-
Notifications
You must be signed in to change notification settings - Fork 5
/
config.yaml
429 lines (429 loc) · 17 KB
/
config.yaml
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
---
config:
gsutil : /snap/bin/gsutil
riot: /usr/share/apache-jena/bin/riot
jq: /usr/bin/jq
java_vm: -Xms4096m -Xmx8192m
manifest:
file_name: "manifest.json"
disease:
etl:
hpo_phenotypes:
uri: http://purl.obolibrary.org/obo/hp/hpoa/phenotype.hpoa
output_filename: hpo-phenotypes.jsonl
path: ontology-inputs
efo:
uri: https://github.com/EBISPOT/efo/releases/download/<EFO_RELEASE_VERSION>/efo_otar_slim.owl
output_filename: ontology-efo.jsonl
path: ontology-inputs
owl_jq: '.["@graph"][] | select (.["@type"] == ("owl:Class","owl:Restriction") and ."@id" != null)|.subClassOf=([.subClassOf]|flatten|del(.[]|nulls))|.hasExactSynonym=([.hasExactSynonym]|flatten|del(.[]|nulls))|.hasDbXref=([.hasDbXref]|flatten|del(.[]|nulls))|.inSubset=([.inSubset]|flatten|del(.[]|nulls))|.hasAlternativeId=([.hasAlternativeId]|flatten|del(.[]|nulls))|@json'
diseases_static_file: diseases_efo.jsonl
url_prefix_mapping:
EFO: http://www.ebi.ac.uk/efo/
OTAR: http://www.ebi.ac.uk/efo/
Orphanet: http://www.orpha.net/ORDO/
url_prefix_mapping_default: http://purl.obolibrary.org/obo/
hpo:
uri: https://raw.githubusercontent.com/obophenotype/human-phenotype-ontology/v2021-10-10/hp.owl
output_filename: ontology-hpo.jsonl
path: ontology-inputs
owl_jq: '.["@graph"][] | select (.["@type"] == "owl:Class") | @json'
mondo:
uri: https://github.com/monarch-initiative/mondo/releases/download/v2021-12-30/mondo.owl
output_filename: ontology-mondo.jsonl
path: ontology-inputs
owl_jq: '.["@graph"][] | @json'
miniset: yes
drug:
http_downloads:
- uri: https://go.drugbank.com/releases/5-1-9/downloads/all-drugbank-vocabulary
path: chembl-inputs
output_filename: 'drugbank_vocabulary.csv'
gs_downloads_latest:
- bucket: otar001-core/DrugBank/annotation
output_filename: drugbank.csv.gz
path: chembl-inputs
etl:
chembl:
type: elasticsearch
url: https://www.ebi.ac.uk/chembl/elk/es
path: chembl-inputs
indices:
chembl-indication:
name: chembl_<CHEMBL_RELEASE_VERSION>_drug_indication
fields:
- '_metadata'
- 'molecule_chembl_id'
- 'efo_id'
- 'max_phase_for_ind'
- 'indication_refs'
chembl-mechanism:
name: chembl_<CHEMBL_RELEASE_VERSION>_mechanism
fields:
- 'molecule_chembl_id'
- 'target_chembl_id'
- 'action_type'
- 'mechanism_of_action'
- 'mechanism_refs'
- 'record_id'
- 'parent_molecule_chembl_id'
- '_metadata'
chembl-molecule:
name: chembl_<CHEMBL_RELEASE_VERSION>_molecule
fields:
- 'molecule_chembl_id'
- 'molecule_hierarchy'
- 'molecule_type'
- 'pref_name'
- 'first_approval'
- 'max_phase'
- 'withdrawn_flag'
- 'black_box_warning'
- 'molecule_synonyms'
- 'cross_references'
- 'chebi_par_id'
- 'molecule_structures'
chembl-target:
name: chembl_<CHEMBL_RELEASE_VERSION>_target
fields:
- '_metadata'
- 'target_chembl_id'
- 'target_components'
- 'target_type'
- 'pref_name'
chembl-drug-warning:
name: chembl_<CHEMBL_RELEASE_VERSION>_drug_warning
fields:
- '_metadata'
- 'molecule_chembl_id'
- 'parent_molecule_chembl_id'
- 'efo_id'
- 'efo_term'
- 'efo_id_for_warning_class'
