Identification of key pathways and genes in colorectal cancer to predict the prognosis based on mRNA interaction network.

{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:31579079", "kind": "science-record", "revision": 7, "content_hash": "sha256:bc65094262d58b78f77758acac9e6075c2678caaf516e6742ebc9e090f72623e", "created_at": "2026-11-01T15:40:50Z", "updated_at": "2026-11-01T22:00:53Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Identification of key pathways and genes in colorectal cancer to predict the prognosis based on mRNA interaction network.", "doi": "10.3892/ol.2019.10698", "pmid": "31579079", "authors": ["Hengzhou Zhu", "Yi Ji", "Wenting Li", "Mianhua Wu"], "journal": "Oncology letters", "year": 2019, "abstract": "The aim of the present study was to identify key genes in colorectal cancer (CRC) that could be used to reliably diagnose this disease and to explore the potential underlying mechanisms in silico. The gene expression profiles of primary human cancer datasets GSE21510 and GSE32323 were downloaded from the Gene Expression Omnibus database. The limma R software package was used to identify differentially expressed (DE) genes. Gene Ontology and Kyoto Encyclopedia of Genes and Genomes (KEGG) pathway enrichment analyses were performed on DE genes using the Database for Annotation, Visualization and Integrated Discovery. The Search Tool for the Retrieval of Interacting Genes/Proteins database was used to construct a protein-protein interaction (PPI) network of the DE genes. Survival rate was analyzed and visualized using The Cancer Genome Atlas (TCGA). A total of 1,126 genes were significantly DE in the present study. All DE genes were enriched in KEGG pathways including 'cell cycle', 'mineral absorption', 'pancreatic secretion', 'pathways in cancer', 'metabolic pathways', 'aldosterone-regulated sodium reabsorption' and 'Wnt signaling pathway'. A total of 5 hub genes enriched in cell cycle and tumor-associated pathways, including E2F2, SKP2, MYC, CDKN1A and CDKN2B, were significantly DE and validated between tumor and normal tissues. CDKN1A and CDKN2B were identified within the PPI network using the Molecular Complex Detection algorithm. Survival and content distribution analyses of 362 clinical samples from TCGA revealed that CDKN1A effectively predicted the prognosis of patients. The present study identified key genes and potential signaling pathways involved in CRC. These findings may provide new insights for survival assessment during the clinical diagnosis of CRC.", "claims": [{"id": "claim-method", "statement": "The solid line represents the results of the Log-rank test analysis data.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:31579079", "locator": "sections[14] \"Survival analysis\" paragraph 3", "quote": "The solid line represents the results of the Log-rank test analysis data."}], "state": "complete"}, {"id": "claim-data-access", "statement": "The datasets used and/or analyzed during the current study are available from the corresponding author on reasonable request.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:31579079", "locator": "sections[18] \"Availability of data and materials\" paragraph 2", "quote": "The datasets used and/or analyzed during the current study are available from the corresponding author on reasonable request."}], "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:31579079"], "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:GSE21510"], "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:GSE21510"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:31579079", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.3892/ol.2019.10698", "sha256": "sha256:78c4ccd39dc46c9e8d9f233f71500eca30d6166354435d6612fe387db269eb48", "bytes": 30545, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.3892/ol.2019.10698", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC6757265", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE21510", "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=GSE21510", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE21510", "version": null, "note": "The datasets used and/or analyzed during the current study are available from the corresponding author on reasonable request.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The datasets used and/or analyzed during the current study are available from the corresponding author on reasonable request.