Identification of key genes in non-small cell lung cancer by bioinformatics analysis.

{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:31844590", "kind": "science-record", "revision": 7, "content_hash": "sha256:ba5873e2b8c0998a62e7c524ff6876fb021d861f10bbf7dfa54b8348efe27d8d", "created_at": "2026-11-01T15:40:53Z", "updated_at": "2026-11-01T22:01:07Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Identification of key genes in non-small cell lung cancer by bioinformatics analysis.", "doi": "10.7717/peerj.8215", "pmid": "31844590", "authors": ["Li Zhang", "Rui Peng", "Yan Sun", "Jia Wang", "Xinyu Chong", "Zheng Zhang"], "journal": "PeerJ", "year": 2019, "abstract": "BACKGROUND: Non-small cell lung cancer (NSCLC) is one of the most common malignant tumors in the world, and it has become the leading cause of death of malignant tumors. However, its mechanisms are not fully clear. The aim of this study is to investigate the key genes and explore their potential mechanisms involving in NSCLC.\nMETHODS: We downloaded gene expression profiles GSE33532, GSE30219 and GSE19804 from the Gene Expression Omnibus (GEO) database and analyzed them by using GEO2R. Gene Ontology and the Kyoto Encyclopedia of Genes and Genomes were used for the functional and pathway enrichment analysis. We constructed the protein-protein interaction (PPI) network by STRING and visualized it by Cytoscape. Further, we performed module analysis and centrality analysis to find the potential key genes. Finally, we carried on survival analysis of key genes by GEPIA.\nRESULTS: In total, we obtained 685 DEGs. Moreover, GO analysis showed that they were mainly enriched in cell adhesion, proteinaceous extracellular region, heparin binding. KEGG pathway analysis revealed that transcriptional misregulation in cancer, ECM-receptor interaction, cell cycle and p53 signaling pathway were involved in. Furthermore, PPI network was constructed including 249 nodes and 1,027 edges. Additionally, a significant module was found, which included eight candidate genes with high centrality features. Further, among the eight candidate genes, the survival of NSCLC patients with the seven high expression genes were significantly worse, including CDK1, CCNB1, CCNA2, BIRC5, CCNB2, KIAA0101 and MELK. In summary, these identified genes should play an important role in NSCLC, which can provide new insight for NSCLC research.", "claims": [{"id": "claim-method", "statement": "The adjusted P-value (q-value) was regarded as the standard to correct the occurrence of false-positive results using the Benjamini and Hochberg false discovery rate method.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:31844590", "locator": "sections[4] \"Identification of DEGs\" paragraph 2", "quote": "The adjusted P-value (q-value) was regarded as the standard to correct the occurrence of false-positive results using the Benjamini and Hochberg false discovery rate method."}], "state": "complete"}, {"id": "claim-data-access", "statement": "The following information was supplied regarding data availability:The raw measurements are available in Table S1.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:31844590", "locator": "sections[24] \"Data Availability\" paragraph 2", "quote": "The following information was supplied regarding data availability:The raw measurements are available in Table S1."}], "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:31844590"], "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:GSE19804"], "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:GSE19804"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:31844590", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.7717/peerj.8215", "sha256": "sha256:8eb0dc28f7563cbc1a3f1eaf6e23dc143660f8db50a7a0570692ba635526c8a9", "bytes": 40299, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.7717/peerj.8215", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC6911687", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE19804", "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=GSE19804", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE19804", "version": null, "note": "The following information was supplied regarding data availability:The raw measurements are available in Table S1.