|
| 1 | +{ |
| 2 | + "bco_id": "https://github.com/biocompute-objects/HIVE_metagenomics/blob/master/HIVE_metagenomics.json", |
| 3 | + "checksum": "ECD541AE0F61AAAAA1FAC14B2B08ABE18F610E1AA4677D54E89B292550F5058A", |
| 4 | + "bco_spec_version" : "https://w3id.org/biocompute/spec/v1.2", |
| 5 | + "provenance_domain": { |
| 6 | + "name": "Healthy human fecal metagenomic diversity", |
| 7 | + "version": "1.0.0", |
| 8 | + "review": [ |
| 9 | + { |
| 10 | + "status": "approved", |
| 11 | + "reviewer_comment": "Approved by GW staff.", |
| 12 | + "reviewer": { |
| 13 | + "name": "Charles Hadley King", |
| 14 | + "affiliation": "George Washington University", |
| 15 | + |
| 16 | + "contribution": ["curatedBy"], |
| 17 | + "orcid": "https://orcid.org/0000-0003-1409-4549" |
| 18 | + } |
| 19 | + } |
| 20 | + ], |
| 21 | + "obsolete_after" : "2118-09-26T14:43:43-0400", |
| 22 | + "embargo" : { |
| 23 | + "start_time": "2000-09-26T14:43:43-0400", |
| 24 | + "end_time": "2000-09-26T14:43:45-0400" |
| 25 | + }, |
| 26 | + "created": "2018-11-29T11:29:08-0500", |
| 27 | + "modified": "2018-11-30T11:29:08-0500", |
| 28 | + "contributors": [ |
| 29 | + { |
| 30 | + "name": "Charles Hadley King", |
| 31 | + "affiliation": "George Washington University", |
| 32 | + |
| 33 | + "contribution": ["createdBy", "curatedBy", "authoredBy"], |
| 34 | + "orcid": "https://orcid.org/0000-0003-1409-4549" |
| 35 | + }, |
| 36 | + { |
| 37 | + "name": "Raja Mazumder", |
| 38 | + "affiliation": "George Washington University", |
| 39 | + |
| 40 | + "contribution": ["createdBy", "curatedBy", "authoredBy"], |
| 41 | + "orcid": "https://orcid.org/0000-0001-88238-9945" |
| 42 | + } |
| 43 | + ], |
| 44 | + "license": "https://spdx.org/licenses/CC-BY-4.0.html" |
| 45 | + }, |
| 46 | + "usability_domain": [ |
| 47 | + "Identify the most common organism present in a human [taxID:9606] fecal [UBERON:0001988] sample, ", |
| 48 | + "Identify the general community composition of organisms in a human [taxID:9606] fecal [UBERON:0001988] sample, ", |
| 49 | + "CensuScope is used to do a census of the composition of the read files. Based on a user-defined threshold, organisms identified are used for alignment in the Hexagon alignment." |
| 50 | + ], |
| 51 | + "extension_domain":{ |
| 52 | + "scm_extension": { |
| 53 | + "scm_repository": "https://github.com/biocompute-objects/HIVE_metagenomics", |
| 54 | + "scm_type": "git", |
| 55 | + "scm_commit": "e4620f642fb20557f6c679397696614305ed07b1", |
| 56 | + "scm_path": "biocompute-objects/HIVE_metagenomics", |
| 57 | + "scm_preview": "https://github.com/example/repo1/blob/c9ffea0b60fa3bcf8e138af7c99ca141a6b8fb21/workflow/hive-viral-mutation-detection.cwl" |
| 58 | + } |
| 59 | + }, |
| 60 | + "description_domain": { |
| 61 | + "keywords": [ |
| 62 | + "metagenome", |
| 63 | + "metagenomic analysis", |
| 64 | + "fecal" |
| 65 | + ], |
| 66 | + "xref": [ |
| 67 | + { |
| 68 | + "namespace": "uberon", |
| 69 | + "name": "Uber Anatomy Ontology", |
| 70 | + "ids": ["0001988"], |
| 71 | + "access_time": "2016-11-30T06:46-0500" |
| 72 | + }, |
| 73 | + { |
| 74 | + "namespace": "taxonomy", |
| 75 | + "name": "Taxonomy", |
| 76 | + "ids": ["9606"], |
| 77 | + "access_time": "2016-11-30T06:46-0500" |
