Mercurial > repos > rnateam > graphclust_align_cluster

changeset 1:953353eacec2 draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
planemo upload for repository https://github.com/bgruening/galaxytools/tools/GraphClust/AlignCluster commit 5fe196bd60c65c884ae1685d4b7fb33119564fa7
author rnateam
date Sun, 28 Oct 2018 18:52:14 -0400
parents c05c83b3ef0f
children 40371e8b6ee2
files align_cluster.xml call_rscape.sh test-data/alignment1.cons.tsv test-data/alignment1.rnaz.out test-data/alignment1.sth test-data/alignment2.sth test-data/alignment3.cons.tsv test-data/alignment3.sth test-data/alignment3_R2R.sto.pdf test-data/cluster3.all test-data/cluster3.all.fa test-data/rscape1.out test-data/rscape3.out test-data/structure.png test-data/structure.ps test-data/structure1.ps test-data/structure3.png
diffstat 12 files changed, 81 insertions(+), 15 deletions(-) [+]
line wrap: on
line diff
--- a/align_cluster.xml	Sat Oct 27 13:21:39 2018 -0400
+++ b/align_cluster.xml	Sun Oct 28 18:52:14 2018 -0400
@@ -38,8 +38,8 @@
             #end if
         #end if
       "
-      && 
-      R-scape --outdir ./RESULTS/ result.aln.sth &&
+      &&
+      '$__tool_directory__/call_rscape.sh' ./RESULTS/ result.aln.sth &&
       RNAz --locarnate '$alignment_clustal' > alignment.rnaz.out &&
       #if  str($genomic_cons_opts.genomic_cons_opts_selector) != "no":
           clustal_to_alma.py '$alignment_clustal' $cluster_all &&
@@ -162,13 +162,29 @@
       <data name="evofold_out" format="txt" from_work_dir="alignment.evofold.out" label="evofold.out"  />
       <data name="cons_tsv" format="tabular" from_work_dir="conservation_metrics.tsv" label="conservation_metrics.tsv"  />    
   </outputs>
+ 
   <tests>
         <test>
+            <param name="cluster_all_fa" value="cluster3.all.fa"/>
+            <param name="cluster_all" value="cluster3.all"/>
+            <output name="cons_tsv" file="alignment3.cons.tsv"   compare="sim_size" delta="0"/>
+            <output name="rscape_out" file="rscape3.out" compare="sim_size"  delta="10"/>
+            <output name="structure_png" file="structure3.png" compare="sim_size" /> 
+            <output name="Rscape_R2R" file="alignment3_R2R.sto.pdf" compare="sim_size" />
+            <output name="alignment_sth" file="alignment3.sth"  compare="sim_size" delta="100" />
+            <conditional name="genomic_cons_opts">
+                <param name="genomic_cons_opts_selector" value="no"/>
+            </conditional>
+            <param name="results_top_num" value="5"/>
+        </test>
+  
+        <test>
             <param name="cluster_all_fa" value="cluster1.all.fa"/>
             <param name="cluster_all" value="cluster1.all"/>
             <output name="alignment_ps" file="alignment1.ps" compare="sim_size" />
             <output name="alignment_png" file="alignment1.png" compare="sim_size" />
             <output name="structure_ps" file="structure1.ps" compare="sim_size" />
+            <output name="rscape_out" file="rscape1.out" compare="sim_size"  delta="10"/>
             <output name="structure_png" file="structure1.png" compare="sim_size" /> 
             <output name="alignment_sth" file="alignment1.sth"  compare="sim_size" delta="100" />
             <output name="alignment_clustal_out" file="alignment1.clustal" />
@@ -210,7 +226,7 @@
                 <param name="transcript_loci_fasta" value="alignment2b-transcript.fa"/>
                 <param name="transcript_loci_bed" value="chr7 27162434 27166719 Hoxa9-Xtend5UTR 2 -"/>
             </conditional>
