From: pvtroshin Date: Thu, 19 Aug 2010 14:36:46 +0000 (+0000) Subject: updates to jaba2 from jaba release branch X-Git-Url: http://source.jalview.org/gitweb/?a=commitdiff_plain;h=cfbceac612220d0a877942f7fb6658a5848d1ccf;p=jabaws.git updates to jaba2 from jaba release branch git-svn-id: link to svn.lifesci.dundee.ac.uk/svn/barton/ptroshin/JABA2@2919 e3abac25-378b-4346-85de-24260fe3988d --- diff --git a/dundee-conf/Engine.cluster.properties b/dundee-conf/Engine.cluster.properties index a6715be..5264236 100644 --- a/dundee-conf/Engine.cluster.properties +++ b/dundee-conf/Engine.cluster.properties @@ -7,5 +7,5 @@ engine.cluster.enable=true # Directory to use for temporary files storage # REQUIRED - cluster nodes must have access to this directory! # An absolute path is required -cluster.tmp.directory=/homes/pvtroshin/workspace/clustengine/jobsout +cluster.tmp.directory=/cluster/gjb_lab/fc/www-jws2/jaba/jobsout diff --git a/dundee-conf/Engine.local.properties b/dundee-conf/Engine.local.properties index 26b7729..a485104 100644 --- a/dundee-conf/Engine.local.properties +++ b/dundee-conf/Engine.local.properties @@ -5,10 +5,10 @@ engine.local.enable=true # Directory to use for temporary files storage # OPTIONAL defaults to java temporary directory # Relative path within the project will be converted in absolute at runtime -local.tmp.directory=jobsout/local +local.tmp.directory=/cluster/gjb_lab/fc/www-jws/jaba/local_jobsout # Number of threads for tasks execution (valid values between 1 and 2x cpu. # Where x is a number of cores available in the system) # OPTIONAL defaults to the number of cores for core number <=4 and # number of cores-1 for greater core numbers -engine.local.thread.number=3 +engine.local.thread.number=2 diff --git a/dundee-conf/Executable.properties b/dundee-conf/Executable.properties index 1f506af..3368475 100644 --- a/dundee-conf/Executable.properties +++ b/dundee-conf/Executable.properties @@ -2,7 +2,7 @@ ### Clustal configuration ### local.clustalw.bin.windows=binaries/clustalw2.exe local.clustalw.bin=binaries/src/clustalw/src/clustalw2 -cluster.clustalw.bin=/homes/pvtroshin/workspace/clustengine/binaries/src/clustalw/src/clustalw2 +cluster.clustalw.bin=/homes/www-jws2/servers/tomcat-jaba/webapps/jabaws/binaries/src/clustalw/src/clustalw2 # Parameters names which come from RunnerConfig -> Parameters.xml file ultimately are all lowercased in comparison! # see engine.client.Util.getExecProperty() method for details # So they are case insensitive. @@ -17,7 +17,7 @@ local.muscle.bin.windows=binaries/muscle.exe local.muscle.bin=binaries/src/muscle/muscle # Beware version of muscle on the cluster older and does not support some # of the newer version attributed thus, will not work with Muscle.java wrapper! -cluster.muscle.bin=/homes/pvtroshin/workspace/clustengine/binaries/src/muscle/muscle +cluster.muscle.bin=/homes/www-jws2/servers/tomcat-jaba/webapps/jabaws/binaries/src/muscle/muscle #The environment variable MUSCLE_MXPATH can be used to specify a path where the matrices are stored # e.g. MUSCLE_MXPATH#binaries/matrices - but need to privide absolute path! muscle.-matrix.path=binaries/matrices @@ -29,7 +29,7 @@ muscle.cluster.settings=-l h_cpu=24:00:00 -l h_vmem=6000M -l ram=6000M ### Mafft configuration ### #local.mafft.bin.windows= local.mafft.bin=binaries/src/mafft/binaries/mafft -cluster.mafft.bin=/homes/pvtroshin/workspace/clustengine/binaries/src/mafft/core/mafft +cluster.mafft.bin=/homes/www-jws2/servers/tomcat-jaba/webapps/jabaws/binaries/src/mafft/binaries/mafft mafft.bin.env=MAFFT_BINARIES#binaries/src/mafft/binaries;FASTA_4_MAFFT#/sw/bin/fasta34; mafft.--aamatrix.path=binaries/matrices mafft.presets.file=conf/settings/MafftPresets.xml @@ -39,7 +39,7 @@ mafft.cluster.settings=-l h_cpu=24:00:00 -l h_vmem=6000M -l ram=6000M ### Tcoffee configuration ### local.tcoffee.bin=binaries/src/tcoffee/t_coffee_source/t_coffee -cluster.tcoffee.bin=/homes/pvtroshin/workspace/clustengine/binaries/src/tcoffee/t_coffee_source/t_coffee +cluster.tcoffee.bin=/homes/www-jws2/servers/tomcat-jaba/webapps/jabaws/binaries/src/tcoffee/t_coffee_source/t_coffee #/sw/bin/t_coffee # Sub matrix support does not work #tcoffee.