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The following information was supplied regarding data availability:The raw measurements are available in Table S1.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM494556", "GSM494557", "GSM494558", "GSM494559", "GSM494560", "GSM494561", "GSM494562", "GSM494563", "GSM494564", "GSM494565", "GSM494566", "GSM494567", "GSM494568", "GSM494569", "GSM494570", "GSM494571", "GSM494572", "GSM494573", "GSM494574", "GSM494575", "GSM494576", "GSM494577", "GSM494578", "GSM494579", "GSM494580", "GSM494581", "GSM494582", "GSM494583", "GSM494584", "GSM494585", "GSM494586", "GSM494587", "GSM494588", "GSM494589", "GSM494590", "GSM494591", "GSM494592", "GSM494593", "GSM494594", "GSM494595", "GSM494596", "GSM494597", "GSM494598", "GSM494599", "GSM494600", "GSM494601", "GSM494602", "GSM494603", "GSM494604", "GSM494605", "GSM494606", "GSM494607", "GSM494608", "GSM494609", "GSM494610", "GSM494611", "GSM494612", "GSM494613", "GSM494614", "GSM494615", "GSM494616", "GSM494617", "GSM494618", "GSM494619", "GSM494620", "GSM494621", "GSM494622", "GSM494623", "GSM494624", "GSM494625", "GSM494626", "GSM494627", "GSM494628", "GSM494629", "GSM494630", "GSM494631", "GSM494632", "GSM494633", "GSM494634", "GSM494635", "GSM494636", "GSM494637", "GSM494638", "GSM494639", "GSM494640", "GSM494641", "GSM494642", "GSM494643", "GSM494644", "GSM494645", "GSM494646", "GSM494647", "GSM494648", "GSM494649", "GSM494650", "GSM494651", "GSM494652", "GSM494653", "GSM494654", "GSM494655", "GSM494656", "GSM494657", "GSM494658", "GSM494659", "GSM494660", "GSM494661", "GSM494662", "GSM494663", "GSM494664", "GSM494665", "GSM494666", "GSM494667", "GSM494668", "GSM494669", "GSM494670", "GSM494671", "GSM494672", "GSM494673", "GSM494674", "GSM494675"], "sample_count": 120, "group_sizes": null, "group_sizes_basis": null, "platform": "570", "taxon": "Homo sapiens", "title": "Genome-wide screening of transcriptional modulation in non-smoking female lung cancer in Taiwan", "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:GSE30219", "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=GSE30219", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE30219", "version": null, "note": "The following information was supplied regarding data availability:The raw measurements are available in Table S1.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The following information was supplied regarding data availability:The raw measurements are available in Table S1.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM1465989", "GSM1465990", "GSM1465991", "GSM1465992", "GSM1465993", "GSM1465994", "GSM1465995", "GSM1465996", "GSM1465997", "GSM1465998", "GSM1465999", "GSM748053", "GSM748054", "GSM748055", "GSM748056", "GSM748057", "GSM748058", "GSM748059", "GSM748060", "GSM748061", "GSM748062", "GSM748063", "GSM748064", "GSM748065", "GSM748066", "GSM748067", "GSM748068", "GSM748069", "GSM748070", "GSM748071", "GSM748072", "GSM748073", "GSM748074", "GSM748075", "GSM748076", "GSM748077", "GSM748078", "GSM748079", "GSM748080", "GSM748081", "GSM748083", "GSM748084", "GSM748085", "GSM748086", "GSM748087", "GSM748088", "GSM748089", "GSM748090", "GSM748091", "GSM748092", "GSM748093", "GSM748094", "GSM748095", "GSM748096", "GSM748097", "GSM748098", "GSM748099", "GSM748100", "GSM748101", "GSM748102", "GSM748103", "GSM748104", "GSM748105", "GSM748106", "GSM748107", "GSM748108", "GSM748109", "GSM748110", "GSM748111", "GSM748112", "GSM748113", "GSM748115", "GSM748116", "GSM748117", "GSM748118", "GSM748119", "GSM748120", "GSM748121", "GSM748122", "GSM748123", "GSM748124", "GSM748125", "GSM748126", "GSM748127", "GSM748128", "GSM748129", "GSM748130", "GSM748131", "GSM748132", "GSM748133", "GSM748134", "GSM748135", "GSM748136", "GSM748137", "GSM748138", "GSM748139", "GSM748140", "GSM748141", "GSM748142", "GSM748143", "GSM748144", "GSM748145", "GSM748146", "GSM748147", "GSM748