count matrix for edger tool

tools/countmatrixforedger/.shed.yml

@@ -0,0 +1,4 @@
+categories: [Computational chemistry]
+description: This tool generates table which can be used in edgeR.
+name: countmatrixforedger
+owner: earlhaminst

tools/countmatrixforedger/countmatrixforedger.xml

@@ -0,0 +1,166 @@
+<tool id="countmatrixforedger" name="countMatrixForEdger" version="1.0">
+    <description>Make a count matrix for edgeR</description>
+    <requirements>
+        <requirement type="package" version="4.1.3">gawk</requirement>
+    </requirements>
+    <command detect_errors="aggressive">
+        <![CDATA[ 
+            #for $i, $s in enumerate( $sample )#
+                echo -e ${s.sample_data}"\t"${s.sample_name}"\t"${s.sample_group} >> script.data;
+            #end for#
+
+            '$__tool_directory__/scrsh.sh' script.data;
+
+        ]]>
+    </command>
+    <inputs>
+        <repeat name="sample" title="">
+            <param name="sample_data" type="data" format="data" label="Output matrix from EDGE-pro (out_rpkm)"/>
+            <param name="sample_name" type="text" label="" help="Sample name"/>
+            <param name="sample_group" type="text" label="" help="Sample group name - it has to be the same string for each sample of this group"/>
+        </repeat>
+    </inputs>
+    <outputs>
+        <data name="count_matrix" format="tabular" from_work_dir="count.matrix" label="countMatrixForEdger: count matrix"/>
+        <data name="annotation" format="tabular" from_work_dir="annotation" label="countMatrixForEdger: annotation"/>
+    </outputs>
+    <tests>
+        <test>
+            <param name="sample_0|sample_data" value="data1"/>
+            <param name="sample_1|sample_data" value="data2"/>
+            <param name="sample_2|sample_data" value="data3"/>
+            <param name="sample_3|sample_data" value="data4"/>
+            <param name="sample_0|sample_name" value="sample1"/>
+            <param name="sample_1|sample_name" value="sample2"/>
+            <param name="sample_2|sample_name" value="sample3"/>
+            <param name="sample_3|sample_name" value="sample4"/>            
+            <param name="sample_0|sample_group" value="gr1"/>
+            <param name="sample_1|sample_group" value="gr1"/>
+            <param name="sample_2|sample_group" value="gr2"/>
+            <param name="sample_3|sample_group" value="gr2"/>
+            <output name="count_matrix" file="count.matrix"/>
+            <output name="annotation" file="annotation"/>
+        </test>
+    </tests>
+    <help>
+        <![CDATA[ 
+
+            **What it does**
+
+            It takes output tables from edge-PRO, samples names, groups names and creates a data 
+            containg numer of reads per each gene for each sample. It also returns table with gene's coordination.
+            The table with number of reads can be used in edgeR tool.
+
+            **Example**
+
+            Input data:
+
+            1.
+
+            * sample_data:
+
+            +---------+-------------+-----------+-------------+--------+------+
+            | gene_ID | start_coord | end_coord | average_cov | #reads | RPKM |
+            +---------+-------------+-----------+-------------+--------+------+
+            | Cj0001  | 1           | 1323      | 11.6        | 416    | 157  |
+            +---------+-------------+-----------+-------------+--------+------+
+            | Cj0003  | 1483        | 2550      | 63.0        | 1818   | 851  |
+            +---------+-------------+-----------+-------------+--------+------+
+            | Cj0001  | 2579        | 4888      | 49.1        | 3067   | 663  |
+            +---------+-------------+-----------+-------------+--------+------+
+            | Cj0004c | 4916        | 5257      | 4.5         | 42     | 61   |
+            +---------+-------------+-----------+-------------+--------+------+
+            | Cj0005c | 5260        | 6498      | 6.4         | 215    | 87   |
+            +---------+-------------+-----------+-------------+--------+------+
+            | Cj0006  | 6703        | 8010      | 5.9         | 208    | 79   |
+            +---------+-------------+-----------+-------------+--------+------+
+            | Cj0007  | 8144        | 12634     | 26.3        | 3190   | 355  |
+            +---------+-------------+-----------+-------------+--------+------+
+            | Cj0008  | 12644       | 14395     | 43.5        | 2059   | 587  |
+            +---------+-------------+-----------+-------------+--------+------+
+
+            * sample_name: **sample1**
+
+            * sample_group: **gr1**
+
+            2. 
+
+            * sample_data:
+
+            +---------+-------------+-----------+-------------+--------+------+
+            | gene_ID | start_coord | end_coord | average_cov | #reads | RPKM |
+            +---------+-------------+-----------+-------------+--------+------+
+            | Cj0001  | 1           | 1323      | 11.4        | 407    | 154  |
+            +---------+-------------+-----------+-------------+--------+------+
+            | Cj0002  | 1483        | 2550      | 61.6        | 1778   | 835  |
+            +---------+-------------+-----------+-------------+--------+------+
+            | Cj0003  | 2579        | 4888      | 48.7        | 3039   | 660  |
+            +---------+-------------+-----------+-------------+--------+------+
+            | Cj0004c | 4916        | 5257      | 3.9         | 36     | 53   |
+            +---------+-------------+-----------+-------------+--------+------+
+            | Cj0005c | 5260        | 6498      | 6.8         | 229    | 93   |
+            +---------+-------------+-----------+-------------+--------+------+
+            | Cj0006  | 6703        | 8010      | 5.7         | 201    | 77   |
+            +---------+-------------+-----------+-------------+--------+------+
+            | Cj0007  | 8144        | 12634     | 24.8        | 3015   | 337  |
+            +---------+-------------+-----------+-------------+--------+------+
+            | Cj0008  | 12644       | 14395     | 43.5        | 2058   | 589  |
+            +---------+-------------+-----------+-------------+--------+------+
+
+            * sample_name: **sample2**
+
+            * sample_group: **gr2**
+
+            Output data:
+
+            * count_matrix:
+
+            +----------+---------+---------+
+            | #        | gr1:gr1 | gr2:gr2 |
+            +----------+---------+---------+
+            | #Feature | sample1 | sample2 |
+            +----------+---------+---------+
+            | Cj0001   | 416     | 407     |
+            +----------+---------+---------+
+            | Cj0002   | 1818    | 1778    |
+            +----------+---------+---------+
+            | Cj0003   | 3067    | 3039    |
+            +----------+---------+---------+
+            | Cj0004c  | 42      | 36      |
+            +----------+---------+---------+
+            | Cj0005c  | 215     | 229     |
+            +----------+---------+---------+
+            | Cj0006   | 208     | 201     |
+            +----------+---------+---------+
+            | Cj0007   | 3190    | 3015    |
+            +----------+---------+---------+
+            | Cj0008   | 2059    | 2058    |
+            +----------+---------+---------+
+
+            * annotation:
+
+            +---------+--------------+-----------+
+            | gene_ID | start_coord  | end_coord |
+            +---------+--------------+-----------+
+            | Cj0001  | 1            | 1323      |
+            +---------+--------------+-----------+
+            | Cj0002  | 1483         | 2550      |
+            +---------+--------------+-----------+
+            | Cj0003  | 2579         | 4888      |
+            +---------+--------------+-----------+
+            | Cj0004c | 4916         | 5257      |
+            +---------+--------------+-----------+
+            | Cj0005c | 5260         | 6498      |
+            +---------+--------------+-----------+
+            | Cj0006  | 6703         | 8010      |
+            +---------+--------------+-----------+
+            | Cj0007  | 8144         | 12634     |
+            +---------+--------------+-----------+
+            | Cj0008  | 12644        | 14395     |
+            +---------+--------------+-----------+
+            | Cj0009  | 14398        | 15843     |
+            +---------+--------------+-----------+
+
+	]]>
+    </help>
+</tool>

