Identifying the impact of ARHGAP and MAP gene families on autism spectrum disorders.

{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:39514479", "kind": "science-record", "revision": 3, "content_hash": "sha256:e81c327fedf6dd0dda5cfe3186cc0dbc58a5943b14f3094b1e5807235fced259", "created_at": "2026-11-01T20:29:46Z", "updated_at": "2026-11-01T22:13:05Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Identifying the impact of ARHGAP and MAP gene families on autism spectrum disorders.", "doi": "10.1371/journal.pone.0306759", "pmid": "39514479", "authors": ["Tianci Gao", "Wenjun Dang", "Zhimei Jiang", "Yuwei Jiang"], "journal": "PloS one", "year": 2024, "abstract": "The rising incidence of Autism Spectrum Disorder (ASD) has become a major concern, affecting children's psychological well-being and placing a significant strain on healthcare systems. Despite its impact, the etiological mechanisms underpinning ASD remain elusive. This study leveraged dorsolateral prefrontal cortex gene data from 452 individuals of European descent, sourced from the CommonMindConsortium, and examined ASD-related gene expression data from the Gene Expression Omnibus (GEO) database (GSE18123), along with Genome-Wide Association Studies (GWAS) data from the Lundbeck Foundation Integrated Psychiatric Research and Psychiatric Genomics Consortium. Expression quantitative trait loci data were sourced from the GTExv8 database. We employed Transcriptome-Wide Association Studies (TWAS) and Weighted Gene Co-expression Network Analysis (WGCNA) to pinpoint genes within ASD-associated susceptibility gene families (ARHGAP, MAP). Four genes-ARHGAP27, MAPT, ARHGAP19, and MAP1B-were scrutinized, and their biological implications were elucidated through Gene Ontology (GO) and Kyoto Encyclopedia of Genes and Genomes (KEGG) enrichment analyses. Protein-Protein Interaction (PPI) analysis and conditional analysis within the TWAS framework helped identify pivotal genes (ARHGAP27, MAPT). A subsequent verification phase involving Mendelian Randomization (MR) evaluated the potential causal links between the identified genes and ASD. The findings revealed no causal association between ARHGAP19, MAP1B, and ASD. In contrast, significant causal relationships were established for ARHGAP27 and MAPT, suggesting that ARHGAP27 may elevate ASD risk as a susceptibility gene, whereas MAPT appears to reduce the risk as a protective gene.", "claims": [{"id": "claim-method", "statement": "We employed Transcriptome-Wide Association Studies (TWAS) and Weighted Gene Co-expression Network Analysis (WGCNA) to pinpoint genes within ASD-associated susceptibility gene families (ARHGAP, MAP).", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:39514479", "locator": "sections[0] \"Abstract\" paragraph 1", "quote": "We employed Transcriptome-Wide Association Studies (TWAS) and Weighted Gene Co-expression Network Analysis (WGCNA) to pinpoint genes within ASD-associated susceptibility gene families (ARHGAP, MAP)."}], "state": "complete"}, {"id": "claim-data-access", "statement": "The data that support the findings of this study are openly available in [CommonMindConsortium (CMC)]at [10.1038/nn.4399] The data that support the findings of this study are openly available in [GSE18123,]at [Gene Expression Omnibus (GEO)] The data that support the findings of this study are openly available in [ASD, the GWAS data comes from the meta-analysis GWAS]at [https://ww.med.unc.edu/pgc] The data that support the findings of this study are openly available in [GTExv8 eQTL]at [(https://www.gtexportal.org/home/].", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:39514479", "locator": "sections[22] \"Data Availability\" paragraph 2", "quote": "The data that support the findings of this study are openly available in [CommonMindConsortium (CMC)]at [10.1038/nn.4399] The data that support the findings of this study are openly available in [GSE18123,]at [Gene Expression Omnibus (GEO)] The data that support the findings of this study are openly available in [ASD, the GWAS data comes from the meta-analysis GWAS]at [https://ww.med.unc.edu/pgc] The data that support the findings of this study are openly available in [GTExv8 eQTL]at [(https://www.gtexportal.org/home/]."