changeset 5:005b200c8841 draft

"planemo upload for repository https://github.com/jj-umn/tools-iuc/tree/arriba/tools/arriba commit bdefea23247f7d999b96e232ce810e2887338680"
author jjohnson
date Sun, 10 Oct 2021 13:00:45 +0000
parents 77021ad5037d
children 7253b367c082
files arriba.xml arriba_download_reference.xml arriba_get_filters.xml test-data/cytobands.tsv test-data/protein_domains.gff3
diffstat 5 files changed, 182 insertions(+), 21 deletions(-) [+]
line wrap: on
line diff
--- a/arriba.xml	Sat Oct 09 15:41:49 2021 +0000
+++ b/arriba.xml	Sun Oct 10 13:00:45 2021 +0000
@@ -71,7 +71,9 @@
         -t '$tags'
     #end if
     -o fusions.tsv
+#if $output_fusions_discarded
     -O fusions.discarded.tsv 
+#end if
 #if str($input_params.input_source) == "use_fastq"
     && samtools sort -@ \${GALAXY_SLOTS:-1} -m 4G -T tmp -O bam Aligned.out.bam > Aligned.sortedByCoord.out.bam
     && samtools index Aligned.sortedByCoord.out.bam
@@ -88,7 +90,7 @@
     #if $visualization.cytobands
     --cytobands='$visualization.cytobands'
     #end if
-    #if '$protein_domains'
+    #if $protein_domains
     --proteinDomains='$protein_domains'
     #end if
 #end if
@@ -130,13 +132,14 @@
         </conditional>
         <param name="genome_assembly" argument="-a" type="data" format="fasta" label="genome assembly fasta"/>
         <param name="gtf" argument="-g" type="data" format="gtf" label="GTF file with gene annotation"/>
-        <param name="blacklist" argument="-b" type="data" format="tabular" optional="true" label="File containing blacklisted ranges."/>
+        <param name="blacklist" argument="-b" type="data" format="tabular,tabular.gz" optional="true" label="File containing blacklisted ranges."/>
         <param name="protein_domains" argument="-p" type="data" format="gff3" optional="true" label="File containing protein domains"/>
-        <param name="known_fusions" argument="-k" type="data" format="tabular"  optional="true" label="File containing known fusions">
+        <param name="known_fusions" argument="-k" type="data" format="tabular,tabular.gz"  optional="true" label="File containing known fusions">
             <help><![CDATA[ file two TAB separated columns: five-prime region three-prime region ]]></help>
         </param>
         <param name="tags" argument="-t" type="data" format="tabular" optional="true" label="File containing tag names for a fusion."
                help="This can be the known fusions if that input has a third column with a name"/>
+        <param name="output_fusions_discarded" type="boolean" truevalue="yes" falsevalue="no" checked="true" label="Output fusions.discarded.tsv"/>
         <conditional name="visualization">
             <param name="do_viz" type="select" label="Generate visualization">
                 <option value="yes">Yes</option>
@@ -147,11 +150,12 @@
             </when>
             <when value="no"/>
         </conditional>
-        
     </inputs>
     <outputs>
         <data name="fusions" format="tabular" label="${tool.name} on ${on_string}: fusions.tsv" from_work_dir="fusions.tsv"/>
-        <data name="discarded" format="tabular" label="${tool.name} on ${on_string}: fusions.discarded.tsv" from_work_dir="fusions.discarded.tsv"/>
+        <data name="discarded" format="tabular" label="${tool.name} on ${on_string}: fusions.discarded.tsv" from_work_dir="fusions.discarded.tsv">
+            <filter> output_fusions_discarded == "yes"</filter>
+        </data> 
         <data name="aligned_bam" format="bam" label="${tool.name} on ${on_string}: Aligned.bam" from_work_dir="Aligned.sortedByCoord.out.bam">
