Identification of significant genes in non-small cell lung cancer by bioinformatics analyses.

{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:35117799", "kind": "science-record", "revision": 9, "content_hash": "sha256:d560045bc11e2a5d5daa97d6d4e920989aa19d40027b3425d8bee872d853aed2", "created_at": "2026-11-01T17:36:52Z", "updated_at": "2026-11-01T23:46:23Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Identification of significant genes in non-small cell lung cancer by bioinformatics analyses.", "doi": "10.21037/tcr-19-2596", "pmid": "35117799", "authors": ["Xia Ye", "Qian Gao", "Jie Wu", "Lin Zhou", "Min Tao"], "journal": "Translational cancer research", "year": 2020, "abstract": "BACKGROUND: Lung cancer is the most malignant cancer featured with undesirable prognosis. It is urgent to identify novel biomarkers to improve both diagnosis and prognosis. The purpose of the study was to identify significant genes involved in lung cancer through bioinformatic methods and reveal potential underlying mechanisms.\nMETHODS: Three datasets GSE19188, GSE27262, GSE118375, containing 122 lung cancer and 96 normal tissues, were available from GEO database. GEO2R and Venn diagram online software were applied to pick out differentially expressed genes (DEGs). Next, we used the Database for Annotation, Visualization and Integrated Discovery (DAVID) to analyze Kyoto Encyclopedia of Gene and Genome (KEGG) pathway and gene ontology (GO) enrichment, followed by protein-protein interaction (PPI) of these DEGs visualized by cytoscape. The MCODE plug-in was performed to construct a module complex of DEGs. In addition, Kaplan-Meier analysis was implemented for analysis of overall survival. To further validate the expression of these genes, Gene Expression Profiling Interactive Analysis (GEPIA) was used.\nRESULTS: A total of 149 DEGs were identified, including 127 downregulated genes and 22 upregulated genes. KEGG analysis revealed that the DEGs were mainly enriched in ECM-receptor interaction, Vascular smooth muscle contraction, and PPAR signaling pathway. GO analysis of DEGs showed that significant functional enrichment of angiogenesis, cell adhesion, and vasculogenesis. 13 genes were selected as hub genes based on MCODE, and 11 of 13 genes had a significance. The results of GEPIA were consistent with survival analysis. Furthermore, reanalysis of these genes found they were significantly enriched in ECM-receptor interaction and PI3K-Akt signaling pathway.\nCONCLUSIONS: We have identified several key genes, which could be potential diagnostic and prognostic biomarker as well as therapy targets.", "claims": [{"id": "claim-data-access", "statement": "Availability of data and materials: The datasets generated and/or analyzed during the study are available from the corresponding author upon reasonable request.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:35117799", "locator": "sections[16] \"Acknowledgments\" paragraph 3", "quote": "Availability of data and materials: The datasets generated and/or analyzed during the study are available from the corresponding author upon reasonable request."}], "state": "complete"}, {"id": "claim-target-result", "statement": "A total of 149 DEGs were identified, including 127 downregulated genes and 22 upregulated genes.", "kind": "qualitative", "target": null, "evidence": [{"asset": "source:pmid:35117799", "locator": "sections[0] \"Abstract\" paragraph 3", "quote": "A total of 149 DEGs were identified, including 127 downregulated genes and 22 upregulated genes."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "complete", "objective": "A total of 149 DEGs were identified, including 127 downregulated genes and 22 upregulated genes.", "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:35117799"], "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:GSE118370"], "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:GSE118370"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:35117799", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.21037/tcr-19-2596", "sha256": "sha256:bf6d108438f0cc8ff51d76bdae88de327fd9c475c70f3d7d98ce71adba0fc371", "bytes": 27702, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.21037/tcr-19-2596", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC8799091", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE118370", "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=GSE118370", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE118370", "version": null, "note": "Availability of data and materials: The datasets generated and/or analyzed during the study are available from the corresponding author upon reasonable request.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "Availability of data and materials: The datasets generated and/or analyzed during the study are available from the corresponding author upon reasonable request.