Mercurial > repos > big-tiandm > sirna_plant

comparison siRNA.pl @ 11:a0222bdfe2ac draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
Uploaded
author big-tiandm
date Wed, 29 Oct 2014 04:18:44 -0400
parents
children 22d79320085c
comparison
equal deleted inserted replaced
10:b20345ef3995 11:a0222bdfe2ac
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 %id;
143 for (my $i=0;$i<@mark ;$i++) {
144 $id{$mark[$i]}=$i+4;
145 }
146 group_and_filter(); #collapse reads to tags
147
148 rfam();
149
150 my @map_read;
151 my $map_tag=0;
152 genome();
153
154 bwt2bed();
155
156 cluster();
157
158 quantify();
159
160 phase();
161
162 if (defined($options{'nat'})&&defined($options{'repeat'})) {
163 class();
164 }
165 else{
166 get_genelist();
167 }
168
169 annotate();
170
171 genome_length();
172
173 plot();
174
175 my @pairdir;
176 if (defined($options{'deg'})) {
177 dec();
178 infor_merge();
179 }
180 else{infor_merge_no_dec()}
181 html();
182 print "\ncluster program end:";
183 Time();
184 ############################sub program###################################################
185 sub make_dir_tmp{
186
187 #make temporary directory
188 if(not -d "$workdir\/cluster_runs"){
189 mkdir("$workdir\/cluster_runs");
190 mkdir("$workdir\/cluster_runs\/ref\/");
191 }
192
193 $dir="$workdir\/cluster_runs\/";
194 #print STDERR "mkdir $dir\n\n";
195 return;
196 }
197
198 #sub read_config{
199 # open IN,"<$config";
200 # while (my $aline=<IN>) {
201 # chomp $aline;
202 # my @tmp=split/\t/,$aline;
203 # push @filein,$tmp[0];
204 # push @mark,$tmp[1];
205 # }
206 # close IN;
207 # if (@filein != @mark) {
208 # die "Maybe config file have some wrong!!!\n";
209 # }
210 # $sample_number=@mark;
211 # $mark=join "\t",@mark;
212 # $sample_mark=join "\#",@mark;
213 #}
214
215
216 sub trim_adapter_and_filter{
217 my $time=time();
218 $preprocess=$dir."preProcess/";
219 mkdir $preprocess;
220 my $can_use_threads = eval 'use threads; 1';
221 if ($can_use_threads) {
222 # Do processing using threads
223 my @filein1=@filein; my @mark1=@mark;
224 while (@filein1>0) {
225 my @thrs; my @res;
226 for (my $i=0;$i<$t ;$i++) {
227 last if(@filein1==0);
228 my $in=shift @filein1;
229 my $out=shift @mark1;
230 push @clip,$dir."preProcess\/$out\_clip\.fq";
231 $thrs[$i]=threads->create(\&clips,$in,$out);
232 }
233 for (my $i=0;$i<@thrs;$i++) {
234 $res[$i]=$thrs[$i]->join();
235 }
236 }
237 }
238 else {
239 # Do not processing using threads
240 for (my $i=0;$i<@filein ;$i++) {
241 my $in=$filein[$i];
242 my $out=$mark[$i];
243 push @clip,$dir."preProcess\/$out\_clip\.fq";
244 &clips($in,$out);
245 }
246 }
247 }
248
249 sub clips{
250 my ($filein,$fileout)=@_;
251 my $adapter=$dir."preProcess\/$fileout\_clip\.fq";
252 if($format eq "fq" || $format eq "fastq"){
253 my $clip=`fastx_clipper -a $adpter -M 6 -Q $phred_qv -i $filein -o $adapter`;
254 }
255 if($format eq "fa" || $format eq "fasta"){
256 my $clip=`fastx_clipper -a $adpter -M 6 -i $filein -o $adapter`;
257 }
258 #my $clean=$dir."preProcess\/$fileout\_clean.fq";
259 #my $filter=`filterReadsByLength.pl -i $adapter -o $clean -min 18 -max 40 `;
