paper demonstrates the genetic and epigenetic mechanisms of irreversible pulpitis by revealing the ceRNA network. The biomarkers identified could provide research direction for the application of genetically modified stem cells in endodontic regeneration.", "claims": [{"id": "claim-method", "statement": "Based on the GSE92681 dataset, the coexpression status of DElncRNAs and DEGs was calculated by using a statistical method—Pearson correlation.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:33777260", "locator": "sections[9] \"2.7. Functional Enrichment Analysis of DElncRNAs\" paragraph 2", "quote": "Based on the GSE92681 dataset, the coexpression status of DElncRNAs and DEGs was calculated by using a statistical method—Pearson correlation."}], "state": "complete"}, {"id": "claim-data-access", "statement": "The data used to support the findings of this study are available from the corresponding author upon reasonable request.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:33777260", "locator": "sections[28] \"Data Availability\" paragraph 2", "quote": "The data used to support the findings of this study are available from the corresponding author upon reasonable request."}], "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:33777260"], "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:GSE77459"], "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:GSE77459"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:33777260", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1155/2021/8831948", "sha256": "sha256:0afa4b11bae509d613ea0c98ceb8eef89e88cb12630a2c80871c1df156b5402c", "bytes": 70049, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1155/2021/8831948", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC7968449", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE77459", "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=GSE77459", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE77459", "version": null, "note": "The data used to support the findings of this study are available from the corresponding author upon reasonable request.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The data used to support the findings of this study are available from the corresponding author upon reasonable request.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM2052371", "GSM2052372", "GSM2052373", "GSM2052374", "GSM2052375", "GSM2052376", "GSM2052377", "GSM2052378", "GSM2052379", "GSM2052380", "GSM2052381", "GSM2052382"], "sample_count": 12, "group_sizes": null, "group_sizes_basis": null, "platform": "17692", "taxon": "Homo sapiens", "title": "Gene Expression Profile of Pulpitis", "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:GSE92681", "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=GSE92681", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE92681", "version": null, "note": "The data used to support the findings of this study are available from the corresponding author upon reasonable request.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The data used to support the findings of this study are available from the corresponding author upon reasonable request.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM2434473", "GSM2434474", "GSM2434475", "GSM2434476", "GSM2434477", "GSM2434478", "GSM2434479", "GSM2434480", "GSM2434481", "GSM2434482", "GSM2434483", "GSM2434484"], "sample_count": 12, "group_sizes": null, "group_sizes_basis": null, "platform": "16956", "taxon": "Homo sapiens", "title": "Differential Expression of LncRNAs and mRNAs in normal and inflamed human pulp", "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:33777260:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:9543c91f1964c55138d19f715f00bfe4ec2fd9831fe79e4656b72025378e8251", "bytes": 394, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[16]/table-wrap[1]#tab1", "version": null, "note": "The