Identification of biomarkers associated with the recurrence of osteosarcoma using ceRNA regulatory network analysis.

{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:30816442", "kind": "science-record", "revision": 6, "content_hash": "sha256:db366de68164dca45663bb4fd76f429d2714b4c526a2a5b07fae7922b48eb044", "created_at": "2026-11-01T15:40:42Z", "updated_at": "2026-11-01T21:22:01Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Identification of biomarkers associated with the recurrence of osteosarcoma using ceRNA regulatory network analysis.", "doi": "10.3892/ijmm.2019.4108", "pmid": "30816442", "authors": ["Shanyong Zhang", "Lei Ding", "Xin Li", "Hongwu Fan"], "journal": "International journal of molecular medicine", "year": 2019, "abstract": "The aim of the present study was to identify the important mRNAs, micro (mi)RNAs and long non‑coding (lnc)RNAs that are associated with osteosarcoma recurrence. The GSE3905 dataset, which contains two sub‑datasets (GSE39040 and GSE39055), was downloaded from the Gene Expression Omnibus (GEO). Prognosis‑associated RNAs were identified by performing Cox regression univariate analysis and were subsequently used to construct a competing endogenous (ce)RNA regulatory network for Gene Set Enrichment Analysis (GSEA). Kaplan‑Meier survival analysis was used to determine the associations between expression levels and survival prognosis. In addition, another independent miRNA profile, GSE79181, was downloaded from GEO for validation. Among the differentially expressed RNAs, 417 RNAs (5 lncRNAs, 19 miRNAs, and 393 mRNAs) were observed to be associated with prognosis. The GSEA for the ceRNA regulatory network revealed that 'Mitogen‑activated protein kinase (MAPK) signaling pathway', 'Chemokine signaling pathway' and 'Spliceosome' were markedly associated with osteosarcoma. In addition, three lncRNAs [long intergenic non‑protein coding RNA 28 (LINC00028), LINC00323, and small nucleolar RNA host gene 1 (SNHG1)] and two miRNAs (hsa‑miR‑124 and hsa‑miR‑7) regulating three mRNAs [Ras‑related protein Rap‑1b (RAP1B), activating transcription factor 2 (ATF2) and protein phosphatase Mg2+/Mn2+ dependent 1B (PPM1B)] participated in the MAPK signaling pathway. The Kaplan‑Meier survival analysis also demonstrated that samples with lower expression levels of LINC00323 and SNHG1 had better prognosis, and samples with increased expression levels of LINC00028, hsa‑miR‑124 and hsa‑miR‑7 had better prognosis. Overexpression of RAP1B, ATF2 and PPM1B was positively associated with osteosarcoma recurrence. The roles of hsa‑miR‑124 and hsa‑miR‑7 in osteosarcoma recurrence were also validated using GSE79181. Thus, in conclusions, the three lncRNAs (LINC00028, LINC00323 and SNHG1), two miRNAs (hsa‑miR‑124 and hsa‑miR‑7) and three mRNAs (RAP1B, ATF2, and PPM1B) were associated with osteosarcoma recurrence.", "claims": [{"id": "claim-data-access", "statement": "The datasets used and/or analyzed during the present study are available from the corresponding author on reasonable request.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:30816442", "locator": "sections[16] \"Availability of data and materials\" paragraph 2", "quote": "The datasets used and/or analyzed during the present study are available from the corresponding author on reasonable request."}], "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:30816442"], "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:GSE39058"], "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:GSE39058"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:30816442", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.3892/ijmm.2019.4108", "sha256": "sha256:071d9e0b6bf274cb11fa7181469e472704936319fd256af4e4993ef79f3f927a", "bytes": 21564, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.3892/ijmm.2019.4108", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC6414158", "source": "europe_pmc_fulltext", "coverage": "whole_body_without_references", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE39058", "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=GSE39058", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE39058", "version": null, "note": "The datasets used and/or analyzed during the present study are available from the corresponding author on reasonable request.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The datasets used and/or analyzed during the present study are available from the corresponding author on reasonable request.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM954459", "GSM954460", "GSM954461", "GSM954462", "GSM954463", "GSM954464", "GSM954465", "GSM954466", "GSM954467", "GSM954468", "GSM954469", "GSM954470", "GSM954471", "GSM954472", "GSM954473", "GSM954474", "GSM954475", "GSM954476", "GSM954477", "GSM954478", "GSM954479", "GSM954480", "GSM954481", "GSM954482", "GSM954483", "GSM954484", "GSM954485", "GSM954486", "GSM954487", "GSM954488", "GSM954489", "GSM954490", "GSM954491", "GSM954492", "GSM954493", "GSM954494", "GSM954495", "GSM954496", "GSM954497", "GSM954498", "GSM954499", "GSM954500", "GSM954501", "GSM954502", "GSM954503", "GSM954504", "GSM954505", "GSM954506", "GSM954507", "GSM954508", "GSM954509", "GSM954510", "GSM954511", "GSM954512", "GSM954513", "GSM954514", "GSM954515", "GSM954516", "GSM954517", "GSM954518", "GSM954519", "GSM954520", "GSM954521", "GSM954522", "GSM954523", "GSM954723", "GSM954724", "GSM954725", "GSM954726", "GSM954727", "GSM954728", "GSM954729", "GSM954730", "GSM954731", "GSM954732", "GSM954733", "GSM954