File: randomFQ

package info (click to toggle)
ea-utils 1.1.2+dfsg-5
  • links: PTS, VCS
  • area: main
  • in suites: bullseye, buster, sid
  • size: 840 kB
  • sloc: ansic: 11,459; cpp: 3,752; perl: 426; makefile: 74; sh: 42
file content (245 lines) | stat: -rwxr-xr-x 5,982 bytes parent folder | download | duplicates (3)
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
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
#!/usr/bin/perl
use strict;
use Getopt::Long;

# Author: Erik Aronesty (earonesty@xpressionanalysis.com) 
# Outputs a random sampled fastq or fasta file, from an input fastq
# Copyright (c) 2011 Expression Analysis


#    This program is free software: you can redistribute it and/or modify
#    it under the terms of the GNU General Public License as published by
#    the Free Software Foundation, either version 3 of the License, or
#    (at your option) any later version.
#
#    This program is distributed in the hope that it will be useful,
#    but WITHOUT ANY WARRANTY; without even the implied warranty of
#    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
#    GNU General Public License for more details.
#
#    You should have received a copy of the GNU General Public License
#    along with this program.  If not, see <http://www.gnu.org/licenses/>.


my $cnt;
my $fasta;
my $out;
my $seed=1;
my $window;
my $always;
my $append;
my $pct;
GetOptions("count=i"=>\$cnt, "pct=f"=>\$pct, "fasta"=>\$fasta, "out=s"=>\$out, "seed=i"=>\$seed, "window=i"=>\$window, "always|a"=>\$always, "append|A"=>\$append) || die usage();
if ($window < $cnt) {
	$window = $cnt * 5; 
	$window = 100000 if $window < 100000;
}

if ($seed) {
	srand($seed);
}

die usage() unless $cnt>0||$pct>0;

my $in = shift;
my $mate = shift;
my $mate2 = shift;

die "Can't see $in\n" unless -e $in;
die "Can't see $mate\n" unless !$mate || -e $mate;
die "Can't see $mate2\n" unless !$mate2 || -e $mate2;

my $s = -s $in;
my $sm = -s $mate;
my $sm2 = -s $mate2;

die "Need -out <prefix> for paired-end" if $mate && !$out;

my $suff;
if ($out =~ s/\%(.*)//) {
	$suff = $1;
}
$out =~ s/_$//;

my $gzmeth = $suff =~ /\.gz/ ? "|gzip -c " : "";

open(IN, $in=~/\.gz$/?"gunzip -c $in|":$in) || die;

$append = $append ? ">>" : ">";

if ($mate) {
	open(MI, $mate=~/\.gz$/?"gunzip -c $mate|":$mate) || die;
	open(MI2, $mate2=~/\.gz$/?"gunzip -c $mate2|":$mate2) if $mate2;
	open(O1, "$gzmeth$append${out}_1$suff") || die;
	open(O2, "$gzmeth$append${out}_2$suff") || die;
	if ($mate2) {
		open(O3, "$gzmeth$append${out}_3$suff") || die;
	}
} else {
	my $gzmeth = $out =~ /\.gz/ ? "|gzip -c " : "";
	if ($out) {
		open(O1, "$gzmeth$append$out");
	} else {
		open(O1, ">&STDOUT");
	}
}

my $lc = 0+`ea-alc -o $in`;
my $stats = $in; $stats =~ s/\.gz$//;  $stats .= ".stats";
if (-e $stats) {
	my $rlc = `grep ^reads $stats | cut -f 2`+0;
	$lc = $rlc if $rlc;
} else {
    if ($in =~ /gz$/) {
        $lc *= .90;         # lower guess
    }
}

