voc curation release v14.7.0, B.1.620 added

README.md

@@ -196,9 +196,14 @@ Hub-CDB and Institut Pasteur
 <br /><br />
 ## WHAT'S NEW IN
 
+### v14.7.0
+
+1) B.1.620 added
+
+
 ### v14.6.0
 
-1) B.1.617.1, B.1.617.2, B.1.617.2 added
+1) B.1.617.1, B.1.617.2, B.1.617.3 added
 
 
 ### v14.5.0

cnr_curation_voc_qc.config

@@ -35,7 +35,7 @@ res.file.path <- paste0(in.path, "Full_Results.tsv") # single character string i
 
 #### files in the gitlab dataset folder
 
-voc.file.path <- "C:/Users/gael/Documents/Git_projects/cnr_curation/dataset/20210505_voc.txt" # single character string indicating the name of the GATK Variant of Concern (VOC) file. Example: /pasteur/zeus/projets/p01/CNRVIR_bioinfoSEQ/sarscov2mapping/20200128_voc_gatk.txt
+voc.file.path <- "C:/Users/gael/Documents/Git_projects/cnr_curation/dataset/20210511_voc.txt" # single character string indicating the name of the GATK Variant of Concern (VOC) file. Example: /pasteur/zeus/projets/p01/CNRVIR_bioinfoSEQ/sarscov2mapping/20200128_voc_gatk.txt
 critical.file.path <- "C:/Users/gael/Documents/Git_projects/cnr_curation/dataset/20210406_critical_pos.txt" # single character string indicating the name of the critical positions listed. Write NULL if not required. Example: "C:/Users/gael/Documents/Git_projects/cnr_curation/dataset/20210203_voc_gatk_critical_var_present.txt"
 
 #### output folder

dataset/20210505_voc.gmt → dataset/20210511_voc.gmt

@@ -15,3 +15,4 @@ B.1.617.1	B.1.617.1	MN908947_Ampliseq:4906-4916	MN908947_Ampliseq:11142-11152	MN
 B.1.617.2	B.1.617.2	MN908947_Ampliseq:14349-14359	MN908947_Ampliseq:21559-21569	MN908947_Ampliseq:22858-22868	MN908947_Ampliseq:22936-22946	MN908947_Ampliseq:23344-23354	MN908947_Ampliseq:23545-23555	MN908947_Ampliseq:25410-25420	MN908947_Ampliseq:26708-26718	MN908947_Ampliseq:27579-27589	MN908947_Ampliseq:28402-28412	MN908947_Ampliseq:28822-28832	MN908947_Ampliseq:29343-29353
 B.1.617.3	B.1.617.3	MN908947_Ampliseq:7237-7247	MN908947_Ampliseq:8149-8159	MN908947_Ampliseq:10575-10585	MN908947_Ampliseq:11263-11273	MN908947_Ampliseq:21559-21569	MN908947_Ampliseq:22858-22868	MN908947_Ampliseq:22953-22963	MN908947_Ampliseq:23344-23354	MN908947_Ampliseq:23545-23555	MN908947_Ampliseq:27579-27589	MN908947_Ampliseq:27911-27921	MN908947_Ampliseq:28822-28832	MN908947_Ampliseq:29343-29353
 B.1.214.3	B.1.214.3	MN908947_Ampliseq:4398-4408	MN908947_Ampliseq:5848-5858	MN908947_Ampliseq:11228-11247	MN908947_Ampliseq:11371-11381	MN908947_Ampliseq:12253-12263	MN908947_Ampliseq:14349-14359	MN908947_Ampliseq:15128-15138	MN908947_Ampliseq:21787-21797	MN908947_Ampliseq:22936-22946	MN908947_Ampliseq:23344-23354	MN908947_Ampliseq:23650-23660	MN908947_Ampliseq:28828-28838
+B.1.620	B.1.620	MN908947_Ampliseq:1414-1424	MN908947_Ampliseq:3714-3724	MN908947_Ampliseq:6177-6187	MN908947_Ampliseq:11228-11247	MN908947_Ampliseq:14349-14359	MN908947_Ampliseq:17051-17061	MN908947_Ampliseq:21579-21589	MN908947_Ampliseq:21705-21721	MN908947_Ampliseq:21880-21890	MN908947_Ampliseq:21931-21944	MN908947_Ampliseq:22221-22240	MN908947_Ampliseq:22236-22246	MN908947_Ampliseq:22933-22943	MN908947_Ampliseq:22953-22963	MN908947_Ampliseq:23344-23354	MN908947_Ampliseq:23545-23555	MN908947_Ampliseq:24583-24593	MN908947_Ampliseq:24855-24865

