LGALS1 was related to the prognosis of clear cell renal cell carcinoma identified by weighted correlation gene network analysis combined with differential gene expression analysis.

{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:36712844", "kind": "science-record", "revision": 3, "content_hash": "sha256:8f0de16fd522ab40b1498684d5968e11edbbca1751d0f8cebd8a3d86f64a25df", "created_at": "2026-11-01T19:01:16Z", "updated_at": "2026-11-01T22:08:39Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "LGALS1 was related to the prognosis of clear cell renal cell carcinoma identified by weighted correlation gene network analysis combined with differential gene expression analysis.", "doi": "10.3389/fgene.2022.1046164", "pmid": "36712844", "authors": ["Jiang Fang", "Xinjun Wang", "Jun Xie", "Xi Zhang", "Yiming Xiao", "JinKun Li", "Guangcheng Luo"], "journal": "Frontiers in genetics", "year": 2022, "abstract": "Understanding the molecular mechanism of clear cell renal cell carcinoma (ccRCC) is essential for predicting the prognosis and developing new targeted therapies. Our study is to identify hub genes related to ccRCC and to further analyze its prognostic significance. The ccRCC gene expression profiles of GSE46699 from the Gene Expression Omnibus (GEO) database and datasets from the Cancer Genome Atlas Database The Cancer Genome Atlas were used for the Weighted Gene Co-expression Network Analysis (WGCNA) and differential gene expression analysis. We screened out 397 overlapping genes from the four sets of results, and then performed Gene Ontology (GO) enrichment analysis and Kyoto Encyclopedia of Genes and Genome (KEGG) pathways. In addition, the protein-protein interaction (PPI) network of 397 overlapping genes was mapped using the STRING database. We identified ten hub genes (KNG1, TIMP1, ALB, C3, GPC3, VCAN, P4HB, CHGB, LGALS1, EGF) using the CytoHubba plugin of Cytoscape based on the Maximal Clique Centrality (MCC) score. According to Kaplan-Meier survival analysis, higher expression of LGALS1 and TIMP1 was related to poorer overall survival (OS) in patients with ccRCC. Univariate and multivariate Cox proportional hazard analysis showed that the expression of LGALS1 was an independent risk factor for poor prognosis. Moreover, the higher the clinical grade and stage of ccRCC, the higher the expression of LGALS1. LGALS1 may play an important role in developing ccRCC and may be potential a biomarker for prognosis and treatment targets.", "claims": [{"id": "claim-method", "statement": "To validate whether the survival of ccRCC patients was affected by hub genes, the data obtained from the TCGA, including the clinical data and gene expression data of 530 ccRCC samples, were used to seek the relationship between hub genes and Overall survival (OS) in patients by Kaplan-Meier univariate survival analysis with the survival R package in R software.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:36712844", "locator": "sections[10] \"Verification of hub genes with survival analysis\" paragraph 2", "quote": "To validate whether the survival of ccRCC patients was affected by hub genes, the data obtained from the TCGA, including the clinical data and gene expression data of 530 ccRCC samples, were used to seek the relationship between hub genes and Overall survival (OS) in patients by Kaplan-Meier univariate survival analysis with the survival R package in R software."}], "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:36712844", "locator": "sections[23] \"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": "Weighted gene co-expression analysis and differential gene expression analysis of GEO and TCGA data identified LGALS1 as a potential prognostic biomarker and therapeutic target in ccRCC.", "kind": "qualitative", "target": null, "evidence": [{"asset": "source:pmid:36712844", "locator": "sections[0] \"Abstract\" paragraph 1", "quote": "The ccRCC gene expression profiles of GSE46699 from the Gene Expression Omnibus (GEO) database and datasets from the Cancer Genome Atlas Database The Cancer Genome Atlas were used for the Weighted Gene Co-expression Network Analysis (WGCNA) and differential gene expression analysis."}, {"asset": "source:pmid:36712844", "locator": "sections[0] \"Abstract\" paragraph 1", "quote": "Univariate and multivariate Cox proportional hazard analysis showed that the expression of LGALS1 was an independent risk factor for poor prognosis."}, {"asset": "source:pmid:36712844", "locator": "sections[0] \"Abstract\" paragraph 1", "quote": "LGALS1 may play an important role in developing ccRCC and may be potential a biomarker for prognosis and treatment targets."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "complete", "objective": "Weighted gene co-expression analysis and differential gene expression analysis of GEO and TCGA data identified LGALS1 as a potential prognostic biomarker and therapeutic target in ccRCC.", "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:36712844"], "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:GSE46699"], "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:GSE46699"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:36712844", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.3389/fgene.2022.1046164", "sha256": "sha256:5e0bb38d01e962f2838b445c4717a70ead163c0c401f26a02864d3e045660271", "bytes": 