Screening of key genes and prediction of therapeutic agents in Arsenic-induced lung carcinoma.

{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:31322542", "kind": "science-record", "revision": 2, "content_hash": "sha256:30f2f087b974e0b7b3f2258c244c1d37067437a93434d225fccfba38805a6541", "created_at": "2026-11-01T17:32:57Z", "updated_at": "2026-11-01T18:51:04Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Screening of key genes and prediction of therapeutic agents in Arsenic-induced lung carcinoma.", "doi": "10.3233/CBM-182333", "pmid": "31322542", "authors": ["Liang Zhang", "Yu Huang", "Junjun Ling", "Ying Xiang", "Wenlei Zhuo"], "journal": "Cancer biomarkers : section A of Disease markers", "year": 2019, "abstract": "BACKGROUND: Evidence indicates that inorganic arsenic (iAs) can directly damage cells and result in malignant transformation with unclear complicated mechanisms. In the present study, we aimed to explore the possible molecules, pathways and therapeutic agents by using bioinformatics methods.\nMETHODS: Microarray-based data were retrieved and analyzed to screen the differentially expressed genes (DEGs) between iAs-treated lung cells and controls. Then, the functions of DEGs were annotated and the hub genes were filtrated. The key genes were selected from the hub genes through validation in The Cancer Genome Atlas (TCGA) cohorts. Possible drugs were predicted by using CMAP tool.\nRESULTS: Two datasets (GSE33520 and GSE36684) were retrieved, and 61 up-regulated and 228 down-regulated DEGs were screened out, which were enriched in various pathways, particularly metabolism-related pathways. Among the DEGs, four hub genes including MTIF2, ACOX1, CAV1, and MRPL17, which might affect lung cancer prognosis, were selected as the key genes. Interestingly, Quinostatin was predicted to be a potential agent reversing iAs-induced lung cell malignant transformation.\nCONCLUSION: The present study sheds novel insights into the mechanisms of iAs-induced lung cell malignant transformation and identified several potential small agents for iAs toxicity prevention and therapy.", "claims": [{"id": "claim-data-access", "statement": "Two datasets (GSE33520 and GSE36684) were retrieved, and 61 up-regulated and 228 down-regulated DEGs were screened out, which were enriched in various pathways, particularly metabolism-related pathways.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:31322542", "locator": "sections[0] \"Abstract\" paragraph 3", "quote": "Two datasets (GSE33520 and GSE36684) were retrieved, and 61 up-regulated and 228 down-regulated DEGs were screened out, which were enriched in various pathways, particularly metabolism-related pathways."}], "state": "complete"}, {"id": "claim-target-result", "statement": "Two datasets (GSE33520 and GSE36684) were retrieved, and 61 up-regulated and 228 down-regulated DEGs were screened out, which were enriched in various pathways, particularly metabolism-related pathways.", "kind": "qualitative", "target": null, "evidence": [{"asset": "source:pmid:31322542", "locator": "sections[0] \"Abstract\" paragraph 3", "quote": "Two datasets (GSE33520 and GSE36684) were retrieved, and 61 up-regulated and 228 down-regulated DEGs were screened out, which were enriched in various pathways, particularly metabolism-related pathways."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "complete", "objective": "Two datasets (GSE33520 and GSE36684) were retrieved, and 61 up-regulated and 228 down-regulated DEGs were screened out, which were enriched in various pathways, particularly metabolism-related pathways.", "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:31322542"], "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:GSE33520"], "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:GSE33520"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:31322542", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.3233/CBM-182333", "sha256": "sha256:77deb8768267c67512deb13a81bf568153b67b57d51bc084576fe26805864523", "bytes": 1345, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.3233/CBM-182333", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC12828840", "source": "ncbi_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE33520", "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=GSE33520", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE33520", "version": null, "note": "Two datasets (GSE33520 and GSE36684) were retrieved, and 61 up-regulated and 228 down-regulated DEGs were screened out, which were enriched in various pathways, particularly metabolism-related pathways.