|
47
|
1 #!/usr/bin/perl -w
|
|
|
2 #Filename:
|
|
|
3 #Author: Tian Dongmei
|
|
|
4 #Email: tiandm@big.ac.cn
|
|
|
5 #Date: 2014-12-2
|
|
|
6 #Modified:
|
|
|
7 #Description: RNA-seq data pre-process
|
|
|
8 my $version=1.00;
|
|
|
9
|
|
|
10 use strict;
|
|
|
11 use Getopt::Long;
|
|
|
12 use threads;
|
|
|
13 #use threads::shared;
|
|
|
14 use File::Path;
|
|
|
15 use File::Basename;
|
|
|
16 #use RNA;
|
|
|
17 #use Term::ANSIColor;
|
|
|
18
|
|
|
19 my %opts;
|
|
|
20 GetOptions(\%opts,"i:s@","tag:s@","format=s","phred:i","gfa=s","rfam:s","idx:s","idx2:s","mis:i","v:i","a:s","M:i","t:i","min:i","max:i","o:s","path:s","h");
|
|
|
21 if (!(defined $opts{i} and defined $opts{format} and defined $opts{gfa} ) || defined $opts{h}) { #necessary arguments
|
|
|
22 &usage;
|
|
|
23 }
|
|
|
24
|
|
|
25 my $time=&Time();
|
|
|
26 print "miPlant program start:\n The time is $time!\n";
|
|
|
27 print "Command line:\n $0 @ARGV\n";
|
|
|
28
|
|
|
29 my $format=$opts{'format'};
|
|
|
30 if ($format ne "fastq" && $format ne "fq" && $format ne "fasta" && $format ne "fa") {
|
|
|
31 #&printErr();
|
|
|
32 die "Parameter \"-format\" is error! Parameter is fastq, fq, fasta or fa\n";
|
|
|
33 }
|
|
|
34
|
|
|
35 my $phred_qv=64;
|
|
|
36 if (defined $opts{'phred'}) {$phred_qv=$opts{'phred'};}
|
|
|
37
|
|
|
38 my @inputfiles=@{$opts{'i'}};
|
|
|
39 my @inputtags=@{$opts{'tag'}};
|
|
|
40
|
|
|
41 my $mypath=`pwd`;
|
|
|
42 chomp $mypath;
|
|
|
43
|
|
|
44 my $dir=defined $opts{'o'} ? $opts{'o'} : "$mypath/preProcess/";
|
|
|
45
|
|
|
46
|
|
|
47 unless ($dir=~/\/$/) {$dir.="/";}
|
|
|
48 if (not -d $dir) {
|
|
|
49 mkdir $dir;
|
|
|
50 }
|
|
|
51 my $config=$dir."/input_config";
|
|
|
52 open CONFIG,">$config";
|
|
|
53 for (my $i=0;$i<@inputfiles;$i++) {
|
|
|
54 print CONFIG $inputfiles[$i],"\t",$inputtags[$i],"\n";
|
|
|
55 }
|
|
|
56 close CONFIG;
|
|
|
57
|
|
|
58 my $scipt_path=defined $opts{'path'} ? $opts{'path'} : "/Users/big/galaxy-dist/tools/myTools/";
|
|
|
59
|
|
|
60 my $a="ATCTCGTATG"; #adapter
|
|
|
61 if (defined $opts{'a'}) {$a=$opts{'a'};}
|
|
|
62
|
|
|
63 my $m=6; #adapter minimum mapped nt
|
|
|
64 if (defined $opts{'M'}) {$m=$opts{'M'};}
|
|
|
65
|
|
|
66 my $t=1; #threads number
|
|
|
67 if (defined $opts{'t'}) {$t=$opts{'t'};}
|
|
|
68
|
|
|
69 my $min_nt=19; # minimum reads length
|
|
|
70 if (defined $opts{'min'}) {$min_nt=$opts{'min'};}
|
|
|
71
|
|
|
72 my $max_nt=28; #maximum reads length
|
|
|
73 if (defined $opts{'max'}) {$max_nt=$opts{'max'};}
|
|
|
74
|
|
|
75 my $mis=0; #mismatch number for microRNA
|
|
|
76 if (defined $opts{'mis'}) {$mis=$opts{'mis'};}
|
|
|
77
|
|
|
78 my $mis_rfam=0;# mismatch number for rfam
|
|
|
79 if (defined $opts{'v'}) {$mis_rfam=$opts{'v'};}
|
|
|
80
|
|
|
81 my (@filein,@mark,@clean);
|
|
|
82 #&read_config();
|
|
|
83 @filein=@inputfiles;
|
|
|
84 @mark=@inputtags;
|
|
|
85
|
|
|
