Data supporting the identification of compound for inhibition of survivin of colorectal cancer by using ingenuity pathway analysis of gene expression profiling of colorectal cancer tissues.

{"sci_version": "1.0", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:26217796", "kind": "science-record", "revision": 5, "content_hash": "sha256:522e4c0af4a4bb0a77c5ce65589e13fb9443a08b1f498821f87e27c40713764d", "created_at": "2026-11-01T15:40:09Z", "updated_at": "2026-11-01T21:20:03Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Data supporting the identification of compound for inhibition of survivin of colorectal cancer by using ingenuity pathway analysis of gene expression profiling of colorectal cancer tissues.", "doi": "10.1016/j.dib.2015.05.017", "pmid": "26217796", "authors": ["Yi-Chao Lee", "Jun-Wei Lee", "Chi-Chen Huang", "Ming-Heng Wu", "Kuen-Haur Lee"], "journal": "Data in brief", "year": 2015, "abstract": "The data in this article is related to the research article entitled, \"Targeting of Multiple Oncogenic Signaling Pathways by Hsp90 Inhibitor Alone or in Combination with Berberine for Treatment of Colorectal Cancer\" [1]. Overexpression of survivin induces resistance to various anticancer therapies such as chemotherapy and radiation therapy in colorectal cancer (CRC) cells. To determine significant correlations of biological functions/pathways with survivin, 4567 significant genes were analyzed from the GEO DataSet (GSE21815) of CRC and these were overlaid onto a global molecular network developed from information contained in the Ingenuity Pathway Analysis (IPA) database. The data here present the most significant disease and disordered biological functions, significant molecular/cellular functions and significant categories in physiological development/system functions which were associated with CRC. The top 10 canonical signaling pathways associated with CRC were categorize in order based on the level of statistical significance.", "claims": [{"id": "claim-method", "statement": "The genes showing significant differences in expression levels between groups will be submitted to IPA for human diseases and disorders, molecular and cellular functions categories and pathway analysis.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:26217796", "locator": "sections[5] \"Ingenuity pathway analysis (IPA)\" paragraph 2", "quote": "The genes showing significant differences in expression levels between groups will be submitted to IPA for human diseases and disorders, molecular and cellular functions categories and pathway analysis."}], "state": "complete"}, {"id": "claim-data-access", "statement": "Microarray expression data for the GEO data set will be retrieved for 132 stages I to IV CRC and 9 normal control from the NCBI GEO (GSE21815).", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:26217796", "locator": "sections[4] \"Acquisition and processing of public microarray data\" paragraph 2", "quote": "Microarray expression data for the GEO data set will be retrieved for 132 stages I to IV CRC and 9 normal control from the NCBI GEO (GSE21815)."}], "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:26217796"], "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:GSE21815"], "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:GSE21815"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:26217796", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1016/j.dib.2015.05.017", "sha256": "sha256:76a03904a768bc7647eb6c751fc8e5899e2e0a5036fa93477c25dfec68701a06", "bytes": 5772, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1016/j.dib.2015.05.017", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC4510466", "source": "europe_pmc_fulltext", "coverage": "whole_body_without_references", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE21815", "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=GSE21815", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE21815", "version": null, "note": "Microarray expression data for the GEO data set will be retrieved for 132 stages I to IV CRC and 9 normal control from the NCBI GEO (GSE21815).", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "Microarray expression data for the GEO data set will be retrieved for 132 stages I to IV CRC and 9 normal control from the NCBI GEO (GSE21815).", "access_statement_kind": "repository_route_statement", "sample_accessions": ["GSM543123", "GSM543124", "GSM543125", "GSM543126", "GSM543127", "GSM543128", "GSM543129", "GSM543130", "GSM543131", "GSM543132", "GSM543133", "GSM543134", "GSM543135", "GSM543136", "GSM543137", "GSM543138", "GSM543139", "GSM543140", "GSM543141", "GSM543142", "GSM543143", "GSM543144", "GSM543145", "GSM543146", "GSM543147", "GSM543148", "GSM543149", "GSM543150", "GSM543151", "GSM543152", "GSM543153", "GSM543154", "GSM543155", "GSM543156", "GSM543157", "GSM543158", "GSM543159", "GSM543160", "GSM543161", "GSM543162", "GSM543163", "GSM543164", "GSM543165", "GSM543166", "GSM543167", "GSM543168", "GSM543169", "GSM543170", "GSM543171", "GSM543172", "GSM543173", "GSM543174", "GSM543175", "GSM543176", "GSM543177", "GSM543178", "GSM543179", "GSM543180", "GSM543181", "GSM543182", "GSM543183", "GSM543184", "GSM543185", "GSM543186", "GSM543187", "GSM543188", "GSM543189", "GSM543190", "GSM543191", "GSM543192", "GSM543193", "GSM543194", "GSM543195", "GSM543196", "GSM543197", "GSM543198", "GSM543199", "GSM543200", "GSM543201", "GSM543202", "GSM543203", "GSM543204", "GSM543205", "GSM543206", "GSM543207", "GSM543208", "GSM543209", "GSM543210", "GSM543211", "GSM543212", "GSM543213", "GSM543214", "GSM543215", "GSM543216", "GSM543217", "GSM543218", "GSM543219", "GSM543220", "GSM543221", "GSM543222", "GSM543223", "GSM543224", "GSM543225", "GSM543226", "GSM543227", "GSM543228", "GSM543229", "GSM543230", "GSM543231", "GSM543232", "GSM543233", "GSM543234", "GSM543235", "GSM543236", "GSM543237", "GSM543238", "GSM543239", "GSM543240", "GSM543241", "GSM543242", "GSM543243", "GSM543244", "GSM543245", "GSM543246", "GSM543247", "GSM543248", "GSM543249", "GSM543250", "GSM543251", "GSM543252", "GSM543253", "GSM543254", "GSM543255", "GSM543256", "GSM543257", "GSM543258", "GSM543259", "GSM543260", "GSM543261", "GSM543262", "GSM543263"], "sample_count": 