}], "state": "complete"}, {"id": "claim-target-result", "statement": "This analysis confirmed a significant causal association for ARHGAP27 and MAPT with ASD.", "kind": "quantitative", "target": {"value": 95.0, "unit": "per cent", "tolerance": null, "source": "These findings pinpoint ARHGAP27 and MAPT as potential susceptibility genes for ASD, with ARHGAP27(OR = 1.195, 95%CI:1.082–1.318. p<0.001) linked to an increased risk and MAPT(OR = 0.832, 95%CI:0.744–0.930, p<0.001) to a decreased risk of developing ASD."}, "evidence": [{"asset": "source:pmid:39514479", "locator": "sections[16] \"MR validation results\" paragraph 4", "quote": "This analysis confirmed a significant causal association for ARHGAP27 and MAPT with ASD."}, {"asset": "source:pmid:39514479", "locator": "sections[16] \"MR validation results\" paragraph 4", "quote": "These findings pinpoint ARHGAP27 and MAPT as potential susceptibility genes for ASD, with ARHGAP27(OR = 1.195, 95%CI:1.082–1.318. p<0.001) linked to an increased risk and MAPT(OR = 0.832, 95%CI:0.744–0.930, p<0.001) to a decreased risk of developing ASD."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "complete", "objective": "This analysis confirmed a significant causal association for ARHGAP27 and MAPT with ASD.", "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:39514479"], "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:GSE18123"], "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:GSE18123"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:39514479", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1371/journal.pone.0306759", "sha256": "sha256:5fe07baed9963e067a4ab9e9a0d12800b881c50e80f52b61ae788cd38a743c8f", "bytes": 37985, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1371/journal.pone.0306759", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC11548836", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE18123", "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=GSE18123", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE18123", "version": null, "note": "The data that support the findings of this study are openly available in [CommonMindConsortium (CMC)]at [10.1038/nn.4399] The data that support the findings of this study are openly available in [GSE18123,]at [Gene Expression Omnibus (GEO)] The data that support the findings of this study are openly available in [ASD, the GWAS data comes from the meta-analysis GWAS]at [https://ww.med.unc.edu/pgc] The data that support the findings of this study are openly available in [GTExv8 eQTL]at [(https://www.gtexportal.org/home/].", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The data that support the findings of this study are openly available in [CommonMindConsortium (CMC)]at [10.1038/nn.4399] The data that support the findings of this study are openly available in [GSE18123,]at [Gene Expression Omnibus (GEO)] The data that support the findings of this study are openly available in [ASD, the GWAS data comes from the meta-analysis GWAS]at [https://ww.med.unc.edu/pgc] The data that support the findings of this study are openly available in [GTExv8 eQTL]at [(https://www.gtexportal.org/home/].", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM650510", "GSM650512", "GSM650513", "GSM650514", "GSM650515", "GSM650516", "GSM650517", "GSM650518", "GSM650519", "GSM650520", "GSM650521", "GSM650522", "GSM650523", "GSM650525", "GSM650526", "GSM650527", "GSM650528", "GSM650529", "GSM650530", "GSM650531", "GSM650532", "GSM650533", "GSM650534", "GSM650536", "GSM650537", "GSM650538", "GSM650540", "GSM650541", "GSM650542", "GSM650543", "GSM650544", "GSM650545", "GSM650546", "GSM650547", "GSM650548", "GSM650549", "GSM650550", "GSM650551", "GSM650552", "GSM650553", "GSM650554", "GSM650555", "GSM650556", "GSM650557", "GSM650558", "GSM650560", "GSM650561", "