Add plink param for ESCO4Cancer/GDI demo (galaxyproject#5624)

* add new plink mode * add new score files * switch to tabular * update test data * add new test file * change filenames * Update tools/plink/plink.xml Co-authored-by: Nicola Soranzo <[email protected]> --------- Co-authored-by: Nicola Soranzo <[email protected]>
pavanvidem · Nov 14, 2023 · 6d29c05 · 6d29c05
1 parent a01d758
commit 6d29c05
Show file tree

Hide file tree

Showing 3 changed files with 274 additions and 18 deletions.
diff --git a/tools/plink/plink.xml b/tools/plink/plink.xml
@@ -1,7 +1,8 @@
 <tool id='plink' name='plink' version='@TOOL_VERSION@+galaxy@VERSION_SUFFIX@'>
+    <description>genome association analysis toolset</description>
     <macros>
         <token name='@TOOL_VERSION@'>1.90b6.21</token>
-        <token name='@VERSION_SUFFIX@'>0</token>
+        <token name='@VERSION_SUFFIX@'>1</token>
         <xml name='template_sanitizer'>
             <sanitizer>
                 <valid initial='default'>
@@ -50,6 +51,7 @@
     </xrefs>
     <requirements>
         <requirement type='package' version='@TOOL_VERSION@'>plink</requirement>
+        <requirement type='package' version='5.3.0'>gawk</requirement>
     </requirements>
     <command detect_errors='exit_code'><![CDATA[
 
@@ -62,17 +64,17 @@
     #if $functions.func == 'data_manage':
         #if $functions.bmerge.set == 'Yes':
             && mkdir bmerge_files
-            && ln -s '$functions.bmerge.bed.extra_files_path'/RgeneticsData.bed bmerge_files/bmerge_input.bed
-            && ln -s '$functions.bmerge.bed.extra_files_path'/RgeneticsData.bim bmerge_files/bmerge_input.bim
-            && ln -s '$functions.bmerge.bed.extra_files_path'/RgeneticsData.fam bmerge_files/bmerge_input.fam
+            && ln -s '$functions.bmerge.bed.extra_files_path/RgeneticsData.bed' 'bmerge_files/bmerge_input.bed'
+            && ln -s '$functions.bmerge.bed.extra_files_path/RgeneticsData.bim' 'bmerge_files/bmerge_input.bim'
+            && ln -s '$functions.bmerge.bed.extra_files_path/RgeneticsData.fam' 'bmerge_files/bmerge_input.fam'
         #end if
     #end if
 
 
     #if $inputs.inputs.filetype == 'bfile':
-        && ln -s '$inputs.inputs.bed.extra_files_path'/RgeneticsData.bed plink_input/plink_input.bed
-        && ln -s '$inputs.inputs.bed.extra_files_path'/RgeneticsData.bim plink_input/plink_input.bim
-        && ln -s '$inputs.inputs.bed.extra_files_path'/RgeneticsData.fam plink_input/plink_input.fam
+        && ln -s '$inputs.inputs.bed.extra_files_path/RgeneticsData.bed' 'plink_input/plink_input.bed'
+        && ln -s '$inputs.inputs.bed.extra_files_path/RgeneticsData.bim' 'plink_input/plink_input.bim'
+        && ln -s '$inputs.inputs.bed.extra_files_path/RgeneticsData.fam' 'plink_input/plink_input.fam'
         && plink --bfile plink_input/plink_input
     #elif $inputs.inputs.filetype == 'vcf':
         #if $inputs.inputs.input.is_of_type('bcf'):
@@ -84,7 +86,7 @@
 
     ## Plink commands by section
     #if $inputs.covar_input:
-            --covar '$inputs.covar_input'
+        --covar '$inputs.covar_input'
     #end if
     #if $inputs.set_pheno.set_pheno == 'Yes':
         --pheno $inputs.set_pheno.pheno $inputs.set_pheno.all_pheno
@@ -232,7 +234,6 @@
             #end if
 
