Merge pull request #90 from nextstrain/update-sc2

Update SC2 datasets

CHANGELOG.md

@@ -1,5 +1,116 @@
 # CHANGELOG
 
+## 2023-09-21
+
+### New SARS-CoV-2 dataset version (tag `2023-09-21T12:00:00Z`)
+
+- Add extra example sequences (GL.1, FL.1.5.1, EG.5.1, HV.1, DV.7.1, GK.2, BA.2.86)
+- Add new frame shifts and stop codons to be ignored by QC
+- Pango lineages designated between 2023-08-09 and 2023-09-20 are now included, unfold below to see a list with designation dates:
+
+<details>
+  <summary> Newly included lineages, with designation date in parentheses</summary>
+
+- JA.1 (2023-08-10)
+- JB.1 (2023-08-10)
+- JB.2 (2023-08-10)
+- FW.1.1 (2023-08-22)
+- JC.1 (2023-08-22)
+- XBB.1.41.2 (2023-08-22)
+- GA.4.1 (2023-08-22)
+- GE.1.1 (2023-08-22)
+- GE.1.2 (2023-08-22)
+- XBB.1.5.102 (2023-08-22)
+- JD.1 (2023-08-22)
+- FL.1.5.2 (2023-08-23)
+- JB.2.1 (2023-08-24)
+- HK.6 (2023-08-24)
+- GS.2 (2023-08-24)
+- GS.3 (2023-08-24)
+- GS.4 (2023-08-24)
+- GS.4.1 (2023-08-24)
+- GE.1.3 (2023-08-24)
+- JE.1 (2023-08-24)
+- HG.2 (2023-08-24)
+- JF.1 (2023-08-24)
+- JF.2 (2023-08-24)
+- GK.1.4 (2023-08-24)
+- GK.2.1 (2023-08-24)
+- HK.3.1 (2023-08-24)
+- XCH (2023-08-24)
+- XCJ (2023-08-24)
+- GM.3 (2023-08-24)
+- GM.3.1 (2023-08-24)
+- HC.2 (2023-08-25)
+- EG.5.1.7 (2023-08-25)
+- JD.1.1 (2023-08-25)
+- JD.1.2 (2023-08-25)
+- XBB.1.5.103 (2023-08-30)
+- XCH.1 (2023-08-30)
+- JG.1 (2023-08-30)
+- HK.7 (2023-08-30)
+- EG.2.2 (2023-08-30)
+- EG.2.3 (2023-08-30)
+- EG.2.4 (2023-08-30)
+- EG.2.5 (2023-08-30)
+- EG.13 (2023-08-31)
+- FL.4.8 (2023-08-31)
+- FL.4.9 (2023-08-31)
+- FL.4.10 (2023-08-31)
+- FY.3.2 (2023-08-31)
+- FY.3.3 (2023-08-31)
+- JH.1 (2023-08-31)
+- JH.2 (2023-08-31)
+- FL.2.6 (2023-08-31)
+- XCK (2023-08-31)
+- FL.10.2 (2023-08-31)
+- XCL (2023-09-01)
+- FL.30 (2023-09-01)
+- GW.1.1 (2023-09-01)
+- GK.2.2 (2023-09-01)
+- HF.1.1 (2023-09-01)
+- HF.1.2 (2023-09-01)
+- XBB.1.5.104 (2023-09-01)
+- XBB.1.16.23 (2023-09-01)
+- XBB.1.5.105 (2023-09-01)
+- HK.8 (2023-09-01)
+- HK.9 (2023-09-01)
+- JJ.1 (2023-09-01)
+- HK.10 (2023-09-01)
+- JK.1 (2023-09-01)
+- HS.1.1 (2023-09-01)
+- HK.11 (2023-09-04)
+- JG.2 (2023-09-04)
+- XBB.1.16.24 (2023-09-04)
+- JL.1 (2023-09-04)
+- BA.2.86.1 (2023-09-05)
+- XCM (2023-09-05)
+- FY.4.1.2 (2023-09-06)
+- EG.6.1.1 (2023-09-07)
+- GJ.1.2.2 (2023-09-10)
+- GJ.1.2.3 (2023-09-10)
+- GJ.1.2.4 (2023-09-10)
+- GJ.1.2.5 (2023-09-10)
+- FL.4.11 (2023-09-10)
+- HK.3.2 (2023-09-10)
+- HK.3.3 (2023-09-10)
+- EG.14 (2023-09-10)
+- GK.3.2 (2023-09-10)
+- CK.1.1.2 (2023-09-10)
+- EF.3 (2023-09-10)
+- GW.5.1 (2023-09-11)
+- GW.5.1.1 (2023-09-11)
+- DV.7.1.1 (2023-09-11)
+- DV.7.1.2 (2023-09-11)
+- EG.5.1.8 (2023-09-11)
+- GK.2.3 (2023-09-17)
+- GK.4 (2023-09-17)
+- EG.5.1.9 (2023-09-17)
+- JG.3 (2023-09-17)
+- XBB.1.5.106 (2023-09-17)
+
+</details>
+
 ## 2023-08-22
 