148", "GSM748149", "GSM748150", "GSM748151", "GSM748152", "GSM748153", "GSM748154", "GSM748155", "GSM748156", "GSM748157", "GSM748158", "GSM748159", "GSM748160", "GSM748161", "GSM748162", "GSM748163", "GSM748164", "GSM748165", "GSM748166", "GSM748167", "GSM748168", "GSM748169", "GSM748170", "GSM748171", "GSM748172", "GSM748173", "GSM748174", "GSM748175", "GSM748176", "GSM748177", "GSM748178", "GSM748179", "GSM748180", "GSM748181", "GSM748182", "GSM748183", "GSM748184", "GSM748185", "GSM748186", "GSM748187", "GSM748188", "GSM748189", "GSM748191", "GSM748192", "GSM748193", "GSM748195", "GSM748196", "GSM748197", "GSM748198", "GSM748199", "GSM748200", "GSM748201", "GSM748202", "GSM748203", "GSM748206", "GSM748207", "GSM748209", "GSM748210", "GSM748211", "GSM748212", "GSM748213", "GSM748214", "GSM748215", "GSM748216", "GSM748217", "GSM748218", "GSM748219", "GSM748220", "GSM748221", "GSM748222", "GSM748223", "GSM748224", "GSM748225", "GSM748226", "GSM748227", "GSM748228", "GSM748229", "GSM748232", "GSM748233", "GSM748234", "GSM748235", "GSM748239", "GSM748240", "GSM748242", "GSM748243", "GSM748244", "GSM748245", "GSM748246", "GSM748247", "GSM748248", "GSM748249", "GSM748250", "GSM748251", "GSM748252", "GSM748253", "GSM748254", "GSM748255", "GSM748256", "GSM748257", "GSM748258", "GSM748259", "GSM748260", "GSM748261", "GSM748262", "GSM748263", "GSM748264", "GSM748265", "GSM748266", "GSM748267", "GSM748268", "GSM748269", "GSM748270", "GSM748271", "GSM748272", "GSM748273", "GSM748274", "GSM748275", "GSM748276", "GSM748277", "GSM748278", "GSM748279", "GSM748280", "GSM748281", "GSM748282", "GSM748283", "GSM748284", "GSM748285", "GSM748286", "GSM748287", "GSM748288", "GSM748291", "GSM748292", "GSM748294", "GSM748295", "GSM748296", "GSM748297", "GSM748298", "GSM748299", "GSM748300", "GSM748301", "GSM748302", "GSM748303", "GSM748304", "GSM748305", "GSM748306", "GSM748307", "GSM748308", "GSM748309", "GSM748310", "GSM748311", "GSM748312", "GSM748313", "GSM748314", "GSM748315", "GSM748316", "GSM748317", "GSM748318", "GSM748319", "GSM748320", "GSM748321", "GSM748323", "GSM748324", "GSM748325", "GSM748326", "GSM748327", "GSM748328", "GSM748329", "GSM748330", "GSM748331", "GSM748332", "GSM748333", "GSM748334", "GSM748335", "GSM748336", "GSM748337", "GSM748338", "GSM748339", "GSM748341", "GSM748342", "GSM748343", "GSM748344", "GSM748345", "GSM748346", "GSM748347", "GSM748348", "GSM748349", "GSM748350", "GSM748351", "GSM748352", "GSM748353", "GSM748354", "GSM748355", "GSM748356", "GSM748357", "GSM748358", "GSM748359", "GSM748360", "GSM748361", "GSM748362", "GSM748363", "GSM748364", "GSM748365", "GSM748366"], "sample_count": 307, "group_sizes": null, "group_sizes_basis": null, "platform": "570", "taxon": "Homo sapiens", "title": "\"Off-context\" gene expression in lung cancer identifies a group of metastatic-prone tumors", "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:GSE33532", "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=GSE33532", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE33532", "version": null, "note": "The following information was supplied regarding data availability:The raw measurements are available in Table S1.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The following information was supplied regarding data availability:The raw measurements are available in Table S1.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM835268", "GSM835269", "GSM835270", "GSM835271", "GSM835272", "GSM835273", "GSM835274", "GSM835275", "GSM835276", "GSM835277", "GSM835278", "GSM835279", "GSM835280", "GSM835281", "GSM835282", "GSM835283", "GSM835284", "GSM835285", "GSM835286", "GSM835287", "GSM835288", "GSM835289", "GSM835290", "GSM835291", "GSM835292", "GSM835293", "GSM835294", "GSM835295", "GSM835296", "GSM835297", "GSM835298", "GSM835299", "GSM835300", "GSM835301", "GSM835302", "GSM835303", "GSM835304", "GSM835305", "GSM835306", "GSM835307", "GSM835308", "GSM835309", "GSM835310", "GSM835311", "GSM835312", "GSM835313", "GSM835314", "GSM835315", "GSM835316", "GSM835317", "GSM835318", "GSM835319", "GSM835320", "GSM835