Add nextclade workflow [#2]

.gitignore

@@ -3,6 +3,13 @@ ingest/benchmarks
 ingest/data
 ingest/logs
 ingest/results
+nextclade/auspice
+nextclade/benchmarks
+nextclade/data
+nextclade/dataset
+nextclade/logs
+nextclade/results
+nextclade/test_output
 phylogenetic/auspice
 phylogenetic/benchmarks
 phylogenetic/logs

.markdownlintrc

@@ -0,0 +1,9 @@
+{
+  // long lines are okay
+  "MD013":{
+    "line_length": 100,
+    "tables": false
+  },
+  // don't require top-level heading on L1
+  "MD041": false
+}

nextclade/README.md

@@ -0,0 +1,29 @@
+# Yellow Fever Virus Nextclade Dataset Tree
+
+This workflow creates a phylogenetic tree that can be used as part of
+a Nextclade dataset to assign genotypes to yellow fever virus samples
+based on [Mutebi et al.][] (J Virol. 2001 Aug;75(15):6999-7008) and
+[Bryant et al.][] (PLoS Pathog. 2007 May 18;3(5):e75).
+
+* Build a tree using samples from the `ingest` output, with the following
+  sampling criteria:
+  * Force-include the following samples:
+    * genotype reference strains from the 2 papers cited above
+* Assign genotypes to each sample and internal nodes of the tree with
+  `augur clades`, using clade-defining mutations in `defaults/clades.tsv`
+* Provide the following coloring options on the tree:
+  * Genotype assignment from `augur clades`
+
+## How to create a new tree
+
+* Run the workflow: `nextstrain build .`
+* Inspect the output tree by comparing genotype assignments from the following sources:
+  * `augur clades` output
+* If unwanted samples are present in the tree, add them to
+  `defaults/dropped_strains.tsv` and re-run the workflow
+* If any changes are needed to the clade-defining mutations, add
+  changes to `defaults/clades.tsv` and re-run the workflow
+* Repeat as needed
+
+[Mutebi et al.]: https://pubmed.ncbi.nlm.nih.gov/11435580/
+[Bryant et al.]: https://pubmed.ncbi.nlm.nih.gov/17511518/

nextclade/Snakefile

@@ -0,0 +1,30 @@
+configfile: "defaults/config.yaml"
+
+rule all:
+    input:
+        auspice_json = config["files"]["auspice_json"],
+        nextclade_dataset = "dataset/tree.json",
+        test_dataset = "test_output",
+
+include: "rules/prepare_sequences.smk"
+include: "rules/construct_phylogeny.smk"
+include: "rules/annotate_phylogeny.smk"
+include: "rules/export.smk"
+include: "rules/assemble_dataset.smk"
+
+rule clean:
+    params:
+        targets = [
+            ".snakemake",
+            "auspice",
+            "benchmarks",
+            "data",
+            "dataset",
+            "logs",
+            "results",
+            "test_output",
+        ]
+    shell:
+        """
+        rm -rfv {params.targets}
+        """

nextclade/defaults/auspice_config.json

@@ -0,0 +1,56 @@
+{
+  "title": "Real-time tracking of yellow fever virus full genome virus evolution",
+  "maintainers": [
+    {"name": "John SJ Anderson", "url": "https://bedford.io/team/john-sj-anderson/"},
+    {"name": "the Nextstrain team", "url": "https://nextstrain.org/team"}
+  ],
+  "data_provenance": [
+    {
+      "name": "GenBank",
+      "url": "https://www.ncbi.nlm.nih.gov/genbank/"
+    }
+  ],
+  "build_url": "https://github.com/nextstrain/yellow-fever",
+  "colorings": [
+    {
+      "key": "gt",
+      "title": "Genotype",
+      "type": "categorical"
+    },
+    {
+      "key": "num_date",
+      "title": "Date",
+      "type": "continuous"
+    },
+    {
+      "key": "region",
+      "title": "Region",
+      "type": "categorical"
+    },
+    {
+      "key": "country",
+      "title": "Country",
+      "type": "categorical"
+    },
+    {
+      "key": "host",
+      "title": "Host",
+      "type": "categorical"
+    }
+  ],
+  "geo_resolutions": [
+    "country",
+    "region"
+  ],
+  "display_defaults": {
+    "map_triplicate": true,
+    "color_by": "region"
+  },
+  "filters": [
+    "clade",
+    "region",
+    "country",
+    "author",
+    "host"
+  ]
+}

