|
0
|
1 #!/usr/bin/perl -w
|
|
|
2 #Filename:
|
|
|
3 #Author: Tian Dongmei
|
|
|
4 #Email: tiandm@big.ac.cn
|
|
|
5 #Date: 2014-5-29
|
|
|
6 #Modified:
|
|
|
7 #Description:
|
|
|
8 my $version=1.00;
|
|
|
9
|
|
|
10 use strict;
|
|
|
11 use Getopt::Long;
|
|
|
12 use File::Basename;
|
|
|
13
|
|
|
14 my %opts;
|
|
|
15 GetOptions(\%opts,"i=s","format=s","o=s","h");
|
|
|
16 if (!(defined $opts{o} and defined $opts{format} and defined $opts{i} ) || defined $opts{h}) { #necessary arguments
|
|
|
17 &usage;
|
|
|
18 }
|
|
|
19 my ($config,$prepath,$rfampath,$genomepath,$clusterpath,$annotatepath,$degpath);
|
|
|
20 my ($predir,$rfamdir,$genomedir,$clusterdir,$annotatedir,$degdir);
|
|
|
21 open IN,"<$opts{i}";
|
|
|
22 $config=<IN>; chomp $config;
|
|
|
23 $prepath=<IN>; chomp $prepath;
|
|
|
24 $rfampath=<IN>;chomp $rfampath;
|
|
|
25 $genomepath=<IN>; chomp $genomepath;
|
|
|
26 $clusterpath=<IN>; chomp $clusterpath;
|
|
|
27 $annotatepath=<IN>; chomp $annotatepath;
|
|
|
28 $degpath=<IN>; chomp $degpath;
|
|
|
29 close IN;
|
|
|
30 my @tmp=split/\//,$prepath;
|
|
|
31 $predir=$tmp[-1];
|
|
|
32 @tmp=split/\//,$rfampath;
|
|
|
33 $rfamdir=$tmp[-1];
|
|
|
34 @tmp=split/\//,$genomepath;
|
|
|
35 $genomedir=$tmp[-1];
|
|
|
36 @tmp=split/\//,$clusterpath;
|
|
|
37 $clusterdir=$tmp[-1];
|
|
|
38 @tmp=split/\//,$annotatepath;
|
|
|
39 $annotatedir=$tmp[-1];
|
|
|
40 @tmp=split/\//,$degpath;
|
|
|
41 $degdir=$tmp[-1];
|
|
|
42
|
|
|
43 my $dir=dirname($opts{'o'});
|
|
|
44
|
|
|
45 open OUT ,">$opts{'o'}";
|
|
|
46 print OUT "<HTML>\n <HEAD>\n <TITLE> Analysis Report </TITLE>\n </HEAD>
|
|
|
47 <BODY bgcolor=\"lightgray\">\n <h1 align=\"center\">\n <font face=\"ºÚÌå\">\n <b>Small RNA Analysis Report</b>\n </font>\n </h1>
|
|
|
48 <h2>1. Sequence No. and quality</h2>
|
|
|
49 <h3>1.1 Sequece No.</h3>
|
|
|
50 ";
|
|
|
51
|
|
|
52 ### raw data no
|
|
|
53 open IN,"<$config";
|
|
|
54 my @files;my @marks; my @rawNo;
|
|
|
55 while (my $aline=<IN>) {
|
|
|
56 chomp $aline;
|
|
|
57 my @tmp=split/\t/,$aline;
|
|
|
58 push @files,$tmp[0];
|
|
|
59
|
|
|
60 my $no=`less $tmp[0] |wc -l `;
|
|
|
61 chomp $no;
|
|
|
62 if ($opts{'format'} eq "fq" || $opts{'format'} eq "fastq") {
|
|
|
63 $no=$no/4;
|
|
|
64 }
|
|
|
65 else{
|
|
|
66 $no=$no/2;
|
|
|
67 }
|
|
|
68 push @rawNo,$no;
|
|
|
69
|
|
|
70 push @marks,$tmp[1];
|
|
|
71 }
|
|
|
72 close IN;
|
|
|
73
|
|
|
74 ### preprocess
|
|
|
75 unless ($prepath=~/\/$/) {
|
|
|
76 $prepath .="/";
|
|
|
77 }
|
|
|
78
|
|
|
79 my @trimNo;my @collapse;
|
|
|
80 my $collapsefile=$prepath."collapse_reads.fa";
|
|
|
81 open IN,"<$collapsefile";
|
|
|
82 while (my $aline=<IN>) {
|
|
|
83 chomp $aline;
|
|
|
84 <IN>;
|
|
|
85 $aline=~/:([\d|_]+)_x(\d+)$/;
|
|
|
86 my @lng=split/_/,$1;
|
|
|
87 for (my $i=0;$i<@lng;$i++) {
|
|
|
88 if ($lng[$i]>0) {
|
|
|
89 $trimNo[$i] +=$lng[$i];
|
|
|
90 $collapse[$i] ++;
|
|