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "Two datasets (GSE33520 and GSE36684) were retrieved, and 61 up-regulated and 228 down-regulated DEGs were screened out, which were enriched in various pathways, particularly metabolism-related pathways.", "access_statement_kind": "repository_route_statement", "sample_accessions": ["GSM829378", "GSM829379", "GSM829380", "GSM829381", "GSM829382", "GSM829383", "GSM829384"], "sample_count": 7, "group_sizes": null, "group_sizes_basis": null, "platform": "6480", "taxon": "Homo sapiens", "title": "Whole genome expression profile of lung epithelial cells following chronic arsenic exposure", "resolution_checked_at": "2026-11-01T17:30:42Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:GSE36684", "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=GSE36684", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE36684", "version": null, "note": "Two datasets (GSE33520 and GSE36684) were retrieved, and 61 up-regulated and 228 down-regulated DEGs were screened out, which were enriched in various pathways, particularly metabolism-related pathways.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "Two datasets (GSE33520 and GSE36684) were retrieved, and 61 up-regulated and 228 down-regulated DEGs were screened out, which were enriched in various pathways, particularly metabolism-related pathways.", "access_statement_kind": "repository_route_statement", "sample_accessions": ["GSM898707", "GSM898708", "GSM898709", "GSM898710", "GSM898711", "GSM898712", "GSM898713", "GSM898714", "GSM898715", "GSM898716", "GSM898717", "GSM898718", "GSM898719", "GSM898720", "GSM898721", "GSM898722", "GSM898723", "GSM898724", "GSM898725", "GSM898726", "GSM898727", "GSM898728", "GSM898729", "GSM898730", "GSM898731", "GSM898732", "GSM898733", "GSM898734", "GSM898735", "GSM898736", "GSM898737", "GSM898738", "GSM898739", "GSM898740", "GSM898741", "GSM898742", "GSM898743", "GSM898744", "GSM898745"], "sample_count": 39, "group_sizes": null, "group_sizes_basis": null, "platform": "6244", "taxon": "Homo sapiens", "title": "Exposure of an immortalized human bronchial epithelial cell line, BEAS-2B, to one of four metals (arsenic, chromium, nickel or vanadium) to determine the early changes that lead to cell transformation", "resolution_checked_at": "2026-11-01T17:30:42Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}], "gaps": ["asset:data:geo:GSE33520 not downloaded", "asset:data:geo:GSE33520 licence not read", "asset:data:geo:GSE36684 not downloaded", "asset:data:geo:GSE36684 licence not read"]}, "analysis": {"state": "absent", "methods": [], "targets": [], "gaps": ["method", "operations"]}, "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": "method", "blocked_on": "method:not_determinable", "axes": {"method": {"tier": "R4", "expressible": false, "required_operations": [], "missing_operations": [], "basis": "The reader quoted the method the paper names (not named), but the corpus's method extractor could not map it onto a DSL operation, so the method is published but not expressible."}, "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": ["GSE33520", "GSE36684"], "resolved_accessions": ["GSE33520", "GSE36684"], "statements": ["Two datasets (GSE33520 and GSE36684) were retrieved, and 61 up-regulated and 228 down-regulated DEGs were screened out, which were enriched in various pathways, particularly metabolism-related pathways."], "basis": "The paper names GSE33520, GSE36684 in GSE33520 and the accession resolves in the repository. No dataset was downloaded and no licence was read."}}, "can_run": {"dsl_operations": [], "assets": ["source:pmid:31322542", "data:geo:GSE33520"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE33520"]}, "gaps": ["method:not_determinable"]}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-11-01T16:58:33Z", "independence": "single_reader"}, "evidence_check": {"method": null, "availability": null}, "calls": 5, "usage": {"prompt_tokens": 1898, "completion_tokens": 931, "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:31322542", "type": "paper", "label": "pmid:31322542"}, {"id": "source:pmid:31322542", "type": "manuscript", "label": "PMID 31322542 full text"}, {"id": "data:geo:GSE33520", "type": "dataset", "label": "GEO GSE33520"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:31322542", "type": "paper", "label": "pmid:31322542"}, {"id": "source:pmid:31322542", "type": "manuscript", "label": "PMID 31322542 full text"}, {"id": "data:geo:GSE33520", "type": "dataset", "label": "GEO GSE33520"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-31322542", "type": "extraction", "used": ["source:pmid:31322542"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE33520", "type": "accession_resolution", "used": ["data:geo:GSE33520"], "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:31322542", "parent_hash": "sha256:dc4af584551377a8c167aea13f1f3aa31dc84501d32ef063aa04c37b5d5a0d26", "fork_of": null, "generation": 1}, "gaps": ["asset:data:geo:GSE33520 licence not read", "asset:data:geo:GSE33520 not downloaded", "asset:data:geo:GSE36684 licence not read", "asset:data:geo:GSE36684 not downloaded", "execution.not_run", "method", "operations", "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": 0.93, "evidence": ["ts by using bioinformatics methods. METHODS: Microarray-based data were retrieved and analyzed to sc"], "order_basis": "paper_text_order:352", "id": "assay:1"}]}