tools/countmatrixforedger/scrsh.sh

@@ -0,0 +1,54 @@
+#!/bin/bash
+
+sample_data=(`cat $1 | cut -f1 | sed ':a;N;$!ba;s/\n/ /g'`)
+sample_name=(`cat $1 | cut -f2 | sed ':a;N;$!ba;s/\n/ /g'`)
+sample_group=(`cat $1 | cut -f3 | sed ':a;N;$!ba;s/\n/ /g'`)
+
+
+group=('#')
+sample=('#Feature')
+
+touch anno.tmp
+touch count.tmp
+
+nsamples=`expr ${#sample_data[@]} - 1`
+
+for i in `seq 0 1 $nsamples`; do
+	group+=(${sample_group[i]}:${sample_group[i]})
+	sample+=(${sample_name[i]})
+
+	cat ${sample_data[i]} | tail -n+3 > dataWithoutHeader
+
+	cat dataWithoutHeader | sort -k1 > dataWithoutHeader.sorted 
+
+	cat dataWithoutHeader.sorted | awk '{print $1}' > anno.sample 
+	cat dataWithoutHeader.sorted | awk '{print $5}' > count.sample 
+
+	paste -d"\t" count.tmp count.sample > count 
+	paste -d"\t" anno.tmp anno.sample > anno 
+
+	cat count > count.tmp
+	cat anno > anno.tmp
+
+done
+
+echo ${group[*]} | sed -e 's/ /\t/g' > count.matrix
+echo ${sample[*]} | sed -e 's/ /\t/g' >> count.matrix
+
+cat count | cut -f 2- > count.tmp
+
+paste -d"\t" anno.sample count.tmp >> count.matrix
+
+cat anno.tmp | cut -f 2- | awk '{for (i=2; i<=NF; i++){if ($1!=$i){print "error"; break}}}' > control.data
+
+echo -e "gene_ID\tstart_coord\tend_coord" > annotation
+cat dataWithoutHeader.sorted | awk '{print $1"\t"$2"\t"$3}' >> annotation
+
+if [[ -s control.data ]]; then
+	echo "" > count.matrix
+	echo "" > annotation
+	echo ERROR: gene_ID\'s have to be in the same order in each sample_data file.
+	exit 1
+else
+	echo "Done."
+fi