321", "GSM835322", "GSM835323", "GSM835324", "GSM835325", "GSM835326", "GSM835327", "GSM835328", "GSM835329", "GSM835330", "GSM835331", "GSM835332", "GSM835333", "GSM835334", "GSM835335", "GSM835336", "GSM835337", "GSM835338", "GSM835339", "GSM835340", "GSM835341", "GSM835342", "GSM835343", "GSM835344", "GSM835345", "GSM835346", "GSM835347", "GSM835348", "GSM835349", "GSM835350", "GSM835351", "GSM835352", "GSM835353", "GSM835354", "GSM835355", "GSM835356", "GSM835357", "GSM835358", "GSM835359", "GSM835360", "GSM835361", "GSM835362", "GSM835363", "GSM835364", "GSM835365", "GSM835366", "GSM835367"], "sample_count": 100, "group_sizes": null, "group_sizes_basis": null, "platform": "570", "taxon": "Homo sapiens", "title": "Intratumor heterogeneity of gene expression profiles in early stage non-small cell lung cancer (NSCLC)", "resolution_checked_at": "2026-11-01T15:39:54Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "asset:table:pmid:31844590:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:edba630d8b87512dde881b6c9cd94b1c58e09495b13157215900bf825e1c9a33", "bytes": 1160, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[14]/table-wrap[1]#table-1", "version": null, "note": "The top 25% centrality parameters of 16 candidate molecules in the PPI network.", "structure": {"pmcid": "PMC6911687", "section_index": 7, "section_title": "Centrality analysis of PPI network", "row_count": 17, "column_count": 5}, "table": {"label": "Table 1", "caption": "The top 25% centrality parameters of 16 candidate molecules in the PPI network.", "rows": [["Genes name", "Degree", "Betweenness", "Closeness", "Eigenvector"], ["CDK1", "42", "0.05442045", "0.34029851", "0.34029851"], ["PRKCB", "10", "0.0897726", "0.35130971", "0.006357714"], ["EDN1", "26", "0.25859441", "0.40140845", "0.012624903"], ["TIMP3", "13", "0.05680489", "0.33878158", "0.005104212"], ["MELK", "36", "0.01845249", "0.33628319", "0.17740285"], ["SPP1", "13", "0.03509843", "0.34131737", "0.02659089"], ["PLA2G1B", "9", "0.05464156", "0.33878158", "0.006098443"], ["BIRC5", "37", "0.0424209", "0.36018957", "0.1761744"], ["CCNB1", "40", "0.01947945", "0.32805755", "0.18236643"], ["KIAA0101", "37", "0.0555325", "0.34285714", "0.17740497"], ["CCNA2", "40", "0.02089539", "0.32900433", "0.18205161"], ["EZH2", "38", "0.09184724", "0.36952998", "0.15754144"], ["CCNB2", "37", "0.01609439", "0.36952998", "0.15754144"], ["LRRK2", "22", "0.16920811", "0.36190476", "0.012165083"], ["SELP", "11", "0.05407089", "0.34131737", "0.006136451"], ["KLF4", "9", "0.05250658", "0.34915773", "0.016391514"]], "row_count": 17, "column_count": 5, "numeric_cells": 65, "header_rows": 1, "locator": "section[14]/table-wrap[1]#table-1"}}, {"id": "asset:table:pmid:31844590:2", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:edba630d8b87512dde881b6c9cd94b1c58e09495b13157215900bf825e1c9a33", "bytes": 1160, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[14]/table-wrap[1]#table-1", "version": null, "note": "The top 25% centrality parameters of 16 candidate molecules in the PPI network.", "structure": {"pmcid": "PMC6911687", "section_index": 14, "section_title": "Centrality analysis of PPI network", "row_count": 17, "column_count": 5}, "table": {"label": "Table 1", "caption": "The top 25% centrality parameters of 16 candidate molecules in the PPI network.", "rows": [["Genes name", "Degree", "Betweenness", "Closeness", "Eigenvector"], ["CDK1", "42", "0.05442045", "0.34029851", "0.34029851"], ["PRKCB", "10", "0.0897726", "0.35130971", "0.006357714"], ["EDN1", "26", "0.25859441", "0.40140845", "0.012624903"], ["TIMP3", "13", "0.05680489", "0.33878158", "0.005104212"], ["MELK", "36", "0.01845249", "0.33628319", "0.17740285"], ["SPP1", "13", "0.03509843", "0.34131737", "0.02659089"], ["PLA2G1B", "9", "0.05464156", "0.33878158", "0.006098443"], ["BIRC5", "37", "0.0424209", "0.36018957", "0.1761744"], ["CCNB1", "40", "0.01947945", "0.32805755", "0.18236643"], ["KIAA0101", "37", "0.0555325", "0.34285714", "0.17740497"], ["CCNA2", "40", "0.02089539", "0.32900433", "0.18205161"], ["EZH2", "38", "0.09184724", "0.36952998", "0.15754144"], ["CCNB2", "37", "0.01609439", "0.36952998", "0.15754144"], ["LRRK2", "22", "0.16920811", "0.36190476", "0.012165083"], ["SELP", "11", "0.05407089", "0.34131737", "0.006136451"], ["KLF4", "9", "0.05250658", "0.34915773", "0.016391514"]], "row_count": 