If proteins are looked for without stop adds an extra option

PASS1_LOOK_FOR_PSEUDO allowing for searching with stop in a second time
(Pseudogene search).

The PASS1_ALLOW_STOP is set back to 0 and the new PASS1_LOOK_FOR_PSEUDO
is set to 1

Former-commit-id: 318327af6bdc3fbdfbe7f438ff7cbea22863a0ab
Former-commit-id: a130baf2b1c3bf1158d367d3633b02600f04674a
This commit is contained in:
2018-11-20 16:02:23 +01:00
parent a040adb132
commit 2ff6ff3308
2 changed files with 14 additions and 2 deletions

View File

@ -151,7 +151,8 @@ endif
Notify " running exonerate of $GenoName on $ProtName"
exonerate \
--model protein2genome \
--model protein2genome \
# -E -S no \
--percent $PASS1_PERCENT \
--showalignment TRUE \
--showvulgar TRUE \
@ -168,6 +169,7 @@ exonerate \
--refineboundary 5000 \
--singlepass FALSE \
--dpmemory 1024 \
--ryo "@@INFO@@ %et %ps" \
$DbFile $GenoFile > $base.exo.raw
CheckAbort 20 "exonerate failure"
@ -181,6 +183,15 @@ $AwkCmd -v MAX_SPAN=$PASS1_MAX_SPAN \
-v EXCLUDE=$GenoName \
-f $LIB_DIR/bestclust.awk $base.exo.raw > $base.exo.best
if ( -z $base.exo.best) then
if ( $PASS1_ALLOW_STOP == "0" && $PASS1_LOOK_FOR_PSEUDO == "1" ) then
$AwkCmd -v MAX_SPAN=$PASS1_MAX_SPAN \
-v ALLOW_STOP=1 \
-v EXCLUDE=$GenoName \
-f $LIB_DIR/bestclust.awk $base.exo.raw > $base.exo.best
endif
endif
#
# get annotations
#

View File

@ -44,7 +44,8 @@ AssignUndef PASS1_SUBMAT $ModelsDir/blosum62.mat
# pass1: cluster selection parameters
#
AssignUndef PASS1_MAX_SPAN 10000
AssignUndef PASS1_ALLOW_STOP 1
AssignUndef PASS1_ALLOW_STOP 0
AssignUndef PASS1_LOOK_FOR_PSEUDO 1
#
# extension parameters