This file is indexed.

/usr/bin/maq_eval.pl is in maq 0.7.1-5.

This file is owned by root:root, with mode 0o755.

The actual contents of the file can be viewed below.

  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
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
#!/usr/bin/perl -w

# Author: lh3

use strict;
use warnings;
use Getopt::Std;

my $version = "0.1.11";

&usage if (@ARGV < 1);
my $command = shift(@ARGV);
my %func = (sub=>\&evalsub, geno=>\&evalgeno, indelpe=>\&evalindelpe, indelsoa=>\&evalindelsoa, subfp=>\&subfp);
die("Unknown command \"$command\".\n") if (!defined($func{$command}));
&{$func{$command}}();
exit(0);

#
#
#

sub subfp {
  my %opts = (L=>2800000000, o=>0, e=>0, q=>20);
  getopts('L:o:e:q:', \%opts);
  die ("Usage: subfp [-L len] [-o homRate] [-e hetRate] [-q qual] <in.fri>\n") if (@ARGV == 0 && -t STDIN);
  my %n;
  while (<>) {
	if (/^(\d+)x/) {
	  my $q = $1*10;
	  my @t = split;
	  if ($opts{o} < 0.1 || $opts{e} < 0.1) {
		$opts{o} = $t[3] / $t[2]; $opts{e} = $t[6] / $t[5];
	  }
	  next if ($q < $opts{q});
	  $n{oe} += $t[2] - $t[3] / $opts{o};
	  $n{ee} += $t[5] - $t[6] / $opts{e};
	  $n{o} += $t[2];
	  $n{e} += $t[5];
	}
  }
  printf("Hom FP: %.2f%% (%d)\n", $n{oe} / $n{o} * 100.0, $n{oe});
  printf("Het FP: %.2f%% (%d)\n", $n{ee} / $n{e} * 100.0, $n{ee});
  printf("All FP: %.2f%% (%d)\n", ($n{oe} + $n{ee}) / ($n{o} + $n{e}) * 100.0, $n{oe} + $n{ee});
  printf("FDR: 1 / %.0f\n", $opts{L}/($n{oe} + $n{ee}));
}

#
# indelsoa command
#

sub evalindelsoa {
  my %opts = (w=>5, s=>3, m=>1);
  getopts('w:s:m:', \%opts);
  die("
Usage:   maq_eval.pl indelsoa [-w $opts{w}] [-s $opts{s}] <true.indel> <predict.indel>\n
Options: -w INT     window size around the true indel [5]
         -s INT     score of SOA indels [3]\n\n") if (@ARGV < 2);
  my ($fn_true, $fn_pred) = @ARGV;
  my (%ins, %del, $fh);
  my $n_all = &read_true_indel($fn_true, \%ins, \%del, $opts{w});
  my @count = (0, 0);
  open($fh, $fn_pred) || die;
  while (<$fh>) {
	my @t = split;
	next if ($t[4] + $t[5] - $t[3] < $opts{s} || $t[3] > $opts{m});
	my $t1 = $t[1] + $t[2];
	if ($del{$t[0],$t[1]} || $ins{$t[0],$t[1]} || $del{$t[0],$t1} || $ins{$t[0],$t1}) {
	  ++$count[0];
	} else {
	  ++$count[1];
	}
  }
  close($fh);
  my $fn = ($n_all == 0)? -1.0 : (1 - $count[0] / $n_all) * 100.0;
  my $fp = ($count[0] + $count[1] == 0)? -1.0 : (1 - $count[0] / ($count[0] + $count[1])) * 100.0;
  printf qq(
IN: $count[0], OUT: $count[1]
FN: %.2f%%
FP: %.2f%%
), $fn, $fp;
}

#
# indelpe command
#

sub evalindelpe {
  my %opts = (w=>20);
  getopts('w:', \%opts);
  die("
Usage:   maq_eval.pl indelpe [-w $opts{w}] <true.indel> <predict.indel>\n
Options: -w INT     window size around the true indel [$opts{w}]\n\n") if (@ARGV < 2);
  my ($fn_true, $fn_pred) = @ARGV;
  my (%ins, %del, $fh);
  my $n_all = &read_true_indel($fn_true, \%ins, \%del);