             <filter>input_params['input_source'] == "use_fastq"</filter>
         </data> 
@@ -168,8 +172,10 @@
             </conditional>
             <param name="genome_assembly" ftype="fasta" value="genome.fasta"/>
             <param name="gtf" ftype="gtf" value="genome.gtf"/>
+            <param name="protein_domains" ftype="gff3" value="protein_domains.gff3"/>
             <conditional name="visualization">
                 <param name="do_viz" value="no"/>
+                <param name="cytobands" ftype="tabular" value="cytobands.tsv"/>
             </conditional>
             <output name="fusions">
                 <assert_contents>
@@ -177,6 +183,24 @@
                 </assert_contents>
             </output>
         </test>
+        <!-- Test 2 - From exisitng BAM with protein_domains and visualization -->
+        <test> 
+            <conditional name="input_params">
+                <param name="input_source" value="use_star"/>
+                <param name="input" ftype="sam" value="Aligned.out.sam"/>
+            </conditional>
+            <param name="genome_assembly" ftype="fasta" value="genome.fasta"/>
+            <param name="gtf" ftype="gtf" value="genome.gtf"/>
+            <conditional name="visualization">
+                <param name="do_viz" value="yes"/>
+            </conditional>
+            <output name="fusions">
+                <assert_contents>
+                    <has_text_matching expression="BCR\tABL1"/>
+                </assert_contents>
+            </output>
+        </test>
+
     </tests>
     <help><![CDATA[
 ** Arriba **
@@ -379,7 +403,10 @@
     The file fusions.discarded.tsv (as specified by the parameter -O) contains all events that Arriba classified as an artifact or that are also observed in healthy tissue. It has the same format as the file fusions.tsv. 
 
 
+** VISUALIZATION_ **
+  - fusions.pdf
 
+    A PDF file with one page for each predicted fusion. Each page depicts the fusion partners, their orientation, the retained exons in the fusion transcript, statistics about the number of supporting reads, and if the column fusion_transcript has a value an excerpt of the sequence around the breakpoint.
 
 
 Code repository: https://github.com/suhrig/arriba
@@ -391,6 +418,7 @@
 .. _Arriba: https://arriba.readthedocs.io/en/latest/
 .. _INPUTS: https://arriba.readthedocs.io/en/latest/input-files/
 .. _OUTPUTS: https://arriba.readthedocs.io/en/latest/output-files/
+.. _VISUALIZATION: https://arriba.readthedocs.io/en/latest/visualization/
 
     ]]></help>
     <expand macro="citations" />
--- a/arriba_download_reference.xml	Sat Oct 09 15:41:49 2021 +0000
+++ b/arriba_download_reference.xml	Sun Oct 10 13:00:45 2021 +0000
@@ -9,19 +9,19 @@
     echo $arriba_reference_name > '$star_index' &&
     BASE_DIR=\$(dirname \$(dirname `which arriba`)) &&
     REF_SCRIPT=`find \$BASE_DIR -name 'download_references.sh'` &&
+    #if $is_test != 'yes'
     \$REF_SCRIPT '$arriba_reference_name' &&
     cp *.fa*  '$genome_fasta' &&
     cp *.gtf*  '$genome_gtf' &&
     mv STAR_index_* '$star_index.extra_files_path'
+    #else
+    [[ -x \$REF_SCRIPT ]]
+    #end if
     ]]></command>
     <inputs>
+        <param name="is_test" type="hidden" value="no"/>
         <param name="arriba_reference_name" type="select" label="Select reference">
-            <option value="GRCh37+ENSEMBL87">GRCh37+ENSEMBL87</option>
-            <option value="GRCh37+GENCODE19">GRCh37+GENCODE19</option>
-            <option value="GRCh37+RefSeq">GRCh37+RefSeq</option>
-            <option value="GRCh37viral+ENSEMBL87">GRCh37viral+ENSEMBL87</option>
-            <option value="GRCh37viral+GENCODE19">GRCh37viral+GENCODE19</option>
