Identification of Hub Genes and Key Pathways Associated With Bipolar Disorder Based on Weighted Gene Co-expression Network Analysis.

{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:31481902", "kind": "science-record", "revision": 5, "content_hash": "sha256:fa0abe9afd7a6bec1cad1b70632fb04873c3224060031ae500adba06f6ccfe61", "created_at": "2026-11-01T15:40:49Z", "updated_at": "2026-11-01T22:00:48Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Identification of Hub Genes and Key Pathways Associated With Bipolar Disorder Based on Weighted Gene Co-expression Network Analysis.", "doi": "10.3389/fphys.2019.01081", "pmid": "31481902", "authors": ["Yang Liu", "Hui-Yun Gu", "Jie Zhu", "Yu-Ming Niu", "Chao Zhang", "Guang-Ling Guo"], "journal": "Frontiers in physiology", "year": 2019, "abstract": "Bipolar disorder (BD) is a complex mental disorder with high mortality and disability rates worldwide; however, research on its pathogenesis and diagnostic methods remains limited. This study aimed to elucidate potential candidate hub genes and key pathways related to BD in a pre-frontal cortex sample. Raw gene expression profile files of GSE53987, including 36 samples, were obtained from the gene expression omnibus (GEO) database. After data pre-processing, 10,094 genes were selected for weighted gene co-expression network analysis (WGCNA). After dividing highly related genes into 19 modules, we found that the pink, midnight blue, and brown modules were highly correlated with BD. Functional annotation and pathway enrichment analysis for modules, which indicated some key pathways, were conducted based on the Enrichr database. One of the most remarkable significant pathways is the Hippo signaling pathway and its positive transcriptional regulation. Finally, 30 hub genes were identified in three modules. Hub genes with a high degree of connectivity in the PPI network are significantly enriched in positive regulation of transcription. In addition, the hub genes were validated based on another dataset (GSE12649). Taken together, the identification of these 30 hub genes and enrichment pathways might have important clinical implications for BD treatment and diagnosis.", "claims": [{"id": "claim-method", "statement": "Weighted gene co-expression network analysis package was necessary for the co-expression network construction (Langfelder and Horvath, 2008).", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:31481902", "locator": "sections[4] \"Co-expression Network Construction\" paragraph 2", "quote": "Weighted gene co-expression network analysis package was necessary for the co-expression network construction (Langfelder and Horvath, 2008)."}], "state": "complete"}, {"id": "claim-data-access", "statement": "Publicly available datasets were analyzed in this study. This data can be found at: https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE53987.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:31481902", "locator": "sections[13] \"Data Availability\" paragraph 2", "quote": "Publicly available datasets were analyzed in this study. This data can be found at: https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE53987."}], "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:31481902"], "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:GSE12649"], "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:GSE12649"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:31481902", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.3389/fphys.2019.01081", "sha256": "sha256:be56553b04c4d1d981ed19bec509192a3e886d8e335252664a9c7b53d24f7e35", "bytes": 25924, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.3389/fphys.2019.01081", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC6710482", "source": "europe_pmc_fulltext", "coverage": "whole_body_without_references", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE12649", "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=GSE12649", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE12649", "version": null, "note": "Publicly available datasets were analyzed in this study. This data can be found at: https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE53987.