new single strand option

guillaume
Commit 5cd6095622a16cb4d80d5b28f0bcc11533d32915 5cd60956 1 parent b4022c59
Showing 1 changed file with 62 additions and 42 deletions
translate_FUNCTION.cpp
--- a/translate_FUNCTION.cpp
View file @5cd6095
+++ b/translate_FUNCTION.cpp
View file @5cd6095
@@ -17,7 +17,7 @@
 vector<int> multiFASTA_seqlen;
 map<string, string> genetic_code;
 vector<string> sCodons;
-int minimum_length = 0;
+int minimum_length = 2; // dipeptides
 // XXX PROTOTYPES
@@ -200,6 +200,14 @@ int main(int argc, char** argv){
 	string optlist =
 		"    Usage:\n"
 		"\n"
+		"    -i              Input file\n"
+		"    -o              Output filenames (default: input filename with .pro and .dna/.rna extensions)\n"
+		"    -s              Start codon\n"
+		"    -m              Minimum ORF length (default: 2)\n"
+		"    -a              Alternative genetic code\n"
+		"    -r              RNA input\n"
+		"    -c              Check FASTA format\n"
+		"    -f              Translate sense strand only\n" // f as in forward
 		"    -h              Help\n";
 	string outFileName;
@@ -208,10 +216,11 @@ int main(int argc, char** argv){
 	bool checkFASTA;
 	string alt_gene_code;
 	string startCodon;
+	bool senseStrand;
 	int opt;
-	while ((opt = getopt(argc,argv,"hrci:o:s:m:a:")) != EOF){
+	while ((opt = getopt(argc,argv,"hrcfi:o:s:m:a:")) != EOF){
 		switch(opt){
 			case 'i': inFileName = optarg; break;
 			case 'o': outFileName = optarg; break;
@@ -220,6 +229,7 @@ int main(int argc, char** argv){
 			case 'a': alt_gene_code = optarg; break;
 			case 'r': rna = true; break;
 			case 'c': checkFASTA = true; break;
+			case 'f': senseStrand = true; break;
 			case 'h': fprintf(stderr, "%s", optlist.c_str()); return 0;
 		}
 	}
@@ -290,56 +300,66 @@ int main(int argc, char** argv){
 	puts("5'-3' translation...");
 	(rna) ? genetic_code = gc_std : genetic_code = gc_std_DNA;
 	translate_3_frames(inFileName, tmp_53_pro_file, tmp_53_dna_file, false);
-	puts("Done");
-
-	/* Reversion of the input sequence by system call: rev + tac */
+	// XXX DIRTY CLEANING
-	puts("Genome reversion...");
+	// awk '/^>/ {if (seq != "") {print head""seq;} seq=""; head=$0"\n";} /^[^>]/ {seq=seq""$0"\n";} END {if (seq != "") print head""seq;}' input.fasta > output.fasta
-	if ( system( ("rev "+inFileName+" | tac > " + tmp_reversed_input).c_str() ) != 0 ){
+	string command = "awk '/^>/ {if (seq != \"\") {print head\"\"seq;} seq=\"\"; head=$0\"\\n\";} /^[^>]/ {seq=seq\"\"$0\"\\n\";} END {if (seq != \"\") print head\"\"seq;}' "+ tmp_53_pro_file + " > " + output_pro + " && rm *.53pro *.53dna";
-		perror("Error while creating reversed genome file");
+	int status = std::system(command.c_str());
-		return(-1);
+	if (status != 0) {
-	}
+		std::cerr << "Error: system call failed with status " << status << std::endl;
-	else{
+		return 1;
-		puts ("Done");
 	}
-
-	/* Reversion of the (global) vector of lengths */
-	reverse(multiFASTA_seqlen.begin(), multiFASTA_seqlen.end());
-
-
-	/* Translation 3'-5' */
-	puts("3'-5' translation...");
-	(rna) ? genetic_code = gc_std_rev : genetic_code = gc_std_DNA_rev;
-	sCodons = complement_sCodons(sCodons, rna);
-	translate_3_frames(tmp_reversed_input, tmp_35_pro_file, tmp_35_dna_file, true);
 	puts("Done");
-	/* Reversion (tac) of the 3'-5' translation, then concatenation */
+	if (not senseStrand){
-	puts("Creating result files...");
+		// TODO Warning for RNA sequence
-	if ( system( ("cat "+tmp_53_pro_file+" > "+output_pro+" && tac "+tmp_35_pro_file+" >> "+output_pro+
+		/* Reversion of the input sequence by system call: rev + tac */
-			" && cat "+tmp_53_dna_file+" > "+output_dna+" && tac "+tmp_35_dna_file+" >> "+output_dna).c_str() ) != 0 ){
+		puts("Genome reversion...");
-		perror("Error while line-reversing and concatenating output files");
+		if ( system( ("rev "+inFileName+" | tac > " + tmp_reversed_input).c_str() ) != 0 ){
-		return(-1);
+			perror("Error while creating reversed genome file");
-	}
+			return(-1);
-	else{
+		}
-		puts("Done");
+		else{
-	}
+			puts ("Done");
-
+		}
-	/* Delete the temporary files */
+	
-	puts("Cleaning temporary files...");
+		/* Reversion of the (global) vector of lengths */
-	if ( system( ("rm "+tmp_reversed_input+" "+tmp_35_pro_file+" "+tmp_35_dna_file+" "+tmp_53_pro_file+" "+tmp_53_dna_file).c_str() ) ){
+		reverse(multiFASTA_seqlen.begin(), multiFASTA_seqlen.end());
-		perror("Error while deleting temporary files");
+	
-		return(-1);
+	
-	}
+		/* Translation 3'-5' */
-	else{
+		puts("3'-5' translation...");
+		(rna) ? genetic_code = gc_std_rev : genetic_code = gc_std_DNA_rev;
+		sCodons = complement_sCodons(sCodons, rna);
+		translate_3_frames(tmp_reversed_input, tmp_35_pro_file, tmp_35_dna_file, true);
 		puts("Done");
+	
+	
+		/* Reversion (tac) of the 3'-5' translation, then concatenation */
+		puts("Creating result files...");
+		if ( system( ("cat "+tmp_53_pro_file+" > "+output_pro+" && tac "+tmp_35_pro_file+" >> "+output_pro+
+				" && cat "+tmp_53_dna_file+" > "+output_dna+" && tac "+tmp_35_dna_file+" >> "+output_dna).c_str() ) != 0 ){
+			perror("Error while line-reversing and concatenating output files");
+			return(-1);
+		}
+		else{
+			puts("Done");
+		}
+	
+		/* Delete the temporary files */
+		puts("Cleaning temporary files...");
+		if ( system( ("rm "+tmp_reversed_input+" "+tmp_35_pro_file+" "+tmp_35_dna_file+" "+tmp_53_pro_file+" "+tmp_53_dna_file).c_str() ) ){
+			perror("Error while deleting temporary files");
+			return(-1);
+		}
+		else{
+			puts("Done");
+		}
 	}
-
-
 	// XXX XXX DETECT SEQUENCE
 	// => output sequence and surrounding