  my %fhash = ("*"=>0, "+"=>1, "-"=>2);
  my @count = (0, 0, 0, 0, 0, 0);
  my $ow = $opts{w};
  open($fh, $fn_pred) || die;
  while (<$fh>) {
	my @t = split;
	next if ($t[2] eq ".");
	my $flag = $fhash{$t[2]};
	my $i;
	$t[4] =~ s/:[ACGTN]+//i;
	if ($t[4] < 0) {
	  for ($i = $t[1]-1; $i < $t[1] + $ow; ++$i) {
		last if ($del{$t[0],$i});
	  }
	  ++$count[$flag*2 + ($i >= $t[1] + $ow)];
	} else {
	  for ($i = $t[1]-1; $i < $t[1] + $ow; ++$i) {
		last if ($ins{$t[0],$i});
	  }
	  ++$count[$flag*2 + ($i >= $t[1] + $ow)];
	}
  }
  close($fh);
  my $n_called = $count[0] + $count[1] + $count[2] + $count[3];
  my $fn = ($n_all == 0)? -1.0 : ($n_all - $count[0] - $count[1]) / $n_all * 100.0;
  my $fp = ($n_called == 0)? -1.0 : ($count[1] + $count[3]) / $n_called * 100.0;
  print "\n";
  print "Type '*' - IN: $count[0], OUT: $count[1]\n";
  print "Type '+' - IN: $count[2], OUT: $count[3]\n";
  print "Type '-' - IN: $count[4], OUT: $count[5]\n\n";
  printf "*/+ FN: %.2f%%\n", $fn;
  printf "*/+ FP: %.2f%%\n", $fp;
}

sub read_true_indel {
  my ($fn, $ins, $del) = @_;
  my $fh;
  my ($n_ins, $n_del) = (0, 0);
  open($fh, $fn) || die;
  while (<$fh>) {
	my @t = split;
	if ($t[2] eq "-") {
	  ++$n_ins;
	  $ins->{$t[0], $t[1]} = 1;
	}
	if ($t[3] eq "-") {
	  ++$n_del;
	  $del->{$t[0],$t[1]} = 1;
	}
  }
  close($fh);
  print "true insertions: $n_ins\n";
  print "true deletions:  $n_del\n";
  return $n_ins + $n_del;
}

#
# sub command
#

sub evalsub {
  die("Usage: maq_eval.pl sub [-e <.err>] [-g] -p <prefix> <dbSNP.snp> <genotyping.snp> <.snp>\n") if (@ARGV < 4);
  my (%opts, $fh);
  getopts('p:e:gs', \%opts);
  my $is_summary = (defined($opts{s}))? 1 : 0;
  my $is_gnuplot = (defined($opts{g}))? 1 : 0;
  my $err_out = ($opts{e})? $opts{e} : '';
  my $prefix = ($opts{p})? $opts{p} : "es-$$";
  my (%ref_hash, %good_hash, %test_hash);
  &read_snp_file($ARGV[0], \%ref_hash);
  &read_snp_file($ARGV[1], \%good_hash);
  &read_snp_file($ARGV[2], \%test_hash, 1);

  my (@n_hit, @n_in, @n_iden, @n_q, @n_het, @cover);
  my (@n_hom10, @n_het10, @n_homhit10, @n_hethit10, @n_cover10);
  for (my $i = 0; $i != 256; ++$i) { $n_hit[$i] = $n_in[$i] = $n_iden[$i] = $n_q[$i] = $n_het[$i] = $cover[$i] = 0; }
  for (my $i = 0; $i <= 9; ++$i) { $n_hom10[$i] = $n_het10[$i] = $n_homhit10[$i] = $n_hethit10[$i] = $n_cover10[$i] = 0; }