-        </test>
+        </test> 
     </tests>
     <help>
     <![CDATA[
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/call_rscape.sh	Sun Oct 28 18:52:14 2018 -0400
@@ -0,0 +1,8 @@
+#!/bin/bash
+
+num_bps=$(grep "SS_cons" $2  | awk '{print $3}' | tr -d '.' | tr -d '\n' | wc -c)
+if [ $num_bps -gt 2 ]; then
+    R-scape --outdir $1 $2
+else
+    echo "No consensus structure, R-scape skipped";
+fi
\ No newline at end of file
--- a/test-data/alignment1.cons.tsv	Sat Oct 27 13:21:39 2018 -0400
+++ b/test-data/alignment1.cons.tsv	Sun Oct 28 18:52:14 2018 -0400
@@ -1,2 +1,2 @@
 	Background model	Columns	Combinations/Pair	Consensus MFE	Covariance contribution	Decision model	Energy contribution	G+C content	Mean pairwise identity	Mean single sequence MFE	Mean z-score	Prediction	Reading direction	SVM RNA-class probability	SVM decision value	Sequences	Shannon entropy	Structure conservation index	alignment	multihit per_species	num_human_seqs_all	num_seqs	num_seqs_all	rscape_#target_E-val	rscape_Found	rscape_MSA	rscape_PPV	rscape_SEN	rscape_TP	rscape_True	rscape_alen	rscape_avgid	rscape_method	rscape_nseq	rscape_out	cluster_bed	cluster_human_ids	cluster_human_loc
-0	dinucleotide	51	2.890	-7.640	-4.520	structural RNA alignment quality	-3.120	0.320	44.050	-5.080	0.220	RNA	forward	1.000	3.530	5.000	1.035	1.500	cluster.aln	0	0	5	12	0.050	5	result.aln_1	100.000	55.560	5	9	50	44.730	GTp	5	RESULTS/result.aln.sum			
+0	dinucleotide	51	2.890	-7.640	-4.520	structural RNA alignment quality	-3.120	0.320	44.050	-5.080	0.210	RNA	forward	1.000	3.540	5.000	1.035	1.500	cluster.aln	0	0	5	12	0.050	5	result.aln_1	100.000	55.560	5	9	50	44.730	GTp	5	RESULTS/result.aln.sum			
--- a/test-data/alignment1.rnaz.out	Sat Oct 27 13:21:39 2018 -0400
+++ b/test-data/alignment1.rnaz.out	Sun Oct 28 18:52:14 2018 -0400
@@ -12,19 +12,19 @@
  Energy contribution:  -3.12
  Covariance contribution:  -4.52
  Combinations/Pair:   2.89
- Mean z-score:   0.22
+ Mean z-score:   0.21
  Structure conservation index:   1.50
  Background model: dinucleotide
  Decision model: structural RNA alignment quality
- SVM decision value:   3.53
- SVM RNA-class probability: 0.999916
+ SVM decision value:   3.54
+ SVM RNA-class probability: 0.999919
  Prediction: RNA
 
 ######################################################################
 
 >SEQ47_2_50_+
 AGGUAU-UAGAAAAAC-CAUUUCAUAACUUUGUCAAAGUUAAAUUAUAGGC
-.(((..-.......))-)......((((((.....)))))).......... (  -4.20, z-score =   0.02, S)
+.(((..-.......))-)......((((((.....)))))).......... (  -4.20, z-score =  -0.01, S)
 >SEQ42_1_50_+
 GUAAAUAUAGUUUAAC-CAAAACAUCAGAUUGUGAAUCUGACAACAGAGGC
 .........((((...-..)))).((((((.....)))))).......... (  -5.90, z-score =  -0.43, R)
--- a/test-data/alignment1.sth	Sat Oct 27 13:21:39 2018 -0400
+++ b/test-data/alignment1.sth	Sun Oct 28 18:52:14 2018 -0400
@@ -1,9 +1,9 @@
 # STOCKHOLM 1.0
 
-SEQ39_1_50_+          GUUCUUGUAGUUGAAA-UACAACGAUGGUUUUUCAUAUCAUUGGUCGUGGU
+SEQ41_1_50_+          ACUCUUUUAGUAUAAA-UAGUACCGUUAACUUCCAAUUAACUAGUUUUGAC
+SEQ34_1_51_+          CAGAGAAUAGUUUAAAUUAGAAUCUUAGCUUUGGGUGCUAAUGGUGGAGUU
 SEQ42_1_50_+          GUAAAUAUAGUUUAAC-CAAAACAUCAGAUUGUGAAUCUGACAACAGAGGC
 SEQ47_2_50_+          AGGUAU-UAGAAAAAC-CAUUUCAUAACUUUGUCAAAGUUAAAUUAUAGGC
-SEQ41_1_50_+          ACUCUUUUAGUAUAAA-UAGUACCGUUAACUUCCAAUUAACUAGUUUUGAC
-SEQ34_1_51_+          CAGAGAAUAGUUUAAAUUAGAAUCUUAGCUUUGGGUGCUAAUGGUGGAGUU
+SEQ39_1_50_+          GUUCUUGUAGUUGAAA-UACAACGAUGGUUUUUCAUAUCAUUGGUCGUGGU
 #=GC SS_cons          .........<<<<......>>>>.<<<<<.......>>>>>..........
