|
50
|
1 #!/usr/bin/perl -w
|
|
|
2 my $version=1.00;
|
|
|
3 use strict;
|
|
|
4 use warnings;
|
|
|
5 use Getopt::Long;
|
|
|
6 use Getopt::Std;
|
|
|
7 use threads;
|
|
|
8 use threads::shared;
|
|
|
9 use Parallel::ForkManager;
|
|
|
10 use lib '/leofs/biotrans/chentt/perl_module/';
|
|
|
11 #perl ../siRNA.pl -i config -g /leofs/biotrans/projects/rice/smallRNA/sRNA_package/bin/test/ref/genome.fa -f /share_bio/hs4/disk3-4/Reference/Plants/Rice_TIGR/Reference/TIGR/version_6.1/all.dir/all.gff3 -path /leofs/biotrans/projects/rice/smallRNA/sRNA_package/bin/ -o /leofs/biotrans/projects/rice/smallRNA/sRNA_package/bin/test -t 3 -rfam /leofs/biotrans/projects/rice/smallRNA/sRNA_package/bin/test/ref/Rfam.fasta -idx /leofs/biotrans/projects/rice/smallRNA/sRNA_package/bin/test/ref/genome -idx2 /leofs/biotrans/projects/rice/smallRNA/sRNA_package/bin/test/ref/rfam -deg deg -n 25 -nat class/nat_1 -repeat class/repeat_1 -cen centromere_TIGR.txt -format fastq
|
|
|
12 print "
|
|
|
13 #####################################
|
|
|
14 # #
|
|
|
15 # sRNA cluster #
|
|
|
16 # #
|
|
|
17 #####################################
|
|
|
18 ";
|
|
|
19 ###########################################################################################
|
|
|
20 my $usage="$0
|
|
|
21 Options:
|
|
|
22 -i input file# fasta
|
|
|
23 -config input file
|
|
|
24 -g genome file
|
|
|
25 -f gff file
|
|
|
26
|
|
|
27 -o workdir file
|
|
|
28 -path script path
|
|
|
29 -t int, number of threads [1]
|
|
|
30 -format fastq, fq, fasta or fa
|
|
|
31 -idx string, genome file index, file-prefix #(must be indexed by bowtie-build) The parameter
|
|
|
32 string must be the prefix of the bowtie index. For instance, if
|
|
|
33 the first indexed file is called 'h_sapiens_37_asm.1.ebwt' then
|
|
|
34 the prefix is 'h_sapiens_37_asm'.##can be null
|
|
|
35 -mis int number of allowed mismatches when mapping reads to genome, default 0
|
|
|
36
|
|
|
37 -n int max hits number,default 25; used in genome alignment
|
|
|
38 -d int distance of tag to merged a cluster; default 100
|
|
|
39 -p cluster method F :conventional default is F
|
|
|
40 T :NIBLES
|
|
|
41 -l int the length of the upstream and downstream,default 1000;used in position annotate
|
|
|
42
|
|
|
43 -nat natural antisense transcripts file
|
|
|
44 -repeat repeat information file out of Repeatmasker
|
|
|
45 -deg file config of de sample
|
|
|
46 -cen centromere file input
|
|
|
47 -span plot span, default 50000
|
|
|
48 ";
|
|
|
49
|
|
|
50 my %options;
|
|
|
51 GetOptions(\%options,"i:s","config=s","g=s","f=s","o=s","path:s","p=s","format=s","nat:s","repeat:s","deg:s","n:i","mis:i","t:i","d:i","l:i","idx:s","cen:s","span:s","h");