pulpitis-related datasets used for the present analysis.", "structure": {"pmcid": "PMC7968449", "section_index": 16, "section_title": "3.2. Identification of DEGs", "row_count": 3, "column_count": 4}, "table": {"label": "Table 1", "caption": "The pulpitis-related datasets used for the present analysis.", "rows": [["Datasets", "Experimental type of datasets", "Sample size of inflamed pulp tissue", "Sample size of healthy pulp tissue"], ["GSE92681", "Noncoding RNA", "7", "5"], ["GSE77459", "mRNA", "6", "6"]], "row_count": 3, "column_count": 4, "numeric_cells": 6, "header_rows": 1, "locator": "section[16]/table-wrap[1]#tab1"}}, {"id": "asset:table:pmid:33777260:2", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:a1d1906e3355972c5116d9ae86b966fdf914bd376bc6959471c1d2ef1d81444f", "bytes": 462, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[16]/table-wrap[2]#tab2", "version": null, "note": "The number of upregulated and downregulated DEGs or DElncRNAs identified from included datasets.", "structure": {"pmcid": "PMC7968449", "section_index": 16, "section_title": "3.2. Identification of DEGs", "row_count": 4, "column_count": 4}, "table": {"label": "Table 2", "caption": "The number of upregulated and downregulated DEGs or DElncRNAs identified from included datasets.", "rows": [["Datasets", "Number of upregulated factors", "Number of downregulated factors", "Number of total factors"], ["GSE92681_DElncRNA", "138", "136", "274"], ["GSE92681_DEG", "486", "178", "664"], ["GSE77459_DEG", "823", "278", "1101"]], "row_count": 4, "column_count": 4, "numeric_cells": 12, "header_rows": 1, "locator": "section[16]/table-wrap[2]#tab2"}}, {"id": "asset:table:pmid:33777260:3", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:4c008fd39f8235459a9c7efd95be809429cf452ff4ab4f08deb09f699b5c1808", "bytes": 1766, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[18]/table-wrap[1]#tab3", "version": null, "note": "The topological characteristics of the top 20 nodes in the PPI network.", "structure": {"pmcid": "PMC7968449", "section_index": 18, "section_title": "3.4. Identification of Hub Genes by Constructing the PPI Network", "row_count": 21, "column_count": 7}, "table": {"label": "Table 3", "caption": "The topological characteristics of the top 20 nodes in the PPI network.", "rows": [["Gene name", "Degree", "Average shortest path length", "Betweenness centrality", "Closeness centrality", "Clustering coefficient", "Topological coefficient"], ["UBD", "656", "2.700089", "0.092136", "0.370358", "0.001564", "0.003702"], ["UBC", "460", "2.20363", "0.309699", "0.453797", "0.004092", "0.005551"], ["IFI16", "436", "2.853032", "0.052658", "0.350504", "0.001381", "0.005531"], ["ARRB2", "369", "2.872067", "0.040035", "0.348181", "0.001915", "0.007365"], ["HLA-B", "338", "2.825255", "0.037735", "0.35395", "0.002915", "0.00551"], ["EZH2", "301", "2.891545", "0.030774", "0.345836", "0.00206", "0.008083"], ["SFN", "296", "2.903608", "0.032059", "0.344399", "0.00213", "0.00725"], ["ADRB2", "294", "2.855246", "0.033685", "0.350233", "0.003088", "0.006755"], ["LYN", "243", "2.795595", "0.03365", "0.357706", "0.013332", "0.008931"], ["MAP3K1", "229", "2.901173", "0.021399", "0.344688", "0.00406", "0.009621"], ["FOS", "226", "2.943448", "0.02579", "0.339738", "0.00468", "0.010265"], ["RPS9", "208", "2.82127", "0.017896", "0.35445", "0.009337", "0.00958"], ["KPNA2", "205", "2.867641", "0.022731", "0.348719", "0.00263", "0.009771"], ["IL7R", "199", "2.931496", "0.015151", "0.341123", "0.002944", "0.011601"], ["LGR4", "198", "3.039287", "0.020276", "0.329025", "3.59E-04", "0.010662"], ["CASP8", "196", "2.906707", "0.020462", "0.344032", "0.008791", "0.010607"], ["CD247", "196", "2.964697", "0.024808", "0.337303", "0.00539", "0.010402"], ["HIF1A", "174", "2.950089", "0.016343", "0.338973", "0.003123", "0.013813"], ["MYO19", "173", "2.93548", "0.0148", "0.34066", "0.010687", "0.00917"], ["MNDA", "168", "3.236498", "0.007305", "0.308976", "7.84E − 04", "0.012766"]], "row_count": 21, "column_count": 7, "numeric_cells": 123, "header_rows": 1, "locator": "section[18]/table-wrap[1]#tab3"}}, {"id": "asset:table:pmid:33777260:4", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:1a8cf64588172a8d97eff01713ed1181e13c6e3b739d606e17cd5aef60223a56", "bytes": 2264, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[21]/table-wrap[1]#tab4", "version": null, "note": "The topological characteristics of the top 20 nodes in the DElncRNA-DEG regulatory network.", "structure": {"pmcid": "PMC7968449", "section_index": 21, "section_title": "3.7. The DElncRNA-DEG Regulatory Network", "row_count": 21, "column_count": 8}, "table": {"label": "Table 4", "caption": "The topological characteristics of the top 20 nodes in the DElncRNA-DEG regulatory network.", "rows": [["Name", "Degree", "Average shortest path length", "Betweenness centrality", "Closeness centrality", "Clustering coefficient", "Topological coefficient", "Regulate"], ["RP11-702F3.3", "32", "2.26666667", "0.09257337", "0.44117647", "0.36363636", "0.2867215", "lncRNAup"], ["RP5-963E22.4", "32", "2.05", "0.14685811", "0.48780488", "0.3982684", "0.27954545", "lncRNAup"], ["RP11-555G19.1", "25", "2.21666667", "0.08384754", "0.45112782", "0.37908497", "0.30401235", "lncRNAup"], ["CTD-2568A17.1", "21", "2.56666667", "0.17922917", "0.38961039", "0.37179487", "0.26627219", "lncRNAup"], ["PRSS29P", "21", "2.28333333", "0.18869008", "0.4379562", "0.20588235", "0.26916221", "lncRNAup"], ["RP11-686F15.2", "20", "2.53333333", "0.01950748", "0.39473684", "0.44761905", "0.35757576", "lncRNAup"], ["RP11-783L4.1", "19", "2.58333333", "0.01555518", "0.38709677", "0.47252747", "0.37327189", "lncRNAup"], ["RP11-1M18.1", "18", "2.06666667", "0.32645541", "0.48387097", "0.3030303", "0.22644928", "lncRNAup"], ["LINC01043", "17", "2.61666667", "0.01053104", "0.38216561", "0.43589744", "0.36923077", "lncRNAup"], ["RP1-15D23.2", "17", "2.48333333", "0.00914061", "0.40268456", "0.59090909", "0.38333333", "lncRNAup"], ["RP11-442O18.1", "17", "2.66666667", "0.03491119", "0.375", "0.3974359", "0.33846154", "lncRNAup"], ["AC017002.1", "16", "2.35", "0.51050061", "0.42553191", "0.05714286", "0.17333333", "lncRNAup"], ["CTD-2275D24.1", "14", "3.23333333", "0.02043004", "0.30927835", "0.44444444", "0.41176471", "lncRNAup"], ["PDE7A", "13", "2.15", "0.08844751", "0.46511628", "0.35897436", "0.33208255", "mRNA up"], ["RP11-145G20.1", "13", "3.33333333", "0.01660117", "0.3", "0.36111111", "0.39869281", "lncRNAup"], ["RP11-521D12.1", "13", "3.35", "0.00459174", "0.29850746", "0.5", "0.43382353", "lncRNAup"], ["RP5-991O23.1", "13", "3.03333333", "0.01404135", "0.32967033", "0.33333333", "0.31481481", "lncRNAup"], ["CTD-2296D1.1", "12", "3.36666667", "0.00429011", "0.2970297", "0.5", "0.453125", "lncRNAup"], ["RP3-340N1.6", "12", "3.35", "0.0054601", "0.29850746", "0.57142857", "0.44852941", "lncRNAup"], ["MIR155HG", "11", "2.55", "0.41865079", "0.39215686", "0", "0.12121212", "lncRNAup"]], "row_count": 21, "column_count": 8, "numeric_cells": 139, "header_rows": 1, "locator": "section[21]/table-wrap[1]#tab4"}}, {"id": "asset:table:pmid:33777260:5", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:fb5350f95fcf420118a8e113d9cf5b3526b64219cb00c054243ac056279c539b", "bytes": 1980, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[22]/table-wrap[1]#tab5", "version": null, "note": "The topological characteristics of the top 20 nodes in the TF-DEG regulatory network.", "structure": {"pmcid": "PMC7968449", "section_index": 22, "section_title": "3.8. Identification of Hub Transcription Factor", "row_count": 21, "column_count": 7}, "table": {"label": "Table 5", "caption": "The