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
|
#!/usr/bin/perl
#
# getAnnoFast.pl
# Creates fasta sequence files from the AUGUSTUS output.
#
# This script is used by the braker.pl pipeline.
# Please be extremely careful when changing this script because the braker.pl
# pipeline may fail upon custom modification of this script.
# In case of doubt, contact katharina.hoff@uni-greifswald.de
#
# Mario Stanke, 10.05.2007, last modification by Katharina J. Hoff on Feb 21st 2018
#
use strict;
use Getopt::Long;
my $usage = "getAnnoFasta.pl augustus.gff\n";
$usage .= " Makes a fasta file with protein sequences (augustus.aa)\n";
$usage .= " and one with coding sequences (augustus.codingseq)\n";
$usage .= " from the sequences provided in the comments of the AUGUSTUS output.\n";
$usage .= " These sequence comments are turned on with --protein=on and --codingseq=on, respectively\n";
$usage .= "Options:\n";
$usage .= " --seqfile=s Input a fasta file with the genomic sequences that AUGUSTUS was run on.\n";
$usage .= " When this option is given, an additional file with the individual\n";
$usage .= " coding exon sequences (augustus.cdsexons) is output.\n";
$usage .= " and a file with the complete mRNA including UTRs (augustus.mrna) is output.\n";
$usage .= " --chop_cds for incomplete transcripts: cut off bases before first codon.\n";
$usage .= " This flag only takes effect if coding sequence is not included in the\n";
$usage .= " AUGUSTUS output.\n";
my ($seqname, $trid, $status, $haveCod, $haveAA, $haveCDS, $haveRNA, $seq, $seqfile, $chop_cds);
GetOptions('seqfile=s'=>\$seqfile, 'chop_cds!'=>\$chop_cds);
if ($#ARGV != 0) {
print $usage;
exit;
}
my $separator = ";";
my $augustusfilename = $ARGV[0];
open(AUG, "<$augustusfilename") || die "Couldn't open $augustusfilename\n";
my $stemfilename = $augustusfilename;
$stemfilename =~ s/(\.gff|\.gtf|.gff3|\.txt)//;
my %sequence = (); # Hash with the DNA sequence. The sequence names are the keys.
# Read in the sequence file in one chunk.
# And sort it in the sequence hash.
# Yes, this requires a lot of memory for large genomes.
if ($seqfile){
open (SEQ, "<$seqfile") or die ("Could not open sequence file $seqfile\n");
$/=">";
while (<SEQ>){
s/>$//;
next unless /\S+/;
/(.*)\n/;
$seqname = $1;
my $sequencepart = $'; #'
$seqname =~ s/\s.*//; # seqname only up to first white space
$sequencepart =~ s/\s//g;
$sequence{$seqname} = $sequencepart;
}
print "Read in " . (scalar keys %sequence) . " sequence(s) from $seqfile.\n";
}
$/="\n";
#
# Go through the augustus output transcript by transcript.
#
$haveCod = $haveAA = $haveCDS = $haveRNA = 0;
$status = 0;
my $exonUTRFormat = 0; # UTR implicitly given by exon features
my $UTRFormat = 0; # UTR explicitly given by *UTR features
my $cdsSeq = "";
my $aaSeq = "";
my %cdsnr = ();
my %cdsTx = (); #keys transcript id, values concatenated coding exon sequences
my %mrnaTx = (); #keys transcript id, values concatenated exon sequences (including UTR)
my %strandTx = (); #keys transcript id, values strands
my %frameTx = (); #keys transcript id, values frames
while(<AUG>) {
if ($seqfile && (/^(\S+)\t\S+\t(\S+)\t(\d+)\t(\d+)\t\S+\t(\S+)\t(\S+)\ttranscript_id "([^"]*)"; gene_id "([^"]*)";$/
|| /^(\S+)\t\S+\t(\S+)\t(\d+)\t(\d+)\t\S+\t(\S+)\t(\S+)\t.*Parent=([^;]+)/)){
my $feat = $2;
$seqname = $1;
my $start = $3;
my $end = $4;
my $strand = $5;
my $frame = $6;
$trid=$7;
$trid =~ s/\s$//;
next unless ($feat eq "CDS" || $feat =~ /UTR/ || $feat eq "exon");
# decide whether to use exon or UTR format for mRNA by whether we see UTR or exon first
$UTRFormat = 1 if (!$exonUTRFormat && $feat =~ /UTR/);
