Merge pull request #141 from tskir/eva-2111-batch-2020-09

EVA-2111 — Changes for batch 2020.09
EBIvariation · Aug 11, 2020 · 681c804 · 681c804
2 parents caeac8c + 9129d7b
commit 681c804
Show file tree

Hide file tree

Showing 12 changed files with 13 additions and 13 deletions.
diff --git a/.gitignore b/.gitignore
@@ -4,8 +4,8 @@
 /eva_cttv_pipeline.egg-info
 /build
 /dist
-/venv
-/venv_3.5
+/env
+/env_3.5
 /eva_cttv_pipeline/evidence_string_generation/resources/schema_local
 .cache
 .eggs

diff --git a/README.md b/README.md
@@ -1,5 +1,5 @@
 [![Build Status](https://travis-ci.com/EBIvariation/eva-opentargets.svg?branch=master)](https://travis-ci.com/EBIvariation/eva-opentargets)
-[![Coverage Status](https://coveralls.io/repos/github/EBIvariation/eva-cttv-pipeline/badge.svg?branch=master)](https://coveralls.io/github/EBIvariation/eva-cttv-pipeline?branch=master)
+[![Coverage Status](https://coveralls.io/repos/github/EBIvariation/eva-opentargets/badge.svg?branch=master)](https://coveralls.io/github/EBIvariation/eva-opentargets?branch=master)
 
 
 

diff --git a/docs/environment.md b/docs/environment.md
@@ -4,7 +4,7 @@ Log in to the LSF cluster, where all data processing must take place. Switch to
 
