Mercurial > repos > big-tiandm > sirna_plant

comparison siRNA.pl @ 21:9dcffd531c76 draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
Uploaded
author big-tiandm
date Wed, 05 Nov 2014 21:09:35 -0500
parents
children
comparison
equal deleted inserted replaced
20:2ed1e1728299 21:9dcffd531c76
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="$0
21 Options:
22 -i input file# raw data file
23 -tag string #raw data sample name
24 -g genome file
25 -f gff file
26
27 -o workdir file
28 -path script path
29 -t int, number of threads [1]
30 -format fastq, fq, fasta or fa
31 -idx string, genome file index, file-prefix #(must be indexed by bowtie-build) The parameter
32 string must be the prefix of the bowtie index. For instance, if
33 the first indexed file is called 'h_sapiens_37_asm.1.ebwt' then
34 the prefix is 'h_sapiens_37_asm'.##can be null
35 -mis int number of allowed mismatches when mapping reads to genome, default 0
36 -rfam string, input file# rfam database file.
37 -idx2 string, rfam file index, file-prefix #(must be indexed by bowtie-build) The parameter
38 string must be the prefix of the bowtie index. For instance, if
39 the first indexed file is called 'h_sapiens_37_asm.1.ebwt' then
40 the prefix is 'h_sapiens_37_asm'.##can be null
41
42 -v int report end-to-end hits w/ <=v mismatches; ignore qualities,default 0; used in rfam alignment
43
44 -a string, ADAPTER string. default is ATCTCGTATG.
45 -n int max hits number,default 25; used in genome alignment
46 -d int distance of tag to merged a cluster; default 100
47 -p cluster method F :conventional default is F
48 T :NIBLES
49 -l int the length of the upstream and downstream,default 1000;used in position annotate
50
51 -nat natural antisense transcripts file
52 -repeat repeat information file out of Repeatmasker
53 -deg file config of de sample
54 -cen centromere file input
55 -span plot span, default 50000
56 ";
57
58 my %options;
59 GetOptions(\%options,"i:s@","tag:s@","g=s","f=s","o=s","a:s","path:s","p=s","format=s","nat:s","repeat:s","deg:s","n:i","mis:i","rfam:s","t:i","v:i","d:i","l:i","idx:s","idx2:s","cen:s","span:s","h");
60 #print help if that option is used
61 if($options{h}){die $usage;}
62
63 my @filein=@{$options{'i'}};
64 my @mark=@{$options{'tag'}};
65
66 #my $config=$options{'i'};
67 my $genome_fa=$options{'g'};
68 my $gff=$options{'f'};
69
70
71 ##########################################################################################
72 my $predir=`pwd`;
73 chomp $predir;
74 my $workdir=defined($options{'o'}) ? $options{'o'}:$predir;
75
76 my $path=$options{'path'};
77
78 my $t=defined($options{'t'})? $options{'t'}:1; #threads number
79
80 my $mis=defined $options{'mis'} ? $options{'mis'}:0;
81
82 my $mis_rfam=defined $options{'v'} ? $options{'v'}:0;
83
84 my $hit=defined $options{'n'}?$options{'n'}:25;
85
86 my $distance_of_merged_tag=defined $options{'d'} ? $options{'d'}:100;
87
88 my $up_down_dis=defined $options{'l'} ?$options{'l'}:1000;
89
90 my $cluster_mothod=defined $options{'p'}?$options{'p'}:"F";
91
92 my $format=$options{'format'};
93 #if ($format ne "fastq" && $format ne "fq" && $format ne "fasta" && $format ne "fa") {
94 # die "Parameter \"-format\" is error! Parameter is fastq, fq, fasta or fa\n";
95 #}
96
