This file is indexed.

/usr/bin/altree-add-S is in altree 1.3.1-1.

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
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
#!/usr/bin/perl

eval 'exec /usr/bin/perl  -S $0 ${1+"$@"}'
    if 0; # not running under some shell

#Ce programme etiquette les haplotypes malades (ajout d'un G) ou témoins (ajout d'un C), en fonction d'un seuil de malade et témoins qui le porte.
#Le programme prend en entrée un fichier .paup, et redonne un autre .paup

use strict;
use diagnostics;
use warnings;
use Getopt::Long; # qw(:config permute);
use Pod::Usage;
#use Getopt::Std;

our($opt_h,$opt_i, $opt_o, $opt_e, $opt_p, $opt_t, $opt_l, $opt_j, 
    $opt_g, $opt_q);

our $VERSION;
$VERSION = sprintf "0.%03d", q$Revision: 427 $ =~ /(\d+)/g;

sub DefineAncDer {
    my $data_type=shift;
    if ($data_type == 0) {
	my $tem=0;
	my $mal=1;
	return ($tem, $mal);
    } elsif ($data_type == 1) {
	my $tem="C";
	my $mal="G";
	return ($tem, $mal);	
    }
}

sub ReadCorrespond 
{
    my($name_correspond) =shift;
    my $data_qual = shift;
    my($ligne, @tableau);
    my(%correspondance);
    open (CORRESP, '<', $name_correspond) || die "Unable to open file $name_correspond: $!\n";
    while ($ligne=<CORRESP>) {
	chomp($ligne);
	if ($ligne =~ /^$/) {
	    next;
	}

	####### Qualitative data ######
	if ($data_qual eq "quali") {
	    @tableau=split(/\s+/, $ligne);
	    if ($#tableau != 2) {
		die "error in $name_correspond: not 3 columns at line '$ligne'\n";
	    } else {
		$tableau[2]=~ s/c//;
		$tableau[1]=~ s/m//;
		if ($tableau[1] =~ /c/ || $tableau[2] =~ /m/) {
		    die "You have probably exchanged the order of cases and controls in file $name_correspond. It should be: haplo_name m_case_number c_control_number\n";
		}
		$correspondance{$tableau[0]}->{"case"}=$tableau[1]+0;
		$correspondance{$tableau[0]}->{"control"}=$tableau[2]+0;
		
	    }
	} else {
	    ##### Quantitative data #######
	    @tableau = split(/\s+/, $ligne);
	    my @quant_val = splice(@tableau, 1);
	    $correspondance{$tableau[0]}=\@quant_val;
	}
    }
    #my($clefs);
    #DEBUG
   # foreach $clefs (keys %correspondance) {
   # print "$clefs case: ", $correspondance{$clefs}->{"case"}, "\n";
   # 	print "$clefs, control: ",$correspondance{$clefs}->{"control"}, "\n";
   # }
    return(\%correspondance);
}

sub calcul_moyenne_variance
{
    my $correspondance = shift;
    
    my $somme=0;
    my $nb_val=0;
    my $somme_carres=0;
    foreach my $haplo (keys %{$correspondance}) {
	foreach my $elem (@{$correspondance->{$haplo}}) {
	    $nb_val++;
	    $somme+=$elem;
	    $somme_carres+=$elem*$elem;
	}
    }
    my $moyenne = $somme/$nb_val;
    my $variance = $somme_carres/$nb_val-$moyenne*$moyenne;
    return ($moyenne, sqrt($variance));
}

sub calcul_moyenne_nbind
{
    my $tableau = shift;
    
    my $somme = 0;
    my $nb_ind=scalar(@{$tableau});
    foreach my $elem (@{$tableau}) {
	$somme+=$elem;
    }
    return ($somme/$nb_ind, $nb_ind);
}

sub test_quanti_bilateral
{
    my $moy_gen = shift;
    my $ec_type_gen = shift;
    my $moy_loc = shift;
    my $nb_ind_loc = shift;
    my $epsilon = shift;

    if ($moy_loc > ($moy_gen + $epsilon*$ec_type_gen/sqrt($nb_ind_loc))) {
	return "eleve";
    } elsif ($moy_loc < ($moy_gen - $epsilon*$ec_type_gen/sqrt($nb_ind_loc))) {
	return "faible";
    } else {
	return "?";
    }