|
91 }
|
|
|
92 }
|
|
|
93 }
|
|
|
94 close IN;
|
|
|
95
|
|
|
96 my @cleanR;my @cleanT;
|
|
|
97 my $clean=$prepath."collapse_reads_18-40.fa";
|
|
|
98 open IN,"<$clean";
|
|
|
99 while (my $aline=<IN>) {
|
|
|
100 chomp $aline;
|
|
|
101 <IN>;
|
|
|
102 $aline=~/:([\d|_]+)_x(\d+)$/;
|
|
|
103 my @lng=split/_/,$1;
|
|
|
104 for (my $i=0;$i<@lng;$i++) {
|
|
|
105 if ($lng[$i]>0) {
|
|
|
106 $cleanR[$i] +=$lng[$i];
|
|
|
107 $cleanT[$i] ++;
|
|
|
108 }
|
|
|
109 }
|
|
|
110 }
|
|
|
111 close IN;
|
|
|
112
|
|
|
113 my @filterR;my @filterT;
|
|
|
114 my $filter=$prepath."collapse_reads_out.fa";
|
|
|
115 open IN,"<$filter";
|
|
|
116 while (my $aline=<IN>) {
|
|
|
117 chomp $aline;
|
|
|
118 <IN>;
|
|
|
119 $aline=~/:([\d|_]+)_x(\d+)$/;
|
|
|
120 my @lng=split/_/,$1;
|
|
|
121 for (my $i=0;$i<@lng;$i++) {
|
|
|
122 if ($lng[$i]>0) {
|
|
|
123 $filterR[$i] +=$lng[$i];
|
|
|
124 $filterT[$i] ++;
|
|
|
125 }
|
|
|
126 }
|
|
|
127 }
|
|
|
128 close IN;
|
|
|
129
|
|
|
130
|
|
|
131 print OUT "<table border=\"1\">
|
|
|
132 <tr align=\"center\">
|
|
|
133 <th> </th>
|
|
|
134 ";
|
|
|
135 foreach (@marks) {
|
|
|
136 print OUT "<th> $_ </th>\n";
|
|
|
137 }
|
|
|
138 print OUT "</tr>
|
|
|
139 <tr align=\"center\">
|
|
|
140 <th align=\"left\">Raw Reads No. </th>
|
|
|
141 ";
|
|
|
142 foreach (@rawNo) {
|
|
|
143 print OUT "<td> $_ </td>\n";
|
|
|
144 }
|
|
|
145 print OUT "</tr>
|
|
|
146 <tr align=\"center\">
|
|
|
147 <th align=\"left\">Reads No. After Trimed 3\' adapter </th>
|
|
|
148 ";
|
|
|
149 foreach (@trimNo) {
|
|
|
150 print OUT "<td> $_ </td>\n";
|
|
|
151 }
|
|
|
152 print OUT "</tr>
|
|
|
153 <tr align=\"center\">
|
|
|
154 <th align=\"left\">Unique Tags No. </th>
|
|
|
155 ";
|
|
|
156 foreach (@collapse) {
|
|
|
157 print OUT "<td> $_ </td>\n";
|
|
|
158 }
|
|
|
159 print OUT "</tr>
|
|
|
160 <tr align=\"center\">
|
|
|
161 <th align=\"left\">Clean Reads No. </th>
|
|
|
162 ";
|
|
|
163 foreach (@cleanR) {
|
|
|
164 print OUT "<td> $_ </td>\n";
|
|
|
165 }
|
|
|
166 print OUT "</tr>
|
|
|
167 <tr align=\"center\">
|
|
|
168 <th align=\"left\">Clean Tags No. </th>
|
|
|
169 ";
|
|
|
170 foreach (@cleanT) {
|
|
|
171 print OUT "<td> $_ </td>\n";
|
|
|
172 }
|
|
|
173 print OUT "</tr>
|
|
|
174 <tr align=\"center\">
|
|
|
175 <th align=\"left\">Filter Reads No. \(reads count \>3\) </th>
|
|
|
176 ";
|
|
|
177 foreach (@filterR) {
|
|
|
178 print OUT "<td> $_ </td>\n";
|
|
|
179 }
|
|
|
180 print OUT "</tr>
|
|
|
181 <tr align=\"center\">
|
|
|
182 <th align=\"left\">Filter Tags No. \(reads count \>3\) </th>
|
|
|
183 ";
|
|
|
184 foreach (@filterT) {
|
|
|
185 print OUT "<td> $_ </td>\n";
|
|
|
186 }
|
|
|
187 print OUT "</tr>\n</table>";
|
|
|
188 print OUT "<p>
|
|
|
189 Note:<br />
|
|
|
190 The raw data file path is: <b>$files[0]</b><br />
|
|
|
191 ";
|
|
|
192 for (my $i=1;$i<@files;$i++) {
|
|
|