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM3325818", "GSM3325819", "GSM3325820", "GSM3325821", "GSM3325822", "GSM3325823", "GSM3325824", "GSM3325825", "GSM3325826", "GSM3325827", "GSM3325828", "GSM3325829"], "sample_count": 12, "group_sizes": null, "group_sizes_basis": null, "platform": "570", "taxon": "Homo sapiens", "title": "Expression data from lung adenocarcinoma tissues and paired normal lung tissues", "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:GSE19188", "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=GSE19188", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE19188", "version": null, "note": "Availability of data and materials: The datasets generated and/or analyzed during the study are available from the corresponding author upon reasonable request.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "Availability of data and materials: The datasets generated and/or analyzed during the study are available from the corresponding author upon reasonable request.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM475656", "GSM475657", "GSM475658", "GSM475659", "GSM475660", "GSM475661", "GSM475662", "GSM475663", "GSM475664", "GSM475665", "GSM475666", "GSM475667", "GSM475668", "GSM475669", "GSM475670", "GSM475671", "GSM475672", "GSM475673", "GSM475674", "GSM475675", "GSM475676", "GSM475677", "GSM475678", "GSM475679", "GSM475680", "GSM475681", "GSM475682", "GSM475683", "GSM475684", "GSM475685", "GSM475686", "GSM475687", "GSM475688", "GSM475689", "GSM475690", "GSM475691", "GSM475692", "GSM475693", "GSM475694", "GSM475695", "GSM475696", "GSM475697", "GSM475698", "GSM475699", "GSM475700", "GSM475701", "GSM475702", "GSM475703", "GSM475704", "GSM475705", "GSM475706", "GSM475707", "GSM475708", "GSM475709", "GSM475710", "GSM475711", "GSM475712", "GSM475713", "GSM475714", "GSM475715", "GSM475716", "GSM475717", "GSM475718", "GSM475719", "GSM475720", "GSM475721", "GSM475722", "GSM475723", "GSM475724", "GSM475725", "GSM475726", "GSM475727", "GSM475728", "GSM475729", "GSM475730", "GSM475731", "GSM475732", "GSM475733", "GSM475734", "GSM475735", "GSM475736", "GSM475737", "GSM475738", "GSM475739", "GSM475740", "GSM475741", "GSM475742", "GSM475743", "GSM475744", "GSM475745", "GSM475746", "GSM475747", "GSM475748", "GSM475749", "GSM475750", "GSM475751", "GSM475752", "GSM475753", "GSM475754", "GSM475755", "GSM475756", "GSM475757", "GSM475758", "GSM475759", "GSM475760", "GSM475761", "GSM475762", "GSM475763", "GSM475764", "GSM475765", "GSM475766", "GSM475767", "GSM475768", "GSM475769", "GSM475770", "GSM475771", "GSM475772", "GSM475773", "GSM475774", "GSM475775", "GSM475776", "GSM475777", "GSM475778", "GSM475779", "GSM475780", "GSM475781", "GSM475782", "GSM475783", "GSM475784", "GSM475785", "GSM475786", "GSM475787", "GSM475788", "GSM475789", "GSM475790", "GSM475791", "GSM475792", "GSM475793", "GSM475794", "GSM475795", "GSM475796", "GSM475797", "GSM475798", "GSM475799", "GSM475800", "GSM475801", "GSM475802", "GSM475803", "GSM475804", "GSM475805", "GSM475806", "GSM475807", "GSM475808", "GSM475809", "GSM475810", "GSM475811"], "sample_count": 156, "group_sizes": null, "group_sizes_basis": null, "platform": "570", "taxon": "Homo sapiens", "title": "Expression data for early stage 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": "data:geo:GSE27262", "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=GSE27262", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE27262", "version": null, "note": "Availability of data and materials: The datasets generated and/or analyzed during the study are available from the corresponding author upon reasonable request.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "Availability of data and materials: The datasets generated and/or analyzed during the study are available from the corresponding author upon reasonable request.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM673870", "GSM673871", "GSM673872", "GSM673873", "GSM673874", "GSM673875", "GSM673876", "GSM673877", "GSM673878", "GSM673879", "GSM673880", "GSM673881", "GSM673882", "GSM673883", "GSM673884", "GSM673885", "GSM673886", "GSM673887", "GSM673888", "GSM673889", "GSM673890", "GSM673891", "GSM673892", "GSM673893", "GSM673894", "GSM673895", "GSM673896", "GSM673897", "GSM673898", "GSM673899", "GSM673900", "GSM673901", "GSM673902", "GSM673903", "GSM673904", "GSM673905", "GSM673906", "GSM673907", "GSM673908", "GSM673909", "GSM673910", "GSM673911", "GSM673912", "GSM673913", "GSM673914", "GSM673915", "GSM673916", "GSM673917", "GSM673918", "GSM673919"], "sample_count": 50, "group_sizes": null, "group_sizes_basis": null, "platform": "570", "taxon": "Homo sapiens", "title": "Gene expression profiling of Non-small cell 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:GSE118375", "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=GSE118375", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE118375", "version": null, "note": "Availability of data and materials: The datasets generated and/or analyzed during the study are available from the corresponding author upon reasonable request.