From bff0beaeee33b0818149d652e51e2508fd2aae84 Mon Sep 17 00:00:00 2001
From: Eric Coissac <eric.coissac@metabarcoding.org>
Date: Sun, 11 Oct 2015 11:58:43 -0300
Subject: [PATCH] Add the reformating of the sequence in EMBL format

Former-commit-id: f58f9d6702775280555d8d05fa167594e33620b2
Former-commit-id: 99eb5825fe75585ac86805ffdcca65f4ee7c0070
---
 organnote.sh | 88 +++++++++++++++++++++++++++++++++++++++++++++++++---
 1 file changed, 84 insertions(+), 4 deletions(-)

diff --git a/organnote.sh b/organnote.sh
index 8258582..14e58d0 100755
--- a/organnote.sh
+++ b/organnote.sh
@@ -36,12 +36,92 @@ pushTmpDir ORG.organnot
 	rm -f ${LOG}
 	openLogFile ${LOG}
 
-	${PROG_DIR}/detectors/normalize/bin/go_normalize.sh ${QUERY} > "${RESULTS}.norm.fasta"
+	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."
 	
-	${PROG_DIR}/detectors/ir/bin/go_ir.sh ${QUERY} > "${RESULTS}.annot"		
-	${PROG_DIR}/detectors/trna/bin/go_trna.sh ${QUERY} >> "${RESULTS}.annot"
+	loginfo "Annotating the Inverted repeats and Single copies (LSC and SSC)..."
+		${PROG_DIR}/detectors/ir/bin/go_ir.sh ${QUERY} > "${RESULTS}.annot"		
+	loginfo "Done."
 	
-	cat "${RESULTS}.annot"
+	loginfo "Annotating the tRNA..."
+		${PROG_DIR}/detectors/trna/bin/go_trna.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