86 &checkfa($opts{gfa});
|
|
|
87
|
|
|
88
|
|
|
89 ##### clip adpter --> clean data start
|
|
|
90 my $preprocess=$dir."preProcess_clean/";
|
|
|
91 mkdir $preprocess;
|
|
|
92 my $can_use_threads = eval 'use threads; 1';
|
|
|
93 if ($can_use_threads) {
|
|
|
94 # Do processing using threads
|
|
|
95 print "Do processing using threads\n";
|
|
|
96 my @filein1=@filein; my @mark1=@mark;
|
|
|
97 while (@filein1>0) {
|
|
|
98 my @thrs; my @res;
|
|
|
99 for (my $i=0;$i<$t ;$i++) {
|
|
|
100 last if(@filein1==0);
|
|
|
101 my $in=shift @filein1;
|
|
|
102 my $out=shift @mark1;
|
|
|
103 push @clean,$preprocess.$out."_clips_adapter.fq";
|
|
|
104 $thrs[$i]=threads->create(\&clips,$in,$out);
|
|
|
105 }
|
|
|
106 for (my $i=0;$i<@thrs;$i++) {
|
|
|
107 $res[$i]=$thrs[$i]->join();
|
|
|
108 }
|
|
|
109 }
|
|
|
110 } else {
|
|
|
111 # Do not processing using threads
|
|
|
112 print "Do not processing using threads\n";
|
|
|
113 for (my $i=0;$i<@filein ;$i++) {
|
|
|
114 my $in=$filein[$i];
|
|
|
115 my $out=$mark[$i];
|
|
|
116 push @clean,$preprocess.$out."_clips_adapter.fq";
|
|
|
117 &clips($in,$out);
|
|
|
118 }
|
|
|
119 }
|
|
|
120
|
|
|
121 ##### clip adpter --> clean data end
|
|
|
122
|
|
|
123 my $collapsed=$preprocess."collapse_reads.fa";
|
|
|
124 my $data=$preprocess."collapse_reads_${min_nt}_${max_nt}.fa"; ## raw clean data
|
|
|
125 &collapse(\@clean,$collapsed); #collapse reads to tags
|
|
|
126
|
|
|
127 &filterbylength(); # filter <$min_nt && >$max_nt
|
|
|
128
|
|
|
129 print "The final clean data file is $data, only contains reads which length is among $min_nt\~$max_nt\n\n";
|
|
|
130
|
|
|
131
|
|
|
132 $time=Time();
|
|
|
133 print "$time: Genome alignment!\n\n";
|
|
|
134 my $genome_map=$dir."genome_match";
|
|
|
135 &genome($data);
|
|
|
136 #my $genome_map=&search($dir,"genome_match_");
|
|
|
137 my $mapfile=$genome_map."/genome_mapped.bwt";
|
|
|
138 my $mapfa=$genome_map."/genome_mapped.fa";
|
|
|
139 my $unmap=$genome_map."/genome_not_mapped.fa";
|
|
|
140
|
|
|
141 chdir $dir;
|
|
|
142 my $pathfile="$dir/path.txt";
|
|
|
143 open PA,">$pathfile";
|
|
|
144 print PA "$config\n";
|
|
|
145 print PA "$preprocess\n";
|
|
|
146 print PA "$genome_map\n";
|
|
|
147
|
|
|
148 if (defined $opts{'rfam'}) { #rfam mapping and analysis
|
|
|
149 $time=Time();
|
|
|
150 print "$time: RNA annotate!\n\n";
|
|
|
151 $time=~s/:/-/g;
|
|
|
152 $time=~s/ /-/g;
|
|
|
153 my $rfam_exp_dir=$dir."rfam_match";
|
|
|
154 &rfam();
|
|
|
155 #my $rfam_exp_dir=&search($dir,"rfam_match_");
|
|
|
156 print PA "$rfam_exp_dir\n";
|
|
|
157
|
|
|
158 my $tag=join "\\;" ,@mark;
|
|
|
159 system("perl $scipt_path/count_rfam_express.pl -i $rfam_exp_dir/rfam_mapped.bwt -tag $tag -o rfam_non-miRNA_annotation.txt");
|
|
|
160 }
|
|
|
161
|
|
|
162
|
|
|
163 close PA;
|
|
|
164 system("perl $scipt_path/html_preprocess.pl -i $pathfile -format $format -min $min_nt -max $max_nt -o $dir/preprocessResult.html");