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "Publicly available datasets were analyzed in this study. This data can be found at: https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE53987.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM317385", "GSM317386", "GSM317387", "GSM317388", "GSM317389", "GSM317390", "GSM317391", "GSM317392", "GSM317393", "GSM317394", "GSM317395", "GSM317396", "GSM317397", "GSM317398", "GSM317399", "GSM317400", "GSM317401", "GSM317402", "GSM317403", "GSM317404", "GSM317405", "GSM317406", "GSM317407", "GSM317408", "GSM317409", "GSM317410", "GSM317411", "GSM317412", "GSM317413", "GSM317414", "GSM317415", "GSM317416", "GSM317417", "GSM317418", "GSM317419", "GSM317420", "GSM317421", "GSM317422", "GSM317423", "GSM317424", "GSM317425", "GSM317426", "GSM317427", "GSM317428", "GSM317429", "GSM317430", "GSM317431", "GSM317432", "GSM317433", "GSM317434", "GSM317435", "GSM317436", "GSM317437", "GSM317438", "GSM317439", "GSM317440", "GSM317441", "GSM317442", "GSM317443", "GSM317444", "GSM317445", "GSM317446", "GSM317447", "GSM317448", "GSM317449", "GSM317450", "GSM317451", "GSM317452", "GSM317453", "GSM317454", "GSM317455", "GSM317456", "GSM317457", "GSM317458", "GSM317459", "GSM317460", "GSM317461", "GSM317462", "GSM317463", "GSM317464", "GSM317465", "GSM317466", "GSM317467", "GSM317468", "GSM317469", "GSM317470", "GSM317471", "GSM317472", "GSM317473", "GSM317474", "GSM317475", "GSM317476", "GSM317477", "GSM317478", "GSM317479", "GSM317480", "GSM317481", "GSM317482", "GSM317483", "GSM317484", "GSM317485", "GSM317486"], "sample_count": 102, "group_sizes": null, "group_sizes_basis": null, "platform": "96", "taxon": "Homo sapiens", "title": "Gene expression from human prefrontal cortex (BA46)", "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:GSE53987", "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=GSE53987", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE53987", "version": null, "note": "Publicly available datasets were analyzed in this study. This data can be found at: https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE53987.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "Publicly available datasets were analyzed in this study. This data can be found at: https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE53987.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM1304852", "GSM1304853", "GSM1304854", "GSM1304855", "GSM1304856", "GSM1304857", "GSM1304858", "GSM1304859", "GSM1304860", "GSM1304861", "GSM1304862", "GSM1304863", "GSM1304864", "GSM1304865", "GSM1304866", "GSM1304867", "GSM1304868", "GSM1304869", "GSM1304870", "GSM1304871", "GSM1304872", "GSM1304873", "GSM1304874", "GSM1304875", "GSM1304876", "GSM1304877", "GSM1304878", "GSM1304879", "GSM1304880", "GSM1304881", "GSM1304882", "GSM1304883", "GSM1304884", "GSM1304885", "GSM1304886", "GSM1304887", "GSM1304888", "GSM1304889", "GSM1304890", "GSM1304891", "GSM1304892", "GSM1304893", "GSM1304894", "GSM1304895", "GSM1304896", "GSM1304897", "GSM1304898", "GSM1304899", "GSM1304900", "GSM1304901", "GSM1304902", "GSM1304903", "GSM1304904", "GSM1304905", "GSM1304906", "GSM1304907", "GSM1304908", "GSM1304909", "GSM1304910", "GSM1304911", "GSM1304912", "GSM1304913", "GSM1304914", "GSM1304915", "GSM1304916", "GSM1304917", "GSM1304918", "GSM1304919", "GSM1304920", "GSM1304921", "GSM1304922", "GSM1304923", "GSM1304924", "GSM1304925", "GSM1304926", "GSM1304927", "GSM1304928", "GSM1304929", "GSM1304930", "GSM1304931", "GSM1304932", "GSM1304933", "GSM1304934", "GSM1304935", "GSM1304936", "GSM1304937", "GSM1304938", "GSM1304939", "GSM1304940", "GSM1304941", "GSM1304942", "GSM1304943", "GSM1304944", "GSM1304945", "GSM1304946", "GSM1304947", "GSM1304948", "GSM1304949", "GSM1304950", "GSM1304951", "GSM1304952", "GSM1304953", "GSM