Identification of Hub Genes and Construction of a Transcriptional Regulatory Network Associated With Tumor Recurrence in Colorectal Cancer by Weighted Gene Co-expression Network Analysis.

{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:33897765", "kind": "science-record", "revision": 7, "content_hash": "sha256:fd3e1af7f3afcfde2d98b96e7714f9c31b91fbe94dc439d21f170ff0e9dccfc3", "created_at": "2026-11-01T15:41:33Z", "updated_at": "2026-11-01T22:03:38Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Identification of Hub Genes and Construction of a Transcriptional Regulatory Network Associated With Tumor Recurrence in Colorectal Cancer by Weighted Gene Co-expression Network Analysis.", "doi": "10.3389/fgene.2021.649752", "pmid": "33897765", "authors": ["Shengwei Liu", "Fanping Zeng", "Guangwen Fan", "Qiyong Dong"], "journal": "Frontiers in genetics", "year": 2021, "abstract": "Tumor recurrence is one of the most important risk factors that can negatively affect the survival rate of colorectal cancer (CRC) patients. However, the key regulators dictating this process and their exact mechanisms are understudied. This study aimed to construct a gene co-expression network to predict the hub genes affecting CRC recurrence and to inspect the regulatory network of hub genes and transcription factors (TFs). A total of 177 cases from the GSE17536 dataset were analyzed via weighted gene co-expression network analysis to explore the modules related to CRC recurrence. Functional annotation of the key module genes was assessed through Gene Ontology and Kyoto Encyclopedia of Genes and Genomes analyses. The protein and protein interaction network was then built to screen hub genes. Samples from the Cancer Genome Atlas (TCGA) were further used to validate the hub genes. Construction of a TFs-miRNAs-hub genes network was also conducted using StarBase and Cytoscape approaches. After identification and validation, a total of five genes (TIMP1, SPARCL1, MYL9, TPM2, and CNN1) were selected as hub genes. A regulatory network of TFs-miRNAs-targets with 29 TFs, 58 miRNAs, and five hub genes was instituted, including model GATA6-MIR106A-CNN1, SP4-MIR424-TPM2, SP4-MIR326-MYL9, ETS1-MIR22-TIMP1, and ETS1-MIR22-SPARCL1. In conclusion, the identification of these hub genes and the prediction of the Regulatory relationship of TFs-miRNAs-hub genes may provide a novel insight for understanding the underlying mechanism for CRC recurrence.", "claims": [{"id": "claim-method", "statement": "GS was calculated by linear regression between gene expression and CRC recurrence, and MS related to clinical CRC recurrence was obtained.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:33897765", "locator": "sections[5] \"Identification of Modules Associated With Clinical Features\" paragraph 2", "quote": "GS was calculated by linear regression between gene expression and CRC recurrence, and MS related to clinical CRC recurrence was obtained."}], "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/s.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:33897765", "locator": "sections[19] \"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/s."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "complete", "objective": null, "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:33897765"], "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:GSE17536"], "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:GSE17536"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:33897765", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.3389/fgene.2021.649752", "sha256": "sha256:92b66a7ff2efb223756dd3a336ecaad32c29f2e410f9aceb15a2300f7a82f03d", "bytes": 45684, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.3389/fgene.2021.649752", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC8058478", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE17536", "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=GSE17536", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE17536", "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/s.", "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/s.