A three miRNAs signature for predicting the transformation of oral leukoplakia to oral squamous cell carcinoma.

{"sci_version": "1.0", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:30210912", "kind": "science-record", "revision": 2, "content_hash": "sha256:dd91b8128a562804d1af763e6212dcd48a651f6c0882ff79bcc366f2bb1095b7", "created_at": "2026-11-01T17:32:22Z", "updated_at": "2026-11-01T18:49:50Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "partial", "title": "A three miRNAs signature for predicting the transformation of oral leukoplakia to oral squamous cell carcinoma.", "doi": null, "pmid": "30210912", "authors": ["Huan Chen", "Xiangzhen Liu", "Zhenning Jin", "Chenyu Gou", "Minglu Liang", "Li Cui", "Xinyuan Zhao"], "journal": "American journal of cancer research", "year": 2018, "abstract": "Oral squamous cell carcinoma (OSCC) remains to be a global health problem. However, the underlying molecular mechanisms regulating the oral leukoplakia (OLK) to OSCC remain poorly known. MicroRNAs (miRNAs) expression profiles of GSE33299 and GSE62809 were downloaded from gene expression omnibus (GEO) respectively. R software and bioconductor packages were used to compare and identify the differentially expressed miRNAs between OLK tissues and OLK transformed OSCC (OLK-OSCC). The target genes of commonly changed miRNAs were then subjected to gene ontology (GO) enrichment analysis, pathway analysis and miRNA-target genes network analysis. The prediction power of commonly changed miRNAs was further tested in an independent cohort. In total, 161 (88 upregulated and 73 downregulated) and 68 (19 upregulated and 49 downregulated) markedly altered miRNAs were identified from GSE33299 and GSE62809 respectively. The downstream targets of these differentially expression miRNAs in the two cohorts shared many top enriched GO and KEGG pathways. A set of three miRNAs signature including miR-129-5p, miR-296-5p and miR-450b-5p was commonly changed in both GSE33299 and GSE62809. Functional analysis revealed that the downstream target genes of the miRNA signature were associates with transcriptional regulation, estrogen signaling pathway, p53 signaling pathway and RIG-I-like receptor signaling pathway. This three-gene signature was further successfully validated in another independent cohort. The expression levels of miR-129-5p and miR-296-5p were significantly downregulated in OLK-OSCC tissues compared to OLK tissues, while miR-450b-5p levels were higher in OLK-OSCC tissues. In addition, this three miRNAs signature could discriminate OLK from OLK-OSCC with high accuracy. In conclusion, our study has identified a three miRNAs signature that might help predict the transformation of OLK to OSCC. Which will provide useful guidance for therapeutic applications.", "claims": [{"id": "claim-data-access", "statement": "MicroRNAs (miRNAs) expression profiles of GSE33299 and GSE62809 were downloaded from gene expression omnibus (GEO) respectively.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:30210912", "locator": "sections[0] \"Abstract\" paragraph 1", "quote": "MicroRNAs (miRNAs) expression profiles of GSE33299 and GSE62809 were downloaded from gene expression omnibus (GEO) respectively."}], "state": "complete"}, {"id": "claim-target-result", "statement": "The study identified a three-miRNA signature that might help predict the transformation of OLK to OSCC.", "kind": "qualitative", "target": null, "evidence": [{"asset": "source:pmid:30210912", "locator": "sections[0] \"Abstract\" paragraph 1", "quote": "In conclusion, our study has identified a three miRNAs signature that might help predict the transformation of OLK to OSCC."}], "state": "complete"}], "gaps": ["doi"]}, "experiment": {"state": "complete", "objective": "The study identified a three-miRNA signature that might help predict the transformation of OLK to OSCC.", "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:30210912"], "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:GSE33299"], "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:GSE33299"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:30210912", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": null, "sha256": "sha256:c4359f0561b884cdf94e589faa373d2c27c9d6d12e0ce6ded947c32eb0aead14", "bytes": 1985, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "30210912", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC6129488", "source": "ncbi_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE33299", "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=GSE33299", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE33299", "version": null, "note": "MicroRNAs (miRNAs) expression profiles of GSE33299 and GSE62809 were downloaded from gene expression omnibus (GEO) respectively.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "MicroRNAs (miRNAs) expression profiles of GSE33299 and GSE62809 were downloaded from gene expression omnibus (GEO) respectively.", "access_statement_kind": "repository_route_statement", "sample_accessions": ["GSM823579", "GSM823580", "GSM823581", "GSM823582", "GSM823583", "GSM823584", "GSM823585", "GSM823586", "GSM823587", "GSM823588", "GSM823589", "GSM823590", "GSM823591", "GSM823592", "GSM823593", "GSM823594", "GSM823595", "GSM823596", "GSM823597", "GSM823598", "GSM823599", "GSM823600", "GSM823601", "GSM823602", "GSM823603", "GSM823604", "GSM823605", "GSM823606", "GSM823607", "GSM823608"], "sample_count": 30, "group_sizes": null, "group_sizes_basis": null, "platform": "14801", "taxon": "Homo sapiens", "title": "MiRNA array based, miRNA expression profiles of oral leukoplakia (OLK) and malignant transformed oral leukoplakia (mtOLK)", "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:GSE62809", "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=GSE62809", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE62809", "version": null, "note": "MicroRNAs (miRNAs) expression profiles of GSE33299 and GSE62809 were downloaded from gene expression omnibus (GEO) respectively.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "MicroRNAs (miRNAs) expression profiles of GSE33299 and GSE62809 were downloaded from gene expression omnibus (GEO) respectively.", "access_statement_kind": "repository_route_statement", "sample_accessions": ["GSM1533721", "GSM1533722", "GSM1533723", "GSM1533724", "GSM1533725", "GSM1533726", "GSM1533727", "GSM1533728", "GSM1533729", "GSM1533730", "GSM1533731", "GSM1533732", "GSM1533733", "GSM1533734", "GSM1533735", "GSM1533736", "GSM1533737", "GSM1533738", "GSM1533739", "GSM1533740"], "sample_count": 20, "group_sizes": null, "group_sizes_basis": null, "platform": "16791", "taxon": "Homo sapiens", "title": "Predictive Value of MicroRNAs in the Progression of Oral Leukoplakias", "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:GSE33299 not downloaded", "asset:data:geo:GSE33299 licence not read", "asset:data:geo:GSE62809 not downloaded", "asset:data:geo:GSE62809 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": ["GSE33299", "GSE62809"], "resolved_accessions": ["GSE33299", "GSE62809"], "statements": ["MicroRNAs (miRNAs) expression profiles of GSE33299 and GSE62809 were downloaded from gene expression omnibus (GEO) respectively."], "basis": "The paper names GSE33299, GSE62809 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": [], "assets": ["source:pmid:30210912", "data:geo:GSE33299"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE33299"]}, "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": "2026-11-01T16:57:53Z", "independence": "single_reader"}, "evidence_check": {"method": null, "availability": null}, "calls": 5, "usage": {"prompt_tokens": 2059, "completion_tokens": 761, "cached_tokens": 188}}, "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:30210912", "type": "paper", "label": "pmid:30210912"}, {"id": "source:pmid:30210912", "type": "manuscript", "label": "PMID 30210912 full text"}, {"id": "data:geo:GSE33299", "type": "dataset", "label": "GEO GSE33299"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:30210912", "type": "paper", "label": "pmid:30210912"}, {"id": "source:pmid:30210912", "type": "manuscript", "label": "PMID 30210912 full text"}, {"id": "data:geo:GSE33299", "type": "dataset", "label": "GEO GSE33299"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-30210912", "type": "extraction", "used": ["source:pmid:30210912"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE33299", "type": "accession_resolution", "used": ["data:geo:GSE33299"], "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:30210912", "parent_hash": "sha256:db5af4b816c970fa6bdbc7258bdab3c32c274b5458b53c4ff474c912823eb8c1", "fork_of": null, "generation": 1}, "gaps": ["asset:data:geo:GSE33299 licence not read", "asset:data:geo:GSE33299 not downloaded", "asset:data:geo:GSE62809 licence not read", "asset:data:geo:GSE62809 not downloaded", "doi", "execution.not_run", "method", "operations", "review.human_critique", "review.independent_reader", "review.machine_critique"]}