Merge pull request #1 from andrewjpage/master

Treat N as a gap

.gitignore

@@ -1,4 +1,2 @@
 *.o
 gubbins
-*.phylip
-*.vcf

alignment_file.c

@@ -175,12 +175,12 @@ int detect_snps(char reference_sequence[], char filename[], int length_of_genome
     for(i = 0; i < length_of_genome; i++)
 		{
 			// If there is an indel in the reference sequence, replace with the first proper base you find
-			if(reference_sequence[i] == '-' && seq->seq.s[i] != '-' )
+			if((reference_sequence[i] == '-' && seq->seq.s[i] != '-' ) || (toupper(reference_sequence[i]) == 'N' && seq->seq.s[i] != 'N' ))
 			{
 				reference_sequence[i] = toupper(seq->seq.s[i]);
 			}
 
-			if(reference_sequence[i] != '*' && seq->seq.s[i] != '-' && reference_sequence[i] != toupper(seq->seq.s[i]))
+			if(reference_sequence[i] != '*' && seq->seq.s[i] != '-' && toupper(seq->seq.s[i]) != 'N' && reference_sequence[i] != toupper(seq->seq.s[i]))
 			{
 				reference_sequence[i] = '*';
 				number_of_snps++;

parse_phylip.c

@@ -52,7 +52,7 @@ int does_column_contain_snps(int snp_column, char reference_base)
 			return 0;	
 		}
 
-		if(sequences[i][snp_column]  != '-' && sequences[i][snp_column] != reference_base)
+		if(sequences[i][snp_column]  != '-' && toupper(sequences[i][snp_column])  != 'N' && sequences[i][snp_column] != reference_base)
 		{
 			return 1;
 		}

tests/data/alignment_file_one_line_per_sequence.aln.phylip

@@ -0,0 +1,110 @@
+109 5
+2956_6_1	AACGC
+2956_6_2	AACGC
+2956_6_3	AACGC
+2956_6_4	AACGC
+2956_6_5	AACGC
+2956_6_6	AACGC
+3002_8_1	GACGC
+3002_8_2	GACGC
+3002_8_3	AACGC
+3002_8_4	AACGC
+3002_8_5	-ACGC
+3002_8_6	GACGC
+3002_8_7	AACGC
+4056_2_10	GACGC
+4056_2_11	AACGC
+4056_2_1	AACGC
+4056_2_12	AACGC
+4056_2_2	AACGC
+4056_2_3	-ACGC
+4056_2_4	GACGT
+4056_2_5	AACGC
+4056_2_6	AACGC
+4056_2_7	AACGC
+4056_2_9	AACGC
+4056_6_10	AACGC
+4056_6_11	AACGC
+4056_6_12	AACGC
+4056_6_2	AACGC
+4056_6_3	AACGC
+4056_6_4	AACGC
+4056_6_5	AACGC
+4056_6_6	AACGC
+4056_6_7	AACGC
+4056_6_9	AACGC
+4056_7_10	AACGC
+4056_7_11	AACGC
+4056_7_1	AACGC
+4056_7_12	AACGC
+4056_7_7	AACGC
+4056_7_8	AACGC
+4056_7_9	AACGC
+4056_8_10	AACGC
+4056_8_1	AACGC
+4056_8_12	AACGC
+4056_8_2	AACGC
+4056_8_3	AACGC
+4056_8_4	AACGC
+4056_8_6	GACGC
+4056_8_8	AACGC
+4056_8_9	AACGC
+4075_3_11	AACGC
+4075_3_12	AACGC
+4075_3_2	AACGC
+4075_3_3	AACGC
+4075_3_5	AACGC
+4075_3_6	AACGC
+4075_3_7	AACGC
+4075_3_8	AACGC
+4075_3_9	AACGC
+4370_2_11	AACGC
+4370_2_12	AACGC
+4370_2_2	AACGC
+4370_2_3	AACGC
+4370_2_4	AACGC
+4370_2_7	AACGC
+4370_2_8	AACGC
+4370_2_9	AACGC
+4370_3_11	AACGC
+4370_3_1	AACGC
+4370_3_6	AACGC
+4370_3_7	AACGC
+4370_3_8	AACGC
+5174_5_1	GACGC
+5174_5_2	AACGC
+5174_5_3	AACGC
+5174_5_4	AACGC
+5174_5_5	AACGC
+5174_5_6	AACGC
+5174_5_7	GACGC
+5174_5_9	GACGC
+5174_6_10	GACGC
+5174_6_1	AACGC
+5174_6_2	AACGC
+5174_6_3	AACGC
+5174_6_4	AACGC
+5174_6_5	AACGC
+5174_6_6	AACGC
+5174_6_7	AACGC
+5174_6_8	AACGC
+5174_6_9	AACGC
+5174_7_10	AACGC
+5174_7_1	GACGC
+5174_7_2	AACGC
+5174_7_3	AACGC
+5174_7_4	AACGC
+5174_7_5	AACGC
+5174_7_6	AACGC
+5174_7_7	AACGC
+5174_7_8	AACGC
+5174_7_9	AACGC
+5174_8_1	AACGC
+5174_8_2	AACGC
+5174_8_3	AACGC
+5174_8_5	GACGC
+5174_8_6	AACGC
+5174_8_8	AACGC
+5174_8_9	AACGC
+Vibrio_parahaemolyticus	-----
+Vibrio_vulnificus	-GGA-

