Identification of potential core genes in lung cancer and therapeutic traditional Chinese medicine compounds using bioinformatics analysis.

{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:39331864", "kind": "science-record", "revision": 2, "content_hash": "sha256:12c5048bf9cc62f45d4a381b461693b13bcd84a36e3769edc94fa90fca3f3a84", "created_at": "2026-11-01T20:29:31Z", "updated_at": "2026-11-01T21:33:59Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Identification of potential core genes in lung cancer and therapeutic traditional Chinese medicine compounds using bioinformatics analysis.", "doi": "10.1097/MD.0000000000039862", "pmid": "39331864", "authors": ["Yue Zhang", "Yaguang Wang", "Xuepu Zhang", "Jiansheng Liu"], "journal": "Medicine", "year": 2024, "abstract": "Lung cancer (LC) remains the leading cause of cancer-related death. We identified potential therapeutic targets and traditional Chinese medicine (TCM) compounds for LC treatment. GSE43346 and GSE18842 were derived from the Gene Expression Omnibus (GEO) database and used to identify differentially expressed genes (DEGs). Gene Ontology and Kyoto Encyclopedia of Genes and Genomes pathway enrichment analyses were performed using The Database for Annotation, Visualization and Integrated Discovery (DAVID). Protein-protein interactions were analyzed using STRING and Cytoscape software. Hub gene expression was validated using Gene Expression Profiling Interactive Analysis and the Human Protein Atlas. Kaplan-Meier survival analysis was conducted to evaluate the prognostic value of hub genes in patients with LC. Therapeutic TCM compounds were screened using the Comparative Toxicogenomics Database, and DEGs were largely enriched in biological processes, including cell division and mitotic nuclear division, such as the cell cycle and p53 signaling pathways. Elevated expression of hub genes was observed in LC samples. Overexpression of CDC20, CCNB2, and TOP2A is an unfavorable prognostic factor for postprogressive survival in patients with LC. Paclitaxel, quercetin, and rotenone have been identified as active substances in TCM. CDC20, CCNB2, and TOP2A are novel hub genes associated with LC. Paclitaxel, quercetin, and rotenone can be used as therapeutic agents in TCM.", "claims": [{"id": "claim-method", "statement": "The GEO2R online analysis tool was used to detect DEGs in the LC and normal samples, and the adjusted P-value and |logFC| were calculated.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:39331864", "locator": "sections[4] \"2.2. Data processing of DEGs\" paragraph 2", "quote": "The GEO2R online analysis tool was used to detect DEGs in the LC and normal samples, and the adjusted P-value and |logFC| were calculated."}], "state": "complete"}, {"id": "claim-data-access", "statement": "The datasets generated during and/or analyzed during the current study are publicly available.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:39331864", "locator": "sections[22] \"fn-group\" paragraph 1", "quote": "The datasets generated during and/or analyzed during the current study are publicly available."}], "state": "complete"}, {"id": "claim-target-result", "statement": "Finally, 162 DEGs were found to be significantly and differentially expressed between the 2 groups, of which 90 were significantly upregulated and 72 were downregulated.", "kind": "qualitative", "target": null, "evidence": [{"asset": "source:pmid:39331864", "locator": "sections[11] \"3.1. Identification of DEGs\" paragraph 2", "quote": "Finally, 162 DEGs were found to be significantly and differentially expressed between the 2 groups, of which 90 were significantly upregulated and 72 were downregulated."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "complete", "objective": "Finally, 162 DEGs were found to be significantly and differentially expressed between the 2 groups, of which 90 were significantly upregulated and 72 were downregulated.", "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:39331864"], "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:GSE18842"], "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:GSE18842"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:39331864", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1097/MD.0000000000039862", "sha256": "sha256:9e7cd26fcb1476f96a13f33bf799c1d7acc61b33c3bc6081a654ffaf8a2fc880", "bytes": 21422, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1097/MD.0000000000039862", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC11441908", "source": "europe_pmc_fulltext", "coverage": "whole_body_without_references", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE18842", "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=GSE18842", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE18842", "version": null, "note": "The datasets generated during and/or analyzed during the current study are publicly available.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The datasets generated during and/or analyzed during the current study are publicly available.