141, "group_sizes": null, "group_sizes_basis": null, "platform": "6480", "taxon": "Homo sapiens", "title": "Gene expression profiles in 132 laser microdissected colorectal cancer tissues", "resolution_checked_at": "2026-11-01T15:39:54Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "asset:table:pmid:26217796:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:40a297003d0b0e4a931aeeb3ac3536c7c240350a49713e8281046a0508b50b19", "bytes": 945, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[1]/table-wrap[1]#t0015", "version": null, "note": null, "structure": {"pmcid": "PMC4510466", "section_index": 1, "section_title": "Specifications table", "row_count": 9, "column_count": 2}, "table": {"label": null, "caption": null, "rows": [["Subject area", "Medicine, biology"], ["More specific subject area", "Molecular biology, Cancer biology"], ["Type of data", "Table"], ["How data was acquired", "Microarray data were obtained from the Gene Expression Omnibus (GEO) repository at the NCBI were analyzed using the Ingenuity pathway analysis (IPA) database"], ["Data format", "Analyzed"], ["Experimental factors", "None"], ["Experimental features", "Gene expression data of 132 samples of laser microdissected CRC tumors and nine normal colon controls were retrieved from the GEO DataSet under the accession number GSE21815 and imported into the IPA Tool to determine significant correlations of biological functions/pathways with survivin"], ["Data source location", "Taipei, Taiwan"], ["Data accessibility", "The data are supplied with this article"]], "row_count": 9, "column_count": 2, "numeric_cells": 1, "header_rows": 1, "locator": "section[1]/table-wrap[1]#t0015"}}], "gaps": ["asset:data:geo:GSE21815 not downloaded", "asset:data:geo:GSE21815 licence not read"]}, "analysis": {"state": "partial", "methods": [{"id": "method-1", "family": null, "specific": null, "label": "Ingenuity Pathway Analysis (IPA)", "dsl_operations": [], "missing_operations": [], "expressible": null, "parameters": {}, "data_shapes": [], "evidence": {"score": 1.0, "band": "verbatim", "quote": "The genes showing significant differences in expression levels between groups will be submitted to IPA for human diseases and disorders, molecular and cellular functions categories and pathway analysis."}}], "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": "method", "blocked_on": "method:not_determinable", "axes": {"method": {"tier": "R4", "expressible": false, "required_operations": [], "missing_operations": [], "basis": "The reader quoted the method the paper names (Ingenuity Pathway Analysis (IPA)), but the corpus's method extractor could not map it onto a DSL operation, so the method is published but not expressible."}, "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": ["GSE21815"], "resolved_accessions": ["GSE21815"], "statements": ["Microarray expression data for the GEO data set will be retrieved for 132 stages I to IV CRC and 9 normal control from the NCBI GEO (GSE21815)."], "basis": "The paper names GSE21815 in NCBI GEO and the accession resolves in the repository. No dataset was downloaded and no licence was read."}}, "can_run": {"dsl_operations": [], "assets": ["source:pmid:26217796", "data:geo:GSE21815", "asset:table:pmid:26217796:1"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE21815"]}, "gaps": ["method:not_determinable"]}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": null, "independence": "same_provider"}, "evidence_check": {"method": "verbatim", "availability": null}, "calls": 0, "usage": {}}, "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:26217796", "type": "paper", "label": "pmid:26217796"}, {"id": "source:pmid:26217796", "type": "manuscript", "label": "PMID 26217796 full text"}, {"id": "data:geo:GSE21815", "type": "dataset", "label": "GEO GSE21815"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:26217796", "type": "paper", "label": "pmid:26217796"}, {"id": "source:pmid:26217796", "type": "manuscript", "label": "PMID 26217796 full text"}, {"id": "data:geo:GSE21815", "type": "dataset", "label": "GEO GSE21815"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-26217796", "type": "extraction", "used": ["source:pmid:26217796"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE21815", "type": "accession_resolution", "used": ["data:geo:GSE21815"], "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:26217796", "parent_hash": "sha256:7be40239f801d3ab42f7796c4f168ea6c93b097dcdd9811dee549cccd3f3c1cb", "fork_of": null, "generation": 4}, "gaps": ["asset:data:geo:GSE21815 licence not read", "asset:data:geo:GSE21815 not downloaded", "execution.not_run", "method.reader_named_unmapped", "review.human_critique", "review.independent_reader", "review.machine_critique"]}