Last active
July 8, 2019 20:28
-
-
Save hammer/fb48c68c1a0d15b1f054730a63719c6c to your computer and use it in GitHub Desktop.
Configuration organized by ES index; note that this will not parse correctly! It's for purely pedagogical purposes.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
# [invalid-]evidence-data | |
evidences: | |
gs_output_dir: evidence-files | |
downloads: | |
- bucket: otar000-evidence_input/CRISPR/json | |
output_filename: crispr-{suffix}.json.gz | |
resource: input-file | |
subset_key: | |
- target | |
- id | |
subset_prefix: http://identifiers.org/ensembl/ | |
- bucket: otar006-reactome | |
output_filename: reactome-{suffix}.json.gz | |
resource: input-file | |
subset_key: | |
- target | |
- id | |
subset_prefix: http://identifiers.org/uniprot/ | |
- bucket: otar007-cosmic | |
output_filename: cosmic-{suffix}.json.gz | |
excludes: hallmarks | |
resource: input-file | |
subset_key: | |
- target | |
- id | |
subset_prefix: http://identifiers.org/ensembl/ | |
- bucket: otar008-chembl | |
output_filename: chembl-{suffix}.json.gz | |
resource: input-file | |
subset_key: | |
- target | |
- id | |
subset_prefix: http://identifiers.org/uniprot/ | |
- bucket: otar009-gwas | |
output_filename: gwas-{suffix}.json.gz | |
resource: input-file | |
subset_key: | |
- target | |
- id | |
subset_prefix: http://identifiers.org/ensembl/ | |
- bucket: otar010-atlas | |
output_filename: atlas-{suffix}.json.gz | |
resource: input-file | |
subset_key: | |
- target | |
- id | |
subset_prefix: http://identifiers.org/ensembl/ | |
- bucket: otar011-uniprot | |
output_filename: uniprot-{suffix}.json.gz | |
resource: input-file | |
subset_key: | |
- target | |
- id | |
subset_prefix: http://identifiers.org/uniprot/ | |
- bucket: otar012-eva | |
output_filename: eva-{suffix}.json.gz | |
resource: input-file | |
subset_key: | |
- target | |
- id | |
subset_prefix: http://identifiers.org/ensembl/ | |
- bucket: otar025-epmc | |
output_filename: epmc-{suffix}.json.gz | |
resource: input-file | |
subset_key: | |
- target | |
- id | |
subset_prefix: http://identifiers.org/uniprot/ | |
- bucket: otar000-evidence_input/Gene2Phenotype/json | |
output_filename: gene2phenotype-{suffix}.json.gz | |
resource: input-file | |
subset_key: | |
- target | |
- id | |
subset_prefix: http://identifiers.org/ensembl/ | |
- bucket: otar000-evidence_input/GenomicsEngland/json | |
output_filename: genomics_england-{suffix}.json.gz | |
resource: input-file | |
subset_key: | |
- target | |
- id | |
subset_prefix: http://identifiers.org/ensembl/ | |
- bucket: otar000-evidence_input/IntOgen/json | |
output_filename: intogen-{suffix}.json.gz | |
resource: input-file | |
subset_key: | |
- target | |
- id | |
subset_prefix: http://identifiers.org/ensembl/ | |
- bucket: otar000-evidence_input/PhenoDigm/json | |
output_filename: phenodigm-{suffix}.json.gz | |
resource: input-file | |
subset_key: | |
- target | |
- id | |
subset_prefix: http://identifiers.org/ensembl/ | |
- bucket: otar000-evidence_input/PheWAS/json | |
output_filename: phewas_catalog-{suffix}.json.gz | |
resource: input-file | |