-matrix.path=binaries/matrices @@ -52,7 +52,7 @@ tcoffee.cluster.settings=-q 64bit-pri.q -pe smp 4 -l h_vmem=1700M -l ram=1700M - ### Probcons configuration ### #local.probcons.bin.windows= local.probcons.bin=binaries/src/probcons/probcons -cluster.probcons.bin=/homes/pvtroshin/workspace/clustengine/binaries/src/probcons/probcons +cluster.probcons.bin=/homes/www-jws2/servers/tomcat-jaba/webapps/jabaws/binaries/src/probcons/probcons #Probcons does not support matrix loading - unrecognised option reported! probcons.parameters.file=conf/settings/ProbconsParameters.xml probcons.limits.file=conf/settings/ProbconsLimits.xml diff --git a/dundee-conf/log4j.properties b/dundee-conf/log4j.properties index df2df68..afcc70b 100644 --- a/dundee-conf/log4j.properties +++ b/dundee-conf/log4j.properties @@ -1,6 +1,6 @@ # change this -logDir = . +logDir =/homes/www-jws2/logs log4j.rootLogger=ERROR, stdout log4j.appender.stdout=org.apache.log4j.ConsoleAppender diff --git a/dundee-conf/settings/ClustalLimits.xml b/dundee-conf/settings/ClustalLimits.xml deleted file mode 100644 index 28adf27..0000000 --- a/dundee-conf/settings/ClustalLimits.xml +++ /dev/null @@ -1,18 +0,0 @@ - - - compbio.runner.clustal.ClustalW - - Disable gap weighting (Speed-oriented) - 2000 - 1000 - - - 1000 - 1000 - - - # LocalEngineExecutionLimit # - 30 - 500 - - diff --git a/dundee-conf/settings/ClustalParameters.xml b/dundee-conf/settings/ClustalParameters.xml deleted file mode 100644 index 7e8de1d..0000000 --- a/dundee-conf/settings/ClustalParameters.xml +++ /dev/null @@ -1,195 +0,0 @@ - - - compbio.runner.clustal.ClustalW - - NOPGAP - Residue-specific gaps off - -NOPGAP - http://www.compbio.dundee.ac.uk/users/pvtroshin/ws/Index.html - - - - No transition weighting - Disable sequence weighting - -NOWEIGHTS - http://www.compbio.dundee.ac.uk/users/pvtroshin/ws/Index.html - - - - NOHGAP - Hydrophilic gaps off - -NOHGAP - http://www.compbio.dundee.ac.uk/users/pvtroshin/ws/Index.html - - - = - - Transition weighting - Type of the sequence (PROTEIN or DNA) - -TRANSWEIGHT - http://www.compbio.dundee.ac.uk/users/pvtroshin/ws/Index.html - - 0.5 - - Float - 0 - 10 - - - - Type - Type of the sequence (PROTEIN or DNA) - -TYPE - http://www.compbio.dundee.ac.uk/users/pvtroshin/ws/Index.html - - PROTEIN - PROTEIN - DNA - - - OUTORDER - As per INPUT or ALIGNED - -OUTORDER - INPUT - INPUT - ALIGNED - - - MATRIX - Protein weight matrix - -MATRIX - http://www.compbio.dundee.ac.uk/users/pvtroshin/ws/Index.html - - BLOSUM62 - - BLOSUM100 - BLOSUM30 - BLOSUM35 - BLOSUM40 - BLOSUM45 - BLOSUM50 - BLOSUM55 - BLOSUM60 - BLOSUM62 - BLOSUM65 - BLOSUM70 - BLOSUM75 - BLOSUM80 - BLOSUM85 - BLOSUM90 - BLOSUMN - DAYHOFF - GONNET - IDENTITY - MATCH - NUC.4.2 - NUC.4.4 - PAM10 - PAM100 - PAM110 - PAM120 - PAM130 - PAM140 - PAM150 - PAM160 - PAM170 - PAM180 - PAM190 - PAM20 - PAM200 - PAM210 - PAM220 - PAM230 - PAM240 - PAM250 - PAM260 - PAM270 - PAM280 - PAM290 - PAM30 - PAM300 - PAM310 - PAM320 - PAM330 - PAM340 - PAM350 - PAM360 - PAM370 - PAM380 - PAM390 - PAM40 - PAM400 - PAM410 - PAM420 - PAM430 - PAM440 - PAM450 - PAM460 - PAM470 - PAM480 - PAM490 - PAM50 - PAM500 - PAM60 - PAM70 - PAM80 - PAM90 - - - GAPOPEN - Gap opening penalty - -GAPOPEN - http://www.compbio.dundee.ac.uk/users/pvtroshin/ws/Index.html - - 10 - - Float - 0 - 1000 - - - - -GAPEXT - Gap extension penalty - -GAPEXT - http://www.compbio.dundee.ac.uk/users/pvtroshin/ws/Index.html - - 0.1 - - Float - 0 - 10 - - - - ENDGAPS - End gap separation pen - -ENDGAPS - http://www.compbio.dundee.ac.uk/users/pvtroshin/ws/Index.html - - 0.5 - - Float - 0 - 10 - - - - GAPDIST - Gap separation pen. range - -GAPDIST - http://www.compbio.dundee.ac.uk/users/pvtroshin/ws/Index.html - - 1 - - Integer - 0 - 50 - - - diff --git a/dundee-conf/settings/ClustalPresets.xml b/dundee-conf/settings/ClustalPresets.xml deleted file mode 100644 index 3115006..0000000 --- a/dundee-conf/settings/ClustalPresets.xml +++ /dev/null @@ -1,13 +0,0 @@ - - - compbio.runner.clustal.ClustalW - - Disable gap weighting (Speed-oriented) - - - - - - - - diff --git a/dundee-conf/settings/MafftLimits.xml b/dundee-conf/settings/MafftLimits.xml deleted file mode 100644 index 82836f8..0000000 --- a/dundee-conf/settings/MafftLimits.xml +++ /dev/null @@ -1,13 +0,0 @@ - - - compbio.runner.mafft.Mafft - - 1000 - 1000 - - - # LocalEngineExecutionLimit # - 30 - 500 - - diff --git a/dundee-conf/settings/MafftParameters.xml b/dundee-conf/settings/MafftParameters.xml deleted file mode 100644 index 74fc854..0000000 --- a/dundee-conf/settings/MafftParameters.xml +++ /dev/null @@ -1,237 +0,0 @@ - - - compbio.runner.mafft.Mafft - - Shared 6mers distance calculation - Distance is calculated based on the number of shared 6mers. Default: on - --6merpair - http://www.compbio.dundee.ac.uk/users/pvtroshin/ws/Index.html - --6merpair - - - Output sequences order - --inputorder - Output order: same as input. - --reorder - Output order: aligned. Default: same as input - --inputorder - --reorder - http://www.compbio.dundee.ac.uk/users/pvtroshin/ws/Index.html - --inputorder - - - Sequence type - - --nuc - Assume the sequences are nucleotide. - --amino - Assume the sequences are amino acid. - --amino - --nuc - --auto - http://www.compbio.dundee.ac.uk/users/pvtroshin/ws/Index.html - --auto - - - Pairwise