|
|
|
52 #print help if that option is used
|
|
|
53 if($options{h}){die $usage;}
|
|
|
54
|
|
|
55 my $filein=$options{'i'};
|
|
|
56
|
|
|
57 #my $config=$options{'i'};
|
|
|
58 my $genome_fa=$options{'g'};
|
|
|
59 my $gff=$options{'f'};
|
|
|
60
|
|
|
61
|
|
|
62 ##########################################################################################
|
|
|
63 my $predir=`pwd`;
|
|
|
64 chomp $predir;
|
|
|
65 my $workdir=defined($options{'o'}) ? $options{'o'}:$predir;
|
|
|
66
|
|
|
67 my $path=$options{'path'};
|
|
|
68
|
|
|
69 my $t=defined($options{'t'})? $options{'t'}:1; #threads number
|
|
|
70
|
|
|
71 my $mis=defined $options{'mis'} ? $options{'mis'}:0;
|
|
|
72
|
|
|
73
|
|
|
74 my $hit=defined $options{'n'}?$options{'n'}:25;
|
|
|
75
|
|
|
76 my $distance_of_merged_tag=defined $options{'d'} ? $options{'d'}:100;
|
|
|
77
|
|
|
78 my $up_down_dis=defined $options{'l'} ?$options{'l'}:1000;
|
|
|
79
|
|
|
80 my $cluster_mothod=defined $options{'p'}?$options{'p'}:"F";
|
|
|
81
|
|
|
82 my $format=$options{'format'};
|
|
|
83 #if ($format ne "fastq" && $format ne "fq" && $format ne "fasta" && $format ne "fa") {
|
|
|
84 # die "Parameter \"-format\" is error! Parameter is fastq, fq, fasta or fa\n";
|
|
|
85 #}
|
|
|
86
|
|
|
87
|
|
|
88
|
|
|
89 my $sample_number;
|
|
|
90 my ($dir,$dir_tmp);
|
|
|
91 ################################ MAIN ##################################################
|
|
|
92 print "\ncluster program start:";
|
|
|
93 my $time=Time();
|
|
|
94 make_dir_tmp();
|
|
|
95
|
|
|
96 my $mark;
|
|
|
97 my $sample_mark;
|
|
|
98
|
|
|
99 my $config=$opts{'config'};
|
|
|
100 my (@filein,@mark);
|
|
|
101 &read_config();
|
|
|
102 $sample_number=@mark;
|
|
|
103 $mark=join "\t",@mark;
|
|
|
104 $sample_mark=join "\#",@mark;
|
|
|
105
|
|
|
106
|
|
|
107
|
|
|
108 my $data3=$filein; ### rfam not mapped reads
|
|
|
109 genome();
|
|
|
110
|
|
|
111 my $bed=$dir."cluster\/"."sample\.bed";
|
|
|
112 my $read=$dir."cluster\/"."sample_reads\.cluster";
|
|
|
113 my $read_txt=$dir."cluster\/"."cluster\.txt";
|
|
|
114 my $rpkm=$dir."cluster\/"."sample_rpkm\.cluster";
|
|
|
115 my $preprocess;
|
|
|
116 my $cluster_file;
|
|
|
117 my $annotate_dir;
|
|
|
118 my $deg_dir;
|
|
|
119 my $plot_dir;
|
|
|
120 my %id;
|
|
|
121 for (my $i=0;$i<@mark ;$i++) {
|
|
|
122 $id{$mark[$i]}=$i+4;
|
|
|
123 }
|
|
|
124
|
|
|
125
|
|
|
126 my @map_read;
|
|
|
127 my $map_tag=0;
|
|
|
128
|
|
|
129 bwt2bed();
|
|
|
130
|
|
|
131 cluster();
|
|
|
132
|
|
|
133 quantify();
|
|
|
134
|
|
|
135 phase();
|
|
|
136
|
|
|