subset_key: | |
- target | |
- id | |
subset_prefix: http://identifiers.org/ensembl/ | |
- bucket: otar000-evidence_input/PROGENy/json | |
output_filename: progeny-{suffix}.json.gz | |
resource: input-file | |
subset_key: | |
- target | |
- id | |
subset_prefix: http://identifiers.org/ensembl/ | |
- bucket: otar000-evidence_input/SLAPEnrich/json | |
output_filename: slapenrich-{suffix}.json.gz | |
resource: input-file | |
subset_key: | |
- target | |
- id | |
subset_prefix: http://identifiers.org/ensembl/ | |
- bucket: otar000-evidence_input/SysBio/json | |
output_filename: sysbio-{suffix}.json.gz | |
resource: input-file | |
subset_key: | |
- target | |
- id | |
subset_prefix: http://identifiers.org/ensembl/ | |
annotations: | |
gs_output_dir: annotation-files | |
downloads: | |
- uri: https://raw.githubusercontent.com/opentargets/data_pipeline/master/mrtarget/resources/eco_scores.tsv | |
output_filename: eco_scores-{suffix}.tsv | |
resource: eco-scores | |
# expression-data | |
- uri: https://raw.githubusercontent.com/opentargets/expression_hierarchy/master/process/map_with_efos.json | |
output_filename: map_with_efos-{suffix}.json | |
resource: tissue-translation-map | |
- uri: https://raw.githubusercontent.com/opentargets/expression_hierarchy/master/process/curation.tsv | |
output_filename: expression_hierarchy_curation-{suffix}.tsv | |
resource: tissue-curation-map | |
- uri: https://www.proteinatlas.org/download/normal_tissue.tsv.zip | |
output_filename: normal_tissue-{suffix}.tsv.zip | |
resource: hpa-normal-tissue | |
- uri: https://storage.googleapis.com/atlas_baseline_expression/expatlas.blueprint2.baseline.binned_v2.tsv | |
output_filename: expatlas.blueprint2.baseline.binned_v2-{suffix}.tsv | |
resource: hpa-rna-level | |
- uri: https://storage.googleapis.com/atlas_baseline_expression/exp_summary_NormCounts_genes_all_Blueprint2_v2.txt | |
output_filename: exp_summary_NormCounts_genes_all_Blueprint2_v2-{suffix}.txt | |
resource: hpa-rna-value | |
- uri: https://storage.googleapis.com/atlas_baseline_expression/expatlas.blueprint2.baseline.z-score.binned_v2.tsv | |
output_filename: expatlas.blueprint2.baseline.z-score.binned_v2-{suffix}.tsv | |
resource: hpa-rna-zscore | |
# efo-data | |
annotations: | |
gs_output_dir: annotation-files | |
downloads: | |
- uri: https://sourceforge.net/p/efo/code/HEAD/tree/trunk/src/efoassociations/ibd_2_pheno_associations.owl?format=raw | |
output_filename: ibd_2_pheno_associations-{suffix}.owl | |
resource: disease-phenotype | |
- uri: https://sourceforge.net/p/efo/code/HEAD/tree/trunk/src/efoassociations/immune_disease_2_pheno.owl?format=raw | |
output_filename: immune_disease_2_pheno-{suffix}.owl | |
resource: disease-phenotype | |
- uri: https://sourceforge.net/p/efo/code/HEAD/tree/trunk/src/efoassociations/rareAlbuminuria_associations_03Jun15.owl?format=raw | |
output_filename: rareAlbuminuria_associations_03Jun15-{suffix}.owl | |
resource: disease-phenotype | |
- uri: https://sourceforge.net/p/efo/code/HEAD/tree/trunk/src/efoassociations/rareIBDpheno.owl?format=raw | |
output_filename: rareIBDpheno-{suffix}.owl | |