-            <option value="GRCh37viral+RefSeq">GRCh37viral+RefSeq</option>
+
             <option value="GRCh38+ENSEMBL93">GRCh38+ENSEMBL93</option>
             <option value="GRCh38+GENCODE28">GRCh38+GENCODE28</option>
             <option value="GRCh38+RefSeq">GRCh38+RefSeq</option>
@@ -32,18 +32,24 @@
             <option value="GRCm38+RefSeq">GRCm38+RefSeq</option>
             <option value="GRCm38viral+GENCODEM25">GRCm38viral+GENCODEM25</option>
             <option value="GRCm38viral+RefSeq">GRCm38viral+RefSeq</option>
+            <option value="hg38+ENSEMBL93">hg38+ENSEMBL93</option>
+            <option value="hg38+GENCODE28">hg38+GENCODE28</option>
+            <option value="hg38+RefSeq">hg38+RefSeq</option>
+            <option value="hg38viral+ENSEMBL93">hg38viral+ENSEMBL93</option>
+            <option value="hg38viral+GENCODE28">hg38viral+GENCODE28</option>
+            <option value="hg38viral+RefSeq">hg38viral+RefSeq</option>
+            <option value="GRCh37+ENSEMBL87">GRCh37+ENSEMBL87</option>
+            <option value="GRCh37+GENCODE19">GRCh37+GENCODE19</option>
+            <option value="GRCh37+RefSeq">GRCh37+RefSeq</option>
+            <option value="GRCh37viral+ENSEMBL87">GRCh37viral+ENSEMBL87</option>
+            <option value="GRCh37viral+GENCODE19">GRCh37viral+GENCODE19</option>
+            <option value="GRCh37viral+RefSeq">GRCh37viral+RefSeq</option>
             <option value="hg19+ENSEMBL87">hg19+ENSEMBL87</option>
             <option value="hg19+GENCODE19">hg19+GENCODE19</option>
             <option value="hg19+RefSeq">hg19+RefSeq</option>
             <option value="hg19viral+ENSEMBL87">hg19viral+ENSEMBL87</option>
             <option value="hg19viral+GENCODE19">hg19viral+GENCODE19</option>
             <option value="hg19viral+RefSeq">hg19viral+RefSeq</option>
-            <option value="hg38+ENSEMBL93">hg38+ENSEMBL93</option>
-            <option value="hg38+GENCODE28">hg38+GENCODE28</option>
-            <option value="hg38+RefSeq">hg38+RefSeq</option>
-            <option value="hg38viral+ENSEMBL93">hg38viral+ENSEMBL93</option>
-            <option value="hg38viral+GENCODE28">hg38viral+GENCODE28</option>
-            <option value="hg38viral+RefSeq">hg38viral+RefSeq</option>
             <option value="hs37d5+ENSEMBL87">hs37d5+ENSEMBL87</option>
             <option value="hs37d5+GENCODE19">hs37d5+GENCODE19</option>
             <option value="hs37d5+RefSeq">hs37d5+RefSeq</option>
@@ -61,12 +67,42 @@
         <data name="genome_gtf" format="gtf" label="${tool.name} ${arriba_reference_name} GTF"/>
         <data name="star_index" format="txt" label="${tool.name} ${arriba_reference_name} STAR index"/>
     </outputs>
+    <tests>
+        <!-- Downloading a genome and annotation plus build a STAR index requires too many resources for testing. 
+              Just test that we can locate the script. -->
+        <test>
+            <param name="is_test" value="yes"/>
+            <param name="arriba_reference_name" value="GRCh38+ENSEMBL93"/>
+            <output name="star_index">
+                <assert_contents>
+                    <has_text text="GRCh38+ENSEMBL93"/>
+                </assert_contents>
+            </output>
+
+        </test>
+    </tests>
     <help><![CDATA[
-** Arriba **
+** Arriba Reference **
 
 Arriba_ is a fast tool to search for aberrant transcripts such as gene fusions.
 It is based on chimeric alignments found by the STAR RNA-Seq aligner.
 
+**Arriba Reference** downloads a genome sequence fasta and its related annoation GTF, and then build a STAR index for the RNA STAR aligner.  
