Comprehensive analysis of core genes and key pathways in Parkinson's disease.

{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:33042444", "kind": "science-record", "revision": 3, "content_hash": "sha256:0ac0486087d9099a229b0c3f99cfc3eb7039f30672668934bf85125e41e1149d", "created_at": "2026-11-01T17:34:11Z", "updated_at": "2026-11-01T21:23:56Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "partial", "title": "Comprehensive analysis of core genes and key pathways in Parkinson's disease.", "doi": null, "pmid": "33042444", "authors": ["Qian Yuan", "Simiao Zhang", "Jingna Li", "Jianhao Xiao", "Xiaodong Li", "Jingmin Yang", "Daru Lu", "Yunliang Wang"], "journal": "American journal of translational research", "year": 2020, "abstract": "Parkinson's disease (PD) is a neurodegenerative disease that occurs mostly in middle-aged and older adults. Its main pathological feature is the progressive death of substantia nigra dopaminergic neurons. As the world's population ages, the number of PD patients is increasing. In this study, we explored the relationship between PD and the cell cycle. In this study, we collected two independent PD transcriptomic datasets, GSE54536 and GSE6613, from the Gene Expression Omnibus (GEO) database. Gene set enrichment analysis (GSEA) was used to identify dysregulated pathways in PD samples. Gene expression was verified by qPCR in PD patients. Nineteen pathways were negatively enriched in both the GSE54536 and GSE6613 datasets. Seven of these 19 pathways were cell cycle-related pathways, including the M/G1 transition, S phase, G1/S transition, mitotic G1-G1/S phases, CDT1 association with the CDC6 ORC origin complex, cell cycle checkpoints and synthesis of DNA. Next, we found that eight genes (PSMA4, PSMB1, PSMC5, PSMD11, MCM4, RPA1, POLE, and PSME4) were mainly enriched in the GSE54536 and GSE6613 datasets. In GSE54536, PSMA4, PSMB1, PSMC5, and PSME4 could significantly predict the occurrence of PD, whereas, in GSE6613, RPA1 and PSME4 could significantly predict the occurrence of PD. Only PSME4 showed significant results in both datasets. Finally, we assessed blood samples from PD patients and controls. Compared with the control samples, the PD samples had lower mRNA levels of PSME4. In summary,these findings can significantly enhance our understanding of the causes and potential molecular mechanisms of PD; the cell cycle signaling pathways and PSME4 may be therapeutic targets for PD.", "claims": [{"id": "claim-method", "statement": "Gene set enrichment analysis (GSEA) was used to identify dysregulated pathways in PD samples.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:33042444", "locator": "sections[0] \"Abstract\" paragraph 1", "quote": "Gene set enrichment analysis (GSEA) was used to identify dysregulated pathways in PD samples."}], "state": "complete"}, {"id": "claim-data-access", "statement": "In this study, we collected two independent PD transcriptomic datasets, GSE54536 and GSE6613, from the Gene Expression Omnibus (GEO) database.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:33042444", "locator": "sections[0] \"Abstract\" paragraph 1", "quote": "In this study, we collected two independent PD transcriptomic datasets, GSE54536 and GSE6613, from the Gene Expression Omnibus (GEO) database."}], "state": "complete"}, {"id": "claim-target-result", "statement": "Nineteen pathways were negatively enriched in both the GSE54536 and GSE6613 datasets.", "kind": "qualitative", "target": null, "evidence": [{"asset": "source:pmid:33042444", "locator": "sections[0] \"Abstract\" paragraph 1", "quote": "Nineteen pathways were negatively enriched in both the GSE54536 and GSE6613 datasets."}], "state": "complete"}], "gaps": ["doi"]}, "experiment": {"state": "complete", "objective": "Nineteen pathways were negatively enriched in both the GSE54536 and GSE6613 datasets.", "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:33042444"], "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:GSE54536"], "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:GSE54536"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:33042444", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": null, "sha256": "sha256:baa729a9207922c2018a902d7f6ecb7cc6b3b9e59e3baf7bcc9397e226370fd0", "bytes": 1718, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "33042444", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC7540129", "source": "ncbi_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE54536", "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=GSE54536", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE54536", "version": null, "note": "In this study, we collected two independent PD transcriptomic datasets, GSE54536 and GSE6613, from the Gene Expression Omnibus (GEO) database.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "In this study, we collected two independent PD transcriptomic datasets, GSE54536 and GSE6613, from the Gene Expression Omnibus (GEO) database.", "access_statement_kind": "repository_route_statement", "sample_accessions": ["GSM1318547", "GSM1318548", "GSM1318549", "GSM1318550", "GSM1318551", "GSM1318552", "GSM1318553", "GSM1318554", "GSM1318555", "GSM1318556"], "sample_count": 10, "group_sizes": null, "group_sizes_basis": null, "platform": "10558", "taxon": "Homo sapiens", "title": "Involvement of endocytosis and alternative splicing in the formation of the pathological process in Parkinson's Disease", "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:GSE6613", "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=GSE6613", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE6613", "version": null, "note": "In this study, we collected two independent PD transcriptomic datasets, GSE54536 and GSE6613, from the Gene Expression Omnibus (GEO) database.