Identification of hub genes of Parkinson's disease through bioinformatics analysis.

{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:36440267", "kind": "science-record", "revision": 4, "content_hash": "sha256:eff2615b26a4549b2316f754e543ef731e2bca9c5d32e0523ceeb93824eadbf3", "created_at": "2026-11-01T19:00:55Z", "updated_at": "2026-11-01T22:50:42Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Identification of hub genes of Parkinson's disease through bioinformatics analysis.", "doi": "10.3389/fnins.2022.974838", "pmid": "36440267", "authors": ["Yajun Yang", "Yi Wang", "Ce Wang", "Xinjuan Xu", "Cai Liu", "Xintao Huang"], "journal": "Frontiers in neuroscience", "year": 2022, "abstract": "Parkinson's disease (PD) is a common neurodegenerative disease, and there is still a lack of effective diagnostic and treatment methods. This study aimed to search for hub genes that might serve as diagnostic or therapeutic targets for PD. All the analysis was performed in R software. The expression profile data of PD (number: GSE7621) was acquired from the Gene Expression Omnibus (GEO) database. Differentially expressed genes (DEGs) associated with PD were screened by the \"Limma\" package of the R software. Key genes associated with PD were screened by the \"WGCNA\" package of the R software. Target genes were screened by merging the results of \"Limma\" and \"WGCNA.\" Enrichment analysis of target genes was performed by Gene Ontology (GO), Disease Ontology (DO), and Kyoto Enrichment of Genes and Genomes (KEGG). Machine learning algorithms were employed to screen for hub genes. Nomogram was constructed using the \"rms\" package. And the receiver operating characteristic curve (ROC) was plotted to detect and validate our prediction model sensitivity and specificity. Additional expression profile data of PD (number: GSE20141) was acquired from the GEO database to validate the nomogram. GSEA was used to determine the biological functions of the hub genes. Finally, RPL3L, PLEK2, PYCRL, CD99P1, LOC100133130, MELK, LINC01101, and DLG3-AS1 were identified as hub genes of PD. These findings can provide a new direction for the diagnosis and treatment of PD.", "claims": [{"id": "claim-method", "statement": "The “Limma” R package was used to screen DEGs between PD and normal samples, and genes with P < 0.05 and |log2FC| >1 were regarded as DEGs (Liu et al., 2021).", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:36440267", "locator": "sections[4] \"Identification of DEGs in the substantia nigra of patients with PD\" paragraph 2", "quote": "The “Limma” R package was used to screen DEGs between PD and normal samples, and genes with P < 0.05 and |log2FC| >1 were regarded as DEGs (Liu et al., 2021)."}], "state": "complete"}, {"id": "claim-data-access", "statement": "The original contributions presented in the study are included in the article/supplementary material, further inquiries can be directed to the corresponding author.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:36440267", "locator": "sections[21] \"Data availability statement\" paragraph 2", "quote": "The original contributions presented in the study are included in the article/supplementary material, further inquiries can be directed to the corresponding author."}], "state": "complete"}, {"id": "claim-target-result", "statement": "Using Limma differential-expression screening, WGCNA, and machine-learning analyses of GEO expression data, the study identified eight PD hub genes and developed a diagnostic nomogram with AUC values of 1.000 in GSE7621 and 0.900 in GSE20141.", "kind": "qualitative", "target": null, "evidence": [{"asset": "source:pmid:36440267", "locator": "sections[15] \"Identification of hub genes of PD based on machine learning algorithms\" paragraph 2", "quote": "Finally, eight common potential genes, namely, RPL3L, PLEK2, PYCRL, CD99P1, LOC100133130, MELK, LINC01101, and DLG3-AS1, were regarded as the hub genes of PD patients using the above three algorithms (Figure 4D)."}, {"asset": "source:pmid:36440267", "locator": "sections[16] \"Establishment of diagnostic nomogram for PD\" paragraph 2", "quote": "The area under the curve (AUC) of the GSE7621 dataset was 1.000 (Figure 5B), and that of the GSE20141 dataset was 0.900 (Figure 5C)."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "complete", "objective": "Using Limma differential-expression screening, WGCNA, and machine-learning analyses of GEO expression data, the study identified eight PD hub genes and developed a diagnostic nomogram with AUC values of 1.000 in GSE7621 and 0.900 in GSE20141.", "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:36440267"], "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:GSE20141"], "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:GSE20141"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:36440267", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.3389/fnins.2022.974838", "sha256": "sha256:2b3012ff1564dc5cc2b27dad912d69d1d1259377932fa53364b931dcca2297cf", "bytes": 26869, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.3389/fnins.2022.974838", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC9683342", "source": "europe_pmc_fulltext", "coverage": "whole_body_without_references", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE20141", "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=GSE20141", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE20141", "version": null, "note": "The original contributions presented in the study are included in the article/supplementary material, further inquiries can be directed to the corresponding author.