Identification of Potential Diagnostic and Prognostic Biomarkers for Colorectal Cancer Based on GEO and TCGA Databases.

{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:33519906", "kind": "science-record", "revision": 8, "content_hash": "sha256:dc4bb7b34b24347b2935e3804b7b12e4d5615709dbd5f8642adea4b702461ec2", "created_at": "2026-11-01T15:41:23Z", "updated_at": "2026-11-01T22:46:02Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Identification of Potential Diagnostic and Prognostic Biomarkers for Colorectal Cancer Based on GEO and TCGA Databases.", "doi": "10.3389/fgene.2020.602922", "pmid": "33519906", "authors": ["Zhenjiang Wang", "Mingyi Guo", "Xinbo Ai", "Jianbin Cheng", "Zaiwei Huang", "Xiaobin Li", "Yuping Chen"], "journal": "Frontiers in genetics", "year": 2020, "abstract": "Colorectal cancer (CRC) is one of the most common neoplastic diseases worldwide. With a high recurrence rate among all cancers, treatment of CRC only improved a little over the last two decades. The mortality and morbidity rates can be significantly lessened by earlier diagnosis and prompt treatment. Available biomarkers are not sensitive enough for the diagnosis of CRC, whereas the standard diagnostic method, endoscopy, is an invasive test and expensive. Hence, seeking the diagnostic and prognostic biomarkers of CRC is urgent and challenging. With that order, we screened the overlapped differentially expressed genes (DEGs) of GEO (GSE110223, GSE110224, GSE113513) and TCGA datasets. Subsequent protein-protein interaction network analysis recognized the hub genes among these DEGs. Further functional analyses including Gene Ontology and KEGG pathway analysis and gene set enrichment analysis were processed to investigate the role of these genes and potential underlying mechanisms in CRC. Kaplan-Meier analysis and Cox hazard ratio analysis were carried out to clarify the diagnostic and prognostic role of these genes. In conclusion, our present study demonstrated that CCNA2, MAD2L1, DLGAP5, AURKA, and RRM2 are all potential diagnostic biomarkers for CRC and may also be potential treatment targets for clinical implication in the future.", "claims": [{"id": "claim-method", "statement": "Using the GEOquery and limma R software packages in the Bioconductor project, the GEO2R web tool was used for identifying differential genes in selected datasets.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:33519906", "locator": "sections[4] \"Identification of DEGs\" paragraph 2", "quote": "Using the GEOquery and limma R software packages in the Bioconductor project, the GEO2R web tool was used for identifying differential genes in selected datasets."}], "state": "complete"}, {"id": "claim-data-access", "statement": "The datasets presented in this study can be found in online repositories. The names of the repository/repositories and accession number(s) can be found in the article/Supplementary Material.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:33519906", "locator": "sections[17] \"Data Availability Statement\" paragraph 2", "quote": "The datasets presented in this study can be found in online repositories. The names of the repository/repositories and accession number(s) can be found in the article/Supplementary Material."}], "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:33519906"], "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:33519906", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.3389/fgene.2020.602922", "sha256": "sha256:afd781f3193a013720b6019805d48ef4602747457b6d2d27760fdce3d4769ad3", "bytes": 34942, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.3389/fgene.2020.602922", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC7841465", "source": "europe_pmc_fulltext", "coverage": "whole_body", "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": "The datasets presented in this study can be found in online repositories. The names of the repository/repositories and accession number(s) can be found in the article/Supplementary Material.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The datasets presented in this study can be found in online repositories. The names of the repository/repositories and accession number(s) can be found in the article/Supplementary Material.", "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": "The datasets presented in this study can be found in online repositories. The names of the repository/repositories and accession number(s) can be found in the article/Supplementary Material.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The datasets presented in this study can be found in online repositories. The names of the repository/repositories and accession number(s) can be found in the article/Supplementary Material.", "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:GSE113513", "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=GSE113513", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE113513", "version": null, "note": "The datasets presented in this study can be found in online repositories. The names of the repository/repositories and accession number(s) can be found in the article/Supplementary Material.