Update build to work with ViPR data

nextstrain · Aug 16, 2019 · 081f9f8 · 081f9f8
1 parent ab70cbd
commit 081f9f8
Show file tree

Hide file tree

Showing 4 changed files with 48 additions and 15 deletions.
diff --git a/README.md b/README.md
@@ -54,6 +54,11 @@ example sequences into the `data/` directory like so:
     mkdir -p data/
     cp example_data/dengue* data/
 
+## AWS
+
+With access to AWS, this can be more quickly run as:
+
+    nextstrain build --aws-batch --aws-batch-cpus 4 --aws-batch-memory 7200 . --jobs 4
 
 [Nextstrain]: https://nextstrain.org
 [fauna]: https://github.com/nextstrain/fauna

diff --git a/Snakefile b/Snakefile
@@ -13,23 +13,23 @@ rule files:
 
 files = rules.files.params
 
-def download_serotype_integer(w):
-    serotype_integer = {
+def download_serotype(w):
+    serotype = {
         'all': 'all',
-        'denv1': '1',
-        'denv2': '2',
-        'denv3': '3',
-        'denv4': '4'
+        'denv1': 'Dengue_virus_1',
+        'denv2': 'Dengue_virus_2',
+        'denv3': 'Dengue_virus_3',
+        'denv4': 'Dengue_virus_4'
     }
-    return serotype_integer[w.serotype]
+    return serotype[w.serotype]
 
 def filter_sequences_per_group(w):
     sequences_per_group = {
         'all': '10',
-        'denv1': '30',
-        'denv2': '30',
-        'denv3': '30',
-        'denv4': '30'
+        'denv1': '36',
+        'denv2': '36',
+        'denv3': '36',
+        'denv4': '36'
     }
     return sequences_per_group[w.serotype]
 
@@ -59,7 +59,7 @@ rule download:
         sequences = "data/dengue_{serotype}.fasta"
     params:
         fasta_fields = "strain virus accession collection_date region country division location source locus authors url title journal puburl",
-        serotype_integer = download_serotype_integer
+        download_serotype = download_serotype
     run:
         if wildcards.serotype == 'all':
             shell("""
@@ -76,7 +76,7 @@ rule download:
                     --database vdb \
                     --virus dengue \
                     --fasta_fields {params.fasta_fields} \
-                    --select serotype:{params.serotype_integer} \
+                    --select serotype:{params.download_serotype} \
                     --path $(dirname {output.sequences}) \
                     --fstem $(basename {output.sequences} .fasta)
             """)
@@ -150,7 +150,7 @@ rule align:
             --output {output.alignment} \
             --fill-gaps \
             --remove-reference \
-            --nthreads auto
+            --nthreads 1
         """
 
 rule tree:
@@ -164,7 +164,7 @@ rule tree:
         augur tree \
             --alignment {input.alignment} \
             --output {output.tree} \
-            --nthreads auto
+            --nthreads 1
         """
 
 rule refine:

diff --git a/config/clades_genotypes.tsv b/config/clades_genotypes.tsv
@@ -10,10 +10,16 @@ DENV1/IV	E	339	S
 DENV1/IV	M	72	E
 DENV1/IV	E	88	T
 DENV1/V	NS1	324	R
+DENV1/V	NS2A	142	P
+DENV1/V	NS3	185	K
 DENV1/V	NS5	834	E
 DENV2/AM	E	71	D
 DENV2/AM	E	81	T
 DENV2/AM	E	129	I
+DENV2/AM	NS1	21	V
+DENV2/AM	NS1	73	S
+DENV2/AM	NS1	99	V
+DENV2/AM	NS1	170	R
 DENV2/AA	E	491	A
 DENV2/AA	M	15	G
 DENV2/AA	M	39	I

diff --git a/config/dropped_strains.txt b/config/dropped_strains.txt
@@ -26,3 +26,25 @@ DENV2/TRINIDAD_AND_TOBAGO/NA/1953
 DENV4/MALAYSIA/P215/1975
 DENV4/MALAYSIA/P514/1975
 DENV4/MALAYSIA/P731120/1973
+D2Sab2015 # miscategorized
+QML22 # miscategorized
+DAK_Ar_A1247 # sylvatic
+Dak_Ar_2039 # sylvatic
+Dak_Ar_578 # sylvatic
+DAK_Ar_510 # sylvatic
+PM33974 # sylvatic
+Dak_Ar_A2022 # sylvatic
+Dak_Ar_141069 # sylvatic
+Dak_Ar_141070 # sylvatic
+Dak_Ar_D75505 # sylvatic
+Dak_HD_10674 # sylvatic
+Dak_Ar_D20761 # sylvatic
+IBH11664 # sylvatic
+IBH11208 # sylvatic
+IBH11234 # sylvatic
+P8_1407 # sylvatic
+P75_514 # sylvatic
+P73_1120 # sylvatic
+P75_215 # sylvatic
+DKD811 # sylvatic
+ZS01/01 # metadata issue