GSM650562", "GSM650563", "GSM650564", "GSM650565", "GSM650566", "GSM650567", "GSM650568", "GSM650569", "GSM650570", "GSM650571", "GSM650572", "GSM650573", "GSM650574", "GSM650575", "GSM650577", "GSM650578", "GSM650579", "GSM650580", "GSM650581", "GSM650600", "GSM650603", "GSM650604", "GSM650606", "GSM650607", "GSM650614", "GSM650615", "GSM650617", "GSM650618", "GSM650619", "GSM650620", "GSM650621", "GSM650622", "GSM650632", "GSM650633", "GSM650636", "GSM650637", "GSM650638", "GSM650639", "GSM650640", "GSM650641", "GSM650642", "GSM650643", "GSM650644", "GSM650645", "GSM650646", "GSM650647", "GSM650648", "GSM650649", "GSM650651", "GSM650652", "GSM650653", "GSM650654", "GSM650655", "GSM650656", "GSM650657", "GSM650658", "GSM650659", "GSM650660", "GSM650661", "GSM650662", "GSM650663", "GSM650664", "GSM650665", "GSM650666", "GSM650667", "GSM650668", "GSM650669", "GSM650670", "GSM650671", "GSM650672", "GSM650673", "GSM650674", "GSM650675", "GSM650676", "GSM650677", "GSM650678", "GSM650679", "GSM650680", "GSM650681", "GSM650682", "GSM650683", "GSM650684", "GSM650685", "GSM650686", "GSM650687", "GSM650688", "GSM650689", "GSM650690", "GSM650691", "GSM650692", "GSM650693", "GSM650694", "GSM650695", "GSM650696", "GSM650697", "GSM650698", "GSM650699", "GSM650700", "GSM650701", "GSM650702", "GSM650703", "GSM650704", "GSM650705", "GSM650706", "GSM650707", "GSM650708", "GSM650709", "GSM650712", "GSM650713", "GSM650714", "GSM650715", "GSM650716", "GSM650717", "GSM650718", "GSM650719", "GSM650720", "GSM650721", "GSM650722", "GSM650723", "GSM650724", "GSM650725", "GSM650726", "GSM650727", "GSM650728", "GSM650729", "GSM650730", "GSM650731", "GSM650732", "GSM650733", "GSM650734", "GSM650735", "GSM650737", "GSM650740", "GSM650744", "GSM650748", "GSM650750", "GSM650752", "GSM650753", "GSM650758", "GSM650760", "GSM650761", "GSM650762", "GSM650763", "GSM650764", "GSM650765", "GSM650766", "GSM650767", "GSM650768", "GSM650769", "GSM650770", "GSM650771", "GSM650772", "GSM650773", "GSM650801", "GSM650802", "GSM650806", "GSM650808", "GSM650809", "GSM650813", "GSM650816", "GSM650818", "GSM650819", "GSM650820", "GSM650821", "GSM650822", "GSM650823", "GSM650824", "GSM650825", "GSM650826", "GSM650827", "GSM650828", "GSM650829", "GSM650830", "GSM650831", "GSM650832", "GSM650833", "GSM650834", "GSM650835", "GSM650836", "GSM650837", "GSM650838", "GSM650839", "GSM650840", "GSM650841", "GSM650842", "GSM650843", "GSM650844", "GSM650845", "GSM650846", "GSM650847", "GSM650848", "GSM650849", "GSM650850", "GSM650851", "GSM650852", "GSM650853", "GSM650854", "GSM650855", "GSM650856", "GSM650857", "GSM650858", "GSM650859", "GSM650860", "GSM650861", "GSM650863", "GSM650864", "GSM650865", "GSM650866", "GSM650867", "GSM650868", "GSM650869", "GSM650870", "GSM650871", "GSM650872", "GSM650873", "GSM650874", "GSM650875", "GSM650876", "GSM650877", "GSM650878", "GSM650879", "GSM650880", "GSM650883", "GSM650885", "GSM650923", "GSM650924", "GSM650930", "GSM650931", "GSM650944", "GSM650946", "GSM650950", "GSM650951", "GSM650954", "GSM650959", "GSM650968", "GSM650969", "GSM650970", "GSM650975"], "sample_count": 285, "group_sizes": null, "group_sizes_basis": null, "platform": "6244;570", "taxon": "Homo sapiens", "title": "Blood gene expression signatures distinguish autism spectrum disorders from controls", "resolution_checked_at": "2026-11-01T17:30:42Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}], "gaps": ["asset:data:geo:GSE18123 not downloaded", "asset:data:geo:GSE18123 licence not read"]}, "analysis": {"state": "partial", "methods": [{"id": "method-1", "family": "genetic_association", "specific": "mendelian_randomisation", "label": "Genetic association (GWAS / linkage / MR)", "dsl_operations": ["mr_estimate"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["genotype_phenotype_table"], "evidence": {"score": 1.0, "band": "verbatim", "quote": "We employed Transcriptome-Wide Association Studies (TWAS) and Weighted Gene Co-expression Network Analysis (WGCNA) to pinpoint genes within ASD-associated susceptibility gene families (ARHGAP, MAP)."