Identification of colorectal cancer-associated macrophage biomarkers by integrated bioinformatic analysis.

{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:33532018", "kind": "science-record", "revision": 4, "content_hash": "sha256:4b1702f53aec92ad2626420187d7443290a7f21abd2f919f9f2a4da9bd99a2cf", "created_at": "2026-11-01T17:34:40Z", "updated_at": "2026-11-01T22:03:02Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "partial", "title": "Identification of colorectal cancer-associated macrophage biomarkers by integrated bioinformatic analysis.", "doi": null, "pmid": "33532018", "authors": ["Dejun Cui", "Wenqiang Yuan", "Chen Chen", "Ran Han"], "journal": "International journal of clinical and experimental pathology", "year": 2021, "abstract": "The aim of this study was to explore colorectal tumor-associated macrophage (TAM) biomarkers for early diagnosis and surveillance of colorectal cancer (CRC). We used bioinformatic methods to screen array expression data of CRC-related macrophages (GEO: GSE29214) to detect the differentially expressed genes (DEGs) between CRC-related macrophages and normal control cells. We found 431 DEGs in TAMs compared with the control group; 399 were up-regulated and 32 were down-regulated. A functional enrichment analysis showed that the DEGs were involved in positive regulation of the ERK1 and ERK2 cascade, cell activation involved in the immune response, cytokine-mediated signaling pathway, and receptor activity, all of which were significantly enriched. We constructed a protein-protein interaction (PPI) network to identify hub genes. We identified 10 hub genes: ITGB2, ITGAM, C3AR1, PTAFR, C3, CYBB, FCER1G, PLAU, STOM, and GPR84, in the PPI network. We verified the results using array expression data of peripheral blood mononuclear cells (GEO: GSE47756). The results showed that the expression trends of CYBB, PLAU, and STOM were consistent with those found in the GSE29214 dataset. Further verification with The Cancer Genome Atlas and Human Protein Atlas showed that the high expression of PLAU in TAMs was statistically significant (P<0.05). We concluded that PLAU may be a biomarker of CRC-associated macrophages and may have prognostic and predictive significance for clinical utility in CRC management.", "claims": [{"id": "claim-method", "statement": "We used bioinformatic methods to screen array expression data of CRC-related macrophages (GEO: GSE29214) to detect the differentially expressed genes (DEGs) between CRC-related macrophages and normal control cells.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:33532018", "locator": "sections[0] \"Abstract\" paragraph 1", "quote": "We used bioinformatic methods to screen array expression data of CRC-related macrophages (GEO: GSE29214) to detect the differentially expressed genes (DEGs) between CRC-related macrophages and normal control cells."}], "state": "complete"}, {"id": "claim-data-access", "statement": "We used bioinformatic methods to screen array expression data of CRC-related macrophages (GEO: GSE29214) to detect the differentially expressed genes (DEGs) between CRC-related macrophages and normal control cells.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:33532018", "locator": "sections[0] \"Abstract\" paragraph 1", "quote": "We used bioinformatic methods to screen array expression data of CRC-related macrophages (GEO: GSE29214) to detect the differentially expressed genes (DEGs) between CRC-related macrophages and normal control cells."}], "state": "complete"}, {"id": "claim-target-result", "statement": "We found 431 DEGs in TAMs compared with the control group; 399 were up-regulated and 32 were down-regulated.", "kind": "qualitative", "target": null, "evidence": [{"asset": "source:pmid:33532018", "locator": "sections[0] \"Abstract\" paragraph 1", "quote": "We found 431 DEGs in TAMs compared with the control group; 399 were up-regulated and 32 were down-regulated."}], "state": "complete"}], "gaps": ["doi"]}, "experiment": {"state": "complete", "objective": "We found 431 DEGs in TAMs compared with the control group; 399 were up-regulated and 32 were down-regulated.", "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:33532018"], "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:GSE29214"], "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:GSE29214"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:33532018", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": null, "sha256": "sha256:2439c5cc4797935a81a4f88eae3500420fa5b73648cba804d61faef614fff22e", "bytes": 1526, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "33532018", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC7847498", "source": "ncbi_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE29214", "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=GSE29214", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE29214", "version": null, "note": "We used bioinformatic methods to screen array expression data of CRC-related macrophages (GEO: GSE29214) to detect the differentially expressed genes (DEGs) between CRC-related macrophages and normal control cells.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "We used bioinformatic methods to screen array expression data of CRC-related macrophages (GEO: GSE29214) to detect the differentially expressed genes (DEGs) between CRC-related macrophages and normal control cells.", "access_statement_kind": "repository_route_statement", "sample_accessions": ["GSM722555", "GSM722556", "GSM722557", "GSM722558", "GSM722559", "GSM722560", "GSM722561", "GSM722562", "GSM722563", "GSM722564"], "sample_count": 10, "group_sizes": null, "group_sizes_basis": null, "platform": "6104", "taxon": "Homo sapiens", "title": "Macrophages in Human Colorectal Cancer are Pro-inflammatory and Prime T Cells towards the Anti-Tumor Type-1 Inflammatory Response", "resolution_checked_at": "2026-11-01T17:30:42Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:GSE47756", "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=GSE47756", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE47756", "version": null, "note": "We used bioinformatic methods to screen array expression data of CRC-related macrophages (GEO: GSE29214) to detect the differentially expressed genes (DEGs) between CRC-related macrophages and normal control cells.