- 'warning_class'
- 'warning_country'
- 'warning_description'
- 'warning_id'
- 'warning_refs'
- 'warning_type'
- 'warning_year'
miniset: yes
evidence:
gs_downloads_latest:
- bucket: otar000-evidence_input/CancerBiomarkers/json
output_filename: cancerbiomarkers.json.gz
output_spark_dir: cancerbiomarkers
path: evidence-files
- bucket: otar000-evidence_input/Orphanet/json
output_filename: orphanet.json.gz
output_spark_dir: orphanet
path: evidence-files
- bucket: otar000-evidence_input/ClinGen/json
output_filename: clingen.json.gz
output_spark_dir: clingen
path: evidence-files
- bucket: otar000-evidence_input/CRISPR/json
output_filename: crispr.json.gz
output_spark_dir: crispr
path: evidence-files
- bucket: otar006-reactome
output_filename: reactome.json.gz
output_spark_dir: reactome
path: evidence-files
- bucket: otar007-cosmic
output_filename: cosmic.json.gz
output_spark_dir: cosmic
excludes: hallmarks
path: evidence-files
- bucket: otar000-evidence_input/ChEMBL/json
output_filename: chembl.json.gz
output_spark_dir: chembl
path: evidence-files
- bucket: otar000-evidence_input/Genetics_portal/json/
output_filename: genetics-portal-evidences.json.gz
output_spark_dir: genetics-portal-evidences
path: evidence-files
- bucket: otar010-atlas
output_filename: atlas.json.bz2
output_spark_dir: atlas
path: evidence-files
- bucket: otar011-uniprot
output_filename: uniprot.json.gz
output_spark_dir: uniprot
path: evidence-files
- bucket: otar012-eva/disease-target-evidence
output_filename: eva.json.gz
output_spark_dir: eva
path: evidence-files
- bucket: otar000-evidence_input/Gene2Phenotype/json
output_filename: gene2phenotype.json.gz
output_spark_dir: gene2phenotype
path: evidence-files
- bucket: otar000-evidence_input/GenomicsEngland/json
output_filename: genomics_england.json.gz
output_spark_dir: genomics-england
path: evidence-files
- bucket: otar000-evidence_input/IntOgen/json
output_filename: intogen.json.gz
output_spark_dir: intogen
path: evidence-files
- bucket: otar000-evidence_input/IMPC/json
output_filename: impc.json.gz
output_spark_dir: impc
path: evidence-files
- bucket: otar000-evidence_input/Crispr_screens/json
output_filename: crispr_screen.json.gz
output_spark_dir: crispr_screen
path: evidence-files
- bucket: otar000-evidence_input/PROGENy/json
output_filename: progeny.json.gz
output_spark_dir: progeny
path: evidence-files
- bucket: otar000-evidence_input/SLAPEnrich/json
output_filename: slapenrich.json.gz
output_spark_dir: slapenrich
path: evidence-files
- bucket: otar000-evidence_input/SysBio/json
output_filename: sysbio.json.gz
output_spark_dir: sysbio
path: evidence-files
- bucket: otar000-evidence_input/GeneBurden/json
output_filename: gene_burden.json.gz
output_spark_dir: gene_burden
path: evidence-files
expression:
http_downloads:
- uri: https://raw.githubusercontent.com/opentargets/expression_hierarchy/master/process/curation.tsv
output_filename: expression_hierarchy_curation.tsv
path: expression-inputs
gs_downloads_latest:
- bucket: atlas_baseline_expression/baseline_expression_binned
output_filename: baseline_expression_binned.tsv
