|
10
|
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,$knownpath,$genomepath,$novelpath);
|
|
|
20 my ($predir,$rfamdir,$knowndir,$genomedir,$noveldir);
|
|
|
21 open IN,"<$opts{i}";
|
|
|
22 $config=<IN>; chomp $config;
|
|
|
23 $prepath=<IN>; chomp $prepath;
|
|
|
24 $rfampath=<IN>;chomp $rfampath;
|
|
|
25 $knownpath=<IN>; chomp $knownpath;
|
|
|
26 $genomepath=<IN>; chomp $genomepath;
|
|
|
27 $novelpath=<IN>; chomp $novelpath;
|
|
|
28 close IN;
|
|
|
29 my @tmp=split/\//,$prepath;
|
|
|
30 $predir=$tmp[-1];
|
|
|
31 @tmp=split/\//,$rfampath;
|
|
|
32 $rfamdir=$tmp[-1];
|
|
|
33 @tmp=split/\//,$knownpath;
|
|
|
34 $knowndir=$tmp[-1];
|
|
|
35 @tmp=split/\//,$genomepath;
|
|
|
36 $genomedir=$tmp[-1];
|
|
|
37 @tmp=split/\//,$novelpath;
|
|
|
38 $noveldir=$tmp[-1];
|
|
|
39
|
|
|
40 my $dir=dirname($opts{'o'});
|
|
|
41
|
|
|
42 open OUT ,">$opts{'o'}";
|
|
|
43 print OUT "<HTML>\n <HEAD>\n <TITLE> Analysis Report </TITLE>\n </HEAD>
|
|
|
44 <BODY bgcolor=\"lightgray\">\n <h1 align=\"center\">\n <font face=\"ºÚÌå\">\n <b>Small RNA Analysis Report</b>\n </font>\n </h1>
|
|
|
45 <h2>1. Sequence No. and quality</h2>
|
|
|
46 <h3>1.1 Sequece No.</h3>
|
|
|
47 ";
|
|
|
48
|
|
|
49 ### raw data no
|
|
|
50 open IN,"<$config";
|
|
|
51 my @files;my @marks; my @rawNo;
|
|
|
52 while (my $aline=<IN>) {
|
|
|
53 chomp $aline;
|
|
|
54 my @tmp=split/\t/,$aline;
|
|
|
55 push @files,$tmp[0];
|
|
|
56
|
|
|
57 my $no=`less $tmp[0] |wc -l `;
|
|
|
58 chomp $no;
|
|
|
59 if ($opts{'format'} eq "fq" || $opts{'format'} eq "fastq") {
|
|
|
60 $no=$no/4;
|
|
|
61 }
|
|
|
62 else{
|
|
|
63 $no=$no/2;
|
|
|
64 }
|
|
|
65 push @rawNo,$no;
|
|
|
66
|
|
|
67 push @marks,$tmp[1];
|
|
|
68 }
|
|
|
69 close IN;
|
|
|
70
|
|
|
71 ### preprocess
|
|
|
72 unless ($prepath=~/\/$/) {
|
|
|
73 $prepath .="/";
|
|
|
74 }
|
|
|
75
|
|
|
76 my @trimNo;my @collapse;
|
|
|
77 my $collapsefile=$prepath."collapse_reads.fa";
|
|
|
78 open IN,"<$collapsefile";
|
|
|
79 while (my $aline=<IN>) {
|
|
|
80 chomp $aline;
|
|
|
81 <IN>;
|
|
|
82 $aline=~/:([\d|_]+)_x(\d+)$/;
|
|
|
83 my @lng=split/_/,$1;
|
|
|
84 for (my $i=0;$i<@lng;$i++) {
|
|
|
85 if ($lng[$i]>0) {
|
|
|
86 $trimNo[$i] +=$lng[$i];
|
|
|
87 $collapse[$i] ++;
|
|
|
88 }
|
|
|
89 }
|
|
|
90 }
|
|
|
91 close IN;
|
|
|
92
|
|
|
93 my @cleanR;my @cleanT;
|
|
|
94 my $clean=$prepath."collapse_reads_19_28.fa";
|
|
|
95 open IN,"<$clean";
|
|
|
96 while (my $aline=<IN>) {
|
|
|
97 chomp $aline;
|
|
|
98 <IN>;
|
|
|
99 $aline=~/:([\d|_]+)_x(\d+)$/;
|
|
|
100 my @lng=split/_/,$1;
|
|
|
101 for (my $i=0;$i<@lng;$i++) {
|
|
|
102 if ($lng[$i]>0) {
|
|
|
103 $cleanR[$i] +=$lng[$i];
|
|
|
104 $cleanT[$i] ++;
|
|
|
105 }
|
|
|
106 }
|
|
|
107 }
|
|
|
108 close IN;
|
|
|
109
|
|
|
110 print OUT "<table border=\"1\">
|
|
|