nextclade/defaults/clades.tsv

@@ -0,0 +1,40 @@
+clade	gene	site	alt
+Angola	nuc	72	A
+Angola	nuc	81	G
+Angola	nuc	88	C
+Angola	nuc	90	A
+Angola	nuc	99	T
+Angola	nuc	111	G
+Angola	nuc	219	T
+Angola	nuc	240	C
+Angola	nuc	246	A
+Angola	nuc	252	A
+Angola	nuc	255	A
+Angola	nuc	291	G
+Angola	nuc	294	A
+Angola	nuc	300	A
+Angola	nuc	315	G
+Angola	nuc	327	G
+Angola	nuc	372	A
+Angola	nuc	420	A
+Angola	nuc	432	A
+Angola	nuc	453	T
+Angola	nuc	492	G
+Angola	nuc	651	T
+East Africa	nuc	45	A
+East Africa	nuc	171	G
+East Africa	nuc	438	G
+East Africa	nuc	468	T
+East/Central Africa	nuc	228	G
+West Africa I	nuc	183	G
+West Africa I	nuc	255	C
+West Africa II	nuc	93	T
+West Africa II	nuc	270	A
+West Africa II	nuc	321	T
+West Africa II	nuc	477 	A
+South America I	nuc	219	A
+South America I	nuc	532	A
+South America II	nuc	114	C
+South America II	nuc	193	T
+South America II	nuc	249	A
+South America II	nuc	639	G

nextclade/defaults/colors.tsv

@@ -0,0 +1,8 @@
+# genotypes assigned by augur clades
+clade_membership	Angola	#FCF007
+clade_membership	East Africa	#4B26B1
+clade_membership	East/Central Africa	#E307FC
+clade_membership	West Africa I	#2CFC07
+clade_membership	West Africa II	#9EFC07
+clade_membership	South America I	#996633
+clade_membership	South America II	#FC0740

nextclade/defaults/config.yaml

@@ -0,0 +1,20 @@
+files:
+    auspice_config: "defaults/auspice_config.json"
+    auspice_json: "auspice/tree.json"
+    clades: "defaults/clades.tsv"
+    colors: "defaults/colors.tsv"
+    include: "defaults/include_strains.txt"
+    reference_prM-E_fasta: "defaults/reference.fasta"
+    reference_prM-E_gff: "defaults/genome_annotation.gff3"
+strain_id_field: "accession"
+align_and_extract_prM-E:
+    min_length: 500
+    min_seed_cover: 0.01
+refine:
+    coalescent: "opt"
+    date_inference: "marginal"
+    clock_filter_iqd: 4
+ancestral:
+    inference: "joint"
+export:
+    metadata_columns: "strain division location region year host"

nextclade/defaults/genome_annotation.gff3

@@ -0,0 +1,5 @@
+##sequence-region prM-E 1 672
+NC_002031.1	feature	source	1	672	.	+	.	gene=nuc
+NC_002031.1	feature	gene	1	333	.	+	.	gene_name=prM
+NC_002031.1	feature	gene	109	333	.	+	.	gene_name=M
+NC_002031.1	feature	gene	334	672	.	+	.	gene_name=E

nextclade/defaults/include_strains.txt

@@ -0,0 +1,136 @@
+# Extracted from tables and figures in Mutebi et al. (J Virol. 2001
+# Aug;75(15):6999-7008) and Bryant et al. (PLoS Pathog. 2007 May
+# 18;3(5):e75)
+AF369669
+AF369670
+AF369671
+AY540431
+AY540432
+AY540433
+AY540434
+AY540435
+U52390
+AY540437
+AY540438
+AY540439
+AY540440
+AY540441
+AY540442
+AY540443
+AY540444
+AY540445
+AY540446
+AY540447
+AY540448
+AY540449
+AY540450
+AY540451
+AY540452
+AY540453
+U23570
+AY540454
+AY540455
+AY540456
+AY540457
+AY540458
+AY540459
+AY540460
+AY540461
+AY540462
+AY540463
+AY540464
+AY540465
+AY540466
+AY540467
+AY540468
+AY540469
+AY540470
+AY540471
+AY540472
+AY540473
+AY540436
+U52392
+U52395
+AF369672
+AF369673
+AY540475
+AY540476
+AY540474
+U52399
+AY540477
+AY540478
+AF369674
+AF369675
+AY572535
+AY640589
+AF369686
+U54798
+AY603338
+AF369676
+U52403
+AF369677
+AF369678
+AF368679
+AF369680
+AF369681
+AF369682
+AF369683
+AF369684
+AF369685
+AY540479
+AY540480
+AY161927
+AY161928
+AY161929
+AY161930
+AY161931
+U52411
+AY161933
+AY161934
+AY161935
+U52405
+U52407
+AY161938
+AY161939
+AY161940
+AY161941
+AY161942
+AY161943
+AY161944
+AY161945
+AY161946
+AY161947
+AY161948
+AY161949
+AY161950
+AY161951
+GI694115
+U89338
+AF369687
+AF369688
+U52413
+AF369689
+AF369690
+AF369691
+AF369692
+AF369693
+AY690831
+AY690832
+AY690833
+DQ872411
+DQ872412
+AY540481
+AY540482
+AY540483
+AY540484
+AY540485
+AY540486
+AF369694
+U52422
+AF369695
+AF369696
+AY540487
+AY540488
+AY540489
+AY540490
+AF369697

nextclade/defaults/nextclade-dataset/CHANGELOG.md

@@ -0,0 +1,3 @@
+## Unreleased
+
+Initial release of yellow fever virus dataset.