97 my $adpter="ATCTCGTATG"; #adapter
98 if (defined $options{'a'}) {$adpter=$options{'a'};}
99
100
101 my $phred_qv=64;
102 my $sample_number;
103 my ($dir,$dir_tmp);
104 ################################ MAIN ##################################################
105 print "\ncluster program start:";
106 my $time=Time();
107 make_dir_tmp();
108
109 my @clip;
110 my $mark;
111 my $sample_mark;
112
113 my $config=$dir."/input_config";
114 open CONFIG,">$config";
115 for (my $i=0;$i<@filein;$i++) {
116 print CONFIG $filein[$i],"\t",$mark[$i],"\n";
117 }
118 close CONFIG;
119 if (@filein != @mark) {
120 die "Maybe config file have some wrong!!!\n";
121 }
122 $sample_number=@mark;
123 $mark=join "\t",@mark;
124 $sample_mark=join "\#",@mark;
125
126
127 #read_config();
128
129 trim_adapter_and_filter();
130
131 my $filter_out=$dir."preProcess\/"."collapse_reads_out.fa";## raw clean data
132 my $data2=$filter_out; ### mirbase not mapped reads
133 my $data3=$dir."\/rfam_match\/rfam_not_mapped\.fa"; ### rfam not mapped reads
134 my $bed=$dir."cluster\/"."sample\.bed";
135 my $read=$dir."cluster\/"."sample_reads\.cluster";
136 my $read_txt=$dir."cluster\/"."cluster\.txt";
137 my $rpkm=$dir."cluster\/"."sample_rpkm\.cluster";
138 my $preprocess;
139 my $cluster_file;
140 my $annotate_dir;
141 my $deg_dir;
142 my $plot_dir;
143 my %id;
144 for (my $i=0;$i<@mark ;$i++) {
145 $id{$mark[$i]}=$i+4;
146 }
147
148 print "\n######## tiandm test start ###########\n";
149 print "\@mark: @mark\n\%id keys number:";
150 print scalar keys %id;
151 print "\n";
152 foreach my $kyess (keys %id){
153 print $kyess," --> $id{$kyess}\n";
154 }
155 print "\n######## tiandm test end ############\n";
156 group_and_filter(); #collapse reads to tags
157
158 rfam();
159
160 my @map_read;
161 my $map_tag=0;
162 genome();
163
164 bwt2bed();
165
166 cluster();
167
168 quantify();
169
170 phase();
171
172 if (defined($options{'nat'})&&defined($options{'repeat'})) {
173 class();
174 }
175 else{
176 get_genelist();
177 }
178
179 annotate();
180
181 genome_length();
182
183 plot();
184
185 my @pairdir;
186 if (defined($options{'deg'})) {
187 dec();
188 infor_merge();
189 }
190 else{infor_merge_no_dec()}
191 html();
192 print "\ncluster program end:";
193 Time();
194 ############################sub program###################################################
195 sub make_dir_tmp{
196
197 #make temporary directory
198 if(not -d "$workdir\/cluster_runs"){
199 mkdir("$workdir\/cluster_runs");
200 mkdir("$workdir\/cluster_runs\/ref\/");
201 }
202
203 $dir="$workdir\/cluster_runs\/";
204 #print STDERR "mkdir $dir\n\n";
205 return;
206 }
207
208 #sub read_config{
209 # open IN,"<$config";
210 # while (my $aline=<IN>) {
211 # chomp $aline;
212 # my @tmp=split/\t/,$aline;
213 # push @filein,$tmp[0];
214 # push @mark,$tmp[1];
215 # }
216 # close IN;
217 # if (@filein != @mark) {
218 # die "Maybe config file have some wrong!!!\n";
219 # }
220 # $sample_number=@mark;
221 # $mark=join "\t",@mark;
222 # $sample_mark=join "\#",@mark;
223 #}
224
225
226 sub trim_adapter_and_filter{
227 my $time=time();
228 $preprocess=$dir."preProcess/";
229 mkdir $preprocess;
230 my $can_use_threads = eval 'use threads; 1';
231 if ($can_use_threads) {
232 # Do processing using threads
233 my @filein1=@filein; my @mark1=@mark;
