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
|
#!/usr/bin/env perl
use strict;
use warnings;
use Getopt::Long qw(:config no_ignore_case bundling);
use FindBin;
use Cwd;
######################################################
## Set to base directory of the Trinity installation:
my $BASEDIR = "$FindBin::RealBin/../";
######################################################
my $usage = <<__EOUSAGE__;
##########################################################################################################
#
# Required:
#
# --DE_method <string> DE method (options: edgeR, DESeq2)
#
# --samples_file <string> tab-delimited text file indicating biological replicate relationships.
# ex.
# cond_A cond_A_rep1 A_rep1_left.fq A_rep1_right.fq
# cond_A cond_A_rep2 A_rep2_left.fq A_rep2_right.fq
# cond_B cond_B_rep1 B_rep1_left.fq B_rep1_right.fq
# cond_B cond_B_rep2 B_rep2_left.fq B_rep2_right.fq
#
# # note, Trinity-specific parameter settings should be included in the samples_file like so:
# # (only --max_memory is absolutely required, since defaults exist for the other settings)
# --CPU=6
# --max_memory=10G
# --seqType=fq
# --SS_lib_type=RF
#
#
#
#
# Optional:
#
# -I Interactive mode, waits between commands.
#
###########################################################################################################
__EOUSAGE__
;
my $help_flag;
my $read_samples_descr_file;
my $PAUSE_EACH_STEP = 0;
my $DE_method;
&GetOptions ( 'h' => \$help_flag,
'samples_file=s' => \$read_samples_descr_file,
'I' => \$PAUSE_EACH_STEP,
'DE_method=s' => \$DE_method,
);
if ($help_flag) {
die $usage;
}
unless ($read_samples_descr_file && $DE_method) {
die $usage;
}
unless ($read_samples_descr_file =~ /^\//) {
$read_samples_descr_file = cwd() . "/$read_samples_descr_file";
}
{
## Check for required software
my @needed_tools = qw (R bowtie bowtie-build); # Trinity.pl, RSEM, and samtools are set by relative paths.
my $missing_flag = 0;
foreach my $prog (@needed_tools) {
my $path = `which $prog`;
unless ($path =~ /\w/) {
print STDERR "\n** ERROR, cannot find path to required software: $prog **\n";
$missing_flag = 1;
}
}
if ($missing_flag) {
die "\nError, at least one required software tool could not be found. Please install tools and/or adjust your PATH settings before retrying.\n";
}
}
my $workdir = cwd();
my %PARAMS;
my %conditions_to_read_info = &parse_sample_descriptions($read_samples_descr_file, \%PARAMS);
my @conditions = sort keys %conditions_to_read_info;
##################
## run DE analysis
##################
foreach my $target_type ("trans", "genes") {
my $edgeR_dir = "${DE_method}_${target_type}";
my $cmd = "$BASEDIR/Analysis/DifferentialExpression/run_DE_analysis.pl "
. " --matrix Trinity_${target_type}.counts.matrix "
. " --method $DE_method "
. " --samples_file $read_samples_descr_file "
. " --output $edgeR_dir ";
&process_cmd($cmd, "Running edgeR for $target_type") unless (-d $edgeR_dir);
chdir $edgeR_dir or die "Error, cannot cd to $edgeR_dir";
## extract the diff. expressed transcripts.
$cmd = "$BASEDIR/Analysis/DifferentialExpression/analyze_diff_expr.pl "
. " --matrix ../Trinity_${target_type}.TMM.fpkm.matrix --samples $read_samples_descr_file ";
if (exists $PARAMS{"-P"}) {
$cmd .= " -P " . $PARAMS{"-P"};
}
if (exists $PARAMS{"-C"}) {
$cmd .= " -C " . $PARAMS{"-C"};
}
&process_cmd($cmd, "Running analysis of DE $target_type, hierarchically clustering transcripts and samples");
chdir $workdir or die "Error, cannot cd back to $workdir";
}
print "Done.\n";
exit(0);
####
sub process_cmd {
my ($cmd, $msg) = @_;
if ($msg) {
print "\n\n";
print "#################################################################\n";
print "$msg\n";
print "#################################################################\n";
}
print "CMD: $cmd\n";
if ($PAUSE_EACH_STEP) {
print STDERR "\n\n-WAITING, PRESS RETURN TO CONTINUE ...";
my $wait = <STDIN>;
print STDERR "executing cmd.\n\n";
}
my $time_start = time();
my $ret = system($cmd);
my $time_end = time();
if ($ret) {
die "Error, CMD: $cmd died with ret $ret";
}
my $number_minutes = sprintf("%.1f", ($time_end - $time_start) / 60);
print "TIME: $number_minutes min. for $cmd\n";
return;
}
####
sub parse_sample_descriptions {
my ($read_samples_descr_file, $PARAMS_href) = @_;
my %samples_descr;
open (my $fh, $read_samples_descr_file) or die "Error, cannot open file: $read_samples_descr_file";
while (<$fh>) {
if (/^\#/) { next; }
unless (/\w/) { next; }
s/^\s+|\s+$//g;
chomp;
my @x = split(/\t/);
if (/=/ && scalar(@x) == 1) {
my ($key, $val) = split(/=/, $x[0]);
$PARAMS_href->{$key} = $val;
}
else {
my ($condition, $replicate, $reads_left, $reads_right) = @x;
## remove gzip extension, will convert to gunzipped version later
$reads_left =~ s/\.gz$//;
$reads_right =~ s/\.gz$// if $reads_right;
$samples_descr{$condition}->{$replicate} = [$reads_left, $reads_right];
}
}
close $fh;
return(%samples_descr);
}
|