|
|
|
165
|
|
|
166 $time=Time();
|
|
|
167 print "$time: Program end!!\n";
|
|
|
168
|
|
|
169 ############################## sub programs ###################################
|
|
|
170 sub genome{
|
|
|
171 my ($file)=@_;
|
|
|
172 if(defined $opts{'idx'}){
|
|
|
173 system("perl $scipt_path/matching.pl -i $file -g $opts{gfa} -r 1000 -v $mis -p $t -o $dir -index $opts{idx}") ;
|
|
|
174 # print "\nmatching.pl -i $file -g $opts{gfa} -v $mis -p $t -r $hit -o $dir -index $opts{idx} -time $time\n";
|
|
|
175 }else{
|
|
|
176 system("perl $scipt_path/matching.pl -i $file -g $opts{gfa} -r 1000 -v $mis -p $t -o $dir") ;
|
|
|
177 # print "\nmatching.pl -i $file -g $opts{gfa} -v $mis -p $t -r $hit -o $dir -time $time\n";
|
|
|
178 }
|
|
|
179 }
|
|
|
180 sub rfam{
|
|
|
181 if (defined $opts{'idx2'}) {
|
|
|
182 system("perl $scipt_path/rfam.pl -i $mapfa -ref $opts{rfam} -v $mis_rfam -p $t -o $dir -index $opts{idx2} ");
|
|
|
183 # print "\nrfam.pl -i $data2 -ref $opts{rfam} -v $mis_rfam -p $t -o $dir -index $opts{idx2} -time $time\n";
|
|
|
184 }else{
|
|
|
185 system("perl $scipt_path/rfam.pl -i $mapfa -ref $opts{rfam} -v $mis_rfam -p $t -o $dir ");
|
|
|
186 # print "\nrfam.pl -i $data2 -ref $opts{rfam} -v $mis_rfam -p $t -o $dir -time $time\n";
|
|
|
187 }
|
|
|
188 }
|
|
|
189 sub filterbylength{
|
|
|
190 my $tmpmark=join ",", @mark;
|
|
|
191 system("perl $scipt_path/filterReadsByLength.pl -i $collapsed -o $data -min $min_nt -max $max_nt -mark $tmpmark");
|
|
|
192 system("perl $scipt_path/Length_Distibution.pl -i $preprocess/reads_length_distribution.txt -o $preprocess/length.html");
|
|
|
193 # print "\nfilterReadsByLength.pl -i $collapsed -o $data -min $min_nt -max $max_nt -mark $tmpmark\n";
|
|
|
194
|
|
|
195 }
|
|
|
196 sub collapse{
|
|
|
197 my ($ins,$data)=@_;
|
|
|
198 my $str="";
|
|
|
199 for (my $i=0;$i<@{$ins};$i++) {
|
|
|
200 $str .="-i $$ins[$i] ";
|
|
|
201 }
|
|
|
202 system ("perl $scipt_path/collapseReads2Tags.pl $str -mark seq -o $data -format $format");
|
|
|
203 # print "\ncollapseReads2Tags.pl $str -mark seq -o $data -format $format\n";
|
|
|
204 }
|
|
|
205
|
|
|
206 sub clips{
|
|
|
207 my ($in,$out)=@_;
|
|
|
208 my $adapter=$preprocess.$out."_clips_adapter.fq";
|
|
|
209 if($format eq "fq" || $format eq "fastq"){
|
|
|
210 system("fastx_clipper -a $a -M $m -Q $phred_qv -i $in -o $adapter") ;
|
|
|
211 # print "\nfastx_clipper -a $a -M $m -Q $phred_qv -i $in -o $adapter\n";
|
|
|
212 }
|
|
|
213 if($format eq "fa" || $format eq "fasta"){
|
|
|
214 system("fastx_clipper -a $a -M $m -i $in -o $adapter") ;
|
|
|
215 # print "\nfastx_clipper -a $a -M $m -i $in -o $adapter\n";
|
|
|
216 }
|
|
|
217 #my $clean=$preprocess.$out."_clean.fq";
|
|
|
218 #system("filterReadsByLength.pl -i $adapter -o $clean -min $min_nt -max $max_nt ");
|
|
|
219