+
+These datasets will be added to your Galaxy history:
+
+    - genome assembly fasta 
+    - genome annotation GTF 
+    - STAR index
+
+See Arriba manual pages:
+
+  - https://arriba.readthedocs.io/en/latest/workflow/
+  - https://arriba.readthedocs.io/en/latest/input-files/
+
+
+**NOTE:** This is a resource intensive process, so the results should be copies to new histories as needed rather than running this in each workflow.
+
 .. _Arriba: https://arriba.readthedocs.io/en/latest/
 
 ]]></help>
--- a/arriba_get_filters.xml	Sat Oct 09 15:41:49 2021 +0000
+++ b/arriba_get_filters.xml	Sun Oct 10 13:00:45 2021 +0000
@@ -34,8 +34,8 @@
         </param>
     </inputs>
     <outputs>
-        <data name="blacklist" format="tabular" label="${tool.name} ${arriba_reference_name} blacklist.tsv"/>
-        <data name="known_fusions" format="tabular" label="${tool.name} ${arriba_reference_name} known_fusions.tsv"/>
+        <data name="blacklist" format="tabular.gz" label="${tool.name} ${arriba_reference_name} blacklist.tsv.gz"/>
+        <data name="known_fusions" format="tabular.gz" label="${tool.name} ${arriba_reference_name} known_fusions.tsv.gz"/>
         <data name="protein_domains" format="gff3" label="${tool.name} ${arriba_reference_name} protein_domains.gff3"/>
         <data name="cytobands" format="tabular" label="${tool.name} ${arriba_reference_name} cytobands.tsv"/>
     </outputs>
@@ -50,12 +50,21 @@
         </test>
     </tests>
     <help><![CDATA[
-** Arriba **
+**Arriba Get Filters**
 
 Arriba_ is a fast tool to search for aberrant transcripts such as gene fusions.
 It is based on chimeric alignments found by the STAR RNA-Seq aligner.
 
+The **Arriba Get Filters** tool adds the following Arriba distribution input_files_ to your galaxy history:
+
+  - blacklist
+  - known_fusions
+  - protein_domains
+  - cytobands
+
+
 .. _Arriba: https://arriba.readthedocs.io/en/latest/
+.. _input_files: https://arriba.readthedocs.io/en/latest/input-files/
 
 ]]></help>
     <expand macro="citations" />
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/cytobands.tsv	Sun Oct 10 13:00:45 2021 +0000
@@ -0,0 +1,5 @@
+contig	start	end	name	giemsa
+22	1	40586	q11.22	gpos25
+22	40586	269079	q11.23	gneg
+9	1	21036	q34.11	gneg
+9	21036	515509	q34.12	gpos25
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/protein_domains.gff3	Sun Oct 10 13:00:45 2021 +0000
@@ -0,0 +1,83 @@
+9	pfam	protein_domain	33502	33541	0	+	.	Name=KH domain;color=#808080;gene_id=ENSG00000107164;gene_name=FUBP3;protein_domain_id=PF00013
+9	pfam	protein_domain	33992	34063	0	+	.	Name=KH domain;color=#808080;gene_id=ENSG00000107164;gene_name=FUBP3;protein_domain_id=PF00013
+9	pfam	protein_domain	35324	35381	0	+	.	Name=KH domain;color=#808080;gene_id=ENSG00000107164;gene_name=FUBP3;protein_domain_id=PF00013
+9	pfam	protein_domain	37391	37409	0	+	.	Name=KH domain;color=#808080;gene_id=ENSG00000107164;gene_name=FUBP3;protein_domain_id=PF00013
