TCGA2BED: extracting, extending, integrating, and querying The Cancer Genome Atlas.

{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:28049410", "kind": "science-record", "revision": 4, "content_hash": "sha256:ad45310c9a8a010ef158f53f246f4179bd13202797dec89bd372fe179cc4039e", "created_at": "2026-11-01T15:40:22Z", "updated_at": "2026-11-01T21:20:46Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "TCGA2BED: extracting, extending, integrating, and querying The Cancer Genome Atlas.", "doi": "10.1186/s12859-016-1419-5", "pmid": "28049410", "authors": ["Fabio Cumbo", "Giulia Fiscon", "Stefano Ceri", "Marco Masseroli", "Emanuel Weitschek"], "journal": "BMC bioinformatics", "year": 2017, "abstract": "BACKGROUND: Data extraction and integration methods are becoming essential to effectively access and take advantage of the huge amounts of heterogeneous genomics and clinical data increasingly available. In this work, we focus on The Cancer Genome Atlas, a comprehensive archive of tumoral data containing the results of high-throughout experiments, mainly Next Generation Sequencing, for more than 30 cancer types.\nRESULTS: We propose TCGA2BED a software tool to search and retrieve TCGA data, and convert them in the structured BED format for their seamless use and integration. Additionally, it supports the conversion in CSV, GTF, JSON, and XML standard formats. Furthermore, TCGA2BED extends TCGA data with information extracted from other genomic databases (i.e., NCBI Entrez Gene, HGNC, UCSC, and miRBase). We also provide and maintain an automatically updated data repository with publicly available Copy Number Variation, DNA-methylation, DNA-seq, miRNA-seq, and RNA-seq (V1,V2) experimental data of TCGA converted into the BED format, and their associated clinical and biospecimen meta data in attribute-value text format.\nCONCLUSIONS: The availability of the valuable TCGA data in BED format reduces the time spent in taking advantage of them: it is possible to efficiently and effectively deal with huge amounts of cancer genomic data integratively, and to search, retrieve and extend them with additional information. The BED format facilitates the investigators allowing several knowledge discovery analyses on all tumor types in TCGA with the final aim of understanding pathological mechanisms and aiding cancer treatments.", "claims": [{"id": "claim-method", "statement": "The GenoMetric Query Language [22] is a high-level, declarative query language for genomic data, and a toolkit is available for its use at http://www.bioinformatics.deib.polimi.it/GMQL/.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:28049410", "locator": "sections[6] \"Integrative querying of TCGA data with the GenoMetric Query Language\" paragraph 2", "quote": "The GenoMetric Query Language [22] is a high-level, declarative query language for genomic data, and a toolkit is available for its use at http://www.bioinformatics.deib.polimi.it/GMQL/."}], "state": "complete"}, {"id": "claim-data-access", "statement": "We created and are maintaining an open access FTP repository (ftp://bioinf.iasi.cnr.it/), which contains the original TCGA data sets [14] addressed by TCGA2BED and the corresponding data converted into the BED format.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:28049410", "locator": "sections[5] \"TCGA2BED data repository\" paragraph 2", "quote": "We created and are maintaining an open access FTP repository (ftp://bioinf.iasi.cnr.it/), which contains the original TCGA data sets [14] addressed by TCGA2BED and the corresponding data converted into the BED format."}], "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:28049410"], "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": "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": [], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": ["step:obtain_source_data blocked on data:accession_absent"]}, "data": {"state": "partial", "assets": [{"id": "source:pmid:28049410", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1186/s12859-016-1419-5", "sha256": "sha256:448c8c6f5b6ded7a7bc7da2b50e7ec697a322aab5562f9e86a92abe12940ab1c", "bytes": 43093, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1186/s12859-016-1419-5", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC5210259", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "asset:table:pmid:28049410:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:92ddda77b7dc3b778de762d26d06c858921f4758836a72fb072c3470be3f9679", "bytes": 602, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[5]/table-wrap[1]#Tab1", "version": null, "note": "Number (#) of considered data for each type of experiment, across all TCGA tumors", "structure": {"pmcid": "PMC5210259", "section_index": 5, "section_title": "TCGA2BED data repository", "row_count": 8, "column_count": 5}, "table": {"label": "Table 1", "caption": "Number (#) of considered data for each type of experiment, across all TCGA tumors", "rows": [["Experiment type", "# Aliquots", "# Samples", "# Patients", "# Tumors"], ["CNV", "22,632", "22,409", "11,162", "33"], ["DNA-seq", "6,914", "6,884", "6,852", "30"], ["DNA-methylation", "12,841", "12,508", "11,26", "33"], ["miRNA-seq", "9,909", "9,763", "9,031", "32"], ["RNA-seq V1", "3,675", "3,674", "3,393", "15"], ["RNA-seq V2", "9,825", "9,823", "9,107", "31"], ["All", "62,335", "22,840", "11,317", "33"]], "row_count": 8, "column_count": 5, "numeric_cells": 28, "header_rows": 1, "locator": "section[5]/table-wrap[1]#Tab1"}}], "gaps": []}, "analysis": {"state": "partial", "methods": [{"id": "method-1", "family": null, "specific": null, "label": "GenoMetric Query Language (GMQL)", "dsl_operations": [], "missing_operations": [], "expressible": null, "parameters": {}, "data_shapes": [], "evidence": {"score": 1.0, "band": "verbatim", "quote": "The GenoMetric Query Language [22] is a high-level, declarative query language for genomic data, and a toolkit is available for its use at http://www.bioinformatics.deib.polimi.it/GMQL/."}}], "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": "data", "blocked_on": "data:accession_absent", "axes": {"method": {"tier": "R4", "expressible": false, "required_operations": [], "missing_operations": [], "basis": "The reader quoted the method the paper names (GenoMetric Query Language (GMQL)), 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": "R4", "reachable": false, "accessions": [], "resolved_accessions": [], "statements": ["We created and are maintaining an open access FTP repository (ftp://bioinf.iasi.cnr.it/), which contains the original TCGA data sets [14] addressed by TCGA2BED and the corresponding data converted into the BED format."], "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:28049410", "asset:table:pmid:28049410:1"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "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": null, "independence": "same_provider"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "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:28049410", "type": "paper", "label": "pmid:28049410"}, {"id": "source:pmid:28049410", "type": "manuscript", "label": "PMID 28049410 full text"}, {"id": "data:geo:None", "type": "dataset", "label": "GEO None"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:28049410", "type": "paper", "label": "pmid:28049410"}, {"id": "source:pmid:28049410", "type": "manuscript", "label": "PMID 28049410 full text"}, {"id": "data:geo:None", "type": "dataset", "label": "GEO None"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-28049410", "type": "extraction", "used": ["source:pmid:28049410"], "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:28049410", "parent_hash": "sha256:03d7c405e45f50eea4587a56c5a007460a31da6fc0cbba4e2910c60b6734d6d0", "fork_of": null, "generation": 3}, "gaps": ["execution.not_run", "method.reader_named_unmapped", "review.human_critique", "review.independent_reader", "review.machine_critique", "step:obtain_source_data blocked on data:accession_absent"], "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": 0.93, "evidence": ["on, DNA-methylation, DNA-seq, miRNA-seq, and RNA-seq (V1,V2) experimental data of TCGA converted"], "order_basis": "paper_text_order:1011", "id": "assay:1"}]}