193 print OUT "          <b>$files[$i]</b><br />";
|
|
|
194 }
|
|
|
195 print OUT "The collapsed file path is: <b>$collapsefile</b><br />
|
|
|
196 The clean data file path is: <b>$clean</b><br />
|
|
|
197 The filter (remain total reads>3) data file path is: <b>$filter</b><br />
|
|
|
198 </p>
|
|
|
199 <h2> 1. Sequence length count</h2>
|
|
|
200 <h3> 1.1 Reads length</h3>
|
|
|
201 ";
|
|
|
202
|
|
|
203 print OUT "<img src=\"./$predir/Reads_length_after_count_filter.png\" alt=\"Reads_length_after_count_filter.png\" width=\"400\" height=\"300\"/>
|
|
|
204 <h3> 1.2 Tags length count</h3>
|
|
|
205 <img src=\"./$predir/Tags_length_after_count_filter.png\" alt=\"Tags_length_after_count_filter.png\" width=\"400\" height=\"300\"/>
|
|
|
206 <p> Note:<br />The sequence length data: <a href=\"./$predir/reads_length_distribution_after_count_filter.txt\"> length file</a>
|
|
|
207 </p>
|
|
|
208 ";
|
|
|
209
|
|
|
210 #### rfam
|
|
|
211 unless ($rfampath=~/\/$/) {
|
|
|
212 $rfampath .="/";
|
|
|
213 }
|
|
|
214 unless ($genomepath=~/\/$/) {
|
|
|
215 $genomepath .="/";
|
|
|
216 }
|
|
|
217 print OUT "<h2>2. Rfam non-miRNA annotation</h2>
|
|
|
218 <h3>2.1 Reads count</h3>
|
|
|
219 <table border=\"1\">
|
|
|
220 <tr align=\"center\">
|
|
|
221 ";
|
|
|
222
|
|
|
223 my @rfamR; my @rfamT;
|
|
|
224 my $tag=1;
|
|
|
225 open IN,"<$dir/rfam_match/rfam_non-miRNA_annotation.txt";
|
|
|
226 while (my $aline=<IN>) {
|
|
|
227 chomp $aline;
|
|
|
228 $tag=0 if($aline=~/tags\s+number/);
|
|
|
229 next if($aline=~/^\#/);
|
|
|
230 next if($aline=~/^\s*$/);
|
|
|
231 my @tmp=split/\s+/,$aline;
|
|
|
232 if($tag == 1){push @rfamR,[@tmp];}
|
|
|
233 else{push @rfamT,[@tmp];}
|
|
|
234 }
|
|
|
235 close IN;
|
|
|
236
|
|
|
237
|
|
|
238 print OUT "<th>RNA Name</th>\n";
|
|
|
239 foreach (@marks) {
|
|
|
240 print OUT "<th> $_ </th>\n";
|
|
|
241 }
|
|
|
242 for (my $i=0;$i<@rfamR;$i++) {
|
|
|
243 print OUT "</tr>
|
|
|
244 <tr align=\"center\">
|
|
|
245 <th align=\"left\">$rfamR[$i][0]</th>
|
|
|
246 ";
|
|
|
247 for (my $j=1;$j<@{$rfamR[$i]} ;$j++) {
|
|
|
248 print OUT "<td> $rfamR[$i][$j]</td>\n";
|
|
|
249 }
|
|
|
250 }
|
|
|
251
|
|
|
252 print OUT "</tr>\n</table>
|
|
|
253 <h3>2.2 Tags count</h3>
|
|
|
254 <table border=\"1\">
|
|
|
255 <tr align=\"center\">
|
|
|
256 <th>RNA Name</th>\n";
|
|
|
257 foreach (@marks) {
|
|
|
258 print OUT "<th> $_ </th>\n";
|
|
|
259 }
|
|
|
260 for (my $i=0;$i<@rfamT;$i++) {
|
|
|
261 print OUT "</tr>
|
|
|
262 <tr align=\"center\">
|
|
|
263 <th align=\"left\">$rfamT[$i][0]</th>
|
|
|
264 ";
|
|
|
265 for (my $j=1;$j<@{$rfamT[$i]} ;$j++) {
|
|
|
266 print OUT "<td> $rfamT[$i][$j]</td>\n";
|
|
|
267 }
|
|
|
268 }
|
|
|
269 print OUT "</tr>\n</table>
|
|
|
270 <p>Note:<br />The rfam mapping results is: <b>$rfampath</b>";
|
|
|
271 print OUT "<b>rfam_mapped.bwt</b></p>";
|
|
|
272
|
|
|
273 open IN,"<$dir/genome_match/genome_mapped.bwt";