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM537330", "GSM537331", "GSM537332", "GSM537333", "GSM537334", "GSM537335", "GSM537336", "GSM537337", "GSM537338", "GSM537339", "GSM537340", "GSM537341", "GSM537342", "GSM537343", "GSM537344", "GSM537345", "GSM537346", "GSM537347", "GSM537348", "GSM537349", "GSM537350", "GSM537351", "GSM537352", "GSM537353", "GSM537354", "GSM537355", "GSM537356", "GSM537357", "GSM537358", "GSM537359", "GSM537360", "GSM537361", "GSM537362", "GSM537363", "GSM537364", "GSM537365", "GSM537366", "GSM537367", "GSM537368", "GSM537369", "GSM537370", "GSM537371", "GSM537372", "GSM537373", "GSM537374", "GSM537375", "GSM537376", "GSM537377", "GSM537378", "GSM537379", "GSM537380", "GSM537381", "GSM537382", "GSM537383", "GSM537384", "GSM537385", "GSM537386", "GSM537387", "GSM537388", "GSM537389", "GSM537390", "GSM537391", "GSM537392", "GSM537393", "GSM537394", "GSM537395", "GSM537396", "GSM537397", "GSM537398", "GSM537399", "GSM537400", "GSM537401", "GSM537402", "GSM537403", "GSM537404", "GSM537405", "GSM537406", "GSM537407", "GSM537408", "GSM537409", "GSM537410", "GSM537411", "GSM537412", "GSM537413", "GSM537414", "GSM537415", "GSM537416", "GSM537417", "GSM537418", "GSM537419", "GSM537420", "GSM537421", "GSM537422", "GSM537423", "GSM537424", "GSM537425", "GSM537426", "GSM537427", "GSM537428", "GSM537429", "GSM537430", "GSM537431", "GSM537432", "GSM537433", "GSM549099", "GSM549100", "GSM549101", "GSM549102", "GSM549103", "GSM549104", "GSM549105", "GSM549106", "GSM549107", "GSM549108", "GSM549109", "GSM549110", "GSM549111", "GSM549112", "GSM549113", "GSM549114", "GSM549115", "GSM549116", "GSM549117", "GSM549118", "GSM549119", "GSM549120", "GSM549121", "GSM549122", "GSM549123", "GSM549124", "GSM549125", "GSM549126", "GSM549127", "GSM549128", "GSM549129", "GSM549130", "GSM549131", "GSM549132", "GSM549133", "GSM549134", "GSM549135", "GSM549136", "GSM549137", "GSM549138", "GSM549139", "GSM549140", "GSM549141", "GSM549142"], "sample_count": 148, "group_sizes": null, "group_sizes_basis": null, "platform": "570", "taxon": "Homo sapiens", "title": "Clinical Significance of Osteoprotegerin Expression in Human Colorectal Cancer", "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:GSE32323", "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=GSE32323", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE32323", "version": null, "note": "The datasets used and/or analyzed during the current study are available from the corresponding author on reasonable request.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The datasets used and/or analyzed during the current study are available from the corresponding author on reasonable request.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM800742", "GSM800743", "GSM800744", "GSM800745", "GSM800746", "GSM800747", "GSM800748", "GSM800749", "GSM800750", "GSM800751", "GSM800752", "GSM800753", "GSM800754", "GSM800755", "GSM800756", "GSM800757", "GSM800758", "GSM800759", "GSM800760", "GSM800761", "GSM800762", "GSM800763", "GSM800764", "GSM800765", "GSM800766", "GSM800767", "GSM800768", "GSM800769", "GSM800770", "GSM800771", "GSM800772", "GSM800773", "GSM800774", "GSM800775", "GSM800776", "GSM800777", "GSM800778", "GSM800779", "GSM800780", "GSM800781", "GSM800782", "GSM800783", "GSM800784", "GSM800785"], "sample_count": 44, "group_sizes": null, "group_sizes_basis": null, "platform": "570", "taxon": "Homo sapiens", "title": "Screening for Epigenetically Masked Genes in Colorectal Cancer using 5-aza-2’-deoxycytidine treatment, Microarray and Gene Expression Profile", "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:31579079:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:7c980b8f2be2dc23aefce037b86f4d7a457312b0cd72395da8996765740ac35c", "bytes": 2070, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[12]/table-wrap[1]#tI-ol-0-0-10698", "version": null, "note": "Functional and pathway enrichment analysis of the differentially expressed genes in colorectal cancer.", "structure": {"pmcid": "PMC6757265", "section_index": 12, "section_title": "KEGG pathway analysis of DE genes and construction of the PPI network", "row_count": 7, "column_count": 4}, "table": {"label": "Table I.", "caption": "Functional and pathway enrichment analysis of the differentially expressed genes in colorectal cancer.", "rows": [["Term", "Genes", "False discovery rate", "P-value"], ["hsa04110: Cell cycle", "CDK1, E2F2, E2F5, DBF4, RBL1, SKP2, PRKDC, TTK, CHEK1, ANAPC10, CHEK2, PTTG1, MCM4, MCM6, CCNB1, CDKN1A, CCNB2, MAD2L1, CDKN2B, PCNA, BUB1, BUB1B, ORC6, MYC, ORC3", "6.71×10−4", "5.10×10−7"], ["hsa04978: Mineral absorption", "SLC11A2, SLC26A3, CLCN2, MT1M, HMOX1, MT2A, MT1E, MT1H, MT1X, MT1G, MT1F", "0.57", "4.36×10−4"], ["hsa04972: Pancreatic secretion", "KCNMA1, CLCA1, CLCA4, SLC12A2, PRKCB, CEL, SLC26A3, PLCB4, ATP2A3, PLA2G2A, CPA3, CA2, SLC4A4, PLCB1, SLC9A1", "2.29", "1.76×10−3"], ["hsa05200: Pathways in cancer", "FGFR2, WNT5A, CKS1B, E2F2, PPARD, GNAI1, FGF9, GNA11, CXCL8, BDKRB1, ZBTB16, MMP1, EDNRA, WNT2, FOS, PLCB4, CDKN2B, AXIN2, PLCB1, TRAF5, MYC, MSH6, BMP2, COL4A1, EPAS1, MAP2K2, MSH2, MET, SKP2, LEF1, ITGA2, FZD3, PRKCB, FZD6, LAMA1, CDKN1A, LAMA3, MAPK3, CKS2, PDGFRA", "3.20", "2.47×10−3"], ["hsa01100: Metabolic pathways", "B3GALT5, B3GALT4, ADH1C, ADH1B, GPAT3, PRIM1, ASPA, PTGIS, ST3GAL4, CPOX, NANP, LPCAT2, GLCE, PLCE1, NME1, AKR1B10, PLA2G2A, ACAA1, PRPS1, XDH, GCNT3, AHCY, GCNT2, GNE, CTPS2, PPAT, B3GNT6, CDA, GCSH, DNMT3B, MAOA, AK1, MAOB, HGD, GART, TST, CEL, POLD4, GGT6, RPE, HMGCS2, MTR, AHCYL2, PC, ATP5D, CYP2C18, ANPEP, PSPH, CKB, ST6GALNAC6, TDO2, PLCB4, HPSE, P4HA1, MGLL, TWISTNB, PLCB1, ATP6V0D1, HYAL1, POLR1D, ACADS, DHRS9, POLR1C, POLR1B, ST6GALNAC1, ACADVL, ATP6V1C2, ADO, PTGDS, ADK, TGDS, AOC1, UGP2, ALPI, SORD, FUT8, HSD17B2, UGDH, UPP1, PIPOX, GLS2, DGKA, ALDH1A1, CKMT2, FUT3, FUT1, PLCD1, UGT2A3, ACSL4, PAPSS2, PLA2G16, NAT2, SI, PCK1, GBA3, GBA2, MBOAT1, SMPD1, PSAT1, PAICS", "3.87", "2.99×10−3"], ["hsa04310: Wnt signaling pathway", "WNT5A, PPARD, MMP7, LEF1, FZD3, PRKCB, FZD6, WNT2, GPC4, PLCB4, SFRP1, SFRP2, WIF1, RUVBL1, AXIN2, PLCB1, MYC", "14.59", "1.19×10−2"]], "row_count": 7, "column_count": 4, "numeric_cells": 23, "header_rows": 1, "locator": "section[12]/table-wrap[1]#tI-ol-0-0-10698"}}], "gaps": ["asset:data:geo:GSE21510 not downloaded", "asset:data:geo:GSE21510 licence not read", "asset:data:geo:GSE32323 not downloaded", "asset:data:geo:GSE32323 licence not read"]}, "analysis": {"state": "complete", "methods": [{"id": "method-1", "family": "survival_analysis", "specific": "log_rank_test", "label": "Survival analysis", "dsl_operations": ["logrank_test"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["time_to_event_with_censoring"], "evidence": {"score": 1.0, "band": "verbatim", "quote": "The solid line represents the results of the Log-rank test analysis data."}}, {"id": "method-2", "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": 0.7, "band": "medium", "quote": "limma"}}, {"id": "method-3", "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-4", "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"}}], "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": ["logrank_test"], "missing_operations": [], "basis": "The paper names the method it used and the corpus's method extractor maps it onto the DSL catalogue: log_rank_test."}, "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": ["GSE21510", "GSE32323"], "resolved_accessions": ["GSE21510", "GSE32323"], "statements": ["The datasets used and/or analyzed during the current study are available from the corresponding author on reasonable request."], "basis": "The paper names GSE21510, GSE32323 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": ["logrank_test"], "assets": ["source:pmid:31579079", "data:geo:GSE21510", "asset:table:pmid:31579079:1"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE21510"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-10-31T18:16:44Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 3, "usage": {"prompt_tokens": 26135, "completion_tokens": 2494, "cached_tokens": 8968}}, "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:31579079", "type": "paper", "label": "pmid:31579079"}, {"id": "source:pmid:31579079", "type": "manuscript", "label": "PMID 31579079 full text"}, {"id": "data:geo:GSE21510", "type": "dataset", "label": "GEO GSE21510"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:31579079", "type": "paper", "label": "pmid:31579079"}, {"id": "source:pmid:31579079", "type": "manuscript", "label": "PMID 31579079 full text"}, {"id": "data:geo:GSE21510", "type": "dataset", "label": "GEO GSE21510"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-31579079", "type": "extraction", "used": ["source:pmid:31579079"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE21510", "type": "accession_resolution", "used": ["data:geo:GSE21510"], "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:31579079", "parent_hash": "sha256:d0bee746f735afcf8f401a8c8e539a17c66026861733efa22a55d0c8f8845918", "fork_of": null, "generation": 6}, "gaps": ["asset:data:geo:GSE21510 licence not read", "asset:data:geo:GSE21510 not downloaded", "asset:data:geo:GSE32323 licence not read", "asset:data:geo:GSE32323 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": ["logrank_test"], "support_state": "supported", "source_hashes": {"dsl_catalogue": "f2132e96ae6c7a4e"}, "confidence": 1.0, "evidence": ["The solid line represents the results of the Log-rank test analysis data."], "order_basis": "analysis_only", "id": "assay:1"}]}