Somatic Copy Number Alterations in Human Cancers: An Analysis of Publicly Available Data From The Cancer Genome Atlas.

{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:34395272", "kind": "science-record", "revision": 7, "content_hash": "sha256:9f575bc111d8bfe2b39fdf0af72750e98da1fd8769a12517ce27605aa4b43fb2", "created_at": "2026-11-01T15:41:48Z", "updated_at": "2026-11-01T22:04:29Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Somatic Copy Number Alterations in Human Cancers: An Analysis of Publicly Available Data From The Cancer Genome Atlas.", "doi": "10.3389/fonc.2021.700568", "pmid": "34395272", "authors": ["Luuk Harbers", "Federico Agostini", "Marcin Nicos", "Dimitri Poddighe", "Magda Bienko", "Nicola Crosetto"], "journal": "Frontiers in oncology", "year": 2021, "abstract": "Somatic copy number alterations (SCNAs) are a pervasive trait of human cancers that contributes to tumorigenesis by affecting the dosage of multiple genes at the same time. In the past decade, The Cancer Genome Atlas (TCGA) and the International Cancer Genome Consortium (ICGC) initiatives have generated and made publicly available SCNA genomic profiles from thousands of tumor samples across multiple cancer types. Here, we present a comprehensive analysis of 853,218 SCNAs across 10,729 tumor samples belonging to 32 cancer types using TCGA data. We then discuss current models for how SCNAs likely arise during carcinogenesis and how genomic SCNA profiles can inform clinical practice. Lastly, we highlight open questions in the field of cancer-associated SCNAs.", "claims": [{"id": "claim-method", "statement": "In (B, C), asterisks indicate statistical significance levels (Wilcoxon’s test, two-sided) at 0.05 (*), 0.01 (**), 0.001 (***) and 0.0001 (****).", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:34395272", "locator": "sections[11] \"How Much of the Genome Is Affected by SCNAs in Different Cancer Types?\" paragraph 3", "quote": "In (B, C), asterisks indicate statistical significance levels (Wilcoxon’s test, two-sided) at 0.05 (*), 0.01 (**), 0.001 (***) and 0.0001 (****)."}], "state": "complete"}, {"id": "claim-data-access", "statement": "The original contributions presented in the study are included in the article/Supplementary Material. Further inquiries can be directed to the corresponding author.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:34395272", "locator": "sections[21] \"Data Availability Statement\" paragraph 2", "quote": "The original contributions presented in the study are included in the article/Supplementary Material. Further inquiries can be directed to the corresponding author."}], "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:34395272"], "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": "blocked", "blocked_on": "method:group_comparison_wilcoxon", "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:run_analysis blocked on method:group_comparison_wilcoxon", "step:obtain_source_data blocked on data:accession_absent"]}, "data": {"state": "partial", "assets": [{"id": "source:pmid:34395272", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.3389/fonc.2021.700568", "sha256": "sha256:e6ff6eb9fbe6b3fd6eb209e636a868fb4734f57f61d890c1694216dc588ee643", "bytes": 37716, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.3389/fonc.2021.700568", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC8355892", "source": "europe_pmc_fulltext", "coverage": "whole_body_without_references", "text_hash_scope": "rendered_section_body"}}], "gaps": []}, "analysis": {"state": "partial", "methods": [{"id": "method-1", "family": "group_comparison", "specific": "wilcoxon", "label": "Group comparison", "dsl_operations": [], "missing_operations": ["group_comparison_wilcoxon"], "expressible": false, "parameters": {}, "data_shapes": ["two_or_more_groups_continuous"], "evidence": {"score": 1.0, "band": "verbatim", "quote": "In (B, C), asterisks indicate statistical significance levels (Wilcoxon’s test, two-sided) at 0.05 (*), 0.01 (**), 0.001 (***) and 0.0001 (****)."}}, {"id": "method-2", "family": "correlation_analysis", "specific": "spearman", "label": "Correlation analysis", "dsl_operations": ["spearman_rho"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["paired_numeric_columns"], "evidence": {"score": 0.8, "band": "high", "quote": "Spearman correlation"}}], "targets": [], "gaps": ["method.group_comparison_wilcoxon"]}, "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": false, "required_operations": [], "missing_operations": ["group_comparison_wilcoxon"], "basis": "The paper names the method it used and the corpus's method extractor maps it onto the DSL catalogue: wilcoxon."}, "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 original contributions presented in the study are included in the article/Supplementary Material. Further inquiries can be directed to the corresponding author."], "basis": "The paper names no accession to its source data, so the data has to come from the authors."}}, "can_run": {"dsl_operations": [], "assets": ["source:pmid:34395272"], "steps": []}, "must_build": {"dsl_operations": [{"operation": "group_comparison_wilcoxon", "unlocks_papers": null, "priority": null}], "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": "2026-10-31T18:33:37Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 3, "usage": {"prompt_tokens": 26680, "completion_tokens": 1929, "cached_tokens": 784}}, "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:34395272", "type": "paper", "label": "pmid:34395272"}, {"id": "source:pmid:34395272", "type": "manuscript", "label": "PMID 34395272 full text"}, {"id": "data:geo:None", "type": "dataset", "label": "GEO None"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:34395272", "type": "paper", "label": "pmid:34395272"}, {"id": "source:pmid:34395272", "type": "manuscript", "label": "PMID 34395272 full text"}, {"id": "data:geo:None", "type": "dataset", "label": "GEO None"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-34395272", "type": "extraction", "used": ["source:pmid:34395272"], "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:34395272", "parent_hash": "sha256:8bc3114b0f8c166d2f8b4ee2f68792b333dd7acd68673712a67297a4ca03b796", "fork_of": null, "generation": 6}, "gaps": ["execution.not_run", "method.group_comparison_wilcoxon", "review.human_critique", "review.independent_reader", "review.machine_critique", "step:obtain_source_data blocked on data:accession_absent", "step:run_analysis blocked on method:group_comparison_wilcoxon"], "assays": [{"role": "analysis", "definition_id": "group_comparison", "definition_version": "f2132e96ae6c7a4e", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"dsl_catalogue": "f2132e96ae6c7a4e"}, "confidence": 1.0, "evidence": ["In (B, C), asterisks indicate statistical significance levels (Wilcoxon’s test, two-sided) at 0.05 (*), 0.01 (**), 0.001 (***) and 0.0001 (****)."], "order_basis": "analysis_only", "id": "assay:1"}]}