}

sub travail
{
    
    my($seuil)=shift;
    my($data_type)=shift;
    my($proportion_malades)=shift;
    my $low =shift;
    my $name_correspond=shift;
    my $outgroup = shift;
    my $data_qual = shift;
    my($ligne);
    my($temoin, $malade, $sequence, $nom, $debut, $ancetre);
    my($anc, $num_car, $prop_mal, $prop_tem);
    my(@tableau, @tab2);
    my($tem, $mal)=DefineAncDer($data_type);
    my($correspondance)=ReadCorrespond($name_correspond,$data_qual);

   #foreach my $clefs (keys %{$correspondance}) {
#	print "$clefs case ", $correspondance->{$clefs}->{"case"}, "\n";
#    	print "$clefs, control ",$correspondance->{$clefs}->{"control"}, "\n";
#    }
    my $found_outgroup=0;
    my $ici = 0;
    my $phylo_prog= "Phylip";
    my $compteur=0;
    while ($ligne=<STDIN>){
	chomp($ligne);
	if ($ligne =~/^$/) {
	    next;
	}
	$compteur++;
	my $diese='#';
	if ($ligne =~ /^\s*$diese[N|n]exus\s*$/) {
	    $phylo_prog="PAUP";
	} 	
	if ($phylo_prog eq "PAUP") {
	    if ($ligne =~ /^\s*matrix\s*$/) {
		print $ligne, "\n";
		$ici=1;
		next
	    }
	    if ($ligne =~ /^\s*;\s*$/) {
		
		$ici=0;
	    }
	    if ($ligne =~ /^\s*\[/) {
		next;
	    }
	} else {
	    if ($compteur>1) {
		$ici=1;
	    } 
	}
	    
	if ($ici==0 && $phylo_prog eq "PAUP") {
	    if ($ligne =~ /dimension ntax=([0-9]+)\s+nchar=([0-9]+);/) {
		$num_car=$2+1;
		print "dimension ntax=$1 nchar=", $num_car, ";\n";
	    }elsif ($ligne =~ /format symbols=\"([0-9ATGCU]+)\"/) {
		my($format)=$1;
		my($format_old)=$1;
		$format =~ tr/GC//d;
		$ligne =~ s/$format_old/${format}CG/;
		print $ligne, "\n";
	    } elsif ($ligne =~ /ancstates\s+\*anc\s+vector\s*=\s*([0-9ATCG]+)\s*;/) {
		$anc=$1;
		$anc=$anc."?";
		$ligne =~ s/$1/$anc/;
		print $ligne,"\n";
	    } elsif ($ligne=~ /begin paup;/) {
		print $ligne,"\n";
		print "exclude $num_car; \n";
	    } elsif ($ligne=~ /\s*describetrees/) {
		print "include $num_car;\n";
		print $ligne,"\n";
	    } elsif ($ligne =~ /^\s*([0-9]+)\s+([0-9]+)$/) {
		$num_car=$2+1;
		print "$1\t$num_car\n";
	    } else {
		print $ligne, "\n";
	    }
	} elsif ($ici==0 && $phylo_prog eq "Phylip") {
	    if ($ligne =~ /^\s*([0-9]+)\s+([0-9]+)\s*$/) {
		print $1, "\t", $2+1, "\n";
	    } else {
		die "Strange line $ligne in Phylip file\n";
	    }
	} elsif ($ici==1) {
	    if ($ligne =~ /^\s+$/) {
		next;
	    }  elsif ($ligne =~ /^\s*\[.+\]$/) {
	#	print STDERR "TTTTT\n";
		next;
	    } 	    else {
		@tableau=split(/\s+/, $ligne);
		$sequence=$tableau[1];
		$nom=$tableau[0];
		#DEBUG	print "$nom $outgroup\n";
		if ($nom eq $outgroup){
		    #	$ancetre=$sequence."?";
		    print "$nom  $sequence?\n";
		    $found_outgroup++;
		    next;
		}
		#    } else {
		#if ($debut =~ /^\s*H[0-9]{3}_m[0-9]{3}_c[0-9]{3}/) {
		#   @tab2=split(/_/,$debut);
		# print $tab2[0],"\n";
		#  $temoin=$tab2[2];
		# $temoin =~ s/c//;
		# print STDERR "temoin=$temoin\n";
		# $malade=$tab2[1];
		# $malade =~ s/m//;
		# if ($malade =~ /c/ || $temoin =~ /m/) {
		#	die "You have probably interverti cases and controls in file correspond.txt. It should be: haplo_name m_case_number c_control_number\n";
		#   }
#		if ($debut eq $anc_name){
#		    $found_anc++;
#		}	
		#$nom=$tableau[0];
		#	print "$nom\n";

