19969880948

Committed 05 Dec 2025 04:53PM UTC coverage: 77.132% (-4.1%) from 81.2%

Build # 19969880948

Build Type

Pull #549

github

Committed by

Juke34

Commit Message

add IPC::ShareLite and remove IPC::Shareable and IPC::Open2

Pull Request Pull Request #549: Parallel version of AGAT

Run Details

1332 of 1519 new or added lines in 74 files covered. (87.69%)

647 existing lines in 9 files now uncovered.

12230 of 15856 relevant lines covered (77.13%)

2542.79 hits per line

Source File
Press 'n' to go to next uncovered line, 'b' for previous

41.27

/bin/agat_sp_complement_annotations.pl

#!/usr/bin/env perl

use strict;
use warnings;
use Carp;
use Getopt::Long;
use Pod::Usage;
use List::MoreUtils qw(uniq);
use AGAT::AGAT;

my $header = get_agat_header();
my $config;
my $cpu;
my $start_run = time();
my $opt_output = undef;
my @opt_files;
my $ref = undef;
my $size_min = 0;
my $opt_help= undef;

# OPTION MANAGMENT
my @copyARGV=@ARGV;
if ( !GetOptions(
    'c|config=s'               => \$config,
    'thread|threads|cpu|cpus|core|cores|job|jobs=i' => \$cpu,
    "h|help"                   => \$opt_help,
    "ref|r|i=s"                => \$ref,
    "add|a=s"                  => \@opt_files,
    "size_min|s=i"             => \$size_min,
    "output|outfile|out|o=s"   => \$opt_output))

{
    pod2usage( { -message => 'Failed to parse command line',
                 -verbose => 1,
                 -exitval => 1 } );
}

# Print Help and exit
if ($opt_help) {
    pod2usage( { -verbose => 99,
                 -exitval => 0,
                 -message => "$header\n" } );
}

if (! $ref or ! @opt_files ){
    pod2usage( {
           -message => "$header\nAt least 2 files are mandatory:\n --ref file1 --add file2\n\n",
           -verbose => 0,
           -exitval => 2 } );
}

# --- Manage config ---
initialize_agat({ config_file_in => $config, input => $ref });
$CONFIG->{cpu} = $cpu if defined($cpu);

######################
# Manage output file #
my $gffout = prepare_gffout( $opt_output );

                #####################
                #     MAIN          #
                #####################

######################
### Parse GFF input #

my ($hash_omniscient) = slurp_gff3_file_JD({ input => $ref });

info_omniscient($hash_omniscient);

#Add the features of the other file in the first omniscient. It takes care of name to not have duplicates
foreach my $next_file (@opt_files){
  my ($hash_omniscient2) = slurp_gff3_file_JD({ input => $next_file });
  print ("$next_file GFF3 file parsed\n");
  info_omniscient($hash_omniscient2);

  # Quick stat hash before complement
  my %quick_stat1;
  foreach my $level ( ('level1', 'level2') ){
    foreach  my $tag (keys %{$hash_omniscient->{$level}}) {
      my $nb_tag = keys %{$hash_omniscient->{$level}{$tag}};
      $quick_stat1{$level}{$tag} = $nb_tag;
    }
  }
  
  ####### COMPLEMENT #######
  complement_omniscients($hash_omniscient, $hash_omniscient2, $size_min); # deal with identical ID by renaming them
  print ("\nComplement done !\n");


 #RESUME COMPLEMENT
  my $complemented=undef;
  # Quick stat hash after complement
  my %quick_stat2;
  foreach my $level ( ('level1', 'level2') ){
    foreach  my $tag (keys %{$hash_omniscient->{$level}}) {
      my $nb_tag = keys %{$hash_omniscient->{$level}{$tag}};
      $quick_stat2{$level}{$tag} = $nb_tag;
    }
  }

  #About tag from hash1 added which exist in hash2
  foreach my $level ( ('level1', 'level2') ){
    foreach my $tag (keys %{$quick_stat1{$level}}){
      if ($quick_stat1{$level}{$tag} != $quick_stat2{$level}{$tag} ){
        print "We added ".($quick_stat2{$level}{$tag}-$quick_stat1{$level}{$tag})." $tag(s)\n";
        $complemented=1;
      }
    }
  }
  #About tag from hash2 added which dont exist in hash1
  foreach my $level ( ('level1', 'level2') ){
    foreach my $tag (keys %{$quick_stat2{$level}}){
      if (! exists $quick_stat1{$level}{$tag} ){
        print "We added ".$quick_stat2{$level}{$tag}." $tag(s)\n";
        $complemented=1;
      }
    }
  }
  #If nothing added
  if(! $complemented){
    print "\nNothing has been added\n";
  }
  else{
    print "\nNow the data contains:\n";
    info_omniscient($hash_omniscient);
  }
}

