Screening and Analysis of Biomarkers in the miRNA-mRNA Regulatory Network of Osteosarcoma.

{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:35340229", "kind": "science-record", "revision": 4, "content_hash": "sha256:edce670544fb985fcc705af6cbea661efbea3e75ecdf72079de845ad90614620", "created_at": "2026-11-01T18:14:08Z", "updated_at": "2026-11-01T22:06:10Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Screening and Analysis of Biomarkers in the miRNA-mRNA Regulatory Network of Osteosarcoma.", "doi": "10.1155/2022/8055052", "pmid": "35340229", "authors": ["Gang Han", "Quanyi Guo", "Nan Li", "Wenzhi Bi", "Meng Xu", "Jinpeng Jia"], "journal": "Journal of healthcare engineering", "year": 2022, "abstract": "Osteosarcoma is a malignant disease, and few effective strategies can completely overcome the prognosis of these patients. This study attempted to reveal the key factors and related molecular mechanisms of osteosarcoma via excavating public microarray datasets. The data were obtained from the Gene Expression Omnibus (GEO) database; the differentially expressed miRNAs and differentially expressed genes were obtained in GSE69470 and GSE12685l, respectively; the target of miRNAs were predicted with the miRDIP database; the functions of the factors were analyzed and visualized by the David database and R language, respectively. Moreover, the protein-protein interaction network and miRNA-mRNA network were performed with the STRING database and Cytoscape software to identify the hub nodes in GSE69470 and GSE12685. The results showed that 834 DEGs were found in GSE12685 and 37 miRNAs were found in GSE69470. Moreover, the target of 37 miRNAs were enriched in PI3K/AKT, P53, Wnt/β-catenin, and TGF-β pathways and related with skeletal system development and cell growth. Besides, the miRNAs including miR-22-3p, miR-154-5p, miR-34a-5p, miR-485-3p, miR-93-5p, and miR-9-5p and the genes including LEF1, RUNX2, CSF1R, CDKN1A, and FBN1 were identified as the hub nodes via network analysis. In conclusion, this study suggested that the miRNAs including miR-22-3p, miR-154-5p, miR-34a-5p, miR-485-3p, miR-93-5p, and miR-9-5p and the genes including LEF1, RUNX2, CSF1R, CDKN1A, and FBN1 act as key factors in the progression of osteosarcoma.", "claims": [{"id": "claim-method", "statement": "All datasets were analyzed with the GEO2R tools of GEO, and the expressed matrix files of the datasets were obtained.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:35340229", "locator": "sections[4] \"2.2. Identification of Differentially Expressed Genes\" paragraph 2", "quote": "All datasets were analyzed with the GEO2R tools of GEO, and the expressed matrix files of the datasets were obtained."}], "state": "complete"}, {"id": "claim-data-access", "statement": "The data to support the findings of this study are available on reasonable request from the corresponding author.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:35340229", "locator": "sections[17] \"Data Availability\" paragraph 2", "quote": "The data to support the findings of this study are available on reasonable request from the corresponding author."}], "state": "complete"}, {"id": "claim-target-result", "statement": "The results showed that 834 DEGs were found in GSE12685 and 37 miRNAs were found in GSE69470.", "kind": "qualitative", "target": null, "evidence": [{"asset": "source:pmid:35340229", "locator": "sections[0] \"Abstract\" paragraph 1", "quote": "The results showed that 834 DEGs were found in GSE12685 and 37 miRNAs were found in GSE69470."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "complete", "objective": "The results showed that 834 DEGs were found in GSE12685 and 37 miRNAs were found in GSE69470.", "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:35340229"], "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:GSE12685"], "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:GSE12685"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:35340229", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1155/2022/8055052", "sha256": "sha256:1e9de10826e263475f3bc82a2c919a400d39509f138c46c0156b00fa8f37d598", "bytes": 26222, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1155/2022/8055052", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC8941547", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE12685", "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=GSE12685", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE12685", "version": null, "note": "The data to support the findings of this study are available on reasonable request from the corresponding author.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The data to support the findings of this study are available on reasonable request from the corresponding author.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM318211", "GSM318212", "GSM318213", "GSM318310", "GSM318311", "GSM318312", "GSM318313", "GSM318314", "GSM318317", "GSM318320", "GSM318321", "GSM318442", "GSM318443", "GSM318445"], "sample_count": 14, "group_sizes": null, "group_sizes_basis": null, "platform": "96", "taxon": "Homo sapiens", "title": "Expression of mRNAs Regulating Synaptic Function and Neuroplasticity in Incipient AD", "resolution_checked_at": "2026-11-01T18:06:43Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:GSE69470", "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=GSE69470", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE69470", "version": null, "note": "The data to support the findings of this study are available on reasonable request from the corresponding author.