|
|
|
274 my @genome_r_u;
|
|
|
275 my @genome_r_m;
|
|
|
276 my @genome_t_u;
|
|
|
277 my @genome_t_m;
|
|
|
278 my $tags_map_number=0;
|
|
|
279 while (my $aline=<IN>) {
|
|
|
280 chomp $aline;
|
|
|
281 my @temp=split/\t/,$aline;
|
|
|
282 if ($temp[6]==0) {
|
|
|
283 $aline=~/:([\d|_]+)_x(\d+)/;
|
|
|
284 my @lng=split/_/,$1;
|
|
|
285 for (my $i=0;$i<@lng;$i++) {
|
|
|
286 if ($lng[$i]>0) {
|
|
|
287 $genome_r_u[$i] +=$lng[$i];
|
|
|
288 $genome_t_u[$i] ++;
|
|
|
289 }
|
|
|
290 }
|
|
|
291 $tags_map_number++;
|
|
|
292 }
|
|
|
293 if ($temp[6]>0) {
|
|
|
294 $aline=~/:([\d|_]+)_x(\d+)/;
|
|
|
295 my @lng=split/_/,$1;
|
|
|
296 for (my $i=0;$i<@lng;$i++) {
|
|
|
297 if ($lng[$i]>0) {
|
|
|
298 $genome_r_m[$i] +=$lng[$i];
|
|
|
299 $genome_t_m[$i] ++;
|
|
|
300 }
|
|
|
301 }
|
|
|
302 for (my $i=0;$i<$temp[6] ;$i++) {
|
|
|
303 my $next=<IN>;
|
|
|
304 }
|
|
|
305 $tags_map_number++;
|
|
|
306 }
|
|
|
307 }
|
|
|
308 close IN;
|
|
|
309 #<h3>3.1 Reads count</h3>
|
|
|
310 #<table border=\"1\">
|
|
|
311 #<tr align=\"center\">
|
|
|
312 print OUT "<h2>3. genome mapping result</h2>
|
|
|
313 <table border=\"1\">
|
|
|
314 <tr align=\"center\">
|
|
|
315 <th align=\"left\">Map</th>\n
|
|
|
316 ";
|
|
|
317 foreach (@marks) {
|
|
|
318 print OUT "<th> $_ </th>\n";
|
|
|
319 }
|
|
|
320 print OUT "</tr>
|
|
|
321 <tr align=\"center\">
|
|
|
322 <th align=\"left\">Uniq Map Reads No.</th>
|
|
|
323 ";
|
|
|
324 for (my $i=0;$i<@genome_r_u ;$i++) {
|
|
|
325 print OUT "<td> $genome_r_u[$i]</td>\n";
|
|
|
326 }
|
|
|
327
|
|
|
328 print OUT "</tr>
|
|
|
329 <tr align=\"center\">
|
|
|
330 <th align=\"left\">Uniq Map Tags No.</th>
|
|
|
331 ";
|
|
|
332 for (my $i=0;$i<@genome_t_u ;$i++) {
|
|
|
333 print OUT "<td> $genome_t_u[$i]</td>\n";
|
|
|
334 }
|
|
|
335
|
|
|
336 print OUT "</tr>
|
|
|
337 <tr align=\"center\">
|
|
|
338 <th align=\"left\">Multiple Map Reads No.</th>
|
|
|
339 ";
|
|
|
340 for (my $i=0;$i<@genome_r_m ;$i++) {
|
|
|
341 print OUT "<td> $genome_r_m[$i]</td>\n";
|
|
|
342 }
|
|
|
343
|
|
|
344 print OUT "</tr>
|
|
|
345 <tr align=\"center\">
|
|
|
346 <th align=\"left\">Multiple Map Tags No.</th>
|
|
|
347 ";
|
|
|
348 for (my $i=0;$i<@genome_t_m ;$i++) {
|
|
|
349 print OUT "<td> $genome_t_m[$i]</td>\n";
|
|
|
350 }
|
|
|
351
|
|
|
352 print OUT "</tr>\n</table>
|
|
|
353 <p>Note:<br />The genome mapping results is: <b>$genomepath</b>";
|
|
|
354 print OUT "<b>genome_mapped.bwt</b></p>";
|
|
|
355
|
|
|
356 my $cluster="$clusterpath/sample_reads.cluster";
|
|
|
357 my $cluster_number=`less $cluster |wc -l `;
|
|
|
358 $cluster_number=$cluster_number-1;
|
|
|
359 my (%cluster_length,@exp,@rpkm);
|
|
|
360 my @exp_range=qw(0 1--9 10--99 100--999 1000--9999 10000--99999 100000--**);
|
|
|
361 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--**);
|
|
|
362
|
|
|
363 open IN,"<$cluster";
|
|
|
