Mercurial > repos > big-tiandm > sirna_plant

comparison html.pl @ 19:e0884a4b996b 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 01:17:26 -0500
parents 0e4b6b0c6e9d
children
comparison
equal deleted inserted replaced
18:22d79320085c 19:e0884a4b996b
11 use Getopt::Long; 11 use Getopt::Long;
12 use File::Basename; 12 use File::Basename;
13 13
14 my %opts; 14 my %opts;
15 GetOptions(\%opts,"i=s","format=s","o=s","h"); 15 GetOptions(\%opts,"i=s","format=s","o=s","h");
16 if (!(defined $opts{o} and defined $opts{format} and defined $opts{i} ) || defined $opts{h}) { #necessary arguments 16 if (!(defined $opts{o} and defined $opts{format} and defined $opts{i} ) || defined $opts{h}) { #necessary arguments
17 &usage; 17 &usage;
18 } 18 }
19 my ($config,$prepath,$rfampath,$genomepath,$clusterpath,$annotatepath,$degpath); 19 my ($config,$prepath,$rfampath,$genomepath,$clusterpath,$annotatepath,$plotpath,$degpath);
20 my ($predir,$rfamdir,$genomedir,$clusterdir,$annotatedir,$degdir); 20 my ($predir,$rfamdir,$genomedir,$clusterdir,$annotatedir,$plotdir,$degdir);
21 open IN,"<$opts{i}"; 21 open IN,"<$opts{i}";
22 $config=<IN>; chomp $config; 22 $config=<IN>; chomp $config;
23 $prepath=<IN>; chomp $prepath; 23 $prepath=<IN>; chomp $prepath;
24 $rfampath=<IN>;chomp $rfampath; 24 $rfampath=<IN>;chomp $rfampath;
25 $genomepath=<IN>; chomp $genomepath; 25 $genomepath=<IN>; chomp $genomepath;
26 $clusterpath=<IN>; chomp $clusterpath; 26 $clusterpath=<IN>; chomp $clusterpath;
27 $annotatepath=<IN>; chomp $annotatepath; 27 $annotatepath=<IN>; chomp $annotatepath;
28 $plotpath=<IN>; chomp $plotpath;
28 my $deg_tag=1; 29 my $deg_tag=1;
29 if(eof){$deg_tag=0;} 30 if(eof){$deg_tag=0;}
30 else{ 31 else{
31 $degpath=<IN>; chomp $degpath; 32 $degpath=<IN>; chomp $degpath;
32 } 33 }
39 $genomedir=$tmp[-1]; 40 $genomedir=$tmp[-1];
40 @tmp=split/\//,$clusterpath; 41 @tmp=split/\//,$clusterpath;
41 $clusterdir=$tmp[-1]; 42 $clusterdir=$tmp[-1];
42 @tmp=split/\//,$annotatepath; 43 @tmp=split/\//,$annotatepath;
43 $annotatedir=$tmp[-1]; 44 $annotatedir=$tmp[-1];
44 #@tmp=split/\//,$degpath; 45 @tmp=split/\//,$plotpath;
45 #$degdir=$tmp[-1]; 46 $plotdir=$tmp[-1];
46 47
47 my $dir=dirname($opts{'o'}); 48 my $dir=dirname($opts{'o'});
48 49
49 open OUT ,">$opts{'o'}"; 50 open OUT ,">$opts{'o'}";
50 print OUT "<HTML>\n <HEAD>\n <TITLE> Analysis Report </TITLE>\n </HEAD> 51 print OUT "<HTML>\n <HEAD>\n <TITLE> Analysis Report </TITLE>\n </HEAD>
199 print OUT "The collapsed file path is: <b>$collapsefile</b><br /> 200 print OUT "The collapsed file path is: <b>$collapsefile</b><br />
200 The clean data file path is: <b>$clean</b><br /> 201 The clean data file path is: <b>$clean</b><br />
201 The filter (remain total reads>3) data file path is: <b>$filter</b><br /> 202 The filter (remain total reads>3) data file path is: <b>$filter</b><br />
202 </p> 203 </p>
203 <h2> 1. Sequence length count</h2> 204 <h2> 1. Sequence length count</h2>
204 <h3> 1.1 Reads length</h3> 205 ";
205 "; 206 print OUT "\n";
206 207
207 print OUT "<img src=\"./$predir/Reads_length_after_count_filter.png\" alt=\"Reads_length_after_count_filter.png\" width=\"400\" height=\"300\"/> 208 my $length=$prepath."length.html";
208 <h3> 1.2 Tags length count</h3> 209 open IN,"<$length";
