Screening feature genes of lung carcinoma with DNA microarray analysis.

{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:26550126", "kind": "science-record", "revision": 4, "content_hash": "sha256:9fe004f7b31e811ebcb615bee32ae7807c3da869fb183543dc882a460e3ac984", "created_at": "2026-11-01T15:40:13Z", "updated_at": "2026-11-01T21:58:46Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "partial", "title": "Screening feature genes of lung carcinoma with DNA microarray analysis.", "doi": null, "pmid": "26550126", "authors": ["Liangdong Chen", "Deqiang Zhuo", "Jiakuan Chen", "Hongyin Yuan"], "journal": "International journal of clinical and experimental medicine", "year": 2015, "abstract": "Lung carcinoma is the most common and aggressive malignant tumor with poor clinical outcome. Identification of new marker of lung cancer is essential for the diagnosis and prognosis of the disease. To identify differentially expressed genes (DEGs) and find associated pathways that may function as targets of lung cancer. Gene expression profiling of GSE40791 were downloaded from GEO (Gene Expression Omnibus), including 100 normal specimens and 94 lung cancer samples. The DEGs were screened out by LIMMA package in R language. Besides, novel genes associated with lung cancer were identified by co-expression analysis. Then, GO enrichment and transcription binding site analysis were performed on these DEGs, and novel genes were predicted using DAVID. Finally, PPI network was constructed by String software in order to get the hub codes involved in cancer carcinoma. A total of 541 DEGs were filtered out between normal samples and patients with lung carcinoma, including 155 up-regulated genes and 386 down-regulated genes. Additionally, nine novel genes, CA4, CDC20, CHRDL1, DLGAP5, EMCN, GPM6A, NUSAP1, S1PR1 and TCF21, were figured out. The transcription biding site analysis showed that these genes were regulated by LHX3, HNF3B, CDP, HFH1, FOXO4, STAT, SOX5, MEF2, FOXO3 and SRY. Hub codes as BUB1B, MAD2L and TOP2A may play as target genes in lung carcinoma in the result of PPI network analysis. Newly predicted genes and hub codes can perform as target genes for diagnose and clinical therapy of lung cancer.", "claims": [{"id": "claim-target-result", "statement": "The study downloaded gene expression profiling from GEO (GSE40791) and screened differentially expressed genes using the LIMMA package in R.", "kind": "qualitative", "target": null, "evidence": [{"asset": "source:pmid:26550126", "locator": "sections[0] \"Abstract\" paragraph 1", "quote": "Gene expression profiling of GSE40791 were downloaded from GEO (Gene Expression Omnibus), including 100 normal specimens and 94 lung cancer samples."}, {"asset": "source:pmid:26550126", "locator": "sections[0] \"Abstract\" paragraph 1", "quote": "The DEGs were screened out by LIMMA package in R language."}], "state": "complete"}], "gaps": ["doi"]}, "experiment": {"state": "partial", "objective": "The study downloaded gene expression profiling from GEO (GSE40791) and screened differentially expressed genes using the LIMMA package in R.", "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:26550126"], "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": "blocked", "blocked_on": "data:accession_absent", "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": [], "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": [], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": ["step:obtain_source_data blocked on data:accession_absent"]}, "data": {"state": "partial", "assets": [{"id": "source:pmid:26550126", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": null, "sha256": "sha256:7ff1509c0a3f275b06fbd9e40b56932ea7cd9023df0828eaa9a80250021f7c99", "bytes": 1535, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "26550126", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC4612811", "source": "ncbi_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}], "gaps": []}, "analysis": {"state": "complete", "methods": [{"id": "method-1", "family": "differential_expression", "specific": "limma_voom", "label": "Differential expression analysis", "dsl_operations": ["normalise_counts", "differential_expression_fit", "fdr_bh"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["count_matrix_with_condition"], "evidence": {"score": 0.7, "band": "medium", "quote": "LIMMA"}}, {"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": "PPI"}}, {"id": "method-3", "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": "GO 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": "blocked", "tier": "R4", "blocking_axis": "data", "blocked_on": "data:accession_absent", "axes": {"method": {"tier": "R1", "expressible": true, "required_operations": ["normalise_counts", "differential_expression_fit", "fdr_bh"], "missing_operations": [], "basis": "The paper names the method it used and the corpus's method extractor maps it onto the DSL catalogue: limma_voom."}, "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": "R4", "reachable": false, "accessions": [], "resolved_accessions": [], "statements": [], "basis": "The paper names no accession to its source data, so the data has to come from the authors."}}, "can_run": {"dsl_operations": ["normalise_counts", "differential_expression_fit", "fdr_bh"], "assets": ["source:pmid:26550126"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:None"]}, "gaps": ["data:accession_absent"]}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-10-31T18:26:12Z", "independence": "single_reader"}, "evidence_check": {"method": null, "availability": null}, "calls": 2, "usage": {"prompt_tokens": 1694, "completion_tokens": 405, "cached_tokens": 528}}, "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:26550126", "type": "paper", "label": "pmid:26550126"}, {"id": "source:pmid:26550126", "type": "manuscript", "label": "PMID 26550126 full text"}, {"id": "data:geo:None", "type": "dataset", "label": "GEO None"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:26550126", "type": "paper", "label": "pmid:26550126"}, {"id": "source:pmid:26550126", "type": "manuscript", "label": "PMID 26550126 full text"}, {"id": "data:geo:None", "type": "dataset", "label": "GEO None"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-26550126", "type": "extraction", "used": ["source:pmid:26550126"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-None", "type": "accession_resolution", "used": ["data:geo:None"], "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:26550126", "parent_hash": "sha256:e333bceb5cce194f0cb4dae209c464f944ce1cf12032d06de6cd4286661e1dd3", "fork_of": null, "generation": 3}, "gaps": ["doi", "execution.not_run", "review.human_critique", "review.independent_reader", "review.machine_critique", "step:obtain_source_data blocked on data:accession_absent"], "assays": [{"role": "data_generation", "definition_id": "microarray", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.93, "evidence": ["ing feature genes of lung carcinoma with DNA microarray analysis."], "order_basis": "paper_text_order:6", "id": "assay:1"}, {"role": "analysis", "definition_id": "differential_expression", "definition_version": "f2132e96ae6c7a4e", "definition_digest": null, "required_operations": ["normalise_counts", "differential_expression_fit", "fdr_bh"], "support_state": "supported", "source_hashes": {"dsl_catalogue": "f2132e96ae6c7a4e"}, "confidence": 0.7, "evidence": ["LIMMA"], "order_basis": "consumes_earlier_output", "id": "assay:2"}]}