tweaks to published files

Author: Rachel Colquhoun

bin/publish_from_config.py

@@ -73,7 +73,7 @@ def get_info_from_config(config_dict, outdir, date, fasta_dict, csv_dict, var_di
 
     if info_dict["fasta"]:
         csv_end = "_metadata.csv"
-        if info_dict["metadata_fields"]:
+        if info_dict["fasta"]=="aligned" or (info_dict["metadata_fields"] and info_dict["fasta"]!="unaligned"):
             info_dict["out_fa"] = "%s_alignment.fa" %start
         else:
             info_dict["out_fa"] = "%s.fa" %start

resources/publish_recipes.json

@@ -3,15 +3,15 @@
     {
       "suffix": "all",
       "data": "cog",
-      "fasta": "unaligned"
+      "fasta": "unaligned",
+      "metadata_fields": ["country","adm1","adm2","outer_postcode","biosample_source_id","central_sample_id","collected_by","collection_date","end_time","flowcell_id","flowcell_type","instrument_make","instrument_model","is_surveillance","layout_insert_length","layout_read_length","library_adaptor_barcode","library_layout_config","library_name","library_primers","library_protocol","library_selection","library_seq_kit","library_seq_protocol","library_source","library_strategy","meta.artic.primers","meta.artic.protocol","meta.epi.cluster","meta.investigation.cluster","meta.investigation.name","meta.investigation.site","metric.ct.1.ct_value","metric.ct.1.test_kit","metric.ct.1.test_platform","metric.ct.1.test_target","metric.ct.2.ct_value","metric.ct.2.test_kit","metric.ct.2.test_platform","metric.ct.2.test_target","metric.ct.max_ct","metric.ct.min_ct","metric.ct.num_tests","published_as","received_date","root_sample_id","run_group","run_name","sample_type_collected","sample_type_received","secondary_accession","secondary_identifier","sequencing_org","sequencing_org_code","sequencing_submission_date","sequencing_uuid","source_age","source_sex","start_time","submission_org","submission_org_code","submission_user","swab_site","header","sequence_name","unmapped_genome_completeness","cov_id","sample_date","why_excluded","epi_week"],
+      "mutations": true,
+      "where": "epi_week=edin_epi_week country=adm0 outer_postcode=adm2_private"
     },
     {
       "suffix": "all",
       "data": "cog",
-      "fasta": "aligned",
-      "metadata_fields": ["country","adm1","adm2","outer_postcode","biosample_source_id","central_sample_id","collected_by","collection_date","end_time","flowcell_id","flowcell_type","instrument_make","instrument_model","is_surveillance","layout_insert_length","layout_read_length","library_adaptor_barcode","library_layout_config","library_name","library_primers","library_protocol","library_selection","library_seq_kit","library_seq_protocol","library_source","library_strategy","meta.artic.primers","meta.artic.protocol","meta.epi.cluster","meta.investigation.cluster","meta.investigation.name","meta.investigation.site","metric.ct.1.ct_value","metric.ct.1.test_kit","metric.ct.1.test_platform","metric.ct.1.test_target","metric.ct.2.ct_value","metric.ct.2.test_kit","metric.ct.2.test_platform","metric.ct.2.test_target","metric.ct.max_ct","metric.ct.min_ct","metric.ct.num_tests","published_as","received_date","root_sample_id","run_group","run_name","sample_type_collected","sample_type_received","secondary_accession","secondary_identifier","sequencing_org","sequencing_org_code","sequencing_submission_date","sequencing_uuid","source_age","source_sex","start_time","submission_org","submission_org_code","submission_user","swab_site","header","sequence_name","length","missing","gaps","cov_id","sample_date","subsample_omit","epi_week"],
-      "mutations": true,
-      "where": "epi_week=edin_epi_week country=adm0 outer_postcode=adm2_private"
+      "fasta": "aligned"
     },
     {
       "fasta": "trimmed",
@@ -30,13 +30,13 @@
       "suffix": "consortium",
       "data": "cog_global",
       "metadata_fields": ["sequence_name","cog_id","gisaid_id","sample_date","epi_week","submission_org_code","root_sample_id","country","adm1","adm2","outer_postcode","adm2_raw","adm2_source","NUTS1","region","latitude","longitude","location","source_age","source_sex","sample_type_collected","sample_type_received","swab_site","ct_n_ct_value","ct_n_test_kit","ct_n_test_platform","ct_n_test_target","pillar_2","is_surveillance","is_travel_history","travel_history","lineage","lineage_support","lineages_version"],
-      "where": "gisaid_id=covv_accession_id cog_id=central_sample_id"
+      "where": "gisaid_id=covv_accession_id cog_id=central_sample_id",
+      "mutations": true
     },
     {
       "suffix": "geography",
       "data": "cog_global",
       "metadata_fields": ["central_sample_id","sequence_name","sample_date","epi_week","country","adm1","adm2","outer_postcode","adm2_raw","adm2_source","NUTS1","region","latitude","longitude","location"],
-      "mutations": true
     },
     {
       "suffix": "mutations",