209 <img src=\"./$predir/Tags_length_after_count_filter.png\" alt=\"Tags_length_after_count_filter.png\" width=\"400\" height=\"300\"/> 210 while (my $aline=<IN>) {
210 <p> Note:<br />The sequence length data: <a href=\"./$predir/reads_length_distribution_after_count_filter.txt\"> length file</a> 211 chomp $aline;
212 print OUT "$aline\n";
213 }
214 close IN;
215
216 print OUT "<p> Note:<br />The sequence length data: <a href=\"./$predir/reads_length_distribution_after_count_filter.txt\"> length file</a>
211 </p> 217 </p>
212 "; 218 ";
213 219
214 #### rfam 220 #### rfam
215 unless ($rfampath=~/\/$/) { 221 unless ($rfampath=~/\/$/) {
359 365
360 my $cluster="$clusterpath/sample_reads.cluster"; 366 my $cluster="$clusterpath/sample_reads.cluster";
361 my $cluster_number=`less $cluster |wc -l `; 367 my $cluster_number=`less $cluster |wc -l `;
362 $cluster_number=$cluster_number-1; 368 $cluster_number=$cluster_number-1;
363 my (%cluster_length,@exp,@rpkm); 369 my (%cluster_length,@exp,@rpkm);
364 my @exp_range=qw(0 1--9 10--99 100--999 1000--9999 10000--99999 100000--**); 370 my @exp_range=qw(0 \(0--10] \(10--100] \(100--1000] \(1000--10000] \(10000--100000] \(100000--**\));
365 my @rpkm_range=qw(0 0--0.25 0.25--0.5 0.5--1 1.0--5.0 5.0--10 10--50 50--100 100--500 500--1000 1000--**); 371 my @rpkm_range=qw(0 \(0--0.25] \(0.25--0.5] \(0.5--1] \(1.0-5.0] \(5--10] \(10--50] \(50--100] \(100--500] \(500--1000] \(1000--**]);
366 372
367 open IN,"<$cluster"; 373 open IN,"<$cluster";
368 while (my $aline=<IN>) { 374 while (my $aline=<IN>) {
369 next if($aline=~/^\"/); 375 next if($aline=~/^\"/);
370 chomp $aline; 376 chomp $aline;
371 my @temp=split/\t/,$aline; 377 my @temp=split/\t/,$aline;
372 my @id=split/:|-/,$temp[0]; 378 my @id=split/:|-/,$temp[0];
373 $cluster_length{$id[2]-$id[1]+1}++; 379 $cluster_length{$id[2]-$id[1]+1}++;
374 for (my $i=0;$i<@marks ;$i++) { 380 for (my $i=0;$i<@marks ;$i++) {
375 if ($temp[$i+3] == 0) {$exp[$i][0]++;} 381 if ($temp[$i+3] == 0) {$exp[0][$i]++;}
376 elsif ($temp[$i+3]>0 && $temp[$i+3]<= 10 ){$exp[$i][1]++;} 382 elsif ($temp[$i+3]>0 && $temp[$i+3]<= 10 ){$exp[1][$i]++;}
377 elsif ($temp[$i+3]>10 && $temp[$i+3]<=100){$exp[$i][2]++;} 383 elsif ($temp[$i+3]>10 && $temp[$i+3]<=100){$exp[2][$i]++;}
378 elsif ($temp[$i+3]>100 && $temp[$i+3]<=1000){$exp[$i][3]++;} 384 elsif ($temp[$i+3]>100 && $temp[$i+3]<=1000){$exp[3][$i]++;}
379 elsif ($temp[$i+3]>1000 && $temp[$i+3]<=10000){$exp[$i][4]++;} 385 elsif ($temp[$i+3]>1000 && $temp[$i+3]<=10000){$exp[4][$i]++;}
380 elsif ($temp[$i+3]>10000 && $temp[$i+3]<=100000){$exp[$i][5]++;} 386 elsif ($temp[$i+3]>10000 && $temp[$i+3]<=100000){$exp[5][$i]++;}
381 elsif ($temp[$i+3]>100000){$exp[$i][6]++;} 387 elsif ($temp[$i+3]>100000){$exp[6][$i]++;}
382 } 388 }
383 } 389 }
384 close IN; 390 close IN;
385 391
386 my $cluster_rpkm="$clusterpath/sample_rpkm.cluster"; 392 my $cluster_rpkm="$clusterpath/sample_rpkm.cluster";
388 while (my $aline=<IN>) { 394 while (my $aline=<IN>) {
389 next if($aline=~/^\#/); 395 next if($aline=~/^\#/);
390 chomp $aline; 396 chomp $aline;
391 my @temp=split/\t/,$aline; 397 my @temp=split/\t/,$aline;
392 for (my $i=0;$i<@marks ;$i++) { 398 for (my $i=0;$i<@marks ;$i++) {