137 if (defined($options{'nat'})&&defined($options{'repeat'})) {
|
|
|
138 class();
|
|
|
139 }
|
|
|
140 else{
|
|
|
141 get_genelist();
|
|
|
142 }
|
|
|
143
|
|
|
144 annotate();
|
|
|
145
|
|
|
146 genome_length();
|
|
|
147
|
|
|
148 plot();
|
|
|
149
|
|
|
150 my @pairdir;
|
|
|
151 if (defined($options{'deg'})) {
|
|
|
152 dec();
|
|
|
153 infor_merge();
|
|
|
154 }
|
|
|
155 else{infor_merge_no_dec()}
|
|
|
156 html();
|
|
|
157 print "\ncluster program end:";
|
|
|
158 Time();
|
|
|
159 ############################sub program###################################################
|
|
|
160 sub make_dir_tmp{
|
|
|
161
|
|
|
162 #make temporary directory
|
|
|
163 if(not -d "$workdir\/cluster_runs"){
|
|
|
164 mkdir("$workdir\/cluster_runs");
|
|
|
165 mkdir("$workdir\/cluster_runs\/ref\/");
|
|
|
166 }
|
|
|
167
|
|
|
168 $dir="$workdir\/cluster_runs\/";
|
|
|
169 #print STDERR "mkdir $dir\n\n";
|
|
|
170 return;
|
|
|
171 }
|
|
|
172
|
|
|
173 sub genome{
|
|
|
174 if(defined $options{'idx'}){
|
|
|
175 system("perl $path\/matching.pl -i $data3 -g $genome_fa -v $mis -p $t -r $hit -o $dir -index $options{idx}") ;
|
|
|
176 }else{
|
|
|
177 system("perl $path\/matching.pl -i $data3 -g $genome_fa -v $mis -p $t -r $hit -o $dir ") ;
|
|
|
178 }
|
|
|
179 #=================== mapping sta ===================================================
|
|
|
180 my $map_file=$dir."genome_match\/genome_mapped\.fa";
|
|
|
181 open (MAP,"<$map_file")||die"$!";
|
|
|
182 print "\n#each sample mapping reads sta:\n\n";
|
|
|
183 print "#$mark\ttotal\n";
|
|
|
184 while (my $ID=<MAP>) {
|
|
|
185 chomp $ID;
|
|
|
186 my @tmp=split/\:/,$ID;
|
|
|
187 my @exp=split/\_/,$tmp[1];
|
|
|
188 $exp[-1] =~ s/^x//;
|
|
|
189 for (my $i=0;$i<@exp ;$i++) {
|
|
|
190 $map_read[$i]+=$exp[$i];
|
|
|
191 }
|
|
|
192 $map_tag++;
|
|
|
193 my $seq=<MAP>;
|
|
|
194 }
|
|
|
195 my $map_read=join"\t",@map_read;
|
|
|
196 print "$map_read\n\n";
|
|
|
197 print "#total mapped tags:$map_read\n\n";
|
|
|
198 close MAP;
|
|
|
199 return 0;
|
|
|
200 }
|
|
|
201
|
|
|
202 sub bwt2bed{
|
|
|
203 $cluster_file=$dir."cluster\/";
|
|
|
204 mkdir ("$cluster_file");
|
|
|
205 print "sam file changed to bed file\n";
|
|
|
206 my ($file) = $dir."genome_match\/genome_mapped\.bwt";
|
|
|
207
|
|
|
208 my $sam2bed=`perl $path\/sam2Bed_bowtie.pl -i $file -mark $sample_mark -o $bed `;
|
|
|
209 print "perl $path\/sam2Bed_bowtie.pl -i $file -mark $sample_mark -o $bed\n\n";
|
|
|
210 return 0;
|
|
|
211 }
|
|
|
212
|
|
|
213 sub cluster{
|
|
|
214 print "tags is ready to merged clusters\n\n";
|
|
|
215 my ($file) =$bed;
|
|
|
216 if ($cluster_mothod eq "F") {