     #elif $functions.func == 'data_manage':
-
         #if $functions.bmerge.set == 'Yes':
             --bmerge bmerge_files/bmerge_input
         #end if
@@ -285,8 +286,6 @@
                 #end if
             #end if
         #end if
-
-
     #elif $functions.func == 'link':
         #if $functions.set_indep.choice == 'Yes':
             --indep-pairwise $functions.set_indep.window $functions.set_indep.step $functions.set_indep.r2
@@ -382,8 +381,8 @@
             #end if
         #end if
 
-##    #elif $functions.func == 'scoring':
-##
+    #elif $functions.func == 'scoring':
+        --score '$functions.score_file' $functions.variant_id_i $functions.allel_codes_j $functions.scores_k $functions.header $functions.sum
 ##    #else:
 ##        --rerun $functions.logfile
 ##      
@@ -410,9 +409,12 @@
         #end if
     #end if
     && mkdir '$plink_out.extra_files_path'
-    && cp plink_output/plink_output.bed '$plink_out.extra_files_path'/RgeneticsData.bed
-    && cp plink_output/plink_output.bim '$plink_out.extra_files_path'/RgeneticsData.bim
-    && cp plink_output/plink_output.fam '$plink_out.extra_files_path'/RgeneticsData.fam
+    && cp plink_output/plink_output.bed '$plink_out.extra_files_path/RgeneticsData.bed'
+    && cp plink_output/plink_output.bim '$plink_out.extra_files_path/RgeneticsData.bim'
+    && cp plink_output/plink_output.fam '$plink_out.extra_files_path/RgeneticsData.fam'
+    #if $functions.func == 'scoring':
+        && awk -v OFS="\t" '{$1=$1; print}' plink_output/plink_output.profile > plink_output/plink_output.profile.tab
+    #end if
     ]]></command>
     <inputs>
         <section name='inputs' title='Data inputs' expanded='true'>
@@ -450,6 +452,7 @@
                 <option value='stratification'>Population stratification</option>
                 <option value='association'>Association analysis</option>
                 <option value='ibd'>Identity-by-descent</option>
+                <option value='scoring'>Apply a linear scoring system (--score)</option>
                 <!-- <option value='rerun'>Rerun</option> -->
             </param>
             <when value='filtering'>
@@ -970,8 +973,20 @@
                 </conditional>
                 <param name='lambda' type='float' label='Lambda value' optional='true'/>
             </when>
-            <!-- <when value='scoring'>
-            </when> -->
+            <when value='scoring'>
+                <!-- this implements a part of the -\-score parameter -->
+                <param name='score_file' format='tabular' type='data' label='Scoring system which should be applied to all samples'/>
+                <param name="variant_id_i" type="data_column" data_ref="score_file" label="Variant ID column"/>
+                <param name="allel_codes_j" type="data_column" data_ref="score_file" label="Allel column"/>
+                <param name="scores_k" type="data_column" data_ref="score_file" label="Score column"/>
+                <param name='header' type='boolean' truevalue='header' falsevalue='' checked='false' label='Is a header line present in the scores file?'/>
+
+                <param name="sum" type="select" label="How to combine the valid per-variant scores?" help="Average is the default, but it can be changed to sum.">
+                    <option value="">Final scores are averages of the valid per-variant scores</option>
+                    <option value="sum">Report sums (sum; can not be used with 'no-mean-imputation'; is automatically on with dosage data)</option>
+                    <option value="no-sum">Disable sum (no-sum)</option>
+                </param>
+            </when>
             <when value='ibd'>
                 <conditional name='genome'>
                     <param name='output_genome' type='select' help='Perform and return results of IBS/IBD computation'>
@@ -1060,6 +1075,11 @@
             <filter>functions['func'] == 'ibd' and functions['genome']['output_genome']</filter>
         </data>
 