111 <tr align=\"center\">
|
|
|
112 <th> </th>
|
|
|
113 ";
|
|
|
114 foreach (@marks) {
|
|
|
115 print OUT "<th> $_ </th>\n";
|
|
|
116 }
|
|
|
117 print OUT "</tr>
|
|
|
118 <tr align=\"center\">
|
|
|
119 <th align=\"left\">Raw Reads No. </th>
|
|
|
120 ";
|
|
|
121 foreach (@rawNo) {
|
|
|
122 print OUT "<td> $_ </td>\n";
|
|
|
123 }
|
|
|
124 print OUT "</tr>
|
|
|
125 <tr align=\"center\">
|
|
|
126 <th align=\"left\">Reads No. After Trimed 3\' adapter </th>
|
|
|
127 ";
|
|
|
128 foreach (@trimNo) {
|
|
|
129 print OUT "<td> $_ </td>\n";
|
|
|
130 }
|
|
|
131 print OUT "</tr>
|
|
|
132 <tr align=\"center\">
|
|
|
133 <th align=\"left\">Unique Tags No. </th>
|
|
|
134 ";
|
|
|
135 foreach (@collapse) {
|
|
|
136 print OUT "<td> $_ </td>\n";
|
|
|
137 }
|
|
|
138 print OUT "</tr>
|
|
|
139 <tr align=\"center\">
|
|
|
140 <th align=\"left\">Clean Reads No. </th>
|
|
|
141 ";
|
|
|
142 foreach (@cleanR) {
|
|
|
143 print OUT "<td> $_ </td>\n";
|
|
|
144 }
|
|
|
145 print OUT "</tr>
|
|
|
146 <tr align=\"center\">
|
|
|
147 <th align=\"left\">Clean Tags No. </th>
|
|
|
148 ";
|
|
|
149 foreach (@cleanT) {
|
|
|
150 print OUT "<td> $_ </td>\n";
|
|
|
151 }
|
|
|
152 print OUT "</tr>\n</table>";
|
|
|
153 print OUT "<p>
|
|
|
154 Note:<br />
|
|
|
155 The raw data file path is: <b>$files[0]</b><br />
|
|
|
156 ";
|
|
|
157 for (my $i=1;$i<@files;$i++) {
|
|
|
158 print OUT "          <b>$files[$i]</b><br />";
|
|
|
159 }
|
|
|
160 print OUT "The collapsed file path is: <b>$collapsefile</b><br />
|
|
|
161 The clean data file path is: <b>$clean</b><br />
|
|
|
162 </p>
|
|
|
163 <h2> 1. Sequence length count</h2>
|
|
|
164 <h3> 1.1 Reads length</h3>
|
|
|
165 ";
|
|
|
166
|
|
|
167 print OUT "<img src=\"./$predir/Reads_length.png\" alt=\"Reads_length.png\" width=\"400\" height=\"300\"/>
|
|
|
168 <h3> 1.2 Tags length count</h3>
|
|
|
169 <img src=\"./$predir/Tags_length.png\" alt=\"Tags_length.png\" width=\"400\" height=\"300\"/>
|
|
|
170 <p> Note:<br />The sequence length data: <a href=\"./$predir/reads_length_distribution.txt\"> length file</a>
|
|
|
171 </p>
|
|
|
172 ";
|
|
|
173
|
|
|
174 #### rfam
|
|
|
175 unless ($rfampath=~/\/$/) {
|
|
|
176 $rfampath .="/";
|
|
|
177 }
|
|
|
178 print OUT "<h2>2. Rfam non-miRNA annotation</h2>
|
|
|
179 <h3>2.1 Reads count</h3>
|
|
|
180 <table border=\"1\">
|
|
|
181 <tr align=\"center\">
|
|
|
182 ";
|
|
|
183
|
|
|
184 my @rfamR; my @rfamT;
|
|
|
185 my $tag=1;
|
|
|
186 open IN,"<$dir/rfam_non-miRNA_annotation.txt";
|
|
|
187 while (my $aline=<IN>) {
|
|
|
188 chomp $aline;
|
|
|
189 $tag=0 if($aline=~/tags\s+number/);
|
|
|
190 next if($aline=~/^\#/);
|
|
|
191 next if($aline=~/^\s*$/);
|
|
|
192 my @tmp=split/\s+/,$aline;
|
|
|
193 if($tag == 1){push @rfamR,[@tmp];}
|
|
|
194 else{push @rfamT,[@tmp];}