dataset/20210505_voc.txt → dataset/20210511_voc.txt

@@ -5,7 +5,7 @@ B.1.1.7	MN908947_Ampliseq	5334	C	A	ORF1ab:A1708D
 B.1.1.7	MN908947_Ampliseq	6900	T	C	ORF1ab:I2230T
 B.1.1.7	MN908947_Ampliseq	11233	GTCTGGTTTT	G	ORF1ab:SGF_3675-3677_del
 B.1.1.7	MN908947_Ampliseq	21710	ATACATG	A	S:HV_69-70_del
-B.1.1.7	MN908947_Ampliseq	21936	TTTA	T	S:Y144_del
+B.1.1.7	MN908947_Ampliseq	21936	ATTA	A	S:Y144_del
 B.1.1.7	MN908947_Ampliseq	23009	A	T	S:N501Y
 B.1.1.7	MN908947_Ampliseq	23217	C	A	S:A570D
 B.1.1.7	MN908947_Ampliseq	23349	A	G	S:D614G
@@ -109,7 +109,7 @@ B.1.616	MN908947_Ampliseq	21023	C	T	ORF1b:T2537I
 B.1.616	MN908947_Ampliseq	21434	A	G	ORF1b:K2674R
 B.1.616	MN908947_Ampliseq	21704	C	G	S:H66D
 B.1.616	MN908947_Ampliseq	21933	G	T	S:G142V
-B.1.616	MN908947_Ampliseq	21936	TTTA	T	S:Y144_del
+B.1.616	MN908947_Ampliseq	21936	ATTA	A	S:Y144_del
 B.1.616	MN908947_Ampliseq	22152	A	G	S:D215G
 B.1.616	MN908947_Ampliseq	22956	T	C	S:V483A
 B.1.616	MN908947_Ampliseq	23349	A	G	S:D614G
@@ -233,4 +233,22 @@ B.1.214.3	MN908947_Ampliseq	22941	C	A	S:T478K
 B.1.214.3	MN908947_Ampliseq	23349	A	G	S:D614G
 B.1.214.3	MN908947_Ampliseq	23655	C	T	S:T716I
 B.1.214.3	MN908947_Ampliseq	28833	C	T	N:T205I
+B.1.620	MN908947_Ampliseq	1419	C	T	ORF1a:T403I
+B.1.620	MN908947_Ampliseq	3719	C	T	ORF1a:R1170C
+B.1.620	MN908947_Ampliseq	6182	G	A	ORF1a:V1991I
+B.1.620	MN908947_Ampliseq	11233	GTCTGGTTTT	G	ORF1ab:SGF_3675-3677_del
+B.1.620	MN908947_Ampliseq	14354	C	T	ORF1b:P314L
+B.1.620	MN908947_Ampliseq	17056	G	T	ORF1b:A1215S
+B.1.620	MN908947_Ampliseq	21584	C	T	S:P26S
+B.1.620	MN908947_Ampliseq	21710	ATACATG	A	S:HV_69-70_del
+B.1.620	MN908947_Ampliseq	21885	T	C	S:V126A
+B.1.620	MN908947_Ampliseq	21936	ATTA	A	S:Y144_del
+B.1.620	MN908947_Ampliseq	22226	ACTTTACTTG	A	S:LLA_241-243_del
+B.1.620	MN908947_Ampliseq	22241	C	T	S:H245Y
+B.1.620	MN908947_Ampliseq	22938	G	A	S:S477N
+B.1.620	MN908947_Ampliseq	22958	G	A	S:E484K
+B.1.620	MN908947_Ampliseq	23349	A	G	S:D614G
+B.1.620	MN908947_Ampliseq	23550	C	A	S:P681H
+B.1.620	MN908947_Ampliseq	24588	C	T	S:T1027I
+B.1.620	MN908947_Ampliseq	24860	G	C	S:D1118H
 

dev/TODO.txt

+1) Consider line full of "" in the Nexclade annot file. This must not be considered as REF
+2) Add Pangolin annot (or replace, even better)
+3) Do not "ToCheck" for new critical if no problem with it
+4) in gmt, solve the fact that in sessions, small shift like if i have to write 27:38 instead of 28:38
\ No newline at end of file

dev/convert.voc_gatk_2_gmt.R

@@ -12,7 +12,7 @@
 
 rm(list = ls())
 
-date <- "20210505"
+date <- "20210511"
 expanse <- 5
 file.in <- "_voc.txt"
 file.out <- "_voc.gmt"