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "Availability of data and materials: The datasets generated and/or analyzed during the study are available from the corresponding author upon reasonable request.", "access_statement_kind": "data_availability_statement", "sample_accessions": [], "sample_count": null, "group_sizes": null, "group_sizes_basis": null, "platform": null, "taxon": null, "title": null, "resolution_checked_at": "2026-11-01T23:38:31Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}], "gaps": ["asset:data:geo:GSE118370 not downloaded", "asset:data:geo:GSE118370 licence not read", "asset:data:geo:GSE19188 not downloaded", "asset:data:geo:GSE19188 licence not read", "asset:data:geo:GSE27262 not downloaded", "asset:data:geo:GSE27262 licence not read", "asset:data:geo:GSE118375 not downloaded", "asset:data:geo:GSE118375 licence not read"]}, "analysis": {"state": "complete", "methods": [{"id": "method-1", "family": "survival_analysis", "specific": "kaplan_meier", "label": "Survival analysis", "dsl_operations": ["survival_km"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["time_to_event_with_censoring"], "evidence": {"score": 0.7, "band": "medium", "quote": "Kaplan-Meier"}}, {"id": "method-2", "family": "survival_analysis", "specific": "log_rank_test", "label": "Survival analysis", "dsl_operations": ["logrank_test"], "missing_operations": [], "expressible": true, "parameters": {"hazard_ratio": "The HR with 95% confidence int", "p_value": "intervals and log rank P value were computed and displ"}, "data_shapes": ["time_to_event_with_censoring"], "evidence": {"score": 0.8, "band": "high", "quote": "log rank"}}, {"id": "method-3", "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-4", "family": "network_analysis", "specific": "pathway_enrichment", "label": "Network / pathway analysis", "dsl_operations": ["pathway_enrich"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["edge_list"], "evidence": {"score": 0.8, "band": "high", "quote": "pathway enrichment"}}], "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": ["survival_km"], "missing_operations": [], "basis": "The paper names the method it used and the corpus's method extractor maps it onto the DSL catalogue: kaplan_meier."}, "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": ["GSE19188", "GSE27262", "GSE118370", "GSE118375"], "resolved_accessions": ["GSE19188", "GSE27262", "GSE118370"], "statements": ["Availability of data and materials: The datasets generated and/or analyzed during the study are available from the corresponding author upon reasonable request."], "basis": "The paper names GSE19188, GSE27262, GSE118370 in Gene Expression Omnibus database at NCBI and the accession resolves in the repository. No dataset was downloaded and no licence was read."}}, "can_run": {"dsl_operations": ["survival_km"], "assets": ["source:pmid:35117799", "data:geo:GSE118370"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE118370"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-11-01T17:32:49Z", "independence": "single_reader"}, "evidence_check": {"method": null, "availability": "verbatim"}, "calls": 5, "usage": {"prompt_tokens": 8570, "completion_tokens": 2345, "cached_tokens": 128}}, "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:35117799", "type": "paper", "label": "pmid:35117799"}, {"id": "source:pmid:35117799", "type": "manuscript", "label": "PMID 35117799 full text"}, {"id": "data:geo:GSE118370", "type": "dataset", "label": "GEO GSE118370"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:35117799", "type": "paper", "label": "pmid:35117799"}, {"id": "source:pmid:35117799", "type": "manuscript", "label": "PMID 35117799 full text"}, {"id": "data:geo:GSE118370", "type": "dataset", "label": "GEO GSE118370"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-35117799", "type": "extraction", "used": ["source:pmid:35117799"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE118370", "type": "accession_resolution", "used": ["data:geo:GSE118370"], "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:35117799", "parent_hash": "sha256:c9601bc06bd313281a018a80c66b579751f0a39f2f1f7bf492a3630e65ae0c6e", "fork_of": null, "generation": 8}, "gaps": ["asset:data:geo:GSE118370 licence not read", "asset:data:geo:GSE118370 not downloaded", "asset:data:geo:GSE118375 licence not read", "asset:data:geo:GSE118375 not downloaded", "asset:data:geo:GSE19188 licence not read", "asset:data:geo:GSE19188 not downloaded", "asset:data:geo:GSE27262 licence not read", "asset:data:geo:GSE27262 not downloaded", "execution.not_run", "review.human_critique", "review.independent_reader", "review.machine_critique"], "assays": [{"role": "analysis", "definition_id": "survival_analysis", "definition_version": "f2132e96ae6c7a4e", "definition_digest": null, "required_operations": ["survival_km"], "support_state": "supported", "source_hashes": {"dsl_catalogue": "f2132e96ae6c7a4e"}, "confidence": 0.7, "evidence": ["Kaplan-Meier"], "order_basis": "analysis_only", "id": "assay:1"}]}