Gene function analysis in osteosarcoma based on microarray gene expression profiling.

{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:26379830", "kind": "science-record", "revision": 4, "content_hash": "sha256:446f4ecb7b9100d42be33471b08661c9b02e9ad2c001fbe7588ff0aed20a0d90", "created_at": "2026-11-01T15:40:10Z", "updated_at": "2026-11-01T21:58:36Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "partial", "title": "Gene function analysis in osteosarcoma based on microarray gene expression profiling.", "doi": null, "pmid": "26379830", "authors": ["Liang Zhao", "Jinghua Zhang", "Hongyu Tan", "Weidong Wang", "Yilin Liu", "Ruipeng Song", "Limin Wang"], "journal": "International journal of clinical and experimental medicine", "year": 2015, "abstract": "Osteosa rcoma is an aggressive malignant neoplasm that exhibits osteoblastic differentiation and produces malignant osteoid. The aim of this study was to find feature genes associated with osteosarcoma and correlative gene functions which can distinguish cancer tissues from non-tumor tissues. Gene expression profile GSE14359 was downloaded from Gene Expression Omnibus (GEO) database, including 10 osteosarcoma samples and 2 normal samples. The differentially expressed genes (DEGs) between osteosarcoma and normal specimens were identified using limma package of R. DAVID was applied to mine osteosarcoma associated genes and analyze the GO enrichment on gene functions and KEGG pathways. Then, corresponding protein-protein interaction (PPI) network of DEGs was constructed based on the data collected from STRING datasets. Principal component of top10 DEGs and PPI network of top 20 DEGs were further analyzed. Finally, transcription factors were predicted by uploading the two groups of DEGs to TfactS database. A total of 437 genes, including 114 up-regulated genes and 323 down-regulated genes, were filtered as DEGs, of which 46 were associated with osteosarcoma by Disease Module. GO and KEGG pathway enrichment analysis showed that genes mainly affected the process of immune response and the development of skeletal and vascular system. The PPI network analysis elucidated that hemoglobin and histocompatibility proteins and enzymes, which were associated with immune response, were closely associated with osteosarcoma. Transcription factors MYC and SP1 were predicted to be significantly related to osteosarcoma. The discovery of gene functions and transcription factors has the potential to use in clinic for diagnosis of osteosarcoma in future. In addition, it will pave the way to studying mechanism and effective therapies for osteosarcoma.", "claims": [{"id": "claim-target-result", "statement": "The study downloaded GSE14359 from the GEO database and used the limma package in R to identify differentially expressed genes between osteosarcoma and normal specimens.", "kind": "qualitative", "target": null, "evidence": [{"asset": "source:pmid:26379830", "locator": "sections[0] \"Abstract\" paragraph 1", "quote": "Gene expression profile GSE14359 was downloaded from Gene Expression Omnibus (GEO) database, including 10 osteosarcoma samples and 2 normal samples."}, {"asset": "source:pmid:26379830", "locator": "sections[0] \"Abstract\" paragraph 1", "quote": "The differentially expressed genes (DEGs) between osteosarcoma and normal specimens were identified using limma package of R."}], "state": "complete"}], "gaps": ["doi"]}, "experiment": {"state": "partial", "objective": "The study downloaded GSE14359 from the GEO database and used the limma package in R to identify differentially expressed genes between osteosarcoma and normal specimens.", "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:26379830"], "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:26379830", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": null, "sha256": "sha256:f0b1c2bf079636be1fbd2b0ebdafc9673f5888f0929191806d96906332e080a1", "bytes": 1871, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "26379830", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC4565213", "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": "protein-protein interaction"}}, {"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:26379830"], "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": "2026-10-31T18:24:47Z", "independence": "single_reader"}, "evidence_check": {"method": null, "availability": null}, "calls": 2, "usage": {"prompt_tokens": 1722, "completion_tokens": 458, "cached_tokens": 520}}, "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:26379830", "type": "paper", "label": "pmid:26379830"}, {"id": "source:pmid:26379830", "type": "manuscript", "label": "PMID 26379830 full text"}, {"id": "data:geo:None", "type": "dataset", "label": "GEO None"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:26379830", "type": "paper", "label": "pmid:26379830"}, {"id": "source:pmid:26379830", "type": "manuscript", "label": "PMID 26379830 full text"}, {"id": "data:geo:None", "type": "dataset", "label": "GEO None"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-26379830", "type": "extraction", "used": ["source:pmid:26379830"], "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:26379830", "parent_hash": "sha256:f230d86bad7c7d1765d04c31a633275e8ed295740a46aa9d1494cb695d83fee7", "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": ["e function analysis in osteosarcoma based on microarray gene expression profiling."], "order_basis": "paper_text_order:3", "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"}]}