		###### QUALITATIVE ######
		if ($data_qual eq "quali") {
		    if (not exists ($correspondance->{$nom})){
			print STDERR "$nom is not found in the file $name_correspond. Assuming it is the outgroup.\nThe number of cases and controls affected to this sequence is set to 0\n";
			$correspondance->{$nom}->{"case"}=0;
			$correspondance->{$nom}->{"control"}=0;  
		    }
		    $malade=$correspondance->{$nom}->{"case"};
		    $temoin=$correspondance->{$nom}->{"control"};
		    
		    if ($malade == 0 && $temoin == 0) {
			print STDERR "$nom is carried by 0 cases and 0 controls. The state ? has been attributed to the S character\n";
			$sequence.="?";
			print "$nom  ", $sequence, "\n";
			next;
		    }
		    
		    
		    #	print " $nom mal=$malade\n";   
		    $prop_mal=$malade/($malade+$temoin);
		    $prop_tem=$temoin/($malade+$temoin);
		    #	print "M=$malade T=$temoin\n";
		    #print "test=$test\n";
		    #	if ($test==0) { # test: difference |mal-tem| >=seuil 
		    #    if ($malade > $temoin && $malade-$temoin>=$seuil) {
		    #$sequence.="G";
		    #    } elsif ($malade < $temoin && $temoin-$malade>=$seuil) {
		    #	$sequence.="C";
		    #    } else {
		    #	$sequence.="?";
		    #    }
		    #} elsif ($test==1) {
		    #  if ($malade+$temoin==1) {
		    #$sequence.="?";
		    if ( $malade+$temoin <= $low) {
			$sequence.="?";
		    }  else {
			if ($prop_mal>$proportion_malades+
			    $seuil*sqrt($prop_mal*$prop_tem/($malade+$temoin))) {
			    $sequence.=$mal;
			} elsif ($prop_mal<$proportion_malades-
				 $seuil*sqrt($prop_mal*$prop_tem/($malade+$temoin))) {
			    $sequence.=$tem;
			} else {
			    $sequence.="?";
			}   
			#}
		    }
		    