alignment computation method - - --globalpair - All pairwise alignments are computed with the Needleman-Wunsch algorithm. More accurate but slower than --6merpair. Suitable for a set of globally alignable sequences. Applicable to up to ~200 sequences. A combination with --maxiterate 1000 is recommended (G-INS-i). Default: off (6mer distance is used) - --genafpair - All pairwise alignments are computed with a local algorithm with the generalized affine gap cost (Altschul 1998). More accurate but slower than --6merpair. Suitable when large internal gaps are expected. Applicable to up to ~200 sequences. A combination with --maxiterate 1000 is recommended (E-INS-i). Default: off (6mer distance is used) - --fastapair - All pairwise alignments are computed with FASTA (Pearson and Lipman 1988). FASTA is required. Default: off (6mer distance is used) - --localpair - All pairwise alignments are computed with the Smith-Waterman algorithm. More accurate but slower than --6merpair. Suitable for a set of locally alignable sequences. Applicable to up to ~200 sequences. A combination with --maxiterate 1000 is recommended (L-INS-i). Default: off (6mer distance is used) - - --fastapair - --genafpair - --localpair - --globalpair - http://www.compbio.dundee.ac.uk/users/pvtroshin/ws/Index.html - --localpair - - - FFT approximation - Use / Do not use FFT approximation in group-to-group alignment. Default: off - --nofft - --fft - http://www.compbio.dundee.ac.uk/users/pvtroshin/ws/Index.html - --nofft - - - No score - Alignment score is not checked in the iterative refinement stage. Default: off (score is checked) - --noscore - http://www.compbio.dundee.ac.uk/users/pvtroshin/ws/Index.html - - - Part tree - - --parttree - Use a fast tree-building method (PartTree, Katoh and Toh 2007) with the 6mer distance. - --dpparttree - the PartTree algorithm is used with distances based on DP. - Slightly more accurate and slower than --parttree. - --fastaparttree - The PartTree algorithm is used with distances based on FASTA. - Slightly more accurate and slower than --parttree. - All methods recommended for a large number (> ~10,000) of sequences are input. - - --dpparttree - --parttree - --fastaparttree - http://www.compbio.dundee.ac.uk/users/pvtroshin/ws/Index.html - --fastaparttree - - - - Max iteration number - number cycles of iterative refinement are performed. Default: 0 - --maxiterate - http://www.compbio.dundee.ac.uk/users/pvtroshin/ws/Index.html - 0 - - Integer - 0 - 1000 - - - - Partsize - The number of partitions in the PartTree algorithm. Default: 50 - --partsize - http://www.compbio.dundee.ac.uk/users/pvtroshin/ws/Index.html - 50 - - Integer - 1 - - - - Group size - Do not make alignment larger than number sequences. Valid only with the --*parttree options. Default: the number of input sequences - --groupsize - http://www.compbio.dundee.ac.uk/users/pvtroshin/ws/Index.html - 20 - - Integer - 0 - - - - Guide tree rebuild - Guide tree is built number times in the progressive stage. Valid with 6mer distance. Default: 2 - --retree - http://www.compbio.dundee.ac.uk/users/pvtroshin/ws/Index.html - 2 - - Integer - 1 - 100 - - - - Gap opening penalty - Gap opening penalty at group-to-group alignment. Default: 1.53 - --op - http://www.compbio.dundee.ac.uk/users/pvtroshin/ws/Index.html - 1.53 - - Float - 0 - - - - Group-to-group gap extension penalty - Offset value, which works like gap extension penalty, for group-to-group alignment. Deafult: 0.123 - --ep - http://www.compbio.dundee.ac.uk/users/pvtroshin/ws/Index.html - 0.123 - - Float - 0 - - - - Gap opening penalty at local pairwise alignment - Gap opening penalty at local pairwise alignment. Valid when the --localpair or --genafpair option is selected. Default: -2.00 - --lop - http://www.compbio.dundee.ac.uk/users/pvtroshin/ws/Index.html - -2.00 - - Float - 0 - - - - Matrix - Substitution Matrix to use - --aamatrix - http://www.compbio.dundee.ac.uk/users/pvtroshin/ws/Index.html - BLOSUM62 - BLOSUM100 - BLOSUM30 - BLOSUM35 - BLOSUM40 - BLOSUM45 - BLOSUM50 - BLOSUM55 - BLOSUM60 - BLOSUM62 - BLOSUM65 - BLOSUM70 - BLOSUM75 - BLOSUM80 - BLOSUM85 - BLOSUM90 - BLOSUMN - DAYHOFF - GONNET - IDENTITY - MATCH - PAM10 - PAM100 - PAM110 - PAM120 - PAM130 - PAM140 - PAM150 - PAM160 - PAM170 - PAM180 - PAM190 - PAM20 - PAM200 - PAM210 - PAM220 - PAM230 - PAM240 - PAM250 - PAM260 - PAM270 - PAM280 - PAM290 - PAM30 - PAM300 - PAM310 - PAM320 - PAM330 - PAM340 - PAM350 - PAM360 - PAM370 - PAM380 - PAM390 - PAM40 - PAM400 - PAM410 - PAM420 - PAM430 - PAM440 - PAM450 - PAM460 - PAM470 - PAM480 - PAM490 - PAM50 - PAM500 - PAM60 - PAM70 - PAM80 - PAM90 - - diff --git a/dundee-conf/settings/MafftPresets.xml b/dundee-conf/settings/MafftPresets.xml deleted file mode 