{ "sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:35036081", "kind": "science-record", "revision": 4, "content_hash": "sha256:b4545d3eaa4aa14df345782945fc7657688816ba9e73ab1a866f2333d8fc7c55", "created_at": "2026-11-01T17:36:45Z", "updated_at": "2026-11-01T22:05:35Z", "generator": { "name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01" }, "paper": { "state": "complete", "title": "Key genes associated with prognosis and metastasis of clear cell renal cell carcinoma.", "doi": "10.7717/peerj.12493", "pmid": "35036081", "authors": [ "Tingting Zhong", "Zeying Jiang", "Xiangdong Wang", "Honglei Wang", "Meiyi Song", "Wenfang Chen", "Shicong Yang" ], "journal": "PeerJ", "year": 2022, "abstract": "BACKGROUND: Clear cell renal cell carcinoma (ccRCC) is a tumor that frequently shows the hematogenous pathway and tends to be resistant to radiotherapy and chemotherapy. However, the exact mechanism of ccRCC metastasis remains unknown.\nMETHODS: Differentially expressed genes (DEGs) of three gene expression profiles (GSE85258, GSE105288 and GSE22541) downloaded from the Gene Expression Omnibus (GEO) database were analyzed by GEO2R analysis, and co-expressed DEGs among the datasets were identified using a Venn drawing tool. The co-expressed DEGs were investigated using Gene Ontology and Kyoto Encyclopedia of Genes and Genomes pathway enrichment analysis, and hub genes were determined based on the protein-protein interaction network established by STRING. After survival analysis performed on UALCAN website, possible key genes were selected and verified in ccRCC cell lines and ccRCC tissues (n = 44). Statistical analysis was conducted using GraphPad Prism (Version 8.1.1).\nRESULTS: A total of 104 co-expressed DEGs were identified in the three datasets. Pathway analysis revealed that these genes were enriched in the extracellular matrix (ECM)-receptor interaction, protein digestion and absorption and focal adhesion. Survival analysis on 17 hub genes revealed that four key genes with a significant impact on survival: procollagen C-endopeptidase enhancer (PCOLCE), prolyl 4-hydroxylase subunit beta (P4HB), collagen type VI alpha 2 (COL6A2) and collagen type VI alpha 3 (COL6A3). Patients with higher expression of these key genes had worse survival than those with lower expression. In vitro experiments revealed that the mRNA expression levels of PCOLCE, P4HB and COL6A2 were three times higher and that of COL6A3 mRNA was 16 times higher in the metastatic ccRCC cell line Caki-1 than the corresponding primary cell line Caki-2. Immunohistochemistry revealed higher expression of the proteins encoded by these four genes in metastatic ccRCC compared with tumors from the corresponding primary sites, with statistical significance.\nCONCLUSION: PCOLCE, P4HB, COL6A2 and COL6A3 are upregulated in metastatic ccRCC and might be related to poor prognosis and distant metastases.", "claims": [ { "id": "claim-method", "statement": "GEO2R (http://www.ncbi.nlm.nih.gov/geo/geo2r), an interactive web tool for DEG analysis of GEO series across experimental conditions, was used to analyze the DEGs between primary ccRCC and metastatic ccRCC in the three datasets.", "kind": "methodological", "target": null, "evidence": [ { "asset": "source:pmid:35036081", "locator": "sections[4] \"Identification of DEGs\" paragraph 2", "quote": "GEO2R (http://www.ncbi.nlm.nih.gov/geo/geo2r), an interactive web tool for DEG analysis of GEO series across experimental conditions, was used to analyze the DEGs between primary ccRCC and metastatic ccRCC in the three datasets." } ], "state": "complete" }, { "id": "claim-data-access", "statement": "The raw measurements are available in the Supplementary File.", "kind": "methodological", "target": null, "evidence": [ { "asset": "source:pmid:35036081", "locator": "sections[24] \"Data Availability\" paragraph 2", "quote": "The raw measurements are available in the Supplementary File." } ], "state": "complete" }, { "id": "claim-target-result", "statement": "A total of 104 co-expressed DEGs were identified in the three datasets.", "kind": "qualitative", "target": null, "evidence": [ { "asset": "source:pmid:35036081", "locator": "sections[0] \"Abstract\" paragraph 3", "quote": "A total of 104 co-expressed DEGs were identified in the three datasets." } ], "state": "complete" } ], "gaps": [] }, "experiment": { "state": "complete", "objective": "A total of 104 co-expressed DEGs were identified in the three 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:35036081" ], "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:GSE105288" ], "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:GSE105288" ], "outputs": [ "the replicated result and its comparison" ], "instruments": [], "reagents": [] } ], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": [] }, "data": { "state": "partial", "assets": [ { "id": "source:pmid:35036081", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.7717/peerj.12493", "sha256": "sha256:0a054763c96ffc73b236f535e62b6a2ff33bd6b9e8a49ef9ddb979cb25dc798e", "bytes": 42182, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.7717/peerj.12493", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": { "pmcid": "PMC8740509", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body" } }, { "id": "data:geo:GSE105288", "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=GSE105288", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE105288", "version": null, "note": "The raw measurements are available in the Supplementary File.", "structure": { "repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The raw measurements are available in the Supplementary File.", "access_statement_kind": "data_availability_statement", "sample_accessions": [ "GSM2825195", "GSM2825196", "GSM2825197", "GSM2825198", "GSM2825199", "GSM2825200", "GSM2825201", "GSM2825202", "GSM2825203", "GSM2825204", "GSM2825205", "GSM2825206", "GSM2825207", "GSM2825208", "GSM2825209", "GSM2825210", "GSM2825211", "GSM2825212", "GSM2825213", "GSM2825214", "GSM2825215", "GSM2825216", "GSM2825217", "GSM2825218", "GSM2825219", "GSM2825220", "GSM2825221", "GSM2825222", "GSM2825223", "GSM2825224", "GSM2825225", "GSM2825226", "GSM2825227", "GSM2825228", "GSM2825229", "GSM2825230", "GSM2825231", "GSM2825232", "GSM2825233", "GSM2825234", "GSM2825235", "GSM2825236", "GSM2825237", "GSM2825238", "GSM2825239", "GSM2825240", "GSM2825241", "GSM2825242", "GSM2825243", "GSM2825244", "GSM2825245", "GSM2825246", "GSM2825247", "GSM2825248", "GSM2825249", "GSM2825250", "GSM2825251", "GSM2825252", "GSM2825253", "GSM2825254", "GSM2825255", "GSM2825256", "GSM2825257", "GSM2825258", "GSM2825259", "GSM2825260", "GSM2825261", "GSM2825262", "GSM2825263", "GSM2825264", "GSM2825265", "GSM2825266", "GSM2825267", "GSM2825268", "GSM2825269", "GSM2825270", "GSM2825271", "GSM2825272", "GSM2825273", "GSM2825274", "GSM2825275", "GSM2825276", "GSM2825277", "GSM2825278", "GSM2825279", "GSM2825280", "GSM2825281", "GSM2825282" ], "sample_count": 88, "group_sizes": null, "group_sizes_basis": null, "platform": "13534;10558", "taxon": "Homo sapiens", "title": "Integrative Epigenetic and Gene Expression Analysis of Renal Tumor Progression to Metastasis", "resolution_checked_at": "2026-11-01T17:30:42Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false } }, { "id": "data:geo:GSE22541", "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=GSE22541", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE22541", "version": null, "note": "The raw measurements are available in the Supplementary File.", "structure": { "repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The raw measurements are available in the Supplementary File.", "access_statement_kind": "data_availability_statement", "sample_accessions": [ "GSM359477", "GSM359478", "GSM359479", "GSM359480", "GSM359481", "GSM359482", "GSM359483", "GSM359484", "GSM359485", "GSM359486", "GSM359487", "GSM359488", "GSM359489", "GSM359490", "GSM359491", "GSM359492", "GSM359493", "GSM359494", "GSM359495", "GSM359496", "GSM559577", "GSM559578", "GSM559579", "GSM559580", "GSM559581", "GSM559582", "GSM559583", "GSM559584", "GSM559585", "GSM559586", "GSM559587", "GSM559588", "GSM559589", "GSM559590", "GSM559591", "GSM559592", "GSM559593", "GSM559594", "GSM559595", "GSM559596", "GSM559597", "GSM559598", "GSM559599", "GSM559600", "GSM559705", "GSM559706", "GSM559707", "GSM559708", "GSM559709", "GSM559710", "GSM559711", "GSM559712", "GSM559713", "GSM559714", "GSM559715", "GSM559716", "GSM559717", "GSM559718", "GSM559719", "GSM559720", "GSM559721", "GSM559722", "GSM559723", "GSM559724", "GSM559725", "GSM559726", "GSM559727", "GSM559728" ], "sample_count": 68, "group_sizes": null, "group_sizes_basis": null, "platform": "570", "taxon": "Homo sapiens", "title": "Expression data from pulmonary metastases and primary tumors of clear-cell renal cell carcinoma (ccRCC) with different disease-free survivals", "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:GSE85258", "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=GSE85258", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE85258", "version": null, "note": "The raw measurements are available in the Supplementary File.", "structure": { "repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The raw measurements are available in the Supplementary File.", "access_statement_kind": "data_availability_statement", "sample_accessions": [ "GSM2263272", "GSM2263273", "GSM2263274", "GSM2263275", "GSM2263276", "GSM2263277", "GSM2263278", "GSM2263279", "GSM2263280", "GSM2263281", "GSM2263282", "GSM2263283", "GSM2263284", "GSM2263285", "GSM2263286", "GSM2263287", "GSM2263288", "GSM2263289", "GSM2263290", "GSM2263291", "GSM2263292", "GSM2263293", "GSM2263294", "GSM2263295", "GSM2263296", "GSM2263297", "GSM2263298", "GSM2263299", "GSM2263300", "GSM2263301", "GSM2263302" ], "sample_count": 31, "group_sizes": null, "group_sizes_basis": null, "platform": "570", "taxon": "Homo sapiens", "title": "Differential gene expression profiling of matched primary renal cell carcinoma and metastases reveals upregulation of extracellular matrix genes", "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:GSE105288 not downloaded", "asset:data:geo:GSE105288 licence not read", "asset:data:geo:GSE22541 not downloaded", "asset:data:geo:GSE22541 licence not read", "asset:data:geo:GSE85258 not downloaded", "asset:data:geo:GSE85258 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": "protein-protein interaction" } }, { "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": "GEO2R differential-expression analysis", "dsl_operations": [], "missing_operations": [], "expressible": null, "parameters": {}, "data_shapes": [], "evidence": { "score": 1.0, "band": "verbatim", "quote": "GEO2R (http://www.ncbi.nlm.nih.gov/geo/geo2r), an interactive web tool for DEG analysis of GEO series across experimental conditions, was used to analyze the DEGs between primary ccRCC and metastatic ccRCC in the three datasets." } } ], "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": [ "GSE85258", "GSE105288", "GSE22541" ], "resolved_accessions": [ "GSE85258", "GSE105288", "GSE22541" ], "statements": [ "The raw measurements are available in the Supplementary File." ], "basis": "The paper names GSE85258, GSE105288, GSE22541 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:35036081", "data:geo:GSE105288" ], "steps": [ "run_analysis" ] }, "must_build": { "dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": [ "data:geo:GSE105288" ] }, "gaps": [] }, "review": { "state": "partial", "machine_critique": { "kind": "extraction_review", "reader": { "model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-11-01T17:15:43Z", "independence": "single_reader" }, "evidence_check": { "method": "verbatim", "availability": "verbatim" }, "calls": 5, "usage": { "prompt_tokens": 13370, "completion_tokens": 1990, "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:35036081", "type": "paper", "label": "pmid:35036081" }, { "id": "source:pmid:35036081", "type": "manuscript", "label": "PMID 35036081 full text" }, { "id": "data:geo:GSE105288", "type": "dataset", "label": "GEO GSE105288" } ], "activities": [ { "id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [ { "id": "pmid:35036081", "type": "paper", "label": "pmid:35036081" }, { "id": "source:pmid:35036081", "type": "manuscript", "label": "PMID 35036081 full text" }, { "id": "data:geo:GSE105288", "type": "dataset", "label": "GEO GSE105288" } ], "agent": "agent:corpus-assay-engine" }, { "id": "activity-read-35036081", "type": "extraction", "used": [ "source:pmid:35036081" ], "agent": "agent:minimax-reader" }, { "id": "activity-resolve-GSE105288", "type": "accession_resolution", "used": [ "data:geo:GSE105288" ], "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:35036081", "parent_hash": "sha256:6bb3ff5ff64d5dcf8d9c80ded63f2762f30c1738b20f1fcbd3e919baed447f45", "fork_of": null, "generation": 3 }, "gaps": [ "asset:data:geo:GSE105288 licence not read", "asset:data:geo:GSE105288 not downloaded", "asset:data:geo:GSE22541 licence not read", "asset:data:geo:GSE22541 not downloaded", "asset:data:geo:GSE85258 licence not read", "asset:data:geo:GSE85258 not downloaded", "execution.not_run", "method.reader_named_unmapped", "review.human_critique", "review.independent_reader", "review.machine_critique" ], "assays": [ { "role": "data_generation", "definition_id": "ihc", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": { "assay_lexicon": "99e1195c7d6f" }, "confidence": 0.99, "evidence": [ "the corresponding primary cell line Caki-2. Immunohistochemistry revealed higher expression of the proteins e", "zed with unpaired t-test, and the results of immunohistochemistry quantification were analyzed with paired t-t", "rmation 3Raw dataqRT-PCR & semi-quantitative immunohistochemistry results10.7717/peerj.12493/supp-3Click here" ], "order_basis": "paper_text_order:1888", "id": "assay:1" }, { "role": "data_generation", "definition_id": "cell_culture", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": { "assay_lexicon": "99e1195c7d6f" }, "confidence": 0.77, "evidence": [ "the BIOWING company in Shanghai. Cells were cultured in DMEM medium with 10% fetal bovine serum (FBS" ], "order_basis": "paper_text_order:2373", "id": "assay:2" }, { "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": [ "protein-protein interaction" ], "order_basis": "consumes_earlier_output", "id": "assay:3" } ] }