43853, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.3389/fgene.2022.1046164", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC9878452", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE46699", "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=GSE46699", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE46699", "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": ["GSM1134764", "GSM1134765", "GSM1134766", "GSM1134767", "GSM1134768", "GSM1134769", "GSM1134770", "GSM1134771", "GSM1134772", "GSM1134773", "GSM1134774", "GSM1134775", "GSM1134776", "GSM1134777", "GSM1134778", "GSM1134779", "GSM1134780", "GSM1134781", "GSM1134782", "GSM1134783", "GSM1134784", "GSM1134785", "GSM1134786", "GSM1134787", "GSM1134788", "GSM1134789", "GSM1134790", "GSM1134791", "GSM1134792", "GSM1134793", "GSM1134794", "GSM1134795", "GSM1134796", "GSM1134797", "GSM1134798", "GSM1134799", "GSM1134800", "GSM1134801", "GSM1134802", "GSM1134803", "GSM1134804", "GSM1134805", "GSM1134806", "GSM1134807", "GSM1134808", "GSM1134809", "GSM1134810", "GSM1134811", "GSM1134812", "GSM1134813", "GSM1134814", "GSM1134815", "GSM1134816", "GSM1134817", "GSM1134818", "GSM1134819", "GSM1134820", "GSM1134821", "GSM1134822", "GSM1134823", "GSM1134824", "GSM1134825", "GSM1134826", "GSM1134827", "GSM1134828", "GSM1134829", "GSM1134830", "GSM1134831", "GSM1134832", "GSM1134833", "GSM1134834", "GSM1134835", "GSM1134836", "GSM1134837", "GSM1134838", "GSM1134839", "GSM1134840", "GSM1134841", "GSM1134842", "GSM1134843", "GSM1134844", "GSM1134845", "GSM1134846", "GSM1134847", "GSM1134848", "GSM1134849", "GSM1134850", "GSM1134851", "GSM1134852", "GSM1134853", "GSM1134854", "GSM1134855", "GSM1134856", "GSM1134857", "GSM1134858", "GSM1134859", "GSM1134860", "GSM1134861", "GSM1134862", "GSM1134863", "GSM1134864", "GSM1134865", "GSM1134866", "GSM1134867", "GSM1134868", "GSM1134869", "GSM1134870", "GSM1134871", "GSM1134872", "GSM1134873", "GSM1134874", "GSM1134875", "GSM1134876", "GSM1134877", "GSM1134878", "GSM1134879", "GSM1134880", "GSM1134881", "GSM1134882", "GSM1134883", "GSM1134884", "GSM1134885", "GSM1134886", "GSM1134887", "GSM1134888", "GSM1134889", "GSM1304420", "GSM1304421", "GSM1304422", "GSM1304423"], "sample_count": 130, "group_sizes": null, "group_sizes_basis": null, "platform": "570", "taxon": "Homo sapiens", "title": "Smoking and Obesity Related Molecular Alterations in Clear Cell Renal Cell Carcinoma", "resolution_checked_at": "2026-11-01T15:39:54Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}], "gaps": ["asset:data:geo:GSE46699 not downloaded", "asset:data:geo:GSE46699 licence not read"]}, "analysis": {"state": "complete", "methods": [{"id": "method-1", "family": "survival_analysis", "specific": "kaplan_meier", "label": "Survival analysis", "dsl_operations": ["survival_km"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["time_to_event_with_censoring"], "evidence": {"score": 1.0, "band": "verbatim", "quote": "To validate whether the survival of ccRCC patients was affected by hub genes, the data obtained from the TCGA, including the clinical data and gene expression data of 530 ccRCC samples, were used to seek the relationship between hub genes and Overall survival (OS) in patients by Kaplan-Meier univariate survival analysis with the survival R package in R software."}}, {"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": "network_analysis", "specific": "pathway_enrichment", "label": "Network / pathway analysis", "dsl_operations": ["pathway_enrich"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["edge_list"], "evidence": {"score": 0.8, "band": "high", "quote": "GO enrichment"}}, {"id": "method-4", "family": "network_analysis", "specific": "centrality", "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": "Centrality"}}], "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": ["survival_km"], "missing_operations": [], "basis": "The paper names the method it used and the corpus's method extractor maps it onto the DSL catalogue: kaplan_meier."}, "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": ["GSE46699"], "resolved_accessions": ["GSE46699"], "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 GSE46699 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": ["survival_km"], "assets": ["source:pmid:36712844", "data:geo:GSE46699"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE46699"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-11-01T18:24:56Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 5, "usage": {"prompt_tokens": 13498, "completion_tokens": 1511, "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:36712844", "type": "paper", "label": "pmid:36712844"}, {"id": "source:pmid:36712844", "type": "manuscript", "label": "PMID 36712844 full text"}, {"id": "data:geo:GSE46699", "type": "dataset", "label": "GEO GSE46699"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:36712844", "type": "paper", "label": "pmid:36712844"}, {"id": "source:pmid:36712844", "type": "manuscript", "label": "PMID 36712844 full text"}, {"id": "data:geo:GSE46699", "type": "dataset", "label": "GEO GSE46699"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-36712844", "type": "extraction", "used": ["source:pmid:36712844"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE46699", "type": "accession_resolution", "used": ["data:geo:GSE46699"], "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:36712844", "parent_hash": "sha256:0c5279bff72151bf1e0d40df28665ca6763039faf1d28a3b925cd1b780bfa19f", "fork_of": null, "generation": 2}, "gaps": ["asset:data:geo:GSE46699 licence not read", "asset:data:geo:GSE46699 not downloaded", "execution.not_run", "review.human_critique", "review.independent_reader", "review.machine_critique"], "assays": [{"role": "analysis", "definition_id": "survival_analysis", "definition_version": "f2132e96ae6c7a4e", "definition_digest": null, "required_operations": ["survival_km"], "support_state": "supported", "source_hashes": {"dsl_catalogue": "f2132e96ae6c7a4e"}, "confidence": 1.0, "evidence": ["To validate whether the survival of ccRCC patients was affected by hub genes, the data obtained from the TCGA, including the clinical data and gene expression data of 530 ccRCC samples, were used to seek the relationship between hub genes and Overall survival (OS) in patients by Kaplan-Meier univariate survival analysis with the survival R package in R software."], "order_basis": "analysis_only", "id": "assay:1"}]}