+9	pfam	protein_domain	37479	37553	0	+	.	Name=KH domain;color=#808080;gene_id=ENSG00000107164;gene_name=FUBP3;protein_domain_id=PF00013
+9	pfam	protein_domain	38833	38931	0	+	.	Name=KH domain;color=#808080;gene_id=ENSG00000107164;gene_name=FUBP3;protein_domain_id=PF00013
+9	pfam	protein_domain	41390	41413	0	+	.	Name=KH domain;color=#808080;gene_id=ENSG00000107164;gene_name=FUBP3;protein_domain_id=PF00013
+9	pfam	protein_domain	41489	41494	0	+	.	Name=KH domain;color=#808080;gene_id=ENSG00000107164;gene_name=FUBP3;protein_domain_id=PF00013
+9	pfam	protein_domain	43744	43846	0	+	.	Name=KH domain;color=#808080;gene_id=ENSG00000107164;gene_name=FUBP3;protein_domain_id=PF00013
+9	pfam	protein_domain	44647	44729	0	+	.	Name=KH domain;color=#808080;gene_id=ENSG00000107164;gene_name=FUBP3;protein_domain_id=PF00013
+9	pfam	protein_domain	47496	47541	0	+	.	Name=KH domain;color=#808080;gene_id=ENSG00000107164;gene_name=FUBP3;protein_domain_id=PF00013
+9	pfam	protein_domain	51664	51812	0	+	.	Name=KH domain;color=#808080;gene_id=ENSG00000107164;gene_name=FUBP3;protein_domain_id=PF00013
+9	pfam	protein_domain	102331	102396	0	+	.	Name=Zinc finger%2C C2H2 type;color=#80FF00;gene_id=ENSG00000130711;gene_name=PRDM12;protein_domain_id=PF00096
+9	pfam	protein_domain	102412	102480	0	+	.	Name=C2H2-type zinc finger;color=#80FF80;gene_id=ENSG00000130711;gene_name=PRDM12;protein_domain_id=PF13894
+9	pfam	protein_domain	114903	114949	0	+	.	Name=Exosome complex exonuclease RRP4 N-terminal region;color=#FF0000;gene_id=ENSG00000130713;gene_name=EXOSC2;protein_domain_id=PF14382
+9	pfam	protein_domain	116528	116596	0	+	.	Name=Exosome complex exonuclease RRP4 N-terminal region;color=#FF0000;gene_id=ENSG00000130713;gene_name=EXOSC2;protein_domain_id=PF14382
+9	pfam	protein_domain	121951	121971	0	+	.	Name=KH domain;color=#000080;gene_id=ENSG00000130713;gene_name=EXOSC2;protein_domain_id=PF15985
+9	pfam	protein_domain	123179	123300	0	+	.	Name=KH domain;color=#000080;gene_id=ENSG00000130713;gene_name=EXOSC2;protein_domain_id=PF15985
+9	pfam	protein_domain	275219	275273	0	+	.	Name=SH3 domain;color=#FF0000;gene_id=ENSG00000097007;gene_name=ABL1;protein_domain_id=PF00018
+9	pfam	protein_domain	275837	275922	0	+	.	Name=SH3 domain;color=#FF0000;gene_id=ENSG00000097007;gene_name=ABL1;protein_domain_id=PF00018
+9	pfam	protein_domain	275962	276132	0	+	.	Name=SH2 domain;color=#80FFFF;gene_id=ENSG00000097007;gene_name=ABL1;protein_domain_id=PF00017
+9	pfam	protein_domain	283799	283855	0	+	.	Name=SH2 domain;color=#80FFFF;gene_id=ENSG00000097007;gene_name=ABL1;protein_domain_id=PF00017
+9	pfam	protein_domain	283973	284071	0	+	.	Name=Protein kinase domain;color=#80FF00;gene_id=ENSG00000097007;gene_name=ABL1;protein_domain_id=PF00069
+9	pfam	protein_domain	293165	293249	0	+	.	Name=Protein kinase domain;color=#80FF00;gene_id=ENSG00000097007;gene_name=ABL1;protein_domain_id=PF00069