 ### New influenza dataset version (tag `2023-08-10T12:00:00Z`)

data/datasets/sars-cov-2-21L/references/BA.2/versions/2023-09-21T12:00:00Z/files/genemap.gff

@@ -0,0 +1,18 @@
+##gff-version 3
+##sequence-region MN908947 1 29903
+# Gene map (genome annotation) of SARS-CoV-2 in GFF format.
+# For gene map purpses we only need some of the columns. We substitute unused values with "." as per GFF spec.
+# See GFF format reference at https://www.ensembl.org/info/website/upload/gff.html
+# seqname	source	feature	start	end	score	strand	frame	attribute
+MN908947	GenBank	gene	266	13468	.	+	.	gene_name=ORF1a
+MN908947	GenBank	gene	13468	21555	.	+	.	gene_name=ORF1b
+MN908947	GenBank	gene	25393	26220	.	+	.	gene_name=ORF3a
+MN908947	GenBank	gene	21563	25384	.	+	.	gene_name=S
+MN908947	GenBank	gene	26245	26472	.	+	.	gene_name=E
+MN908947	GenBank	gene	26523	27191	.	+	.	gene_name=M
+MN908947	GenBank	gene	27202	27387	.	+	.	gene_name=ORF6
+MN908947	GenBank	gene	27394	27759	.	+	.	gene_name=ORF7a
+MN908947	GenBank	gene	27756	27887	.	+	.	gene_name=ORF7b
+MN908947	GenBank	gene	27894	28259	.	+	.	gene_name=ORF8
+MN908947	GenBank	gene	28274	29533	.	+	.	gene_name=N
+MN908947	GenBank	gene	28284	28577	.	+	.	gene_name=ORF9b

data/datasets/sars-cov-2-21L/references/BA.2/versions/2023-09-21T12:00:00Z/files/primers.csv

@@ -0,0 +1 @@
+Country (Institute),Target,Oligonucleotide,Sequence

data/datasets/sars-cov-2-21L/references/BA.2/versions/2023-09-21T12:00:00Z/files/tag.json

@@ -0,0 +1,25 @@
+{
+  "tag": "2023-09-21T12:00:00Z",
+  "comment": "Update to include lineage BA.2.86",
+  "compatibility": {
+    "nextcladeCli": {
+      "min": "1.10.0",
+      "max": null
+    },
+    "nextcladeWeb": {
+      "min": "1.13.0",
+      "max": null
+    }
+  },
+  "enabled": true,
+  "files": {
+    "geneMap": "genemap.gff",
+    "primers": "primers.csv",
+    "qc": "qc.json",
+    "reference": "reference.fasta",
+    "sequences": "sequences.fasta",
+    "tree": "tree.json",
+    "virusPropertiesJson": "virus_properties.json"
+  },
+  "metadata": {}
+}

data/datasets/sars-cov-2/references/MN908947/versions/2023-09-21T12:00:00Z/files/genemap.gff

@@ -0,0 +1,18 @@
+##gff-version 3
+##sequence-region MN908947 1 29903
+# Gene map (genome annotation) of SARS-CoV-2 in GFF format.
+# For gene map purpses we only need some of the columns. We substitute unused values with "." as per GFF spec.
+# See GFF format reference at https://www.ensembl.org/info/website/upload/gff.html
+# seqname	source	feature	start	end	score	strand	frame	attribute
+MN908947	GenBank	gene	266	13468	.	+	.	gene_name=ORF1a
+MN908947	GenBank	gene	13468	21555	.	+	.	gene_name=ORF1b
+MN908947	GenBank	gene	25393	26220	.	+	.	gene_name=ORF3a
+MN908947	GenBank	gene	21563	25384	.	+	.	gene_name=S
+MN908947	GenBank	gene	26245	26472	.	+	.	gene_name=E
+MN908947	GenBank	gene	26523	27191	.	+	.	gene_name=M
+MN908947	GenBank	gene	27202	27387	.	+	.	gene_name=ORF6
+MN908947	GenBank	gene	27394	27759	.	+	.	gene_name=ORF7a
+MN908947	GenBank	gene	27756	27887	.	+	.	gene_name=ORF7b
+MN908947	GenBank	gene	27894	28259	.	+	.	gene_name=ORF8
+MN908947	GenBank	gene	28274	29533	.	+	.	gene_name=N
+MN908947	GenBank	gene	28284	28577	.	+	.	gene_name=ORF9b

data/datasets/sars-cov-2/references/MN908947/versions/2023-09-21T12:00:00Z/files/primers.csv

