SPP1 and FN1 are significant gene biomarkers of tongue squamous cell carcinoma.

{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:34457068", "kind": "science-record", "revision": 7, "content_hash": "sha256:347e37009f5ddaf4317e4de4b38f78e502d32de85f0f651313929f13ec3e7a2e", "created_at": "2026-11-01T15:41:50Z", "updated_at": "2026-11-01T22:04:36Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "SPP1 and FN1 are significant gene biomarkers of tongue squamous cell carcinoma.", "doi": "10.3892/ol.2021.12974", "pmid": "34457068", "authors": ["Xiao-Liang Xu", "Hui Liu", "Ying Zhang", "Su-Xin Zhang", "Zhong Chen", "Yang Bao", "Tian-Ke Li"], "journal": "Oncology letters", "year": 2021, "abstract": "Tongue squamous cell carcinoma (TSCC) is one of the most common malignant tumor types in the oral and maxillofacial region. The etiology and pathogenesis behind TSCC is complicated. In the present study, three gene expression profiles, namely GSE31056, GSE13601 and GSE78060, were downloaded from the Gene Expression Omnibus (GEO). The GEO2R online tool was utilized to identify differentially expressed genes (DEGs) between TSCC and normal tissue samples. Furthermore, a protein-protein interaction (PPI) network was constructed and hub genes were validated and analyzed. A total of 83 common DEGs were obtained in three datasets, including 48 upregulated and 35 downregulated genes. Pathway enrichment analysis indicated that DEGs were primarily enriched in cell adhesion, extracellular matrix (ECM) organization, and proteolysis. A total of 63 nodes and 218 edges were included in the PPI network. The top 11 candidate hub genes were acquired, namely plasminogen activator urokinase (PLAU), signal transducer and activator of transcription 1, C-X-C motif chemokine ligand 12, matrix metallopeptidase (MMP) 13, secreted phosphoprotein 1 (SPP1), periostin, MMP1, MMP3, fibronectin 1 (FN1), serpin family E member 1 and snail family transcriptional repressor 2. Overall, 83 DEGs and 11 hub genes were screened from TSCC and normal individuals using bioinformatics and microarray technology. These genes may be used as diagnostic and therapeutic biomarkers for TSCC. In addition, SPP1 and FNl were identified as potential biomarkers for the progression of TSCC.", "claims": [{"id": "claim-method", "statement": "GEO2R, an online tool (https://www.ncbi.nlm.nih.gov/geo/geo2r/), was utilized to identify DEGs from the GEO series between TSCC and normal tissues.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:34457068", "locator": "sections[5] \"Identification of DEGs\" paragraph 2", "quote": "GEO2R, an online tool (https://www.ncbi.nlm.nih.gov/geo/geo2r/), was utilized to identify DEGs from the GEO series between TSCC and normal tissues."}], "state": "complete"}, {"id": "claim-data-access", "statement": "The datasets used and/or analyzed during the current study are available from the corresponding author on reasonable request.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:34457068", "locator": "sections[23] \"Availability of data and materials\" paragraph 2", "quote": "The datasets used and/or analyzed during the current 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:34457068"], "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:GSE13601"], "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:GSE13601"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:34457068", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.3892/ol.2021.12974", "sha256": "sha256:60b56b79cb284fbe08c0135a72a50b40018fc84535f4b133772fb97f0dfd3d68", "bytes": 28547, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.3892/ol.2021.12974", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC8358624", "source": "europe_pmc_fulltext", "coverage": "whole_body_without_references", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE13601", "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=GSE13601", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE13601", "version": null, "note": "The datasets used and/or analyzed during the current 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 current study are available from the corresponding author on reasonable request.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM342530", "GSM342531", "GSM342532", "GSM342533", "GSM342534", "GSM342535", "GSM342536", "GSM342537", "GSM342538", "GSM342539", "GSM342540", "GSM342541", "GSM342542", "GSM342543", "GSM342544", "GSM342545", "GSM342546", "GSM342547", "GSM342548", "GSM342549", "GSM342550", "GSM342551", "GSM342552", "GSM342553", "GSM342554", "GSM342555", "GSM342556", "GSM342557", "GSM342558", "GSM342559", "GSM342560", "GSM342561", "GSM342562", "GSM342563", "GSM342564", "GSM342565", "GSM342566", "GSM342567", "GSM342568", "GSM342569", "GSM342570", "GSM342571", "GSM342572", "GSM342573", "GSM342574", "GSM342575", "GSM342576", "GSM342577", "GSM342578", "GSM342579", "GSM342580", "GSM342581", "GSM342582", "GSM342583", "GSM342584", "GSM342585", "GSM342586", "GSM342587"], "sample_count": 58, "group_sizes": null, "group_sizes_basis": null, "platform": "8300", "taxon": "Homo sapiens", "title": "Oral tongue cancer gene expression profiling: Identification of novel potential prognosticators", "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:GSE31056", "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=GSE31056", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE31056", "version": null, "note": "The datasets used and/or analyzed during the current 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 current study are available from the corresponding author on reasonable request.