if (!$always && ($cnt > $lc/2)) {
	$cnt *= 4;
	warn "Source is too small relative to count requested, just returning tail -$cnt\n";
	if ($mate) {
		if ($in=~/gz$/) {
			system("gunzip -c $in | head -$cnt $gzmeth $append ${out}_1$suff");
		} else {
			system("tail -$cnt $in $gzmeth $append ${out}_1$suff");
		}
		if ($mate=~/gz$/) {
			system("gunzip -c $mate | head -$cnt $gzmeth $append ${out}_2$suff");
		} else {
			system("tail -$cnt $mate $gzmeth $append ${out}_2$suff");
		}
		if ($mate2=~/gz$/) {
			system("gunzip -c $mate2 | head -$cnt $gzmeth $append ${out}_3$suff");
		} else {
			system("tail -$cnt $mate2 $gzmeth $append ${out}_3$suff") if ($mate2);
		}
		exit 0;
	} else {
		if ($out) {
			$gzmeth = $out =~ /\.gz/ ? "|gzip -c " : "";
			$out = "$gzmeth $append $out";
		}
		if ($in=~/gz$/) {
			exec("gunzip -c $in | head -$cnt $out");
			die("Exec failed : $!\n");
		} else {
			exec("tail -$cnt $in $out");
			die("Exec failed : $!\n");
		}
	}
}

# reads to sample from....whole file or a smaller part?
$window = $lc if $window > $lc;

my $fudge = 1.5;                # top weighted
$fudge = 1.2 if $always;        # less top-weighted

# larger = more chance to keep read
my $prob;

if ($pct) {
    $prob = $pct/100;
    $cnt = 10000000000;
} else {
    $prob = ($cnt*$fudge)/$window;
}

# we used to seek ... but this broke too much ... if you want to fix... fix randomFQ-broken ... 
if (!$always && !$pct) {
    # skip some reads at the beginning
    my $skip = ($lc-$window) / 10;
    $skip = 200000 if $skip > 200000;
    for (my $i=0;$i<$skip;++$i)	{
        scalar <IN>; scalar <IN>; scalar <IN>; scalar <IN>;
        scalar <MI>; scalar <MI>; scalar <MI>; scalar <MI>;
        scalar <MI2>; scalar <MI2>; scalar <MI2>; scalar <MI2>;
    }
}

while ($cnt > 0) {
	if (rand() > $prob) {
		# discard
		<IN>; <IN>; <IN>; <IN>;
		<MI>; <MI>; <MI>; <MI>;
		<MI2>; <MI2>; <MI2>; <MI2>;
		next;
	}

	# id
	my $i = <IN>;
    if (!$i) {
        $cnt = 0;
        last;
    }
	my $i2 = <MI> if $mate;
	my $i3 = <MI2> if $mate2;

	# read
	my $r = <IN>;
	my $r2 = <MI> if $mate;
	my $r3 = <MI2> if $mate2;

	if ($fasta) {
		# only need id and read
		$i=~ s/^\@/>/;
		$i2=~ s/^\@/>/;
		$i3=~ s/^\@/>/;
		print O1 "$i$r";
		print O2 "$i2$r2" if $mate;
		print O3 "$i3$r3" if $mate2;
		<IN>;<IN>;
		<MI>;<MI>;
	} else {
		# print id and read
		print O1 "$i$r";
		print O2 "$i2$r2";
		print O3 "$i3$r3";
		# copy comment and quality
		print O1 scalar <IN>;
		print O2 scalar <MI> if $mate;
		print O3 scalar <MI2> if $mate2;
		print O1 scalar <IN>;
		print O2 scalar <MI> if $mate;
		print O3 scalar <MI2> if $mate2;
	}
	--$cnt;
}

close IN;

sub usage() {
	return <<EOF
usage: $0 (-c <count> | -p <pct>) [-fasta] [-out <prefix>] [-seed <int>] <input-fastq> [<input-2> [<index-3>] ]

Returns <count> number of random entries from the input fastq.

Output is fastq, unless you specify -fasta

If the -out parameter ends in .gz, the result is gzipped in-place.

-p returns a % of total reads, -c returns a fixed count.

SINGLE END:

Outputs to standard output, unless -out <file> is specified.   

PAIRED END:

Pass 2 (or 3) files as input, -out is required.

If the paired-end output contains a "%" sign, it is replaced with the 1 & 2 for paired-end.

IE: -o output_%.fastq.gz

Otherwise it's jsut output_1 and output_2

*** If one file is an indexed read, it has to be the 3rd file (for now).
EOF
}

sub max {
	return $_[0] > $_[1] ? $_[0] : $_[1];
}