@@ -0,0 +1,37 @@
+Country (Institute),Target,Oligonucleotide,Sequence
+Charité (Germany),RdRp,Charité_RdRp_F,GTGARATGGTCATGTGTGGCGG
+Charité (Germany),RdRp,Charité_S_RdRp_P,CAGGTGGAACCTCATCAGGAGATGC
+Charité (Germany),RdRp,Charité_RdRp_R,CARATGTTAAASACACTATTAGCATA
+Charité (Germany),E,Charité_E_F,ACAGGTACGTTAATAGTTAATAGCGT
+Charité (Germany),E,Charité_E_P,ACACTAGCCATCCTTACTGCGCTTCG
+Charité (Germany),E,Charité_E_R,ATATTGCAGCAGTACGCACACA
+Charité (Germany),N,Charité_N_F,CACATTGGCACCCGCAATC
+Charité (Germany),N,Charité_N_P,ACTTCCTCAAGGAACAACATTGCCA
+Charité (Germany),N,Charité_N_R,GAGGAACGAGAAGAGGCTTG
+HKU (Hong Kong),ORF1b-nsp14,HKU_ORF_F,TGGGGYTTTACRGGTAACCT
+HKU (Hong Kong),ORF1b-nsp14,HKU_ORF_P,TAGTTGTGATGCWATCATGACTAG
+HKU (Hong Kong),ORF1b-nsp14,HKU_ORF_R,AACRCGCTTAACAAAGCACTC
+HKU (Hong Kong),N,HKU_N_F,TAATCAGACAAGGAACTGATTA
+HKU (Hong Kong),N,HKU_N_P,GCAAATTGTGCAATTTGCGG
+HKU (Hong Kong),N,HKU_N_R,CGAAGGTGTGACTTCCATG
+China CDC (China),N,ChinaCDC_N_F,GGGGAACTTCTCCTGCTAGAAT
+China CDC (China),N,ChinaCDC_N_P,TTGCTGCTGCTTGACAGATT
+China CDC (China),N,ChinaCDC_N_R,CAGACATTTTGCTCTCAAGCTG
+China CDC (China),ORF1ab-nsp10,ChinaCDC_ORF_F,CCCTGTGGGTTTTACACTTAA
+China CDC (China),ORF1ab-nsp10,ChinaCDC_ORF_P,CCGTCTGCGGTATGTGGAAAGGTTATGG
+China CDC (China),ORF1ab-nsp10,ChinaCDC_ORF_R,ACGATTGTGCATCAGCTGA
+US CDC (United States),N1,USCDC_N1_F,GACCCCAAAATCAGCGAAAT
+US CDC (United States),N1,USCDC_N1_P,ACCCCGCATTACGTTTGGTGGACC
+US CDC (United States),N1,USCDC_N1_R,TCTGGTTACTGCCAGTTGAATCTG
+US CDC (United States),N2,USCDC_N2_F,TTACAAACATTGGCCGCAAA
+US CDC (United States),N2,USCDC_N2_P,ACAATTTGCCCCCAGCGCTTCAG
+US CDC (United States),N2,USCDC_N2_R,GCGCGACATTCCGAAGAA
+US CDC (United States),N3,USCDC_N3_F,GGGAGCCTTGAATACACCAAAA
+US CDC (United States),N3,USCDC_N3_P,AYCACATTGGCACCCGCAATCCTG
+US CDC (United States),N3,USCDC_N3_R,TGTAGCACGATTGCAGCATTG
+"Institut Pasteur, Paris (France)",RdRp,Pasteur_IP2_F,ATGAGCTTAGTCCTGTTG
+"Institut Pasteur, Paris (France)",RdRp,Pasteur_IP2_P,AGATGTCTTGTGCTGCCGGTA
+"Institut Pasteur, Paris (France)",RdRp,Pasteur_IP2_R,CTCCCTTTGTTGTGTTGT
+"Institut Pasteur, Paris (France)",RdRp,Pasteur_IP4_F,GGTAACTGGTATGATTTCG
+"Institut Pasteur, Paris (France)",RdRp,Pasteur_IP4_P,TCATACAAACCACGCCAGG
+"Institut Pasteur, Paris (France)",RdRp,Pasteur_IP4_R,CTGGTCAAGGTTAATATAGG