|
|
|
217 my $cluster=`perl $path\/conventional.pl -i $file -d $distance_of_merged_tag -n $sample_number -mark $sample_mark -o $read -t $read_txt`;
|
|
|
218 print "Using converntional method\n perl $path\/conventional.pl -i $file -d $distance_of_merged_tag -n $sample_number -mark $sample_mark -o $read -t $read_txt\n\n";
|
|
|
219 }
|
|
|
220 elsif($cluster_mothod eq "T"){
|
|
|
221 my $cluster=`perl $path\/nibls.pl -f $file -m $distance_of_merged_tag -o $read -t $read_txt -k $sample_mark`;
|
|
|
222 print "Using nibls method\n perl $path\/nibls.pl -f $file -m $distance_of_merged_tag -o $read -t $dir\/cluster.txt -k $sample_mark\n\n";
|
|
|
223 }
|
|
|
224 else{print "\-p is wrong!\n\n";}
|
|
|
225 return 0;
|
|
|
226 }
|
|
|
227
|
|
|
228
|
|
|
229 sub quantify{
|
|
|
230 print "clusters is ready to quantified\n\n";
|
|
|
231 my @depth=@map_read;
|
|
|
232 pop @depth;
|
|
|
233 my $depth=join ",",@depth;
|
|
|
234 my $quantify=`perl $path\/quantify.pl -i $read -d $depth -o $rpkm`;
|
|
|
235 print "perl $path\/quantify_siRNA.pl -i $read -d $depth -o $rpkm\n\n\n";
|
|
|
236 return 0;
|
|
|
237 }
|
|
|
238
|
|
|
239 sub phase{
|
|
|
240 $annotate_dir=$dir."annotate\/";
|
|
|
241 mkdir ("$annotate_dir");
|
|
|
242 print "clusters is to predict phase siRNA\n";
|
|
|
243 my $phase=`perl $path\/phased_siRNA.pl -i $read_txt -o $annotate_dir\/phase.out`;
|
|
|
244 print "perl $path\/phased_siRNA.pl -i $read_txt -o $annotate_dir\/phase.out\n\n\n";
|
|
|
245 return 0;
|
|
|
246 }
|
|
|
247
|
|
|
248 sub class{
|
|
|
249 print "clusters is ready to annotate by sources\n\n";
|
|
|
250 my $nat=$options{'nat'};
|
|
|
251 my $repeat=$options{'repeat'};
|
|
|
252 my $class=`perl $path\/ClassAnnotate.pl -i $rpkm -g $gff -n $nat -r $repeat -p $annotate_dir\/phase.out -o $annotate_dir\/sample_class.anno -t $annotate_dir\/nat.out -l $dir\/ref\/genelist.txt`;
|
|
|
253 print "perl $path\/ClassAnnotate.pl -i $rpkm -g $gff -n $nat -r $repeat -p $annotate_dir\/phase.out -o $annotate_dir\/sample_class.anno -t $annotate_dir\/nat.out -l $dir\/ref\/genelist.txt\n\n";
|
|
|
254 }
|
|
|
255
|
|
|
256 sub annotate{
|
|
|
257 print "clusters is ready to annotate by gff file\n\n";
|
|
|
258 my $file;
|
|
|
259 if (defined($options{'nat'})&&defined($options{'repeat'})) {
|
|
|
260 $file="$annotate_dir\/sample_class.anno";
|
|
|
261 }
|
|
|
262 else{
|
|
|
263 $file=$rpkm;
|
|
|
264 }
|
|
|
265 my $annotate=`perl $path\/Annotate.pl -i $file -g $dir\/ref\/genelist.txt -d $up_down_dis -o $annotate_dir\/sample_c_p.anno`;
|
|
|
266 print "perl $path\/Annotate.pl -i $file -g $dir\/ref\/genelist.txt -d $up_down_dis -o $annotate_dir\/sample_c_p.anno\n\n";
