Add management of partial sequences

Former-commit-id: abd6112ac558592616c197f2fe761880a847b031
Former-commit-id: d2ea2e7e306512bf8ef92d3497a0302919b81010
This commit is contained in:
2016-10-05 15:11:26 +02:00
parent 466308267e
commit cf5a5d1ce5

View File

@ -24,6 +24,7 @@ normalization="yes"
irdetection="yes" irdetection="yes"
organism="no" organism="no"
types="chloro" types="chloro"
partial=0
function usage { function usage {
echo "Usage:" ; echo "Usage:" ;
@ -52,12 +53,21 @@ function usage {
echo echo
echo ' -m | --mitochondrion' echo ' -m | --mitochondrion'
echo ' Selects for the annotation of an animal mitochondrion genome' echo ' Selects for the annotation of an animal mitochondrion genome'
echo
echo ' -p | --partial'
echo ' Indicates that the genome sequence is partial and therefore in several contigs'
exit $2 exit $2
} }
function fastaIterator() {
awk '/^>/ {if (seq) printf("%s\f",seq); seq=""} \
{if (seq) seq=seq"\n"; seq=seq $1} \
END {print seq}' "$1"
}
# options may be followed by one colon to indicate they have a required argument # options may be followed by one colon to indicate they have a required argument
if ! options=$(getopt -o t:o:icrmh -l ncbi-taxid:,organism,no-ir-detection,chloroplast,nuclear-rdna,mitochondrion,help -- "$@") if ! options=$(getopt -o t:o:icrmhp -l ncbi-taxid:,organism,no-ir-detection,chloroplast,nuclear-rdna,mitochondrion,partial,help -- "$@")
then then
# something went wrong, getopt will put out an error message for us # something went wrong, getopt will put out an error message for us
usage $0 1 usage $0 1
@ -74,6 +84,7 @@ do
-c|--chloroplast) types="chloro" ;; -c|--chloroplast) types="chloro" ;;
-r|--nuclear-rdna) types="nucrdna" ;; -r|--nuclear-rdna) types="nucrdna" ;;
-m|--mitochondrion) types="mito" ;; -m|--mitochondrion) types="mito" ;;
-p|--partial) partial="1" ;;
-h|--help) usage $0 0;; -h|--help) usage $0 0;;
(--) shift; break;; (--) shift; break;;
(-*) echo "$0: error - unrecognized option $1" 1>&2; exit 1;; (-*) echo "$0: error - unrecognized option $1" 1>&2; exit 1;;
@ -101,22 +112,34 @@ pushTmpDir ORG.organnot
rm -f ${LOG} rm -f ${LOG}
openLogFile ${LOG} openLogFile ${LOG}
IFS=$'\f'
for sequence in $(fastaIterator "${QUERY}") ; do
unset IFS
if [[ ! -z "${sequence}" ]] ; then
echo "${sequence}" > toannotate.fasta
seqid=$(awk '(NR==1) {print substr($1,2,1000)}' toannotate.fasta)
case "$types" in case "$types" in
chloro) chloro)
loginfo "Annotating a plant chloroplast genome..." loginfo "Annotating a plant chloroplast genome..."
if [ "$irdetection"=="yes" ]; then if [[ "$irdetection"=="yes" ]] && (( partial == 0 )) ; then
loginfo "Normalizing the structure of the Chloroplast sequence..." loginfo "Normalizing the structure of the Chloroplast sequence..."
loginfo " LSC + IRB + SSC + IRA" loginfo " LSC + IRB + SSC + IRA"
${PROG_DIR}/detectors/normalize/bin/go_normalize.sh ${QUERY} > "${RESULTS}.norm.fasta" ${PROG_DIR}/detectors/normalize/bin/go_normalize.sh toannotate.fasta > "${RESULTS}.norm.fasta"
loginfo "Done." loginfo "Done."
loginfo "Annotating the Inverted repeats and Single copies (LSC and SSC)..." loginfo "Annotating the Inverted repeats and Single copies (LSC and SSC)..."
${PROG_DIR}/detectors/ir/bin/go_ir.sh "${RESULTS}.norm.fasta" > "${RESULTS}.annot" ${PROG_DIR}/detectors/ir/bin/go_ir.sh "${RESULTS}.norm.fasta" > "${RESULTS}.annot"
loginfo "Done." loginfo "Done."
else
cat toannotate.fasta > "${RESULTS}.norm.fasta"
rm -f "${RESULTS}.annot"
touch "${RESULTS}.annot"
fi fi
loginfo "Annotating the tRNA..." loginfo "Annotating the tRNA..."
@ -131,14 +154,20 @@ pushTmpDir ORG.organnot
tcsh -f ${PROG_DIR}/detectors/cds/bin/go_cds.sh "${RESULTS}.norm.fasta" >> "${RESULTS}.annot" tcsh -f ${PROG_DIR}/detectors/cds/bin/go_cds.sh "${RESULTS}.norm.fasta" >> "${RESULTS}.annot"