topological characteristics of the top 20 nodes in the TF-DEG regulatory network.", "rows": [["Name", "Degree", "Average shortest path length", "Betweenness centrality", "Closeness centrality", "Clustering coefficient", "Topological coefficient"], ["GATA2", "518", "2.03887936", "0.11659147", "0.49046551", "0.00308432", "0.02016302"], ["ETS1", "508", "2.05603202", "0.11527216", "0.48637375", "0.0028654", "0.02038007"], ["YBX1", "425", "2.22012579", "0.09284757", "0.45042493", "0.00137625", "0.02440558"], ["AR", "414", "2.18753573", "0.08279112", "0.45713539", "0.0032635", "0.02330064"], ["FOXP3", "407", "2.24013722", "0.09211348", "0.44640123", "0.00128297", "0.02202286"], ["GATA1", "322", "2.30360206", "0.03470622", "0.43410276", "0.00336681", "0.02811219"], ["SP1", "214", "2.3619211", "0.02271018", "0.42338417", "0.00842438", "0.03168479"], ["E2F4", "203", "2.50714694", "0.02510997", "0.39885975", "0.00248744", "0.03155395"], ["PRDM14", "194", "2.47970269", "0.01761185", "0.40327415", "0.00459377", "0.03274385"], ["ARNT", "190", "2.47970269", "0.00990145", "0.40327415", "0.00668338", "0.04482786"], ["MIA3", "182", "2.51172098", "0.00828163", "0.39813339", "0.00558557", "0.04629319"], ["JUN", "179", "2.45740423", "0.0132459", "0.40693346", "0.01726194", "0.03584432"], ["CREB1", "178", "2.43853631", "0.0134572", "0.41008206", "0.01314035", "0.03899076"], ["FOS", "178", "2.04116638", "0.03258878", "0.48991597", "0.05986161", "0.0352397"], ["STAT1", "176", "2.51229274", "0.01672367", "0.39804279", "0.00525974", "0.03983636"], ["CEBPA", "168", "2.58604917", "0.01187163", "0.38669025", "0.00377816", "0.04812159"], ["AHR", "168", "2.53459119", "0.00776619", "0.39454094", "0.00620188", "0.04722287"], ["E2F1", "165", "2.50085763", "0.01123109", "0.39986283", "0.00657797", "0.04104892"], ["PAX5", "164", "2.51172098", "0.00771197", "0.39813339", "0.00890319", "0.0434212"], ["Pax-5", "161", "2.56089194", "0.0066902", "0.39048895", "0.00535714", "0.04834386"]], "row_count": 21, "column_count": 7, "numeric_cells": 122, "header_rows": 1, "locator": "section[22]/table-wrap[1]#tab5"}}, {"id": "asset:table:pmid:33777260:6", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:656908f5b07b7f754b76691f1100a6b249c0238399910197741f9b290a8b473b", "bytes": 2124, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[24]/table-wrap[1]#tab6", "version": null, "note": "The topological characteristics of the top 25 gene nodes in the PPI network of the blue module within the GSE77549 dataset.", "structure": {"pmcid": "PMC7968449", "section_index": 24, "section_title": "3.10. Construction of PPI Network for Selected Significant Gene Modules", "row_count": 26, "column_count": 7}, "table": {"label": "Table 6", "caption": "The topological characteristics of the top 25 gene nodes in the PPI network of the blue module within the GSE77549 dataset.", "rows": [["Name", "Degree", "Betweenness centrality", "Closeness centrality", "Clustering coefficient", "Topological coefficient", "Regulate"], ["NTRK1", "1981", "0.797678", "0.550769", "8.10E − 05", "0.00147", "Other_gene"], ["TUBA4A", "182", "0.057422", "0.34576", "2.46E − 04", "0.012097", "Other_gene"], ["PTPRK", "110", "0.048111", "0.334924", "5.10E − 04", "0.017763", "Other_gene"], ["ACTN2", "101", "0.04028", "0.340466", "8.08E − 04", "0.012519", "Other_gene"], ["MSH6", "98", "0.029296", "0.414544", "0.009211", "0.011399", "Other_gene"], ["COPS7A", "87", "0.027065", "0.331267", "0", "0.024951", "Other_gene"], ["BIRC3", "79", "0.030191", "0.33259", "0", "0.022419", "mRNA