364 while (my $aline=<IN>) {
|
|
|
365 next if($aline=~/^\"/);
|
|
|
366 chomp $aline;
|
|
|
367 my @temp=split/\t/,$aline;
|
|
|
368 my @id=split/:|-/,$temp[0];
|
|
|
369 $cluster_length{$id[2]-$id[1]+1}++;
|
|
|
370 for (my $i=0;$i<@marks ;$i++) {
|
|
|
371 if ($temp[$i+3] == 0) {$exp[$i][0]++;}
|
|
|
372 elsif ($temp[$i+3]>0 && $temp[$i+3]<= 10 ){$exp[$i][1]++;}
|
|
|
373 elsif ($temp[$i+3]>10 && $temp[$i+3]<=100){$exp[$i][2]++;}
|
|
|
374 elsif ($temp[$i+3]>100 && $temp[$i+3]<=1000){$exp[$i][3]++;}
|
|
|
375 elsif ($temp[$i+3]>1000 && $temp[$i+3]<=10000){$exp[$i][4]++;}
|
|
|
376 elsif ($temp[$i+3]>10000 && $temp[$i+3]<=100000){$exp[$i][5]++;}
|
|
|
377 elsif ($temp[$i+3]>100000){$exp[$i][6]++;}
|
|
|
378 }
|
|
|
379 }
|
|
|
380 close IN;
|
|
|
381
|
|
|
382 my $cluster_rpkm="$clusterpath/sample_rpkm.cluster";
|
|
|
383 open IN,"<$cluster_rpkm";
|
|
|
384 while (my $aline=<IN>) {
|
|
|
385 next if($aline=~/^\#/);
|
|
|
386 chomp $aline;
|
|
|
387 my @temp=split/\t/,$aline;
|
|
|
388 for (my $i=0;$i<@marks ;$i++) {
|
|
|
389 if ($temp[$i+3]==0) {$rpkm[$i][0]++;}
|
|
|
390 elsif($temp[$i+3]>0 && $temp[$i+3]<=0.25){$rpkm[$i][1]++;}
|
|
|
391 elsif($temp[$i+3]>0.25 && $temp[$i+3]<=0.5){$rpkm[$i][2]++;}
|
|
|
392 elsif($temp[$i+3]>0.5 && $temp[$i+3]<=1){$rpkm[$i][3]++;}
|
|
|
393 elsif($temp[$i+3]>1 && $temp[$i+3]<=5){$rpkm[$i][4]++;}
|
|
|
394 elsif($temp[$i+3]>5 && $temp[$i+3]<=10){$rpkm[$i][5]++;}
|
|
|
395 elsif($temp[$i+3]>10 && $temp[$i+3]<=50){$rpkm[$i][6]++;}
|
|
|
396 elsif($temp[$i+3]>50 && $temp[$i+3]<=100){$rpkm[$i][7]++;}
|
|
|
397 elsif($temp[$i+3]>100 && $temp[$i+3]<=500){$rpkm[$i][8]++;}
|
|
|
398 elsif($temp[$i+3]>500 && $temp[$i+3]<=1000){$rpkm[$i][9]++;}
|
|
|
399 else{$rpkm[$i][10]++;}
|
|
|
400 }
|
|
|
401 }
|
|
|
402
|
|
|
403 close IN;
|
|
|
404
|
|
|
405 my $cluster_length_file="$clusterpath/cluster_length.txt";
|
|
|
406 open LEN,">$cluster_length_file";
|
|
|
407 print LEN "\#length\tcluster_number\n";
|
|
|
408 foreach my $key (sort keys %cluster_length) {
|
|
|
409 print LEN "$key\t$cluster_length{$key}\n";
|
|
|
410 }
|
|
|
411 close LEN;
|
|
|
412 print OUT "<h2>4. cluster result</h2>
|
|
|
413 <h3>4.1 Cluster count</h3>
|
|
|
414 <table border=\"1\">
|
|
|
415 <tr align=\"center\">
|
|
|
416 <th align=\"left\"> </th>
|
|
|
417 <td>Merged samples</td></tr>
|
|
|
418 <tr align=\"center\">
|
|
|
419 <th align=\"left\">Tags number</th>
|
|
|
420 <td>$tags_map_number</td></tr>
|
|
|
421 <tr align=\"center\">
|
|
|
422 <th align=\"left\">Cluster number</th>
|
|
|
423 <td>$cluster_number</td></tr>\n</table>
|
|
|
424 ";
|
|
|
425
|
|
|
426 print OUT "<h3>4.2 Cluster length</h3>
|
|
|
427 <p> Note:<br />The clusters length data: <a href=\"./$clusterdir/cluster_length.txt\"> length file</a>
|
|
|
428 </p>
|
|
|
429 ";
|
|
|
430 print OUT "<h3>4.3 Quantify</h3>
|
|
|
431 <table border=\"1\">
|
|
|
432 <tr align=\"center\">