+9	pfam	protein_domain	293896	294073	0	+	.	Name=Protein kinase domain;color=#80FF00;gene_id=ENSG00000097007;gene_name=ABL1;protein_domain_id=PF00069
+9	pfam	protein_domain	295904	296088	0	+	.	Name=Protein kinase domain;color=#80FF00;gene_id=ENSG00000097007;gene_name=ABL1;protein_domain_id=PF00069
+9	pfam	protein_domain	299451	299603	0	+	.	Name=Protein kinase domain;color=#80FF00;gene_id=ENSG00000097007;gene_name=ABL1;protein_domain_id=PF00069
+9	pfam	protein_domain	301104	301156	0	+	.	Name=Protein kinase domain;color=#80FF00;gene_id=ENSG00000097007;gene_name=ABL1;protein_domain_id=PF00069
+9	pfam	protein_domain	306405	306716	0	+	.	Name=F-actin binding;color=#800000;gene_id=ENSG00000097007;gene_name=ABL1;protein_domain_id=PF08919
+9	pfam	protein_domain	314470	314862	0	-	.	Name=Orexigenic neuropeptide Qrfp/P518 ;color=#808000;gene_id=ENSG00000188710;gene_name=QRFP;protein_domain_id=PF11109
+9	pfam	protein_domain	325106	325108	0	-	.	Name=Fibrinogen beta and gamma chains%2C C-terminal globular domain;color=#808000;gene_id=ENSG00000130720;gene_name=FIBCD1;protein_domain_id=PF00147
+9	pfam	protein_domain	325118	325359	0	-	.	Name=Fibrinogen beta and gamma chains%2C C-terminal globular domain;color=#808000;gene_id=ENSG00000130720;gene_name=FIBCD1;protein_domain_id=PF00147
+9	pfam	protein_domain	326270	326449	0	-	.	Name=Fibrinogen beta and gamma chains%2C C-terminal globular domain;color=#808000;gene_id=ENSG00000130720;gene_name=FIBCD1;protein_domain_id=PF00147
+9	pfam	protein_domain	332828	332924	0	-	.	Name=Fibrinogen beta and gamma chains%2C C-terminal globular domain;color=#808000;gene_id=ENSG00000130720;gene_name=FIBCD1;protein_domain_id=PF00147
+9	pfam	protein_domain	344780	344908	0	-	.	Name=Fibrinogen beta and gamma chains%2C C-terminal globular domain;color=#808000;gene_id=ENSG00000130720;gene_name=FIBCD1;protein_domain_id=PF00147
+9	pfam	protein_domain	430353	430623	0	+	.	Name=Laminin N-terminal (Domain VI);color=#000080;gene_id=ENSG00000050555;gene_name=LAMC3;protein_domain_id=PF00055
+9	pfam	protein_domain	447321	447625	0	+	.	Name=Laminin N-terminal (Domain VI);color=#000080;gene_id=ENSG00000050555;gene_name=LAMC3;protein_domain_id=PF00055
+9	pfam	protein_domain	453081	453209	0	+	.	Name=Laminin N-terminal (Domain VI);color=#000080;gene_id=ENSG00000050555;gene_name=LAMC3;protein_domain_id=PF00055
+9	pfam	protein_domain	457203	457334	0	+	.	Name=Laminin EGF domain;color=#FFFFFF;gene_id=ENSG00000050555;gene_name=LAMC3;protein_domain_id=PF00053
+9	pfam	protein_domain	459902	460054	0	+	.	Name=Laminin EGF domain;color=#FFFFFF;gene_id=ENSG00000050555;gene_name=LAMC3;protein_domain_id=PF00053
+9	pfam	protein_domain	460070	460088	0	+	.	Name=Laminin EGF domain;color=#FFFFFF;gene_id=ENSG00000050555;gene_name=LAMC3;protein_domain_id=PF00053
+9	pfam	protein_domain	460167	460282	0	+	.	Name=Laminin EGF domain;color=#FFFFFF;gene_id=ENSG00000050555;gene_name=LAMC3;protein_domain_id=PF00053