17, "column_count": 5, "numeric_cells": 65, "header_rows": 1, "locator": "section[14]/table-wrap[1]#table-1"}}], "gaps": ["asset:data:geo:GSE19804 not downloaded", "asset:data:geo:GSE19804 licence not read", "asset:data:geo:GSE30219 not downloaded", "asset:data:geo:GSE30219 licence not read", "asset:data:geo:GSE33532 not downloaded", "asset:data:geo:GSE33532 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": 0.7, "band": "medium", "quote": "pathway enrichment"}}, {"id": "method-3", "family": "network_analysis", "specific": "centrality", "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": "centrality"}}, {"id": "method-4", "family": null, "specific": null, "label": "Benjamini–Hochberg false discovery rate correction", "dsl_operations": [], "missing_operations": [], "expressible": null, "parameters": {}, "data_shapes": [], "evidence": {"score": 1.0, "band": "verbatim", "quote": "The adjusted P-value (q-value) was regarded as the standard to correct the occurrence of false-positive results using the Benjamini and Hochberg false discovery rate method."}}], "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": ["GSE33532", "GSE30219", "GSE19804"], "resolved_accessions": ["GSE33532", "GSE30219", "GSE19804"], "statements": ["The following information was supplied regarding data availability:The raw measurements are available in Table S1."], "basis": "The paper names GSE33532, GSE30219, GSE19804 in Gene Expression Omnibus (GEO) and the accession resolves in the repository. No dataset was downloaded and no licence was read."}}, "can_run": {"dsl_operations": ["build_graph", "centrality_scores", "pathway_enrich"], "assets": ["source:pmid:31844590", "data:geo:GSE19804", "asset:table:pmid:31844590:1", "asset:table:pmid:31844590:2"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE19804"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-10-31T18:17:23Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 3, "usage": {"prompt_tokens": 32888, "completion_tokens": 1450, "cached_tokens": 792}}, "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:31844590", "type": "paper", "label": "pmid:31844590"}, {"id": "source:pmid:31844590", "type": "manuscript", "label": "PMID 31844590 full text"}, {"id": "data:geo:GSE19804", "type": "dataset", "label": "GEO GSE19804"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:31844590", "type": "paper", "label": "pmid:31844590"}, {"id": "source:pmid:31844590", "type": "manuscript", "label": "PMID 31844590 full text"}, {"id": "data:geo:GSE19804", "type": "dataset", "label": "GEO GSE19804"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-31844590", "type": "extraction", "used": ["source:pmid:31844590"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE19804", "type": "accession_resolution", "used": ["data:geo:GSE19804"], "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:31844590", "parent_hash": "sha256:27edc98974733ffe1a46bdf52523037e554c279d8e072ba8599e8ffe357b1a40", "fork_of": null, "generation": 6}, "gaps": ["asset:data:geo:GSE19804 licence not read", "asset:data:geo:GSE19804 not downloaded", "asset:data:geo:GSE30219 licence not read", "asset:data:geo:GSE30219 not downloaded", "asset:data:geo:GSE33532 licence not read", "asset:data:geo:GSE33532 not downloaded", "execution.not_run", "method.reader_named_unmapped", "review.human_critique", "review.independent_reader", "review.machine_critique"], "assays": [{"role": "analysis", "definition_id": "network_analysis", "definition_version": "f2132e96ae6c7a4e", "definition_digest": null, "required_operations": ["build_graph", "centrality_scores", "pathway_enrich"], "support_state": "supported", "source_hashes": {"dsl_catalogue": "f2132e96ae6c7a4e"}, "confidence": 0.7, "evidence": ["protein-protein interaction"], "order_basis": "analysis_only", "id": "assay:1"}]}