|
|
|
433 <th align=\"left\">Reads Range</th>\n
|
|
|
434 ";
|
|
|
435 foreach (@marks) {
|
|
|
436 print OUT "<th> $_ </th>\n";
|
|
|
437 }
|
|
|
438 for (my $i=0;$i<@exp_range;$i++) {
|
|
|
439 print OUT "</tr>
|
|
|
440 <tr align=\"center\">
|
|
|
441 <th align=\"left\">$exp_range[$i]</th>
|
|
|
442 ";
|
|
|
443 for (my $j=0;$j<@marks ;$j++) {
|
|
|
444 if (!(defined($exp[$i][$j]))) {
|
|
|
445 print OUT "<td> 0</td>\n";
|
|
|
446 }
|
|
|
447 else{print OUT "<td> $exp[$i][$j]</td>\n";}
|
|
|
448 }
|
|
|
449 }
|
|
|
450 print OUT "</tr>\n</table>";
|
|
|
451
|
|
|
452 print OUT "\n<table border=\"1\">
|
|
|
453 <tr align=\"center\">
|
|
|
454 <th align=\"left\">RPKM Range</th>\n
|
|
|
455 ";
|
|
|
456 foreach (@marks) {
|
|
|
457 print OUT "<th> $_ </th>\n";
|
|
|
458 }
|
|
|
459 for (my $i=0;$i<@rpkm_range;$i++) {
|
|
|
460 print OUT "</tr>
|
|
|
461 <tr align=\"center\">
|
|
|
462 <th align=\"left\">$rpkm_range[$i]</th>
|
|
|
463 ";
|
|
|
464 for (my $j=0;$j<@marks ;$j++) {
|
|
|
465 if (!(defined($rpkm[$i][$j]))) {
|
|
|
466 print OUT "<td> 0</td>\n";
|
|
|
467 }
|
|
|
468 else{print OUT "<td> $rpkm[$i][$j]</td>\n";}
|
|
|
469 }
|
|
|
470 }
|
|
|
471 print OUT "</tr>\n</table>";
|
|
|
472
|
|
|
473 my $annotate="$annotatepath/sample_c_p.anno";
|
|
|
474 my (%posit,%repeat,%nat1,%nat2);
|
|
|
475 my (@phase,@long,@repeat,@nat);
|
|
|
476 for (my $j=0;$j<@marks ;$j++) {
|
|
|
477 $phase[$j]=0;
|
|
|
478 $long[$j]=0;
|
|
|
479 $repeat[$j]=0;
|
|
|
480 $nat[$j]=0;
|
|
|
481 }
|
|
|
482 open ANNO,"<$annotate";
|
|
|
483 while (my $aline=<ANNO>) {
|
|
|
484 next if($aline=~/^\#/);
|
|
|
485 chomp $aline;
|
|
|
486 my @temp=split/\t/,$aline;
|
|
|
487 for (my $i=3+@marks+6;$i<@temp;$i++) {
|
|
|
488 my @posit=split/\;/,$temp[$i];
|
|
|
489 for (my $j=0;$j<@marks ;$j++) {
|
|
|
490 if ($temp[3+$j]>0) {
|
|
|
491 $posit{$posit[0]}[$j]++;
|
|
|
492 }
|
|
|
493 else{
|
|
|
494 if (!(defined($posit{$posit[0]}[$j]))) {
|
|
|
495 $posit{$posit[0]}[$j]=0;
|
|
|
496 }
|
|
|
497 }
|
|
|
498 }
|
|
|
499 }
|
|
|
500 for (my $j=0;$j<@marks ;$j++) {
|
|
|
501 if ($temp[3+$j]>0) {
|
|
|
502 if ($temp[6] eq "phase") {
|
|
|
503 $phase[$j]++;
|
|
|
504 }
|
|
|
505 if ($temp[7] eq "long") {
|
|
|
506 $long[$j]++;
|
|
|
507 }
|
|
|
508 if ($temp[8] ne "\/") {
|
|
|
509 $repeat[$j]++;
|
|
|
510 my @rr=split/\;/,$temp[8];
|
|
|
511 foreach (@rr) {
|
|
|
512 $repeat{$_}[$j]++;
|
|
|
513 }
|
|
|
514 }
|
|
|
515 if ($temp[9] ne "\/") {
|
|
|
516 $nat[$j]++;
|
|
|
517 my @nn1=split/\;/,$temp[9];
|
|
|
518 my @nn2=split/\;/,$temp[10];
|
|
|
519 for (my $k=0;$k<@nn1 ;$k++) {
|
|
|
520 $nat1{$nn1[$k]}[$j]++;
|
|
|
521 $nat2{$nn2[$k]}[$j]++;
|
|
|
522 }
|
|
|
523 }
|
|
|
524 }
|
|
|
525 }
|
|
|
526 }
|
|
|
527 close ANNO;
|
|
|
528
|
|
|
529 print OUT "<h2>5. Cluster Annotate</h2>
|
|
|
530 <h3>5.1 Cluster genome position annotate</h3>
|
|
|
531 <table border=\"1\">