 Notes:
 * The first five variables are installation-specific and are blanked in this repository. You can get the values for the EVA use case from the [private repository](https://github.com/EBIvariation/configuration/blob/master/open-targets-configuration.md).
-* By modifying the `*REMOTE` and `*BRANCH` variables, you can run arbitrary versions of both the main and the VEP pipeline. This is highly useful for development and debugging. By default it fetches master branches of both repositories.
+* By modifying the `*REMOTE` and `*BRANCH` variables, you can run arbitrary versions of the pipeline. This is highly useful for development and debugging. By default it fetches the master branch from the main pipeline repository.
 * Running these commands will overwrite any local changes you had in the repository copy on the cluster, including any changes to the Java ClinVar XML parser. Be sure to commit and push those before re-running this block of commands.
 
 ```bash

diff --git a/docs/generate-evidence-strings.md b/docs/generate-evidence-strings.md
@@ -20,7 +20,7 @@ export CLINVAR_RELEASE_YEAR=YYYY
 export CLINVAR_RELEASE_MONTH=MM
 
 # Open Targets JSON schema version
-export OT_SCHEMA_VERSION=1.6.7
+export OT_SCHEMA_VERSION=1.7.1
 
 # Open Targets validator schema version
 export OT_VALIDATOR_VERSION=0.6.0
@@ -112,10 +112,10 @@ Update the currently supported version mentioned in this document.
 ### Update the code to reflect the Open Targets schema change
 Open Targets have a [JSON schema](https://github.com/opentargets/json_schema) used to validate submitted data. Validation of generated evidence strings is carried out during generation.
 
-When Open Targets schema version changes, test files in `tests/evidence_string_generation/resources` also need to be updated, as well as all mentions of old schema version throughout the code (use global search for that). The currently supported schema version is **1.6.7.**
+When Open Targets schema version changes, test files in `tests/evidence_string_generation/resources` also need to be updated, as well as all mentions of old schema version throughout the code (use global search for that). The currently supported schema version is **1.7.1.**
 
 ### Check and correct known problematic mappings
-There is a [spreadsheet](https://docs.google.com/spreadsheets/d/1m4ld3y3Pfust5JSOJOX9ZmImRCKRGi-fGYj_dExoGj8/edit) which was created to track trait-to-ontology mappings which were especially problematic in the past to users of Open Targets platform. Prior to running subsequent steps, make sure that all traits mentioned in that spreadsheet are mapped to the correct ontology terms in `${BATCH_ROOT_BASE}/manual_curation/trait_mapping/latest_mappings.tsv`.
+There is a [spreadsheet](https://docs.google.com/spreadsheets/d/1m4ld3y3Pfust5JSOJOX9ZmImRCKRGi-fGYj_dExoGj8/edit) which was created to track trait-to-ontology mappings which were especially problematic in the past to users of Open Targets platform. Prior to running subsequent steps, make sure that all traits mentioned in that spreadsheet are mapped to the correct ontology terms in `${BATCH_ROOT_BASE}/manual_curation/latest_mappings.tsv`.
 
 ## 4. Process data
 Here, we run several steps in sequence:

diff --git a/eva_cttv_pipeline/evidence_string_generation/resources/CTTVGeneticsEvidenceString.json b/eva_cttv_pipeline/evidence_string_generation/resources/CTTVGeneticsEvidenceString.json
@@ -6,7 +6,7 @@
     "type": null,
     "id": []
   },
-  "validated_against_schema_version": "1.6.7",
+  "validated_against_schema_version": "1.7.1",
   "disease": {
     "id": []
   },

diff --git a/eva_cttv_pipeline/evidence_string_generation/resources/CTTVSomaticEvidenceString.json b/eva_cttv_pipeline/evidence_string_generation/resources/CTTVSomaticEvidenceString.json
@@ -2,7 +2,7 @@
   "type": "somatic_mutation",
   "access_level": "public",
   "sourceID": "eva_somatic",
-  "validated_against_schema_version": "1.6.7",
+  "validated_against_schema_version": "1.7.1",
   "disease": {
     "id": []
   },

diff --git a/tests/evidence_string_generation/config.py b/tests/evidence_string_generation/config.py
@@ -4,6 +4,6 @@
 
 snp_2_gene_file = os.path.join(test_dir, 'resources/snp2gene_extract.tsv')
 test_clinvar_record_file = os.path.join(test_dir, 'resources/test_clinvar_record.json')
-open_targets_schema_gz = os.path.join(test_dir, 'resources/opentargets.1.6.7.json.gz')
+open_targets_schema_gz = os.path.join(test_dir, 'resources/opentargets.1.7.1.json.gz')
 expected_genetics_evidence_string = os.path.join(test_dir, 'resources/expected_genetics_evidence_string.json')
 expected_somatic_evidence_string = os.path.join(test_dir, 'resources/expected_somatic_evidence_string.json')
diff --git a/tests/evidence_string_generation/resources/expected_genetics_evidence_string.json b/tests/evidence_string_generation/resources/expected_genetics_evidence_string.json
@@ -123,7 +123,7 @@
     "phenotype": "http://www.orpha.net/ORDO/Orphanet_88991",
     "variant_id": "rs28940313"
   },
-  "validated_against_schema_version": "1.6.7",
+  "validated_against_schema_version": "1.7.1",
   "variant": {
     "id": "http://identifiers.org/dbsnp/rs28940313",
     "type": "snp single"

diff --git a/tests/evidence_string_generation/resources/expected_somatic_evidence_string.json b/tests/evidence_string_generation/resources/expected_somatic_evidence_string.json
@@ -94,5 +94,5 @@
     "phenotype": "http://www.orpha.net/ORDO/Orphanet_88991",
     "variant_id": "rs28940313"
   },
-  "validated_against_schema_version": "1.6.7"
+  "validated_against_schema_version": "1.7.1"
 }
diff --git a/tests/evidence_string_generation/resources/opentargets.1.6.7.json.gz b/tests/evidence_string_generation/resources/opentargets.1.6.7.json.gz
diff --git a/tests/evidence_string_generation/resources/opentargets.1.7.1.json.gz b/tests/evidence_string_generation/resources/opentargets.1.7.1.json.gz
diff --git a/tests/evidence_string_generation/test_evidence_strings.py b/tests/evidence_string_generation/test_evidence_strings.py
@@ -218,7 +218,7 @@ def setUp(self):
         test_args = get_input_data_for_evidence_string_generation()
         self.test_ses = evidence_strings.CTTVSomaticEvidenceString(*test_args)
         ot_schema_path = os.path.join(
-            os.path.dirname(__file__), 'resources', 'opentargets.1.6.7.json.gz')
+            os.path.dirname(__file__), 'resources', 'opentargets.1.7.1.json.gz')
         self.ot_schema_contents = json.loads(gzip.open(ot_schema_path).read().decode('utf-8'))
 
     def test_db_xref_url(self):