Weighted gene co-expression network analysis (WGCNA) to explore genes responsive to Streptococcus oralis biofilm and immune infiltration analysis in human gingival fibroblasts cells.

{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:33781179", "kind": "science-record", "revision": 7, "content_hash": "sha256:eeeab001f4c2f698274a60a8648a47e77d498bd64389b507120058bcd59477a6", "created_at": "2026-11-01T15:41:30Z", "updated_at": "2026-11-01T22:03:27Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Weighted gene co-expression network analysis (WGCNA) to explore genes responsive to Streptococcus oralis biofilm and immune infiltration analysis in human gingival fibroblasts cells.", "doi": "10.1080/21655979.2021.1902697", "pmid": "33781179", "authors": ["Xia Chen", "Jianfeng Ma"], "journal": "Bioengineered", "year": 2021, "abstract": "The correlation between oral bacteria and dental implants failure has been reported. However, the effect and mechanism of bacteria during dental implants is unclear. In this study, we explored key genes and candidate gene clusters in human gingival fibroblasts (HGF) cells in response to Streptococcus oralis biofilm through weighted gene co-expression network analysis (WGCNA) and differential genes analysis using gene expression matrix, GSE134481, downloaded from the Gene Expression Omnibus (GEO) database. We obtained 325 genes in the module significantly associated with S. oralis infection and 113 differentially expressed genes (DEGs) in the S. oralis biofilm; 62 DEGs indicated significant correlation with S. oralis injury. Multiple immune pathways, such as the tumor necrosis factor (TNF) signaling pathway, were considerably enriched. We obtained a candidate genes cluster containing 12 genes - IL6, JUN, FOS, CSF2, HBEGF, EDN1, CCL2, MYC, NGF, SOCS3, CXCL1, and CXCL2; we observed 5 candidate hub genes associated with S. oralis infection - JUN, IL6, FOS, MYC, and CCL2. The fraction of macrophage M0 cells was significantly increased in biofilm treatment compared with control; expression of FOS and MYC was significantly positively correlated with macrophage M0 cells. Our findings present a fierce inflammation changes in the transcript level of HGF in response to S. oralis.", "claims": [{"id": "claim-method", "statement": "In this study, we explored key genes and candidate gene clusters in human gingival fibroblasts (HGF) cells in response to Streptococcus oralis biofilm through weighted gene co-expression network analysis (WGCNA) and differential genes analysis using gene expression matrix, GSE134481, downloaded from the Gene Expression Omnibus (GEO) database.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:33781179", "locator": "sections[0] \"Abstract\" paragraph 1", "quote": "In this study, we explored key genes and candidate gene clusters in human gingival fibroblasts (HGF) cells in response to Streptococcus oralis biofilm through weighted gene co-expression network analysis (WGCNA) and differential genes analysis using gene expression matrix, GSE134481, downloaded from the Gene Expression Omnibus (GEO) database."}], "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:33781179", "locator": "sections[20] \"Availability of data and material\" 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:33781179"], "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:GSE134481"], "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": {"p_value": "s determined with ANOVA p-value calculated with R packa"}, "inputs": ["data:geo:GSE134481"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:33781179", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1080/21655979.2021.1902697", "sha256": "sha256:1cb0bde955d2c929d1910364c077f6f09c9bea65a8a5361627b9e3f37670be37", "bytes": 33187, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1080/21655979.2021.1902697", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC8806260", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE134481", "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=GSE134481", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE134481", "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": ["GSM3950728", "GSM3950729", "GSM3950730", "GSM3950731", "GSM3950732", "GSM3950733", "GSM3950734", "GSM3950735", "GSM3950736", "GSM3950737", "GSM3950738", "GSM3950739", "GSM3950740", "GSM3950741", "GSM3950742", "GSM3950743", "GSM3950744", "GSM3950745", "GSM3950746", "GSM3950747", "GSM3950748", "GSM3950749", "GSM3950750", "GSM3950751"], "sample_count": 