|
|
|
195 }
|
|
|
196 close IN;
|
|
|
197
|
|
|
198
|
|
|
199 print OUT "<th>RNA Name</th>\n";
|
|
|
200 foreach (@marks) {
|
|
|
201 print OUT "<th> $_ </th>\n";
|
|
|
202 }
|
|
|
203 for (my $i=0;$i<@rfamR;$i++) {
|
|
|
204 print OUT "</tr>
|
|
|
205 <tr align=\"center\">
|
|
|
206 <th align=\"left\">$rfamR[$i][0]</th>
|
|
|
207 ";
|
|
|
208 for (my $j=1;$j<@{$rfamR[$i]} ;$j++) {
|
|
|
209 print OUT "<td> $rfamR[$i][$j]</td>\n";
|
|
|
210 }
|
|
|
211 }
|
|
|
212
|
|
|
213 print OUT "</tr>\n</table>
|
|
|
214 <h3>2.2 Tags count</h3>
|
|
|
215 <table border=\"1\">
|
|
|
216 <tr align=\"center\">
|
|
|
217 <th>RNA Name</th>\n";
|
|
|
218 foreach (@marks) {
|
|
|
219 print OUT "<th> $_ </th>\n";
|
|
|
220 }
|
|
|
221 for (my $i=0;$i<@rfamT;$i++) {
|
|
|
222 print OUT "</tr>
|
|
|
223 <tr align=\"center\">
|
|
|
224 <th align=\"left\">$rfamT[$i][0]</th>
|
|
|
225 ";
|
|
|
226 for (my $j=1;$j<@{$rfamT[$i]} ;$j++) {
|
|
|
227 print OUT "<td> $rfamT[$i][$j]</td>\n";
|
|
|
228 }
|
|
|
229 }
|
|
|
230 print OUT "</tr>\n</table>
|
|
|
231 <p>Note:<br />The rfam mapping results is: <b>$rfampath</b>";
|
|
|
232 print OUT "<b>rfam_mapped.bwt</b></p>
|
|
|
233 <h2>3. MicroRNA result</h2>
|
|
|
234 <h3>3.1 known microRNA</h3>
|
|
|
235 <p>The known microRNA express list: <a href=\"./known_microRNA_express.txt\"> known_microRNA_express.txt</a><br/>
|
|
|
236 The known microRNA alngment file: <a href=\"./known_microRNA_express.aln\"> known_microRNA_express.aln</a><br/>
|
|
|
237 The known moRs file: <a href=\"./known_microRNA_express.moRs\"> known_microRNA_express.moRs</a><br/>
|
|
|
238 The known microRNA mature sequence file: <a href=\"./known_microRNA_mature.fa\"> known_microRNA_mature.fa</a><br/>
|
|
|
239 The knowm microRNA precursor sequence file: <a href=\"./known_microRNA_precursor.fa\"> known_microRNA_precursor.fa</a>
|
|
|
240 </p>
|
|
|
241
|
|
|
242 <h3>3.2 novel microRNA</h3>
|
|
|
243 <p>The novel microRNA prediction file:<a href=\"./microRNA_prediction.mrd\"> microRNA_prediction.mrd</a><br/>
|
|
|
244 The novel microRNA express list: <a href=\"./novel_microRNA_express.txt\"> novel_microRNA_express.txt</a><br/>
|
|
|
245 The novel microRNA mature sequence file: <a href=\"./novel_microRNA_mature.fa\"> novel_microRNA_mature.fa</a><br/>
|
|
|
246 The novel microRNA precursor sequence file: <a href=\"./novel_microRNA_precursor.fa\"> novel_microRNA_precursor.fa</a>
|
|
|
247 </p>
|
|
|
248 ";
|
|
|
249
|
|
|
250
|
|
|
251
|
|
|
252 print OUT "
|
|
|
253 </BODY>
|
|
|
254 </HTML>
|
|
|
255 ";
|
|
|
256 close OUT;
|
|
|
257
|
|
|
258 sub usage{
|
|
|
259 print <<"USAGE";
|
|
|
260 Version $version
|
|
|
261 Usage:
|
|
|
262 $0 -o
|
|
|
263 options:
|
|
|
264 -o output file
|
|
|
265 -h help
|
|
|
266 USAGE
|
|
|
267 exit(1);
|
|
|
268 }
|
|
|
269
|
