changeset 7:07ad2d77f28a draft

planemo upload for repository https://github.com/eteriSokhoyan/galaxytools/tree/branchForIterations/tools/GraphClust commit 4379e712f76f2bb12ee2cc270dd8a0e806df2cd6

--- a/preprocessing.xml	Sat Mar 25 16:53:38 2017 -0400
+++ b/preprocessing.xml	Mon May 22 12:45:22 2017 -0400
@@ -1,4 +1,4 @@
-<tool id="preproc" name="Preprocessing" version="0.1">
+<tool id="preproc" name="Preprocessing" version="0.2">
   <requirements>
     <requirement type="package" version="0.1.12">graphclust-wrappers</requirement>
   </requirements>
@@ -7,41 +7,47 @@
     </stdio>
     <command>
 		<![CDATA[
+        preprocessing.pl
+            '$fastaFile'
+            $max_length
+            $in_winShift
+            $min_seq_length
 
-    'preprocessing.pl'
-    '$fastaFile'  $max_length $in_winShift $min_seq_length
-
+        #if $SHAPEdata:
+            &&
+            python '$__tool_directory__/splitSHAPE.py' 
+                '$SHAPEdata'
+                $max_length
+        #end if
 ]]>
 	</command>
     <inputs>
         <param type="data" name="fastaFile" format="fasta" />
+        <param type="data" name="SHAPEdata" format="txt" optional="true" label="SHAPE data"/>
         <param name="max_length" type="integer" value="10000" size="5" label="window size"/>
         <param name="in_winShift" type="integer" value="100" size="5" label="window shift in percent"/>
         <param name="min_seq_length" type="integer" value="5" size="5" label="minimum sequence length"/>
     </inputs>
-
     <outputs>
         <data name="data.fasta" format="fasta" from_work_dir="FASTA/data.fasta" label="data.fasta"/>
         <data name="data.map" format="txt" from_work_dir="FASTA/data.map" label="data.map"/>
         <data name="data.names" format="txt" from_work_dir="FASTA/data.names" label="data.names"/>
         <data name="data.fasta.scan" format="fasta" from_work_dir="FASTA/data.fasta.scan" label="data.fasta.scan"/>
         <data name="FASTA" format="zip" from_work_dir="FASTA.zip" label="FASTA.ZIP"/>
+        <data name="shape_data_split" format="txt" from_work_dir="shape_data_split.react" label="SHAPE data splited"/>
     </outputs>
-
-
     <tests>
-    <test>
-        <param name="fastaFile" value="input.fa"/>
-        <param name="max_length" value="10000"/>
-        <param name="in_winShift" value="100"/>
-        <param name="min_seq_length" value="5"/>
-        <output name="data.fasta" file="FASTA/data.fasta"/>
-        <output name="data.map" file="FASTA/data.map" />
-        <output name="data.names" file="FASTA/data.names"/>
-        <output name="data.fasta.scan" file="FASTA/data.fasta.scan" />
-    </test>
-</tests>
-
+        <test>
+            <param name="fastaFile" value="input.fa"/>
+            <param name="max_length" value="10000"/>
+            <param name="in_winShift" value="100"/>
+            <param name="min_seq_length" value="5"/>
+            <output name="data.fasta" file="FASTA/data.fasta"/>
+            <output name="data.map" file="FASTA/data.map" />
+            <output name="data.names" file="FASTA/data.names"/>
+            <output name="data.fasta.scan" file="FASTA/data.fasta.scan" />
+        </test>
+    </tests>
     <help>
 <![CDATA[
 
@@ -57,8 +63,6 @@
   Slightly larger windows are usually ok. Too small windows can disturb existing signals.
 
 
-
-
 + **window shift in percent** : Relative window size in % for window shift during input preprocessing.
   Please note that a small shift results in much more fragments for clustering. The benefit is that RNA
   motifs/structures are not destroyed by arbitrary split points. Smaller
@@ -67,19 +71,11 @@
   no other occurences in the dataset can be found.
 
 
-
-
-
 + **minimum sequence length** : Minimal length of input sequences.
   Every input sequence below that length is ignored completely during clustering.
 
-
     ]]></help>
-
-
     <citations>
         <citation type="doi">10.1093/bioinformatics/bts224</citation>
     </citations>
-
-
 </tool>

--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/splitSHAPE.py	Mon May 22 12:45:22 2017 -0400
@@ -0,0 +1,64 @@
+import os
+import re
+import sys
+
+shape_file = sys.argv[1]
+win_size = int(sys.argv[2])
+
+pattern = re.compile("^>.*$")
+toWrite = ""
+
+count_for_id = 1
+seq_counter = 0
+new_id = ""
+
+seq_id = []
+seq_string = []
+orig_id = []
+name_file = "FASTA/data.names"
+array_all_chunks = []
+with open(name_file, 'r') as f:
+    content = f.read()
+    lines = content.split('\n')[:-1]
+    for line in lines:
+        seq_id.append(int(line.split()[0]))
+        seq_string.append(line.split()[1])
+        orig_id_srt = line.split()[3]
+        orig_id_srt = orig_id_srt.rsplit('_',1)[0]
+        orig_id.append(orig_id_srt)
+
+
+react_dict = {}
+react_arr = []
+
+with open(shape_file, 'r') as shape:
+    content = shape.read()
+    lines = content.split('\n')
+    for line in lines:
+        if pattern.match(line):
+            line = line.replace('>','').strip()
+            react_arr=[]
+            react_dict[line] = react_arr
+            continue
+        else:
+            react_arr.append(line)
+
+toWrite = ""
+chunks = []
+for i in range(len(orig_id)):
+    if not orig_id[i] in react_dict:
+        raise RuntimeError('Error key {} not found'.format(orig_id))
+
+    react_val = react_dict[orig_id[i]]
+    toWrite += '>' + str(seq_id[i]) + " " + seq_string[i] + "\n"
+    chunks = re.findall(r'\d+', seq_string[i])
+
+    for j in react_val[int(chunks[1])-1:int(chunks[2])]:
+        id_s = int(j.split()[0])
+
+        if id_s > win_size:
+            id_s = id_s - int(chunks[1])
+        toWrite += str(id_s) + '\t' + j.split()[1] + "\n"
+
+with open("shape_data_split.react", 'w') as out:
+    out.write(toWrite)