{"lab": {"title": "4DN DCIC, HMS", "display_title": "4DN DCIC, HMS", "status": "current", "@type": ["Lab", "Item"], "uuid": "828cd4fe-ebb0-4b36-a94a-d2e3a36cc989", "@id": "/labs/4dn-dcic-lab/", "correspondence": [{"contact_email": "cGV0ZXJfcGFya0BobXMuaGFydmFyZC5lZHU=", "@id": "/users/fb287a31-e765-41c5-8c1d-665f8e9f025b/", "display_title": "Peter Park"}], "pi": {"error": "no view permissions"}, "principals_allowed": {"view": ["system.Everyone"], "edit": ["group.admin", "role.lab_submitter", "submits_for.828cd4fe-ebb0-4b36-a94a-d2e3a36cc989"]}}, "name": "hi-c-processing-pairs", "tags": ["accepted"], "award": {"@id": "/awards/1U01CA200059-01/", "display_title": "4D NUCLEOME NETWORK DATA COORDINATION AND INTEGRATION CENTER - PHASE I", "uuid": "b0b9c607-f8b4-4f02-93f4-9895b461334b", "status": "current", "description": "DCIC: The goals of the 4D Nucleome (4DN) Data Coordination and Integration Center (DCIC) are to collect, store, curate, display, and analyze data generated in the 4DN Network. We have assembled a team of investigators with a strong track record in analysis of chromatin interaction data, image processing and three-dimensional data visualization, integrative analysis of genomic and epigenomic data, data portal development, large-scale computing, and development of secure and flexible cloud technologies. In Aim 1, we will develop efficient submission pipelines for data and metadata from 4DN data production groups. We will define data/metadata requirements and quality metrics in conjunction with the production groups and ensure that high-quality, well- annotated data become available to the wider scientific community in a timely manner. In Aim 2, we will develop a user-friendly data portal for the broad scientific community. This portal will provide an easy-to-navigate interface for accessing raw and intermediate data files, allow for programmatic access via APIs, and will incorporate novel analysis and visualization tools developed by DCIC as well as other Network members. For computing and storage scalability and cost-effectiveness, significant efforts will be devoted to development and deployment of cloud-based technology. We will conduct tutorials and workshops to facilitate the use of 4DN data and tools by external investigators. In Aim 3, we will coordinate and assist in conducting integrative analysis of the multiple data types. These efforts will examine key questions in higher-order chromatin organization using both sequence and image data, and the tools and algorithms developed here will be incorporated into the data portal for use by other investigators. These three aims will ensure that the data generated in 4DN will have maximal impact for the scientific community.", "center_title": "DCIC - DCIC", "name": "1U01CA200059-01", "@type": ["Award", "Item"], "project": "4DN", "pi": {"error": "no view permissions"}, "principals_allowed": {"view": ["system.Everyone"], "edit": ["group.admin"]}}, "steps": [{"meta": {"description": "Merging pair files", "software_used": [{"source_url": "https://github.com/4dn-dcic/pairix", "uuid": "9baf9f73-2d59-4eca-a326-340007b2a8b8", "version": "0.3.3", "title": "pairix_0.3.3", "@type": ["Software", "Item"], "name": "pairix", "display_title": "pairix_0.3.3", "@id": "/softwares/9baf9f73-2d59-4eca-a326-340007b2a8b8/", "status": "released", "principals_allowed": {"view": ["system.Everyone"], "edit": ["group.admin"]}}], "analysis_step_types": ["merging"]}, "name": "merge-pairs", "inputs": [{"meta": {"type": "data