Screening of non-alcoholic steatohepatitis (NASH)-related datasets and identification of NASH-related genes.

{"sci_version": "1.0", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:34093943", "kind": "science-record", "revision": 2, "content_hash": "sha256:d08838051ece9591a699ce1bbab13e7d74a4a82af8cdab7bb4399b74a2977528", "created_at": "2026-11-01T17:35:24Z", "updated_at": "2026-11-01T18:55:40Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "partial", "title": "Screening of non-alcoholic steatohepatitis (NASH)-related datasets and identification of NASH-related genes.", "doi": null, "pmid": "34093943", "authors": ["Ming-Jiang Liu", "Hu Jin", "Yu-Bing Chen", "Jing-Jing Yu", "Zhen-Ya Guo", "Song-Qing He", "Yong-Lian Zeng"], "journal": "International journal of clinical and experimental pathology", "year": 2021, "abstract": "Non-alcoholic steatohepatitis (NASH) is a common liver disease in the western world. The mechanisms behind NASH formation are poorly understood, but there may be multiple targets considering the disease's multifactorial nature. To explore the genes related to the pathogenesis of NASH, we downloaded clinical data and gene expression of NASH patients from the Gene Expression Omnibus database (GEO). We identified 281 genes with a common expression in two NASH-related datasets (GSE89632 and GSE83452), suggesting that they may be related to NASH. Further study showed that Angptl4, Foxo1, and Ttc39B might be essential for NASH progression, and these have been poorly studied. Therefore, we explored their roles in NASH. Our data show that these genes participate in the development of NASH through lipid metabolism. This suggests that the three genes can be used as therapeutic targets in NASH.", "claims": [{"id": "claim-data-access", "statement": "To explore the genes related to the pathogenesis of NASH, we downloaded clinical data and gene expression of NASH patients from the Gene Expression Omnibus database (GEO).", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:34093943", "locator": "sections[0] \"Abstract\" paragraph 1", "quote": "To explore the genes related to the pathogenesis of NASH, we downloaded clinical data and gene expression of NASH patients from the Gene Expression Omnibus database (GEO)."}], "state": "complete"}, {"id": "claim-target-result", "statement": "We identified 281 genes with a common expression in two NASH-related datasets (GSE89632 and GSE83452), suggesting that they may be related to NASH.", "kind": "qualitative", "target": null, "evidence": [{"asset": "source:pmid:34093943", "locator": "sections[0] \"Abstract\" paragraph 1", "quote": "We identified 281 genes with a common expression in two NASH-related datasets (GSE89632 and GSE83452), suggesting that they may be related to NASH."}], "state": "complete"}], "gaps": ["doi"]}, "experiment": {"state": "complete", "objective": "We identified 281 genes with a common expression in two NASH-related datasets (GSE89632 and GSE83452), suggesting that they may be related to NASH.", "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:34093943"], "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:GSE83452"], "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:GSE83452"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:34093943", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": null, "sha256": "sha256:9114dd920fee0f3f7992ddbc4bf5a30c04510d895d3d17aa336ae35ae8a0aefa", "bytes": 909, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "34093943", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC8167495", "source": "ncbi_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE83452", "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=GSE83452", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE83452", "version": null, "note": "To explore the genes related to the pathogenesis of NASH, we downloaded clinical data and gene expression of NASH patients from the Gene Expression Omnibus database (GEO).", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "To explore the genes related to the pathogenesis of NASH, we downloaded clinical data and gene expression of NASH patients from the Gene Expression Omnibus database (GEO).", "access_statement_kind": "repository_route_statement", "sample_accessions": ["GSM2203254", "GSM2203255", "GSM2203256", "GSM2203257", "GSM2203258", "GSM2203259", "GSM2203260", "GSM2203261", "GSM2203262", "GSM2203263", "GSM2203264", "GSM2203265", "GSM2203266", "GSM2203267", "GSM2203268", "GSM2203269", "GSM2203270", "GSM2203271", "GSM2203272", "GSM2203273", "GSM2203274", "GSM2203275", "GSM2203276", "GSM2203277", "GSM2203278", "GSM2203279", "GSM2203280", "GSM2203281", "GSM2203282", "GSM2203283", "GSM2203284", "GSM2203285", "GSM2203286", "GSM2203287", "GSM2203288", "GSM2203289", "GSM2203290", "GSM2203291", "GSM2203292", "GSM2203293", "GSM2203294", "GSM2203295", "GSM2203296", "GSM2203297", "GSM2203298", "GSM2203299", "GSM2203300", "GSM2203301", "GSM2203302", "GSM2203303", "GSM2203304", "GSM2203305", "GSM2203306", "GSM2203307", "GSM2203308", "GSM2203309", "GSM2203310", "GSM2203311", "GSM2203312", "GSM2203313", "GSM2203314", "GSM2203315", "GSM2203316", "GSM2203317", "GSM2203318", "GSM2203319", "GSM2203320", "GSM2203321", "GSM2203322", "GSM2203323", "GSM2203324", "GSM2203325", "GSM2203326", "GSM2203327", "GSM2203328", "GSM2203329", "GSM2203330", "GSM2203331", "GSM2203332", "GSM2203333", "GSM2203334", "GSM2203335", "GSM2203336", "GSM2203337", "GSM2203338", "GSM2203339", "GSM2203340", "GSM2203341", "GSM2203342", "GSM2203343", "GSM2203344", "GSM2203345", "GSM2203346", "GSM2203347", "GSM2203348", "GSM2203349", "GSM2203350", "GSM2203351", "GSM2203352", "GSM2203353", "GSM2203354", "GSM2203355", "GSM2203356", "GSM2203357", "GSM2203358", "GSM2203359", "GSM2203360", "GSM2203361", "GSM2203362", "GSM2203363", "GSM2203364", "GSM2203365", "GSM2203366", "GSM2203367", "GSM2203368", "GSM2203369", "GSM2203370", "GSM2203371", "GSM2203372", "GSM2203373", "GSM2203374", "GSM2203375", "GSM2203376", "GSM2203377", "GSM2203378", "GSM2203379", "GSM2203380", "GSM2203381", "GSM2203382", "GSM2203383", "GSM2203384", "GSM2203385", "GSM2203386", "GSM2203387", "GSM2203388", "GSM2203389", "GSM2203390", "GSM2203391", "GSM2203392", "GSM2203393", "GSM2203394", "GSM2203395", "GSM2203396", "GSM2203397", "GSM2203398", "GSM2203399", "GSM2203400", "GSM2203401", "GSM2203402", "GSM2203403", "GSM2203404", "GSM2203405", "GSM2203406", "GSM2203407", "GSM2203408", "GSM2203409", "GSM2203410", "GSM2203411", "GSM2203412", "GSM2203413", "GSM2203414", "GSM2203415", "GSM2203416", "GSM2203417", "GSM2203418", "GSM2203419", "GSM2203420", "GSM2203421", "GSM2203422", "GSM2203423", "GSM2203424", "GSM2203425", "GSM2203426", "GSM2203427", "GSM2203428", "GSM2203429", "GSM2203430", "GSM2203431", "GSM2203432", "GSM2203433", "GSM2203434", "GSM2203435", "GSM2203436", "GSM2203437", "GSM2203438", "GSM2203439", "GSM2203440", "GSM2203441", "GSM2203442", "GSM2203443", "GSM2203444", "GSM2203445", "GSM2203446", "GSM2203447", "GSM2203448", "GSM2203449", "GSM2203450", "GSM2203451", "GSM2203452", "GSM2203453", "GSM2203454", "GSM2203455", "GSM2203456", "GSM2203457", "GSM2203458", "GSM2203459", "GSM2203460", "GSM2203461", "GSM2203462", "GSM2203463", "GSM2203464", "GSM2203465", "GSM2203466", "GSM2203467", "GSM2203468", "GSM2203469", "GSM2203470", "GSM2203471", "GSM2203472", "GSM2203473", "GSM2203474", "GSM2203475", "GSM2203476", "GSM2203477", "GSM2203478", "GSM2203479", "GSM2203480", "GSM2203481", "GSM2203482", "GSM2203483", "GSM2203484"], "sample_count": 231, "group_sizes": null, "group_sizes_basis": null, "platform": "16686", "taxon": "Homo sapiens", "title": "Expression data from liver of obese patients", "resolution_checked_at": "2026-11-01T15:39:55Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:GSE89632", "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=GSE89632", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE89632", "version": null, "note": "To explore the genes related to the pathogenesis of NASH, we downloaded clinical data and gene expression of NASH patients from the Gene Expression Omnibus database (GEO).", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "To explore the genes related to the pathogenesis of NASH, we downloaded clinical data and gene expression of NASH patients from the Gene Expression Omnibus database (GEO).", "access_statement_kind": "repository_route_statement", "sample_accessions": ["GSM2385720", "GSM2385721", "GSM2385722", "GSM2385723", "GSM2385724", "GSM2385725", "GSM2385726", "GSM2385727", "GSM2385728", "GSM2385729", "GSM2385730", "GSM2385731", "GSM2385732", "GSM2385733", "GSM2385734", "GSM2385735", "GSM2385736", "GSM2385737", "GSM2385738", "GSM2385739", "GSM2385740", "GSM2385741", "GSM2385742", "GSM2385743", "GSM2385744", "GSM2385745", "GSM2385746", "GSM2385747", "GSM2385748", "GSM2385749", "GSM2385750", "GSM2385751", "GSM2385752", "GSM2385753", "GSM2385754", "GSM2385755", "GSM2385756", "GSM2385757", "GSM2385758", "GSM2385759", "GSM2385760", "GSM2385761", "GSM2385762", "GSM2385763", "GSM2385764", "GSM2385765", "GSM2385766", "GSM2385767", "GSM2385768", "GSM2385769", "GSM2385770", "GSM2385771", "GSM2385772", "GSM2385773", "GSM2385774", "GSM2385775", "GSM2385776", "GSM2385777", "GSM2385778", "GSM2385779", "GSM2385780", "GSM2385781", "GSM2385782"], "sample_count": 63, "group_sizes": null, "group_sizes_basis": null, "platform": "14951", "taxon": "Homo sapiens", "title": "Genome-wide analysis of hepatic gene expression in patients with non-alcoholic fatty liver disease  and in healthy donors in relation to hepatic fatty acid composition and other nutritional factors", "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:GSE83452 not downloaded", "asset:data:geo:GSE83452 licence not read", "asset:data:geo:GSE89632 not downloaded", "asset:data:geo:GSE89632 licence not read"]}, "analysis": {"state": "absent", "methods": [], "targets": [], "gaps": ["method", "operations"]}, "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": "blocked", "tier": "R4", "blocking_axis": "method", "blocked_on": "method:not_determinable", "axes": {"method": {"tier": "R4", "expressible": false, "required_operations": [], "missing_operations": [], "basis": "The reader quoted the method the paper names (not named), but the corpus's method extractor could not map it onto a DSL operation, so the method is published but not expressible."}, "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": ["GSE89632", "GSE83452"], "resolved_accessions": ["GSE89632", "GSE83452"], "statements": ["To explore the genes related to the pathogenesis of NASH, we downloaded clinical data and gene expression of NASH patients from the Gene Expression Omnibus database (GEO)."], "basis": "The paper names GSE89632, GSE83452 in Gene Expression Omnibus database (GEO) and the accession resolves in the repository. No dataset was downloaded and no licence was read."}}, "can_run": {"dsl_operations": [], "assets": ["source:pmid:34093943", "data:geo:GSE83452"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE83452"]}, "gaps": ["method:not_determinable"]}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-11-01T17:02:09Z", "independence": "single_reader"}, "evidence_check": {"method": null, "availability": null}, "calls": 5, "usage": {"prompt_tokens": 1831, "completion_tokens": 773, "cached_tokens": 188}}, "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:34093943", "type": "paper", "label": "pmid:34093943"}, {"id": "source:pmid:34093943", "type": "manuscript", "label": "PMID 34093943 full text"}, {"id": "data:geo:GSE83452", "type": "dataset", "label": "GEO GSE83452"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:34093943", "type": "paper", "label": "pmid:34093943"}, {"id": "source:pmid:34093943", "type": "manuscript", "label": "PMID 34093943 full text"}, {"id": "data:geo:GSE83452", "type": "dataset", "label": "GEO GSE83452"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-34093943", "type": "extraction", "used": ["source:pmid:34093943"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE83452", "type": "accession_resolution", "used": ["data:geo:GSE83452"], "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:34093943", "parent_hash": "sha256:89fd454bac22c9b5382ebb3e3287fe4e016775b306a88c8ef2ac686173c05d98", "fork_of": null, "generation": 1}, "gaps": ["asset:data:geo:GSE83452 licence not read", "asset:data:geo:GSE83452 not downloaded", "asset:data:geo:GSE89632 licence not read", "asset:data:geo:GSE89632 not downloaded", "doi", "execution.not_run", "method", "operations", "review.human_critique", "review.independent_reader", "review.machine_critique"]}