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The data to support the findings of this study are available on reasonable request from the corresponding author.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM1701622", "GSM1701623", "GSM1701624", "GSM1701625", "GSM1701626", "GSM1701627", "GSM1701628", "GSM1701629", "GSM1701630", "GSM1701631", "GSM1701632", "GSM1701633", "GSM1701634", "GSM1701635", "GSM1701636", "GSM1701637", "GSM1701638", "GSM1701639", "GSM1701640", "GSM1701641", "GSM1701642", "GSM1701643", "GSM1701644", "GSM1701645", "GSM1701646", "GSM1701647", "GSM1701648", "GSM1701649", "GSM1701650", "GSM1701651", "GSM1701652", "GSM1701653", "GSM1701654", "GSM1701655", "GSM1701656", "GSM1701657", "GSM1701658", "GSM1701659", "GSM1701660", "GSM1701661", "GSM1701662", "GSM1701663", "GSM1701664", "GSM1701665", "GSM1701666", "GSM1701667", "GSM1701668", "GSM1701669", "GSM1701670", "GSM1701671", "GSM1701672", "GSM1701673", "GSM1701674", "GSM1701675", "GSM1701676", "GSM1701677", "GSM1701678", "GSM1701679", "GSM1701680", "GSM1701681", "GSM1701682", "GSM1701683", "GSM1701684", "GSM1701685", "GSM1701686", "GSM1701687", "GSM1701688", "GSM1701689", "GSM1701690", "GSM1701691", "GSM1701692", "GSM1701693", "GSM1701694", "GSM1701695", "GSM1701696", "GSM1701697", "GSM1701698"], "sample_count": 77, "group_sizes": null, "group_sizes_basis": null, "platform": "20275", "taxon": "Homo sapiens", "title": "microRNA expression  profiling of human sarcoma cell lines (~68)  in the Molecular Pharmacology Branch, DTP, DCTD NCI collection of human cell lines", "resolution_checked_at": "2026-11-01T18:06:44Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}], "gaps": ["asset:data:geo:GSE12685 not downloaded", "asset:data:geo:GSE12685 licence not read", "asset:data:geo:GSE69470 not downloaded", "asset:data:geo:GSE69470 licence not read"]}, "analysis": {"state": "partial", "methods": [{"id": "method-1", "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": "protein-protein interaction"}}, {"id": "method-2", "family": null, "specific": null, "label": "GEO2R", "dsl_operations": [], "missing_operations": [], "expressible": null, "parameters": {}, "data_shapes": [], "evidence": {"score": 1.0, "band": "verbatim", "quote": "All datasets were analyzed with the GEO2R tools of GEO, and the expressed matrix files of the datasets were obtained."}}], "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": ["build_graph", "centrality_scores", "pathway_enrich"], "missing_operations": [], "basis": "The paper names the method it used and the corpus's method extractor maps it onto the DSL catalogue: ppi_network."}, "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": ["GSE12685", "GSE69470"], "resolved_accessions": ["GSE12685", "GSE69470"], "statements": ["The data to support the findings of this study are available on reasonable request from the corresponding author."], "basis": "The paper names GSE12685, GSE69470 in Gene Expression Omnibus (GEO) database and the accession resolves in the repository. No dataset was downloaded and no licence was read."}}, "can_run": {"dsl_operations": ["build_graph", "centrality_scores", "pathway_enrich"], "assets": ["source:pmid:35340229", "data:geo:GSE12685"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE12685"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-11-01T17:39:15Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 5, "usage": {"prompt_tokens": 9205, "completion_tokens": 1176, "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:35340229", "type": "paper", "label": "pmid:35340229"}, {"id": "source:pmid:35340229", "type": "manuscript", "label": "PMID 35340229 full text"}, {"id": "data:geo:GSE12685", "type": "dataset", "label": "GEO GSE12685"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:35340229", "type": "paper", "label": "pmid:35340229"}, {"id": "source:pmid:35340229", "type": "manuscript", "label": "PMID 35340229 full text"}, {"id": "data:geo:GSE12685", "type": "dataset", "label": "GEO GSE12685"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-35340229", "type": "extraction", "used": ["source:pmid:35340229"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE12685", "type": "accession_resolution", "used": ["data:geo:GSE12685"], "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:35340229", "parent_hash": "sha256:873bd33a32d072358c24d6120c5c658fcc12397b2d227d2bba8079902a235de4", "fork_of": null, "generation": 3}, "gaps": ["asset:data:geo:GSE12685 licence not read", "asset:data:geo:GSE12685 not downloaded", "asset:data:geo:GSE69470 licence not read", "asset:data:geo:GSE69470 not downloaded", "execution.not_run", "method.reader_named_unmapped", "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": ["anisms of osteosarcoma via excavating public microarray datasets. The data were obtained from the Ge"], "order_basis": "paper_text_order:287", "id": "assay:1"}, {"role": "analysis", "definition_id": "network_analysis", "definition_version": "f2132e96ae6c7a4e", "definition_digest": null, "required_operations": ["build_graph", "centrality_scores", "pathway_enrich"], "support_state": "supported", "source_hashes": {"dsl_catalogue": "f2132e96ae6c7a4e"}, "confidence": 0.7, "evidence": ["protein-protein interaction"], "order_basis": "consumes_earlier_output", "id": "assay:2"}]}