|
|
|
220 return;
|
|
|
221 }
|
|
|
222
|
|
|
223 sub read_config{
|
|
|
224 open CON,"<$config";
|
|
|
225 while (my $aline=<CON>) {
|
|
|
226 chomp $aline;
|
|
|
227 my @tmp=split/\t/,$aline;
|
|
|
228 push @filein,$tmp[0];
|
|
|
229 push @mark,$tmp[1];
|
|
|
230 &check_rawdata($tmp[0]);
|
|
|
231 }
|
|
|
232 close CON;
|
|
|
233 if (@filein != @mark) {
|
|
|
234 #&printErr();
|
|
|
235 die "Maybe config file have some wrong!!!\n";
|
|
|
236 }
|
|
|
237 }
|
|
|
238 sub check_rawdata{
|
|
|
239 my ($fileforcheck)=@_;
|
|
|
240 if (!(-s $fileforcheck)) {
|
|
|
241 #&printErr();
|
|
|
242 die "Can not find $fileforcheck, or file is empty!!!\n";
|
|
|
243 }
|
|
|
244 if ($format eq "fasta" || $format eq "fa") {
|
|
|
245 &checkfa($fileforcheck);
|
|
|
246 }
|
|
|
247 if ($format eq "fastq" || $format eq "fq") {
|
|
|
248 &checkfq($fileforcheck);
|
|
|
249 }
|
|
|
250 }
|
|
|
251 sub checkfa{
|
|
|
252 my ($file_reads)=@_;
|
|
|
253 open N,"<$file_reads";
|
|
|
254 my $line=<N>;
|
|
|
255 chomp $line;
|
|
|
256 if($line !~ /^>\S+/){
|
|
|
257 #printErr();
|
|
|
258 die "The first line of file $file_reads does not start with '>identifier'
|
|
|
259 Reads file $file_reads is not a valid fasta file\n\n";
|
|
|
260 }
|
|
|
261 if(<N> !~ /^[ACGTNacgtn]*$/){
|
|
|
262 #printErr();
|
|
|
263 die "File $file_reads contains not allowed characters in sequences
|
|
|
264 Allowed characters are ACGTN
|
|
|
265 Reads file $file_reads is not a fasta file\n\n";
|
|
|
266 }
|
|
|
267 close N;
|
|
|
268 }
|
|
|
269 sub checkfq{
|
|
|
270 my ($file_reads)=@_;
|
|
|
271
|
|
|
272 open N,"<$file_reads";
|
|
|
273 for (my $i=0;$i<10;$i++) {
|
|
|
274 my $a=<N>;
|
|
|
275 my $b=<N>;
|
|
|
276 my $c=<N>;
|
|
|
277 my $d=<N>;
|
|
|
278 chomp $a;
|
|
|
279 chomp $b;
|
|
|
280 chomp $c;
|
|
|
281 chomp $d;
|
|
|
282 if($a!~/^\@/){
|
|
|
283 #&printErr();
|
|
|
284 die "$file_reads is not a fastq file\n\n";
|
|
|
285 }
|
|
|
286 if($b!~ /^[ACGTNacgtn]*$/){
|
|
|
287 #&printErr();
|
|
|
288 die "File $file_reads contains not allowed characters in sequences
|
|
|
289 Allowed characters are ACGTN
|
|
|
290 Reads file $file_reads is not a fasta file\n\n";
|
|
|
291 }
|
|
|
292 if ($c!~/^\@/ && $c!~/^\+/) {
|
|
|
293 #&printErr();
|
|
|
294 die "$file_reads is not a fastq file\n\n";
|
|
|
295 }
|
|
|
296 if ((length $b) != (length $d)) {
|
|
|
297 #&printErr();
|
|
|
298 die "$file_reads is not a fastq file\n\n";
|
|
|
299 }
|
|
|
300 my @qv=split //,$d;
|
|
|
301 for (my $j=0;$j<@qv ;$j++) {
|
|
|
302 my $q=ord($qv[$j])-64;
|
|
|
303 if($q<0){$phred_qv=33;}
|
|
|
304 }
|
|
|
305 }
|
|
|
306 close N;
|
|
|
307 }
|
|
|
308
|
|
|
309 sub search{
|
|
|
310 my ($dir,$str)=@_;
|
|
|
311 opendir I,$dir;
|
|
|
312 my @ret;
|
|
|
313 while (my $file=readdir I) {
|
|
|
314 if ($file=~/$str/) {
|
|
|
315 push @ret, $file;
|
|
|
316 }
|
|
|
317 }
|
|
|
318 closedir I;
|