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM466947", "GSM466948", "GSM466949", "GSM466950", "GSM466951", "GSM466952", "GSM466953", "GSM466954", "GSM466955", "GSM466956", "GSM466957", "GSM466958", "GSM466959", "GSM466960", "GSM466961", "GSM466962", "GSM466963", "GSM466964", "GSM466965", "GSM466966", "GSM466967", "GSM466968", "GSM466969", "GSM466970", "GSM466971", "GSM466972", "GSM466973", "GSM466974", "GSM466975", "GSM466976", "GSM466977", "GSM466978", "GSM466979", "GSM466980", "GSM466981", "GSM466982", "GSM466983", "GSM466984", "GSM466985", "GSM466986", "GSM466987", "GSM466988", "GSM466989", "GSM466990", "GSM466991", "GSM466992", "GSM466993", "GSM466994", "GSM466995", "GSM466996", "GSM466997", "GSM466998", "GSM466999", "GSM467000", "GSM467001", "GSM467002", "GSM467003", "GSM467004", "GSM467005", "GSM467006", "GSM467007", "GSM467008", "GSM467009", "GSM467010", "GSM467011", "GSM467012", "GSM467013", "GSM467014", "GSM467015", "GSM467016", "GSM467017", "GSM467018", "GSM467019", "GSM467020", "GSM467021", "GSM467022", "GSM467023", "GSM467024", "GSM467025", "GSM467026", "GSM467027", "GSM467028", "GSM467029", "GSM467030", "GSM467031", "GSM467032", "GSM467033", "GSM467034", "GSM467035", "GSM467036", "GSM467037"], "sample_count": 91, "group_sizes": null, "group_sizes_basis": null, "platform": "570", "taxon": "Homo sapiens", "title": "Gene expression analysis of human lung cancer and control samples", "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:GSE43346", "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=GSE43346", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE43346", "version": null, "note": "The datasets generated during and/or analyzed during the current study are publicly available.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The datasets generated during and/or analyzed during the current study are publicly available.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM1060726", "GSM1060727", "GSM1060728", "GSM1060729", "GSM1060730", "GSM1060731", "GSM1060732", "GSM1060733", "GSM1060734", "GSM1060735", "GSM1060736", "GSM1060737", "GSM1060738", "GSM1060739", "GSM1060740", "GSM1060741", "GSM1060742", "GSM1060743", "GSM1060744", "GSM1060745", "GSM1060746", "GSM1060747", "GSM1060748", "GSM1060749", "GSM1060750", "GSM1060751", "GSM1060752", "GSM1060753", "GSM1060754", "GSM1060755", "GSM1060756", "GSM1060757", "GSM1060758", "GSM1060759", "GSM1060760", "GSM1060761", "GSM1060762", "GSM1060763", "GSM1060764", "GSM1060765", "GSM1060766", "GSM1060767", "GSM1060768", "GSM1060769", "GSM1060770", "GSM1060771", "GSM1060772", "GSM1060773", "GSM1060774", "GSM1060775", "GSM1060776", "GSM1060777", "GSM1060778", "GSM1060779", "GSM1060780", "GSM1060781", "GSM1060782", "GSM1060783", "GSM1060784", "GSM1060785", "GSM1060786", "GSM1060787", "GSM1060788", "GSM1060789", "GSM1060790", "GSM1060791", "GSM1060792", "GSM1060793", "GSM1060794", "GSM1060795"], "sample_count": 70, "group_sizes": null, "group_sizes_basis": null, "platform": "96;97;570", "taxon": "Homo sapiens", "title": "Gene repression with H3K27me3 modification in human small cell lung cancer", "resolution_checked_at": "2026-11-01T15:39:54Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}], "gaps": ["asset:data:geo:GSE18842 not downloaded", "asset:data:geo:GSE18842 licence not read", "asset:data:geo:GSE43346 not downloaded", "asset:data:geo:GSE43346 licence not read"]}, "analysis": {"state": "partial", "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": "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": null, "specific": null, "label": "GEO2R online analysis tool", "dsl_operations": [], "missing_operations": [], "expressible": null, "parameters": {}, "data_shapes": [], "evidence": {"score": 1.0, "band": "verbatim", "quote": "The GEO2R online analysis tool was used to detect DEGs in the LC and normal samples, and the adjusted P-value and |logFC| were calculated."}}], "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": ["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": ["GSE43346", "GSE18842"], "resolved_accessions": ["GSE43346", "GSE18842"], "statements": ["The datasets generated during and/or analyzed during the current study are publicly available."], "basis": "The paper names GSE43346, GSE18842 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": ["survival_km"], "assets": ["source:pmid:39331864", "data:geo:GSE18842"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE18842"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-11-01T19:32:56Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 5, "usage": {"prompt_tokens": 7407, "completion_tokens": 1104, "cached_tokens": 256}}, "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:39331864", "type": "paper", "label": "pmid:39331864"}, {"id": "source:pmid:39331864", "type": "manuscript", "label": "PMID 39331864 full text"}, {"id": "data:geo:GSE18842", "type": "dataset", "label": "GEO GSE18842"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:39331864", "type": "paper", "label": "pmid:39331864"}, {"id": "source:pmid:39331864", "type": "manuscript", "label": "PMID 39331864 full text"}, {"id": "data:geo:GSE18842", "type": "dataset", "label": "GEO GSE18842"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-39331864", "type": "extraction", "used": ["source:pmid:39331864"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE18842", "type": "accession_resolution", "used": ["data:geo:GSE18842"], "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:39331864", "parent_hash": "sha256:a0f9c68b8a4f2a6d1dd955a973018e15e374f9fcdfba314770dc9f5b0f3d7076", "fork_of": null, "generation": 1}, "gaps": ["asset:data:geo:GSE18842 licence not read", "asset:data:geo:GSE18842 not downloaded", "asset:data:geo:GSE43346 licence not read", "asset:data:geo:GSE43346 not downloaded", "execution.not_run", "method.reader_named_unmapped", "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"}]}