+9	pfam	protein_domain	462677	462771	0	+	.	Name=Laminin EGF domain;color=#FFFFFF;gene_id=ENSG00000050555;gene_name=LAMC3;protein_domain_id=PF00053
+9	pfam	protein_domain	466560	466608	0	+	.	Name=Laminin EGF domain;color=#FFFFFF;gene_id=ENSG00000050555;gene_name=LAMC3;protein_domain_id=PF00053
+9	pfam	protein_domain	470157	470166	0	+	.	Name=Laminin B (Domain IV);color=#FFFF80;gene_id=ENSG00000050555;gene_name=LAMC3;protein_domain_id=PF00052
+9	pfam	protein_domain	473527	473719	0	+	.	Name=Laminin B (Domain IV);color=#FFFF80;gene_id=ENSG00000050555;gene_name=LAMC3;protein_domain_id=PF00052
+9	pfam	protein_domain	473886	474001	0	+	.	Name=Laminin B (Domain IV);color=#FFFF80;gene_id=ENSG00000050555;gene_name=LAMC3;protein_domain_id=PF00052
+9	pfam	protein_domain	477965	478038	0	+	.	Name=Laminin B (Domain IV);color=#FFFF80;gene_id=ENSG00000050555;gene_name=LAMC3;protein_domain_id=PF00052
+9	pfam	protein_domain	478042	478107	0	+	.	Name=Laminin EGF domain;color=#FFFFFF;gene_id=ENSG00000050555;gene_name=LAMC3;protein_domain_id=PF00053
+9	pfam	protein_domain	478144	478183	0	+	.	Name=Laminin EGF domain;color=#FFFFFF;gene_id=ENSG00000050555;gene_name=LAMC3;protein_domain_id=PF00053
+9	pfam	protein_domain	482071	482168	0	+	.	Name=Laminin EGF domain;color=#FFFFFF;gene_id=ENSG00000050555;gene_name=LAMC3;protein_domain_id=PF00053
+9	pfam	protein_domain	482175	482259	0	+	.	Name=Laminin EGF domain;color=#FFFFFF;gene_id=ENSG00000050555;gene_name=LAMC3;protein_domain_id=PF00053
+9	pfam	protein_domain	487996	488060	0	+	.	Name=Laminin EGF domain;color=#FFFFFF;gene_id=ENSG00000050555;gene_name=LAMC3;protein_domain_id=PF00053
+9	pfam	protein_domain	488076	488222	0	+	.	Name=Laminin EGF domain;color=#FFFFFF;gene_id=ENSG00000050555;gene_name=LAMC3;protein_domain_id=PF00053
+9	pfam	protein_domain	489116	489262	0	+	.	Name=Laminin EGF domain;color=#FFFFFF;gene_id=ENSG00000050555;gene_name=LAMC3;protein_domain_id=PF00053
+9	pfam	protein_domain	489945	490067	0	+	.	Name=Laminin EGF domain;color=#FFFFFF;gene_id=ENSG00000050555;gene_name=LAMC3;protein_domain_id=PF00053
+9	pfam	protein_domain	490710	490856	0	+	.	Name=Laminin EGF domain;color=#FFFFFF;gene_id=ENSG00000050555;gene_name=LAMC3;protein_domain_id=PF00053
+22	pfam	protein_domain	2420	2524	0	-	.	Name=Armadillo/beta-catenin-like repeat;color=#000080;gene_id=ENSG00000100218;gene_name=RSPH14;protein_domain_id=PF00514
+22	pfam	protein_domain	36321	37004	0	+	.	Name=G-protein alpha subunit;color=#80FFFF;gene_id=ENSG00000128266;gene_name=GNAZ;protein_domain_id=PF00503
+22	pfam	protein_domain	63673	63981	0	+	.	Name=G-protein alpha subunit;color=#80FFFF;gene_id=ENSG00000128266;gene_name=GNAZ;protein_domain_id=PF00503
+22	pfam	protein_domain	90736	90740	0	+	.	Name=Ras family;color=#80FFFF;gene_id=ENSG00000100228;gene_name=RAB36;protein_domain_id=PF00071
+22	pfam	protein_domain	93060	93112	0	+	.	Name=Ras family;color=#80FFFF;gene_id=ENSG00000100228;gene_name=RAB36;protein_domain_id=PF00071