 //
\ No newline at end of file
--- a/test-data/alignment2.sth	Sat Oct 27 13:21:39 2018 -0400
+++ b/test-data/alignment2.sth	Sun Oct 28 18:52:14 2018 -0400
@@ -1,9 +1,9 @@
 # STOCKHOLM 1.0
 
-SEQ5_526_595_+           CUUUGUCCCUGACUGACUAUGCUUGUGGUUCUCCUCCAGUUGAUAGAGAAAAACAACCCAGCGAAGGCGC
+SEQ16_526_595_+          CUUUGUCCCUGACUGACUAUGCUUGUGGUUCUCCUCCAGUUGAUAGAGAAAAACAACCCAGCGAAGGCGC
+SEQ19_523_592_+          CUUUGUCCCUGACUGACUAUGCUUGUGGUUCUCCUCCAGUUGAUAGAGAAAAACAACCCAGCGAAGGCGC
 SEQ4_526_595_+           CUUUGUCCCUGACUGACUAUGCUUGUGGUUCUCCUCCAGUUGAUAGAGAAAAACAACCCAGCGAAGGCGC
 SEQ14_529_598_+          CUUUGUCCCUGACUGACUAUGCUUGUGGUUCUCCUUCAGUUGAUAGAGAAAAACAACCCAGCGAAGGCGC
-SEQ19_523_592_+          CUUUGUCCCUGACUGACUAUGCUUGUGGUUCUCCUCCAGUUGAUAGAGAAAAACAACCCAGCGAAGGCGC
-SEQ16_526_595_+          CUUUGUCCCUGACUGACUAUGCUUGUGGUUCUCCUCCAGUUGAUAGAGAAAAACAACCCAGCGAAGGCGC
+SEQ5_526_595_+           CUUUGUCCCUGACUGACUAUGCUUGUGGUUCUCCUCCAGUUGAUAGAGAAAAACAACCCAGCGAAGGCGC
 #=GC SS_cons             <<<<<<<...<<<<<<<<<<....>>>>>.......>>>>>>>>>>>>............<<<....>>>
 //
\ No newline at end of file
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/alignment3.cons.tsv	Sun Oct 28 18:52:14 2018 -0400
@@ -0,0 +1,2 @@
+	Background model	Columns	Combinations/Pair	Consensus MFE	Covariance contribution	Decision model	Energy contribution	G+C content	Mean pairwise identity	Mean single sequence MFE	Mean z-score	Prediction	Reading direction	SVM RNA-class probability	SVM decision value	Sequences	Shannon entropy	Structure conservation index	alignment	multihit per_species	num_human_seqs_all	num_seqs	num_seqs_all	cluster_bed	cluster_human_ids	cluster_human_loc
+0	dinucleotide	53	0.000	0.000	0.000	structural RNA alignment quality	0.000	0.188	39.920	-1.500	0.480	OTHER	forward	0.000	-3.260	5.000	1.022	-0.000	cluster.aln	0	0	5	12			
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/alignment3.sth	Sun Oct 28 18:52:14 2018 -0400
@@ -0,0 +1,9 @@
+# STOCKHOLM 1.0
+
+SEQ34_1_51_+          UUUUUUUUUUU-----------UUUUUUUCUUUUUUUUGGGUGCUAAGGAGUU
+SEQ41_1_50_+          ACUCUUUUAGU-----------AUAAAUUUUUUUUUUUUUUU--UGUUUUGAC
+SEQ47_2_50_+          UUUUUUUUUUU-----------UUUUUUUUUUAAAGUUAAAU----UAUAGGC
+SEQ42_1_50_+          GUAAAUAUAGUUUAACCAA---AACAUCAGAUUGUGAAUCUGACAACAGAGGC
+SEQ39_1_50_+          GUUCUUGUAGUUUUUUUGAUGGUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUU
+#=GC SS_cons          .....................................................