file", "global": true, "cardinality": "array", "file_format": {"status": "released", "uuid": "d13d06cf-218e-4f61-aaf0-91f226248b2c", "@type": ["FileFormat", "Item"], "@id": "/file-formats/pairs/", "display_title": "pairs", "principals_allowed": {"view": ["system.Everyone"], "edit": ["group.admin"]}}}, "name": "input_pairs", "source": [{"name": "input_pairs"}]}], "outputs": [{"meta": {"type": "data file", "global": true, "cardinality": "single", "file_format": "pairs"}, "name": "merged_pairs", "target": [{"name": "merged_pairs"}, {"name": "input_pairs", "step": "addfragtopairs"}, {"name": "pairs", "step": "cooler"}]}]}, {"meta": {"description": "Adding restriction enzyme site information to the pairs file", "software_used": [{"source_url": "https://github.com/4dn-dcic/pairix", "uuid": "9baf9f73-2d59-4eca-a326-340007b2a8b8", "version": "0.3.3", "title": "pairix_0.3.3", "@type": ["Software", "Item"], "name": "pairix", "display_title": "pairix_0.3.3", "@id": "/softwares/9baf9f73-2d59-4eca-a326-340007b2a8b8/", "status": "released", "principals_allowed": {"view": ["system.Everyone"], "edit": ["group.admin"]}}], "analysis_step_types": ["annotation"]}, "name": "addfragtopairs", "inputs": [{"meta": {"type": "data file", "global": false, "cardinality": "single", "file_format": {"status": "released", "uuid": "d13d06cf-218e-4f61-aaf0-91f226248b2c", "@type": ["FileFormat", "Item"], "@id": "/file-formats/pairs/", "display_title": "pairs", "principals_allowed": {"view": ["system.Everyone"], "edit": ["group.admin"]}}}, "name": "input_pairs", "source": [{"name": "merged_pairs", "step": "merge-pairs"}]}, {"meta": {"type": "reference file", "global": true, "cardinality": "single", "file_format": {"status": "released", "uuid": "d13d06cf-218e-4f61-55f0-94f226248b2c", "@type": ["FileFormat", "Item"], "@id": "/file-formats/juicer_format_restriction_site_file/", "display_title": "juicer_format_restriction_site_file", "principals_allowed": {"view": ["system.Everyone"], "edit": ["group.admin"]}}}, "name": "restriction_file", "source": [{"name": "restriction_file"}]}, {"meta": {"type": "parameter", "global": true, "cardinality": "single"}, "name": "donothing", "source": [{"name": "nofrag"}]}], "outputs": [{"meta": {"type": "data file", "global": false, "cardinality": "single", "file_format": "pairs"}, "name": "pairs_with_frags", "target": [{"name": "input_pairs", "step": "pairs2hic"}]}]}, {"meta": {"description": "Merged Pairs file is processed using Cooler", "software_used": [{"source_url": "https://github.com/mirnylab/cooler", "uuid": "b43e5d6d-f1a6-4713-9b48-8f5c060dad6c", "version": "0.7.6", "title": "cooler_0.7.6", "@type": ["Software", "Item"], "name": "cooler", "display_title": "cooler_0.7.6", "@id": "/softwares/b43e5d6d-f1a6-4713-9b48-8f5c060dad6c/", "status": "released", "principals_allowed": {"view": ["system.Everyone"], "edit": ["group.admin"]}}], "analysis_step_types": ["aggregation"]}, "name": "cooler", "inputs": [{"meta": {"type": "data file", "global": false, "cardinality": "single", "file_format": {"status": "released", "uuid": "d13d06cf-218e-4f61-aaf0-91f226248b2c", "@type": ["FileFormat", "Item"], "@id": "/file-formats/pairs/", "display_title": "pairs", "principals_allowed": {"view": ["system.Everyone"], "edit": ["group.admin"]}}}, "name": "pairs", "source": [{"name": "merged_pairs", "step": "merge-pairs"}]}, {"meta": {"type": "reference