Merge pull request #30 from nextstrain/exclude-passaged-strains-29

Exclude passaged strains

ingest/Snakefile

@@ -35,6 +35,7 @@ else:
 rule clean:
     params:
         targets = [
+            ".snakemake",
             "benchmarks",
             "data",
             "logs",

ingest/defaults/229e/annotations.tsv

@@ -19,39 +19,6 @@ KF514432.1	name	229E/human/USA/932-72/1993
 KF514431.1	name	229E/human/USA/953-49/1995
 KF514430.1	name	229E/human/USA/933-50/1993
 KF514429.1	name	229E/human/USA/892-11/1989
-KF293666.1	passage_type	cell#sequences from this experiment are cell-culture escape from K22 antiviral
-KF293665.1	passage_type	cell
-KF293664.1	passage_type	cell
-KF293663.1	passage_type	cell
-KF293662.1	passage_type	cell
-KF285482.1	passage_type	cell
-KF285481.1	passage_type	cell
-KF285480.1	passage_type	cell
-KF285479.1	passage_type	cell
-KF285478.1	passage_type	cell
-KF285477.1	passage_type	cell
-KF285476.1	passage_type	cell
-KF285475.1	passage_type	cell
-KF285474.1	passage_type	cell
-KF285473.1	passage_type	cell
-KF285472.1	passage_type	cell
-KF285471.1	passage_type	cell
-KF285470.1	passage_type	cell
-HH977460.1	passage_type	pharma
-GN352064.1	passage_type	pharma
-GN352063.1	passage_type	pharma
-GN352062.1	passage_type	pharma
-GN352061.1	passage_type	pharma
-GN352060.1	passage_type	pharma
-GN352059.1	passage_type	pharma
-GN352058.1	passage_type	pharma
-GN352057.1	passage_type	pharma
-GN352056.1	passage_type	pharma
-GN352055.1	passage_type	pharma
-GN352054.1	passage_type	pharma
-GN352053.1	passage_type	pharma
-FW337969.1	passage_type	pharma
-FW337968.1	passage_type	pharma
 DQ243976.1	date	1992-06-17
 DQ243975.1	date	1992-05-12
 DQ243974.1	date	1992-06-25
@@ -119,23 +86,6 @@ DQ243943.1	date	1982-10-06
 DQ243942.1	date	1982-06-16
 DQ243941.1	date	1982-09-22
 DQ243940.1	date	1979-06-11
-DL470169.1	passage_type	pharma
-DJ009221.1	passage_type	pharma
-DJ009220.1	passage_type	pharma
-DJ009219.1	passage_type	pharma
-DJ009218.1	passage_type	pharma
-DJ009217.1	passage_type	pharma
-DJ009216.1	passage_type	pharma
-DJ009215.1	passage_type	pharma
-DJ009214.1	passage_type	pharma
-CS123986.1	passage_type	pharma
-CS123984.1	passage_type	pharma
-CS123982.1	passage_type	pharma
-CS123980.1	passage_type	pharma
-CS123978.1	passage_type	pharma
-CS123977.1	passage_type	pharma
-CS123975.1	passage_type	pharma
-CS123973.1	passage_type	pharma
 KF514433.1	country	USA#the following samples have country names like USA: Nashville
 KF514432.1	country	USA
 KF514431.1	country	USA

ingest/defaults/config.yaml

@@ -48,7 +48,6 @@ curate:
     Submitter Names: authors
     Submitter Affiliation: institution
     SRA Accessions: sra_accession
-    passage_type: passage_type
 
   # List of date fields to standardize to ISO format YYYY-MM-DD
   date_fields: ["date"]
@@ -116,7 +115,6 @@ curate:
     - region
     - country
     - host
-    - passage_type
     - sra_accession
     - abbr_authors
     - authors

phylogenetic/Snakefile

@@ -16,6 +16,7 @@ include: "rules/export.smk"
 rule clean:
     params:
         targets = [
+            ".snakemake",
             "auspice",
             "data",
             "logs",

phylogenetic/defaults/229e/dropped_strains.txt

@@ -2,3 +2,53 @@ OK662398.1
 OK625404.1
 MZ712010.1
 PP810610.1 # extreme outlier in tree
+KF293666.1 # excluded because of repeated cell passage under selection
+KF293665.1 # excluded because of repeated cell passage under selection
+KF293664.1 # excluded because of repeated cell passage under selection
+KF293663.1 # excluded because of repeated cell passage under selection
+KF293662.1 # excluded because of repeated cell passage under selection
+KF285482.1 # excluded because of repeated cell passage under selection
+KF285481.1 # excluded because of repeated cell passage under selection
+KF285480.1 # excluded because of repeated cell passage under selection
+KF285479.1 # excluded because of repeated cell passage under selection
+KF285478.1 # excluded because of repeated cell passage under selection
+KF285477.1 # excluded because of repeated cell passage under selection
+KF285476.1 # excluded because of repeated cell passage under selection
+KF285475.1 # excluded because of repeated cell passage under selection
+KF285474.1 # excluded because of repeated cell passage under selection
+KF285473.1 # excluded because of repeated cell passage under selection
+KF285472.1 # excluded because of repeated cell passage under selection
+KF285471.1 # excluded because of repeated cell passage under selection
+KF285470.1 # excluded because of repeated cell passage under selection
+HH977460.1 # excluded because of short sequence length
+GN352064.1 # excluded because of short sequence length
+GN352063.1 # excluded because of short sequence length
+GN352062.1 # excluded because of short sequence length
+GN352061.1 # excluded because of short sequence length
+GN352060.1 # excluded because of short sequence length
+GN352059.1 # excluded because of short sequence length
+GN352058.1 # excluded because of short sequence length
+GN352057.1 # excluded because of short sequence length
+GN352056.1 # excluded because of short sequence length
+GN352055.1 # excluded because of short sequence length
+GN352054.1 # excluded because of short sequence length
+GN352053.1 # excluded because of short sequence length
+FW337969.1 # excluded because of short sequence length
+FW337968.1 # excluded because of short sequence length
+DL470169.1 # excluded because of short sequence length
+DJ009221.1 # excluded because of short sequence length
+DJ009220.1 # excluded because of short sequence length
+DJ009219.1 # excluded because of short sequence length
+DJ009218.1 # excluded because of short sequence length
+DJ009217.1 # excluded because of short sequence length
+DJ009216.1 # excluded because of short sequence length
+DJ009215.1 # excluded because of short sequence length
+DJ009214.1 # excluded because of short sequence length
+CS123986.1 # excluded because of short sequence length
+CS123984.1 # excluded because of short sequence length
+CS123982.1 # excluded because of short sequence length
+CS123980.1 # excluded because of short sequence length
+CS123978.1 # excluded because of short sequence length
+CS123977.1 # excluded because of short sequence length
+CS123975.1 # excluded because of short sequence length
+CS123973.1 # excluded because of short sequence length