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "We used bioinformatic methods to screen array expression data of CRC-related macrophages (GEO: GSE29214) to detect the differentially expressed genes (DEGs) between CRC-related macrophages and normal control cells.", "access_statement_kind": "repository_route_statement", "sample_accessions": ["GSM1156513", "GSM1156514", "GSM1156515", "GSM1156516", "GSM1156517", "GSM1156518", "GSM1156519", "GSM1156520", "GSM1156521", "GSM1156522", "GSM1156523", "GSM1156524", "GSM1156525", "GSM1156526", "GSM1156527", "GSM1156528", "GSM1156529", "GSM1156530", "GSM1156531", "GSM1156532", "GSM1156533", "GSM1156534", "GSM1156535", "GSM1156536", "GSM1156537", "GSM1156538", "GSM1156539", "GSM1156540", "GSM1156541", "GSM1156542", "GSM1156543", "GSM1156544", "GSM1156545", "GSM1156546", "GSM1156547", "GSM1156548", "GSM1156549", "GSM1156550", "GSM1156551", "GSM1156552", "GSM1156553", "GSM1156554", "GSM1156555", "GSM1156556", "GSM1156557", "GSM1156558", "GSM1156559", "GSM1156560", "GSM1156561", "GSM1156562", "GSM1156563", "GSM1156564", "GSM1156565", "GSM1156566", "GSM1156567", "GSM1156568", "GSM1156569", "GSM1156570", "GSM1156571", "GSM1156572", "GSM1156573", "GSM1156574", "GSM1156575", "GSM1156576", "GSM1156577", "GSM1156578", "GSM1156579", "GSM1156580", "GSM1156581", "GSM1156582", "GSM1156583", "GSM1156584", "GSM1156585", "GSM1156586", "GSM1156587", "GSM1156588", "GSM1156589", "GSM1156590", "GSM1156591", "GSM1156592", "GSM1156593", "GSM1156594", "GSM1156595", "GSM1156596", "GSM1156597", "GSM1156598", "GSM1156599", "GSM1156600", "GSM1156601", "GSM1156602", "GSM1156603", "GSM1156604", "GSM1156605"], "sample_count": 93, "group_sizes": null, "group_sizes_basis": null, "platform": "10558", "taxon": "Homo sapiens", "title": "Tumor-educated circulating monocytes are powerful specific biomarkers for diagnosis of colorectal cancer", "resolution_checked_at": "2026-11-01T17:30:42Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}], "gaps": ["asset:data:geo:GSE29214 not downloaded", "asset:data:geo:GSE29214 licence not read", "asset:data:geo:GSE47756 not downloaded", "asset:data:geo:GSE47756 licence not read"]}, "analysis": {"state": "partial", "methods": [{"id": "method-1", "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-2", "family": null, "specific": null, "label": "bioinformatic methods", "dsl_operations": [], "missing_operations": [], "expressible": null, "parameters": {}, "data_shapes": [], "evidence": {"score": 1.0, "band": "verbatim", "quote": "We used bioinformatic methods to screen array expression data of CRC-related macrophages (GEO: GSE29214) to detect the differentially expressed genes (DEGs) between CRC-related macrophages and normal control cells."}}], "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": "complete", "tier": "R1", "blocking_axis": "none", "blocked_on": "nothing:replicable_now", "axes": {"method": {"tier": "R1", "expressible": true, "required_operations": ["build_graph", "centrality_scores", "pathway_enrich"], "missing_operations": [], "basis": "The paper names the method it used and the corpus's method extractor maps it onto the DSL catalogue: ppi_network."}, "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": ["GSE29214", "GSE47756"], "resolved_accessions": ["GSE29214", "GSE47756"], "statements": ["We used bioinformatic methods to screen array expression data of CRC-related macrophages (GEO: GSE29214) to detect the differentially expressed genes (DEGs) between CRC-related macrophages and normal control cells."], "basis": "The paper names GSE29214, GSE47756 in GEO and the accession resolves in the repository. No dataset was downloaded and no licence was read."}}, "can_run": {"dsl_operations": ["build_graph", "centrality_scores", "pathway_enrich"], "assets": ["source:pmid:33532018", "data:geo:GSE29214"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE29214"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-11-01T17:01:35Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": null}, "calls": 5, "usage": {"prompt_tokens": 1959, "completion_tokens": 1535, "cached_tokens": 128}}, "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:33532018", "type": "paper", "label": "pmid:33532018"}, {"id": "source:pmid:33532018", "type": "manuscript", "label": "PMID 33532018 full text"}, {"id": "data:geo:GSE29214", "type": "dataset", "label": "GEO GSE29214"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:33532018", "type": "paper", "label": "pmid:33532018"}, {"id": "source:pmid:33532018", "type": "manuscript", "label": "PMID 33532018 full text"}, {"id": "data:geo:GSE29214", "type": "dataset", "label": "GEO GSE29214"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-33532018", "type": "extraction", "used": ["source:pmid:33532018"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE29214", "type": "accession_resolution", "used": ["data:geo:GSE29214"], "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:33532018", "parent_hash": "sha256:914a09b7fa07ba00e8b11c884253f90003af704210dea42c7fb0f6338d2d22a1", "fork_of": null, "generation": 3}, "gaps": ["asset:data:geo:GSE29214 licence not read", "asset:data:geo:GSE29214 not downloaded", "asset:data:geo:GSE47756 licence not read", "asset:data:geo:GSE47756 not downloaded", "doi", "execution.not_run", "method.reader_named_unmapped", "review.human_critique", "review.independent_reader", "review.machine_critique"], "assays": [{"role": "analysis", "definition_id": "network_analysis", "definition_version": "f2132e96ae6c7a4e", "definition_digest": null, "required_operations": ["build_graph", "centrality_scores", "pathway_enrich"], "support_state": "supported", "source_hashes": {"dsl_catalogue": "f2132e96ae6c7a4e"}, "confidence": 0.7, "evidence": ["protein-protein interaction"], "order_basis": "analysis_only", "id": "assay:1"}]}