Mercurial > repos > peterjc > tmhmm_and_signalp
changeset 19:4cd848c5590b draft
Uploaded v0.2.5 preview 3, use $NSLOTS in the PSORT wrappers.
author | peterjc |
---|---|
date | Thu, 23 May 2013 12:49:18 -0400 |
parents | 2b35b5c4b7f4 |
children | a538e182fab3 |
files | tools/protein_analysis/promoter2.xml tools/protein_analysis/psortb.xml tools/protein_analysis/signalp3.xml tools/protein_analysis/tmhmm2.xml tools/protein_analysis/wolf_psort.xml |
diffstat | 5 files changed, 37 insertions(+), 12 deletions(-) [+] |
line wrap: on
line diff
--- a/tools/protein_analysis/promoter2.xml Fri May 10 07:48:26 2013 -0400 +++ b/tools/protein_analysis/promoter2.xml Thu May 23 12:49:18 2013 -0400 @@ -1,13 +1,15 @@ -<tool id="promoter2" name="Promoter 2.0" version="0.0.5"> +<tool id="promoter2" name="Promoter 2.0" version="0.0.6"> <description>Find eukaryotic PolII promoters in DNA sequences</description> <!-- If job splitting is enabled, break up the query file into parts --> <!-- Using 2000 per chunk so 4 threads each doing 500 is ideal --> <parallelism method="basic" split_inputs="fasta_file" split_mode="to_size" split_size="2000" merge_outputs="tabular_file"></parallelism> <command interpreter="python"> promoter2.py "\$NSLOTS" $fasta_file $tabular_file + ##I want the number of threads to be a Galaxy config option... ##Set the number of threads in the runner entry in universe_wsgi.ini ##which (on SGE at least) will set the $NSLOTS environment variable. - ##If the environment variable isn't set, get "", and defaults to one. + ##If the environment variable isn't set, get "", and the python wrapper + ##defaults to four threads. </command> <stdio> <!-- Anything other than zero is an error --> @@ -41,10 +43,14 @@ The input is a FASTA file of nucleotide sequences (e.g. upstream regions of your genes), and the output is tabular with five columns (one row per promoter): - 1. Sequence identifier (first word of FASTA header) - 2. Promoter position, e.g. 600 - 3. Promoter score, e.g. 1.063 - 4. Promoter likelihood, e.g. Highly likely prediction +====== ================================================== +Column Description +------ -------------------------------------------------- + 1 Sequence identifier (first word of FASTA header) + 2 Promoter position, e.g. 600 + 3 Promoter score, e.g. 1.063 + 4 Promoter likelihood, e.g. Highly likely prediction +====== ================================================== The scores are classified very simply as follows:
--- a/tools/protein_analysis/psortb.xml Fri May 10 07:48:26 2013 -0400 +++ b/tools/protein_analysis/psortb.xml Thu May 23 12:49:18 2013 -0400 @@ -1,10 +1,17 @@ -<tool id="Psortb" name="psortb" version="0.0.2"> +<tool id="Psortb" name="psortb" version="0.0.3"> <description>Determines sub-cellular localisation of bacterial/archaeal protein sequences</description> <!-- If job splitting is enabled, break up the query file into parts --> <!-- Using 2000 chunks meaning 4 threads doing 500 each is ideal --> <parallelism method="basic" split_inputs="fasta_file" split_mode="to_size" split_size="2000" merge_outputs="tabular_file"></parallelism> <version_command interpreter="python">psortb.py --version</version_command> - <command interpreter="python">psortb.py "\$NSLOTS" "$type" "$long" "$cutoff" "$divergent" "$sequence" "$outfile"</command> + <command interpreter="python"> + psortb.py "\$NSLOTS" "$type" "$long" "$cutoff" "$divergent" "$sequence" "$outfile" + ##I want the number of threads to be a Galaxy config option... + ##Set the number of threads in the runner entry in universe_wsgi.ini + ##which (on SGE at least) will set the $NSLOTS environment variable. + ##If the environment variable isn't set, get "", and python wrapper + ##defaults to four threads. + </command> <stdio> <!-- Anything other than zero is an error --> <exit_code range="1:" />
--- a/tools/protein_analysis/signalp3.xml Fri May 10 07:48:26 2013 -0400 +++ b/tools/protein_analysis/signalp3.xml Thu May 23 12:49:18 2013 -0400 @@ -7,7 +7,8 @@ signalp3.py $organism $truncate "\$NSLOTS" $fasta_file $tabular_file ##Set the number of threads in the runner entry in universe_wsgi.ini ##which (on SGE at least) will set the $NSLOTS environment variable. - ##If the environment variable isn't set, get "", and defaults to one. + ##If the environment variable isn't set, get "", and the python wrapper + ##defaults to four threads. </command> <stdio> <!-- Anything other than zero is an error -->
--- a/tools/protein_analysis/tmhmm2.xml Fri May 10 07:48:26 2013 -0400 +++ b/tools/protein_analysis/tmhmm2.xml Thu May 23 12:49:18 2013 -0400 @@ -5,9 +5,11 @@ <parallelism method="basic" split_inputs="fasta_file" split_mode="to_size" split_size="2000" merge_outputs="tabular_file"></parallelism> <command interpreter="python"> tmhmm2.py "\$NSLOTS" $fasta_file $tabular_file + ##I want the number of threads to be a Galaxy config option... ##Set the number of threads in the runner entry in universe_wsgi.ini ##which (on SGE at least) will set the $NSLOTS environment variable. - ##If the environment variable isn't set, get "", and defaults to one. + ##If the environment variable isn't set, get "", and the python wrapper + ##defaults to four threads. </command> <stdio> <!-- Anything other than zero is an error -->
--- a/tools/protein_analysis/wolf_psort.xml Fri May 10 07:48:26 2013 -0400 +++ b/tools/protein_analysis/wolf_psort.xml Thu May 23 12:49:18 2013 -0400 @@ -1,8 +1,12 @@ -<tool id="wolf_psort" name="WoLF PSORT" version="0.0.5"> +<tool id="wolf_psort" name="WoLF PSORT" version="0.0.6"> <description>Eukaryote protein subcellular localization prediction</description> <command interpreter="python"> - wolf_psort.py $organism 8 $fasta_file $tabular_file + wolf_psort.py $organism "\$NSLOTS" "$fasta_file" "$tabular_file" ##I want the number of threads to be a Galaxy config option... + ##Set the number of threads in the runner entry in universe_wsgi.ini + ##which (on SGE at least) will set the $NSLOTS environment variable. + ##If the environment variable isn't set, get "", and python wrapper + ##defaults to four threads. </command> <stdio> <!-- Anything other than zero is an error --> @@ -84,6 +88,11 @@ vacu vacuolar membrane 0005774(2) ====== ===================== ===================== +Numbers in parentheses, such as "0005856(2)" indicate that descendant "part_of" +cellular components were also included, up to the specified depth (2 in this case). +For example, all of the children and grandchildren of "GO:0005856" were +included as "cysk". + Additionally compound predictions like mito_nucl are also given.