|
|
|
267 return 0;
|
|
|
268 }
|
|
|
269 sub get_genelist{
|
|
|
270
|
|
|
271 my $get_genelist=`perl $path\/get_genelist.pl -i $gff -o $dir\/ref\/genelist.txt`;
|
|
|
272 print "perl $path\/get_genelist.pl -i $gff -o $dir\/ref\/genelist.txt";
|
|
|
273 }
|
|
|
274
|
|
|
275 sub dec{
|
|
|
276 print "deg reading\n\n";
|
|
|
277 my $deg_file=$options{'deg'};
|
|
|
278 open IN,"<$deg_file";
|
|
|
279 my @deg;
|
|
|
280 my $s=0;
|
|
|
281 while (my $aline=<IN>) {
|
|
|
282 chomp $aline;
|
|
|
283 next if($aline=~/^\#/);
|
|
|
284 $deg[$s]=$aline;
|
|
|
285 my @ea=split/\s+/,$aline;
|
|
|
286 push @pairdir,"$ea[0]_VS_$ea[1]\/";
|
|
|
287 #print "$deg[$s]\n";
|
|
|
288 $s++;
|
|
|
289 }
|
|
|
290 close IN;
|
|
|
291 $deg_dir=$dir."deg\/";
|
|
|
292 mkdir ("$deg_dir");
|
|
|
293 my $max_process = 10;
|
|
|
294 my $pm = new Parallel::ForkManager( $max_process );
|
|
|
295 my $number=@deg-1;
|
|
|
296 foreach(0..$number){
|
|
|
297 $pm->start and next;
|
|
|
298 &dec_pel($deg[$_]);
|
|
|
299 $pm->finish;
|
|
|
300 }
|
|
|
301 $pm->wait_all_children;
|
|
|
302 }
|
|
|
303
|
|
|
304 sub dec_pel{
|
|
|
305 print "\n******************\nstart:\n";
|
|
|
306 Time();
|
|
|
307 my $sample=shift(@_);
|
|
|
308 my @each=split/\s+/,$sample;
|
|
|
309 print "$each[0]\t$each[1]\n";
|
|
|
310 my $deg_sample_dir=$deg_dir."$each[0]_VS_$each[1]\/";
|
|
|
311 mkdir ("$deg_sample_dir");
|
|
|
312 print "read: $read\n";
|
|
|
313 print "deg_sample_dir: $deg_sample_dir\n";
|
|
|
314 print "$id{$each[0]}\t$each[0]\n";
|
|
|
315 print "$id{$each[1]}\t$each[1]\n";
|
|
|
316 my $deg=`perl $path\/DEGseq_2.pl -i $read -outdir $deg_sample_dir -column1 $id{$each[0]} -mark1 $each[0] -column2 $id{$each[1]} -mark2 $each[1]`; #-depth1 -depth2
|
|
|
317 my $time2=time();
|
|
|
318 print "end:\n*************************\n";
|
|
|
319 Time();
|
|
|
320 sleep 1;
|
|
|
321 }
|
|
|
322
|
|
|
323 sub infor_merge{
|
|
|
324 my ($input,$mark);
|
|
|
325 foreach (@pairdir) {
|
|
|
326 print "@pairdir\n";
|
|
|
327 $mark.=" -mark $_ ";
|
|
|
328 $input.=" -i $dir/deg\/$_\/output_score\.txt ";
|
|
|
329 print "$input\n$mark\n";
|
|
|
330 }
|
|
|
331 my $infor_merge=`perl $path\/SampleDEGseqMerge.pl $input $mark -f $annotate_dir\/sample_c_p.anno -n $sample_number -o $dir\/total.result `;
|
|
|
332 print "perl $path\/SampleDEGseqMerge.pl $input $mark -f $annotate_dir\/sample_c_p.anno -n $sample_number -o $dir\/total.result\n\n";
|
|
|
333 }
|
|
|
334
|
|
|
335 sub infor_merge_no_dec{
|
|
|
336 my $infor_merge_no_dec=`cp $annotate_dir\/sample_c_p.anno $dir\/total.result`;
|
|