| 78 | + } |
| 79 | + ], |
| 80 | + "platform": ["hive"], |
| 81 | + "pipeline_steps": [ |
| 82 | + { |
| 83 | + "step_number": 1, |
| 84 | + "name": "CensuScope", |
| 85 | + "description": "Detect taxonomic composition of a metagenomic data set.", |
| 86 | + "version": "1.3", |
| 87 | + "prerequisite": [ |
| 88 | + { |
| 89 | + "name": "Filtered_NT_feb18_2016", |
| 90 | + "uri": { |
| 91 | + "uri": "https://hive.biochemistry.gwu.edu/genome/513957", |
| 92 | + "access_time": "2016-11-30T06:46-0500" |
| 93 | + } |
| 94 | + } |
| 95 | + ], |
| 96 | + "input_list": [ |
| 97 | + { |
| 98 | + "uri": "https://hive.biochemistry.gwu.edu/nuc-read/545722", |
| 99 | + "access_time": "2016-11-30T06:46-0500" |
| 100 | + }, |
| 101 | + { |
| 102 | + "uri": "https://hive.biochemistry.gwu.edu/nuc-read/545721", |
| 103 | + "access_time": "2016-11-30T06:46-0500" |
| 104 | + } |
| 105 | + ], |
| 106 | + "output_list": [ |
| 107 | + { |
| 108 | + "uri": "https://hive.biochemistry.gwu.edu/546223/dnaAccessionBasedResult.csv", |
| 109 | + "access_time": "2016-11-30T06:46-0500" |
| 110 | + } |
| 111 | + ] |
| 112 | + }, |
| 113 | + { |
| 114 | + "step_number": 2, |
| 115 | + "name": "HIVE-hexagon", |
| 116 | + "description": "Alignment of reads to a set of references", |
| 117 | + "version": "1.3", |
| 118 | + "input_list": [ |
| 119 | + { |
| 120 | + "uri": "http://example.com/data/546223/dnaAccessionBased.csv", |
| 121 | + "access_time": "2016-11-30T06:46-0500" |
| 122 | + }, |
| 123 | + { |
| 124 | + "uri": "https://hive.biochemistry.gwu.edu/nuc-read/545722", |
| 125 | + "access_time": "2016-11-30T06:46-0500" |
| 126 | + }, |
| 127 | + { |
| 128 | + "uri": "https://hive.biochemistry.gwu.edu/nuc-read/545721", |
| 129 | + "access_time": "2016-11-30T06:46-0500" |
| 130 | + } |
| 131 | + ], |
| 132 | + "output_list": [ |
| 133 | + { |
| 134 | + "uri": "https://hive.biochemistry.gwu.edu/546232/alCount-Unalignedo524569-alCount--1.csv", |
| 135 | + "access_time": "2016-11-30T06:46-0500" |
| 136 | + } |
| 137 | + ] |
| 138 | + } |
| 139 | + ] |
| 140 | + }, |
| 141 | + "execution_domain": { |
| 142 | + "script": [ |
| 143 | + { |
| 144 | + "uri": { |
| 145 | + "uri": "https://github.com/biocompute-objects/HIVE_metagenomics/blob/master/driverHIVEmetagenomic.py" |
| 146 | + } |
| 147 | + } |
| 148 | + ], |
| 149 | + "script_driver": "shell", |
| 150 | + "software_prerequisites": [ |
| 151 | + { |
| 152 | + "name": "CensuScope", |
| 153 | + "version": "albinoni.2", |
| 154 | + "uri": { |
| 155 | + "uri": "http://example.com/dna.cgi?cmd=dna-screening&cmdMode=-", |
| 156 | + "access_time": "2017-01-24T09:40:17-0500" |
| 157 | + } |
| 158 | + }, |
| 159 | + { |
| 160 | + "name": "HIVE-hexagon", |
| 161 | + "version": "babajanian.1", |
| 162 | + "uri": { |
| 163 | + "uri": "http://example.com/dna.cgi?cmd=dna-hexagon&cmdMode=-", |
| 164 | + "access_time": "2017-01-24T09:40:17-0500" |
| 165 | + } |
| 166 | + } |
| 167 | + ], |
| 168 | + "external_data_endpoints": [ |
| 169 | + { |
| 170 | + "name": "HIVE", |
| 171 | + "url": "https://hive.biochemistry.gwu.edu/dna.cgi?cmd=login" |
| 172 | + }, |
| 173 | + { |
| 174 | + "name": "access to e-utils", |
| 175 | + "url": "http://eutils.ncbi.nlm.nih.gov/entrez/eutils/" |
| 176 | + } |
| 177 | + ], |