+//
\ No newline at end of file
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/cluster3.all	Sun Oct 28 18:52:14 2018 -0400
@@ -0,0 +1,12 @@
+SEQ44#1#51#+  RESULT  2  CM_SCORE  43.7  MODEL     1.3  ORIGID  RF00005_rep.46_AF347015.1/1604-1672_44      ORIGHEAD  RF00005_rep.46  
+SEQ8#1#48#+   RESULT  2  CM_SCORE  39.1  MODEL     1.3  ORIGID  RF00005_rep.13_AC067849.6/4771-4840_8       ORIGHEAD  RF00005_rep.13  
+SEQ47#2#50#+  RESULT  2  CM_SCORE  38.0  MODEL     1.3  ORIGID  RF00005_rep.6_X93334.1/6942-7009_47         ORIGHEAD  RF00005_rep.6   
+SEQ48#1#52#+  RESULT  2  CM_SCORE  37.9  MODEL     1.3  ORIGID  RF00005_rep.7_AF347005.1/12268-12338_48     ORIGHEAD  RF00005_rep.7   
+SEQ43#1#52#+  RESULT  2  CM_SCORE  35.3  MODEL     1.3  ORIGID  RF00005_rep.45_AF382005.1/581-651_43        ORIGHEAD  RF00005_rep.45  
+SEQ39#1#50#+  RESULT  2  CM_SCORE  28.6  MODEL     1.3  ORIGID  RF00005_rep.41_AC093311.2/140036-139968_39  ORIGHEAD  RF00005_rep.41  
+SEQ34#1#51#+  RESULT  2  CM_SCORE  22.2  MODEL     1.3  ORIGID  RF00005_rep.37_AF347001.1/16015-15948_34    ORIGHEAD  RF00005_rep.37  
+SEQ42#1#50#+  RESULT  2  CM_SCORE  45.6  CMSEARCH  1.3  ORIGID  RF00005_rep.44_AC008670.6/83597-83665_42    ORIGHEAD  RF00005_rep.44  
+SEQ38#1#50#+  RESULT  2  CM_SCORE  45.2  CMSEARCH  1.3  ORIGID  RF00005_rep.40_AF382013.1/10403-10467_38    ORIGHEAD  RF00005_rep.40  
+SEQ6#1#51#+   RESULT  2  CM_SCORE  43.6  CMSEARCH  1.3  ORIGID  RF00005_rep.11_AF346992.1/15890-15955_6     ORIGHEAD  RF00005_rep.11  
+SEQ41#1#50#+  RESULT  2  CM_SCORE  40.6  CMSEARCH  1.3  ORIGID  RF00005_rep.43_L23320.1/77-10_41            ORIGHEAD  RF00005_rep.43  
+SEQ49#1#50#+  RESULT  2  CM_SCORE  35.7  CMSEARCH  1.3  ORIGID  RF00005_rep.8_AF134583.1/1599-1666_49       ORIGHEAD  RF00005_rep.8   
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/cluster3.all.fa	Sun Oct 28 18:52:14 2018 -0400
@@ -0,0 +1,19 @@
+>SEQ34_1_51_+ RESULT 2 SCORE 22.2 EVALUE 1.9e-06 CLUSTER 1.3 LOC MISS ORIGID RF00005_rep.37_AF347001.1/16015-15948_34 ORIGHEAD RF00005_rep.37