up"], ["SH3GL1", "79", "0.025169", "0.330228", "0", "0.023044", "Other_gene"], ["EPS8", "78", "0.030772", "0.33259", "0", "0.022436", "Other_gene"], ["PTPRJ", "76", "0.02319", "0.408163", "0.008288", "0.014223", "Other_gene"], ["UBC", "75", "0.16533", "0.47619", "0.005405", "0.017173", "Other_gene"], ["RPRD1B", "71", "0.019601", "0.329863", "0", "0.026232", "Other_gene"], ["TJP2", "68", "0.019477", "0.328079", "0", "0.027715", "Other_gene"], ["BID", "65", "0.018865", "0.33035", "0", "0.030769", "Other_gene"], ["TBL1XR1", "62", "0.023597", "0.409283", "0.010929", "0.017196", "Other_gene"], ["GRAP2", "59", "0.019032", "0.330838", "6.05E − 04", "0.027809", "Other_gene"], ["MAP2", "57", "0.016676", "0.406541", "0.014935", "0.018914", "Other_gene"], ["TIMMDC1", "53", "0.022335", "0.327539", "7.54E − 04", "0.025227", "Other_gene"], ["BACH1", "48", "0.013952", "0.327929", "0", "0.036859", "Other_gene"], ["DTL", "48", "0.009929", "0.332961", "0.006475", "0.032282", "Other_gene"], ["CORO1A", "46", "0.016515", "0.327929", "0", "0.029927", "mRNA up"], ["MX1", "43", "0.013576", "0.329347", "0", "0.037265", "Other_gene"], ["TWIST1", "41", "0.011401", "0.290915", "0", "0.053215", "Other_gene"], ["ITPR3", "39", "0.011085", "0.327419", "0", "0.039683", "mRNA up"], ["PTPRB", "36", "0.007233", "0.37609", "0.018487", "0.029667", "mRNA up"]], "row_count": 26, "column_count": 7, "numeric_cells": 125, "header_rows": 1, "locator": "section[24]/table-wrap[1]#tab6"}}, {"id": "asset:table:pmid:33777260:7", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:8d3f7bb9b5c16e8b4e57df092662be8bbd20ef772c93a8800f4ee4ba1352e21d", "bytes": 2507, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[24]/table-wrap[2]#tab7", "version": null, "note": "The topological characteristics of the top 25 gene nodes in the PPI network of the green module within the GSE92681 dataset.", "structure": {"pmcid": "PMC7968449", "section_index": 24, "section_title": "3.10. Construction of PPI Network for Selected Significant Gene Modules", "row_count": 26, "column_count": 8}, "table": {"label": "Table 7", "caption": "The topological characteristics of the top 25 gene nodes in the PPI network of the green module within the GSE92681 dataset.", "rows": [["Name", "Degree", "Average shortest path length", "Betweenness centrality", "Closeness centrality", "Clustering coefficient", "Topological coefficient", "Regulate"], ["PSMA2", "145", "2.84572072", "0.30956005", "0.35140483", "0", "0.01436782", "Other gene"], ["IK", "83", "3.14752252", "0.16898579", "0.3177102", "0", "0.02628697", "mRNA down"], ["BCAR1", "82", "3.0731982", "0.18704239", "0.32539392", "0", "0.02264808", "Other gene"], ["TCF12", "77", "2.88400901", "0.27221312", "0.34673955", "0", "0.01974026", "Other gene"], ["SAV1", "74", "3.6768018", "0.14809265", "0.2719755", "0", "0.02402402", "Other gene"], ["NDN", "61", "3.29391892", "0.12878792", "0.30358974", "0", "0.02157032", "Other gene"], ["ERGIC3", "55", "3.31644144", "0.11672478", "0.30152801", "0", "0.02121212", "Other gene"], ["ASB3", "38", "3.51914414", "0.07839935", "0.28416", "0", "0.03827751", "Other gene"], ["MMP7", "37", "4.70157658", "0.08120061", "0.21269461", "0", "0.04054054", "mRNA up"], ["WT1", "35", "3.74887387", "0.08035061", "0.26674677", "0", "0.04642857", "Other gene"], ["DGCR14", "32", "3.37274775", "0.05414526", "0.29649416", "0", "0.05208333", "Other gene"], ["RIOK3", "28", "3.19256757", "0.06657298", "0.31322751", "0", "0.05844156", "Other gene"], ["DUS3L", "26", "3.3704955", "0.04976931", "0.29669228", "0", "0.05668016", "Other gene"], ["FAM74A4", "26", "4.65202703", "0.02931155", "0.21496006", "0", "0.19230769", "Other gene"], ["FAM74A6", "25", "4.65427928", "0.0262998", "0.21485604", "0", "0.19333333", "Other gene"], ["LRRC1", "23", "3.20157658", "0.05583233", "0.31234611", "0", "0.06126482", "Other gene"], ["PCYT2", "21", "3.31869369", "0.04192798", "0.30132338", "0", "0.05555556", "Other gene"], ["UBC", "18", "2.51351351", "0.42421401", "0.39784946", "0", "0.06050955", "Other gene"], ["BCORL1", "16", "3.4786036", "0.02550435", "0.28747167", "0", "0.08455882", "Other gene"], ["NCOA7", "13", "4.68581081", "0.02298401", "0.21341024", "0", "0.07692308", "Other