########
# Print results
print_omniscient( {omniscient => $hash_omniscient, output => $gffout} );
#END
print "usage: $0 @copyARGV\n";
my $end_run = time();
my $run_time = $end_run - $start_run;
print "Job done in $run_time seconds\n";
__END__

=head1 NAME

agat_sp_complement_annotations.pl

=head1 DESCRIPTION

The script allows to complement a reference annotation with other annotations.
A l1 feature from the addfile.gff that does not overlap a l1 feature from the reference annotation will be added.
A l1 feature from the addfile.gff without a CDS that overlaps a l1 feature with a CDS from the reference annotation will be added.
A l1 feature from the addfile.gff with a CDS that overlaps a l1 feature without a CDS from the reference annotation will be added.
A l1 feature from the addfile.gff with a CDS that overlaps a l1 feature with a CDS from the reference annotation will be added only if the CDSs don't overlap.
A l1 feature from the addfile.gff without a CDS that overlaps a l1 feature without a CDS from the reference annotation will be added only if none of the l3 features overlap.
/!\ It is sufficiant that only one isoform is overlapping to prevent the whole gene (l1 feature) from the addfile.gff to be added in the output.

=head1 SYNOPSIS

    agat_sp_complement_annotations.pl --ref annotation_ref.gff --add addfile1.gff --add addfile2.gff --out outFile
    agat_sp_complement_annotations.pl --help

=head1 OPTIONS

=over 8

=item B<--ref>,  B<-r> or B<-i>

Input GTF/GFF file used as reference.

=item B<--add> or B<-a>

Annotation(s) file you would like to use to complement the reference annotation. You can specify as much file you want like so: -a addfile1 -a addfile2 -a addfile3
/!\ The order you provide these files matter. Once the reference file has been complemented by file1, this new annotation becomes the new reference that will be complemented by file2 etc.
/!\ The result with -a addfile1 -a addfile2 will differ to the result from -a addfile2 -a addfile1. So, be aware of what you want if you use several addfiles.

=item  B<--size_min> or B<-s>

Option to keep the non-overlping gene only if the CDS size (in nucleotide) is over the minimum size defined. Default = 0 that means all of them are kept.

=item  B<--out>, B<--output>, B<--outfile> or B<-o>

Output gff3 containing the reference annotation with all the non-overlapping newly added genes from addfiles.gff.

=item B<-thread>, B<threads>, B<cpu>, B<cpus>, B<core>, B<cores>, B<job> or B<jobs>

Integer - Number of parallel processes to use for file input parsing (via forking).

=item B<-c> or B<--config>

String - Input agat config file. By default AGAT takes as input agat_config.yaml file from the working directory if any, 
otherwise it takes the orignal agat_config.yaml shipped with AGAT. To get the agat_config.yaml locally type: "agat config --expose".
The --config option gives you the possibility to use your own AGAT config file (located elsewhere or named differently).

=item B<--help> or B<-h>

Display this helpful text.

=back

=head1 FEEDBACK

=head2 Did you find a bug?

Do not hesitate to report bugs to help us keep track of the bugs and their
resolution. Please use the GitHub issue tracking system available at this
address:

            https://github.com/NBISweden/AGAT/issues

 Ensure that the bug was not already reported by searching under Issues.
 If you're unable to find an (open) issue addressing the problem, open a new one.
 Try as much as possible to include in the issue when relevant:
 - a clear description,
 - as much relevant information as possible,
 - the command used,
 - a data sample,
 - an explanation of the expected behaviour that is not occurring.

=head2 Do you want to contribute?

You are very welcome, visit this address for the Contributing guidelines:
https://github.com/NBISweden/AGAT/blob/master/CONTRIBUTING.md