file", "global": true, "cardinality": "single", "file_format": {"status": "released", "uuid": "d13d06cf-218e-4f61-55f0-93f226248b2c", "@type": ["FileFormat", "Item"], "@id": "/file-formats/chromsizes/", "display_title": "chromsizes", "principals_allowed": {"view": ["system.Everyone"], "edit": ["group.admin"]}}}, "name": "chrsizes", "source": [{"name": "chromsizes"}]}, {"meta": {"type": "parameter", "global": true, "cardinality": "single"}, "name": "binsize", "source": [{"name": "min_res"}]}, {"meta": {"type": "parameter", "global": true, "cardinality": "single"}, "name": "ncores", "source": [{"name": "nthreads"}]}, {"meta": {"type": "parameter", "global": true, "cardinality": "single"}, "name": "max_split", "source": [{"name": "max_split_cooler"}]}], "outputs": [{"meta": {"type": "data file", "global": false, "cardinality": "single", "file_format": "cool"}, "name": "cool", "target": [{"name": "input_cool", "step": "cool2mcool"}]}]}, {"meta": {"description": "Merged Pairs file is processed using Juicebox", "software_used": [{"source_url": "https://github.com/theaidenlab/juicebox", "uuid": "b0c823f7-ca1e-44fb-b0f6-3eefb19eae46", "version": "1.8.9-cuda8", "title": "juicer_tools_1.8.9-cuda8", "@type": ["Software", "Item"], "name": "juicer_tools", "display_title": "juicer_tools_1.8.9-cuda8", "@id": "/softwares/b0c823f7-ca1e-44fb-b0f6-3eefb19eae46/", "status": "released", "principals_allowed": {"view": ["system.Everyone"], "edit": ["group.admin"]}}], "analysis_step_types": ["aggregation", "normalization"]}, "name": "pairs2hic", "inputs": [{"meta": {"type": "data file", "global": false, "cardinality": "single", "file_format": {"status": "released", "uuid": "d13d06cf-218e-4f61-aaf0-91f226248b2c", "@type": ["FileFormat", "Item"], "@id": "/file-formats/pairs/", "display_title": "pairs", "principals_allowed": {"view": ["system.Everyone"], "edit": ["group.admin"]}}}, "name": "input_pairs", "source": [{"name": "pairs_with_frags", "step": "addfragtopairs"}]}, {"meta": {"type": "reference file", "global": true, "cardinality": "single", "file_format": {"status": "released", "uuid": "d13d06cf-218e-4f61-55f0-93f226248b2c", "@type": ["FileFormat", "Item"], "@id": "/file-formats/chromsizes/", "display_title": "chromsizes", "principals_allowed": {"view": ["system.Everyone"], "edit": ["group.admin"]}}}, "name": "chromsizes", "source": [{"name": "chromsizes"}]}, {"meta": {"type": "parameter", "global": true, "cardinality": "single"}, "name": "min_res", "source": [{"name": "min_res"}]}, {"meta": {"type": "parameter", "global": true, "cardinality": "single"}, "name": "higlass", "source": [{"name": "higlass"}]}, {"meta": {"type": "parameter", "global": true, "cardinality": "single"}, "name": "custom_res", "source": [{"name": "custom_res"}]}, {"meta": {"type": "parameter", "global": true, "cardinality": "single"}, "name": "maxmem", "source": [{"name": "maxmem"}]}, {"meta": {"type": "parameter", "global": true, "cardinality": "single"}, "name": "mapqfilter", "source": [{"name": "mapqfilter_juicer"}]}], "outputs": [{"meta": {"global": true}, "name": "hic", "target": [{"name": "hic"}, {"name": "input_hic", "step": "add-hic-normvector-to-mcool"}]}]}, {"meta": {"description": "Cooler file is converted to mcool", "software_used": [{"source_url": "https://github.com/mirnylab/cooler", "uuid": "b43e5d6d-f1a6-4713-9b48-8f5c060dad6c", "version": "0.7.6", "title": "cooler_0.7.6", "@type": ["Software", "Item"], "name": "cooler", "display_title": "cooler_0.7.6", "@id": "/softwares/b43e5d6d-f1a6-4713-9b48-8f5c060dad6c/", "status": "released", "principals_allowed": {"view": ["system.Everyone"], "edit": ["group.admin"]}}], "analysis_step_types": ["aggregation", "normalization", "file format conversion"]}, "name": "cool2mcool", "inputs": [{"meta": {"type": "data