$exonUTRFormat = 1 if (!$UTRFormat && $feat eq "exon");
$cdsnr{$trid}++ if ($feat eq "CDS");
my $seqpart = lc(substr($sequence{$seqname}, $start-1, $end - $start + 1));
#print "$seqname $trid CDS $cdsnr{$trid} $start -> $end $seqpart\n";
if ($seqpart ne "") {
# add mRNA if applicable
if (($exonUTRFormat && $feat eq "exon") ||
($UTRFormat && ($feat eq "CDS" || $feat =~ /UTR/))) {
$mrnaTx{$trid} = "" if (!defined($mrnaTx{$trid}));
$mrnaTx{$trid} .= $seqpart;
}
if ($feat eq "CDS"){
if (!$haveCDS) {
open (CDSEXON, ">$stemfilename.cdsexons");
$haveCDS++;
}
$cdsTx{$trid} = "" if (!defined($cdsTx{$trid}));
$cdsTx{$trid} .= $seqpart;
push(@{$frameTx{$trid}}, $frame);
if ($strand eq '-') {
$seqpart = rc($seqpart);
$strandTx{$trid} = $strand;
}
print CDSEXON ">$trid.cds" . $cdsnr{$trid} . "\n$seqpart\n";
}
}
}
if (/^(\S+)\t.*\ttranscript_id "([^"]*)"; gene_id "([^"]*)";$/ ||
/^(\S+)\t.*Parent=([^;]+)/){
$seqname=$1;
$trid=$2;
$trid =~ s/\s$//;
$status=1;
} elsif (/coding sequence = \[(.*)/ && $status == 1){
if ($haveCod == 0) {
open (COD, ">$stemfilename.codingseq");
}
$haveCod++;
$seq = $1;
$seq =~ s/\]$//;
print COD ">$seqname.$trid\n$seq\n";
$status=2;
} elsif ($status == 2 && /^\# ([\w\]]*)$/){
$seq = $1;
$seq =~ s/\]$//;
print COD "$seq\n";
$status=2;
} elsif (/protein sequence = \[(.*)/ && $status >= 1){
if ($haveAA == 0) {
open (AA, ">$stemfilename.aa");
}
$haveAA++;
$seq = $1;
$seq =~ s/\]$//;
# print AA ">$seqname$separator$trid\n$seq\n";
# print AA ">$trid\n";
$aaSeq .= $seq;
if (!/\]/){
$status=3;
} else {
if ($aaSeq ne ""){
print AA ">$trid\n";
print AA getFa($aaSeq, 100);
}
$aaSeq = "";
$status=1;
}
} elsif ($status == 3 && /^\# (.*)/){
$seq = $1;
$seq =~ s/\]$//;
# print AA "$seq\n";
$aaSeq .= $seq;
if (!/\]/){
$status=3;
} else {
if ($aaSeq ne ""){
print AA ">$trid\n";
print AA getFa($aaSeq, 100);
}
$aaSeq = "";
$status=1;
}
}
}
#
# print coding sequences, if not already done (because included in output)
#
if (!$haveCod && scalar(keys %cdsTx)>0){
open (COD, ">$stemfilename.codingseq") or die ("Could not open $stemfilename.codingseq for writing.");
foreach my $trid (sort by_id keys %cdsTx){
print COD ">$trid\n";
my $codingseq = $cdsTx{$trid};
$codingseq = rc($codingseq) if ($strandTx{$trid} eq "-");
if($chop_cds){
if ($strandTx{$trid} eq "-"){
if($frameTx{$trid}[-1] != 0){
$codingseq = substr($codingseq, $frameTx{$trid}[-1]);
}
}else{
if($frameTx{$trid}[0] != 0){
$codingseq = substr($codingseq, $frameTx{$trid}[0]);
}
}
}
print COD getFa($codingseq);
}
}
#
# print mRNA sequences
#
if (scalar(keys %mrnaTx)>0){
open (MRNA, ">$stemfilename.mrna") or die ("Could not open $stemfilename.mrna for writing.");
foreach my $trid (sort by_id keys %mrnaTx){
print MRNA ">$trid\n";
my $mrnaseq = $mrnaTx{$trid};
$mrnaseq = rc($mrnaseq) if ($strandTx{$trid} eq "-");
print MRNA getFa($mrnaseq);
}
}
#
# sort by increasing transcript id
#
sub by_id{
$a =~ /g(\d+)\.t(\d+)/;
my ($ag,$at)=($1,$2);
$b =~ /g(\d+)\.t(\d+)/;
my ($bg,$bt)=($1,$2);
if ($ag>$bg){
return 1;
} elsif ($bg>$ag){
return -1;
} else {
return $at <=> $bt;
}
}
# reverse complement
sub rc{
my $s = shift;
$s = reverse $s;
$s =~ s/a/T/g;
$s =~ s/c/G/g;
$s =~ s/g/C/g;
$s =~ s/t/A/g;
$s = lc $s;
return $s;
}
sub getFa{
my $seq = shift;
my $cols = 100;
$cols = shift if (@_);
my $start = 0;
my $ret = "";
while (length($seq)-$start >= $cols) {
my $shortline = substr($seq, $start, $cols);
$ret .= "$shortline\n";
$start += $cols;
}
$ret .= substr($seq, $start, $cols) . "\n" if ($start<length($seq));
return $ret;
}
|