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The original contributions presented in the study are included in the article/supplementary material, further inquiries can be directed to the corresponding author.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM503950", "GSM503951", "GSM503952", "GSM503953", "GSM503954", "GSM503955", "GSM503956", "GSM503957", "GSM503958", "GSM503959", "GSM503960", "GSM503961", "GSM503962", "GSM503963", "GSM503964", "GSM503965", "GSM503966", "GSM503967"], "sample_count": 18, "group_sizes": null, "group_sizes_basis": null, "platform": "570", "taxon": "Homo sapiens", "title": "Expression analysis of laser-dissected SNpc neurons in Parkinson's disease", "resolution_checked_at": "2026-11-01T18:46:34Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:GSE7621", "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=GSE7621", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE7621", "version": null, "note": "The original contributions presented in the study are included in the article/supplementary material, further inquiries can be directed to the corresponding author.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The original contributions presented in the study are included in the article/supplementary material, further inquiries can be directed to the corresponding author.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM184354", "GSM184355", "GSM184356", "GSM184357", "GSM184358", "GSM184359", "GSM184360", "GSM184361", "GSM184362", "GSM184363", "GSM184364", "GSM184365", "GSM184366", "GSM184367", "GSM184368", "GSM184369", "GSM184370", "GSM184371", "GSM184372", "GSM184373", "GSM184374", "GSM184375", "GSM184376", "GSM184377", "GSM184378"], "sample_count": 25, "group_sizes": null, "group_sizes_basis": null, "platform": "570", "taxon": "Homo sapiens", "title": "Expression data of substantia nigra from postmortem human brain of Parkinson's disease patients (PD)", "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:GSE20141 not downloaded", "asset:data:geo:GSE20141 licence not read", "asset:data:geo:GSE7621 not downloaded", "asset:data:geo:GSE7621 licence not read"]}, "analysis": {"state": "complete", "methods": [{"id": "method-1", "family": "differential_expression", "specific": "limma_voom", "label": "Differential expression analysis", "dsl_operations": ["normalise_counts", "differential_expression_fit", "fdr_bh"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["count_matrix_with_condition"], "evidence": {"score": 1.0, "band": "verbatim", "quote": "The “Limma” R package was used to screen DEGs between PD and normal samples, and genes with P < 0.05 and |log2FC| >1 were regarded as DEGs (Liu et al., 2021)."}}], "targets": [], "gaps": []}, "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": ["normalise_counts", "differential_expression_fit", "fdr_bh"], "missing_operations": [], "basis": "The paper names the method it used and the corpus's method extractor maps it onto the DSL catalogue: limma_voom."}, "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": ["GSE7621", "GSE20141"], "resolved_accessions": ["GSE7621", "GSE20141"], "statements": ["The original contributions presented in the study are included in the article/supplementary material, further inquiries can be directed to the corresponding author."], "basis": "The paper names GSE7621, GSE20141 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": ["normalise_counts", "differential_expression_fit", "fdr_bh"], "assets": ["source:pmid:36440267", "data:geo:GSE20141"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE20141"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-11-01T18:17:17Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 5, "usage": {"prompt_tokens": 8647, "completion_tokens": 1536, "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:36440267", "type": "paper", "label": "pmid:36440267"}, {"id": "source:pmid:36440267", "type": "manuscript", "label": "PMID 36440267 full text"}, {"id": "data:geo:GSE20141", "type": "dataset", "label": "GEO GSE20141"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:36440267", "type": "paper", "label": "pmid:36440267"}, {"id": "source:pmid:36440267", "type": "manuscript", "label": "PMID 36440267 full text"}, {"id": "data:geo:GSE20141", "type": "dataset", "label": "GEO GSE20141"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-36440267", "type": "extraction", "used": ["source:pmid:36440267"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE20141", "type": "accession_resolution", "used": ["data:geo:GSE20141"], "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:36440267", "parent_hash": "sha256:5136e21f759015c19bb0d4feec5dca62bd3db0214b64dce76e04e44aefeab244", "fork_of": null, "generation": 3}, "gaps": ["asset:data:geo:GSE20141 licence not read", "asset:data:geo:GSE20141 not downloaded", "asset:data:geo:GSE7621 licence not read", "asset:data:geo:GSE7621 not downloaded", "execution.not_run", "review.human_critique", "review.independent_reader", "review.machine_critique"], "assays": [{"role": "analysis", "definition_id": "differential_expression", "definition_version": "f2132e96ae6c7a4e", "definition_digest": null, "required_operations": ["normalise_counts", "differential_expression_fit", "fdr_bh"], "support_state": "supported", "source_hashes": {"dsl_catalogue": "f2132e96ae6c7a4e"}, "confidence": 1.0, "evidence": ["The “Limma” R package was used to screen DEGs between PD and normal samples, and genes with P < 0.05 and |log2FC| >1 were regarded as DEGs (Liu et al., 2021)."], "order_basis": "analysis_only", "id": "assay:1"}]}