{ "analyses": [ { "alias": "Analysis_1", "analysis_method": "AnalysisMethod_Alignment", "title": "Alignment of the 15 days samples", "research_data_files": [ "my_first_file.fastq.gz", "my_second_file.fastq.gz", "my_third_file.fastq.gz", "my_fourth_file.fastq.gz" ] }, { "alias": "Analysis_2", "analysis_method": "AnalysisMethod_Alignment", "title": "Alignment of the 30 days samples", "research_data_files": [ "my_fifth_file.fastq.gz", "my_sixth_file.fastq.gz", "my_seventh_file.fastq.gz", "my_eighth_file.fastq.gz" ] }, { "alias": "Analysis_3", "analysis_method": "AnalysisMethod_VariantCalling", "title": "Variant calling", "description": "Variant calling on my_first_bam.bam.gz and my_second_bam.bam.gz.", "research_data_files": [ "my_first_file.fastq.gz", "my_second_file.fastq.gz", "my_third_file.fastq.gz", "my_fourth_file.fastq.gz", "my_fifth_file.fastq.gz", "my_sixth_file.fastq.gz", "my_seventh_file.fastq.gz", "my_eighth_file.fastq.gz" ] } ], "analysis_methods": [ { "alias": "AnalysisMethod_Alignment", "name": "Alignment", "description": "Alignment of WGS reads to the reference genome.", "type": "Alignment", "workflow_name": "Example alignment workflow", "workflow_version": "1.0.0", "workflow_repository": "https://github.com/example/alignment-workflow", "workflow_doi": "10.0000/example.alignment", "reference_name": "GRCh38", "reference_type": "GENOME" }, { "alias": "AnalysisMethod_VariantCalling", "name": "Variant Calling", "description": "Somatic variant calling on the aligned reads.", "type": "Variant calling", "workflow_name": "Example variant calling workflow", "workflow_version": "1.0.0", "workflow_repository": "https://github.com/example/variant-calling-workflow", "workflow_doi": "10.0000/example.variantcalling", "reference_name": "GRCh38", "reference_type": "GENOME" } ], "analysis_method_supporting_files": [], "studies": [ { "alias": "STUDY_1", "title": "Example study: whole-genome sequencing of a bone cancer patient", "description": "Illustrative example submission from the GHGA documentation. Tumour (case) and matched normal (control) samples of one patient with a bone tumour were whole-genome sequenced.", "types": [ "CANCER_GENOMICS" ], "affiliations": [ "German Cancer Research Center (DKFZ)" ] } ], "individuals": [ { "alias": "Patient_1", "diagnosis_ids": [ "ICD-10: C40" ], "diagnosis_terms": [ "Malignant neoplasm of bone and articular cartilage of limbs" ], "sex": "MALE" } ], "individual_supporting_files": [ { "alias": "Patient_1_Phenopacket.json", "format": "JSON", "individual": "Patient_1", "name": "Patient_1_Phenopacket.json", "dataset": "DS_CLINICAL", "included_in_submission": true } ], "samples": [ { "alias": "Sample_15_01", "individual": "Patient_1", "name": "Sample_15_01", "biological_replicate": 1, "description": "Case sample for Patient_1 at 15days", "disease_or_healthy": "DISEASE", "case_control_status": "CASE", "biospecimen_age_at_sampling": "UNKNOWN", "attributes": [ { "key": "time_point", "value": "15days" } ] }, { "alias": "Sample_15_02", "individual": "Patient_1", "name": "Sample_15_02", "biological_replicate": 1, "description": "Control sample for Patient_1 at 15days", "disease_or_healthy": "HEALTHY", "case_control_status": "CONTROL", "biospecimen_age_at_sampling": "UNKNOWN", "attributes": [ { "key": "time_point", "value": "15days" } ] }, { "alias": "Sample_30_01", "individual": "Patient_1", "name": "Sample_30_01", "biological_replicate": 2, "description": "Case sample for Patient_1 at 30days", "disease_or_healthy": "DISEASE", "case_control_status": "CASE", "biospecimen_age_at_sampling": "UNKNOWN", "attributes": [ { "key": "time_point", "value": "30days" } ] }, { "alias": "Sample_30_02", "individual": "Patient_1", "name": "Sample_30_02", "biological_replicate": 2, "description": "Control sample for Patient_1 at 30days", "disease_or_healthy": "HEALTHY", "case_control_status": "CONTROL", "biospecimen_age_at_sampling": "UNKNOWN", "attributes": [ { "key": "time_point", "value": "30days" } ] } ], "experiment_methods": [ { "alias": "Method_1", "name": "WGS on Illumina HiSeq X Ten", "description": "WGS performed on Illumina HiSeq X Ten", "type": "WGS", "library_type": "WGS", "library_selection_methods": [ "RANDOM_METHOD" ], "library_preparation": "PCR-free library preparation", "instrument_model": "HISEQ_X_TEN", "sequencing_layout": "SE" } ], "experiment_method_supporting_files": [], "experiments": [ { "alias": "Exp_1", "experiment_method": "Method_1", "title": "WGS of Sample_15_01", "description": "WGS performed on Illumina HiSeq X