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM437093", "GSM437094", "GSM437095", "GSM437096", "GSM437097", "GSM437098", "GSM437099", "GSM437100", "GSM437101", "GSM437102", "GSM437103", "GSM437104", "GSM437105", "GSM437106", "GSM437107", "GSM437108", "GSM437109", "GSM437110", "GSM437111", "GSM437112", "GSM437113", "GSM437114", "GSM437115", "GSM437116", "GSM437117", "GSM437118", "GSM437119", "GSM437120", "GSM437121", "GSM437122", "GSM437123", "GSM437124", "GSM437125", "GSM437126", "GSM437127", "GSM437128", "GSM437129", "GSM437130", "GSM437131", "GSM437132", "GSM437133", "GSM437134", "GSM437135", "GSM437136", "GSM437137", "GSM437138", "GSM437139", "GSM437140", "GSM437141", "GSM437142", "GSM437143", "GSM437144", "GSM437145", "GSM437146", "GSM437147", "GSM437148", "GSM437149", "GSM437150", "GSM437151", "GSM437152", "GSM437153", "GSM437154", "GSM437155", "GSM437156", "GSM437157", "GSM437158", "GSM437159", "GSM437160", "GSM437161", "GSM437162", "GSM437163", "GSM437164", "GSM437165", "GSM437166", "GSM437167", "GSM437168", "GSM437169", "GSM437170", "GSM437171", "GSM437172", "GSM437173", "GSM437174", "GSM437175", "GSM437176", "GSM437177", "GSM437178", "GSM437179", "GSM437180", "GSM437181", "GSM437182", "GSM437183", "GSM437184", "GSM437185", "GSM437186", "GSM437187", "GSM437188", "GSM437189", "GSM437190", "GSM437191", "GSM437192", "GSM437193", "GSM437194", "GSM437195", "GSM437196", "GSM437197", "GSM437198", "GSM437199", "GSM437200", "GSM437201", "GSM437202", "GSM437203", "GSM437204", "GSM437205", "GSM437206", "GSM437207", "GSM437208", "GSM437209", "GSM437210", "GSM437211", "GSM437212", "GSM437213", "GSM437214", "GSM437215", "GSM437216", "GSM437217", "GSM437218", "GSM437219", "GSM437220", "GSM437221", "GSM437222", "GSM437223", "GSM437224", "GSM437225", "GSM437226", "GSM437227", "GSM437228", "GSM437229", "GSM437230", "GSM437231", "GSM437232", "GSM437233", "GSM437234", "GSM437235", "GSM437236", "GSM437237", "GSM437238", "GSM437239", "GSM437240", "GSM437241", "GSM437242", "GSM437243", "GSM437244", "GSM437245", "GSM437246", "GSM437247", "GSM437248", "GSM437249", "GSM437250", "GSM437251", "GSM437252", "GSM437253", "GSM437254", "GSM437255", "GSM437256", "GSM437257", "GSM437258", "GSM437259", "GSM437260", "GSM437261", "GSM437262", "GSM437263", "GSM437264", "GSM437265", "GSM437266", "GSM437267", "GSM437268", "GSM437269"], "sample_count": 177, "group_sizes": null, "group_sizes_basis": null, "platform": "570", "taxon": "Homo sapiens", "title": "Metastasis Gene Expression Profile Predicts Recurrence and Death in Colon Cancer Patients (Moffitt Samples)", "resolution_checked_at": "2026-11-01T15:39:54Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "asset:table:pmid:33897765:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:1debe9117fe4d4323c53a565efbc7c2949260f9afcb2b6460feca8ca319a4131", "bytes": 1635, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[16]/table-wrap[1]#T1", "version": null, "note": "Summary of top 10 regulatory biomolecules (TFs and miRNAs) of the five hub genes in CRC identified from TFs-miRNAs-hub genes interactions.", "structure": {"pmcid": "PMC8058478", "section_index": 16, "section_title": "Construction of TFs-miRNA–Hub Genes Network Associated With CRC Recurrence", "row_count": 24, "column_count": 5}, "table": {"label": "TABLE 1", "caption": "Summary of top 10 regulatory biomolecules (TFs and miRNAs) of the five hub genes in CRC identified from TFs-miRNAs-hub genes interactions.", "rows": [["Number", "Symbol", "Degree", "Feature", "References"], ["", "TFs", "", "", ""], ["1", "POLR2A", "14", "Afflicted with cancer", "Xu et al., 2019"], ["2", "SP4", "10", "Afflicted with CRC", "Meng et al., 2020"], ["3", "TEAD4", "10", "Afflicted with CRC", "Kim et al., 2020"], ["4", "HMGA1", "8", "Afflicted with CRC", "Yang et al., 2020"], ["5", "GATA6", "8", "Afflicted with CRC", "Lai et al., 2020"], ["6", "HSF1", "7", "Afflicted with CRC", "Song et al., 2020"], ["7", "NR3C1", "7", "Afflicted with CRC", "Sun et al., 2020"], ["8", "ATF1", "5", "Afflicted with CRC", "Zhao et al., 2020"], ["9", "PDLIM5", "5", "Afflicted with CRC", "Shi et al., 2020"], ["10", "ETS1", "5", "Afflicted with CRC", "Xu et al., 2020"], ["11", "TBP", "5", "Afflicted with CRC", "Wei et