+UUUUUUUUUUUUUUUUUUCUUUUUUUUGGGUGCUAAGGAGUU
+>SEQ41_1_50_+ RESULT 2 SCORE 40.6 EVALUE 3.3e-14 CLUSTER 1.3 LOC MISS ORIGID RF00005_rep.43_L23320.1/77-10_41 ORIGHEAD RF00005_rep.43
+ACUCUUUUAGUAUAAAUUUUUUUUUUUUUUUUGUUUUGAC
+>SEQ47_2_50_+ RESULT 2 SCORE 38.0 EVALUE 4e-13 CLUSTER 1.3 LOC MISS ORIGID RF00005_rep.6_X93334.1/6942-7009_47 ORIGHEAD RF00005_rep.6
+UUUUUUUUUUUUUUUUUUUUUAAAGUUAAAUUAUAGGC
+>SEQ42_1_50_+ RESULT 2 SCORE 45.6 EVALUE 2.6e-16 CLUSTER 1.3 LOC MISS ORIGID RF00005_rep.44_AC008670.6/83597-83665_42 ORIGHEAD RF00005_rep.44
+GUAAAUAUAGUUUAACCAAAACAUCAGAUUGUGAAUCUGACAACAGAGGC
+>SEQ39_1_50_+ RESULT 2 SCORE 28.6 EVALUE 3.7e-09 CLUSTER 1.3 LOC MISS ORIGID RF00005_rep.41_AC093311.2/140036-139968_39 ORIGHEAD RF00005_rep.41
+GUUCUUGUAGUUUUUUUGAUGGUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUU
+>SEQ43_1_52_+ RESULT 2 SCORE 35.3 EVALUE 5.8e-12 CLUSTER 1.3 LOC MISS ORIGID RF00005_rep.45_AF382005.1/581-651_43 ORIGHEAD RF00005_rep.45
+GUUUAUGUAGCUUACCUCCUCAAAUUUUUUUUUUUUUUUUUUUUUUUUU
+>SEQ49_1_50_+ RESULT 2 SCORE 35.7 EVALUE 3.9e-12 CLUSTER 1.3 LOC MISS ORIGID RF00005_rep.8_AF134583.1/1599-1666_49 ORIGHEAD RF00005_rep.8
+AGAAAUUUAGGUUAAAUACAGACCAAGAUUUUUUUUUUUUUUUUUUUUUUUUUU
+>SEQ44_1_51_+ RESULT 2 SCORE 43.7 EVALUE 1.7e-15 CLUSTER 1.3 LOC MISS ORIGID RF00005_rep.46_AF347015.1/1604-1672_44 ORIGHEAD RF00005_rep.46
+CAGAGUGUAGCUUUUUUUUUUUUUUUUUUUUUUUUUUUUUU
+>SEQ8_1_48_+ RESULT 2 SCORE 39.1 EVALUE 1.4e-13 CLUSTER 1.3 LOC MISS ORIGID RF00005_rep.13_AC067849.6/4771-4840_8 ORIGHEAD RF00005_rep.13
+CACUGUAAAGCUAACUUAGCAUUAACCUUUUUUUUUUUUUUUUUU
+
--- a/test-data/structure1.ps	Sat Oct 27 13:21:39 2018 -0400
+++ b/test-data/structure1.ps	Sun Oct 28 18:52:14 2018 -0400
@@ -1,6 +1,6 @@
 %!PS-Adobe-3.0 EPSF-3.0
 %%Creator: ViennaRNA-2.2.10
-%%CreationDate: Sat Oct 27 14:38:56 2018
+%%CreationDate: Sun Oct 28 22:59:38 2018
 %%Title: RNA Secondary Structure Plot
 %%BoundingBox: 66 210 518 662
 %%DocumentFonts: Helvetica
Binary file test-data/structure3.png has changed