A Novel Seventeen-Gene Metabolic Signature for Predicting Prognosis in Colon Cancer.

{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:33282950", "kind": "science-record", "revision": 6, "content_hash": "sha256:403a790d7bf6210c1aece251a548d04a9a4ba547c76f49e529c6c157a3bda8df", "created_at": "2026-11-01T15:41:18Z", "updated_at": "2026-11-01T21:24:14Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "A Novel Seventeen-Gene Metabolic Signature for Predicting Prognosis in Colon Cancer.", "doi": "10.1155/2020/4845360", "pmid": "33282950", "authors": ["Dakui Luo", "Zezhi Shan", "Qi Liu", "Sanjun Cai", "Qingguo Li", "Xinxiang Li"], "journal": "BioMed research international", "year": 2020, "abstract": "A metabolic disorder is considered one of the hallmarks of cancer. Multiple differentially expressed metabolic genes have been identified in colon cancer (CC), and their biological functions and prognostic values have been well explored. The purpose of the present study was to establish a metabolic signature to optimize the prognostic prediction in CC. The related data were downloaded from The Cancer Genome Atlas (TCGA), Genotype-Tissue Expression (GTEx) database, and Gene Expression Omnibus (GEO) combined with GSE39582 set, GSE17538 set, GSE33113 set, and GSE37892 set. The differentially expressed metabolic genes were selected for univariate Cox regression and lasso Cox regression analysis using TCGA and GTEx datasets. Finally, a seventeen-gene metabolic signature was developed to divide patients into a high-risk group and a low-risk group. Patients in the high-risk group presented poorer prognosis compared to the low-risk group in both TCGA and GEO datasets. Moreover, gene set enrichment analyses demonstrated multiple significantly enriched metabolism-related pathways. To sum up, our study described a novel seventeen-gene metabolic signature for prognostic prediction of colon cancer.", "claims": [{"id": "claim-method", "statement": "Survival differences were evaluated using the Kaplan–Meier estimate with the log-rank test.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:33282950", "locator": "sections[8] \"2.6. Statistical Analysis\" paragraph 2", "quote": "Survival differences were evaluated using the Kaplan–Meier estimate with the log-rank test."}], "state": "complete"}, {"id": "claim-data-access", "statement": "The datasets included in our current study are available in Genotype-tissue expression (GTEx) (https://www.gtexportal.org/home/index.html), TCGA-COAD (https://portal.gdc.cancer.gov), GSE39582 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE39582), GSE17538 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE17538), GSE33113 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE33113), and GSE37892 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE37892).", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:33282950", "locator": "sections[18] \"Data Availability\" paragraph 2", "quote": "The datasets included in our current study are available in Genotype-tissue expression (GTEx) (https://www.gtexportal.org/home/index.html), TCGA-COAD (https://portal.gdc.cancer.gov), GSE39582 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE39582), GSE17538 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE17538), GSE33113 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE33113), and GSE37892 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE37892)."}], "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:33282950"], "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:33282950", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1155/2020/4845360", "sha256": "sha256:f8ce71bbf6d689d28dadaf45fcc82d6d23e073261cd7fd7906131c697432a719", "bytes": 20653, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1155/2020/4845360", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC7685801", "source": "europe_pmc_fulltext", "coverage": "whole_body_without_references", "text_hash_scope": "rendered_section_body"}}], "gaps": []}, "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": "Survival differences were evaluated using the Kaplan–Meier estimate with the log-rank test."}}, {"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": 0.7, "band": "medium", "quote": "Cox regression"}}], "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": "blocked", "tier": "R4", "blocking_axis": "data", "blocked_on": "data:accession_absent", "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": "R4", "reachable": false, "accessions": [], "resolved_accessions": [], "statements": ["The datasets included in our current study are available in Genotype-tissue expression (GTEx) (https://www.gtexportal.org/home/index.html), TCGA-COAD (https://portal.gdc.cancer.gov), GSE39582 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE39582), GSE17538 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE17538), GSE33113 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE33113), and GSE37892 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE37892)."], "basis": "The paper names no accession to its source data, so the data has to come from the authors."}}, "can_run": {"dsl_operations": ["logrank_test"], "assets": ["source:pmid:33282950"], "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": "2026-10-31T19:17:53Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 3, "usage": {"prompt_tokens": 16199, "completion_tokens": 2186, "cached_tokens": 5384}}, "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:33282950", "type": "paper", "label": "pmid:33282950"}, {"id": "source:pmid:33282950", "type": "manuscript", "label": "PMID 33282950 full text"}, {"id": "data:geo:None", "type": "dataset", "label": "GEO None"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:33282950", "type": "paper", "label": "pmid:33282950"}, {"id": "source:pmid:33282950", "type": "manuscript", "label": "PMID 33282950 full text"}, {"id": "data:geo:None", "type": "dataset", "label": "GEO None"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-33282950", "type": "extraction", "used": ["source:pmid:33282950"], "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:33282950", "parent_hash": "sha256:e1b4d29af1d4e81f10d3a20866a2a76a92ef7556c72f037c69e3537e19972ae7", "fork_of": null, "generation": 5}, "gaps": ["execution.not_run", "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": ["logrank_test"], "support_state": "supported", "source_hashes": {"dsl_catalogue": "f2132e96ae6c7a4e"}, "confidence": 1.0, "evidence": ["Survival differences were evaluated using the Kaplan–Meier estimate with the log-rank test."], "order_basis": "analysis_only", "id": "assay:1"}]}