bugfix release for SC2

nextstrain · Jul 26, 2022 · 8409ef3 · 8409ef3
1 parent 32ddfe4
commit 8409ef3
Show file tree

Hide file tree

Showing 17 changed files with 700,602 additions and 0 deletions.
diff --git a/CHANGELOG.md b/CHANGELOG.md
@@ -1,3 +1,19 @@
+## 2022-07-26
+
+### SARS-CoV-2 and SARS-CoV-2-no-recomb
+
+#### Bug fix release (tag `2022-07-26T12:00:00Z`)
+
+Fix: Ancestral reconstruction of mutations was wrong due to recombinants attaching directly to the root and causing the root mutations to be different from Wuhan.
+
+This caused:
+
+- _displayed_ mutations in Auspice to be wrong for all tips since around the time recombinants were first included in the tree (since `2022-03-24T12:00:00Z`)
+- Some of the _calculated_ reconstructed mutations on _recombinants_ to be wrong, affecting nearest neighbor placement of _some_ recombinants.
+
+The fix will cause a few recombinants to become recombinants and improve QC values of some recombinants but should not have large effects overall.
+The biggest perceived impact will be that mutations displayed by Auspice will now be correct.
+
 ## 2022-07-22
 
 ### SARS-CoV-2 and SARS-CoV-2-no-recomb

diff --git a/.../sars-cov-2-no-recomb/references/MN908947/versions/2022-07-26T12:00:00Z/files/genemap.gff b/.../sars-cov-2-no-recomb/references/MN908947/versions/2022-07-26T12:00:00Z/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
diff --git a/.../sars-cov-2-no-recomb/references/MN908947/versions/2022-07-26T12:00:00Z/files/primers.csv b/.../sars-cov-2-no-recomb/references/MN908947/versions/2022-07-26T12:00:00Z/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
diff --git a/...sets/sars-cov-2-no-recomb/references/MN908947/versions/2022-07-26T12:00:00Z/files/qc.json b/...sets/sars-cov-2-no-recomb/references/MN908947/versions/2022-07-26T12:00:00Z/files/qc.json
@@ -0,0 +1,141 @@
+{
+  "schemaVersion": "1.2.0",
+  "privateMutations": {
+    "enabled": true,
+    "typical": 8,
+    "cutoff": 24,
+    "weightLabeledSubstitutions": 4,
+    "weightReversionSubstitutions": 6,
+    "weightUnlabeledSubstitutions": 1
+  },
+  "missingData": {
+    "enabled": true,
+    "missingDataThreshold": 2700,
+    "scoreBias": 300
+  },
+  "snpClusters": {
+    "enabled": true,
+    "windowSize": 100,
+    "clusterCutOff": 6,
+    "scoreWeight": 50
+  },
+  "mixedSites": {
+    "enabled": true,
+    "mixedSitesThreshold": 10
+  },
+  "frameShifts": {
+    "enabled": true,
+    "ignoredFrameShifts": [
+      { "geneName": "ORF3a", "codonRange": {"begin": 103, "end": 276 } },
+      { "geneName": "ORF3a", "codonRange": {"begin": 256, "end": 276 } },
+      { "geneName": "ORF3a", "codonRange": {"begin": 258, "end": 276 } },
+      { "geneName": "ORF6", "codonRange": {"begin": 21, "end": 62 } },
+      { "geneName": "ORF6", "codonRange": {"begin": 29, "end": 62 } },
+      { "geneName": "ORF6", "codonRange": {"begin": 30, "end": 62 } },
+      { "geneName": "ORF6", "codonRange": {"begin": 33, "end": 62 } },
+      { "geneName": "ORF6", "codonRange": {"begin": 37, "end": 62 } },
+      { "geneName": "ORF6", "codonRange": {"begin": 58, "end": 62 } },
+      { "geneName": "ORF6", "codonRange": {"begin": 61, "end": 62 } },
+      { "geneName": "ORF7a", "codonRange": {"begin": 22, "end": 122 } },
+      { "geneName": "ORF7a", "codonRange": {"begin": 45, "end": 122 } },
+      { "geneName": "ORF7a", "codonRange": {"begin": 53, "end": 122 } },
+      { "geneName": "ORF7a", "codonRange": {"begin": 54, "end": 122 } },
+      { "geneName": "ORF7a", "codonRange": {"begin": 61, "end": 122 } },
+      { "geneName": "ORF7a", "codonRange": {"begin": 62, "end": 122 } },
+      { "geneName": "ORF7a", "codonRange": {"begin": 63, "end": 122 } },
+      { "geneName": "ORF7a", "codonRange": {"begin": 64, "end": 122 } },
+      { "geneName": "ORF7a", "codonRange": {"begin": 65, "end": 122 } },
+      { "geneName": "ORF7a", "codonRange": {"begin": 66, "end": 122 } },
+      { "geneName": "ORF7a", "codonRange": {"begin": 68, "end": 122 } },
+      { "geneName": "ORF7a", "codonRange": {"begin": 71, "end": 122 } },
+      { "geneName": "ORF7a", "codonRange": {"begin": 72, "end": 122 } },
+      { "geneName": "ORF7a", "codonRange": {"begin": 74, "end": 122 } },
+      { "geneName": "ORF7a", "codonRange": {"begin": 75, "end": 122 } },
+      { "geneName": "ORF7a", "codonRange": {"begin": 76, "end": 122 } },
+      { "geneName": "ORF7a", "codonRange": {"begin": 77, "end": 122 } },
+      { "geneName": "ORF7a", "codonRange": {"begin": 78, "end": 122 } },
