Some patches to the DB + a bugfix on a date

covigator/pipeline/vcf_loader.py

@@ -190,7 +190,7 @@ def _parse_variant_observation(
             gene_name=covigator_variant.gene_name,
             hgvs_p=covigator_variant.hgvs_p,
             hgvs_c=covigator_variant.hgvs_c,
-            date=sample.first_created,
+            date=sample.collection_date,
             variant_type=covigator_variant.variant_type,
             length=self._get_variant_length(variant),
             reference_amino_acid=covigator_variant.reference_amino_acid,

scripts/sql/20230104_patch_start_end_mutations.sql

@@ -0,0 +1,29 @@
+
+
+
+delete from variant_observation_on where position <= 50;
+delete from variant_on where position <= 50;
+delete from variant_observation_on where position >= 29804;
+delete from variant_on where position >= 29804;
+
+delete from subclonal_variant_observation_on where position <= 50;
+delete from subclonal_variant_on where position <= 50;
+delete from subclonal_variant_observation_on where position >= 29804;
+delete from subclonal_variant_on where position >= 29804;
+
+delete from low_frequency_variant_observation_on where position <= 50;
+delete from low_frequency_variant_on where position <= 50;
+delete from low_frequency_variant_observation_on where position >= 29804;
+delete from low_frequency_variant_on where position >= 29804;
+
+delete from lq_clonal_variant_observation_on where position <= 50;
+delete from lq_clonal_variant_on where position <= 50;
+delete from lq_clonal_variant_observation_on where position >= 29804;
+delete from lq_clonal_variant_on where position >= 29804;
+
+delete from variant_observation_covid19portal_on where position <= 50;
+delete from variant_covid19portal_on where position <= 50;
+delete from variant_observation_covid19portal_on where position >= 29804;
+delete from variant_covid19portal_on where position >= 29804;
+
+

scripts/sql/20230105_path_collection_date_in_variants.sql

@@ -0,0 +1,11 @@
+
+-- The date stored in the variant observations tables need to be patched with the collection date from the corresponding sample.
+
+-- patch ENA dataset
+update variant_observation_on set date=s.collection_date from sample_ena_on as s where s.run_accession = variant_observation_on.sample;
+update subclonal_variant_observation_on set date=s.collection_date from sample_ena_on as s where s.run_accession = subclonal_variant_observation_on.sample;
+update low_frequency_variant_observation_on set date=s.collection_date from sample_ena_on as s where s.run_accession = low_frequency_variant_observation_on.sample;
+update lq_clonal_variant_observation_on set date=s.collection_date from sample_ena_on as s where s.run_accession = lq_clonal_variant_observation_on.sample;
+
+-- patch COVID19 Data Portal dataset
+update variant_observation_covid19portal_on set date=s.collection_date from sample_covid19_portal_on as s where s.run_accession = variant_observation_covid19portal_on.sample;