Mercurial > repos > iuc > gffcompare
changeset 4:0f710191a66d draft
"planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/gffcompare commit 851f81495c875ac09d936537ffd2b32e6af2c8c5"
| author | iuc |
|---|---|
| date | Thu, 17 Oct 2019 03:01:26 -0400 |
| parents | 2bb86e2c417f |
| children | f99dd58de04f |
| files | gffcompare.xml test-data/gffcompare_out3.stats |
| diffstat | 2 files changed, 41 insertions(+), 28 deletions(-) [+] |
line wrap: on
line diff
--- a/gffcompare.xml Mon May 27 13:54:15 2019 -0400 +++ b/gffcompare.xml Thu Oct 17 03:01:26 2019 -0400 @@ -3,7 +3,7 @@ <macros> <token name="@GFFCOMPARE_VERSION@">0.11.2</token> </macros> - <requirements> + <requirements> <requirement type="package" version="@GFFCOMPARE_VERSION@">gffcompare</requirement> </requirements> <version_command>gffcompare -v | awk '{print $2}'</version_command> @@ -49,6 +49,7 @@ $discard_single_exon $discard_duplicates +$no_merge -e $max_dist_exon -d $max_dist_group $chr_stats @@ -79,7 +80,7 @@ <when value="cached"> <param argument="-r" label="Using reference annotation" name="index" type="select"> <options from_data_table="gene_sets"> - <filter column="1" key="dbkey" ref="gffinputs" type="data_meta" /> + <filter column="dbkey" key="dbkey" ref="gffinputs" type="data_meta" /> </options> <validator message="No reference annotation is available for the build associated with the selected input dataset" type="no_options" /> </param> @@ -117,7 +118,7 @@ <when value="cached"> <param argument="-s" label="Using reference genome" name="index" type="select"> <options from_data_table="fasta_indexes"> - <filter column="1" key="dbkey" ref="gffinputs" type="data_meta" /> + <filter column="dbkey" key="dbkey" ref="gffinputs" type="data_meta" /> </options> <validator message="No reference genome is available for the build associated with the selected input dataset" type="no_options" /> </param> @@ -143,7 +144,7 @@ <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" /> <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" /> <section name="adv_output" title="Options for the combined GTF output file"> - <param argument="-p" type="text" value="TCONS" label="name prefix for consensus transcripts" help="for combined.gtf (default: 'TCONS')" /> + <param argument="-p" type="text" value="TCONS" label="name prefix for consensus transcripts" help="for combined.gtf" /> <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" /> <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" /> <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" /> @@ -184,14 +185,14 @@ <not_has_text text="-Q " /> <not_has_text text="--strict-match " /> <not_has_text text="-T " /> - <not_has_text text="-s " /> + <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 --> <not_has_text text="-M " /> <not_has_text text="-N " /> <has_text text="-e 100 " /> <has_text text="-d 100 " /> <not_has_text text="-D " /> <not_has_text text="--no-merge " /> - <has_text text="-p TCONS " /> + <has_text text="-p 'TCONS' " /> <not_has_text text="-C " /> <not_has_text text="-A " /> <not_has_text text="-X " /> @@ -221,12 +222,12 @@ <not_has_text text="-R " /> <not_has_text text="-Q " /> <has_text text="-T " /> - <has_text text="-s " /> + <has_text_matching expression="gffcompare.*-s " /> <!-- since ln also has -s a more complicated regexp is needed here to check if -s is set --> <not_has_text text="-M " /> <not_has_text text="-N " /> <has_text text="-e 100 " /> <has_text text="-d 100 " /> - <has_text text="-p TCONS " /> + <has_text text="-p 'TCONS' " /> <not_has_text text="-C " /> <not_has_text text="-A " /> <not_has_text text="-X " /> @@ -255,12 +256,12 @@ <not_has_text text="-R " /> <not_has_text text="-Q " /> <has_text text="-T " /> - <has_text text="-s " /> + <has_text_matching expression="gffcompare.