+      { "geneName": "ORF7a", "codonRange": {"begin": 79, "end": 122 } },
+      { "geneName": "ORF7a", "codonRange": {"begin": 80, "end": 122 } },
+      { "geneName": "ORF7a", "codonRange": {"begin": 81, "end": 122 } },
+      { "geneName": "ORF7a", "codonRange": {"begin": 82, "end": 122 } },
+      { "geneName": "ORF7a", "codonRange": {"begin": 84, "end": 122 } },
+      { "geneName": "ORF7a", "codonRange": {"begin": 86, "end": 122 } },
+      { "geneName": "ORF7a", "codonRange": {"begin": 96, "end": 122 } },
+      { "geneName": "ORF7a", "codonRange": {"begin": 84, "end": 122 } },
+      { "geneName": "ORF7a", "codonRange": {"begin": 100, "end": 122 } },
+      { "geneName": "ORF7a", "codonRange": {"begin": 101, "end": 122 } },
+      { "geneName": "ORF7a", "codonRange": {"begin": 102, "end": 122 } },
+      { "geneName": "ORF7a", "codonRange": {"begin": 103, "end": 122 } },
+      { "geneName": "ORF7a", "codonRange": {"begin": 109, "end": 122 } },
+      { "geneName": "ORF7a", "codonRange": {"begin": 116, "end": 122 } },
+      { "geneName": "ORF7a", "codonRange": {"begin": 120, "end": 122 } },
+      { "geneName": "ORF7b", "codonRange": {"begin": 12, "end": 44 } },
+      { "geneName": "ORF7b", "codonRange": {"begin": 14, "end": 44 } },
+      { "geneName": "ORF7b", "codonRange": {"begin": 15, "end": 44 } },
+      { "geneName": "ORF7b", "codonRange": {"begin": 41, "end": 44 } },
+      { "geneName": "ORF7b", "codonRange": {"begin": 42, "end": 44 } },
+      { "geneName": "ORF8", "codonRange": {"begin": 2, "end": 122 } },
+      { "geneName": "ORF8", "codonRange": {"begin": 4, "end": 122 } },
+      { "geneName": "ORF8", "codonRange": {"begin": 5, "end": 122 } },
+      { "geneName": "ORF8", "codonRange": {"begin": 21, "end": 122 } },
+      { "geneName": "ORF8", "codonRange": {"begin": 58, "end": 122 } },
+      { "geneName": "ORF8", "codonRange": {"begin": 45, "end": 122 } },
+      { "geneName": "ORF8", "codonRange": {"begin": 67, "end": 122 } },
+      { "geneName": "ORF8", "codonRange": {"begin": 107, "end": 122 } },
+      { "geneName": "ORF8", "codonRange": {"begin": 118, "end": 120 } },
+      { "geneName": "ORF8", "codonRange": {"begin": 119, "end": 122 } },
+      { "geneName": "ORF8", "codonRange": {"begin": 120, "end": 122 } },
+      { "geneName": "ORF8", "codonRange": {"begin": 121, "end": 122 } }
+    ]
+  },
+  "stopCodons": {
+    "enabled": true,
+    "ignoredStopCodons": [
+      { "geneName": "ORF3a", "codon": 240 },
+      { "geneName": "ORF3a", "codon": 253 },
+      { "geneName": "ORF3a", "codon": 260 },
+      { "geneName": "ORF3a", "codon": 265 },
+      { "geneName": "ORF6", "codon": 7 },
+      { "geneName": "ORF6", "codon": 53 },
+      { "geneName": "ORF6", "codon": 54 },
+      { "geneName": "ORF6", "codon": 58 },
+      { "geneName": "ORF7a", "codon": 34 },
+      { "geneName": "ORF7a", "codon": 37 },
+      { "geneName": "ORF7a", "codon": 40 },
+      { "geneName": "ORF7a", "codon": 61 },
+      { "geneName": "ORF7a", "codon": 75 },
+      { "geneName": "ORF7a", "codon": 76 },
+      { "geneName": "ORF7a", "codon": 89 },
+      { "geneName": "ORF7a", "codon": 90 },
+      { "geneName": "ORF7a", "codon": 91 },
+      { "geneName": "ORF7a", "codon": 93 },
+      { "geneName": "ORF7a", "codon": 94 },
+      { "geneName": "ORF7a", "codon": 117 },
+      { "geneName": "ORF7a", "codon": 120 },
+      { "geneName": "ORF7b", "codon": 2 },
+      { "geneName": "ORF7b", "codon": 28 },
+      { "geneName": "ORF7b", "codon": 32 },
+      { "geneName": "ORF7b", "codon": 38 },
+      { "geneName": "ORF8", "codon": 7 },
+      { "geneName": "ORF8", "codon": 17 },
+      { "geneName": "ORF8", "codon": 18 },
+      { "geneName": "ORF8", "codon": 22 },
+      { "geneName": "ORF8", "codon": 26 },
+      { "geneName": "ORF8", "codon": 44 },
+      { "geneName": "ORF8", "codon": 49 },
+      { "geneName": "ORF8", "codon": 53 },
+      { "geneName": "ORF8", "codon": 58 },
+      { "geneName": "ORF8", "codon": 63 },
+      { "geneName": "ORF8", "codon": 67 },
+      { "geneName": "ORF8", "codon": 90 },
+      { "geneName": "ORF8", "codon": 94 },
+      { "geneName": "ORF8", "codon": 102 },
+      { "geneName": "ORF8", "codon": 105 },
+      { "geneName": "ORF8", "codon": 109 },
+      { "geneName": "ORF8", "codon": 118 },
+      { "geneName": "ORF8", "codon": 119 },
+      { "geneName": "ORF9b", "codon": 19 },
+      { "geneName": "ORF9b", "codon": 76 }
+    ]
+  }
+}