734", "GSM954735", "GSM954736", "GSM954737", "GSM954738", "GSM954739", "GSM954740", "GSM954741", "GSM954742", "GSM954743", "GSM954744", "GSM954745", "GSM954746", "GSM954747", "GSM954748", "GSM954749", "GSM954750", "GSM954751", "GSM954752", "GSM954753", "GSM954754", "GSM954755", "GSM954756", "GSM954757", "GSM954758", "GSM954759", "GSM954760", "GSM954761", "GSM954762", "GSM954763", "GSM954764", "GSM954765", "GSM954766", "GSM954767", "GSM954768", "GSM954769", "GSM954770", "GSM954771", "GSM954772", "GSM954773", "GSM954774", "GSM954790", "GSM954791", "GSM954792", "GSM954793", "GSM954794", "GSM954795", "GSM954796", "GSM954797", "GSM954798", "GSM954799", "GSM954800", "GSM954801", "GSM954802", "GSM954803", "GSM954804", "GSM954805", "GSM954806", "GSM954807", "GSM954808", "GSM954809", "GSM954810", "GSM954811", "GSM954812", "GSM954813", "GSM954814", "GSM954815", "GSM954816", "GSM954817", "GSM954818", "GSM954819", "GSM954820", "GSM954821", "GSM954822", "GSM954823", "GSM954824", "GSM954825", "GSM954826", "GSM954847", "GSM954848", "GSM954849", "GSM954850", "GSM954851", "GSM954852", "GSM954853", "GSM954854", "GSM954855", "GSM954856"], "sample_count": 164, "group_sizes": null, "group_sizes_basis": null, "platform": "15762;14951", "taxon": "Homo sapiens", "title": "microRNA- and mRNA-based studies in paraffin-archived human osteosarcoma specimens reveal profiles with reproducible and independent prognostic value", "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:GSE79181", "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=GSE79181", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE79181", "version": null, "note": "The datasets used and/or analyzed during the present study are available from the corresponding author on reasonable request.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The datasets used and/or analyzed during the present study are available from the corresponding author on reasonable request.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM2087322", "GSM2087323", "GSM2087324", "GSM2087325", "GSM2087326", "GSM2087327", "GSM2087328", "GSM2087329", "GSM2087330", "GSM2087331", "GSM2087332", "GSM2087333", "GSM2087334", "GSM2087335", "GSM2087336", "GSM2087337", "GSM2087338", "GSM2087339", "GSM2087340", "GSM2087341", "GSM2087342", "GSM2087343", "GSM2087344", "GSM2087345", "GSM2087346"], "sample_count": 25, "group_sizes": null, "group_sizes_basis": null, "platform": "15497", "taxon": "Homo sapiens", "title": "In silico analyses  of survival-associated microRNA signatures in pediatric osteosarcoma", "resolution_checked_at": "2026-11-01T15:39:55Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}], "gaps": ["asset:data:geo:GSE39058 not downloaded", "asset:data:geo:GSE39058 licence not read", "asset:data:geo:GSE79181 not downloaded", "asset:data:geo:GSE79181 licence not read"]}, "analysis": {"state": "complete", "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": 1.0, "band": "reordered", "quote": "“Kaplan-Meier survival analysis, conducted with R software (version 3.4.1), was used to determine the associations between the expression levels and survival prognosis.”"}}, {"id": "method-2", "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": 0.7, "band": "medium", "quote": "Cox regression"}}], "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": ["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": ["GSE39058", "GSE79181"], "resolved_accessions": ["GSE39058", "GSE79181"], "statements": ["The datasets used and/or analyzed during the present study are available from the corresponding author on reasonable request."], "basis": "The paper names GSE39058, GSE79181 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:30816442", "data:geo:GSE39058"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE39058"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-10-31T18:14:01Z", "independence": "single_reader"}, "evidence_check": {"method": "reordered", "availability": "verbatim"}, "calls": 3, "usage": {"prompt_tokens": 17232, "completion_tokens": 1765, "cached_tokens": 5896}}, "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:30816442", "type": "paper", "label": "pmid:30816442"}, {"id": "source:pmid:30816442", "type": "manuscript", "label": "PMID 30816442 full text"}, {"id": "data:geo:GSE39058", "type": "dataset", "label": "GEO GSE39058"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:30816442", "type": "paper", "label": "pmid:30816442"}, {"id": "source:pmid:30816442", "type": "manuscript", "label": "PMID 30816442 full text"}, {"id": "data:geo:GSE39058", "type": "dataset", "label": "GEO GSE39058"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-30816442", "type": "extraction", "used": ["source:pmid:30816442"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE39058", "type": "accession_resolution", "used": ["data:geo:GSE39058"], "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:30816442", "parent_hash": "sha256:cc4cbe45b9c970826a01d502e9021d8f02d7b3cc3df805169e12ca9d318789f9", "fork_of": null, "generation": 5}, "gaps": ["asset:data:geo:GSE39058 licence not read", "asset:data:geo:GSE39058 not downloaded", "asset:data:geo:GSE79181 licence not read", "asset:data:geo:GSE79181 not downloaded", "execution.not_run", "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": 1.0, "evidence": ["“Kaplan-Meier survival analysis, conducted with R software (version 3.4.1), was used to determine the associations between the expression levels and survival prognosis.”"], "order_basis": "analysis_only", "id": "assay:1"}]}