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "In this study, we collected two independent PD transcriptomic datasets, GSE54536 and GSE6613, from the Gene Expression Omnibus (GEO) database.", "access_statement_kind": "repository_route_statement", "sample_accessions": ["GSM153404", "GSM153405", "GSM153406", "GSM153407", "GSM153408", "GSM153409", "GSM153410", "GSM153411", "GSM153412", "GSM153413", "GSM153414", "GSM153415", "GSM153416", "GSM153417", "GSM153418", "GSM153419", "GSM153420", "GSM153421", "GSM153422", "GSM153423", "GSM153424", "GSM153425", "GSM153426", "GSM153427", "GSM153428", "GSM153429", "GSM153430", "GSM153431", "GSM153432", "GSM153433", "GSM153434", "GSM153435", "GSM153436", "GSM153437", "GSM153438", "GSM153439", "GSM153440", "GSM153441", "GSM153442", "GSM153443", "GSM153444", "GSM153445", "GSM153446", "GSM153447", "GSM153448", "GSM153449", "GSM153450", "GSM153451", "GSM153452", "GSM153453", "GSM153454", "GSM153455", "GSM153456", "GSM153457", "GSM153458", "GSM153459", "GSM153460", "GSM153461", "GSM153462", "GSM153463", "GSM153464", "GSM153465", "GSM153466", "GSM153467", "GSM153468", "GSM153469", "GSM153470", "GSM153471", "GSM153472", "GSM153473", "GSM153474", "GSM153475", "GSM153476", "GSM153477", "GSM153478", "GSM153479", "GSM153480", "GSM153481", "GSM153482", "GSM153483", "GSM153484", "GSM153485", "GSM153486", "GSM153487", "GSM153488", "GSM153489", "GSM153490", "GSM153491", "GSM153492", "GSM153493", "GSM153494", "GSM153495", "GSM153496", "GSM153497", "GSM153498", "GSM153499", "GSM153500", "GSM153501", "GSM153502", "GSM153503", "GSM153504", "GSM153505", "GSM153506", "GSM153507", "GSM153508"], "sample_count": 105, "group_sizes": null, "group_sizes_basis": null, "platform": "96", "taxon": "Homo sapiens", "title": "Parkinson's disease vs. controls, whole blood", "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:GSE54536 not downloaded", "asset:data:geo:GSE54536 licence not read", "asset:data:geo:GSE6613 not downloaded", "asset:data:geo:GSE6613 licence not read"]}, "analysis": {"state": "partial", "methods": [{"id": "method-1", "family": null, "specific": null, "label": "Gene set enrichment analysis (GSEA)", "dsl_operations": [], "missing_operations": [], "expressible": null, "parameters": {}, "data_shapes": [], "evidence": {"score": 1.0, "band": "verbatim", "quote": "Gene set enrichment analysis (GSEA) was used to identify dysregulated pathways in PD samples."}}], "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": "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 (Gene set enrichment analysis (GSEA)), 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": ["GSE54536", "GSE6613"], "resolved_accessions": ["GSE54536", "GSE6613"], "statements": ["In this study, we collected two independent PD transcriptomic datasets, GSE54536 and GSE6613, from the Gene Expression Omnibus (GEO) database."], "basis": "The paper names GSE54536, GSE6613 in Gene Expression Omnibus (GEO) database and the accession resolves in the repository. No dataset was downloaded and no licence was read."}}, "can_run": {"dsl_operations": [], "assets": ["source:pmid:33042444", "data:geo:GSE54536"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE54536"]}, "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": "2026-11-01T17:00:49Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": null}, "calls": 5, "usage": {"prompt_tokens": 2025, "completion_tokens": 815, "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:33042444", "type": "paper", "label": "pmid:33042444"}, {"id": "source:pmid:33042444", "type": "manuscript", "label": "PMID 33042444 full text"}, {"id": "data:geo:GSE54536", "type": "dataset", "label": "GEO GSE54536"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:33042444", "type": "paper", "label": "pmid:33042444"}, {"id": "source:pmid:33042444", "type": "manuscript", "label": "PMID 33042444 full text"}, {"id": "data:geo:GSE54536", "type": "dataset", "label": "GEO GSE54536"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-33042444", "type": "extraction", "used": ["source:pmid:33042444"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE54536", "type": "accession_resolution", "used": ["data:geo:GSE54536"], "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:33042444", "parent_hash": "sha256:fc863d1287b7691eb18224f4935876e5b115caf1b8a202ed893c88ec8f6ebe1c", "fork_of": null, "generation": 2}, "gaps": ["asset:data:geo:GSE54536 licence not read", "asset:data:geo:GSE54536 not downloaded", "asset:data:geo:GSE6613 licence not read", "asset:data:geo:GSE6613 not downloaded", "doi", "execution.not_run", "method.reader_named_unmapped", "review.human_critique", "review.independent_reader", "review.machine_critique"], "assays": [{"role": "data_generation", "definition_id": "qpcr", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.93, "evidence": ["PD samples. Gene expression was verified by qPCR in PD patients. Nineteen pathways were negat"], "order_basis": "paper_text_order:656", "id": "assay:1"}, {"role": "data_generation", "definition_id": "clinical_cohort", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.77, "evidence": ["sults in both datasets. Finally, we assessed blood samples from PD patients and controls. Compared with the"], "order_basis": "paper_text_order:1407", "id": "assay:2"}]}