100644 index 794d20c..0000000 --- a/dundee-conf/settings/MafftPresets.xml +++ /dev/null @@ -1,62 +0,0 @@ - - - compbio.runner.mafft.Mafft - - L-INS-i (Accuracy-oriented) - L-INS-i (probably most accurate; recommended for <200 - sequences; iterative refinement method incorporating local pairwise - alignment information) - - - - - - - G-INS-i (Accuracy-oriented) - G-INS-i (suitable for sequences of similar lengths; - recommended for <200 sequences; iterative refinement method - incorporating global pairwise alignment information) - - - - - - - E-INS-i (Accuracy-oriented) - E-INS-i (suitable for sequences containing large - unalignable regions; recommended for <200 sequences) - - - - - - - - FFT-NS-i (Speed oriented) - FFT-NS-i (iterative refinement method; two cycles only) - - - - - - - FFT-NS-1 (Speed oriented) - FFT-NS-1 (very fast; recommended for >2000 sequences; - progressive method with a rough guide tree) - - - - - - - NW-NS-PartTree-1 (Speed oriented) - NW-NS-PartTree-1 (recommended for ~10,000 to ~50,000 - sequences; progressive method with the PartTree algorithm) - - - - - - - - diff --git a/dundee-conf/settings/MuscleLimits.xml b/dundee-conf/settings/MuscleLimits.xml deleted file mode 100644 index 043c458..0000000 --- a/dundee-conf/settings/MuscleLimits.xml +++ /dev/null @@ -1,13 +0,0 @@ - - - compbio.runner.muscle.Muscle - - 1000 - 1000 - - - # LocalEngineExecutionLimit # - 30 - 500 - - diff --git a/dundee-conf/settings/MuscleParameters.xml b/dundee-conf/settings/MuscleParameters.xml deleted file mode 100644 index 11c36d8..0000000 --- a/dundee-conf/settings/MuscleParameters.xml +++ /dev/null @@ -1,289 +0,0 @@ - - - compbio.runner.muscle.Muscle - - Group sequences - Group sequences by similarity (this is the default) or preserve the input order - -group - -stable - http://www.compbio.dundee.ac.uk/users/pvtroshin/ws/Index.html - -stable - - - Anchor optimisation - Enable/disable anchor optimization in tree dependent refinement iterations - -anchors - -noanchors - http://www.compbio.dundee.ac.uk/users/pvtroshin/ws/Index.html - -anchors - - - Root alignment computation method - Use Steven Brenner's method for computing the root alignment. - -brenner - http://www.compbio.dundee.ac.uk/users/pvtroshin/ws/Index.html - - - - dimer - Use dimer approximation for the SP score (faster, slightly less accurate) - -dimer - http://www.compbio.dundee.ac.uk/users/pvtroshin/ws/Index.html - - - Diagonal - Use diagonal optimizations. Faster, especially for closely related sequences, but may be less accurate. - -diags - - - Diagonal 1 - Use diagonal optimizations in first iteration (faster for similar sequences) - -diags1 - - - Profile scoring method - le - use log-expectation profile score VTML240 (default for amino acid sequences.) - sp - use sum-of-pairs protein profile score (PAM200). - sv - use sum-of-pairs profile score (VTML240) - -le - -sp - -sv - http://www.compbio.dundee.ac.uk/users/pvtroshin/ws/Index.html - -le - - - - Sequence type - Sequence type - Amino acid/Nucleotide - -seqtype - http://www.compbio.dundee.ac.uk/users/pvtroshin/ws/Index.html - auto - auto - protein - nucleo - - - Maxiters - Maximum number of iterations (integer, default 16) - -maxiters - http://www.compbio.dundee.ac.uk/users/pvtroshin/ws/Index.html - 16 - - Integer - 1 - 100 - - - - Matrix - Substitution Matrix to use - -matrix - http://www.compbio.dundee.ac.uk/users/pvtroshin/ws/Index.html - BLOSUM62 - BLOSUM100 - BLOSUM30 - BLOSUM35 - BLOSUM40 - BLOSUM45 - BLOSUM50 - BLOSUM55 - BLOSUM60 - BLOSUM62 - BLOSUM65 - BLOSUM70 - BLOSUM75 - BLOSUM80 - BLOSUM85 - BLOSUM90 - BLOSUMN - DAYHOFF - GONNET - IDENTITY - MATCH - NUC.4.2 - NUC.4.4 - PAM10 - PAM100 - PAM110 - PAM120 - PAM130 - PAM140 - PAM150 - PAM160 - PAM170 - PAM180 - PAM190 - PAM20 - PAM200 - PAM210 - PAM220 - PAM230 - PAM240 - PAM250 - PAM260 - PAM270 - PAM280 - PAM290 - PAM30 - PAM300 - PAM310 - PAM320 - PAM330 - PAM340 - PAM350 - PAM360 - PAM370 - PAM380 - PAM390 - PAM40 - PAM400 - PAM410 - PAM420 - PAM430 - PAM440 - PAM450 - PAM460 - PAM470 - PAM480 - PAM490 - PAM50 - PAM500 - PAM60 - PAM70 - PAM80 - PAM90 - - - Gap open penalty - Gap opening penalty. Must be negative - -gapopen - http://www.compbio.dundee.ac.uk/users/pvtroshin/ws/Index.html - -12.0 - - Float - -100 - 0 - - - - Gap extension penalty - Gap extension penalty. Must be negative - -gapextend - http://www.compbio.dundee.ac.uk/users/pvtroshin/ws/Index.html - -1.0 - - Float - -100 - 0 - - - - Center - Center parameter. Should be negative. - -center - http://www.compbio.dundee.ac.uk/users/pvtroshin/ws/Index.html - 0.0 - - Float - -100 - 0 - - - - Hydro - Window size for determining whether a region is hydrophobic. - -hydro - http://www.compbio.dundee.ac.uk/users/pvtroshin/ws/Index.html - 5 - - Integer - 0 - 100 - - - - Hydrofactor - Multiplier for gap open/close penalties in hydrophobic regions. - -hydrofactor - http://www.compbio.dundee.ac.uk/users/pvtroshin/ws/Index.html - 1.2 - - Float - 0 - 10 - - - - cluster1 - Clustering method to use on the iteration 1 - -cluster1 - http://www.compbio.dundee.ac.uk/users/pvtroshin/ws/Index.html - upgma - upgma - - - cluster2 - Clustering method to use on the iteration 2 and all subsequent itarations - -cluster2 - http://www.compbio.dundee.ac.uk/users/pvtroshin/ws/Index.html - upgmb - upgmb - neighborjoining - - - Sequence weighting scheme 1 - Sequence weighting scheme to use on the iteration 1 and 2 - none=all sequences have equal weight. - henikoff=Henikoff & Henikoff weighting scheme. - henikoffpb=Modified Henikoff scheme as used in PSI-BLAST. - clustalw=CLUSTALW method. - threeway=Gotoh three-way method - -weight1 - http://www.compbio.dundee.ac.uk/users/pvtroshin/ws/Index.html - clustalw - none - henikoff - henikoffpb - gsc - clustalw - threeway - - - Sequence weighting scheme 2 - Sequence weighting scheme to use on the iteration 3 and all subsequent - iterations for tree-dependent refinement. - none=all sequences have equal weight. - henikoff=Henikoff & Henikoff weighting scheme. - henikoffpb=Modified Henikoff scheme as used in PSI-BLAST. - clustalw=CLUSTALW method. - threeway=Gotoh three-way method - -weight2 - http://www.compbio.dundee.ac.uk/users/pvtroshin/ws/Index.html - clustalw - none - henikoff - henikoffpb - gsc - clustalw - threeway - - - Distance1 - Distance measure for iteration 1. Defaults Kmer6_6 (for amino ) or Kmer4_6 (for nucleo) - -distance1 - http://www.compbio.dundee.ac.uk/users/pvtroshin/ws/Index.html - kmer6_6 - kmer6_6 - kmer20_3 - kbit20_3 - kmer20_4 - kmer4_6 - - diff --git a/dundee-conf/settings/MusclePresets.xml b/dundee-conf/settings/MusclePresets.xml deleted file mode 100644 index 190adad..0000000 --- a/dundee-conf/settings/MusclePresets.xml +++ /dev/null @@ -1,31 +0,0 @@ - - - compbio.runner.muscle.Muscle - - Protein alignment(Fastest speed) - Fastest possible speed for protein sequences. Gives acceptable quality alignments for closely related sequences - - - - - - - - - Nucleotide alignment(Fastest speed) - Fastest possible speed for nucleotide sequences. Gives acceptable quality alignments for closely related sequences - - - - - - - Huge alignments (speed-oriented) - Very large number of sequences (several thousand), or they are very long, - - - - - - - diff --git a/dundee-conf/settings/ProbconsLimits.xml b/dundee-conf/settings/ProbconsLimits.xml deleted file mode 100644 index 96c8b31..0000000 --- a/dundee-conf/settings/ProbconsLimits.xml +++ /dev/null @@ -1,13 +0,0 @@ - - - compbio.runner.probcons.Probcons - - 1000 - 1000 - - - # LocalEngineExecutionLimit # - 30 - 500 - - diff --git a/dundee-conf/settings/ProbconsParameters.xml b/dundee-conf/settings/ProbconsParameters.xml deleted file mode 100644 index aa8ef07..0000000 --- a/dundee-conf/settings/ProbconsParameters.xml +++ /dev/null @@ -1,147 +0,0 @@ - - - compbio.runner.probcons.Probcons - - - Output aligned - Output sequences in alignment order rather than input order - -a - http://www.compbio.dundee.ac.uk/users/pvtroshin/ws/Index.html - - - - - Rounds of pre-training before aligning the sequences - This specifies the number of rounds of EM to be applied on the set of sequences being -aligned. This option is used in case the default parameters are not appropriate for the -particular sequences being aligned; in general, this option is not recommended as it may -lead to unstable alignment parameters. - -pre - http://www.compbio.dundee.ac.uk/users/pvtroshin/ws/Index.html - 0 - - Integer - 0 - 20 - - - - Passes of iterative refinement - This specifies the number of iterations of iterative refinement to be performed. In each -stage of iterative refinement, the set of sequences in the alignment is randomly -partitioned into two groups. After projecting the alignments to these groups, the two -groups are realigned, resulting in an alignment whose objective score is guaranteed to be -at least that of the original alignment - -ir - http://www.compbio.dundee.ac.uk/users/pvtroshin/ws/Index.html - 100 - - Integer - 0 - 1000 - - - - Passes of consistency transformation - Each pass applies one round of the consistency transformation on the set of sequences. - The consistency transformation is described in detail in the mentioned papers. In each - round, the aligner computes the consistency transformation for each pair of sequences - using all other sequences. The aligner then updates the posterior probability matrices of - the pairwise alignments. - -c - http://www.compbio.dundee.ac.uk/users/pvtroshin/ws/Index.html - 2 - - Integer - 