234 while (@filein1>0) {
235 my @thrs; my @res;
236 for (my $i=0;$i<$t ;$i++) {
237 last if(@filein1==0);
238 my $in=shift @filein1;
239 my $out=shift @mark1;
240 push @clip,$dir."preProcess\/$out\_clip\.fq";
241 $thrs[$i]=threads->create(\&clips,$in,$out);
242 }
243 for (my $i=0;$i<@thrs;$i++) {
244 $res[$i]=$thrs[$i]->join();
245 }
246 }
247 }
248 else {
249 # Do not processing using threads
250 for (my $i=0;$i<@filein ;$i++) {
251 my $in=$filein[$i];
252 my $out=$mark[$i];
253 push @clip,$dir."preProcess\/$out\_clip\.fq";
254 &clips($in,$out);
255 }
256 }
257 }
258
259 sub clips{
260 my ($filein,$fileout)=@_;
261 my $adapter=$dir."preProcess\/$fileout\_clip\.fq";
262 if($format eq "fq" || $format eq "fastq"){
263 my $clip=`fastx_clipper -a $adpter -M 6 -Q $phred_qv -i $filein -o $adapter`;
264 }
265 if($format eq "fa" || $format eq "fasta"){
266 my $clip=`fastx_clipper -a $adpter -M 6 -i $filein -o $adapter`;
267 }
268 #my $clean=$dir."preProcess\/$fileout\_clean.fq";
269 #my $filter=`filterReadsByLength.pl -i $adapter -o $clean -min 18 -max 40 `;
270 return $fileout;
271 }
272
273 sub group_and_filter{
274 #my ($ins,$data)=@_;
275 my @ins=@clip;
276 my $str="";
277 my $group_out_file=$dir."preProcess\/"."collapse_reads.fa";
278 #print "$$ins[0]\t$$ins[0]\n";
279 for (my $i=0;$i<@clip;$i++) {
280 $str .="-i $clip[$i] ";
281 #print "$$ins[$i]\n";
282 }
283 my $group=`perl $path\/collapseReads2Tags.pl $str -mark seq -o $group_out_file -format $format`;
284 print "perl $path\/collapseReads2Tags.pl $str -mark seq -o $group_out_file -format $format\n\n";
285
286 my $l_out=$dir."preProcess\/"."collapse_reads_18-40.fa";
287 my $length_f=`perl $path\/filterReadsByLength_1.pl -i $group_out_file -o $l_out -min 18 -max 40 -mark $sample_mark`;
288 print "perl $path\/filterReadsByLength_1.pl -i $group_out_file -o $l_out -min 18 -max 40 -mark $sample_mark\n\n";
289 my $cout_f=`perl $path\/filterReadsByCount.pl -i $l_out -o $filter_out -mark $sample_mark`;
290 print "perl $path\/filterReadsByCount.pl -i $l_out -o $filter_out -mark $sample_mark\n\n";
291 my $plot_l_D=`perl $path/Length_Distibution.pl -i $dir/preProcess/reads_length_distribution_after_count_filter.txt -o $dir/preProcess/length.html `;
292 print "perl $path\/Length_Distibution.pl -i $dir\/preProcess\/reads_length_distribution_after_count_filter.txt -o $dir\/preProcess\/length\.html\n\n";
293 return 0;
294 }
295
296 sub rfam{
297 if (defined $options{'idx2'}) {
298 system("perl $path\/rfam.pl -i $data2 -ref $options{rfam} -v $mis_rfam -p $t -o $dir -index $options{idx2}");
299 }else{
300 system("perl $path\/rfam.pl -i $data2 -ref $options{rfam} -v $mis_rfam -p $t -o $dir");
301 }
302 my $tag=join "\\;" ,@mark;
303 my $rfam_count=`perl $path\/count_rfam_express.pl -i $dir\/rfam_match\/rfam_mapped.bwt -tag $tag -o $dir\/rfam_match\/rfam_non-miRNA_annotation.txt`;
304 return 0;
305 }
306 sub genome{
307 if(defined $options{'idx'}){
308 system("perl $path\/matching.pl -i $data3 -g $genome_fa -v $mis -p $t -r $hit -o $dir -index $options{idx}") ;
309 }else{
310 system("perl $path\/matching.pl -i $data3 -g $genome_fa -v $mis -p $t -r $hit -o $dir ") ;
311 }
312 #=================== mapping sta ===================================================