260 return $fileout;
261 }
262
263 sub group_and_filter{
264 #my ($ins,$data)=@_;
265 my @ins=@clip;
266 my $str="";
267 my $group_out_file=$dir."preProcess\/"."collapse_reads.fa";
268 #print "$$ins[0]\t$$ins[0]\n";
269 for (my $i=0;$i<@clip;$i++) {
270 $str .="-i $clip[$i] ";
271 #print "$$ins[$i]\n";
272 }
273 my $group=`perl $path\/collapseReads2Tags.pl $str -mark seq -o $group_out_file -format $format`;
274 print "perl $path\/collapseReads2Tags.pl $str -mark seq -o $group_out_file -format $format\n\n";
275
276 my $l_out=$dir."preProcess\/"."collapse_reads_18-40.fa";
277 my $length_f=`perl $path\/filterReadsByLength_1.pl -i $group_out_file -o $l_out -min 18 -max 40 -mark $sample_mark`;
278 print "perl $path\/filterReadsByLength_1.pl -i $group_out_file -o $l_out -min 18 -max 40 -mark $sample_mark\n\n";
279 my $cout_f=`perl $path\/filterReadsByCount.pl -i $l_out -o $filter_out -mark $sample_mark`;
280 print "perl $path\/filterReadsByCount.pl -i $l_out -o $filter_out -mark $sample_mark\n\n";
281 return 0;
282 }
283
284 sub rfam{
285 if (defined $options{'idx2'}) {
286 system("perl $path\/rfam.pl -i $data2 -ref $options{rfam} -v $mis_rfam -p $t -o $dir -index $options{idx2}");
287 }else{
288 system("perl $path\/rfam.pl -i $data2 -ref $options{rfam} -v $mis_rfam -p $t -o $dir");
289 }
290 my $tag=join "\\;" ,@mark;
291 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`;
292 return 0;
293 }
294 sub genome{
295 if(defined $options{'idx'}){
296 system("perl $path\/matching.pl -i $data3 -g $genome_fa -v $mis -p $t -r $hit -o $dir -index $options{idx}") ;
297 }else{
298 system("perl $path\/matching.pl -i $data3 -g $genome_fa -v $mis -p $t -r $hit -o $dir ") ;
299 }
300 #=================== mapping sta ===================================================
301 my $map_file=$dir."genome_match\/genome_mapped\.fa";
302 open (MAP,"<$map_file")||die"$!";
303 print "\n#each sample mapping reads sta:\n\n";
304 print "#$mark\ttotal\n";
305 while (my $ID=<MAP>) {
306 chomp $ID;
307 my @tmp=split/\:/,$ID;
308 my @exp=split/\_/,$tmp[1];
309 $exp[-1] =~ s/^x//;
310 for (my $i=0;$i<@exp ;$i++) {
311 $map_read[$i]+=$exp[$i];
312 }
313 $map_tag++;
314 my $seq=<MAP>;
315 }
316 my $map_read=join"\t",@map_read;
317 print "$map_read\n\n";
318 print "#total mapped tags:$map_read\n\n";
319 close MAP;
320 return 0;
321 }
322
323 sub bwt2bed{
324 $cluster_file=$dir."cluster\/";
325 mkdir ("$cluster_file");
326 print "sam file changed to bed file\n";
327 my ($file) = $dir."genome_match\/genome_mapped\.bwt";
328
329 my $sam2bed=`perl $path\/sam2Bed_bowtie.pl -i $file -mark $sample_mark -o $bed `;
330 print "perl $path\/sam2Bed_bowtie.pl -i $file -mark $sample_mark -o $bed\n\n";
331 return 0;
332 }
333
334 sub cluster{
335 print "tags is ready to merged clusters\n\n";
336 my ($file) =$bed;
337 if ($cluster_mothod eq "F") {
338 my $cluster=`perl $path\/conventional.pl -i $file -d $distance_of_merged_tag -n $sample_number -mark $sample_mark -o $read -t $read_txt`;
339 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 $read_txt\n\n";
340 }
341 elsif($cluster_mothod eq "T"){
