Identification and Verification of Core Genes in Colorectal Cancer.

{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:32462020", "kind": "science-record", "revision": 8, "content_hash": "sha256:4ec920969e64d6c0d777f6c9830ccd470a91683aecb6c5fb5f8c4f57ce8918f9", "created_at": "2026-11-01T15:41:02Z", "updated_at": "2026-11-01T22:44:54Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Identification and Verification of Core Genes in Colorectal Cancer.", "doi": "10.1155/2020/8082697", "pmid": "32462020", "authors": ["Houxi Xu", "Yuzhu Ma", "Jinzhi Zhang", "Jialin Gu", "Xinyue Jing", "Shengfeng Lu", "Shuping Fu", "Jiege Huo"], "journal": "BioMed research international", "year": 2020, "abstract": "Colorectal cancer, a malignant neoplasm that occurs in the colorectal mucosa, is one of the most common types of gastrointestinal cancer. Colorectal cancer has been studied extensively, but the molecular mechanisms of this malignancy have not been characterized. This study identified and verified core genes associated with colorectal cancer using integrated bioinformatics analysis. Three gene expression profiles (GSE15781, GSE110223, and GSE110224) were downloaded from the Gene Expression Omnibus (GEO) databases. A total of 87 common differentially expressed genes (DEGs) among GSE15781, GSE110223, and GSE110224 were identified, including 19 upregulated genes and 68 downregulated genes. Gene ontology and Kyoto Encyclopedia of Genes and Genomes pathway enrichment analysis was performed for common DEGs using clusterProfiler. These common DEGs were significantly involved in cancer-associated functions and signaling pathways. Then, we constructed protein-protein interaction networks of these common DEGs using Cytoscape software, which resulted in the identification of the following 10 core genes: SST, PYY, CXCL1, CXCL8, CXCL3, ZG16, AQP8, CLCA4, MS4A12, and GUCA2A. Analysis using qRT-PCR has shown that SST, CXCL8, and MS4A12 were significant differentially expressed between colorectal cancer tissues and normal colorectal tissues (P < 0.05). Gene Expression Profiling Interactive Analysis (GEPIA) overall survival (OS) has shown that low expressions of AQP8, ZG16, CXCL3, and CXCL8 may predict poor survival outcome in colorectal cancer. In conclusion, the core genes identified in this study contributed to the understanding of the molecular mechanisms involved in colorectal cancer development and may be targets for early diagnosis, prevention, and treatment of colorectal cancer.", "claims": [{"id": "claim-method", "statement": "Analysis of DEGs was performed using the limma package of R software [14].", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:32462020", "locator": "sections[4] \"2.2. Identification of Common DEGs in Colorectal Cancer\" paragraph 2", "quote": "Analysis of DEGs was performed using the limma package of R software [14]."}], "state": "complete"}, {"id": "claim-data-access", "statement": "GSE15781, GSE110223, and GSE110224 can be downloaded from the GEO database. URL of the GEO database: https://www.ncbi.nlm.nih.gov/geo/.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:32462020", "locator": "sections[17] \"Data Availability\" paragraph 2", "quote": "GSE15781, GSE110223, and GSE110224 can be downloaded from the GEO database. URL of the GEO database: https://www.ncbi.nlm.nih.gov/geo/."}], "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:32462020"], "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:GSE110223"], "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:GSE110223"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:32462020", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1155/2020/8082697", "sha256": "sha256:694e27e24a1970662da163695c7dc106cb2391bd0d127a4c77d6c34ea244538a", "bytes": 32637, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1155/2020/8082697", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC7232680", "source": "europe_pmc_fulltext", "coverage": "whole_body_without_references", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE110223", "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=GSE110223", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE110223", "version": null, "note": "GSE15781, GSE110223, and GSE110224 can be downloaded from the GEO database. URL of the GEO database: https://www.ncbi.nlm.nih.gov/geo/.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "GSE15781, GSE110223, and GSE110224 can be downloaded from the GEO database. URL of the GEO database: https://www.ncbi.nlm.nih.gov/geo/.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM2982906", "GSM2982907", "GSM2982908", "GSM2982909", "GSM2982910", "GSM2982911", "GSM2982912", "GSM2982913", "GSM2982914", "GSM2982915", "GSM2982916", "GSM2982917", "GSM2982918", "GSM2982919", "GSM2982920", "GSM2982921", "GSM2982922", "GSM2982923", "GSM2982924", "GSM2982925", "GSM2982926", "GSM2982927", "GSM2982928", "GSM2982929", "GSM2982930", "GSM2982931"], "sample_count": 26, "group_sizes": null, "group_sizes_basis": null, "platform": "96", "taxon": "Homo sapiens", "title": "Expression data from 13 patients with 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:GSE110224", "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=GSE110224", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE110224", "version": null, "note": "GSE15781, GSE110223, and GSE110224 can be downloaded from the GEO database. URL of the GEO database: https://www.ncbi.nlm.nih.gov/geo/.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "GSE15781, GSE110223, and GSE110224 can be downloaded from the GEO database. URL of the GEO database: https://www.ncbi.nlm.nih.gov/geo/.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM2982932", "GSM2982933", "GSM2982934", "GSM2982935", "GSM2982936", "GSM2982937", "GSM2982938", "GSM2982939", "GSM2982940", "GSM2982941", "GSM2982942", "GSM2982943", "GSM2982944", "GSM2982945", "GSM2982946", "GSM2982947", "GSM2982948", "GSM2982949", "GSM2982950", "GSM2982951", "GSM2982952", "GSM2982953", "GSM2982954", "GSM2982955", "GSM2982956", "GSM2982957", "GSM2982958", "GSM2982959", "GSM2982960", "GSM2982961", "GSM2982962", "GSM2982963", "GSM2982964", "GSM2982965"], "sample_count": 34, "group_sizes": null, "group_sizes_basis": null, "platform": "570", "taxon": "Homo sapiens", "title": "Expression data from 17 patients with 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:GSE15781", "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=GSE15781", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE15781", "version": null, "note": "GSE15781, GSE110223, and GSE110224 can be downloaded from the GEO database. URL of the GEO database: https://www.ncbi.nlm.nih.gov/geo/.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "GSE15781, GSE110223, and GSE110224 can be downloaded from the GEO database. URL of the GEO database: https://www.ncbi.nlm.nih.gov/geo/.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM396309", "GSM396310", "GSM396311", "GSM396312", "GSM396313", "GSM396314", "GSM396315", "GSM396316", "GSM396317", "GSM396318", "GSM396319", "GSM396320", "GSM396321", "GSM396322", "GSM396323", "GSM396324", "GSM396325", "GSM396326", "GSM396327", "GSM396328", "GSM396329", "GSM396330", "GSM396331", "GSM396332", "GSM396333", "GSM396334", "GSM396335", "GSM396336", "GSM396337", "GSM396338", "GSM396339", "GSM396340", "GSM396341", "GSM396342", "GSM396343", "GSM396344", "GSM396345", "GSM396346", "GSM396347", "GSM396348", "GSM396349", "GSM396350"], "sample_count": 42, "group_sizes": null, "group_sizes_basis": null, "platform": "2986", "taxon": "Homo sapiens", "title": "New specific molecular targets for radiochemotherapy in 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}}], "gaps": ["asset:data:geo:GSE110223 not downloaded", "asset:data:geo:GSE110223 licence not read", "asset:data:geo:GSE110224 not downloaded", "asset:data:geo:GSE110224 licence not read", "asset:data:geo:GSE15781 not downloaded", "asset:data:geo:GSE15781 licence not read"]}, "analysis": {"state": "complete", "methods": [{"id": "method-1", "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": 1.0, "band": "verbatim", "quote": "Analysis of DEGs was performed using the limma package of R software [14]."}}, {"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": 0.7, "band": "medium", "quote": "protein-protein interaction"}}, {"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": 0.7, "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": ["normalise_counts", "differential_expression_fit", "fdr_bh"], "missing_operations": [], "basis": "The paper names the method it used and the corpus's method extractor maps it onto the DSL catalogue: limma_voom."}, "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": ["GSE15781", "GSE110223", "GSE110224"], "resolved_accessions": ["GSE15781", "GSE110223", "GSE110224"], "statements": ["GSE15781, GSE110223, and GSE110224 can be downloaded from the GEO database. URL of the GEO database: https://www.ncbi.nlm.nih.gov/geo/."], "basis": "The paper names GSE15781, GSE110223, GSE110224 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": ["normalise_counts", "differential_expression_fit", "fdr_bh"], "assets": ["source:pmid:32462020", "data:geo:GSE110223"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE110223"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-10-31T18:20:02Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 3, "usage": {"prompt_tokens": 23151, "completion_tokens": 1224, "cached_tokens": 793}}, "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:32462020", "type": "paper", "label": "pmid:32462020"}, {"id": "source:pmid:32462020", "type": "manuscript", "label": "PMID 32462020 full text"}, {"id": "data:geo:GSE110223", "type": "dataset", "label": "GEO GSE110223"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:32462020", "type": "paper", "label": "pmid:32462020"}, {"id": "source:pmid:32462020", "type": "manuscript", "label": "PMID 32462020 full text"}, {"id": "data:geo:GSE110223", "type": "dataset", "label": "GEO GSE110223"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-32462020", "type": "extraction", "used": ["source:pmid:32462020"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE110223", "type": "accession_resolution", "used": ["data:geo:GSE110223"], "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:32462020", "parent_hash": "sha256:d9d871d3803be94ddb9356277507bd25f52aff05b160a04073b45beb6fb07f7e", "fork_of": null, "generation": 7}, "gaps": ["asset:data:geo:GSE110223 licence not read", "asset:data:geo:GSE110223 not downloaded", "asset:data:geo:GSE110224 licence not read", "asset:data:geo:GSE110224 not downloaded", "asset:data:geo:GSE15781 licence not read", "asset:data:geo:GSE15781 not downloaded", "execution.not_run", "review.human_critique", "review.independent_reader", "review.machine_critique"], "assays": [{"role": "analysis", "definition_id": "differential_expression", "definition_version": "f2132e96ae6c7a4e", "definition_digest": null, "required_operations": ["normalise_counts", "differential_expression_fit", "fdr_bh"], "support_state": "supported", "source_hashes": {"dsl_catalogue": "f2132e96ae6c7a4e"}, "confidence": 1.0, "evidence": ["Analysis of DEGs was performed using the limma package of R software [14]."], "order_basis": "analysis_only", "id": "assay:1"}]}