Construction of a CXC Chemokine-Based Prediction Model for the Prognosis of Colon Cancer.

{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:32337262", "kind": "science-record", "revision": 6, "content_hash": "sha256:8dec035f473ab56cf8ab1d591dd905fa5470ca2aa47e687c49f1ebca48fbe277", "created_at": "2026-11-01T15:41:00Z", "updated_at": "2026-11-01T21:23:10Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Construction of a CXC Chemokine-Based Prediction Model for the Prognosis of Colon Cancer.", "doi": "10.1155/2020/6107865", "pmid": "32337262", "authors": ["Kaisheng Liu", "Minshan Lai", "Shaoxiang Wang", "Kai Zheng", "Shouxia Xie", "Xiao Wang"], "journal": "BioMed research international", "year": 2020, "abstract": "Colon cancer is the third most common cancer, with a high incidence and mortality. Construction of a specific and sensitive prediction model for prognosis is urgently needed. In this study, profiles of patients with colon cancer with clinical and gene expression data were downloaded from Gene Expression Omnibus and The Cancer Genome Atlas (TCGA). CXC chemokines in patients with colon cancer were investigated by differential expression gene analysis, overall survival analysis, receiver operating characteristic analysis, gene set enrichment analysis (GSEA), and weighted gene coexpression network analysis. CXCL1, CXCL2, CXCL3, and CXCL11 were upregulated in patients with colon cancer and significantly correlated with prognosis. The area under curve (AUC) of the multigene forecast model of CXCL1, CXCL11, CXCL2, and CXCL3 was 0.705 in the GSE41258 dataset and 0.624 in TCGA. The prediction model was constructed using the risk score of the multigene model and three clinicopathological risk factors and exhibited 92.6% and 91.8% accuracy in predicting 3-year and 5-year overall survival of patients with colon cancer, respectively. In addition, by GSEA, expression of CXCL1, CXCL11, CXCL2, and CXCL3 was correlated with several signaling pathways, including NOD-like receptor, oxidative phosphorylation, mTORC1, interferon-gamma response, and IL6/JAK/STAT3 pathways. Patients with colon cancer will benefit from this prediction model for prognosis, and this will pave the way to improve the survival rate and optimize treatment for colon cancer.", "claims": [{"id": "claim-data-access", "statement": "The data used to support the findings of this study are available from the corresponding author upon request.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:32337262", "locator": "sections[18] \"Data Availability\" paragraph 2", "quote": "The data used to support the findings of this study are available from the corresponding author upon request."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "partial", "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:32337262"], "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": "blocked", "blocked_on": "data:accession_absent", "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": [], "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": [], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": ["step:obtain_source_data blocked on data:accession_absent"]}, "data": {"state": "partial", "assets": [{"id": "source:pmid:32337262", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1155/2020/6107865", "sha256": "sha256:9217c27d3f1afea2d2549fa435089a95f8ea74b1b6821b9b8b44252f399e268e", "bytes": 22354, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1155/2020/6107865", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC7150705", "source": "europe_pmc_fulltext", "coverage": "whole_body_without_references", "text_hash_scope": "rendered_section_body"}}], "gaps": []}, "analysis": {"state": "partial", "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": 0.8, "band": "high", "quote": "Kaplan-Meier"}}, {"id": "method-2", "family": "survival_analysis", "specific": "cox_proportional_hazards", "label": "Survival analysis", "dsl_operations": ["cox_ph"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["time_to_event_with_censoring"], "evidence": {"score": 0.8, "band": "high", "quote": "Cox regression"}}, {"id": "method-3", "family": "correlation_analysis", "specific": "pearson", "label": "Correlation analysis", "dsl_operations": ["pearson_r"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["paired_numeric_columns"], "evidence": {"score": 0.8, "band": "high", "quote": "Pearson's correlation"}}, {"id": "method-4", "family": null, "specific": null, "label": "Kaplan–Meier survival analysis, with survival data obtained from GEO and TCGA", "dsl_operations": [], "missing_operations": [], "expressible": null, "parameters": {}, "data_shapes": [], "evidence": {"score": 1.0, "band": "reordered", "quote": "“Survival analysis of patients in regard to the overlapping DEGs was conducted using the Kaplan-Meier method in R and based on the gene expression in tumor samples and overall survival of the patients.” “The survival data of all patients with tumor samples in GSE41258 and 428 of 456 patients with tumor samples in TCGA were included in the other analyses.”"}}], "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": "blocked", "tier": "R4", "blocking_axis": "data", "blocked_on": "data:accession_absent", "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": "R4", "reachable": false, "accessions": [], "resolved_accessions": [], "statements": ["The data used to support the findings of this study are available from the corresponding author upon request."], "basis": "The paper names no accession to its source data, so the data has to come from the authors."}}, "can_run": {"dsl_operations": ["survival_km"], "assets": ["source:pmid:32337262"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:None"]}, "gaps": ["data:accession_absent"]}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-10-31T19:01:09Z", "independence": "single_reader"}, "evidence_check": {"method": "reordered", "availability": "verbatim"}, "calls": 3, "usage": {"prompt_tokens": 18186, "completion_tokens": 1487, "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:32337262", "type": "paper", "label": "pmid:32337262"}, {"id": "source:pmid:32337262", "type": "manuscript", "label": "PMID 32337262 full text"}, {"id": "data:geo:None", "type": "dataset", "label": "GEO None"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:32337262", "type": "paper", "label": "pmid:32337262"}, {"id": "source:pmid:32337262", "type": "manuscript", "label": "PMID 32337262 full text"}, {"id": "data:geo:None", "type": "dataset", "label": "GEO None"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-32337262", "type": "extraction", "used": ["source:pmid:32337262"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-None", "type": "accession_resolution", "used": ["data:geo:None"], "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:32337262", "parent_hash": "sha256:7383a16eec59d8a9b3497518e0057d3820a77fb62580a211ed352f55ce5a06aa", "fork_of": null, "generation": 5}, "gaps": ["execution.not_run", "method.reader_named_unmapped", "review.human_critique", "review.independent_reader", "review.machine_critique", "step:obtain_source_data blocked on data:accession_absent"], "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": 0.8, "evidence": ["Kaplan-Meier"], "order_basis": "analysis_only", "id": "assay:1"}]}