loginfo "Done." loginfo "Done."
if (( partial == 0 )) ; then
topology="circular" topology="circular"
defline="plastid, complete genome" defline="plastid, complete genome"
else
topology="linear"
defline="plastid, partial sequence"
fi
;; ;;
nucrdna) nucrdna)
loginfo "Annotating a plant rDNA cistron..." loginfo "Annotating a plant rDNA cistron..."
loginfo "Normalizing the structure of the cistron sequence..." loginfo "Normalizing the structure of the cistron sequence..."
${PROG_DIR}/detectors/normalizerdna/bin/go_normalizerdna.sh ${QUERY} > "${RESULTS}.norm.fasta" ${PROG_DIR}/detectors/normalizerdna/bin/go_normalizerdna.sh toannotate.fasta > "${RESULTS}.norm.fasta"
loginfo "Done." loginfo "Done."
loginfo "Annotating the rRNA genes..." loginfo "Annotating the rRNA genes..."
@ -148,15 +177,22 @@ pushTmpDir ORG.organnot
topology="linear" topology="linear"
defline="18S rRNA gene, ITS1, 5.8S rRNA gene, ITS2 and 28S rRNA gene" defline="18S rRNA gene, ITS1, 5.8S rRNA gene, ITS2 and 28S rRNA gene"
;; ;;
mito) mito)
loginfo "Annotating an animal mitochondrial genome..." loginfo "Annotating an animal mitochondrial genome..."
logerror "Not yet implemented" logerror "Not yet implemented"
if (( partial == 0 )) ; then
topology="circular" topology="circular"
defline="mitochondrion, complete genome" defline="mitochondrion, complete genome"
else
topology="linear"
defline="mitochondrion, partial sequence"
fi
exit 1 exit 1
;; ;;
*) *)
usage $0 1;; usage $0 1;;
esac esac
@ -167,10 +203,12 @@ pushTmpDir ORG.organnot
organism="$(echo ${organism} | tr '_' ' ')" organism="$(echo ${organism} | tr '_' ' ')"
fi fi
sl=$(seqlength "${RESULTS}.norm.fasta")
loginfo "Printing minimal header..." loginfo "Printing minimal header..."
echo "ID XXX; XXX; ${topology}; genomic DNA; XXX; XXX; $(seqlength ${RESULTS}.norm.fasta) BP." echo "ID ${seqid}; ${seqid}; ${topology}; genomic DNA; XXX; XXX; ${sl} BP."
echo "XX" echo "XX"
echo "AC XXX;" echo "AC ${seqid};"
echo "DE ${organism} ${defline}." echo "DE ${organism} ${defline}."
echo "XX" echo "XX"
loginfo "Done." loginfo "Done."
@ -179,8 +217,36 @@ pushTmpDir ORG.organnot
echo "FH Key Location/Qualifiers" echo "FH Key Location/Qualifiers"
loginfo "Done." loginfo "Done."
loginfo "Printing the source feature"
echo "FT source 1..${sl}" >> "${RESULTS}.annot"
if [[ "${organism}" != "{organism}" ]] ; then
echo "FT /organism=\"${organism}\"" >> "${RESULTS}.annot"
fi
case "${types}" in
chloro)
echo "FT /organelle=\"plastid:chloroplast\"" >> "${RESULTS}.annot"
;;
mito)
echo "FT /organelle=\"mitochondrion\"" >> "${RESULTS}.annot"
;;
*)
loginfo "Nuclear sequence"
;;
esac
echo "FT /mol_type=\"genomic DNA\"" >> "${RESULTS}.annot"
if [[ "${taxid}" != "no" ]] ; then
echo "FT /db_xref=\"taxon:${taxid}\"" >> "${RESULTS}.annot"
fi
# echo "FT /country=\"Poland: Bialowieza Forest\"" >> "${RESULTS}.annot"
loginfo "Done."
loginfo "Ordering annotations..." loginfo "Ordering annotations..."
awk '/^.....(misc|repeat|rRNA|tRNA|gene)/ { \ awk '/^.....(misc|repeat|rRNA|tRNA|gene|source)/ { \
match($3,"[0-9][0-9]*"); \ match($3,"[0-9][0-9]*"); \
pos=substr($3,RSTART,RLENGTH)*1000 + 1; \ pos=substr($3,RSTART,RLENGTH)*1000 + 1; \
print pos,$0; \ print pos,$0; \
@ -194,6 +260,8 @@ pushTmpDir ORG.organnot
print line}' print line}'
loginfo "Done." loginfo "Done."
loginfo "Closing annotations table..." loginfo "Closing annotations table..."
echo "XX" echo "XX"
loginfo "Done." loginfo "Done."
@ -246,6 +314,9 @@ pushTmpDir ORG.organnot
loginfo "Closing sequence part..." loginfo "Closing sequence part..."
echo "//" echo "//"
loginfo "Done." loginfo "Done."
fi
IFS=$'\f'
done # End of the loop over the sequences
popTmpDir popTmpDir