+22	pfam	protein_domain	93619	93720	0	+	.	Name=Ras family;color=#80FFFF;gene_id=ENSG00000100228;gene_name=RAB36;protein_domain_id=PF00071
+22	pfam	protein_domain	96554	96622	0	+	.	Name=Ras family;color=#80FFFF;gene_id=ENSG00000100228;gene_name=RAB36;protein_domain_id=PF00071
+22	pfam	protein_domain	98578	98629	0	+	.	Name=Ras family;color=#80FFFF;gene_id=ENSG00000100228;gene_name=RAB36;protein_domain_id=PF00071
+22	pfam	protein_domain	99484	99565	0	+	.	Name=Ras family;color=#80FFFF;gene_id=ENSG00000100228;gene_name=RAB36;protein_domain_id=PF00071
+22	pfam	protein_domain	99749	99839	0	+	.	Name=Ras family;color=#80FFFF;gene_id=ENSG00000100228;gene_name=RAB36;protein_domain_id=PF00071
+22	pfam	protein_domain	101465	101502	0	+	.	Name=Ras family;color=#80FFFF;gene_id=ENSG00000100228;gene_name=RAB36;protein_domain_id=PF00071
+22	pfam	protein_domain	121553	121771	0	+	.	Name=Bcr-Abl oncoprotein oligomerisation domain;color=#FF0000;gene_id=ENSG00000186716;gene_name=BCR;protein_domain_id=PF09036
+22	pfam	protein_domain	201581	201640	0	+	.	Name=RhoGEF domain;color=#000000;gene_id=ENSG00000186716;gene_name=BCR;protein_domain_id=PF00621
+22	pfam	protein_domain	201941	202126	0	+	.	Name=RhoGEF domain;color=#000000;gene_id=ENSG00000186716;gene_name=BCR;protein_domain_id=PF00621
+22	pfam	protein_domain	208994	209101	0	+	.	Name=RhoGEF domain;color=#000000;gene_id=ENSG00000186716;gene_name=BCR;protein_domain_id=PF00621
+22	pfam	protein_domain	212118	212178	0	+	.	Name=RhoGEF domain;color=#000000;gene_id=ENSG00000186716;gene_name=BCR;protein_domain_id=PF00621
+22	pfam	protein_domain	213667	213719	0	+	.	Name=RhoGEF domain;color=#000000;gene_id=ENSG00000186716;gene_name=BCR;protein_domain_id=PF00621
+22	pfam	protein_domain	214220	214312	0	+	.	Name=RhoGEF domain;color=#000000;gene_id=ENSG00000186716;gene_name=BCR;protein_domain_id=PF00621
+22	pfam	protein_domain	230954	230999	0	+	.	Name=C2 domain;color=#00FF00;gene_id=ENSG00000186716;gene_name=BCR;protein_domain_id=PF00168
+22	pfam	protein_domain	233127	233224	0	+	.	Name=C2 domain;color=#00FF00;gene_id=ENSG00000186716;gene_name=BCR;protein_domain_id=PF00168
+22	pfam	protein_domain	235610	235741	0	+	.	Name=C2 domain;color=#00FF00;gene_id=ENSG00000186716;gene_name=BCR;protein_domain_id=PF00168
+22	pfam	protein_domain	250010	250018	0	+	.	Name=C2 domain;color=#00FF00;gene_id=ENSG00000186716;gene_name=BCR;protein_domain_id=PF00168
+22	pfam	protein_domain	252302	252422	0	+	.	Name=RhoGAP domain;color=#FFFFFF;gene_id=ENSG00000186716;gene_name=BCR;protein_domain_id=PF00620
+22	pfam	protein_domain	253473	253607	0	+	.	Name=RhoGAP domain;color=#FFFFFF;gene_id=ENSG00000186716;gene_name=BCR;protein_domain_id=PF00620
+22	pfam	protein_domain	254554	254659	0	+	.	Name=RhoGAP domain;color=#FFFFFF;gene_id=ENSG00000186716;gene_name=BCR;protein_domain_id=PF00620
+22	pfam	protein_domain	255138	255228	0	+	.	Name=RhoGAP domain;color=#FFFFFF;gene_id=ENSG00000186716;gene_name=BCR;protein_domain_id=PF00620