file", "global": false, "cardinality": "single", "file_format": {"status": "released", "uuid": "d13d06cf-218e-4f61-bbf0-91f226248b2c", "@type": ["FileFormat", "Item"], "@id": "/file-formats/cool/", "display_title": "cool", "principals_allowed": {"view": ["system.Everyone"], "edit": ["group.admin"]}}}, "name": "input_cool", "source": [{"name": "cool", "step": "cooler"}]}, {"meta": {"type": "parameter", "global": true, "cardinality": "single"}, "name": "ncores", "source": [{"name": "nthreads"}]}, {"meta": {"type": "parameter", "global": true, "cardinality": "single"}, "name": "chunksize", "source": [{"name": "chunksize"}]}, {"meta": {"type": "parameter", "global": true, "cardinality": "single"}, "name": "juicer_res", "source": [{"name": "juicer_res"}]}, {"meta": {"type": "parameter", "global": true, "cardinality": "single"}, "name": "custom_res", "source": [{"name": "custom_res"}]}], "outputs": [{"meta": {"type": "data file", "global": false, "cardinality": "single", "file_format": "mcool"}, "name": "mcool", "target": [{"name": "input_mcool", "step": "add-hic-normvector-to-mcool"}]}]}, {"meta": {"description": "HiC normalization vector is added to mcooler", "software_used": [{"source_url": "https://github.com/4dn-dcic/hic2cool", "uuid": "c1c772a8-5d1c-4481-8ab7-30729f3f6cb2", "version": "0.4.1", "title": "hic2cool_0.4.1", "@type": ["Software", "Item"], "name": "hic2cool", "display_title": "hic2cool_0.4.1", "@id": "/softwares/c1c772a8-5d1c-4481-8ab7-30729f3f6cb2/", "status": "released", "principals_allowed": {"view": ["system.Everyone"], "edit": ["group.admin"]}}], "analysis_step_types": ["file format conversion"]}, "name": "add-hic-normvector-to-mcool", "inputs": [{"meta": {"type": "data file", "global": false, "cardinality": "single", "file_format": {"status": "released", "uuid": "d13d06cf-218e-4f61-ccf0-91f226248b2c", "@type": ["FileFormat", "Item"], "@id": "/file-formats/mcool/", "display_title": "mcool", "principals_allowed": {"view": ["system.Everyone"], "edit": ["group.admin"]}}}, "name": "input_mcool", "source": [{"name": "mcool", "step": "cool2mcool"}]}, {"meta": {"type": "data file", "global": false, "cardinality": "single", "file_format": {"status": "released", "uuid": "d13d11cf-218e-4f61-bbf0-91f226248b2c", "@type": ["FileFormat", "Item"], "@id": "/file-formats/hic/", "display_title": "hic", "principals_allowed": {"view": ["system.Everyone"], "edit": ["group.admin"]}}}, "name": "input_hic", "source": [{"name": "hic", "step": "pairs2hic"}]}], "outputs": [{"meta": {"type": "data file", "global": true, "cardinality": "single", "file_format": "mcool"}, "name": "mcool_with_hicnorm", "target": [{"name": "mcool"}, {"name": "mcool", "step": "extract-mcool-normvector-for-juicebox"}]}]}, {"meta": {"description": "Extracting HiC normalization vector", "software_used": [{"source_url": "https://github.com/SooLee/mcool2hic", "uuid": "f3907ef2-a9fe-4324-bc54-253a4cd53e3c", "title": "mcool2hic_87a912c", "@type": ["Software", "Item"], "name": "mcool2hic", "commit": "87a912c", "display_title": "mcool2hic_87a912c", "@id": "/softwares/f3907ef2-a9fe-4324-bc54-253a4cd53e3c/", "status": "released", "principals_allowed": {"view": ["system.Everyone"], "edit": ["group.admin"]}}], "analysis_step_types": ["file format conversion"]}, "name": "extract-mcool-normvector-for-juicebox", "inputs": [{"meta": {"type": "parameter", "global": true, "cardinality": "single"}, "name": "custom_res", "source": [{"name": "custom_res"}]}, {"meta": {"type": "reference file", "global": true, "cardinality": "single", "file_format": {"status": "released", "uuid": "d13d06cf-218e-4f61-55f0-93f226248b2c", "@type": ["FileFormat", "Item"], "@id": "/file-formats/chromsizes/", "display_title": "chromsizes", "principals_allowed": {"view": ["system.Everyone"], "edit": ["group.admin"]}}}, "name": "chromsize", "source": [{"name": "chromsizes"}]}, {"meta": {"type": "data