Repository 'gffcompare'
hg clone https://toolshed.g2.bx.psu.edu/repos/iuc/gffcompare

Changeset 4:0f710191a66d (2019-10-17)
Previous changeset 3:2bb86e2c417f (2019-05-27) Next changeset 5:f99dd58de04f (2023-02-03)
Commit message:
"planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/gffcompare commit 851f81495c875ac09d936537ffd2b32e6af2c8c5"
modified:
gffcompare.xml
test-data/gffcompare_out3.stats
b
diff -r 2bb86e2c417f -r 0f710191a66d gffcompare.xml
--- a/gffcompare.xml Mon May 27 13:54:15 2019 -0400
+++ b/gffcompare.xml Thu Oct 17 03:01:26 2019 -0400
b
b'@@ -3,7 +3,7 @@\n     <macros>\n         <token name="@GFFCOMPARE_VERSION@">0.11.2</token>\n     </macros>\n-\t<requirements>\n+    <requirements>\n         <requirement type="package" version="@GFFCOMPARE_VERSION@">gffcompare</requirement>\n     </requirements>\n     <version_command>gffcompare -v | awk \'{print $2}\'</version_command>\n@@ -49,6 +49,7 @@\n \n $discard_single_exon\n $discard_duplicates\n+$no_merge\n -e $max_dist_exon\n -d $max_dist_group\n $chr_stats\n@@ -79,7 +80,7 @@\n                     <when value="cached">\n                         <param argument="-r" label="Using reference annotation" name="index" type="select">\n                             <options from_data_table="gene_sets">\n-                                <filter column="1" key="dbkey" ref="gffinputs" type="data_meta" />\n+                                <filter column="dbkey" key="dbkey" ref="gffinputs" type="data_meta" />\n                             </options>\n                             <validator message="No reference annotation is available for the build associated with the selected input dataset" type="no_options" />\n                         </param>\n@@ -117,7 +118,7 @@\n                     <when value="cached">\n                         <param argument="-s" label="Using reference genome" name="index" type="select">\n                             <options from_data_table="fasta_indexes">\n-                                <filter column="1" key="dbkey" ref="gffinputs" type="data_meta" />\n+                                <filter column="dbkey" key="dbkey" ref="gffinputs" type="data_meta" />\n                             </options>\n                             <validator message="No reference genome is available for the build associated with the selected input dataset" type="no_options" />\n                         </param>\n@@ -143,7 +144,7 @@\n         <param argument="-d" help="max. distance (range) for grouping transcript start sites. Default: 100" label="Max distance for transcript grouping" name="max_dist_group" type="integer" value="100" />\n         <param name="chr_stats" argument="--chr-stats" type="boolean" checked="false" truevalue="--chr-stats" falsevalue="" label="Show summary and accuracy data separately for each reference sequence in the transcript accuracy data set" />\n         <section name="adv_output" title="Options for the combined GTF output file">\n-            <param argument="-p"  type="text" value="TCONS" label="name prefix for consensus transcripts" help="for combined.gtf (default: \'TCONS\')" />\n+            <param argument="-p"  type="text" value="TCONS" label="name prefix for consensus transcripts" help="for combined.gtf" />\n             <param argument="-C"  type="boolean" checked="false" truevalue="-C" falsevalue=""  label="discard matching and \'contained\' transfrags" help="i.e. collapse intron-redundant transfrags across all query files" />\n             <param argument="-A"  type="boolean" checked="false" truevalue="-A" falsevalue=""  label="discard the \'contained\' transfrags except intron-redundant transfrags starting with a different 5\' exon" help="like -C but does not discard intron-redundant transfrags if they start with a different 5\' exon" />\n             <param argument="-X"  type="boolean" checked="false" truevalue="-X" falsevalue=""  label="discard the \'contained\' transfrags also if ends stick out within the container\'s introns" help="like -C but also discard contained transfrags if transfrag ends stick out within the container\'s introns" />\n@@ -184,14 +185,14 @@\n                 <not_has_text text="-Q " />\n                 <not_has_text text="--strict-match " />\n                 <not_has_text text="-T " />\n-                <not_has_text text="-s " />\n+                <has_text_matching expression="^.*gffcompare((?!-s).)*$" /> <!-- since ln also has -s a more complicated regexp is needed here to check if -s is not set -->\n                 <not_has_text text="-M " />\n                 <not_has_text text="-N " />\n                 <has_te'..b'            <not_has_text text="-K " />\n             </assert_command>\n-            <output file="gffcompare_out2.stats" name="transcripts_stats" lines_diff="6" />\n-            <output file="gffcompare_out2.loci" name="transcripts_loci" lines_diff="2" />\n+            <output file="gffcompare_out2.stats" name="transcripts_stats" />\n+            <output file="gffcompare_out2.loci" name="transcripts_loci" compare="sim_size" />\n             <output file="gffcompare_out2.tracking" name="transcripts_tracking" />\n             <output file="gffcompare_out2.gtf" name="transcripts_combined" />\n             <output_collection name="refmap_output" type="list" count="2">\n@@ -346,7 +351,7 @@\n                 <has_text text="-D " />\n                 <has_text text="--no-merge " />\n                 <has_text text="--chr-stats" />\n-                <not_has_text text="-p TCONS " />\n+                <has_text text="-p \'TCONS\' " />\n                 <not_has_text text="-C " />\n                 <not_has_text text="-A " />\n                 <not_has_text text="-X " />\n@@ -382,12 +387,16 @@\n             <assert_command>\n                 <not_has_text text="-R " />\n                 <not_has_text text="-Q " />\n+                <not_has_text text="--strict-match " />\n                 <not_has_text text="-T " />\n                 <not_has_text text="-M " />\n                 <not_has_text text="-N " />\n                 <has_text text="-e 100 " />\n                 <has_text text="-d 100 " />\n-                <has_text text="-p OTHER " />\n+                <not_has_text text="-D " />\n+                <not_has_text text="--no-merge " />\n+                <not_has_text text="--chr-stats" />\n+                <has_text text="-p \'OTHER\' " />\n                 <has_text text="-C " />\n                 <has_text text="-A " />\n                 <has_text text="-X " />\n@@ -416,19 +425,23 @@\n             <assert_command>\n                 <not_has_text text="-R " />\n                 <not_has_text text="-Q " />\n+                <not_has_text text="--strict-match " />\n                 <has_text text="-T " />\n                 <not_has_text text="-M " />\n                 <not_has_text text="-N " />\n                 <has_text text="-e 100 " />\n                 <has_text text="-d 100 " />\n-                <has_text text="-p TCONS " />\n+                <not_has_text text="-D " />\n+                <not_has_text text="--no-merge " />\n+                <not_has_text text="--chr-stats" />\n+                <has_text text="-p \'TCONS\' " />\n                 <not_has_text text="-C " />\n                 <not_has_text text="-A " />\n                 <not_has_text text="-X " />\n                 <not_has_text text="-K " />\n             </assert_command>\n-            <output file="gffcompare_out2.stats" name="transcripts_stats" lines_diff="6" />\n-            <output file="gffcompare_out2.loci" name="transcripts_loci" lines_diff="2" />\n+            <output file="gffcompare_out2.stats" name="transcripts_stats" lines_diff="2" />\n+            <output file="gffcompare_out2.loci" name="transcripts_loci" compare="sim_size" />\n             <output file="gffcompare_out2.tracking" name="transcripts_tracking" />\n             <output file="gffcompare_out2.gtf" name="transcripts_combined" />\n         </test>\n@@ -449,8 +462,8 @@\n             <param name="discard_single_exon" value="" />\n             <param name="max_dist_exon" value="100" />\n             <param name="max_dist_group" value="100" />\n-            <output file="gffcompare_out3.stats" name="transcripts_stats" lines_diff="6" />\n-            <output file="gffcompare_out3.loci" name="transcripts_loci" />\n+            <output file="gffcompare_out3.stats" name="transcripts_stats"/>\n+            <output file="gffcompare_out3.loci" name="transcripts_loci" compare="sim_size" />\n             <output file="gffcompare_out3.tracking" name="transcripts_tracking" />\n             <output file="gffcompare_out3.gtf" name="transcripts_annotated" />\n         </test>\n'
b
diff -r 2bb86e2c417f -r 0f710191a66d test-data/gffcompare_out3.stats
--- a/test-data/gffcompare_out3.stats Mon May 27 13:54:15 2019 -0400
+++ b/test-data/gffcompare_out3.stats Thu Oct 17 03:01:26 2019 -0400
b
@@ -1,29 +1,29 @@
-# gffcompare v0.10.6 | Command line was:
+# gffcompare v0.11.2 | Command line was:
 #gffcompare -r ref_annotation -R -T -e 100 -d 100 -p TCONS gffcompare_in4_gtf
 #
 