1304954", "GSM1304955", "GSM1304956", "GSM1304957", "GSM1304958", "GSM1304959", "GSM1304960", "GSM1304961", "GSM1304962", "GSM1304963", "GSM1304964", "GSM1304965", "GSM1304966", "GSM1304967", "GSM1304968", "GSM1304969", "GSM1304970", "GSM1304971", "GSM1304972", "GSM1304973", "GSM1304974", "GSM1304975", "GSM1304976", "GSM1304977", "GSM1304978", "GSM1304979", "GSM1304980", "GSM1304981", "GSM1304982", "GSM1304983", "GSM1304984", "GSM1304985", "GSM1304986", "GSM1304987", "GSM1304988", "GSM1304989", "GSM1304990", "GSM1304991", "GSM1304992", "GSM1304993", "GSM1304994", "GSM1304995", "GSM1304996", "GSM1304997", "GSM1304998", "GSM1304999", "GSM1305000", "GSM1305001", "GSM1305002", "GSM1305003", "GSM1305004", "GSM1305005", "GSM1305006", "GSM1305007", "GSM1305008", "GSM1305009", "GSM1305010", "GSM1305011", "GSM1305012", "GSM1305013", "GSM1305014", "GSM1305015", "GSM1305016", "GSM1305017", "GSM1305018", "GSM1305019", "GSM1305020", "GSM1305021", "GSM1305022", "GSM1305023", "GSM1305024", "GSM1305025", "GSM1305026", "GSM1305027", "GSM1305028", "GSM1305029", "GSM1305030", "GSM1305031", "GSM1305032", "GSM1305033", "GSM1305034", "GSM1305035", "GSM1305036", "GSM1305037", "GSM1305038", "GSM1305039", "GSM1305040", "GSM1305041", "GSM1305042", "GSM1305043", "GSM1305044", "GSM1305045", "GSM1305046", "GSM1305047", "GSM1305048", "GSM1305049", "GSM1305050", "GSM1305051", "GSM1305052", "GSM1305053", "GSM1305054", "GSM1305055", "GSM1305056"], "sample_count": 205, "group_sizes": null, "group_sizes_basis": null, "platform": "570", "taxon": "Homo sapiens", "title": "Microarray profiling of PFC, HPC and STR from subjects with schizophrenia, bipolar, MDD or control", "resolution_checked_at": "2026-11-01T15:39:54Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "asset:table:pmid:31481902:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:5b086245536a34b05c8c2fc076604b961d384f2ad686bdfc6aa132cf867fa322", "bytes": 2829, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[10]/table-wrap[1]#T1", "version": null, "note": "Hub genes from the interesting modules.", "structure": {"pmcid": "PMC6710482", "section_index": 10, "section_title": "Validation of Hub Gene and PPI Network Construction", "row_count": 31, "column_count": 6}, "table": {"label": "TABLE 1", "caption": "Hub genes from the interesting modules.", "rows": [["Gene symbol", "ENTREZ_GENE_ID", "Gene ontology", "geneModuleMembership", "Gene trait significance", "Up or down"], ["AGT", "183", "Alkylguanine DNA binding", "0.887157454", "0.298842057", "Down"], ["AHCYL1", "10768", "Adenosylmethionine hydrolase activity", "0.892921034", "0.263587391", "Down"], ["APOE", "348", "Cognition", "0.906508824", "0.259473598", "Down"], ["ATP1A2", "477", "Temperature gated cation channel activity", "0.944732073", "0.358469425", "Down"], ["CHRDL1", "91851", "Negative regulation of secondary growth", "0.863182953", "0.462817741", "Down"], ["EMX2", "2018", "Forebrain neuroblast differentiation", "0.943545349", "0.339285953", "Down"], ["ETNPPL", "64850", "/", "0.905878301", "0.312454124", "Down"], ["FAM189A2", "9413", "Gene expression", "0.872771128", "0.313792924", "Down"], ["FGF2", "2247", "fibroblast proliferation", "0.9348346", "0.45704696", "Down"], ["GJA1", "2697", "Gap junction", "0.920113458", "0.328482543", "Down"], ["GNA12", "2768", "Spermatid nucleus differentiation", "0.867055073", "0.311316484", "Down"], ["HEPH", "9843", "Copper exporting atpase activity", "0.959262811", "0.384839787", "Down"], ["IL17RB", "55540", "Cardiac fibroblast cell fate commitment", "0.87323481", "0.315545635", "Down"], ["MAOA", "4128", "Monoamine oxidase activity", "0.889016805", "0.495684", "Down"], ["METTL7A", "25840", "RNA polymerase II regulatory region DNA binding", "0.93466073", "0.322509631", "Down"], ["NOTCH2", "4853", "Notch signaling pathway", "0.952637565", "0.360026782", "Down"], ["NTRK2", "4915", "Regulation of neurotrophin TRK receptor signaling pathway", "0.947485184", "0.327326464", "Down"], ["PARD3", "56288", "Positive regulation