file", "global": false, "cardinality": "single", "file_format": {"status": "released", "uuid": "d13d06cf-218e-4f61-ccf0-91f226248b2c", "@type": ["FileFormat", "Item"], "@id": "/file-formats/mcool/", "display_title": "mcool", "principals_allowed": {"view": ["system.Everyone"], "edit": ["group.admin"]}}}, "name": "mcool", "source": [{"name": "mcool_with_hicnorm", "step": "add-hic-normvector-to-mcool"}]}], "outputs": [{"meta": {"type": "data file", "global": true, "cardinality": "single", "file_format": "normvector_juicerformat"}, "name": "cooler_normvector", "target": [{"name": "cooler_normvector"}]}]}], "title": "Generation of multiresolution Hi-C contact matrices from a set of contact lists 0.2.6", "status": "released", "aliases": [], "app_name": "hi-c-processing-pairs", "category": ["processing"], "accession": "4DNWFTKI1QLK", "arguments": [{"argument_type": "Input file", "argument_format": {"status": "released", "@type": ["FileFormat", "Item"], "display_title": "pairs", "file_format": "pairs", "@id": "/file-formats/pairs/", "uuid": "d13d06cf-218e-4f61-aaf0-91f226248b2c", "principals_allowed": {"view": ["system.Everyone"], "edit": ["group.admin"]}}, "workflow_argument_name": "input_pairs"}, {"argument_type": "Input file", "argument_format": {"status": "released", "@type": ["FileFormat", "Item"], "display_title": "chromsizes", "file_format": "chromsizes", "@id": "/file-formats/chromsizes/", "uuid": "d13d06cf-218e-4f61-55f0-93f226248b2c", "principals_allowed": {"view": ["system.Everyone"], "edit": ["group.admin"]}}, "workflow_argument_name": "chromsizes"}, {"argument_type": "Input file", "argument_format": {"status": "released", "@type": ["FileFormat", "Item"], "display_title": "juicer_format_restriction_site_file", "file_format": "juicer_format_restriction_site_file", "@id": "/file-formats/juicer_format_restriction_site_file/", "uuid": "d13d06cf-218e-4f61-55f0-94f226248b2c", "principals_allowed": {"view": ["system.Everyone"], "edit": ["group.admin"]}}, "workflow_argument_name": "restriction_file"}, {"argument_type": "parameter", "workflow_argument_name": "nthreads"}, {"argument_type": "parameter", "workflow_argument_name": "min_res"}, {"argument_type": "parameter", "workflow_argument_name": "maxmem"}, {"argument_type": "parameter", "workflow_argument_name": "higlass"}, {"argument_type": "parameter", "workflow_argument_name": "juicer_res"}, {"argument_type": "parameter", "workflow_argument_name": "custom_res"}, {"argument_type": "parameter", "workflow_argument_name": "nres"}, {"argument_type": "parameter", "workflow_argument_name": "chunksize"}, {"argument_type": "parameter", "workflow_argument_name": "mapqfilter_juicer"}, {"argument_type": "parameter", "workflow_argument_name": "max_split_cooler"}, {"argument_type": "parameter", "workflow_argument_name": "nofrag"}, {"argument_type": "Output processed file", "argument_format": {"status": "released", "@type": ["FileFormat", "Item"], "display_title": "pairs", "file_format": "pairs", "@id": "/file-formats/pairs/", "uuid": "d13d06cf-218e-4f61-aaf0-91f226248b2c", "principals_allowed": {"view": ["system.Everyone"], "edit": ["group.admin"]}}, "secondary_file_formats": [{"@id": "/file-formats/pairs_px2/", "uuid": "d13d06cf-218e-4f61-aaf0-91f226348b2c", "status": "released", "display_title": "pairs_px2", "@type": ["FileFormat", "Item"], "principals_allowed": {"view": ["system.Everyone"], "edit": ["group.admin"]}}], "workflow_argument_name": "merged_pairs"}, {"argument_type": "Output processed