{"doi":"10.1093/bioinformatics/btaf546","title":"Oncopacket: integration of cancer research data using GA4GH phenopackets","abstract":"SUMMARY: Lack of data integration remains a significant impediment to cancer research, and many analyses still require customized software to transform and prepare cancer data. We describe a software package to harmonize genetic and clinical cancer data into the GA4GH Phenopacket schema, an ISO standard for representing clinical case data. We integrated demographic, mutation, morphology, diagnosis, intervention, and survival data using case data from the National Cancer Institute for 12 cancer types. The Phenopacket standard provides a foundation for downstream use, including sophisticated statistical and AI/ML analyses. We demonstrate fitness for purpose by using the integrated data to recapitulate a known association between mutations in the gene encoding isocitrate dehydrogenase 1 and survival time in brain cancer patients. AVAILABILITY AND IMPLEMENTATION: Source code is freely available at: https://github.com/monarch-initiative/oncopacket (archived at 10.5281/zenodo.15353125).","journal":"Bioinformatics","year":2025,"id":576313,"datarank":0.0,"base_score":0.0,"endowment":0.0,"self_citation_contribution":0.0,"citation_network_contribution":0.0,"self_endowment_contribution":0.0,"citer_contribution":0.0,"corpus_percentile":null,"corpus_rank":null,"citation_count":0,"citer_count":0,"citers_with_citation_signal":0,"citers_with_endowment":0,"datacite_reuse_total":0,"is_dataset":false,"is_dataset_confidence":0.5964,"is_data_producer":false,"deposit_databanks":null,"is_oa":true,"file_count":0,"downloads":0,"has_version_chain":false,"published_date":"2025-01-01","fair_score":null,"fair_percentile":null,"algorithm_id":"datarank_citation_only_1hop_v6","ranking_scope":"data_only","authors":[{"id":1485245,"name":"Daniel Danis","orcid":null,"position":1,"is_corresponding":false},{"id":1399204,"name":"Sagar Patil","orcid":"0000-0001-6142-1106","position":2,"is_corresponding":false},{"id":1485246,"name":"Nobal Kishor","orcid":null,"position":3,"is_corresponding":false},{"id":1485247,"name":"Rajdeep Mondal","orcid":null,"position":4,"is_corresponding":false},{"id":302290,"name":"Abhishek Jha","orcid":"0000-0001-9161-0450","position":5,"is_corresponding":false},{"id":418267,"name":"Qingrong Chen","orcid":"0000-0003-1325-6147","position":6,"is_corresponding":false},{"id":4142,"name":"Chunhua Yan","orcid":"0000-0001-5474-7431","position":7,"is_corresponding":false},{"id":95743,"name":"Monica C Munoz-Torres","orcid":"0000-0001-8430-6039","position":8,"is_corresponding":false},{"id":418276,"name":"Daoud Meerzaman","orcid":"0000-0002-0129-5256","position":9,"is_corresponding":false},{"id":49925,"name":"Peter N. Robinson","orcid":"0000-0002-0736-9199","position":10,"is_corresponding":false},{"id":37898,"name":"Justin T Reese","orcid":"0000-0002-2170-2250","position":11,"is_corresponding":false},{"id":1109033,"name":"Michael Sierk","orcid":"0000-0002-0657-0288","position":0,"is_corresponding":true}],"reference_count":16,"raw_metadata":null,"created_at":"2026-07-19T02:57:56.636458Z","pmid":"41017641","pmcid":null,"fwci":null,"citation_percentile":null,"influential_citations":0,"oa_status":null,"license":null,"views":0,"total_file_size_bytes":0,"version_count":0,"fair_f":null,"fair_a":null,"fair_i":null,"fair_r":null,"fair_zscore":null,"fair_rationale":null,"fair_model":null,"fair_agent_version":null,"fair_fulltext_source":null,"fair_has_llm":null,"fair_computed_at":null,"clinical_trials":[],"software_tools":[],"db_accessions":[],"linked_datasets":[],"topics":[]}