Skip to content

Commit

Permalink
treat N as gap
Browse files Browse the repository at this point in the history
  • Loading branch information
andrewjpage committed Jan 24, 2012
1 parent 0654d8a commit 413134d
Show file tree
Hide file tree
Showing 5 changed files with 5 additions and 5 deletions.
4 changes: 2 additions & 2 deletions alignment_file.c
Original file line number Diff line number Diff line change
Expand Up @@ -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++;
Expand Down
2 changes: 1 addition & 1 deletion parse_phylip.c
Original file line number Diff line number Diff line change
Expand Up @@ -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;
}
Expand Down
Binary file modified snp_sites
Binary file not shown.
Binary file modified tests/check_snp_sites
Binary file not shown.
4 changes: 2 additions & 2 deletions vcf.c
Original file line number Diff line number Diff line change
Expand Up @@ -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)
{
Expand Down Expand Up @@ -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, "." );
}
Expand Down

0 comments on commit 413134d

Please sign in to comment.