313 my $map_file=$dir."genome_match\/genome_mapped\.fa";
314 open (MAP,"<$map_file")||die"$!";
315 print "\n#each sample mapping reads sta:\n\n";
316 print "#$mark\ttotal\n";
317 while (my $ID=<MAP>) {
318 chomp $ID;
319 my @tmp=split/\:/,$ID;
320 my @exp=split/\_/,$tmp[1];
321 $exp[-1] =~ s/^x//;
322 for (my $i=0;$i<@exp ;$i++) {
323 $map_read[$i]+=$exp[$i];
324 }
325 $map_tag++;
326 my $seq=<MAP>;
327 }
328 my $map_read=join"\t",@map_read;
329 print "$map_read\n\n";
330 print "#total mapped tags:$map_read\n\n";
331 close MAP;
332 return 0;
333 }
334
335 sub bwt2bed{
336 $cluster_file=$dir."cluster\/";
337 mkdir ("$cluster_file");
338 print "sam file changed to bed file\n";
339 my ($file) = $dir."genome_match\/genome_mapped\.bwt";
340
341 my $sam2bed=`perl $path\/sam2Bed_bowtie.pl -i $file -mark $sample_mark -o $bed `;
342 print "perl $path\/sam2Bed_bowtie.pl -i $file -mark $sample_mark -o $bed\n\n";
343 return 0;
344 }
345
346 sub cluster{
347 print "tags is ready to merged clusters\n\n";
348 my ($file) =$bed;
349 if ($cluster_mothod eq "F") {
350 my $cluster=`perl $path\/conventional.pl -i $file -d $distance_of_merged_tag -n $sample_number -mark $sample_mark -o $read -t $read_txt`;
351 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 $read_txt\n\n";
352 }
353 elsif($cluster_mothod eq "T"){
354 my $cluster=`perl $path\/nibls.pl -f $file -m $distance_of_merged_tag -o $read -t $read_txt -k $sample_mark`;
355 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";
356 }
357 else{print "\-p is wrong!\n\n";}
358 return 0;
359 }
360
361
362 sub quantify{
363 print "clusters is ready to quantified\n\n";
364 my @depth=@map_read;
365 pop @depth;
366 my $depth=join ",",@depth;
367 my $quantify=`perl $path\/quantify.pl -i $read -d $depth -o $rpkm`;
368 print "perl $path\/quantify.pl -i $read -d $depth -o $rpkm\n\n\n";
369 return 0;
370 }
371
372 sub phase{
373 $annotate_dir=$dir."annotate\/";
374 mkdir ("$annotate_dir");
375 print "clusters is to predict phase siRNA\n";
376 my $phase=`perl $path\/phased_siRNA.pl -i $read_txt -o $annotate_dir\/phase.out`;
377 print "perl $path\/phased_siRNA.pl -i $read_txt -o $annotate_dir\/phase.out\n\n\n";
378 return 0;
379 }
380
381 sub class{
382 print "clusters is ready to annotate by sources\n\n";
383 my $nat=$options{'nat'};
384 my $repeat=$options{'repeat'};
385 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`;
386 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";
387 }
388
389 sub annotate{
390 print "clusters is ready to annotate by gff file\n\n";
391 my $file;
392 if (defined($options{'nat'})&&defined($options{'repeat'})) {
393 $file="$annotate_dir\/sample_class.anno";
394 }
395 else{
396 $file=$rpkm;
397 }
398 my $annotate=`perl $path\/Annotate.pl -i $file -g $dir\/ref\/genelist.txt -d $up_down_dis -o $annotate_dir\/sample_c_p.anno`;
399 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";
400 return 0;
401 }
402 sub get_genelist{
403
404 my $get_genelist=`perl $path\/get_genelist.pl -i $gff -o $dir\/ref\/genelist.txt`;
405 print "perl $path\/get_genelist.pl -i $gff -o $dir\/ref\/genelist.txt";
406 }
407
408 sub dec{
409 print "deg reading\n\n";
410 my $deg_file=$options{'deg'};
411 open IN,"<$deg_file";
412 my @deg;
413 my $s=0;
414 while (my $aline=<IN>) {
415 chomp $aline;
