CDS detector added

Former-commit-id: 93fac7a70052d06c2a12bf8af59820c653edd31b
Former-commit-id: 0869fdad0f550941a0f78f1e4c57f4fcdb3f6076

org-annotate.sh

@@ -0,0 +1,131 @@
+#!/bin/bash
+#
+#
+
+#
+#                           Annotate tRNA 
+#
+#========================================================================================
+#
+#  Annotate tRNA based on the Aragorn software predictions.
+
+#  go_trna.sh <FASTAFILE>
+#
+#		- <FASTAFILE> : The fasta file containing the genome to annotate
+#
+#  Results are printed to the standart output
+#
+#========================================================================================
+
+# -- CAUTION -- Works as long than the script 
+#               is not called through a symlink
+SCRIPT_DIR="$(dirname ${BASH_SOURCE[0]})"
+source "${SCRIPT_DIR}/scripts/bash_init.sh"
+
+pushTmpDir ORG.organnot
+
+	if [[ ! "$1" =~ ^/ ]]; then
+		QUERY="${CALL_DIR}/$1"
+	else
+		QUERY="$1"
+	fi
+
+	RESULTS=$(basename ${QUERY/.*/})
+	LOG="${CALL_DIR}/${RESULTS}.log"
+	
+	rm -f ${LOG}
+	openLogFile ${LOG}
+
+	loginfo "Normalizing the structure of the Chloroplast sequence..."
+		loginfo "   LSC + IRB + SSC + IRA"
+		${PROG_DIR}/detectors/normalize/bin/go_normalize.sh ${QUERY} > "${RESULTS}.norm.fasta"
+	loginfo "Done."
+	
+	loginfo "Annotating the Inverted repeats and Single copies (LSC and SSC)..."
+		${PROG_DIR}/detectors/ir/bin/go_ir.sh ${QUERY} > "${RESULTS}.annot"		
+	loginfo "Done."
+	
+	loginfo "Annotating the tRNA..."
+		${PROG_DIR}/detectors/trna/bin/go_trna.sh ${QUERY} >> "${RESULTS}.annot"
+	loginfo "Done."
+	
+	loginfo "Annotating the rRNA genes..."
+		${PROG_DIR}/detectors/rrna/bin/go_rrna.sh ${QUERY} >> "${RESULTS}.annot"
+	loginfo "Done."
+	
+	
+	loginfo "Printing annotations header..."
+		echo "XX"
+    	echo "FH   Key             Location/Qualifiers"
+	loginfo "Done."
+	
+	loginfo "Ordering annotations..."
+		awk '/^.....[^ ]/ { \
+		        match($3,"[0-9][0-9]*"); \
+		        pos=substr($3,RSTART,RLENGTH)*1000 + 1; \
+		        print pos,$0} \
+		     /^..... / { \
+		        pos++; \
+		        print pos,$0}' "${RESULTS}.annot" | \
+		sort -nk1 | \
+		awk '{ \
+		        match($0,"^[0-9]* ");\
+		        line=substr($0,RLENGTH+1,100000);\
+		        print line}' 
+	loginfo "Done."
+	
+	loginfo "Closing annotations table..."
+		echo "XX"
+	loginfo "Done."
+	
+	loginfo "Computing statistics on nucleotide usage..."
+		awk '! /^>/ { \
+			    seq=toupper($0); \
+				gsub(" ","",seq); \
+			    lseq=length(seq); \
+				for (i=0; i < lseq; i++) { \
+					freq[substr(seq,i,1)]++}\
+					} \
+			 END { \
+			 	other=0; \
+			 	for (i in freq) { \
+			 		if (i!="A" && i!="C" && i!="G" && i!="T") {\
+			 			other+=freq[i] \
+			 			} \
+			 		}; \
+			 		print "SQ   Sequence "\
+			 		      (freq["A"]+freq["C"]+freq["G"]+freq["T"]+other) \
+			 		      " BP; "\
+			 		      freq["A"]" A; "\
+			 		      freq["C"]" C; "\
+			 		      freq["G"]" G; "\
+			 		      freq["T"]" T; "\
+			 		      other" other;" \
+			 }' ${QUERY}
+	loginfo "Done."
+	
+	loginfo "Reformating sequences..."
+		lines=$(wc -l ${QUERY} | awk '{print $1}')
+		awk -v lines=$lines ' \
+			! /^>/ { \
+					seq=tolower($0); \
+					gsub(" ","",seq); \
+					printf("     ") ;\
+					for (i=0; i < 6; i++) { \
+						f=substr(seq,i * 10, 10); \
+						pos+=length(f); \
+						f = f  substr("          ",1,10-length(f)); \
+						printf("%s ",f) \
+					}; \
+					if (NR==lines) \
+					  {pos-=1}; \
+					printf("   %6d\n",pos) \
+			   }' ${QUERY}
+	loginfo "Done."
+	
+	loginfo "Closing sequence part..."
+		echo "//"
+	loginfo "Done."
+
+popTmpDir
+