|
|
319 if (@ret != 1) {
|
|
|
320 #&printErr();
|
|
|
321
|
|
|
322 die "Can not find directory or file which name has string: $str !!!\n";
|
|
|
323 }
|
|
|
324 return $ret[0];
|
|
|
325 }
|
|
|
326
|
|
|
327 sub Time{
|
|
|
328 my $time=time();
|
|
|
329 my ($sec,$min,$hour,$day,$month,$year) = (localtime($time))[0,1,2,3,4,5,6];
|
|
|
330 $month++;
|
|
|
331 $year+=1900;
|
|
|
332 if (length($sec) == 1) {$sec = "0"."$sec";}
|
|
|
333 if (length($min) == 1) {$min = "0"."$min";}
|
|
|
334 if (length($hour) == 1) {$hour = "0"."$hour";}
|
|
|
335 if (length($day) == 1) {$day = "0"."$day";}
|
|
|
336 if (length($month) == 1) {$month = "0"."$month";}
|
|
|
337 #print "$year-$month-$day $hour:$min:$sec\n";
|
|
|
338 return("$year-$month-$day $hour:$min:$sec");
|
|
|
339 }
|
|
|
340
|
|
|
341
|
|
|
342 sub usage{
|
|
|
343 print <<"USAGE";
|
|
|
344 Version $version
|
|
|
345 Usage:
|
|
|
346 $0 -i -format -gfa -index -rfam -a -M -min -max -mis -v -t -o -path
|
|
|
347 options:
|
|
|
348 -i input files, # raw data file, can be multipe eg. -i xxx.fq -i xxx .fq ...
|
|
|
349 -tag string # raw data file names, -tag xxx -tag xxx
|
|
|
350
|
|
|
351 -format string,#specific input rawdata file format : fastq|fq|fasta|fa
|
|
|
352 -phred int # phred quality number, default is 64
|
|
|
353
|
|
|
354 -path scirpt path
|
|
|
355
|
|
|
356 -gfa string, input file # genome fasta. sequence file
|
|
|
357 -idx string, genome file index, file-prefix #(must be indexed by bowtie-build) The parameter
|
|
|
358 string must be the prefix of the bowtie index. For instance, if
|
|
|
359 the first indexed file is called 'h_sapiens_37_asm.1.ebwt' then
|
|
|
360 the prefix is 'h_sapiens_37_asm'.##can be null
|
|
|
361
|
|
|
362 -rfam string, input file# rfam database file, microRNAs must not be contained in this file## if not define, rfam small RNA will not be count.
|
|
|
363 -idx2 string, rfam file index, file-prefix #(must be indexed by bowtie-build) The parameter
|
|
|
364 string must be the prefix of the bowtie index. For instance, if
|
|
|
365 the first indexed file is called 'h_sapiens_37_asm.1.ebwt' then
|
|
|
366 the prefix is 'h_sapiens_37_asm'.##can be null
|
|
|
367
|
|
|
368 -a string, ADAPTER string. default is ATCTCGTATG.
|
|
|
369 -M int, require minimum adapter alignment length of N. If less than N nucleotides aligned with the adapter - don't clip it.
|
|
|
370 -min int, reads min length,default is 19.
|
|
|
371 -max int, reads max length,default is 28.
|
|
|
372
|
|
|
373 -mis [int] number of allowed mismatches when mapping reads to genome, default 0
|
|
|
374 -v <int> report end-to-end hits w/ <=v mismatches; ignore qualities,default 0; used in rfam alignment
|
|
|
375
|
|
|
376 -t int, number of threads [1]
|
|
|
377
|
|
|
378 -o output directory# absolute path
|
|
|
379 -h help
|
|
|
380 USAGE
|
|
|
381 exit(1);
|
|
|
382 }
|
|
|
383
|
