Variational graph autoencoder for reconstructed transcriptomic data associated with NLRP3 mediated pyroptosis in periodontitis.

{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:39809940", "kind": "science-record", "revision": 2, "content_hash": "sha256:c611ef2b2e4566c6c437b57722e7dddfb340cb590dbea79f3d3c9b51daa246ea", "created_at": "2026-11-01T20:30:07Z", "updated_at": "2026-11-01T21:34:42Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Variational graph autoencoder for reconstructed transcriptomic data associated with NLRP3 mediated pyroptosis in periodontitis.", "doi": "10.1038/s41598-025-86455-4", "pmid": "39809940", "authors": ["Pradeep K Yadalam", "Prabhu Manickam Natarajan", "Carlos M Ardila"], "journal": "Scientific reports", "year": 2025, "abstract": "The NLRP3 inflammasome, regulated by TLR4, plays a pivotal role in periodontitis by mediating inflammatory cytokine release and bone loss induced by Porphyromonas gingivalis. Periodontal disease creates a hypoxic environment, favoring anaerobic bacteria survival and exacerbating inflammation. The NLRP3 inflammasome triggers pyroptosis, a programmed cell death that amplifies inflammation and tissue damage. This study evaluates the efficacy of Variational Graph Autoencoders (VGAEs) in reconstructing gene data related to NLRP3-mediated pyroptosis in periodontitis. The NCBI GEO dataset GSE262663, containing three samples with and without hypoxia exposure, was analyzed using unsupervised K-means clustering. This method identifies natural groupings within biological data without prior labels. VGAE, a deep learning model, captures complex graph relationships for tasks like link prediction and edge detection. The VGAE model demonstrated exceptional performance with an accuracy of 99.42% and perfect precision. While it identified 5,820 false negatives, indicating a conservative approach, it accurately predicted 4,080 out of 9,900 positive samples. The model's latent space distribution differed significantly from the original data, suggesting a tightly clustered representation of the gene expression patterns. K-means clustering and VGAE show promise in gene expression analysis and graph structure reconstruction for periodontitis research.", "claims": [{"id": "claim-method", "statement": "The Variational Graph Autoencoder (VGAE)12 is a generative model designed for graph-structured data that combines graph convolutional networks (GCNs) with variational inference.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:39809940", "locator": "sections[5] \"Variational graph autoencoder (VGAE) model architecture\" paragraph 2", "quote": "The Variational Graph Autoencoder (VGAE)12 is a generative model designed for graph-structured data that combines graph convolutional networks (GCNs) with variational inference."}], "state": "complete"}, {"id": "claim-data-access", "statement": "The datasets generated during and/or analysed during the current study are available from the corresponding author on reasonable request.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:39809940", "locator": "sections[22] \"Data availability\" paragraph 2", "quote": "The datasets generated during and/or analysed during the current study are available from the corresponding author on reasonable request."}], "state": "complete"}, {"id": "claim-target-result", "statement": "The VGAE model achieved 99.42% accuracy and perfect precision, but identified only 4,080 of 9,900 positive samples.", "kind": "quantitative", "target": {"value": 99.42, "unit": "per cent", "tolerance": null, "source": "The model demonstrated exceptional performance with an accuracy of 99.42% and perfect precision, as indicated by a confusion matrix showing no false positives and a high number of true negatives (990,100)."}, "evidence": [{"asset": "source:pmid:39809940", "locator": "sections[15] \"Performance evaluation\" paragraph 2", "quote": "The model demonstrated exceptional performance with an accuracy of 99.42% and perfect precision, as indicated by a confusion matrix showing no false positives and a high number of true negatives (990,100)."}, {"asset": "source:pmid:39809940", "locator": "sections[15] \"Performance evaluation\" paragraph 2", "quote": "However, it identified only 4,080 true positives out of 9,900 positive samples, resulting in 5,820 false negatives."