  # calculate how many candidate SNPs are in dbSNPs
  foreach my $pos (keys %test_hash) {
	$test_hash{$pos} =~ /(\S),(\d+)$/;
	my $q10 = int($2/10);
	my $is_het;
	$is_het = ($1 ne 'A' && $1 ne 'C' && $1 ne 'G' && $1 ne 'T')? 1 : 0;
	++$n_q[$2];
	if ($is_het) {
	  ++$n_het[$2]; ++$n_het10[$q10];
	} else { ++$n_hom10[$q10]; }
	if (defined($ref_hash{$pos})) {
	  ++$n_hit[$2];
	  if ($is_het) { ++$n_hethit10[$q10]; }
	  else { ++$n_homhit10[$q10]; }
	}
  }
  # calculate how many ExoSeq SNPs are covered/correct.
  foreach my $pos (keys %good_hash) {
	if (defined($test_hash{$pos})) {
	  $test_hash{$pos} =~ /(\S),(\d+)/;
	  ++$n_in[$2];
	  ++$n_iden[$2] if ($1 eq $good_hash{$pos});
	}
  }
  # accumulate
  for (my $i = 98; $i >= 0; --$i) {
	$n_hit[$i] += $n_hit[$i+1];
	$n_in[$i] += $n_in[$i+1];
	$n_iden[$i] += $n_iden[$i+1];
	$n_q[$i] += $n_q[$i+1];
	$n_het[$i] += $n_het[$i+1];
  }
  # calculate the percetage
  for (my $i = 0; $i <= 99; ++$i) {
	if ($n_q[$i] == 0) {
	  $n_hit[$i] = 100;
	  $n_het[$i] = 100;
	} else {
	  $n_hit[$i] /= $n_q[$i] * .01;
	  $n_het[$i] /= $n_q[$i] * .01;
	}
	if (scalar(keys %good_hash) == 0) {
	  $n_in[$i] = 100;
	  $n_iden[$i] = 100;
	} else {
	  $n_in[$i] /= scalar(keys %good_hash) * .01;
	  $n_iden[$i] /= scalar(keys %good_hash) * .01;
	}
  }
  # read ".err"
  if ($err_out) {
	my ($tot_len, $sum);
	open($fh, $err_out) || die;
	while (<$fh>) {
	  if (/S0 reference length: (\d+)/) {
		$tot_len = $1/1000.0; $sum = 0;
	  } elsif (/S0 number of gaps in the reference: (\d+)/) {
		$tot_len -= $1/1000.0;
	  } elsif (/^S1\s+(\d+)\s+(\S+)\s+(\S+)/) {
		$sum += $2/1000.0;
		$cover[$1] = $sum / $tot_len * 100.0;
		$n_cover10[int($1/10)] += $2 / 1000.0;
	  }
	}
	close($fh);
  }
  # print out to ".txt"
  open($fh, ">$prefix.txt");
  for (my $i = 99; $i >= 0; --$i) {
	my $tmp = ($n_in[$i] == 0)? 100 : $n_iden[$i]/$n_in[$i]*100;
	printf $fh ("$i\t$n_q[$i]\t%.2f\t%.2f\t%.2f\t%.2f\t%.2f\n", $n_hit[$i], $n_in[$i], $tmp,
				$n_het[$i], $cover[$i]);
  }
  close($fh);
  # print out to ".fri"
  open($fh, ">$prefix.fri");
  printf $fh ("Q %12s%8s%8s%8s%8s%8s%8s%8s%8s%8s%8s%12s\n", "coverage", "n_hom", "homHit", "homFrac",
			  "n_het", "hetHit", "hetFrac", "total", "totHit", "totFrac", "totCum", "covCum");
  my ($totSum, $covSum) = (0, 0);
  for (my $i = 9; $i >= 0; --$i) {
	$totSum += $n_hom10[$i]+$n_het10[$i];
	$covSum += $n_cover10[$i];
	my $tmp1 = $n_hom10[$i] > 0? 100.0*$n_homhit10[$i]/$n_hom10[$i] : 100;
	my $tmp2 = $n_het10[$i] > 0? 100.0*$n_hethit10[$i]/$n_het10[$i] : 100;
	my $tmp3 = $n_hom10[$i]+$n_het10[$i] > 0? ($n_homhit10[$i]+$n_hethit10[$i])/($n_hom10[$i]+$n_het10[$i])*100.0 : 100;
	printf $fh ("%dx%12.3f%8d%8d%7.2f%%%8d%8d%7.2f%%%8d%8d%7.2f%%%8d%13.3f\n", $i, $n_cover10[$i], $n_hom10[$i], $n_homhit10[$i],
				$tmp1, $n_het10[$i], $n_hethit10[$i], $tmp2,
				$n_hom10[$i]+$n_het10[$i], $n_homhit10[$i]+$n_hethit10[$i],
				$tmp3, $totSum, $covSum);
  }
  close($fh);
  # plot
  if ($is_gnuplot) {
	my $fn = "$prefix.txt";
	my $y2skip = int($n_q[0]/10+0.5);
	open($fh, "| gnuplot") || die;
	print $fh qq(
set t po eps so co;
set xlab "PHRED quality";
set ylab "Percentage (Cumulated)";
set y2lab "Cumulated Number of SNPs";
set out "$prefix.eps";
set size 1.2,1.2;
set key left bottom;
set yran [0:100];
set ytics 10;
set y2ran [0:$n_q[0]];
set y2tics $y2skip;
set grid;
plot "$fn" u 1:3 t "in_dbSNP%" w l lw 7, "$fn" u 1:4 t "GenoTyping-cover%" w l lw 7, "$fn" u 1:6 t "het%" w l, "$fn" u 1:7 t "coverage%" w l, "$fn" u 1:2 t "n_SNPs" w l ax x1y2, "$fn" u 1:5 t "GenoTyping-exact%" w l;
exit;
\n);
	close($fh);
  }
}