24, "group_sizes": null, "group_sizes_basis": null, "platform": "13497", "taxon": "Homo sapiens", "title": "Effects of Streptococcus oralis biofilm on peri-implant soft-tissue cells", "resolution_checked_at": "2026-11-01T15:39:54Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}], "gaps": ["asset:data:geo:GSE134481 not downloaded", "asset:data:geo:GSE134481 licence not read"]}, "analysis": {"state": "partial", "methods": [{"id": "method-1", "family": "group_comparison", "specific": "anova", "label": "Group comparison", "dsl_operations": ["group_summary", "welch_t", "bootstrap_mean_difference", "group_comparison_anova"], "missing_operations": [], "expressible": true, "parameters": {"p_value": "s determined with ANOVA p-value calculated with R packa"}, "data_shapes": ["two_or_more_groups_continuous"], "evidence": {"score": 0.8, "band": "high", "quote": "ANOVA"}}, {"id": "method-2", "family": null, "specific": null, "label": "weighted gene co-expression network analysis (WGCNA)", "dsl_operations": [], "missing_operations": [], "expressible": null, "parameters": {}, "data_shapes": [], "evidence": {"score": 1.0, "band": "verbatim", "quote": "In this study, we explored key genes and candidate gene clusters in human gingival fibroblasts (HGF) cells in response to Streptococcus oralis biofilm through weighted gene co-expression network analysis (WGCNA) and differential genes analysis using gene expression matrix, GSE134481, downloaded from the Gene Expression Omnibus (GEO) database."}}], "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": ["group_summary", "welch_t", "bootstrap_mean_difference", "group_comparison_anova"], "missing_operations": [], "basis": "The paper names the method it used and the corpus's method extractor maps it onto the DSL catalogue: anova."}, "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": ["GSE134481"], "resolved_accessions": ["GSE134481"], "statements": ["The datasets used and/or analyzed during the current study are available from the corresponding author on reasonable request."], "basis": "The paper names GSE134481 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": ["group_summary", "welch_t", "bootstrap_mean_difference", "group_comparison_anova"], "assets": ["source:pmid:33781179", "data:geo:GSE134481"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE134481"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-10-31T18:28:38Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 3, "usage": {"prompt_tokens": 25561, "completion_tokens": 1296, "cached_tokens": 656}}, "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:33781179", "type": "paper", "label": "pmid:33781179"}, {"id": "source:pmid:33781179", "type": "manuscript", "label": "PMID 33781179 full text"}, {"id": "data:geo:GSE134481", "type": "dataset", "label": "GEO GSE134481"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:33781179", "type": "paper", "label": "pmid:33781179"}, {"id": "source:pmid:33781179", "type": "manuscript", "label": "PMID 33781179 full text"}, {"id": "data:geo:GSE134481", "type": "dataset", "label": "GEO GSE134481"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-33781179", "type": "extraction", "used": ["source:pmid:33781179"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE134481", "type": "accession_resolution", "used": ["data:geo:GSE134481"], "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:33781179", "parent_hash": "sha256:9970d0430588b57f6c7e981167e692f7492f62f2a2736b5fe6b019d37c9a0964", "fork_of": null, "generation": 6}, "gaps": ["asset:data:geo:GSE134481 licence not read", "asset:data:geo:GSE134481 not downloaded", "execution.not_run", "method.reader_named_unmapped", "review.human_critique", "review.independent_reader", "review.machine_critique"], "assays": [{"role": "analysis", "definition_id": "group_comparison", "definition_version": "f2132e96ae6c7a4e", "definition_digest": null, "required_operations": ["group_summary", "welch_t", "bootstrap_mean_difference", "group_comparison_anova"], "support_state": "supported", "source_hashes": {"dsl_catalogue": "f2132e96ae6c7a4e"}, "confidence": 0.8, "evidence": ["ANOVA"], "order_basis": "analysis_only", "id": "assay:1"}]}