gene"], ["STX10", "13", "3.48536036", "0.02685944", "0.28691438", "0", "0.07692308", "Other gene"], ["SGK3", "12", "3.35472973", "0.03075664", "0.29808661", "0", "0.11507937", "Other gene"], ["PRKX", "11", "4.67004505", "0.01823525", "0.2141307", "0", "0.18181818", "Other gene"], ["RNF135", "10", "4.73536036", "0.01245585", "0.21117717", "0", "0.2", "Other gene"], ["DFNA5", "9", "3.49436937", "0.01078561", "0.28617467", "0", "0.16339869", "Other gene"]], "row_count": 26, "column_count": 8, "numeric_cells": 156, "header_rows": 1, "locator": "section[24]/table-wrap[2]#tab7"}}, {"id": "asset:table:pmid:33777260:8", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:6cbf384f0c00e50ca5a1a669716338108bb092b6801dfff62c384919bd441507", "bytes": 1818, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[25]/table-wrap[1]#tab8", "version": null, "note": "The topological characteristics of the top 20 nodes in the ceRNA network.", "structure": {"pmcid": "PMC7968449", "section_index": 25, "section_title": "3.11. The ceRNA Network", "row_count": 21, "column_count": 6}, "table": {"label": "Table 8", "caption": "The topological characteristics of the top 20 nodes in the ceRNA network.", "rows": [["Name", "Degree", "Average shortest path length", "Betweenness centrality", "Closeness centrality", "Topological coefficient"], ["XIST", "95", "1.85534591", "0.78103311", "0.53898305", "0.03168803"], ["hsa-miR-340-5p", "21", "2.58490566", "0.07287356", "0.38686131", "0.06802721"], ["MIR155HG", "17", "3.73899371", "0.06134578", "0.26745164", "0.09207161"], ["hsa-miR-4731-5p", "15", "2.7327044", "0.05609297", "0.36593786", "0.07777778"], ["hsa-miR-5590-3p", "15", "2.71069182", "0.03529256", "0.36890951", "0.09122807"], ["hsa-miR-27a-3p", "14", "2.75157233", "0.02751162", "0.36342857", "0.0924812"], ["hsa-miR-27b-3p", "14", "2.75157233", "0.02751162", "0.36342857", "0.0924812"], ["hsa-miR-329-3p", "14", "2.71698113", "0.03095743", "0.36805556", "0.09323308"], ["hsa-miR-362-3p", "13", "2.72327044", "0.02835696", "0.36720554", "0.09797571"], ["LCP1", "13", "3.71069182", "0.0012642", "0.26949153", "0.36153846"], ["hsa-miR-494-3p", "13", "2.72955975", "0.03199119", "0.36635945", "0.10576923"], ["hsa-miR-424-5p", "12", "2.71698113", "0.02811", "0.36805556", "0.12152778"], ["hsa-miR-2682-5p", "12", "2.72327044", "0.02462859", "0.36720554", "0.12457045"], ["hsa-miR-515-5p", "12", "2.78301887", "0.02610732", "0.35932203", "0.10283688"], ["hsa-miR-766-5p", "12", "2.70440252", "0.04407579", "0.36976744", "0.11139456"], ["hsa-miR-449c-5p", "12", "2.72327044", "0.01602592", "0.36720554", "0.13058419"], ["EZH2", "11", "3.40880503", "0.01905647", "0.29335793", "0.27548209"], ["NR4A1", "11", "3.46226415", "0.01590906", "0.28882834", "0.30976431"], ["hsa-miR-34a-5p", "11", "2.77044025", "0.01309547", "0.36095346", "0.13492823"], ["hsa-miR-449a", "11", "2.77044025", "0.01309547", "0.36095346", "0.13492823"]], "row_count": 21, "column_count": 6, "numeric_cells": 116, "header_rows": 1, "locator": "section[25]/table-wrap[1]#tab8"}}], "gaps": ["asset:data:geo:GSE77459 not downloaded", "asset:data:geo:GSE77459 licence not read", "asset:data:geo:GSE92681 not downloaded", "asset:data:geo:GSE92681 licence not read"]}, "analysis": {"state": "complete", "methods": [{"id": "method-1", "family": "correlation_analysis", "specific": "pearson", "label": "Correlation analysis", "dsl_operations": ["pearson_r"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["paired_numeric_columns"], "evidence": {"score": 1.0, "band": "verbatim", "quote": "Based on the GSE92681 dataset, the coexpression status of DElncRNAs and DEGs was calculated by using a statistical method—Pearson correlation."