of JAK STAT cascade", "0.877332438", "0.357811988", "Down"], ["PAX6", "5080", "Eye development", "0.912624234", "0.408751454", "Down"], ["PDLIM5", "10611", "Activation of bipolar cell growth", "0.92796358", "0.456391993", "Down"], ["PPAP2B", "8613", "Cell migration involved in coronary angiogenesis", "0.882924502", "0.299775962", "Down"], ["RAB31", "11031", "ER body", "0.908780797", "0.376400336", "Down"], ["SDC2", "6383", "Positive regulation of synapse maturation", "0.935916785", "0.333198546", "Down"], ["SDC4", "6385", "Small molecule catabolic process", "0.889206651", "0.361762932", "Down"], ["SLC1A3", "6507", "Negative regulation of L glutamate transport", "0.930712467", "0.322178332", "Down"], ["SMAD2", "4087", "SMAD2 protein complex", "0.841744744", "0.431128371", "Down"], ["SOX2", "6657", "Stem cell differentiation", "0.960030288", "0.437884345", "Down"], ["TP53BP2", "7159", "P53 binding", "0.916365941", "0.261334186", "Down"], ["YAP1", "10413", "Hippo signaling", "0.946460117", "0.317467764", "Down"], ["YES1", "7525", "Regulation of B cell antigen processing and presentation", "0.913582422", "0.40331199", "Down"]], "row_count": 31, "column_count": 6, "numeric_cells": 96, "header_rows": 1, "locator": "section[10]/table-wrap[1]#T1"}}], "gaps": ["asset:data:geo:GSE12649 not downloaded", "asset:data:geo:GSE12649 licence not read", "asset:data:geo:GSE53987 not downloaded", "asset:data:geo:GSE53987 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": "PPI"}}, {"id": "method-2", "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-3", "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": "Weighted gene co-expression network analysis package was necessary for the co-expression network construction (Langfelder and Horvath, 2008)."}}], "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": ["GSE53987", "GSE12649"], "resolved_accessions": ["GSE53987", "GSE12649"], "statements": ["Publicly available datasets were analyzed in this study. This data can be found at: https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE53987."], "basis": "The paper names GSE53987, GSE12649 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": ["build_graph", "centrality_scores", "pathway_enrich"], "assets": ["source:pmid:31481902", "data:geo:GSE12649", "asset:table:pmid:31481902:1"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE12649"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-10-31T18:16:00Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 3, "usage": {"prompt_tokens": 19249, "completion_tokens": 1656, "cached_tokens": 12544}}, "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:31481902", "type": "paper", "label": "pmid:31481902"}, {"id": "source:pmid:31481902", "type": "manuscript", "label": "PMID 31481902 full text"}, {"id": "data:geo:GSE12649", "type": "dataset", "label": "GEO GSE12649"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:31481902", "type": "paper", "label": "pmid:31481902"}, {"id": "source:pmid:31481902", "type": "manuscript", "label": "PMID 31481902 full text"}, {"id": "data:geo:GSE12649", "type": "dataset", "label": "GEO GSE12649"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-31481902", "type": "extraction", "used": ["source:pmid:31481902"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE12649", "type": "accession_resolution", "used": ["data:geo:GSE12649"], "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:31481902", "parent_hash": "sha256:594a49c0f6d1de449d4b67a30e7222697e49f119e2cae218059b6f30dac1db09", "fork_of": null, "generation": 4}, "gaps": ["asset:data:geo:GSE12649 licence not read", "asset:data:geo:GSE12649 not downloaded", "asset:data:geo:GSE53987 licence not read", "asset:data:geo:GSE53987 not downloaded", "execution.not_run", "method.reader_named_unmapped", "review.human_critique", "review.independent_reader", "review.machine_critique"], "assays": [{"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": ["PPI"], "order_basis": "analysis_only", "id": "assay:1"}]}