|
|
|
532 <tr align=\"center\">
|
|
|
533 <th align=\"left\">clusters number</th>\n
|
|
|
534 ";
|
|
|
535
|
|
|
536 foreach (@marks) {
|
|
|
537 print OUT "<th> $_ </th>\n";
|
|
|
538 }
|
|
|
539 foreach my $key (sort keys %posit) {
|
|
|
540 print OUT "</tr>
|
|
|
541 <tr align=\"center\">
|
|
|
542 <th align=\"left\">$key</th>
|
|
|
543 ";
|
|
|
544 foreach (@{$posit{$key}}) {
|
|
|
545 print OUT "<td> $_</td>\n";
|
|
|
546 }
|
|
|
547 }
|
|
|
548 print OUT "</tr>\n</table>";
|
|
|
549 print OUT "<p>
|
|
|
550 Note:<br />
|
|
|
551 One cluster mybe annotate to multiple genes<br />
|
|
|
552 ";
|
|
|
553
|
|
|
554 print OUT "<h3>5.2 Cluster source mechanism annotate</h3>
|
|
|
555 <table border=\"1\">
|
|
|
556 <tr align=\"center\">
|
|
|
557 <th align=\"left\">clusters number</th>\n
|
|
|
558 ";
|
|
|
559
|
|
|
560 foreach (@marks) {
|
|
|
561 print OUT "<th> $_ </th>\n";
|
|
|
562 }
|
|
|
563 print OUT "</tr>
|
|
|
564 <tr align=\"center\">
|
|
|
565 <th align=\"left\">Phase</th>\n
|
|
|
566 ";
|
|
|
567 foreach (@phase) {
|
|
|
568 print OUT "<td> $_ </td>\n";
|
|
|
569 }
|
|
|
570
|
|
|
571 print OUT "</tr>
|
|
|
572 <tr align=\"center\">
|
|
|
573 <th align=\"left\">Long</th>\n
|
|
|
574 ";
|
|
|
575 foreach (@long) {
|
|
|
576 print OUT "<td> $_ </td>\n";
|
|
|
577 }
|
|
|
578
|
|
|
579 print OUT "</tr>
|
|
|
580 <tr align=\"center\">
|
|
|
581 <th align=\"left\">Repeat</th>\n
|
|
|
582 ";
|
|
|
583 foreach (@repeat) {
|
|
|
584 print OUT "<td> $_ </td>\n";
|
|
|
585 }
|
|
|
586
|
|
|
587 print OUT "</tr>
|
|
|
588 <tr align=\"center\">
|
|
|
589 <th align=\"left\">Nat</th>\n
|
|
|
590 ";
|
|
|
591 foreach (@nat) {
|
|
|
592 print OUT "<td> $_ </td>\n";
|
|
|
593 }
|
|
|
594 print OUT "</tr>\n</table>";
|
|
|
595
|
|
|
596 print OUT "<p>
|
|
|
597 Repeat subclass annotate:
|
|
|
598 ";
|
|
|
599
|
|
|
600 print OUT "<table border=\"1\">
|
|
|
601 <tr align=\"center\">
|
|
|
602 <th align=\"left\">Repeat subclass</th>\n
|
|
|
603 ";
|
|
|
604 foreach (@marks) {
|
|
|
605 print OUT "<th> $_ </th>\n";
|
|
|
606 }
|
|
|
607
|
|
|
608 foreach my $key (sort keys %repeat) {
|
|
|
609 print OUT "</tr>
|
|
|
610 <tr align=\"center\">
|
|
|
611 <th align=\"left\">$key</th>
|
|
|
612 ";
|
|
|
613 for (my $i=0;$i<@marks ;$i++) {
|
|
|
614 if (defined($repeat{$key}[$i])) {
|
|
|
615 print OUT "<td> $repeat{$key}[$i] </td>\n";
|
|
|
616 }
|
|
|
617 else{print OUT "<td> 0 </td>\n";}
|
|
|
618 }
|
|
|
619 }
|
|
|
620 print OUT "</tr>\n</table>";
|
|
|
621
|
|
|
622
|
|
|
623 print OUT "<p>
|
|
|
624 Nat subclass1 annotate:
|
|
|
625 ";
|
|
|
626
|
|
|
627 print OUT "<table border=\"1\">
|
|
|
628 <tr align=\"center\">
|
|
|
629 <th align=\"left\">Nat subclass1</th>\n
|
|
|
630 ";
|
|
|
631 foreach (@marks) {
|
|
|
632 print OUT "<th> $_ </th>\n";
|
|
|
633 }
|
|
|
634 foreach my $key (sort keys %nat1) {
|
|
|
635 print OUT "</tr>