path: expression-inputs
- bucket: atlas_baseline_expression/baseline_expression_counts
output_filename: baseline_expression_counts.tsv
path: expression-inputs
- bucket: atlas_baseline_expression/baseline_expression_zscore_binned
output_filename: baseline_expression_zscore_binned.tsv
path: expression-inputs
etl:
tissue_translation_map:
uri: https://raw.githubusercontent.com/opentargets/expression_hierarchy/master/process/map_with_efos.json
output_filename: tissue-translation-map.json
path: expression-inputs
normal_tissues:
uri: https://www.proteinatlas.org/download/normal_tissue.tsv.zip
output_filename: normal_tissue.tsv.gz
path: expression-inputs
go:
http_downloads:
- uri: http://purl.obolibrary.org/obo/go.obo
output_filename: go.obo
path: gene-ontology-inputs
homologues:
uri: https://ftp.ensembl.org/pub/release-{release}/json/
path_gene_dictionary: 'gene_dictionary'
uri_homologues: https://ftp.ensembl.org/pub/release-{release}/tsv/ensembl-compara/homologies
path_homologues: 'homologies'
types_homologues:
- 'protein'
- 'ncrna'
path: target-inputs/homologue
release: <ENSEMBL_RELEASE_VERSION>
jq: ".genes[] | [.id, .name] | @tsv"
resources:
- 'caenorhabditis_elegans'
- 'canis_lupus_familiaris'
- 'cavia_porcellus'
- 'danio_rerio'
- 'drosophila_melanogaster'
- 'macaca_mulatta'
- 'mus_musculus'
- 'oryctolagus_cuniculus'
- 'pan_troglodytes'
- 'rattus_norvegicus'
- 'sus_scrofa'
- 'xenopus_tropicalis'
- 'homo_sapiens'
baselineexpression:
gs_downloads_latest:
- bucket: otar000-evidence_input/BaselineExpression/json
output_filename: baseline_expression.json.gz
path: expression-inputs
interactions:
gs_downloads_latest:
- bucket: otar001-core/stringInteractions
output_filename: string-interactions.txt.gz
path: interactions-inputs
ftp_downloads:
- uri: https://ftp.ebi.ac.uk/pub/databases/RNAcentral/current_release/id_mapping/database_mappings/ensembl.tsv
output_filename: rna_central_ensembl.tsv
path: interactions-inputs
- uri : https://ftp.ebi.ac.uk/pub/databases/uniprot/current_release/knowledgebase/idmapping/by_organism/HUMAN_9606_idmapping.dat.gz
output_filename: HUMAN_9606_idmapping.dat.gz
path: interactions-inputs
- uri : https://ftp.ebi.ac.uk/pub/databases/intact/various/ot_graphdb/current/data/interactor_pair_interactions.json
output_filename: intact-interactors.json
path: interactions-inputs
http_downloads:
- uri: https://ftp.ensembl.org/pub/release-<ENSEMBL_RELEASE_VERSION>/gtf/homo_sapiens/Homo_sapiens.GRCh38.<ENSEMBL_RELEASE_VERSION>.chr.gtf.gz
output_filename: Homo_sapiens.GRCh38.chr.gtf.gz
path: interactions-inputs
mousephenotypes:
gs_downloads_latest:
- bucket: otar001-core/MousePhenotypes
output_filename: mouse_phenotypes.json.gz
path: mouse-phenotypes-inputs
pharmacogenomics:
gs_downloads_latest:
- bucket: otar001-core/Pharmacogenetics/json/
output_filename: pharmacogenomics.json.gz
path: pharmacogenomics-inputs
pppevidence:
gs_downloads_latest:
- bucket: otar013-ppp/validation_lab/
output_filename: validation_lab.json.gz
path: evidence-files
- bucket: otar013-ppp/encore/
output_filename: encore.json.gz
path: evidence-files
- bucket: otar013-ppp/ot_crispr/
output_filename: ot_crispr.json.gz