| 178 | + "environment_variables": { |
| 179 | + "key": "HOSTTYPE", |
| 180 | + "value" : "x86_64-linux" |
| 181 | + } |
| 182 | + }, |
| 183 | + "parametric_domain": [ |
| 184 | + {"param": "seed", "value": "14", "step": "2"}, |
| 185 | + {"param":"minimum_match_len", "value": "66", "step": "2"}, |
| 186 | + {"param": "divergence_threshold_percent", "value": "0.30", "step": "2"}, |
| 187 | + {"param": "minimum_coverage", "value": "15", "step": "2"}, |
| 188 | + {"param": "freq_cutoff", "value": "0.10", "step": "2"} |
| 189 | + ], |
| 190 | + "io_domain": { |
| 191 | + "input_subdomain": [ |
| 192 | + { |
| 193 | + "uri": { |
| 194 | + "filename": "Hepatitis C virus genotype 1", |
| 195 | + "uri": "http://www.ncbi.nlm.nih.gov/nuccore/22129792", |
| 196 | + "access_time": "2017-01-24T09:40:17-0500" |
| 197 | + } |
| 198 | + }, |
| 199 | + { |
| 200 | + "uri": { |
| 201 | + "filename": "Hepatitis C virus type 1b complete genome", |
| 202 | + "uri": "http://www.ncbi.nlm.nih.gov/nuccore/5420376", |
| 203 | + "access_time": "2017-01-24T09:40:17-0500" |
| 204 | + } |
| 205 | + }, |
| 206 | + { |
| 207 | + "uri": { |
| 208 | + "filename": "Hepatitis C virus (isolate JFH-1) genomic RNA", |
| 209 | + "uri": "http://www.ncbi.nlm.nih.gov/nuccore/13122261", |
| 210 | + "access_time": "2017-01-24T09:40:17-0500" |
| 211 | + } |
| 212 | + }, |
| 213 | + { |
| 214 | + "uri": { |
| 215 | + "filename": "Hepatitis C virus clone J8CF, complete genome", |
| 216 | + "uri": "http://www.ncbi.nlm.nih.gov/nuccore/386646758", |
| 217 | + "access_time": "2017-01-24T09:40:17-0500" |
| 218 | + } |
| 219 | + }, |
| 220 | + { |
| 221 | + "uri": { |
| 222 | + "filename": "Hepatitis C virus S52 polyprotein gene", |
| 223 | + "uri": "http://www.ncbi.nlm.nih.gov/nuccore/295311559", |
| 224 | + "access_time": "2017-01-24T09:40:17-0500" |
| 225 | + } |
| 226 | + }, |
| 227 | + { |
| 228 | + "uri": { |
| 229 | + "filename": "HCV1a_drug_resistant_sample0001-01", |
| 230 | + "uri": "http://example.com/nuc-read/514682", |
| 231 | + "access_time": "2017-01-24T09:40:17-0500" |
| 232 | + } |
| 233 | + }, |
| 234 | + { |
| 235 | + |
| 236 | + "uri": { |
| 237 | + "filename": "HCV1a_drug_resistant_sample0001-02", |
| 238 | + "uri": "http://example.com/nuc-read/514683", |
| 239 | + "access_time": "2017-01-24T09:40:17-0500" |
| 240 | + } |
| 241 | + } |
| 242 | + ], |
| 243 | + "output_subdomain": [ |
| 244 | + { |
| 245 | + "mediatype": "text/csv", |
| 246 | + "uri": { |
| 247 | + "uri": "http://example.com/data/514769/dnaAccessionBased.csv", |
| 248 | + "access_time": "2017-01-24T09:40:17-0500" |
| 249 | + } |
| 250 | + }, |
| 251 | + { |
| 252 | + "mediatype": "text/csv", |
| 253 | + "uri": { |
| 254 | + "uri": "http://example.com/data/514801/SNPProfile*.csv", |
| 255 | + "access_time": "2017-01-24T09:40:17-0500" |
| 256 | + } |
| 257 | + } |
| 258 | + ] |
| 259 | + }, |
| 260 | + "error_domain": { |
| 261 | + "empirical_error": { |
| 262 | + "false_negative_alignment_hits": "<0.0010", |
| 263 | + "false_discovery": "<0.05" |
| 264 | + }, |
| 265 | + "algorithmic_error": { |
| 266 | + "false_positive_mutation_calls_discovery": "<0.00005", |
| 267 | + "false_discovery": "0.005" |
| 268 | + } |
| 269 | + } |
| 270 | +} |
0 commit comments