file", "argument_format": {"status": "released", "@type": ["FileFormat", "Item"], "display_title": "hic", "file_format": "hic", "@id": "/file-formats/hic/", "uuid": "d13d11cf-218e-4f61-bbf0-91f226248b2c", "principals_allowed": {"view": ["system.Everyone"], "edit": ["group.admin"]}}, "workflow_argument_name": "hic"}, {"argument_type": "Output processed file", "argument_format": {"status": "released", "@type": ["FileFormat", "Item"], "display_title": "mcool", "file_format": "mcool", "@id": "/file-formats/mcool/", "uuid": "d13d06cf-218e-4f61-ccf0-91f226248b2c", "principals_allowed": {"view": ["system.Everyone"], "edit": ["group.admin"]}}, "workflow_argument_name": "mcool"}, {"argument_type": "Output processed file", "argument_format": {"status": "released", "@type": ["FileFormat", "Item"], "display_title": "normvector_juicerformat", "file_format": "normvector_juicerformat", "@id": "/file-formats/normvector_juicerformat/", "uuid": "d13d06cf-218e-4f61-55f0-94f226118b2c", "principals_allowed": {"view": ["system.Everyone"], "edit": ["group.admin"]}}, "workflow_argument_name": "cooler_normvector"}], "app_version": "0.2.6", "description": "This is a subworkflow of the Hi-C data analysis pipeline. It takes pairs files for all replicates of a sample, merges them and then produces multi-resolution Hi-c matrices for visualization. The pipeline produces 4 output files. 1) Replicated merged pairs file 2) Contact matrices in .hic format 3) Multiresolution mcool file and 4) normalization vector of mcool files for visualization in juicebox.", "max_runtime": 200, "date_created": "2018-02-09T15:25:21.781673+00:00", "submitted_by": {"error": "no view permissions"}, "last_modified": {"modified_by": {"error": "no view permissions"}, "date_modified": "2024-07-26T14:55:58.129545+00:00"}, "public_release": "2018-02-14", "schema_version": "7", "project_release": "2018-02-14", "experiment_types": ["Hi-C"], "cwl_directory_url": "https://raw.githubusercontent.com/4dn-dcic/pipelines-cwl/0.2.6/cwl_awsem_v1/", "cwl_main_filename": "hi-c-processing-pairs.cwl", "docker_image_name": "duplexa/4dn-hic:v42", "workflow_language": "CWL", "cwl_child_filenames": ["merge-pairs.cwl", "addfragtopairs.cwl", "cooler.cwl", "pairs2hic.cwl", "cool2mcool.cwl", "add-hic-normvector-to-mcool.cwl", "extract-mcool-normvector-for-juicebox.cwl"], "docker_registry_url": "https://hub.docker.com/", "cwl_directory_url_v1": "https://raw.githubusercontent.com/4dn-dcic/pipelines-cwl/0.2.6/cwl_awsem_v1/", "cwl_directory_url_draft3": "", "@id": "/workflows/4DNWFTKI1QLK/", "@type": ["Workflow", "Item"], "uuid": "c9e0e6f7-b0ed-4a42-9466-cadc2dd84df0", "principals_allowed": {"view": ["system.Everyone"], "edit": ["group.admin"]}, "display_title": "Generation of multiresolution Hi-C contact matrices from a set of contact lists 0.2.6 - 4DNWFTKI1QLK", "external_references": [], "newer_versions": [{"uuid": "23bd6d73-4190-496d-837c-21bcdb3802ed", "@type": ["Workflow", "Item"], "@id": "/workflows/4DNWF2YBHXQM/", "status": "released", "display_title": "Generation of multiresolution Hi-C contact matrices from a set of contact lists 0.2.7 - 4DNWF2YBHXQM", "principals_allowed": {"view": ["system.Everyone"], "edit": ["group.admin"]}}, {"uuid": "612a5081-8f28-4b52-9d4c-7e5b05370950", "@type": ["Workflow", "Item"], "@id": "/workflows/4DNWFMNIBK4F/", "status": "released", "display_title": "Generation of multiresolution Hi-C contact matrices from a set of contact lists 0.3.0 - 4DNWFMNIBK4F", "principals_allowed": {"view": ["system.Everyone"], "edit": ["group.admin"]}}], "@context": "/terms/", "aggregated-items": {}, "validation-errors": []}