0 - 5 - - - diff --git a/dundee-conf/settings/TcoffeeLimits.xml b/dundee-conf/settings/TcoffeeLimits.xml deleted file mode 100644 index 9776d7b..0000000 --- a/dundee-conf/settings/TcoffeeLimits.xml +++ /dev/null @@ -1,13 +0,0 @@ - - - compbio.runner.tcoffee.Tcoffee - - 1000 - 1000 - - - # LocalEngineExecutionLimit # - 30 - 500 - - diff --git a/dundee-conf/settings/TcoffeeParameters.xml b/dundee-conf/settings/TcoffeeParameters.xml deleted file mode 100644 index a18052f..0000000 --- a/dundee-conf/settings/TcoffeeParameters.xml +++ /dev/null @@ -1,367 +0,0 @@ - - - compbio.runner.tcoffee.Tcoffee - - Search sequences in PDB - - Forces t_coffee to run extract_from_pdb to check the pdb status of each sequence. - This can considerably slow down the program. - - -check_pdb_status - http://www.compbio.dundee.ac.uk/users/pvtroshin/ws/Index.html - - = - - - Preset Mode - It indicates that t_coffee will use some hard coded parameters. These include: - quickaln: Very fast, sequence type - all, accuracy - medium low - - http://www.compbio.dundee.ac.uk/users/pvtroshin/ws/Index.html - -mode - quickaln - quickaln - - - - - Distance matrix computation method - - This flag indicates the method used for computing the distance matrix (distance between every pair of sequences) required for the computation of the dendrogram. - Slow The chosen dp_mode using the extended library, - fast: The fasta dp_mode using the extended library. - very_fast The fasta dp_mode using blosum62mt. - ktup Ktup matching (Muscle kind) - aln Read the distances on a precomputed MSA - -distance_matrix_mode - http://www.compbio.dundee.ac.uk/users/pvtroshin/ws/Index.html - very_fast - slow - fast - very_fast - ktup - aln - - - Tree Computation method - - gotoh_pair_wise: implementation of the gotoh algorithm (quadratic in memory and time) - myers_miller_pair_wise: implementation of the Myers and Miller dynamic programming algorithm ( quadratic in time and linear in space). This algorithm is recommended for very long sequences. It is about 2 times slower than gotoh and only accepts tg_mode=1or 2 (i.e. gaps penalized for opening). - fasta_pair_wise: implementation of the fasta algorithm. The sequence is hashed, looking for ktuples words. Dynamic programming is only carried out on the ndiag best scoring diagonals. This is much faster but less accurate than the two previous. This mode is controlled by the parameters -ktuple, -diag_mode and -ndiag - cfasta_pair_wise: c stands for checked. It is the same algorithm. The dynamic programming is made on the ndiag best diagonals, and then on the 2*ndiags, and so on until the scores converge. Complexity will depend on the level of divergence of the sequences, but will usually be L*log(L), with an accuracy comparable to the two first mode ( this was checked on BaliBase). This mode is controlled by the parameters -ktuple, -diag_mode and -ndiag - - -dp_mode - http://www.compbio.dundee.ac.uk/users/pvtroshin/ws/Index.html - cfasta_pair_wise - gotoh_pair_wise - myers_miller_pair_wise - fasta_pair_wise - cfasta_pair_wise - - - - Number of diagonals used by the fasta_pair_wise algorithm - - Indicates the number of diagonals used by the fasta_pair_wise algorithm (cf -dp_mode). When -ndiag=0, n_diag=Log (length of the smallest sequence)+1. - When -ndiag and -diag_threshold are set, diagonals are selected if and only if they fulfill both conditions. - - -ndiag - http://www.compbio.dundee.ac.uk/users/pvtroshin/ws/Index.html - 0 - - Integer - 0 - 1000 - - - - Number of diagonals used by the fasta_pair_wise algorithm - - Indicates the manner in which diagonals are scored during the fasta hashing. -0: indicates that the score of a diagonal is equal to the sum of the scores of the exact matches it contains. -1 indicates that this score is set equal to the score of the best uninterrupted segment (useful when dealing with fragments of sequences). - - -diag_mode - http://www.compbio.dundee.ac.uk/users/pvtroshin/ws/Index.html - 0 - 0 - 1 - - - Diagonal threshold - - Sets the value of the threshold when selecting diagonals. - 0: indicates that -ndiag should be used to select the diagonals (cf -ndiag section). - - -diag_threshold - http://www.compbio.dundee.ac.uk/users/pvtroshin/ws/Index.html - 0 - - Integer - 0 - 1000 - - - - Alphabet degeneration method - - Indicates the manner in which the amino acid alphabet is degenerated when hashing in the - fasta_pairwise dynamic programming. Standard ClustalW matrices are all valid. - They are used to define groups of amino acids having positive substitution values. - In T-Coffee, the default is a 13 letter grouping named Vasiliky, with residues grouped as follows: - rk, de, qh, vilm, fy (other residues kept alone). - This alphabet is set with the flag -sim_matrix=vasiliky. - In order to keep the alphabet non degenerated, -sim_matrix=idmat can be used to retain - the standard alphabet. - - -sim_matrix - http://www.compbio.dundee.ac.uk/users/pvtroshin/ws/Index.html - vasiliky - vasiliky - idmat - - - Substitution Matrix - -This flag sets the matrix that will be used by alignment methods within t_coffee (slow_pair, lalign_id_pair). It does not affect external methods (like clustal_pair, clustal_aln). -Users can also provide their own matrices, using the matrix format described in the appendix. - - -matrix - http://www.compbio.dundee.ac.uk/users/pvtroshin/ws/Index.html - blosum62mt - - - - - Match penalty - - Indicates the penalty to associate with a match. When using a library, - all matches are positive or equal to 0. Matches equal to 0 are unsupported by the - library but non-penalized. Setting nomatch to a non-negative value makes it possible - to penalize these null matches and prevent unrelated sequences from being aligned - (this can be useful when the alignments are meant to be used for structural modeling) - -nomatch - http://www.compbio.dundee.ac.uk/users/pvtroshin/ws/Index.html - 0 - - Integer - 0 - 1000 - - - - Gap opening penalty - - Indicates the penalty applied for opening a gap. The penalty must be negative. - If no value is provided when using a substitution matrix, a value will be automatically computed. - Here are some guidelines regarding the tuning of gapopen and gapext. - In T-Coffee matches get a score between 0 (match) and 1000 (match perfectly consistent with the library). - The default cosmetic penalty is set to -50 (5% of a perfect match). - If you want to tune -gapoen and see a strong effect, you should therefore consider values between 0 - and -1000. - - -gapopen - http://www.compbio.dundee.ac.uk/users/pvtroshin/ws/Index.html - 0 - - Integer - -1000 - 0 - - - - Gap extension penalty - - Indicates the penalty applied for extending a gap. The penalty must be negative. - - -gapext - http://www.compbio.dundee.ac.uk/users/pvtroshin/ws/Index.html - 0 - - Integer - -1000 - 0 - - - - Cosmetic penalty - - Indicates the penalty applied for opening a gap. The penalty must be negative and is set to a very low value by default. - It will only have an influence on the portions of the alignment that are unalignable. - It will not make them more correct, but only more pleasing to the eye ( i.e. Avoid stretches - of lonely residues). The cosmetic penalty is automatically turned off if a substitution matrix is - used rather than a library. - - -cosmetic_penalty - http://www.compbio.dundee.ac.uk/users/pvtroshin/ws/Index.html - -50 - - Integer - -1000 - 0 - - - - Terminal gaps penalty - - 0: terminal gaps penalized with -gapopen + -gapext*len - 1: terminal gaps penalized with a -gapext*len - 2: terminal gaps unpenalized. - - -tg_mode - http://www.compbio.dundee.ac.uk/users/pvtroshin/ws/Index.html - 1 - 0 - 1 - 2 - - - Number of iterations - - Sequences are extracted in turn and realigned to the MSA. - If iterate is set to -1, each sequence is realigned, otherwise the number of iterations is - set by -iterate. - - -iterate - http://www.compbio.dundee.ac.uk/users/pvtroshin/ws/Index.html - 0 - - Integer - -1 - 100 - - - - Output order - - Sets the order of the sequences in the output alignment: -outorder=input means the sequences - are kept in the original order. -outorder=aligned means the sequences come in the order - indicated by the tree. This order can be seen as a one-dimensional projection of the tree distances. - - -outorder - http://www.compbio.dundee.ac.uk/users/pvtroshin/ws/Index.html - input - input - aligned - - - Input order - - Multiple alignments based on dynamic programming depend slightly on the order in which - the incoming sequences are provided. To prevent this effect sequences are arbitrarily - sorted at the beginning of the program (-inorder=aligned). - However, this affects the sequence order within the library. - You can switch this off by setting -inorder=input - - -inorder - http://www.compbio.dundee.ac.uk/users/pvtroshin/ws/Index.html - aligned - input - aligned - - diff --git a/dundee-conf/settings/TcoffeePresets.xml b/dundee-conf/settings/TcoffeePresets.xml deleted file mode 100644 index 585bb21..0000000 --- a/dundee-conf/settings/TcoffeePresets.xml +++ /dev/null @@ -1,54 +0,0 @@ - - - compbio.runner.tcoffee.Tcoffee - - Quick align. Very fast approximate (Speed-oriented) - quickaln: Very fast, sequence type - all, accuracy - medium low - - - - - - - - diff --git a/website/develhome.html b/website/develhome.html index 1053faf..0d5fbdf 100644 --- a/website/develhome.html +++ b/website/develhome.html @@ -12,12 +12,17 @@
+
@@ -44,7 +49,7 @@ The repository contains a complete JABAWS Eclip