342 my $cluster=`perl $path\/nibls.pl -f $file -m $distance_of_merged_tag -o $read -t $read_txt -mark $sample_mark`;
343 print "Using nibls method\n perl $path\/nibls.pl -f $file -m $distance_of_merged_tag -o $read -t $dir\/cluster.txt -mark $sample_mark\n\n";
344 }
345 else{print "\-p is wrong!\n\n";}
346 return 0;
347 }
348
349
350 sub quantify{
351 print "clusters is ready to quantified\n\n";
352 my @depth=@map_read;
353 pop @depth;
354 my $depth=join ",",@depth;
355 my $quantify=`perl $path\/quantify.pl -i $read -d $depth -o $rpkm`;
356 print "perl $path\/quantify.pl -i $read -d $depth -o $rpkm\n\n\n";
357 return 0;
358 }
359
360 sub phase{
361 $annotate_dir=$dir."annotate\/";
362 mkdir ("$annotate_dir");
363 print "clusters is to predict phase siRNA\n";
364 my $phase=`perl $path\/phased_siRNA.pl -i $read_txt -o $annotate_dir\/phase.out`;
365 print "perl $path\/phased_siRNA.pl -i $read_txt -o $annotate_dir\/phase.out\n\n\n";
366 return 0;
367 }
368
369 sub class{
370 print "clusters is ready to annotate by sources\n\n";
371 my $nat=$options{'nat'};
372 my $repeat=$options{'repeat'};
373 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`;
374 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";
375 }
376
377 sub annotate{
378 print "clusters is ready to annotate by gff file\n\n";
379 my $file;
380 if (defined($options{'nat'})&&defined($options{'repeat'})) {
381 $file="$annotate_dir\/sample_class.anno";
382 }
383 else{
384 $file=$rpkm;
385 }
386 my $annotate=`perl $path\/Annotate.pl -i $file -g $dir\/ref\/genelist.txt -d $up_down_dis -o $annotate_dir\/sample_c_p.anno`;
387 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";
388 return 0;
389 }
390 sub get_genelist{
391
392 my $get_genelist=`perl $path\/get_genelist.pl -i $gff -o $dir\/ref\/genelist.txt`;
393 print "perl $path\/get_genelist.pl -i $gff -o $dir\/ref\/genelist.txt";
394 }
395
396 sub dec{
397 print "deg reading\n\n";
398 my $deg_file=$options{'deg'};
399 open IN,"<$deg_file";
400 my @deg;
401 my $s=0;
402 while (my $aline=<IN>) {
403 chomp $aline;
404 next if($aline=~/^\#/);
405 $deg[$s]=$aline;
406 my @ea=split/\s+/,$aline;
407 push @pairdir,"$ea[0]_VS_$ea[1]\/";
408 #print "$deg[$s]\n";
409 $s++;
410 }
411 close IN;
412 $deg_dir=$dir."deg\/";
413 mkdir ("$deg_dir");
414 my $max_process = 10;
415 my $pm = new Parallel::ForkManager( $max_process );
416 my $number=@deg-1;
417 foreach(0..$number){
418 $pm->start and next;
419 &dec_pel($deg[$_]);
420 $pm->finish;
421 }
422 $pm->wait_all_children;
423 }
424
425 sub dec_pel{
426 print "start:\n";
427 Time();
428 my $sample=shift(@_);
429 my @each=split/\s+/,$sample;
430 print "$each[0]\t$each[1]\n";
431 my $deg_sample_dir=$deg_dir."$each[0]_VS_$each[1]\/";
432 mkdir ("$deg_sample_dir");
433 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
434 my $time2=time();
435 print "end:\n";
436 Time();
437 sleep 1;
438 }
439
440 sub infor_merge{
441 my ($input,$mark);
442 foreach (@pairdir) {
443 print "@pairdir\n";
444 $mark.=" -mark $_ ";
445 $input.=" -i $dir/deg\/$_\/output_score\.txt ";
446 print "$input\n$mark\n";
447 }