393 if ($temp[$i+3]==0) {$rpkm[$i][0]++;} 399 if ($temp[$i+3]==0) {$rpkm[0][$i]++;}
394 elsif($temp[$i+3]>0 && $temp[$i+3]<=0.25){$rpkm[$i][1]++;} 400 elsif($temp[$i+3]>0 && $temp[$i+3]<=0.25){$rpkm[1][$i]++;}
395 elsif($temp[$i+3]>0.25 && $temp[$i+3]<=0.5){$rpkm[$i][2]++;} 401 elsif($temp[$i+3]>0.25 && $temp[$i+3]<=0.5){$rpkm[2][$i]++;}
396 elsif($temp[$i+3]>0.5 && $temp[$i+3]<=1){$rpkm[$i][3]++;} 402 elsif($temp[$i+3]>0.5 && $temp[$i+3]<=1){$rpkm[3][$i]++;}
397 elsif($temp[$i+3]>1 && $temp[$i+3]<=5){$rpkm[$i][4]++;} 403 elsif($temp[$i+3]>1 && $temp[$i+3]<=5){$rpkm[4][$i]++;}
398 elsif($temp[$i+3]>5 && $temp[$i+3]<=10){$rpkm[$i][5]++;} 404 elsif($temp[$i+3]>5 && $temp[$i+3]<=10){$rpkm[5][$i]++;}
399 elsif($temp[$i+3]>10 && $temp[$i+3]<=50){$rpkm[$i][6]++;} 405 elsif($temp[$i+3]>10 && $temp[$i+3]<=50){$rpkm[6][$i]++;}
400 elsif($temp[$i+3]>50 && $temp[$i+3]<=100){$rpkm[$i][7]++;} 406 elsif($temp[$i+3]>50 && $temp[$i+3]<=100){$rpkm[7][$i]++;}
401 elsif($temp[$i+3]>100 && $temp[$i+3]<=500){$rpkm[$i][8]++;} 407 elsif($temp[$i+3]>100 && $temp[$i+3]<=500){$rpkm[8][$i]++;}
402 elsif($temp[$i+3]>500 && $temp[$i+3]<=1000){$rpkm[$i][9]++;} 408 elsif($temp[$i+3]>500 && $temp[$i+3]<=1000){$rpkm[9][$i]++;}
403 else{$rpkm[$i][10]++;} 409 else{$rpkm[10][$i]++;}
404 } 410 }
405 } 411 }
406 412
407 close IN; 413 close IN;
408 414
482 $long[$j]=0; 488 $long[$j]=0;
483 $repeat[$j]=0; 489 $repeat[$j]=0;
484 $nat[$j]=0; 490 $nat[$j]=0;
485 } 491 }
486 492
487 my $class_anno=6; 493 my $class_anno=1;
488 open ANNO,"<$annotate"; 494 open ANNO,"<$annotate";
489 while (my $aline=<ANNO>) { 495 while (my $aline=<ANNO>) {
490 chomp $aline; 496 chomp $aline;
491 my @temp=split/\t/,$aline; 497 my @temp=split/\t/,$aline;
492 if($aline=~/^\#/){ 498 if($aline=~/^\#/){
692 print OUT "<h3>5.2 Cluster source mechanism annotate</h3> 698 print OUT "<h3>5.2 Cluster source mechanism annotate</h3>
693 <br />Do not do source mechanism annotate <br />"; 699 <br />Do not do source mechanism annotate <br />";
694 700
695 } 701 }
696 702
703 print OUT "<h2>6. Graph of Clusters of all samples</h2> \n";
704
705 my $plot=$plotpath."cluster.html";
706 open IN,"<$plot";
707 while (my $aline=<IN>) {
708 chomp $aline;
709 print OUT "$aline\n";
710 }
711 close IN;
712
713
697 if ($deg_tag) { 714 if ($deg_tag) {
698 my $deg_file=`ls $degpath`; 715 my $deg_file=`ls $degpath`;
699 chomp $deg_file; 716 chomp $deg_file;
700 my @deg_file=split/\n/,$deg_file; 717 my @deg_file=split/\n/,$deg_file;
701 my %deg; 718 my %deg;
720 } 737 }
721 } 738 }
722 close IN; 739 close IN;
723 } 740 }
724 741
725 print OUT "<h2>6. DEG</h2> 742 print OUT "<h2>7. DEG</h2>
726 <table border=\"1\"> 743 <table border=\"1\">
727 <tr align=\"center\"> 744 <tr align=\"center\">
728 <th align=\"left\">Genes number</th>\n 745 <th align=\"left\">Genes number</th>\n
729 <th> DEG </th>\n 746 <th> DEG </th>\n
730 <th> UP </th>\n 747 <th> UP </th>\n
741 } 758 }
742 } 759 }
743 print OUT "</tr>\n</table>"; 760 print OUT "</tr>\n</table>";
744 } 761 }
745 else{ 762 else{
746 print OUT "<h2>6. DEG</h2> 763 print OUT "<h2>7. DEG</h2>
747 <br />Do not do DE clusters <br />"; 764 <br />Do not do DE clusters <br />";
748 } 765 }
749 766
750 print OUT " 767 print OUT "
751 </BODY> 768 </BODY>