=cut

AUTHOR - Jacques Dainat

1	#!/usr/bin/env perl
2
3	use strict;	6✔
4	use warnings;	6✔
5	use Carp;	6✔
6	use Getopt::Long;	6✔
7	use Pod::Usage;	6✔
8	use List::MoreUtils qw(uniq);	6✔
9	use AGAT::AGAT;	6✔
10
11	my $header = get_agat_header();	6✔
12	my $config;	6✔
13	my $cpu;
14	my $start_run = time();	6✔
15	my $opt_output = undef;	6✔
16	my @opt_files;	6✔
17	my $ref = undef;	6✔
18	my $size_min = 0;	6✔
19	my $opt_help= undef;	6✔
20
21	# OPTION MANAGMENT
22	my @copyARGV=@ARGV;	6✔
23	if ( !GetOptions(	6✔
24	'c\|config=s' => \$config,
25	'thread\|threads\|cpu\|cpus\|core\|cores\|job\|jobs=i' => \$cpu,
26	"h\|help" => \$opt_help,
27	"ref\|r\|i=s" => \$ref,
28	"add\|a=s" => \@opt_files,
29	"size_min\|s=i" => \$size_min,
30	"output\|outfile\|out\|o=s" => \$opt_output))
31
32	{
33	pod2usage( { -message => 'Failed to parse command line',	×
34	-verbose => 1,
35	-exitval => 1 } );
36	}
37
38	# Print Help and exit
39	if ($opt_help) {	6✔
40	pod2usage( { -verbose => 99,	×
41	-exitval => 0,
42	-message => "$header\n" } );
43	}
44
45	if (! $ref or ! @opt_files ){	6✔
46	pod2usage( {	×
47	-message => "$header\nAt least 2 files are mandatory:\n --ref file1 --add file2\n\n",
48	-verbose => 0,
49	-exitval => 2 } );
50	}
51
52	# --- Manage config ---
53	initialize_agat({ config_file_in => $config, input => $ref });	6✔
54	$CONFIG->{cpu} = $cpu if defined($cpu);	6✔
55
56	######################
57	# Manage output file #
58	my $gffout = prepare_gffout( $opt_output );	6✔
59
60	#####################
61	# MAIN #
62	#####################
63
64	######################
65	### Parse GFF input #
66
67	my ($hash_omniscient) = slurp_gff3_file_JD({ input => $ref });	6✔
68
69	info_omniscient($hash_omniscient);	4✔
70
71	#Add the features of the other file in the first omniscient. It takes care of name to not have duplicates
72	foreach my $next_file (@opt_files){	4✔
73	my ($hash_omniscient2) = slurp_gff3_file_JD({ input => $next_file });	4✔
UNCOV 74	print ("$next_file GFF3 file parsed\n");	×
UNCOV 75	info_omniscient($hash_omniscient2);	×
76
77	# Quick stat hash before complement
UNCOV 78	my %quick_stat1;	×
UNCOV 79	foreach my $level ( ('level1', 'level2') ){	×
UNCOV 80	foreach my $tag (keys %{$hash_omniscient->{$level}}) {	×
UNCOV 81	my $nb_tag = keys %{$hash_omniscient->{$level}{$tag}};	×
UNCOV 82	$quick_stat1{$level}{$tag} = $nb_tag;	×
83	}
84	}
85
86	####### COMPLEMENT #######
NEW 87	complement_omniscients($hash_omniscient, $hash_omniscient2, $size_min); # deal with identical ID by renaming them	×
UNCOV 88	print ("\nComplement done !\n");	×
89
90
91	#RESUME COMPLEMENT
UNCOV 92	my $complemented=undef;	×
93	# Quick stat hash after complement
UNCOV 94	my %quick_stat2;	×
UNCOV 95	foreach my $level ( ('level1', 'level2') ){	×
UNCOV 96	foreach my $tag (keys %{$hash_omniscient->{$level}}) {	×
UNCOV 97	my $nb_tag = keys %{$hash_omniscient->{$level}{$tag}};	×
UNCOV 98	$quick_stat2{$level}{$tag} = $nb_tag;	×
99	}
100	}
101
102	#About tag from hash1 added which exist in hash2
UNCOV 103	foreach my $level ( ('level1', 'level2') ){	×
UNCOV 104	foreach my $tag (keys %{$quick_stat1{$level}}){	×
UNCOV 105	if ($quick_stat1{$level}{$tag} != $quick_stat2{$level}{$tag} ){	×
UNCOV 106	print "We added ".($quick_stat2{$level}{$tag}-$quick_stat1{$level}{$tag})." $tag(s)\n";	×
UNCOV 107	$complemented=1;	×
108	}
109	}
110	}
111	#About tag from hash2 added which dont exist in hash1
UNCOV 112	foreach my $level ( ('level1', 'level2') ){	×
UNCOV 113	foreach my $tag (keys %{$quick_stat2{$level}}){	×
UNCOV 114	if (! exists $quick_stat1{$level}{$tag} ){	×
UNCOV 115	print "We added ".$quick_stat2{$level}{$tag}." $tag(s)\n";	×
UNCOV 116	$complemented=1;	×
117	}
118	}
119	}
120	#If nothing added
UNCOV 121	if(! $complemented){	×
UNCOV 122	print "\nNothing has been added\n";	×
123	}
124	else{
UNCOV 125	print "\nNow the data contains:\n";	×
UNCOV 126	info_omniscient($hash_omniscient);	×
127	}
128	}
129
130	########
131	# Print results
UNCOV 132	print_omniscient( {omniscient => $hash_omniscient, output => $gffout} );	×
133	#END
UNCOV 134	print "usage: $0 @copyARGV\n";	×
UNCOV 135	my $end_run = time();	×
UNCOV 136	my $run_time = $end_run - $start_run;	×