+        <!--scores-->
+        <data name='scores' format='tabular' from_work_dir='plink_output/plink_output.profile.tab' label='${tool.name}: Scores'>
+            <filter>functions['func'] == 'scoring'</filter>
+        </data>
+
         <!--Stratifiction-->
         <data name='mds' format='txt' from_work_dir='plink_output/plink_output.mds' label='${tool.name}: MDS'>
             <filter>functions['func'] == 'stratification' and functions['cluster']['cluster'] == 'Yes' and functions['cluster']['mds']['mds_scaling'] == 'Yes'</filter>
@@ -1203,6 +1223,7 @@
             <expand macro="log_out_assert"/>
         </test>
 
+
         <test expect_num_outputs='8'>
             <section name='inputs'>
                 <conditional name='inputs'>
@@ -1393,6 +1414,30 @@
             <expand macro="log_out_assert"/>
             <output name='genome' file='out.genome'/>
         </test>
+        <!-- scoring function test-->
+        <test expect_num_outputs='3'>
+            <section name='inputs'>
+                <conditional name='inputs'>
+                    <param name='filetype' value='bfile'/>
+                    <param name='bed' value='' ftype="pbed">
+                        <composite_data value="plink.bim"/>
+                        <composite_data value="plink.bed"/>
+                        <composite_data value="plink.fam"/>
+                    </param>
+                </conditional>
+            </section>
+            <conditional name='functions'>
+                <param name='func' value='scoring'/>
+                <param name='score_file' value='scores_file.tab'/>
+                <param name='variant_id_i' value='1'/>
+                <param name='allel_codes_j' value='2'/>
+                <param name='scores_k' value='3'/>
+                <param name='header' value='true'/>
+                <param name='sum' value='sum'/>
+            </conditional>
+            <expand macro="log_out_assert"/>
+            <output name='scores' file='scores_results.tab'/>
+        </test>
     </tests>
     <help><![CDATA[
         PLINK is a free, open-source whole genome association analysis toolset, designed to perform a range of basic, large-scale analyses in a computationally efficient manner.