tests/data/alignment_file_one_line_per_sequence.aln.vcf

@@ -0,0 +1,8 @@
+##fileformat=VCFv4.1
+##INFO=<ID=AB,Number=1,Type=String,Description="Alt Base">
+#CHROM	POS	ID	REF	ALT	QUAL	FILTER	INFO	FORMAT	2956_6_1	2956_6_2	2956_6_3	2956_6_4	2956_6_5	2956_6_6	3002_8_1	3002_8_2	3002_8_3	3002_8_4	3002_8_5	3002_8_6	3002_8_7	4056_2_10	4056_2_11	4056_2_1	4056_2_12	4056_2_2	4056_2_3	4056_2_4	4056_2_5	4056_2_6	4056_2_7	4056_2_9	4056_6_10	4056_6_11	4056_6_12	4056_6_2	4056_6_3	4056_6_4	4056_6_5	4056_6_6	4056_6_7	4056_6_9	4056_7_10	4056_7_11	4056_7_1	4056_7_12	4056_7_7	4056_7_8	4056_7_9	4056_8_10	4056_8_1	4056_8_12	4056_8_2	4056_8_3	4056_8_4	4056_8_6	4056_8_8	4056_8_9	4075_3_11	4075_3_12	4075_3_2	4075_3_3	4075_3_5	4075_3_6	4075_3_7	4075_3_8	4075_3_9	4370_2_11	4370_2_12	4370_2_2	4370_2_3	4370_2_4	4370_2_7	4370_2_8	4370_2_9	4370_3_11	4370_3_1	4370_3_6	4370_3_7	4370_3_8	5174_5_1	5174_5_2	5174_5_3	5174_5_4	5174_5_5	5174_5_6	5174_5_7	5174_5_9	5174_6_10	5174_6_1	5174_6_2	5174_6_3	5174_6_4	5174_6_5	5174_6_6	5174_6_7	5174_6_8	5174_6_9	5174_7_10	5174_7_1	5174_7_2	5174_7_3	5174_7_4	5174_7_5	5174_7_6	5174_7_7	5174_7_8	5174_7_9	5174_8_1	5174_8_2	5174_8_3	5174_8_5	5174_8_6	5174_8_8	5174_8_9	Vibrio_parahaemolyticus	Vibrio_vulnificus	
+1	824	.	A	G	.	.	AB	.	.	.	.	.	.	.	G	G	.	.	.	G	.	G	.	.	.	.	.	G	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	G	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	G	.	.	.	.	.	G	G	G	.	.	.	.	.	.	.	.	.	.	G	.	.	.	.	.	.	.	.	.	.	.	G	.	.	.	.	.
+1	1277	.	A	G	.	.	AB	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	G
+1	1280	.	C	G	.	.	AB	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	G
+1	1298	.	G	A	.	.	AB	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	A
+1	1434	.	C	T	.	.	AB	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	T	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.

vcf.c

@@ -116,7 +116,7 @@ void alternative_bases(char reference_base, char * bases_for_snp, char alt_bases
 	int num_alt_bases = 0;
 	for(i=0; i< number_of_samples; i++ )
 	{
-		if((bases_for_snp[i] != reference_base) && (bases_for_snp[i] != '-'))
+		if((bases_for_snp[i] != reference_base) && (bases_for_snp[i] != '-') && (toupper(bases_for_snp[i]) != 'N') )
 		{
 			if(check_if_char_in_string(alt_bases, bases_for_snp[i], num_alt_bases) == 0)
 			{
@@ -156,7 +156,7 @@ void output_vcf_row_samples_bases(FILE * vcf_file_pointer, char reference_base,
 
 	for(i=0; i < number_of_samples ; i++ )
 	{
-		if((bases_for_snp[i] == reference_base) || (bases_for_snp[i] == '-'))
+		if((bases_for_snp[i] == reference_base) || (bases_for_snp[i] == '-') || (toupper(bases_for_snp[i]) == 'N') )
 		{
 			fprintf( vcf_file_pointer, "." );	
 		}