al., 2020"], ["", "miRNAs", "", "", ""], ["1", "MIR106A", "18", "Afflicted with CRC", "Liu et al., 2020"], ["2", "MIR424", "17", "Afflicted with CRC", "Di et al., 2020"], ["3", "MIR497", "16", "Afflicted with CRC", "Bai et al., 2020"], ["4", "MIR326", "16", "Afflicted with CRC", "Xian et al., 2020"], ["5", "MIR212", "15", "Afflicted with CRC", "Mou et al., 2019"], ["6", "MIR193A", "14", "Afflicted with CRC", "Hejazi et al., 2020"], ["7", "MIR214", "11", "Afflicted with CRC", "Liu et al., 2019"], ["8", "MIR22", "11", "Afflicted with CRC", "Cong et al., 2020"], ["9", "MIR193B", "10", "Afflicted with cancer", "Tian et al., 2020"], ["10", "MIR182", "6", "Afflicted with CRC", "Lin et al., 2020"]], "row_count": 24, "column_count": 5, "numeric_cells": 73, "header_rows": 1, "locator": "section[16]/table-wrap[1]#T1"}}], "gaps": ["asset:data:geo:GSE17536 not downloaded", "asset:data:geo:GSE17536 licence not read"]}, "analysis": {"state": "complete", "methods": [{"id": "method-1", "family": "regression_modelling", "specific": "ols", "label": "Regression modelling", "dsl_operations": ["ols_fit"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["predictors_and_outcome"], "evidence": {"score": 1.0, "band": "verbatim", "quote": "GS was calculated by linear regression between gene expression and CRC recurrence, and MS related to clinical CRC recurrence was obtained."}}, {"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": 0.8, "band": "high", "quote": "PPI"}}, {"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": "Pathway enrichment"}}], "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": ["ols_fit"], "missing_operations": [], "basis": "The paper names the method it used and the corpus's method extractor maps it onto the DSL catalogue: ols."}, "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": ["GSE17536"], "resolved_accessions": ["GSE17536"], "statements": ["The original contributions presented in the study are included in the article/Supplementary Material, further inquiries can be directed to the corresponding author/s."], "basis": "The paper names GSE17536 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": ["ols_fit"], "assets": ["source:pmid:33897765", "data:geo:GSE17536", "asset:table:pmid:33897765:1"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE17536"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-10-31T18:29:25Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 3, "usage": {"prompt_tokens": 36809, "completion_tokens": 1204, "cached_tokens": 784}}, "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:33897765", "type": "paper", "label": "pmid:33897765"}, {"id": "source:pmid:33897765", "type": "manuscript", "label": "PMID 33897765 full text"}, {"id": "data:geo:GSE17536", "type": "dataset", "label": "GEO GSE17536"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:33897765", "type": "paper", "label": "pmid:33897765"}, {"id": "source:pmid:33897765", "type": "manuscript", "label": "PMID 33897765 full text"}, {"id": "data:geo:GSE17536", "type": "dataset", "label": "GEO GSE17536"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-33897765", "type": "extraction", "used": ["source:pmid:33897765"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE17536", "type": "accession_resolution", "used": ["data:geo:GSE17536"], "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:33897765", "parent_hash": "sha256:c6b24e1a3c69751cc2cb996cf368744a8f7e199d6e0a0f51dfc53a75f13a225f", "fork_of": null, "generation": 6}, "gaps": ["asset:data:geo:GSE17536 licence not read", "asset:data:geo:GSE17536 not downloaded", "execution.not_run", "review.human_critique", "review.independent_reader", "review.machine_critique"], "assays": [{"role": "analysis", "definition_id": "regression_modelling", "definition_version": "f2132e96ae6c7a4e", "definition_digest": null, "required_operations": ["ols_fit"], "support_state": "supported", "source_hashes": {"dsl_catalogue": "f2132e96ae6c7a4e"}, "confidence": 1.0, "evidence": ["GS was calculated by linear regression between gene expression and CRC recurrence, and MS related to clinical CRC recurrence was obtained."], "order_basis": "analysis_only", "id": "assay:1"}]}