resource: disease-phenotype | |
- uri: https://sourceforge.net/p/efo/code/HEAD/tree/trunk/src/efoassociations/ordo_hpo_mappings.owl?format=raw | |
output_filename: ordo_hpo_mappings-{suffix}.owl | |
resource: disease-phenotype | |
- uri: https://sourceforge.net/p/efo/code/HEAD/tree/trunk/src/efoassociations/charite_HP_ORDO_07Oct15.owl?format=raw | |
output_filename: charite_HP_ORDO_07Oct15-{suffix}.owl | |
resource: disease-phenotype | |
# gene-data Plugin: Safety | |
known_target_safety: | |
output_filename: known_target_safety-{suffix}.json | |
resource: safety | |
gs_output_dir: annotation-files | |
spreadsheets: | |
- gkey: 1EvpcnUkDASUNoBU5PzQPGD5YtZxh7cgotr2MqClJ7t0 | |
gid: 1760619926 | |
output_filename: adverse_effects.tsv | |
s_type: adr | |
- gkey: 1EvpcnUkDASUNoBU5PzQPGD5YtZxh7cgotr2MqClJ7t0 | |
gid: 650742396 | |
output_filename: safety_risk_information.tsv | |
s_type: sri | |
- gkey: 1EvpcnUkDASUNoBU5PzQPGD5YtZxh7cgotr2MqClJ7t0 | |
gid: 1774810192 | |
output_filename: UBERON_mapping.tsv | |
s_type: ubr | |
- gkey: 1EvpcnUkDASUNoBU5PzQPGD5YtZxh7cgotr2MqClJ7t0 | |
gid: 1717378859 | |
output_filename: EFO_mapping.tsv | |
s_type: efo | |
- gkey: 1EvpcnUkDASUNoBU5PzQPGD5YtZxh7cgotr2MqClJ7t0 | |
gid: 1223815020 | |
output_filename: references.tsv | |
s_type: ref | |
# gene-data Plugin: Tractability | |
annotations_from_buckets: | |
gs_output_dir: annotation-files | |
downloads: | |
- bucket: otar001-core/Tractability | |
output_filename: tractability_buckets-{suffix}.tsv | |
resource: tractability | |
# gene-data Plugin: ChemicalProbes | |
chemical_probes: | |
output_filename: chemicalprobes_portalprobes-{suffix}.tsv | |
resource: chemical-probes-1 | |
gs_output_dir: annotation-files | |
spreadsheets: | |
- gkey: 1VL3eHGpvJMaQ7LYp0Kp1plEo-NueP3CT7FUCrW0p2dg | |
gid: 1686598114 | |
output_filename: chemical_probes_SGC.tsv | |
cp_type: sgc | |
- gkey: 1VL3eHGpvJMaQ7LYp0Kp1plEo-NueP3CT7FUCrW0p2dg | |
gid: 1636863333 | |
output_filename: chemical_probes_portal.tsv | |
cp_type: cpp | |
- gkey: 1VL3eHGpvJMaQ7LYp0Kp1plEo-NueP3CT7FUCrW0p2dg | |
gid: 349856989 | |
output_filename: open_science_probes.tsv | |
cp_type: osp | |
annotations_from_buckets: | |
gs_output_dir: annotation-files | |
downloads: | |
- bucket: otar001-core/ProbeMiner/annotation | |
output_filename: chemicalprobes_probeminer-{suffix}.tsv | |
resource: chemical-probes-2 | |
# gene-data Plugin: CancerBiomarkers | |
annotations_from_buckets: | |
gs_output_dir: annotation-files | |
downloads: | |
- bucket: otar001-core/CancerBiomarkers/annotation | |
output_filename: cancerbiomarkers-{suffix}.tsv | |
resource: biomarker | |
# gene-data Plugin: Hallmarks | |
annotations_from_buckets: | |
gs_output_dir: annotation-files | |
downloads: | |
- bucket: otar007-cosmic | |
output_filename: cosmic-hallmarks-{suffix}.tsv.gz | |
resource: hallmark | |
includes: hallmarks | |
# gene-data Plugin: MousePhenotypes | |
annotations: | |
gs_output_dir: annotation-files | |
downloads: | |
- uri: http://www.informatics.jax.org/downloads/reports/HMD_HumanPhenotype.rpt | |
output_filename: HMD_HumanPhenotype-{suffix}.rpt | |