diff --git a/tools/plink/test-data/scores_file.tab b/tools/plink/test-data/scores_file.tab
@@ -0,0 +1,10 @@
+variant	effect_allele	beta
+snp1	T	-0.078507
+snp2	A	0.16488
+snp3	C	-0.043171
+snp18	C	-0.37606
+snp19	T	-0.039295
+snp20	A	0.033082
+snp21	T	0.13057
+snp22	C	0.02329
+snp23	G	0.027248
diff --git a/tools/plink/test-data/scores_results.tab b/tools/plink/test-data/scores_results.tab
@@ -0,0 +1,201 @@
+FID	IID	PHENO	CNT	CNT2	SCORESUM
+per0	per0	1	4	0	0
+per1	per1	2	4	2	0.066164
+per2	per2	1	4	3	0.231044
+per3	per3	1	4	2	0.197962
+per4	per4	1	4	2	0.197962
+per5	per5	1	4	1	0.16488
+per6	per6	2	4	2	0.32976
+per7	per7	2	4	2	0.197962
+per8	per8	1	4	2	0.197962
+per9	per9	1	4	2	0.197962
+per10	per10	1	4	2	0.197962
+per11	per11	2	4	1	0.16488
+per12	per12	1	4	0	0
+per13	per13	2	4	3	0.362842
+per14	per14	2	4	3	0.231044
+per15	per15	1	4	1	0.16488
+per16	per16	2	4	2	0.197962
+per17	per17	2	4	1	0.16488
+per18	per18	1	4	2	0.197962
+per19	per19	2	4	3	0.231044
+per20	per20	2	4	3	0.362842
+per21	per21	2	4	2	0.197962
+per22	per22	2	4	1	0.033082
+per23	per23	2	4	0	0
+per24	per24	1	4	2	0.32976
+per25	per25	1	4	4	0.395924
+per26	per26	2	4	1	0.033082
+per27	per27	2	4	1	0.16488
+per28	per28	2	4	1	0.033082
+per29	per29	2	4	3	0.231044
+per30	per30	2	4	2	0.197962
+per31	per31	2	4	2	0.197962
+per32	per32	2	4	0	0
+per33	per33	1	4	2	0.32976
+per34	per34	1	4	2	0.197962
+per35	per35	1	4	4	0.395924
+per36	per36	2	4	1	0.033082
+per37	per37	2	4	3	0.231044
+per38	per38	2	4	1	0.033082
+per39	per39	1	4	2	0.197962
+per40	per40	1	4	2	0.197962
+per41	per41	1	4	2	0.197962
+per42	per42	2	4	2	0.197962
+per43	per43	2	4	2	0.32976
+per44	per44	2	4	4	0.395924
+per45	per45	2	4	4	0.395924
+per46	per46	2	4	2	0.066164
+per47	per47	2	4	2	0.197962
+per48	per48	1	4	3	0.231044
+per49	per49	1	4	4	0.395924
+per50	per50	2	4	3	0.231044
+per51	per51	1	4	2	0.197962
+per52	per52	2	4	1	0.033082
+per53	per53	1	4	3	0.362842
+per54	per54	2	4	1	0.033082
+per55	per55	1	4	2	0.32976
+per56	per56	2	4	1	0.033082
+per57	per57	2	4	2	0.32976
+per58	per58	2	4	2	0.066164
+per59	per59	1	4	2	0.197962
+per60	per60	2	4	2	0.32976
+per61	per61	2	4	1	0.16488
+per62	per62	2	4	1	0.033082
+per63	per63	1	4	2	0.197962
+per64	per64	1	4	3	0.231044
+per65	per65	2	4	3	0.362842
+per66	per66	2	4	4	0.395924
+per67	per67	1	4	2	0.066164
+per68	per68	2	4	3	0.231044
+per69	per69	1	4	1	0.16488
+per70	per70	2	4	2	0.197962
+per71	per71	2	4	2	0.197962
+per72	per72	2	4	2	0.32976
+per73	per73	1	4	1	0.033082
+per74	per74	2	4	1	0.16488
+per75	per75	1	4	2	0.066164
+per76	per76	2	4	1	0.16488
+per77	per77	2	4	3	0.231044
+per78	per78	1	4	2	0.066164
+per79	per79	2	4	3	0.362842
+per80	per80	1	4	3	0.362842
+per81	per81	2	4	3	0.231044
+per82	per82	1	4	2	0.197962
+per83	per83	1	4	3	0.362842
+per84	per84	1	4	2	0.197962
+per85	per85	2	4	0	0
+per86	per86	1	4	3	0.362842
+per87	per87	2	4	1	0.033082
+per88	per88	1	4	2	0.32976
+per89	per89	2	4	2	0.32976
+per90	per90	2	4	1	0.16488
+per91	per91	1	4	2	0.197962
+per92	per92	2	4	3	0.231044
+per93	per93	1	4	3	0.231044
+per94	per94	2	4	1	0.16488
+per95	per95	2	4	3	0.362842