448 my $infor_merge=`perl $path\/SampleDEGseqMerge.pl $input $mark -f $annotate_dir\/sample_c_p.anno -n $sample_number -o $dir\/total.result `;
449 print "perl $path\/SampleDEGseqMerge.pl $input $mark -f $annotate_dir\/sample_c_p.anno -n $sample_number -o $dir\/total.result\n\n";
450 }
451
452 sub infor_merge_no_dec{
453 my $infor_merge_no_dec=`cp $annotate_dir\/sample_c_p.anno $dir\/total.result`;
454 }
455
456 sub genome_length{
457 my $length=`perl $path\/count_ref_length.pl -i $genome_fa -o $dir\/ref\/genome\.length`;
458 print "perl $path\/count_ref_length.pl -i $genome_fa -o $dir\/ref\/genome\.length\n\n"
459
460 }
461
462 sub plot{
463 my $plot_file="$dir\/plot\/";
464 mkdir ("$plot_file");
465 my $genome_plot="$dir\/plot\/genome\/";
466 mkdir ("$genome_plot");
467 #genome cluster
468 my $span=defined($options{span})?$options{span}:50000;
469 foreach (1..$sample_number) {
470 my $mark=$mark[$_-1];
471 my $cen="";
472 if (defined $options{cen}) {
473 $cen="-cen $options{cen}";
474 }
475 my $plot=`perl $path\/sRNA_rpkm_distribution_along_genome.pl -c $rpkm -n $_ -mark $mark -span $span -l $dir\/ref\/genome\.length $cen -o $genome_plot\/$mark\.html -out $genome_plot\/$mark\.txt`;
476 print "perl $path\/sRNA_rpkm_distribution_along_genome.pl -c $rpkm -n $_ -mark $mark -span $span -l $dir\/ref\/genome\.length $cen -o $genome_plot\/$mark\.html -out $genome_plot\/$mark\.txt\n\n";
477 }
478
479 my $chr_plot_dir="$dir\/plot\/chr\/";
480 mkdir("$chr_plot_dir");
481 my %chr;
482 open LEN,"<$dir\/ref\/genome\.length";
483 while (my $aline=<LEN>) {
484 next if($aline=~/^\#/);
485 chomp $aline;
486 my @temp=split/\t/,$aline;
487 $chr{$temp[0]}=$temp[1];
488 }
489 close LEN;
490 foreach my $chr (sort keys %chr) {
491 my $cen="";
492 if (defined $options{cen}) {
493 $cen="-cen $options{cen}";
494 }
495 my $chr_plot=`perl $path\/chr_plot.pl -l $chr{$chr} -chro $chr -g $dir\/ref\/genelist.txt -span $span -c $rpkm -mark $sample_mark -o $chr_plot_dir\/$chr\.html`;
496 print "perl $path\/chr_plot.pl -l $chr{$chr} -chro $chr -g $dir\/ref\/genelist.txt -span $span -c $rpkm -mark $sample_mark -o $chr_plot_dir\/$chr\.html\n";
497 }
498 }
499
500 sub html{
501 my $pathfile="$dir/path.txt";
502 open PA,">$pathfile";
503 print PA "$config\n";
504 print PA "$preprocess\n";
505 print PA "$dir"."rfam_match\n";
506 print PA "$dir"."genome_match\n";
507 print PA "$cluster_file\n";
508 print PA "$annotate_dir\n";
509 if (defined($deg_dir)) {
510 print PA "$deg_dir\n";
511 }
512 close PA;
513 my $html=`perl $path\/html.pl -i $pathfile -format $format -o $dir/result.html`;
514 }
515
516 sub Time{
517 my $time=time();
518 my ($sec,$min,$hour,$day,$month,$year) = (localtime($time))[0,1,2,3,4,5,6];
519 $month++;
520 $year+=1900;
521 if (length($sec) == 1) {$sec = "0"."$sec";}
522 if (length($min) == 1) {$min = "0"."$min";}
523 if (length($hour) == 1) {$hour = "0"."$hour";}
524 if (length($day) == 1) {$day = "0"."$day";}
525 if (length($month) == 1) {$month = "0"."$month";}
526 print "$year-$month-$day $hour:$min:$sec\n";
527 return("$year-$month-$day-$hour-$min-$sec");
528 }
529 #################################################################################