Skip to content
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

Deterministic miRDeep2_core_algorithm.pl #65

Open
wants to merge 2 commits into
base: master
Choose a base branch
from
Open

Deterministic miRDeep2_core_algorithm.pl #65

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
435eb44
make find_mature_query in miRDeep2_core_algorithm.pl deterministic
Mar 30, 2020
3eba769
make print_hash_comp in miRDeep2_core_algorithm.pl deterministic
Mar 30, 2020
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
48 changes: 23 additions & 25 deletions src/miRDeep2_core_algorithm.pl
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -112,6 +112,7 @@
my %hash_comp;
my %hash_bp;
my %hash_stars;
my %reads_hash;


#other variables
Expand Down Expand Up @@ -1110,12 +1111,20 @@ sub find_mature_query{
#finds the query with the highest frequency of reads and returns it
#is used to determine the positions of the potential mature sequence

my @queries=sort {$hash_query{$b}{"freq"} <=> $hash_query{$a}{"freq"}} keys %hash_query;
my @queries=sort sort_queries keys %hash_query;
my $mature_query=$queries[0];
return $mature_query;
}


sub sort_queries{
if ($hash_query{$b}{'freq'} == $hash_query{$a}{'freq'}){
return ($a cmp $b);
}
else{
return ($hash_query{$b}{'freq'} <=> $hash_query{$a}{'freq'});
}
}


sub reset_variables{
Expand All @@ -1126,6 +1135,7 @@ sub reset_variables{
%hash_comp=();
%hash_bp=();
%hash_stars=();
%reads_hash=();

$lines=();

Expand Down Expand Up @@ -1335,7 +1345,6 @@ sub print_hash_comp{
my $spacer=multh("pri_seq",$col1_width);

my $shift;
my %reads_hash;

print ">$hash_comp{'pri_id'}\n";
my $spacer2s=0;
Expand Down Expand Up @@ -1484,29 +1493,7 @@ sub print_hash_comp{
}
}

## sorted keys by begin postion
my @skeys = sort { $reads_hash{$a}{"beg"} <=> $reads_hash{$b}{"beg"} } keys %reads_hash;
my @elist; # final sorted array

my $first = $reads_hash{$skeys[0]}{"beg"}; ## all keys that have same begin position should match this value
my %rorder; ## temporary hash to store all keys with same begin position

for(my $j = 0; $j < scalar @skeys; $j++){
if($reads_hash{$skeys[$j]}{"beg"} eq $first){
$rorder{$j} = $reads_hash{$skeys[$j]}{"end"}; ## insert key and end position to hash
}else{ ## if new begin position
$first = $reads_hash{$skeys[$j]}{"beg"};
for(sort {$rorder{$a} <=> $rorder{$b}} keys %rorder){ ## sort hash keys by end position
push(@elist,$skeys[$_]); ## attend keys to elist
}
for(keys %rorder){delete $rorder{$_};} ## delete hash
$rorder{$j} = $reads_hash{$skeys[$j]}{"end"};
}
}

for(sort {$rorder{$a} <=> $rorder{$b}} keys %rorder){
push(@elist,$skeys[$_]);
}
my @elist = sort sort_reads keys %reads_hash; # final sorted array

foreach(@elist){ ## output elist.
$rseq = lc $reads_hash{$_}{'seq'};
Expand Down Expand Up @@ -1538,6 +1525,17 @@ sub print_hash_comp{
}


sub sort_reads{
if ($reads_hash{$a}{'beg'} == $reads_hash{$b}{'beg'} && $reads_hash{$a}{'end'} == $reads_hash{$b}{'end'}){
return $reads_hash{$a}{'id'} cmp $reads_hash{$b}{'id'};
}
elsif ($reads_hash{$a}{'beg'} == $reads_hash{$b}{'beg'}){
return $reads_hash{$a}{'end'} <=> $reads_hash{$b}{'end'};
}
else{
return $reads_hash{$a}{'beg'} <=> $reads_hash{$b}{'beg'};
}
}


sub print_hash_bp{
Expand Down