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM771152", "GSM771153", "GSM771154", "GSM771155", "GSM771156", "GSM771157", "GSM771158", "GSM771159", "GSM771160", "GSM771161", "GSM771162", "GSM771163", "GSM771164", "GSM771165", "GSM771166", "GSM771167", "GSM771168", "GSM771169", "GSM771170", "GSM771171", "GSM771172", "GSM771173", "GSM771174", "GSM771175", "GSM771176", "GSM771177", "GSM771178", "GSM771179", "GSM771180", "GSM771181", "GSM771182", "GSM771183", "GSM771184", "GSM771185", "GSM771186", "GSM771187", "GSM771188", "GSM771189", "GSM771190", "GSM771191", "GSM771192", "GSM771193", "GSM771194", "GSM771195", "GSM771196", "GSM771197", "GSM771198", "GSM771199", "GSM771200", "GSM771201", "GSM771202", "GSM771203", "GSM771204", "GSM771205", "GSM771206", "GSM771207", "GSM771208", "GSM771209", "GSM771210", "GSM771211", "GSM771212", "GSM771213", "GSM771214", "GSM771215", "GSM771216", "GSM771217", "GSM771218", "GSM771219", "GSM771220", "GSM771221", "GSM771222", "GSM771223", "GSM771224", "GSM771225", "GSM771226", "GSM771227", "GSM771228", "GSM771229", "GSM771230", "GSM771231", "GSM771232", "GSM771233", "GSM771234", "GSM771235", "GSM771236", "GSM771237", "GSM771238", "GSM771239", "GSM771240", "GSM771241", "GSM771242", "GSM771243", "GSM771244", "GSM771245", "GSM771246", "GSM771247"], "sample_count": 96, "group_sizes": null, "group_sizes_basis": null, "platform": "10526", "taxon": "Homo sapiens", "title": "A gene signature in histologically normal surgical margins is predictive of oral carcinoma recurrence", "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:GSE78060", "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=GSE78060", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE78060", "version": null, "note": "The datasets used and/or analyzed during the current 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 current study are available from the corresponding author on reasonable request.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM2065795", "GSM2065796", "GSM2065797", "GSM2065798", "GSM2065799", "GSM2065800", "GSM2065801", "GSM2065802", "GSM2065803", "GSM2065804", "GSM2065805", "GSM2065806", "GSM2065807", "GSM2065808", "GSM2065809", "GSM2065810", "GSM2065811", "GSM2065812", "GSM2065813", "GSM2065814", "GSM2065815", "GSM2065816", "GSM2065817", "GSM2065818", "GSM2065819", "GSM2065820", "GSM2065821", "GSM2065822", "GSM2065823", "GSM2065824"], "sample_count": 30, "group_sizes": null, "group_sizes_basis": null, "platform": "570", "taxon": "Homo sapiens", "title": "A gene expression profiling to predict recurrence of advanced tongue squamous cell carcinoma (TSCC): Discovery and external validation", "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:GSE13601 not downloaded", "asset:data:geo:GSE13601 licence not read", "asset:data:geo:GSE31056 not downloaded", "asset:data:geo:GSE31056 licence not read", "asset:data:geo:GSE78060 not downloaded", "asset:data:geo:GSE78060 licence not read"]}, "analysis": {"state": "partial", "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": 0.8, "band": "high", "quote": "Kaplan-Meier"}}, {"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": "Pathway enrichment"}}, {"id": "method-4", "family": null, "specific": null, "label": "GEO2R", "dsl_operations": [], "missing_operations": [], "expressible": null, "parameters": {}, "data_shapes": [], "evidence": {"score": 1.0, "band": "verbatim", "quote": "GEO2R, an online tool (https://www.ncbi.nlm.nih.gov/geo/geo2r/), was utilized to identify DEGs from the GEO series between TSCC and normal tissues."}}], "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": ["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": ["GSE31056", "GSE13601", "GSE78060"], "resolved_accessions": ["GSE31056", "GSE13601", "GSE78060"], "statements": ["The datasets used and/or analyzed during the current study are available from the corresponding author on reasonable request."], "basis": "The paper names GSE31056, GSE13601, GSE78060 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:34457068", "data:geo:GSE13601"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE13601"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-10-31T18:34:08Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 3, "usage": {"prompt_tokens": 20906, "completion_tokens": 1244, "cached_tokens": 784}}, "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:34457068", "type": "paper", "label": "pmid:34457068"}, {"id": "source:pmid:34457068", "type": "manuscript", "label": "PMID 34457068 full text"}, {"id": "data:geo:GSE13601", "type": "dataset", "label": "GEO GSE13601"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:34457068", "type": "paper", "label": "pmid:34457068"}, {"id": "source:pmid:34457068", "type": "manuscript", "label": "PMID 34457068 full text"}, {"id": "data:geo:GSE13601", "type": "dataset", "label": "GEO GSE13601"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-34457068", "type": "extraction", "used": ["source:pmid:34457068"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE13601", "type": "accession_resolution", "used": ["data:geo:GSE13601"], "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:34457068", "parent_hash": "sha256:2111c75fb9c7d1415468525891f82921716f76eff6462abb01374f2e3c969422", "fork_of": null, "generation": 6}, "gaps": ["asset:data:geo:GSE13601 licence not read", "asset:data:geo:GSE13601 not downloaded", "asset:data:geo:GSE31056 licence not read", "asset:data:geo:GSE31056 not downloaded", "asset:data:geo:GSE78060 licence not read", "asset:data:geo:GSE78060 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": 0.99, "evidence": ["normal individuals using bioinformatics and microarray technology. These genes may be used as diagn", "lidation and analysis of hub genes Published microarray data were retrieved from the Oncomine databa"], "order_basis": "paper_text_order:1404", "id": "assay:1"}, {"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": 0.8, "evidence": ["Kaplan-Meier"], "order_basis": "consumes_earlier_output", "id": "assay:2"}]}