|
337 }
|
|
|
338
|
|
|
339 sub genome_length{
|
|
|
340 my $length=`perl $path\/count_ref_length.pl -i $genome_fa -o $dir\/ref\/genome\.length`;
|
|
|
341 print "perl $path\/count_ref_length.pl -i $genome_fa -o $dir\/ref\/genome\.length\n\n"
|
|
|
342
|
|
|
343 }
|
|
|
344
|
|
|
345 sub plot{
|
|
|
346 $plot_dir="$dir\/plot\/";
|
|
|
347 mkdir ("$plot_dir");
|
|
|
348 my $span=defined($options{span})?$options{span}:50000;
|
|
|
349 my $cen="";
|
|
|
350 if (defined $options{cen}) {
|
|
|
351 $cen="-cen $options{cen}";
|
|
|
352 }
|
|
|
353 my $plot=`perl $path/sRNA_plot.pl -c $rpkm -g $dir/ref/genelist.txt -span 50000 -mark $sample_mark -l $dir/ref/genome\.length $cen -o $plot_dir/cluster.html -out $plot_dir/cluster.txt `;
|
|
|
354 "print perl $path/sRNA_plot.pl -c $rpkm -g $dir/ref/genelist.txt -span 50000 -mark $sample_mark -l $dir/ref/genome.length $cen -o $plot_dir/cluster.html -out $plot_dir/cluster.txt \n";
|
|
|
355
|
|
|
356 }
|
|
|
357
|
|
|
358 sub html{
|
|
|
359 my $pathfile="$dir/path.txt";
|
|
|
360 open PA,">$pathfile";
|
|
|
361 print PA "$config\n";
|
|
|
362 print PA "$preprocess\n";
|
|
|
363 print PA "$dir"."rfam_match\n";
|
|
|
364 print PA "$dir"."genome_match\n";
|
|
|
365 print PA "$cluster_file\n";
|
|
|
366 print PA "$annotate_dir\n";
|
|
|
367 print PA "$plot_dir\n";
|
|
|
368 if (defined($deg_dir)) {
|
|
|
369 print PA "$deg_dir\n";
|
|
|
370 }
|
|
|
371 close PA;
|
|
|
372 my $html=`perl $path\/html.pl -i $pathfile -format $format -o $dir/result.html`;
|
|
|
373 }
|
|
|
374
|
|
|
375 sub Time{
|
|
|
376 my $time=time();
|
|
|
377 my ($sec,$min,$hour,$day,$month,$year) = (localtime($time))[0,1,2,3,4,5,6];
|
|
|
378 $month++;
|
|
|
379 $year+=1900;
|
|
|
380 if (length($sec) == 1) {$sec = "0"."$sec";}
|
|
|
381 if (length($min) == 1) {$min = "0"."$min";}
|
|
|
382 if (length($hour) == 1) {$hour = "0"."$hour";}
|
|
|
383 if (length($day) == 1) {$day = "0"."$day";}
|
|
|
384 if (length($month) == 1) {$month = "0"."$month";}
|
|
|
385 print "$year-$month-$day $hour:$min:$sec\n";
|
|
|
386 return("$year-$month-$day-$hour-$min-$sec");
|
|
|
387 }
|
|
|
388 #################################################################################
|
|
|
389 sub read_config{
|
|
|
390 open CON,"<$config";
|
|
|
391 while (my $aline=<CON>) {
|
|
|
392 chomp $aline;
|
|
|
393 my @tmp=split/\t/,$aline;
|
|
|
394 push @filein,$tmp[0];
|
|
|
395 push @mark,$tmp[1];
|
|
|
396 #&check_rawdata($tmp[0]);
|
|
|
397 }
|
|
|
398 close CON;
|
|
|
399 if (@filein != @mark) {
|
|
|
400 #&printErr();
|
|
|
401 die "Maybe config file have some wrong!!!\n";
|
|
|
402 }
|
|
|
403 }
|