|
|
|
636 <tr align=\"center\">
|
|
|
637 <th align=\"left\">$key</th>
|
|
|
638 ";
|
|
|
639 for (my $i=0;$i<@marks ;$i++) {
|
|
|
640 if (defined($nat1{$key}[$i])) {
|
|
|
641 print OUT "<td> $nat1{$key}[$i] </td>\n";
|
|
|
642 }
|
|
|
643 else{print OUT "<td> 0 </td>\n";}
|
|
|
644 }
|
|
|
645 }
|
|
|
646 print OUT "</tr>\n</table>";
|
|
|
647
|
|
|
648 print OUT "<p>
|
|
|
649 Nat subclass2 annotate:
|
|
|
650 ";
|
|
|
651
|
|
|
652 print OUT "<table border=\"1\">
|
|
|
653 <tr align=\"center\">
|
|
|
654 <th align=\"left\">Nat subclass2</th>\n
|
|
|
655 ";
|
|
|
656 foreach (@marks) {
|
|
|
657 print OUT "<th> $_ </th>\n";
|
|
|
658 }
|
|
|
659 foreach my $key (sort keys %nat2) {
|
|
|
660 print OUT "</tr>
|
|
|
661 <tr align=\"center\">
|
|
|
662 <th align=\"left\">$key</th>
|
|
|
663 ";
|
|
|
664 for (my $i=0;$i<@marks ;$i++) {
|
|
|
665 if (defined($nat2{$key}[$i])) {
|
|
|
666 print OUT "<td> $nat2{$key}[$i] </td>\n";
|
|
|
667 }
|
|
|
668 else{print OUT "<td> 0 </td>\n";}
|
|
|
669 }
|
|
|
670 }
|
|
|
671 print OUT "</tr>\n</table>";
|
|
|
672 print OUT "<p>
|
|
|
673 Note:<br />
|
|
|
674 One cluster mybe annotate to multiple repeats or nats<br />
|
|
|
675 ";
|
|
|
676
|
|
|
677 my $deg_file=`ls $degpath`;
|
|
|
678 chomp $deg_file;
|
|
|
679 my @deg_file=split/\n/,$deg_file;
|
|
|
680 my %deg;
|
|
|
681 foreach (@deg_file) {
|
|
|
682 my $output="$degpath/$_/output_score.txt";
|
|
|
683 open IN,"<$output";
|
|
|
684 $deg{$_}[0]=0;
|
|
|
685 $deg{$_}[1]=0;
|
|
|
686 $deg{$_}[2]=0;
|
|
|
687 while (my $aline=<IN>) {
|
|
|
688 next if ($aline=~/^\"/);
|
|
|
689 chomp $aline;
|
|
|
690 my @temp=split/\t/,$aline;
|
|
|
691 if ($temp[9] eq "TRUE") {
|
|
|
692 $deg{$_}[0]++;
|
|
|
693 if ($temp[4] >0) {
|
|
|
694 $deg{$_}[1]++;
|
|
|
695 }
|
|
|
696 if ($temp[4] <0) {
|
|
|
697 $deg{$_}[2]++;
|
|
|
698 }
|
|
|
699 }
|
|
|
700 }
|
|
|
701 close IN;
|
|
|
702 }
|
|
|
703
|
|
|
704
|
|
|
705 print OUT "<h2>6. DEG</h2>
|
|
|
706 <table border=\"1\">
|
|
|
707 <tr align=\"center\">
|
|
|
708 <th align=\"left\">Genes number</th>\n
|
|
|
709 <th> DEG </th>\n
|
|
|
710 <th> UP </th>\n
|
|
|
711 <th> DOWN </th>\n
|
|
|
712 ";
|
|
|
713
|
|
|
714 foreach my $key (sort keys %deg) {
|
|
|
715 print OUT "</tr>
|
|
|
716 <tr align=\"center\">
|
|
|
717 <th align=\"left\">$key</th>
|
|
|
718 ";
|
|
|
719 for (my $i=0;$i<@{$deg{$key}} ;$i++) {
|
|
|
720 print OUT "<td> $deg{$key}[$i] </td>\n";
|
|
|
721 }
|
|
|
722 }
|
|
|
723 print OUT "</tr>\n</table>";
|
|
|
724
|
|
|
725 print OUT "
|
|
|
726 </BODY>
|
|
|
727 </HTML>
|
|
|
728 ";
|
|
|
729 close OUT;
|
|
|
730
|
|
|
731
|
|
|
732
|
|
|
733
|
|
|
734 sub usage{
|
|
|
735 print <<"USAGE";
|
|
|
736 Version $version
|
|
|
737 Usage:
|
|
|
738 $0 -o
|
|
|
739 options:
|
|
|
740 -i
|
|
|
741 -format
|
|
|
742 -o output file
|
|
|
743 -h help
|
|
|
744 USAGE
|
|
|
745 exit(1);
|
|
|
746 }
|