		    print "$nom  ", $sequence, "\n";
		    #"_m$malade", "_c$temoin\t", $sequence, "\n";
		} else {
		    ###### QUANTITATIVE #######
		    if (not exists ($correspondance->{$nom})){
			print STDERR "$nom is not found in the file". 
			    "$name_correspond\n"; 	
		    }
		    my ($moyenne_gen, $ec_type) = calcul_moyenne_variance
			($correspondance);
		    my ($moyenne_loc, $nb_ind)= calcul_moyenne_nbind
			($correspondance->{$nom});
		    #DEBUG print "$nom\n";
		    #DEBUG print "Moyenne: $moyenne_gen\n";
		    #DEBUG print "Variance: $ec_type\n";
		    #DEBUG print "Moyenne locale: $moyenne_loc\n";
		    #DEBUG print "nb_ind: $nb_ind\n";
		    if ($nb_ind <= $low) {
			$sequence.="?";
		    }  else {
			if (test_quanti_bilateral($moyenne_gen, $ec_type, $moyenne_loc, $nb_ind, $seuil) eq "eleve") {
			    $sequence.=$mal;
			} elsif (test_quanti_bilateral($moyenne_gen, $ec_type, $moyenne_loc, $nb_ind, $seuil) eq "faible") {
			    $sequence.=$tem; 
			} else {
			    $sequence.="?";
			}
		    }
		    print "$nom  ", $sequence, "\n";
		}
	    } 
	}
    }
    #print "anc? $found_anc\n";
   if ($found_outgroup==0 && $outgroup ne "nooutgroup") {
	die "outgroup not found in the file\n";
    } elsif ($found_outgroup ==1 && $outgroup eq "noanc") {
	die " false outgroup found\n";
    } elsif ($found_outgroup > 1) {
	die "Too many outgroups found ($found_outgroup outgroup)";
    }
}

sub usage {
    my $msg =shift;
    my($progname) =shift;
    print STDERR "Error! ".$msg;
    print STDERR "usage :$progname [options]\n";
    print STDERR " Options :\n";
    print STDERR "    [-h]  this help\n";
    print STDERR "     -i   input file\n";
    print STDERR "     -j   input2 file (correspond.txt)\n";
    print STDERR "     -o   output file\n";
    print STDERR "     -t   data type: SNP or DNA\n";
# ancienne option -t test: 0= mal-tem>seuil 1= seuil proportion0+/-sqr(pq/n)]
    print STDERR "     -p   proportion of cases in the whole data set\n";
    print STDERR "     -e   epsilon parameter\n";
    print STDERR "     -q   quantitative or qualitative data\n";
    print STDERR "    [-g]  name of the outgroup\n"; 
    print STDERR "     -l   if an haplotype is present equal or less than -l times, the state of S will be set to ?\n"; 
}

sub main
{
    my($progname);
    my($seuil, $test, $proportion);
    
    my %options= (
    	"first-input-file" => \$opt_i,
	"second-input-file" => \$opt_j,
	"output-file" => \$opt_o,
	"epsilon" => \$opt_e,
	"data-type" => \$opt_t,
	"proportion" => \$opt_p,
	"outgroup" => \$opt_g,
	"low" => \$opt_l,
	"data-qual" => \$opt_q,
	);
    	
    #getopts('ho:i:j:e:t:p:l');
    GetOptions (\%options,
		"version",
		"short-help|h",
		"help",
		"man",
		"first-input-file|i=s",
                "second-input-file|j=s",
                "output-file|o=s",
		"epsilon|e=s",
		"data-type|t=s",
		"proportion|p=s",
		"outgroup|g=s",
		"low|l=i",
		"data-qual|q=s",
		) or pod2usage(2);
    if (defined($options{"version"})) {
	print $0, " version ", $VERSION, "\n";
	print "(Perl version ", $], ")\n";
	exit 0;
    }
    if (defined($options{"short-help"})) {
	pod2usage(-exitstatus => 0, -verbose => 0);
    }
    if (defined($options{"help"})) {
	pod2usage(-exitstatus => 0, -verbose => 1);
    }
    if (defined($options{"man"})) {
	pod2usage(-exitstatus => 0, -verbose => 2);
    }
    
    if ($opt_i) {
	open(STDIN, '<', $opt_i) or die "Impossible to open $opt_i : $!" ;
    }