416 next if($aline=~/^\#/);
417 $deg[$s]=$aline;
418 my @ea=split/\s+/,$aline;
419 push @pairdir,"$ea[0]_VS_$ea[1]\/";
420 #print "$deg[$s]\n";
421 $s++;
422 }
423 close IN;
424 $deg_dir=$dir."deg\/";
425 mkdir ("$deg_dir");
426 my $max_process = 10;
427 my $pm = new Parallel::ForkManager( $max_process );
428 my $number=@deg-1;
429 foreach(0..$number){
430 $pm->start and next;
431 &dec_pel($deg[$_]);
432 $pm->finish;
433 }
434 $pm->wait_all_children;
435 }
436
437 sub dec_pel{
438 print "\n******************\nstart:\n";
439 Time();
440 my $sample=shift(@_);
441 my @each=split/\s+/,$sample;
442 print "$each[0]\t$each[1]\n";
443 my $deg_sample_dir=$deg_dir."$each[0]_VS_$each[1]\/";
444 mkdir ("$deg_sample_dir");
445 print "read: $read\n";
446 print "deg_sample_dir: $deg_sample_dir\n";
447 print "$id{$each[0]}\t$each[0]\n";
448 print "$id{$each[1]}\t$each[1]\n";
449 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
450 my $time2=time();
451 print "end:\n*************************\n";
452 Time();
453 sleep 1;
454 }
455
456 sub infor_merge{
457 my ($input,$mark);
458 foreach (@pairdir) {
459 print "@pairdir\n";
460 $mark.=" -mark $_ ";
461 $input.=" -i $dir/deg\/$_\/output_score\.txt ";
462 print "$input\n$mark\n";
463 }
464 my $infor_merge=`perl $path\/SampleDEGseqMerge.pl $input $mark -f $annotate_dir\/sample_c_p.anno -n $sample_number -o $dir\/total.result `;
465 print "perl $path\/SampleDEGseqMerge.pl $input $mark -f $annotate_dir\/sample_c_p.anno -n $sample_number -o $dir\/total.result\n\n";
466 }
467
468 sub infor_merge_no_dec{
469 my $infor_merge_no_dec=`cp $annotate_dir\/sample_c_p.anno $dir\/total.result`;
470 }
471
472 sub genome_length{
473 my $length=`perl $path\/count_ref_length.pl -i $genome_fa -o $dir\/ref\/genome\.length`;
474 print "perl $path\/count_ref_length.pl -i $genome_fa -o $dir\/ref\/genome\.length\n\n"
475
476 }
477
478 sub plot{
479 $plot_dir="$dir\/plot\/";
480 mkdir ("$plot_dir");
481 my $span=defined($options{span})?$options{span}:50000;
482 my $cen="";
483 if (defined $options{cen}) {
484 $cen="-cen $options{cen}";
485 }
486 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 `;
487 "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";
488
489 }
490
491 sub html{
492 my $pathfile="$dir/path.txt";
493 open PA,">$pathfile";
494 print PA "$config\n";
495 print PA "$preprocess\n";
496 print PA "$dir"."rfam_match\n";
497 print PA "$dir"."genome_match\n";
498 print PA "$cluster_file\n";
499 print PA "$annotate_dir\n";
500 print PA "$plot_dir\n";
501 if (defined($deg_dir)) {
502 print PA "$deg_dir\n";
503 }
504 close PA;
505 my $html=`perl $path\/html.pl -i $pathfile -format $format -o $dir/result.html`;
506 }
507
508 sub Time{
509 my $time=time();
510 my ($sec,$min,$hour,$day,$month,$year) = (localtime($time))[0,1,2,3,4,5,6];
511 $month++;
512 $year+=1900;
513 if (length($sec) == 1) {$sec = "0"."$sec";}
514 if (length($min) == 1) {$min = "0"."$min";}
515 if (length($hour) == 1) {$hour = "0"."$hour";}
516 if (length($day) == 1) {$day = "0"."$day";}
517 if (length($month) == 1) {$month = "0"."$month";}
518 print "$year-$month-$day $hour:$min:$sec\n";
519 return("$year-$month-$day-$hour-$min-$sec");
520 }
521 #################################################################################