path: evidence-files
openfda:
http_downloads:
- uri: 'https://raw.githubusercontent.com/opentargets/platform-etl-backend/master/src/main/resources/blacklisted_events.txt'
path: fda-inputs
output_filename: 'blacklisted_events.txt'
etl:
downloads:
uri: 'https://api.fda.gov/download.json'
path: fda-inputs
output_filename: 'openfda_file_listing.json'
reactome:
http_downloads:
- uri: https://reactome.org/download/current/ReactomePathways.txt
output_filename: ReactomePathways.txt
path: reactome-inputs
- uri: https://reactome.org/download/current/ReactomePathwaysRelation.txt
output_filename: ReactomePathwaysRelation.txt
path: reactome-inputs
so:
etl:
uri: https://raw.githubusercontent.com/The-Sequence-Ontology/SO-Ontologies/master/Ontology_Files/so.owl
output_filename: ontology-so-{suffix}.json
path: so-inputs
owl_jq: '.["@graph"][] | select (.["@type"] == "owl:Class" and .id != null)|.subClassOf=([.subClassOf]|flatten|del(.[]|nulls))|.hasExactSynonym=([.hasExactSynonym]|flatten|del(.[]|nulls))|.hasDbXref=([.hasDbXref]|flatten|del(.[]|nulls))|.inSubset=([.inSubset]|flatten|del(.[]|nulls))|.hasAlternativeId=([.hasAlternativeId]|flatten|del(.[]|nulls))|@json'
target:
http_downloads:
- uri: https://ftp.ebi.ac.uk/pub/databases/genenames/new/json/hgnc_complete_set.json
output_filename: hgnc_complete_set.json
path: target-inputs/genenames
- uri: https://reactome.org/download/current/Ensembl2Reactome.txt
output_filename: Ensembl2Reactome.txt
path: target-inputs/reactome
- uri: https://ftp.ebi.ac.uk/pub/databases/genenames/hcop/human_all_hcop_sixteen_column.txt.gz
output_filename: human_all_hcop_sixteen_column.txt.gz
path: target-inputs/genenames
- uri: https://cog.sanger.ac.uk/cmp/download/gene_identifiers_latest.csv.gz
output_filename: gene_identifiers_latest.csv.gz
path: target-inputs/project-scores
- uri: https://rest.uniprot.org/uniprotkb/stream?compressed=true&format=txt&query=%28%28reviewed%3Atrue%29%29%20AND%20%28model_organism%3A9606%29
output_filename: uniprot.txt.gz
path: target-inputs/uniprot
- uri: https://rest.uniprot.org/locations/stream?compressed=true&fields=id%2Cname%2Ccategory&format=tsv&query=%28%2A%29
output_filename: uniprot-ssl.tsv.gz
path: target-inputs/uniprot
gs_downloads_latest:
- bucket: otar000-evidence_input/Essentiality/json
output_filename: essentiality.json.gz
path: target-inputs/gene-essentiality
- bucket: otar001-core/subcellularLocations
output_filename: subcellular_locations_ssl.tsv
path: target-inputs/hpa
- bucket: otar007-cosmic
output_filename: cosmic-hallmarks.tsv.gz
path: target-inputs/hallmarks
includes: hallmarks
- bucket: otar001-core/TEPs
output_filename: tep.json.gz
path: target-inputs/tep
- bucket: otar001-core/ChemicalProbes/annotation
output_filename: chemicalprobes.json.gz
path: target-inputs/chemicalprobes
- bucket: otar001-core/TargetSafety/json
output_filename: safetyLiabilities.json.gz
path: target-inputs/safety
- bucket: otar001-core/Tractability
output_filename: tractability.tsv
path: target-inputs/tractability
ftp_downloads:
- uri: https://ftp.ebi.ac.uk/pub/databases/gencode/Gencode_human/release_40/gencode.v40.annotation.gff3.gz