resource: mouse-phenotypes-orthology | |
- uri: http://www.informatics.jax.org/downloads/reports/MGI_PhenoGenoMP.rpt | |
output_filename: MGI_PhenoGenoMP-{suffix}.rpt | |
resource: mouse-phenotypes-report | |
# drug-data | |
# gene-data Plugin: ChEMBL | |
ChEMBL: | |
gs_output_dir: annotation-files | |
downloads: | |
drug: | |
uri: https://www.ebi.ac.uk/chembl/api/data/drug_indication.json | |
output_filename: chembl_drug_indication_rest_api-{suffix}.json | |
resource: chembl-drug-indication | |
molecule: | |
uri: https://www.ebi.ac.uk/chembl/api/data/molecule.json | |
output_filename: chembl_molecule_rest_api-{suffix}.json | |
resource: chembl-molecule | |
target: | |
uri: https://www.ebi.ac.uk/chembl/api/data/target.json | |
output_filename: chembl_target_rest_api-{suffix}.json | |
resource: chembl-target | |
mechanism: | |
uri: https://www.ebi.ac.uk/chembl/api/data/mechanism.json | |
output_filename: chembl_mechanism_rest_api-{suffix}.json | |
resource: chembl-mechanism | |
target_component: | |
uri: https://www.ebi.ac.uk/chembl/api/data/target_component.json | |
output_filename: chembl_target_component_rest_api-{suffix}.json | |
resource: chembl-component | |
protein_class: | |
uri: https://www.ebi.ac.uk/chembl/api/data/protein_class.json | |
output_filename: chembl_protein_class_rest_api-{suffix}.json | |
resource: chembl-protein | |
# gene-data Plugin: Orthologs | |
annotations: | |
gs_output_dir: annotation-files | |
downloads: | |
- uri: http://ftp.ebi.ac.uk/pub/databases/genenames/hcop/human_all_hcop_sixteen_column.txt.gz | |
output_filename: human_all_hcop_sixteen_column-{suffix}.txt.gz | |
resource: hgnc-orthologs | |
# gene-data Plugin: HGNC | |
annotations: | |
gs_output_dir: annotation-files | |
downloads: | |
- uri: http://ftp.ebi.ac.uk/pub/databases/genenames/new/json/hgnc_complete_set.json | |
output_filename: hgnc_complete_set-{suffix}.json | |
resource: hgnc-complete-set | |
# reactome-data | |
annotations: | |
gs_output_dir: annotation-files | |
downloads: | |
- uri: https://www.reactome.org/download/current/ReactomePathways.txt | |
output_filename: ReactomePathways-{suffix}.txt | |
resource: reactome-pathway-data | |
- uri: https://www.reactome.org/download/current/ReactomePathwaysRelation.txt | |
output_filename: ReactomePathwaysRelation-{suffix}.txt | |
resource: reactome-pathway-relation | |
# uniprot-data | |
annotations: | |
gs_output_dir: annotation-files | |
downloads: | |
- uri: https://www.uniprot.org/uniprot/?query=reviewed%3Ayes%2BAND%2Borganism%3A9606&compress=yes&format=xml | |
output_filename: uniprot-{suffix}.xml.gz | |
resource: uniprot-uri | |
# ensembl-data | |
ensembl: | |
resource: ensembl-filename | |
conda_env: backend-genetics | |
conda_create: bash -c "~/anaconda2/bin/conda env create -f {root_dir}/scripts/ensembl/environment.yaml" | |
python_script: python {script_path}/create_genes_dictionary.py -o {ensembl_output_dir}/. | |
-e -z -n | |
ensembl_release: homo_sapiens_core_96_38 | |
extension_file: _genes.json.gz | |
gs_output_dir: annotation-files |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment