Fix: update dropped strains file to list accession instead of strain names

phylogenetic/config/config_dengue.yaml

@@ -2,7 +2,7 @@ strain_id_field: "accession"
 display_strain_field: "strain"
 
 filter:
-  exclude: "config/dropped_strains.txt"
+  exclude: "config/exclude.txt"
   group_by: "year region"
   min_length: 5000
   sequences_per_group:

phylogenetic/config/exclude.txt

@@ -0,0 +1,50 @@
+# Format: <GenBank accession> [# <strain name> <reason>]
+JF260983 # DENV/SPAIN/EEB17/2009 # sylvatic according to https://www.ncbi.nlm.nih.gov/pmc/articles/PMC3149010/
+HE795086 # DENV1/FRANCE/00475/2008 # 2008/00475
+EF457905 # DENV1/MALAYSIA/P1244/1972 # P72-1244
+GU131762 # DENV1/VIETNAM/BIDV3990/2008 # DENV-1/VN/BID-V3990/2008
+EU482536 # DENV1/VIETNAM/BIDV992/2006 # DENV-1/VN/BID-V992/2006
+KX702403 # DENV2/HAITI/DENGUEVIRUS2HOMOSAPIENS1/2016
+MW946564 # DENV2/SENEGAL/0674/1970 # SENDAK-HD-10674
+DENV2/TRINIDAD_AND_TOBAGO/NA/1953 # Perhaps from https://pubmed.ncbi.nlm.nih.gov/13351628/, but did not search far for the accession
+KY923048 # D2Sab2015 # miscategorized # DENV2/MALAYSIA/SAB/2015
+KX274130 # QML22 # miscategorized # DENV2/AUSTRALIA/QML22/2015
+EF105383 # DAK_Ar_A1247 # sylvatic # DENV2/COTE_D_IVOIRE/DAKARA1247/1980
+EF105382 # Dak_Ar_2039 # sylvatic # DENV2/BURKINA_FASO/DAKAR2039/1980
+EF105380 # Dak_Ar_578 # sylvatic # DENV2/COTE_D_IVOIRE/DAKAR578/1980
+EF105381 # DAK_Ar_510 # sylvatic # DENV2/COTE_D_IVOIRE/DAKAR510/1980
+EF105378 # PM33974 # sylvatic # DENV2/GUINEA/PM33974/1981
+EF105386 # Dak_Ar_A2022 # sylvatic # DENV2/BURKINA_FASO/DAKARA2022/1980
+EF105389 # Dak_Ar_141069 # sylvatic # DENV2/SENEGAL/DAKAR141069/1999
+EF105390 # Dak_Ar_141070 # sylvatic # DENV2/SENEGAL/DAKAR141070/1999
+EF457904 # Dak_Ar_D75505 # sylvatic # DENV2/SENEGAL/DAKARD75505/1999
+EF105384 # Dak_HD_10674 # sylvatic
+EF105385 # Dak_Ar_D20761 # sylvatic # DENV2/SENEGAL/DAKAR0761/1974
+EF105388 # IBH11664 # sylvatic # DENV2/NIGERIA/IBH11664/1966
+EF105387 # IBH11208 # sylvatic # DENV2/NIGERIA/IBH11208/1966
+EU003591 # IBH11234 # sylvatic # DENV2/NIGERIA/IBH11234/1966
+EF105379 # P8_1407 # sylvatic # DENV2/MALAYSIA/P81407/1970
+JF262779 # P75_514 # sylvatic # DENV4/MALAYSIA/P514/1975
+JF262780 # P73_1120 # sylvatic # DENV4/MALAYSIA/P731120/1973
+EF457906 # P75_215 # sylvatic # DENV4/MALAYSIA/P215/1975
+FJ467493 # DKD811 # sylvatic # DENV2/MALAYSIA/DKD811/2008
+EF051521 # ZS01/01 # metadata issue
+MT929160 # Vero # cell line
+MH048676 # MS13002673 # too divergent
+MH048674 # MS11011405 # too divergent
+MT597439 # V43257 # too divergent
+MN448607 # KDC0574A2_06/02/2011 # too divergent
+ON046268 # 00178/03 # too divergent
+ON046278 # 00759/12 # too divergent
+ON046276 # 00988/11 # too divergent
+ON046273 # 01113/10 # too divergent
+ON046270 # 01224/04 # too divergent
+ON046274 # 01231/10 # too divergent
+ON046272 # 01488/09 # too divergent
+ON046271 # 01542/04 # too divergent
+MZ284953 # dev1 # too divergent
+MZ215848 # DKE_121 # too divergent
+MW946564 # SENDAK_HD_10674 # sylvatic
+OK605757 # DENV2_1_DAK_HD_76395 # sylvatic
+MW945427 # DENV3/PUERTORICO/1963/PRS_228762_AC27 # too divergent
+OM258630 # PR_6 # too divergent