Ten", "sample": "Sample_15_01" }, { "alias": "Exp_2", "experiment_method": "Method_1", "title": "WGS of Sample_15_02", "description": "WGS performed on Illumina HiSeq X Ten", "sample": "Sample_15_02" }, { "alias": "Exp_3", "experiment_method": "Method_1", "title": "WGS of Sample_30_01", "description": "WGS performed on Illumina HiSeq X Ten", "sample": "Sample_30_01" }, { "alias": "Exp_4", "experiment_method": "Method_1", "title": "WGS of Sample_30_02", "description": "WGS performed on Illumina HiSeq X Ten", "sample": "Sample_30_02" } ], "research_data_files": [ { "alias": "my_first_file.fastq.gz", "format": "FASTQ", "technical_replicate": 1, "sequencing_lane_id": "4", "experiments": [ "Exp_1" ], "name": "my_first_file.fastq.gz", "dataset": "DS_WGS", "included_in_submission": true }, { "alias": "my_second_file.fastq.gz", "format": "FASTQ", "technical_replicate": 2, "sequencing_lane_id": "4", "experiments": [ "Exp_1" ], "name": "my_second_file.fastq.gz", "dataset": "DS_WGS", "included_in_submission": true }, { "alias": "my_third_file.fastq.gz", "format": "FASTQ", "technical_replicate": 1, "sequencing_lane_id": "5", "experiments": [ "Exp_2" ], "name": "my_third_file.fastq.gz", "dataset": "DS_WGS", "included_in_submission": true }, { "alias": "my_fourth_file.fastq.gz", "format": "FASTQ", "technical_replicate": 2, "sequencing_lane_id": "5", "experiments": [ "Exp_2" ], "name": "my_fourth_file.fastq.gz", "dataset": "DS_WGS", "included_in_submission": true }, { "alias": "my_fifth_file.fastq.gz", "format": "FASTQ", "technical_replicate": 1, "sequencing_lane_id": "2", "experiments": [ "Exp_3" ], "name": "my_fifth_file.fastq.gz", "dataset": "DS_WGS", "included_in_submission": true }, { "alias": "my_sixth_file.fastq.gz", "format": "FASTQ", "technical_replicate": 2, "sequencing_lane_id": "2", "experiments": [ "Exp_3" ], "name": "my_sixth_file.fastq.gz", "dataset": "DS_WGS", "included_in_submission": true }, { "alias": "my_seventh_file.fastq.gz", "format": "FASTQ", "technical_replicate": 1, "sequencing_lane_id": "6", "experiments": [ "Exp_4" ], "name": "my_seventh_file.fastq.gz", "dataset": "DS_WGS", "included_in_submission": true }, { "alias": "my_eighth_file.fastq.gz", "format": "FASTQ", "technical_replicate": 2, "sequencing_lane_id": "6", "experiments": [ "Exp_4" ], "name": "my_eighth_file.fastq.gz", "dataset": "DS_WGS", "included_in_submission": true } ], "process_data_files": [ { "alias": "my_first_bam.bam.gz", "format": "BAM", "analysis": "Analysis_1", "name": "my_first_bam.bam.gz", "dataset": "DS_ALIGNMENT", "included_in_submission": true }, { "alias": "my_second_bam.bam.gz", "format": "BAM", "analysis": "Analysis_2", "name": "my_second_bam.bam.gz", "dataset": "DS_ALIGNMENT", "included_in_submission": true }, { "alias": "my_first_VCF.vcf.gz", "format": "VCF", "analysis": "Analysis_3", "name": "my_first_VCF.vcf.gz", "dataset": "DS_VARIANTS", "included_in_submission": true } ], "datasets": [ { "alias": "DS_WGS", "title": "Bone cancer WGS dataset", "description": "Whole-genome sequencing reads (FASTQ) of tumour and matched normal samples of one bone cancer patient.", "types": [ "WGS" ], "data_access_policy": "DKFZ_DAP", "study": "STUDY_1" }, { "alias": "DS_ALIGNMENT", "title": "Alignment results", "description": "Aligned reads (BAM) of the tumour and matched normal samples.", "types": [ "WGS" ], "data_access_policy": "DKFZ_DAP", "study": "STUDY_1" }, { "alias": "DS_VARIANTS", "title": "Variant calling result", "description": "Variant calls (VCF) derived from the aligned reads.", "types": [ "Genomic variant calling" ], "data_access_policy": "DKFZ_DAP", "study": "STUDY_1" }, { "alias": "DS_CLINICAL", "title": "Clinical data", "description": "Phenopacket with structured clinical information on Patient_1.", "types": [ "Phenotype information" ], "data_access_policy": "DKFZ_DAP", "study": "STUDY_1" } ], "data_access_policies": [ { "alias": "DKFZ_DAP", "name": "Example data access policy", "description": "Access for research on bone cancer, granted by the DKFZ Data Access Committee.", "policy_text": "Data may only be used for research on bone cancer. Requests are reviewed by the Data Access Committee; a Data Transfer Agreement must be signed before access is granted.", "data_use_permission_term": "DISEASE_SPECIFIC_RESEARCH", "data_use_permission_id": "DUO:0000007", "data_access_committee": "DKFZ_DAC" } ], "data_access_committees": [ { "alias": "DKFZ_DAC", "email": "data-access-committee@example.org", "institute": "German Cancer Research Center (DKFZ)" } ], "publications": [] }