}}, {"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": "genetic_association", "specific": "gwas", "label": "Genetic association (GWAS / linkage / MR)", "dsl_operations": ["gwas_locus_scan"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["genotype_phenotype_table"], "evidence": {"score": 0.7, "band": "medium", "quote": "Genome-Wide Association Studies"}}], "targets": [{"id": "target-published-estimate", "claim_id": "claim-target-result", "operation": "build_graph", "expected_value": 95.0, "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."}, {"id": "target-published-estimate-p-value", "claim_id": "claim-target-result", "operation": "build_graph", "expected_value": 0.001, "unit": "p-value", "tolerance": null, "state": "complete", "note": "The threshold the paper applied to its own result, as the paper states it. A run that reproduces the effect is judged against this threshold."}], "gaps": ["method.reader_differs_from_extractor"]}, "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": ["mr_estimate"], "missing_operations": [], "basis": "The paper names the method it used and the corpus's method extractor maps it onto the DSL catalogue: mendelian_randomisation."}, "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": ["GSE18123"], "resolved_accessions": ["GSE18123"], "statements": ["The data that support the findings of this study are openly available in [CommonMindConsortium (CMC)]at [10.1038/nn.4399] The data that support the findings of this study are openly available in [GSE18123,]at [Gene Expression Omnibus (GEO)] The data that support the findings of this study are openly available in [ASD, the GWAS data comes from the meta-analysis GWAS]at [https://ww.med.unc.edu/pgc] The data that support the findings of this study are openly available in [GTExv8 eQTL]at [(https://www.gtexportal.org/home/]."], "basis": "The paper names GSE18123 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": ["mr_estimate"], "assets": ["source:pmid:39514479", "data:geo:GSE18123"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE18123"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-11-01T19:37:52Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 5, "usage": {"prompt_tokens": 11478, "completion_tokens": 1963, "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:39514479", "type": "paper", "label": "pmid:39514479"}, {"id": "source:pmid:39514479", "type": "manuscript", "label": "PMID 39514479 full text"}, {"id": "data:geo:GSE18123", "type": "dataset", "label": "GEO GSE18123"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:39514479", "type": "paper", "label": "pmid:39514479"}, {"id": "source:pmid:39514479", "type": "manuscript", "label": "PMID 39514479 full text"}, {"id": "data:geo:GSE18123", "type": "dataset", "label": "GEO GSE18123"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-39514479", "type": "extraction", "used": ["source:pmid:39514479"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE18123", "type": "accession_resolution", "used": ["data:geo:GSE18123"], "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:39514479", "parent_hash": "sha256:938c1628fbcd9ca4e8e87917b7be9d7742ef73829dcbd7386807c3ecf385f26e", "fork_of": null, "generation": 2}, "gaps": ["asset:data:geo:GSE18123 licence not read", "asset:data:geo:GSE18123 not downloaded", "execution.not_run", "method.reader_differs_from_extractor", "review.human_critique", "review.independent_reader", "review.machine_critique"], "assays": [{"role": "analysis", "definition_id": "genetic_association", "definition_version": "f2132e96ae6c7a4e", "definition_digest": null, "required_operations": ["mr_estimate"], "support_state": "supported", "source_hashes": {"dsl_catalogue": "f2132e96ae6c7a4e"}, "confidence": 1.0, "evidence": ["We employed Transcriptome-Wide Association Studies (TWAS) and Weighted Gene Co-expression Network Analysis (WGCNA) to pinpoint genes within ASD-associated susceptibility gene families (ARHGAP, MAP)."], "order_basis": "analysis_only", "id": "assay:1"}]}