    my $correspond_name;
    if ($opt_j) {
	$correspond_name=$opt_j;
    } else {
	$correspond_name="correspond.txt"
	}
    if ($opt_o) {
	open(STDOUT, '>', $opt_o) or die "Impossible to open $opt_o : $!" ;
    }
    if ($opt_e) {
	$seuil=$opt_e;
    } else {
	usage("The epsilon parameter is not defined!!\n", $progname);
    } 
    my($data_type);
    if (defined($opt_t)) {
	if ($opt_t =~ /[Dd][Nn][Aa]/) {
	    $data_type=1;
	} elsif ($opt_t =~ /[Ss][Nn][Ps]/) {
	    $data_type=0;
	} else {
	    usage("The data type (SNP or DNA) is missing\n", $progname);
	}
	# if (defined($opt_t)) {
	#	if ($opt_t==0) {
	#	    $test=0;
	#	} elsif ($opt_t==1) {
	#	    $test=1;
	#	} else {
	#	    $test=-999;
	#	    print STDERR "illegal value of opt_t\n";
	#	}
	#  } else {
	#	die "manque le numero du test: 0: mal-tem=seuil  1: seuil=P0+/-sqr(pq/n)!!\n";
	# }    
	
	my($low);
	# Si $low !=0, if only one case or one control, then the state of S is ?
	if (not defined $opt_l) {
	    die "The minimum number of haplotype should be set by -l\n"; 
	} else {
	    $low=$opt_l;
	}
	
	my $data_qual;
	if (!$opt_q) {
	    die "data-qual must be specified\n";
	} elsif ($opt_q eq "qualitative") {
	    $data_qual="quali";
	} elsif ($opt_q eq "quantitative") {
	    $data_qual="quanti";
	} else {
	    die "Invalid value for data-qual (opt_q)\n";
	}
	
	if ($data_qual eq "quali") { 
	    if ($opt_p) {
		$proportion=$opt_p;
	    } else {
		usage("The proportion of cases in the sample is missing!\n", $progname);
	    }
	}
	my $outgroup="nooutgroup";
	if ($opt_g) {
	    $outgroup = $opt_g;
	}    
	travail($seuil, $data_type,  $proportion, $low, $correspond_name, $outgroup, $data_qual);
	
    }
}


main;

__END__
    
=head1 NAME

altree-add-S - Title...

=head1 SYNOPSIS

altree-add-S [options]

 Options:
    --version             program version
    --short-help|h        brief help message
    --help                help message with options descriptions
    --man                 full documentation
    --first-input-file|i  input file 1
    --second-input-file|j input file 2 data concerning the trait (qualitative or quantitative)
    --output-file|o       output file
    --epsilon|e           epsilon value
    --data-type|t         data type: SNP or DNA
    --proportion|p        proportion of cases in the sample (for qualitative data only)
    --data-qual|q         data type: qualitative or quantitative
    [--outgroup|g]        name of the outgroup
    --low|l               if an haplotype is present equal or less than -l times, the state of S will be set to "?"
    

=head1 OPTIONS

=over 8

=item B<--version>

Print the program version and exits.

=item B<--short-help>

Print a brief help message and exits.

=item B<--help>

Print a help message with options descriptions and exits.

=item B<--man>

Prints the manual page and exits.

=item B<--first-input-file|i>

Input file 1 (paup or phylip file)

=item B<--second-input-file|j>

Input file 2, contains the number of times a given haplotypes is carried by  case and control individuals (qualitative data) or the quantitative values correqsponding to a givent haplotype (quantitative data)

=item B<--output-file|o>

Output file

=item B<--epsilon|e>

espilon parameter (see formula in the documentation)

=item B<--data-type|t>  

Type of data: DNA (ATGCU) or SNP (0-1)

=item B<--proportion|p>

Proportion of case individuals in the sample

=item B<--outgroup|g>

Name of the outgroup (if it is not in the file containing the number of cases and controls per haplotype)

=item B<--data-qual|q> 

Specify if the data are qualitative or quantitative

=item B<--low|l>

if an haplotype is present equal or less than -l times, the state of S will be set to "?"

=back

=head1 DESCRIPTION

B<This program> adds a new character (called "character S") to each haplotype in the input file according to the number of cases and controls carrying it.  

=cut