Merge pull request #4 from rlibouba/repeatmasker415

Test 4 error species - testing with rattus
galaxyproject · Apr 20, 2023 · 3096704 · 3096704
2 parents 0e597ee + 43e7738
commit 3096704
Show file tree

Hide file tree

Showing 5 changed files with 20 additions and 21 deletions.
diff --git a/tools/repeatmasker/repeatmasker.xml b/tools/repeatmasker/repeatmasker.xml
@@ -213,7 +213,7 @@
       <param name="input_fasta" value="small.fasta" ftype="fasta" />
       <param name="source_type" value="dfam_up" />
       <param name="dfam_lib" value="Dfam_partial_test.h5" ftype="h5" />
-      <param name="species_name" value="rodent" />
+      <param name="species_name" value="rattus" />
       <output name="output_masked_genome" file="small_dfam_up.fasta.masked" />
       <output name="output_table" file="small_dfam_up.fasta.stats" lines_diff="2" />
       <output name="output_repeat_catalog" file="small_dfam_up.fasta.cat" lines_diff="2" />

diff --git a/tools/repeatmasker/test-data/small.fasta.cat b/tools/repeatmasker/test-data/small.fasta.cat
@@ -98,6 +98,6 @@ Gap_init rate = 0.03 (1 / 35), avg. gap size = 1.00 (1 / 1)
 ## Total Length: 14220
 ## Total NonMask ( excluding >20bp runs of N/X bases ): 14220
 ## Total NonSub ( excluding all non ACGT bases ):14220
-RepeatMasker version 4.1.2-p1 , default mode
-run with rmblastn version 2.10.0+
+RepeatMasker version 4.1.5 , default mode
+run with rmblastn version 2.13.0+
 RM Library: 
diff --git a/tools/repeatmasker/test-data/small.fasta.gff b/tools/repeatmasker/test-data/small.fasta.gff
@@ -1,11 +1,10 @@
-##gff-version 2
-##date 2021-05-20
-##sequence-region rm_input.fasta
-scaffold_1	RepeatMasker	similarity	613	632	 0.0	+	.	Target "Motif:(GT)n" 1 20
-scaffold_1	RepeatMasker	similarity	780	824	18.3	+	.	Target "Motif:(ATAATA)n" 1 45
-scaffold_1	RepeatMasker	similarity	2231	2274	23.9	+	.	Target "Motif:(CAGA)n" 1 46
-scaffold_1	RepeatMasker	similarity	4853	4901	18.4	+	.	Target "Motif:(TC)n" 1 54
-scaffold_1	RepeatMasker	similarity	6230	6284	19.1	+	.	Target "Motif:(TAATTAA)n" 1 52
-scaffold_1	RepeatMasker	similarity	6548	6606	28.3	+	.	Target "Motif:(GACA)n" 1 57
-scaffold_1	RepeatMasker	similarity	11981	12050	 2.9	+	.	Target "Motif:(CT)n" 1 71
-scaffold_1	RepeatMasker	similarity	12078	12113	15.4	+	.	Target "Motif:(CT)n" 1 37
+##gff-version 3
+##sequence-region scaffold_1 1 14220
+scaffold_1	RepeatMasker	dispersed_repeat	613	632	 0.0	+	.	ID=1;Target "Motif:(GT)n" 1 20
+scaffold_1	RepeatMasker	dispersed_repeat	780	824	18.3	+	.	ID=2;Target "Motif:(ATAATA)n" 1 45
+scaffold_1	RepeatMasker	dispersed_repeat	2231	2274	23.9	+	.	ID=3;Target "Motif:(CAGA)n" 1 46
+scaffold_1	RepeatMasker	dispersed_repeat	4853	4901	18.4	+	.	ID=4;Target "Motif:(TC)n" 1 54
+scaffold_1	RepeatMasker	dispersed_repeat	6230	6284	19.1	+	.	ID=5;Target "Motif:(TAATTAA)n" 1 52
+scaffold_1	RepeatMasker	dispersed_repeat	6548	6606	28.3	+	.	ID=6;Target "Motif:(GACA)n" 1 57
+scaffold_1	RepeatMasker	dispersed_repeat	11981	12050	 2.9	+	.	ID=7;Target "Motif:(CT)n" 1 71
+scaffold_1	RepeatMasker	dispersed_repeat	12078	12113	15.4	+	.	ID=8;Target "Motif:(CT)n" 1 37
diff --git a/tools/repeatmasker/test-data/small.fasta.log b/tools/repeatmasker/test-data/small.fasta.log
@@ -1,4 +1,4 @@
-SW scoret% div.t% del.t% ins.tquery sequencetpos in  query: begintendt(left)trepeattclass/familytpos in repeat: begintendt(left)tID
+SW score	% div.	% del.	% ins.	query sequence	pos in  query: begin	end	(left)	repeat	class/family	pos in repeat: begin	end	(left)	ID
 
 18	0.0	0.0	0.0	scaffold_1	613	632	(13588)	(GT)n	Simple_repeat	1	20	(0)	1
 16	18.3	2.2	2.2	scaffold_1	780	824	(13396)	(ATAATA)n	Simple_repeat	1	45	(0)	2

diff --git a/tools/repeatmasker/test-data/small.fasta.stats b/tools/repeatmasker/test-data/small.fasta.stats
@@ -10,7 +10,7 @@ bases masked:        378 bp ( 2.66 %)
 --------------------------------------------------
 Retroelements            0            0 bp    0.00 %
    SINEs:                0            0 bp    0.00 %
-   Penelope              0            0 bp    0.00 %
+   Penelope:             0            0 bp    0.00 %
    LINEs:                0            0 bp    0.00 %
     CRE/SLACS            0            0 bp    0.00 %
      L2/CR1/Rex          0            0 bp    0.00 %
@@ -28,7 +28,7 @@ DNA transposons          0            0 bp    0.00 %
    hobo-Activator        0            0 bp    0.00 %
    Tc1-IS630-Pogo        0            0 bp    0.00 %
    En-Spm                0            0 bp    0.00 %
-   MuDR-IS905            0            0 bp    0.00 %
+   MULE-MuDR             0            0 bp    0.00 %
    PiggyBac              0            0 bp    0.00 %
    Tourist/Harbinger     0            0 bp    0.00 %
    Other (Mirage,        0            0 bp    0.00 %
@@ -53,8 +53,8 @@ Low complexity:          0            0 bp    0.00 %
   Runs of >=20 X/Ns in query were excluded in % calcs
 
 
-RepeatMasker version 4.1.2-p1 , default mode
-
-run with rmblastn version 2.10.0+
-The query was compared to unclassified sequences in ".../dataset_a3b3078d-de09-4651-9e83-62019a3d45ba.dat"
+RepeatMasker version 4.1.5 , default mode
+                                        
+run with rmblastn version 2.13.0+
+The query was compared to unclassified sequences in ".../dataset_01b79536-5cb7-47c1-a696-23dbb13fa826.dat"
 FamDB: