1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
|
use strict;
#transcript sequences file
open(TRANSCRIPTS_FILE,$ARGV[0]);
my @transcripts=<TRANSCRIPTS_FILE>;
#source of transcript sequences
my $transcript_source=$ARGV[1];
#name of the anchoring enzyme and sequence of its restriction site
my $enzyme=$ARGV[2];
my $restriction_site=uc($ARGV[3]); #if restriction site sequence isn't written in capital letters, we write it in capital letters
$restriction_site =~ s/\s//g; #keep out eventual blanks in the sequence
#initialization:
#one transcript sequence
my $transcript_seq='';
#one transcript description line (i.e. the line beginning by ">" excepted the symbol ">")
chomp($transcripts[0]);
my $transcript_line_desc=substr($transcripts[0],1,length($transcripts[0]));
#number of virtual tags extracted from transcript sequences
my $tags_nb=$ARGV[4]+1;
#number of transcript sequences
my $transcripts_nb=$ARGV[5]+1;
#opening of load data files
open(TAGS,">>loaddata_VirtualTag");
open(CONNECTION,">>loaddata_VirtualTagTranscript");
open(TRANSCRIPTS,">>loaddata_Transcript");
#reading of the transcript file from second line
#(the first one was used for initialization)
for (my $i=1; $i<=$#transcripts; $i++)
{
my $line=$transcripts[$i];
chomp($line);
if ($line =~ /^>/){
#analyzing the previous transcript sequence
$transcript_seq =~ s/\s//g; #keep out eventual blanks in the sequence
$transcript_seq = uc($transcript_seq); #if transcript sequence isn't written in capital letters, we write it in capital letters
#finding the virtual tags in the transcript sequence
my @tags_id = Find_Tags($transcript_seq,$tags_nb,$enzyme,$restriction_site);
if ($#tags_id != -1)
{
$tags_nb = $tags_id[$#tags_id]+1; #incrementation of the number of virtual tags already extracted from transcript sequences
}
#analyzing transcript sequence
Analyze_Transcript($transcript_seq,$transcript_line_desc,$transcripts_nb,$transcript_source);
#connection between virtual tags and transcript
foreach my $id (@tags_id)
{
print CONNECTION $id."\t".$transcripts_nb."\n";
}
#consideration of the next transcript sequence
$transcript_line_desc=substr($line,1,length($line));
$transcripts_nb ++;
$transcript_seq='';
}
else
{
$transcript_seq .= $line;
}
}
#analyzing the last transcript sequence
$transcript_seq =~ s/\s//g; #keep out eventual blanks in the sequence
$transcript_seq = uc($transcript_seq); #if transcript sequence isn't written in capital letters, we write it in capital letters
#finding the virtual tags in the transcript sequence
my @tags_id = Find_Tags($transcript_seq,$tags_nb,$enzyme,$restriction_site);
$tags_nb = $tags_id[$#tags_id]; #incrementation of the number of virtual tags already extracted from transcript sequences
#analyzing transcript sequence
Analyze_Transcript($transcript_seq,$transcript_line_desc,$transcripts_nb,$transcript_source);
#connection between virtual tags and transcript
foreach my $id (@tags_id)
{
print CONNECTION $id."\t".$transcripts_nb."\n";
}
#closing of files to load into corresponding tables
close TAGS;
close CONNECTION;
close TRANSCRIPTS;
close TRANSCRIPTS_FILE;
#printing number of virtual tags and transcripts in files to load into corresponding tables
print "$tags_nb\n$transcripts_nb\n";
exit; |
erreur : "vm_allocate(size=8421376) failed (error code=3)" et ouverture de fichier
)
Répondre avec citation
Partager