 #= Summary for dataset: gffcompare_in4_gtf 
 #     Query mRNAs :      35 in      29 loci  (15 multi-exon transcripts)
 #            (3 multi-transcript loci, ~1.2 transcripts per locus)
-# Reference mRNAs :      20 in       7 loci  (19 multi-exon)
+# Reference mRNAs :      19 in       6 loci  (19 multi-exon)
 # Super-loci w/ reference transcripts:        6
 #-----------------| Sensitivity | Precision  |
-        Base level:    72.6     |    60.7    |
-        Exon level:    80.0     |    55.7    |
+        Base level:    72.7     |    60.7    |
+        Exon level:    81.0     |    55.7    |
       Intron level:    81.2     |    64.4    |
 Intron chain level:    10.5     |    13.3    |
-  Transcript level:    10.0     |     5.7    |
-       Locus level:    28.6     |     6.9    |
+  Transcript level:    10.5     |     5.7    |
+       Locus level:    33.3     |     6.9    |
 
      Matching intron chains:       2
        Matching transcripts:       2
               Matching loci:       2
 
-          Missed exons:       3/85 (  3.5%)
+          Missed exons:       2/84 (  2.4%)
            Novel exons:      46/122 ( 37.7%)
         Missed introns:      11/69 ( 15.9%)
          Novel introns:      28/87 ( 32.2%)
-           Missed loci:       0/7 (  0.0%)
+           Missed loci:       0/6 (  0.0%)
             Novel loci:      15/29 ( 51.7%)
 
  Total union super-loci across all input datasets: 21