Identification of differential protein-coding gene expressions in early phase lung adenocarcinoma.

{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:29266838", "kind": "science-record", "revision": 7, "content_hash": "sha256:369e6d0ace5a20a6e64933319be3e8532c4ee623475134dc30c842700db0eadf", "created_at": "2026-11-01T15:40:30Z", "updated_at": "2026-11-01T21:59:38Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Identification of differential protein-coding gene expressions in early phase lung adenocarcinoma.", "doi": "10.1111/1759-7714.12569", "pmid": "29266838", "authors": ["Li-Na Zhou", "Shi-Cheng Li", "Xue-Ying Li", "Hong Ge", "Hong-Mei Li"], "journal": "Thoracic cancer", "year": 2018, "abstract": "BACKGROUND: The diagnosis of early phase lung adenocarcinoma (LADC) is associated with therapeutic strategy, effect, and survival time. However, the sensitive biomarkers of early phase LADC are still unclear. This study aimed to identify protein-coding genes that can be used as biomarkers of early stage LADC.\nMETHODS: Gene microarray analysis was performed to identify key hub genes that show different expression in lung adenocarcinoma compared to normal tissues. The microarray data of lung adenocarcinoma in stages IA, IB, IIA, IIB, and normal tissues (GSE10072) were downloaded from a free online database, Gene Expression Omnibus (GEO).\nRESULTS: A total of 572 differentially expressed genes (DEGs) were identified between early phase lung adenocarcinoma and normal tissues using R software. Database for Annotation, Visualization and Integrated Discovery online tools were used to obtain Gene Ontology analysis and the Kyoto Encyclopedia of Genes and Genomes was used to analyze DEGs. Cytoscape software was used to express the protein-protein interaction network. We found that some cancer-related Gene Ontology terms and pathways (e.g. cell adhesion, cell surface receptor signaling pathway, PI3K-Akt signaling pathway) were significantly enriched in DEGs.\nCONCLUSION: Protein-coding genes JUN, FYN, CAV1, and SFN may play vital roles in the progress of early-stage lung adenocarcinoma. Consequently, through bioinformatics analysis, the key genes could be established to provide more potential references for the therapeutic targets of lung adenocarcinoma.", "claims": [{"id": "claim-method", "statement": "Kaplan–Meier survival and univariate Cox proportional hazards regression analyses were performed for the hub genes", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:29266838", "locator": "sections[11] \"Survival analysis of hub genes\" paragraph 2", "quote": "Kaplan–Meier survival and univariate Cox proportional hazards regression analyses were performed for the hub genes"}], "state": "complete"}, {"id": "claim-data-access", "statement": "The microarray data obtained for this study were available in the GEO database under the expression dataset profile of GSE10072, based on the GPL96 platform.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:29266838", "locator": "sections[3] \"Microarray data\" paragraph 2", "quote": "The microarray data obtained for this study were available in the GEO database under the expression dataset profile of GSE10072, based on the GPL96 platform."}], "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:29266838"], "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:GSE10072"], "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:GSE10072"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:29266838", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1111/1759-7714.12569", "sha256": "sha256:51af4476add2566a60428a6e8a579e676f28cc2a9410966021916d1377b9a554", "bytes": 16860, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1111/1759-7714.12569", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC5792719", "source": "europe_pmc_fulltext", "coverage": "whole_body_without_references", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE10072", "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=GSE10072", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE10072", "version": null, "note": "The microarray data obtained for this study were available in the GEO database under the expression dataset profile of GSE10072, based on the GPL96 platform.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The microarray data obtained for this study were available in the GEO database under the expression dataset profile of GSE10072, based on the GPL96 platform.