+per96	per96	2	4	3	0.362842
+per97	per97	1	4	2	0.197962
+per98	per98	2	4	1	0.16488
+per99	per99	2	4	0	0
+per100	per100	2	4	1	0.033082
+per101	per101	2	4	1	0.16488
+per102	per102	1	4	0	0
+per103	per103	1	4	2	0.197962
+per104	per104	1	4	1	0.16488
+per105	per105	2	4	1	0.033082
+per106	per106	2	4	2	0.197962
+per107	per107	2	4	1	0.16488
+per108	per108	2	4	2	0.32976
+per109	per109	1	4	3	0.362842
+per110	per110	1	4	2	0.066164
+per111	per111	1	4	2	0.197962
+per112	per112	2	4	4	0.395924
+per113	per113	1	4	0	0
+per114	per114	2	4	3	0.231044
+per115	per115	1	4	2	0.197962
+per116	per116	1	4	1	0.16488
+per117	per117	2	4	2	0.197962
+per118	per118	2	4	2	0.066164
+per119	per119	2	4	0	0
+per120	per120	2	4	1	0.16488
+per121	per121	1	4	3	0.231044
+per122	per122	2	4	0	0
+per123	per123	1	4	4	0.395924
+per124	per124	1	4	2	0.197962
+per125	per125	1	4	3	0.362842
+per126	per126	2	4	2	0.066164
+per127	per127	1	4	2	0.066164
+per128	per128	2	4	1	0.16488
+per129	per129	2	4	2	0.197962
+per130	per130	2	4	1	0.16488
+per131	per131	2	4	1	0.033082
+per132	per132	2	4	3	0.362842
+per133	per133	2	4	2	0.066164
+per134	per134	1	4	2	0.197962
+per135	per135	1	4	1	0.033082
+per136	per136	1	4	0	0
+per137	per137	1	4	3	0.362842
+per138	per138	1	4	2	0.32976
+per139	per139	1	4	1	0.033082
+per140	per140	1	4	0	0
+per141	per141	1	4	3	0.362842
+per142	per142	1	4	1	0.16488
+per143	per143	1	4	2	0.197962
+per144	per144	2	4	2	0.066164
+per145	per145	2	4	2	0.197962
+per146	per146	1	4	3	0.362842
+per147	per147	2	4	2	0.197962
+per148	per148	2	4	2	0.197962
+per149	per149	2	4	3	0.362842
+per150	per150	1	4	2	0.066164
+per151	per151	2	4	1	0.033082
+per152	per152	1	4	1	0.16488
+per153	per153	2	4	3	0.231044
+per154	per154	2	4	1	0.16488
+per155	per155	1	4	3	0.231044
+per156	per156	1	4	2	0.32976
+per157	per157	1	4	3	0.362842
+per158	per158	2	4	1	0.16488
+per159	per159	1	4	2	0.066164
+per160	per160	2	4	3	0.231044
+per161	per161	1	4	2	0.197962
+per162	per162	2	4	2	0.197962
+per163	per163	1	4	2	0.197962
+per164	per164	2	4	3	0.231044
+per165	per165	2	4	4	0.395924
+per166	per166	1	4	2	0.197962
+per167	per167	1	4	2	0.197962
+per168	per168	1	4	2	0.197962
+per169	per169	1	4	1	0.033082
+per170	per170	2	4	1	0.16488
+per171	per171	1	4	1	0.033082
+per172	per172	1	4	3	0.231044
+per173	per173	1	4	3	0.362842
+per174	per174	1	4	1	0.033082
+per175	per175	2	4	2	0.197962
+per176	per176	2	4	0	0
+per177	per177	2	4	2	0.197962
+per178	per178	1	4	1	0.033082
+per179	per179	1	4	2	0.197962
+per180	per180	1	4	2	0.066164
+per181	per181	1	4	1	0.033082
+per182	per182	1	4	3	0.362842
+per183	per183	1	4	4	0.395924
+per184	per184	1	4	3	0.362842
+per185	per185	1	4	2	0.197962
+per186	per186	2	4	3	0.231044
+per187	per187	1	4	1	0.16488
+per188	per188	1	4	3	0.231044
+per189	per189	2	4	2	0.197962
+per190	per190	1	4	1	0.033082
+per191	per191	1	4	4	0.395924
+per192	per192	1	4	2	0.197962
+per193	per193	2	4	1	0.033082
+per194	per194	2	4	2	0.197962
+per195	per195	1	4	2	0.32976
+per196	per196	1	4	2	0.197962
+per197	per197	1	4	3	0.231044
+per198	per198	1	4	3	0.231044
+per199	per199	2	4	4	0.395924