Skip to content

Added code to handle snps less than 30nt from start/end of chromosomes #2

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
ethering wants to merge 1 commit into
base: master
Choose a base branch
from
+55 −27
Open

Added code to handle snps less than 30nt from start/end of chromosomes #2

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
82 changes: 55 additions & 27 deletions code/Funseq_SNV.pm
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -491,53 +491,81 @@ sub motif_gain{
}
close SCORE;



# retrieve + & - 29bp around the SNP & gain of motif calculation;
#create a hash of sequence lengths from the reference sequence
my %seq_lengths;
my $input_seqs = Bio::SeqIO->new ( '-format' => 'Fasta' , '-file' => $reference_file);
while ( my $seq = $input_seqs->next_seq() )
{
my $seq_name = $seq->display_id();
my $seqLength = length($seq->seq());
$seq_lengths{$seq_name}=$seqLength;
}

foreach $id(sort keys %{$self->{GENE}}){
# retrieve + & - 29bp around the SNP & gain of motif calculation;

foreach $id(sort keys %{$self->{GENE}})
{
my $switch = 0;
foreach my $gene(keys %{$self -> {GENE}->{$id}}){
if (defined $self ->{GENE} ->{$id} ->{$gene} -> {"Promoter"} || defined $self ->{GENE}->{$id}->{$gene}->{"Distal"}){
foreach my $gene(keys %{$self -> {GENE}->{$id}})
{
if (defined $self ->{GENE} ->{$id} ->{$gene} -> {"Promoter"} || defined $self ->{GENE}->{$id}->{$gene}->{"Distal"})
{
$switch = 1;
}
}
if ($switch == 1){
if ($switch == 1)
{
@des = split /\s+/,$self->{DES}->{$id};
push @id,$id;
$chr = $des[0];
$chr =~ s/chr//g;
my $chr_length = $seq_lengths{$chr};
# $chr =~ s/chr//g;
$start = $des[1];
$snp_file .= join("",$chr,"\t",$start-29,"\t",$start+30,"\n");
my $search_start = 0;
if ($start > 29)
{

$search_start = $start - 29;
}
my $search_end = $start+30;
if ($search_end > $chr_length)
{
$search_end = $chr_length;
}

$snp_file .= join("",$chr,"\t",$search_start,"\t",$search_end,"\n");
push @ref,uc($des[3]);
push @alt,uc($des[4]);
push @start,$start;
# push @start,$start;
push @start,$search_start;
}
}
}

open(O,">$out_tmp")||die;
print O $snp_file;
close O;

if (-s $out_tmp){


open(O,">$out_tmp")||die;
print O $snp_file;
close O;

if (-s $out_tmp){

@des = split /\n/, `fastaFromBed -fi $reference_file -bed $out_tmp -fo stdout`;

if (scalar @des >0){
for $i (0 .. (scalar @des/2)-1){

if (scalar @des >0)
{
for $i (0 .. (scalar @des/2)-1)
{
$ref = $ref[$i]; $alt = $alt[$i];
$id = $id[$i]; $start = $start[$i];
$extract_seq=uc($des[$i*2+1]);
@extract_seq = split //,$extract_seq;
$extract_seq[29] = $alt;

#positive strand
$extract_seq[29] = $alt;
#positive strand
&seq_scan(\@extract_seq,"+");

#negative strand
#negative strand
$extract_seq =~ tr/ATCGatcg/TAGCTAGC/;
@extract_seq = reverse(split //,$extract_seq);
$ref =~ tr/ATCGatcg/TAGCTAGC/;
$ref =~ tr/ATCGatcg/TAGCTAGC/;
$alt =~ tr/ATCGatcg/TAGCTAGC/;
$extract_seq[29] = $alt;
&seq_scan(\@extract_seq,"-");
Expand Down