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "complete", "objective": "The VGAE model achieved 99.42% accuracy and perfect precision, but identified only 4,080 of 9,900 positive samples.", "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:39809940"], "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:GSE262663"], "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:GSE262663"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:39809940", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1038/s41598-025-86455-4", "sha256": "sha256:cc628af548bd0c6697eb694da5b70bee7a817008ac3d4a00e7b09fdcbdeeed5d", "bytes": 41190, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1038/s41598-025-86455-4", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC11733260", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE262663", "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=GSE262663", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE262663", "version": null, "note": "The datasets generated during and/or analysed 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 generated during and/or analysed during the current study are available from the corresponding author on reasonable request.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM8173268", "GSM8173269", "GSM8173270", "GSM8173271", "GSM8173272", "GSM8173273"], "sample_count": 6, "group_sizes": null, "group_sizes_basis": null, "platform": "24676", "taxon": "Homo sapiens", "title": "Hypoxia activates AMPK and drives NLRP3-mediated pyroptosis in periodontitis", "resolution_checked_at": "2026-11-01T20:16:08Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}], "gaps": ["asset:data:geo:GSE262663 not downloaded", "asset:data:geo:GSE262663 licence not read"]}, "analysis": {"state": "partial", "methods": [{"id": "method-1", "family": "clustering", "specific": "kmeans", "label": "Clustering", "dsl_operations": ["kmeans_fit"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["feature_matrix"], "evidence": {"score": 0.7, "band": "medium", "quote": "K-means"}}, {"id": "method-2", "family": null, "specific": null, "label": "Variational Graph Autoencoder (VGAE)", "dsl_operations": [], "missing_operations": [], "expressible": null, "parameters": {}, "data_shapes": [], "evidence": {"score": 1.0, "band": "verbatim", "quote": "The Variational Graph Autoencoder (VGAE)12 is a generative model designed for graph-structured data that combines graph convolutional networks (GCNs) with variational inference."}}], "targets": [{"id": "target-published-estimate", "claim_id": "claim-target-result", "operation": "kmeans_fit", "expected_value": 99.42, "unit": "per cent", "tolerance": null, "state": "complete", "note": "The published estimate as the reader quoted it from the paper. No tolerance is published because the paper states none."}], "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": ["kmeans_fit"], "missing_operations": [], "basis": "The paper names the method it used and the corpus's method extractor maps it onto the DSL catalogue: kmeans."}, "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": ["GSE262663"], "resolved_accessions": ["GSE262663"], "statements": ["The datasets generated during and/or analysed during the current study are available from the corresponding author on reasonable request."], "basis": "The paper names GSE262663 in NCBI GEO and the accession resolves in the repository. No dataset was downloaded and no licence was read."}}, "can_run": {"dsl_operations": ["kmeans_fit"], "assets": ["source:pmid:39809940", "data:geo:GSE262663"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE262663"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-11-01T19:44:35Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 5, "usage": {"prompt_tokens": 10467, "completion_tokens": 1131, "cached_tokens": 264}}, "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:39809940", "type": "paper", "label": "pmid:39809940"}, {"id": "source:pmid:39809940", "type": "manuscript", "label": "PMID 39809940 full text"}, {"id": "data:geo:GSE262663", "type": "dataset", "label": "GEO GSE262663"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:39809940", "type": "paper", "label": "pmid:39809940"}, {"id": "source:pmid:39809940", "type": "manuscript", "label": "PMID 39809940 full text"}, {"id": "data:geo:GSE262663", "type": "dataset", "label": "GEO GSE262663"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-39809940", "type": "extraction", "used": ["source:pmid:39809940"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE262663", "type": "accession_resolution", "used": ["data:geo:GSE262663"], "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:39809940", "parent_hash": "sha256:f43eaa9214099c39c324dd9d1613a781c6958775af69979e56dbbb9c81df668c", "fork_of": null, "generation": 1}, "gaps": ["asset:data:geo:GSE262663 licence not read", "asset:data:geo:GSE262663 not downloaded", "execution.not_run", "method.reader_named_unmapped", "review.human_critique", "review.independent_reader", "review.machine_critique"], "assays": [{"role": "analysis", "definition_id": "clustering", "definition_version": "f2132e96ae6c7a4e", "definition_digest": null, "required_operations": ["kmeans_fit"], "support_state": "supported", "source_hashes": {"dsl_catalogue": "f2132e96ae6c7a4e"}, "confidence": 0.7, "evidence": ["K-means"], "order_basis": "analysis_only", "id": "assay:1"}]}