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The datasets presented in this study can be found in online repositories. The names of the repository/repositories and accession number(s) can be found in the article/Supplementary Material.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM3108231", "GSM3108232", "GSM3108233", "GSM3108234", "GSM3108235", "GSM3108236", "GSM3108237", "GSM3108238", "GSM3108239", "GSM3108240", "GSM3108241", "GSM3108242", "GSM3108243", "GSM3108244", "GSM3108245", "GSM3108246", "GSM3108247", "GSM3108248", "GSM3108249", "GSM3108250", "GSM3108251", "GSM3108252", "GSM3108253", "GSM3108254", "GSM3108255", "GSM3108256", "GSM3108257", "GSM3108258"], "sample_count": 28, "group_sizes": null, "group_sizes_basis": null, "platform": "15207", "taxon": "Homo sapiens", "title": "Gene expression profile of human colorectal carcinoma", "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:GSE113513 not downloaded", "asset:data:geo:GSE113513 licence not read"]}, "analysis": {"state": "partial", "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": "Using the GEOquery and limma R software packages in the Bioconductor project, the GEO2R web tool was used for identifying differential genes in selected datasets."}}, {"id": "method-2", "family": "survival_analysis", "specific": "kaplan_meier", "label": "Survival analysis", "dsl_operations": ["survival_km"], "missing_operations": [], "expressible": true, "parameters": {"hazard_ratio": "-Meier analysis and Cox hazard ratio analysis were carried o"}, "data_shapes": ["time_to_event_with_censoring"], "evidence": {"score": 0.7, "band": "medium", "quote": "Kaplan-Meier"}}, {"id": "method-3", "family": "principal_component_analysis", "specific": "pca", "label": "Principal component analysis", "dsl_operations": ["pca_fit"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["wide_numeric_matrix"], "evidence": {"score": 0.8, "band": "high", "quote": "principal component analysis"}}, {"id": "method-4", "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-5", "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": 0.8, "band": "high", "quote": "GO enrichment"}}], "targets": [], "gaps": ["method.reader_differs_from_extractor"]}, "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": ["GSE110223", "GSE110224", "GSE113513"], "resolved_accessions": ["GSE110223", "GSE110224", "GSE113513"], "statements": ["The datasets presented in this study can be found in online repositories. The names of the repository/repositories and accession number(s) can be found in the article/Supplementary Material."], "basis": "The paper names GSE110223, GSE110224, GSE113513 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:33519906", "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": "2026-10-31T18:26:40Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 3, "usage": {"prompt_tokens": 28953, "completion_tokens": 2138, "cached_tokens": 792}}, "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:33519906", "type": "paper", "label": "pmid:33519906"}, {"id": "source:pmid:33519906", "type": "manuscript", "label": "PMID 33519906 full text"}, {"id": "data:geo:GSE110223", "type": "dataset", "label": "GEO GSE110223"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:33519906", "type": "paper", "label": "pmid:33519906"}, {"id": "source:pmid:33519906", "type": "manuscript", "label": "PMID 33519906 full text"}, {"id": "data:geo:GSE110223", "type": "dataset", "label": "GEO GSE110223"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-33519906", "type": "extraction", "used": ["source:pmid:33519906"], "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:33519906", "parent_hash": "sha256:23d44b57057a8b74bd7d0eceb0f00a318150e9e754e84ac928002c1b98e8f6d8", "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:GSE113513 licence not read", "asset:data:geo:GSE113513 not downloaded", "execution.not_run", "method.reader_differs_from_extractor", "review.human_critique", "review.independent_reader", "review.machine_critique"], "assays": [{"role": "data_generation", "definition_id": "rna_seq", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.99, "evidence": ["s standard processing methods to analyze the RNA sequencing expression data of 9,736 tumors and 8,587 no", "s.html) is an online database that uses TCGA transcriptome and clinical patient data to enable research"], "order_basis": "paper_text_order:1609", "id": "assay:1"}, {"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": ["Using the GEOquery and limma R software packages in the Bioconductor project, the GEO2R web tool was used for identifying differential genes in selected datasets."], "order_basis": "consumes_earlier_output", "id": "assay:2"}]}