sub evalgeno {
  my %opts = (Q=>40, d=>3, D=>254, q=>20, c=>0.25, n=>20);
  my %ishom = (A=>1, C=>1, G=>1, T=>1, a=>1, c=>1, g=>1, t=>1);
  my %test_hash;
  getopts("Q:q:D:d:c:n:", \%opts);
  die("
Usage:   maq_eval.pl geno [options] <in.geno> <in.snp>\n
Options: -q INT      minimum consensus quality [$opts{q}]
         -Q INT      minimum mapping quality [$opts{Q}]
         -d INT      minimum read depth [$opts{d}]
         -D INT      maximum read depth [$opts{D}]
         -n INT      minimum neighbouring quality [$opts{n}]
\n") if (@ARGV < 2);
  &read_snp_file($ARGV[1], \%test_hash);
  my ($fh, $n_total, $n_seg, @count);
  $n_total = $n_seg = 0;
  open($fh, $ARGV[0]) || die;
  for my $x (0..2) { for (0..9) { $count[$x][$_] = 0; } }
  while (<$fh>) {
	my @t = split;
	++$n_total;
	my $row = ($t[2] eq $t[10])? 0 : (($ishom{$t[10]})? 1 : 2);
	my $is_filt = ($t[5] >= $opts{d} && $t[5] <= $opts{D} && $t[6] >= $opts{c}
				   && $t[7] >= $opts{Q} && $t[4] >= $opts{q} && $t[8] >= $opts{n})? 0 : 1;
	$is_filt = 1 if ($t[2] ne $t[3] && !$test_hash{$t[0],$t[1]}); # correct $is_filt for other filters
	my $col = ($t[2] eq $t[3])? 1 : (($ishom{$t[3]})? 2 : 3);
	$col = 0 if ($is_filt);
	$col = 4 if (lc($t[3]) eq 'n');
	++$n_seg if ($row);
	my $is_wrong = ($t[3] eq $t[10])? 0 : 1;
	$col = $col * 2 + $is_wrong;
	$count[$row][$col]++;
	warn($_) if ($row < 2 && $is_wrong && $col > 1 && $col < 8);
  }
  close($fh);
  #$count[0][0] = ">=$count[0][0]";
  printf "\n# genotyped sites: $n_total\n";
  printf "# segregating sites: $n_seg\n\n";
  printf "%11s%12s%18s%18s%18s%18s\n", "", "filtered", "mono", "hom", "het", "uncalled(N)";
  my @label = ("true_mono", "true_hom", "true_het");
  for my $x (0..2) {
	printf "%11s", $label[$x];
	for my $y (0..4) { printf "%8s / %-7s", $count[$x][2*$y], $count[$x][2*$y+1]; }
	print "\n";
  }
  print "\n";
}

sub read_snp_file {
  my ($fn, $hash2, $is_qual) = @_;
  my $fh;
  open($fh, $fn) || die;
  while (<$fh>) {
	my @t = split;
	next if ($t[2] eq '-' || $t[3] eq '-'); # skip indel sites
	$t[4] = 99 if ($t[4] =~ /^\d+$/ && $t[4] > 99);
	$hash2->{$t[0],$t[1]} = ($is_qual)? "$t[3],$t[4]" : $t[3];
  }
  close($fh);
}

sub usage {
  die qq(
Program: maq_eval.pl (evaluate Maq SNPs/indels)
Version: $version
Contact: Heng Li <lh3\@sanger.ac.uk>\n
Usage:   maq_eval.pl <command> <arguments>\n
Options: sub        evaluate substitutions
         geno       evaluate genotyping results
         indelpe    evaluate indelpe results
\n);
}