output_filename: gencode.gff3.gz
path: target-inputs/gencode
- uri: https://ftp.ebi.ac.uk/pub/databases/RNAcentral/current_release/id_mapping/database_mappings/ensembl.tsv
output_filename: ensembl.tsv
path: target-inputs/go
- uri: https://ftp.ebi.ac.uk/pub/databases/GO/goa/HUMAN/goa_human.gaf.gz
output_filename: goa_human.gaf.gz
path: target-inputs/go
- uri: https://ftp.ebi.ac.uk/pub/databases/GO/goa/HUMAN/goa_human_rna.gaf.gz
output_filename: goa_human_rna.gaf.gz
path: target-inputs/go
- uri: https://ftp.ebi.ac.uk/pub/databases/GO/goa/HUMAN/goa_human.gpa.gz
output_filename: goa_human_eco.gpa.gz
path: target-inputs/go
- uri: https://ftp.ensembl.org/pub/release-<ENSEMBL_RELEASE_VERSION>/species_EnsemblVertebrates.txt
output_filename: species_EnsemblVertebrates.txt
path: target-inputs/homologue
- uri: https://ftp.ncbi.nlm.nih.gov/gene/DATA/GENE_INFO/Mammalia/Homo_sapiens.gene_info.gz
output_filename: Homo_sapiens.gene_info.gz
path: target-inputs/ncbi
etl:
gnomad:
uri: https://storage.googleapis.com/gcp-public-data--gnomad/release/2.1.1/constraint/gnomad.v2.1.1.lof_metrics.by_gene.txt.bgz
output_filename: gnomad_lof_by_gene.txt.gz
path: target-inputs/gnomad
subcellular_location:
uri: https://www.proteinatlas.org/download/subcellular_location.tsv.zip
output_filename: subcellular_location.tsv.gz
path: target-inputs/hpa
project_scores:
uri: https://cog.sanger.ac.uk/cmp/download/essentiality_matrices.zip
output_filename: essentiality_matrices.zip
path: target-inputs/project-scores
ensembl:
release: <ENSEMBL_RELEASE_VERSION>
uri: https://ftp.ensembl.org/pub/release-{release}/json/homo_sapiens/homo_sapiens.json
output_filename: homo_sapiens.jsonl
path: target-inputs/ensembl
jq: '.genes[] | {id: .id, biotype: .biotype, description: .description, end: .end, start: .start, strand: .strand, chromosome: .seq_region_name, approvedSymbol: .name, transcripts: .transcripts, signalP: .SignalP, uniprot_trembl: ."Uniprot/SPTREMBL", uniprot_swissprot: ."Uniprot/SWISSPROT"}'
miniset: yes
literature:
http_downloads:
- uri: https://ftp.ebi.ac.uk/pub/databases/pmc/DOI/PMID_PMCID_DOI.csv.gz
output_filename: PMID_PMCID_DOI.csv.gz
path: literature-inputs
otar:
resource: otarproject
gs_output_dir: otar-inputs
sheets:
- id_spreadsheet: 1CV_shXJy1ACM09HZBB_-3Nl6l_dfkrA26elMAF0ttHs
worksheet_name: MetaData
output_format: csv
output_filename: otar_meta.csv
- id_spreadsheet: 1CV_shXJy1ACM09HZBB_-3Nl6l_dfkrA26elMAF0ttHs
worksheet_name: Project2Disease
output_format: csv
output_filename: otar_project_to_efo.csv
targetengine:
http_downloads:
- uri: https://www.proteinatlas.org/download/proteinatlas.json.gz
output_filename: proteinatlas.json.gz
path: targetEngine-inputs
- uri: https://rest.uniprot.org/locations/stream?compressed=true&fields=id%2Cname%2Ccategory%2Cgene_ontologies%2Cpart_of%2Cis_a&format=tsv&query=%28%2A%29
output_filename: uniprot_locations.tsv.gz
path: targetEngine-inputs
- uri: https://raw.githubusercontent.com/opentargets/target_engine/main/src/data_flow/phenotypeScores/20230825_mousePheScores.csv
output_filename: mouse_pheno_scores.csv
path: targetEngine-inputs