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM254625", "GSM254626", "GSM254627", "GSM254628", "GSM254629", "GSM254630", "GSM254631", "GSM254632", "GSM254633", "GSM254634", "GSM254635", "GSM254636", "GSM254637", "GSM254638", "GSM254639", "GSM254640", "GSM254641", "GSM254642", "GSM254643", "GSM254644", "GSM254645", "GSM254646", "GSM254647", "GSM254648", "GSM254649", "GSM254650", "GSM254651", "GSM254652", "GSM254653", "GSM254654", "GSM254655", "GSM254656", "GSM254657", "GSM254658", "GSM254659", "GSM254660", "GSM254661", "GSM254662", "GSM254663", "GSM254664", "GSM254665", "GSM254666", "GSM254667", "GSM254668", "GSM254669", "GSM254670", "GSM254671", "GSM254672", "GSM254673", "GSM254674", "GSM254675", "GSM254676", "GSM254677", "GSM254678", "GSM254679", "GSM254680", "GSM254681", "GSM254682", "GSM254683", "GSM254684", "GSM254685", "GSM254686", "GSM254687", "GSM254688", "GSM254689", "GSM254690", "GSM254691", "GSM254692", "GSM254693", "GSM254694", "GSM254695", "GSM254696", "GSM254697", "GSM254698", "GSM254699", "GSM254700", "GSM254701", "GSM254702", "GSM254703", "GSM254704", "GSM254705", "GSM254706", "GSM254707", "GSM254708", "GSM254709", "GSM254710", "GSM254711", "GSM254712", "GSM254713", "GSM254714", "GSM254715", "GSM254716", "GSM254717", "GSM254718", "GSM254719", "GSM254720", "GSM254721", "GSM254722", "GSM254723", "GSM254724", "GSM254725", "GSM254726", "GSM254727", "GSM254728", "GSM254729", "GSM254730", "GSM254731"], "sample_count": 107, "group_sizes": null, "group_sizes_basis": null, "platform": "96", "taxon": "Homo sapiens", "title": "Gene expression signature of cigarette smoking and its role in lung adenocarcinoma development and survival", "resolution_checked_at": "2026-11-01T15:30:21Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}], "gaps": ["asset:data:geo:GSE10072 not downloaded", "asset:data:geo:GSE10072 licence not read"]}, "analysis": {"state": "complete", "methods": [{"id": "method-1", "family": "survival_analysis", "specific": "cox_proportional_hazards", "label": "Survival analysis", "dsl_operations": ["cox_ph"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["time_to_event_with_censoring"], "evidence": {"score": 1.0, "band": "verbatim", "quote": "Kaplan–Meier survival and univariate Cox proportional hazards regression analyses were performed for the hub genes"}}, {"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": 0.7, "band": "medium", "quote": "protein-protein interaction"}}], "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": ["cox_ph"], "missing_operations": [], "basis": "The paper names the method it used and the corpus's method extractor maps it onto the DSL catalogue: cox_proportional_hazards."}, "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": ["GSE10072"], "resolved_accessions": ["GSE10072"], "statements": ["The microarray data obtained for this study were available in the GEO database under the expression dataset profile of GSE10072, based on the GPL96 platform."], "basis": "The paper names GSE10072 in GEO and the accession resolves in the repository. No dataset was downloaded and no licence was read."}}, "can_run": {"dsl_operations": ["cox_ph"], "assets": ["source:pmid:29266838", "data:geo:GSE10072"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE10072"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": null, "independence": "same_provider"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 0, "usage": {}}, "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:29266838", "type": "paper", "label": "pmid:29266838"}, {"id": "source:pmid:29266838", "type": "manuscript", "label": "PMID 29266838 full text"}, {"id": "data:geo:GSE10072", "type": "dataset", "label": "GEO GSE10072"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:29266838", "type": "paper", "label": "pmid:29266838"}, {"id": "source:pmid:29266838", "type": "manuscript", "label": "PMID 29266838 full text"}, {"id": "data:geo:GSE10072", "type": "dataset", "label": "GEO GSE10072"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-29266838", "type": "extraction", "used": ["source:pmid:29266838"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE10072", "type": "accession_resolution", "used": ["data:geo:GSE10072"], "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:29266838", "parent_hash": "sha256:341a9def8aecc3db31def0410f5c284f9cfba3e633451ea1ab1fc9a5f5b4cbad", "fork_of": null, "generation": 6}, "gaps": ["asset:data:geo:GSE10072 licence not read", "asset:data:geo:GSE10072 not downloaded", "execution.not_run", "review.human_critique", "review.independent_reader", "review.machine_critique"], "assays": [{"role": "data_generation", "definition_id": "microarray", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.99, "evidence": ["iomarkers of early stage LADC. METHODS: Gene microarray analysis was performed to identify key hub g", "enocarcinoma compared to normal tissues. The microarray data of lung adenocarcinoma in stages IA, IB"], "order_basis": "paper_text_order:379", "id": "assay:1"}, {"role": "analysis", "definition_id": "survival_analysis", "definition_version": "f2132e96ae6c7a4e", "definition_digest": null, "required_operations": ["cox_ph"], "support_state": "supported", "source_hashes": {"dsl_catalogue": "f2132e96ae6c7a4e"}, "confidence": 1.0, "evidence": ["Kaplan–Meier survival and univariate Cox proportional hazards regression analyses were performed for the hub genes"], "order_basis": "consumes_earlier_output", "id": "assay:2"}]}