}}, {"id": "method-2", "family": "network_analysis", "specific": "ppi_network", "label": "Network / pathway analysis", "dsl_operations": ["build_graph", "centrality_scores", "pathway_enrich"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["edge_list"], "evidence": {"score": 0.8, "band": "high", "quote": "PPI"}}], "targets": [], "gaps": []}, "capability": {"state": "complete", "requirements": [{"capability_id": "capability:computational_analysis", "label": "Computational analysis platform", "assay_families": ["meta_analysis", "machine_learning", "survival_analysis", "statistical_regression", "pca", "molecular_docking", "network_analysis", "differential_expression", "gwas"], "availability_state": "owned", "tier_unlocked": "R1", "candidate": "Automated Assays Laravel application and simulated adapters"}], "gaps": []}, "readiness": {"state": "complete", "tier": "R1", "blocking_axis": "none", "blocked_on": "nothing:replicable_now", "axes": {"method": {"tier": "R1", "expressible": true, "required_operations": ["pearson_r"], "missing_operations": [], "basis": "The paper names the method it used and the corpus's method extractor maps it onto the DSL catalogue: pearson."}, "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": ["GSE92681", "GSE77459"], "resolved_accessions": ["GSE92681", "GSE77459"], "statements": ["The data used to support the findings of this study are available from the corresponding author upon reasonable request."], "basis": "The paper names GSE92681, GSE77459 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": ["pearson_r"], "assets": ["source:pmid:33777260", "data:geo:GSE77459", "asset:table:pmid:33777260:1", "asset:table:pmid:33777260:2", "asset:table:pmid:33777260:3", "asset:table:pmid:33777260:4", "asset:table:pmid:33777260:5", "asset:table:pmid:33777260:6", "asset:table:pmid:33777260:7", "asset:table:pmid:33777260:8"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE77459"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-10-31T18:28:31Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 3, "usage": {"prompt_tokens": 57309, "completion_tokens": 1468, "cached_tokens": 19208}}, "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:33777260", "type": "paper", "label": "pmid:33777260"}, {"id": "source:pmid:33777260", "type": "manuscript", "label": "PMID 33777260 full text"}, {"id": "data:geo:GSE77459", "type": "dataset", "label": "GEO GSE77459"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:33777260", "type": "paper", "label": "pmid:33777260"}, {"id": "source:pmid:33777260", "type": "manuscript", "label": "PMID 33777260 full text"}, {"id": "data:geo:GSE77459", "type": "dataset", "label": "GEO GSE77459"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-33777260", "type": "extraction", "used": ["source:pmid:33777260"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE77459", "type": "accession_resolution", "used": ["data:geo:GSE77459"], "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:33777260", "parent_hash": "sha256:c994fceab4542fb2d8980aac3c3a737479fb56ff1e967b908b95ae15ae9e8e43", "fork_of": null, "generation": 6}, "gaps": ["asset:data:geo:GSE77459 licence not read", "asset:data:geo:GSE77459 not downloaded", "asset:data:geo:GSE92681 licence not read", "asset:data:geo:GSE92681 not downloaded", "execution.not_run", "review.human_critique", "review.independent_reader", "review.machine_critique"], "assays": [{"role": "analysis", "definition_id": "correlation_analysis", "definition_version": "f2132e96ae6c7a4e", "definition_digest": null, "required_operations": ["pearson_r"], "support_state": "supported", "source_hashes": {"dsl_catalogue": "f2132e96ae6c7a4e"}, "confidence": 1.0, "evidence": ["Based on the GSE92681 dataset, the coexpression status of DElncRNAs and DEGs was calculated by using a statistical method—Pearson correlation."], "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":"2026-11-04T02:15:05+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}}}