UNCOV 137	print "Job done in $run_time seconds\n";	×
138	__END__
139
140	=head1 NAME
141
142	agat_sp_complement_annotations.pl
143
144	=head1 DESCRIPTION
145
146	The script allows to complement a reference annotation with other annotations.
147	A l1 feature from the addfile.gff that does not overlap a l1 feature from the reference annotation will be added.
148	A l1 feature from the addfile.gff without a CDS that overlaps a l1 feature with a CDS from the reference annotation will be added.
149	A l1 feature from the addfile.gff with a CDS that overlaps a l1 feature without a CDS from the reference annotation will be added.
150	A l1 feature from the addfile.gff with a CDS that overlaps a l1 feature with a CDS from the reference annotation will be added only if the CDSs don't overlap.
151	A l1 feature from the addfile.gff without a CDS that overlaps a l1 feature without a CDS from the reference annotation will be added only if none of the l3 features overlap.
152	/!\ It is sufficiant that only one isoform is overlapping to prevent the whole gene (l1 feature) from the addfile.gff to be added in the output.
153
154	=head1 SYNOPSIS
155
156	agat_sp_complement_annotations.pl --ref annotation_ref.gff --add addfile1.gff --add addfile2.gff --out outFile
157	agat_sp_complement_annotations.pl --help
158
159	=head1 OPTIONS
160
161	=over 8
162
163	=item B<--ref>, B<-r> or B<-i>
164
165	Input GTF/GFF file used as reference.
166
167	=item B<--add> or B<-a>
168
169	Annotation(s) file you would like to use to complement the reference annotation. You can specify as much file you want like so: -a addfile1 -a addfile2 -a addfile3
170	/!\ The order you provide these files matter. Once the reference file has been complemented by file1, this new annotation becomes the new reference that will be complemented by file2 etc.
171	/!\ The result with -a addfile1 -a addfile2 will differ to the result from -a addfile2 -a addfile1. So, be aware of what you want if you use several addfiles.
172
173	=item B<--size_min> or B<-s>
174
175	Option to keep the non-overlping gene only if the CDS size (in nucleotide) is over the minimum size defined. Default = 0 that means all of them are kept.
176
177	=item B<--out>, B<--output>, B<--outfile> or B<-o>
178
179	Output gff3 containing the reference annotation with all the non-overlapping newly added genes from addfiles.gff.
180
181	=item B<-thread>, B<threads>, B<cpu>, B<cpus>, B<core>, B<cores>, B<job> or B<jobs>
182
183	Integer - Number of parallel processes to use for file input parsing (via forking).
184
185	=item B<-c> or B<--config>
186
187	String - Input agat config file. By default AGAT takes as input agat_config.yaml file from the working directory if any,
188	otherwise it takes the orignal agat_config.yaml shipped with AGAT. To get the agat_config.yaml locally type: "agat config --expose".
189	The --config option gives you the possibility to use your own AGAT config file (located elsewhere or named differently).
190
191	=item B<--help> or B<-h>
192
193	Display this helpful text.
194
195	=back
196
197	=head1 FEEDBACK
198
199	=head2 Did you find a bug?
200
201	Do not hesitate to report bugs to help us keep track of the bugs and their
202	resolution. Please use the GitHub issue tracking system available at this
203	address:
204
205	https://github.com/NBISweden/AGAT/issues
206
207	Ensure that the bug was not already reported by searching under Issues.
208	If you're unable to find an (open) issue addressing the problem, open a new one.
209	Try as much as possible to include in the issue when relevant:
210	- a clear description,
211	- as much relevant information as possible,
212	- the command used,
213	- a data sample,
214	- an explanation of the expected behaviour that is not occurring.
215
216	=head2 Do you want to contribute?
217
218	You are very welcome, visit this address for the Contributing guidelines:
219	https://github.com/NBISweden/AGAT/blob/master/CONTRIBUTING.md
220
221	=cut
222
223	AUTHOR - Jacques Dainat

NBISweden / AGAT / 19969880948

Source File Press 'n' to go to next uncovered line, 'b' for previous

Source File
Press 'n' to go to next uncovered line, 'b' for previous