*-s " /> <not_has_text text="-M " /> <not_has_text text="-N " /> <has_text text="-e 100 " /> <has_text text="-d 100 " /> - <has_text text="-p TCONS " /> + <has_text text="-p 'TCONS' " /> <not_has_text text="-C " /> <not_has_text text="-A " /> <not_has_text text="-X " /> @@ -287,19 +288,23 @@ <assert_command> <not_has_text text="-R " /> <not_has_text text="-Q " /> + <not_has_text text="--strict-match " /> <not_has_text text="-T " /> <not_has_text text="-M " /> <not_has_text text="-N " /> <has_text text="-e 100 " /> <has_text text="-d 100 " /> - <has_text text="-p TCONS " /> + <not_has_text text="-D " /> + <not_has_text text="--no-merge " /> + <not_has_text text="--chr-stats" /> + <has_text text="-p 'TCONS' " /> <not_has_text text="-C " /> <not_has_text text="-A " /> <not_has_text text="-X " /> <not_has_text text="-K " /> </assert_command> - <output file="gffcompare_out2.stats" name="transcripts_stats" lines_diff="6" /> - <output file="gffcompare_out2.loci" name="transcripts_loci" lines_diff="2" /> + <output file="gffcompare_out2.stats" name="transcripts_stats" /> + <output file="gffcompare_out2.loci" name="transcripts_loci" compare="sim_size" /> <output file="gffcompare_out2.tracking" name="transcripts_tracking" /> <output file="gffcompare_out2.gtf" name="transcripts_combined" /> <output_collection name="refmap_output" type="list" count="2"> @@ -346,7 +351,7 @@ <has_text text="-D " /> <has_text text="--no-merge " /> <has_text text="--chr-stats" /> - <not_has_text text="-p TCONS " /> + <has_text text="-p 'TCONS' " /> <not_has_text text="-C " /> <not_has_text text="-A " /> <not_has_text text="-X " /> @@ -382,12 +387,16 @@ <assert_command> <not_has_text text="-R " /> <not_has_text text="-Q " /> + <not_has_text text="--strict-match " /> <not_has_text text="-T " /> <not_has_text text="-M " /> <not_has_text text="-N " /> <has_text text="-e 100 " /> <has_text text="-d 100 " /> - <has_text text="-p OTHER " /> + <not_has_text text="-D " /> + <not_has_text text="--no-merge " /> + <not_has_text text="--chr-stats" /> + <has_text text="-p 'OTHER' " /> <has_text text="-C " /> <has_text text="-A " /> <has_text text="-X " /> @@ -416,19 +425,23 @@ <assert_command> <not_has_text text="-R " /> <not_has_text text="-Q " /> + <not_has_text text="--strict-match " /> <has_text text="-T " /> <not_has_text text="-M " /> <not_has_text text="-N " /> <has_text text="-e 100 " /> <has_text text="-d 100 " /> - <has_text text="-p TCONS " /> + <not_has_text text="-D " /> + <not_has_text text="--no-merge " /> + <not_has_text text="--chr-stats" /> + <has_text text="-p 'TCONS' " /> <not_has_text text="-C " /> <not_has_text text="-A " /> <not_has_text text="-X " /> <not_has_text text="-K " /> </assert_command> - <output file="gffcompare_out2.stats" name="transcripts_stats" lines_diff="6" /> - <output file="gffcompare_out2.loci" name="transcripts_loci" lines_diff="2" /> + <output file="gffcompare_out2.stats" name="transcripts_stats" lines_diff="2" /> + <output file="gffcompare_out2.loci" name="transcripts_loci" compare="sim_size" /> <output file="gffcompare_out2.tracking" name="transcripts_tracking" /> <output file="gffcompare_out2.gtf" name="transcripts_combined" /> </test> @@ -449,8 +462,8 @@ <param name="discard_single_exon" value="" /> <param name="max_dist_exon" value="100" /> <param name="max_dist_group" value="100" /> - <output file="gffcompare_out3.stats" name="transcripts_stats" lines_diff="6" /> - <output file="gffcompare_out3.loci" name="transcripts_loci" /> + <output file="gffcompare_out3.stats" name="transcripts_stats"/> + <output file="gffcompare_out3.loci" name="transcripts_loci" compare="sim_size" /> <output file="gffcompare_out3.tracking" name="transcripts_tracking" /> <output file="gffcompare_out3.gtf" name="transcripts_annotated" /> </test>
--- 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 @@ -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