forked from nextstrain/ncov
-
Notifications
You must be signed in to change notification settings - Fork 0
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
Add normalize_gisaid_fasta.sh for issue nextstrain#53
- Loading branch information
Brian Pardy
committed
Feb 25, 2020
1 parent
b5ef0fc
commit d3c90c7
Showing
1 changed file
with
35 additions
and
0 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,35 @@ | ||
#!/usr/bin/env bash | ||
set -e | ||
GISAID_SARSCOV2_IN=$1 | ||
GISAID_SARSCOV2_OUT=$2 | ||
MIN_LENGTH=$3 | ||
|
||
if [[ ! -r "$GISAID_SARSCOV2_IN" ]] | ||
then | ||
echo "$0: input $GISAID_SARSCOV2_IN not found" | ||
exit 1 | ||
fi | ||
|
||
if [[ -z "$MIN_LENGTH" ]] | ||
then | ||
echo "Using default minimum length of 15000" | ||
MIN_LENGTH=15000 | ||
fi | ||
|
||
echo "Normalizing GISAID file $GISAID_SARSCOV2_IN to $GISAID_SARSCOV2_OUT (min length $MIN_LENGTH)" | ||
|
||
# Remove leading 'BetaCoV' and 'BetaCov' from sequence names | ||
# Remove embedded spaces in sequence names (Hong Kong sequences) | ||
# Remove trailing |EPI_ISL_id|datestamp from sequence names | ||
# Remove sequences shorter than minimum length | ||
# Eliminate duplicate sequences (keep only the first seen) | ||
|
||
cat $GISAID_SARSCOV2_IN | | ||
sed 's/^>BetaCoV\//>/gi' | # remove leading BetaCo[vV] | ||
sed 's/ //g' | # remove embedded spaces | ||
sed 's/|.*$//' | # remove trailing metadata | ||
awk "BEGIN{RS=\">\";FS=\"\n\"}length>$MIN_LENGTH{print \">\"\$0}" | # remove short seqs | ||
awk 'BEGIN{RS=">";FS="\n"}!x[$1]++{print ">"$0}' | # remove duplicates | ||
grep -v '^>*$' > $GISAID_SARSCOV2_OUT | ||
|
||
exit 0 |