A client package contains only classes from data model layer and a simple web services client. Framework package is for anyone who want to use JABAWS framework for controlling native executables in local or cluster environments. Framework exclude the web services layer. Server package contains all the code.

Running tests

-

The test results for the JABAWS package offered for download can be found here: Test Results
+

The test results for the JABAWS package offered for download can be found here: Test Results
JABAWS uses TestNG for testing. There is a TestNG plugin available for Eclipse which has functionality similar to JUnit. However, no plugins are necessary to run the test cases, as testng jar is supplied with JABAWS together with an ant tasks to run the test cases.

The best way to ensure that JABAWS framework is completely functional on your system is to run all test cases. Test cases tests all aspects of JABAWS functionality. Consequently, one need to have non windows operation system and support of the cluster to be able to run all tests. If your system does not support cluster, then you could run all test excluding those that depends on the cluster. @@ -103,10 +108,20 @@ Several testing groups are supported:

JABAWS are the standard JAX-WS web services, which are WS-I basic profile compatible.

- +
- + + + diff --git a/website/download.html b/website/download.html index 95037c8..beca92b 100644 --- a/website/download.html +++ b/website/download.html @@ -1,83 +1,172 @@ - + - -Java Bioinformatics Analysis Web Services (JABAWS) download page + + +Java Bioinformatics Analysis Web Services (JABAWS) download +page - - +
+ + + + +

JAva Bioinformatics Analysis Web Services

+ +
-
- Home - Manual - How To - Download - Jalview + +
-

JABAWS Client

-

-For anyone who would like to program against JABA Web Services or use a command line client. -Download (64k)

+ +

The client is an executable java archive which provides a +command line client, and can be used by anyone who would like to +program against the JABA Web Services in Java.

+ +

JABAWS Server

-

-Download this if you intend to run JABAWS for your lab/university locally. + +

The server is provided as a self-contained web application +archive containing all necessary binaries, ready to install in any +'modern' Java based web application server +. Download this +if you intend to run JABAWS services locally.

+
    -
  • A Complete Server for all platforms: download (45M)
    • -
  • A Complete Server for windows: download (16M)
    • +
  • A Complete Server for all platforms: download +(45M)
    • + +
  • A Complete Server for windows: download +(16M)
-

+
- + +
+
+
+ + +
+ + +
+ + +
- - - - + + + + + + diff --git a/website/howto.html b/website/howto.html index 3d58b8c..cc01084 100644 --- a/website/howto.html +++ b/website/howto.html @@ -18,8 +18,13 @@
- + + + +
+ + + + + + + diff --git a/website/manual.html b/website/manual.html index 91b0778..2ce3903 100644 --- a/website/manual.html +++ b/website/manual.html @@ -1,205 +1,524 @@ - + - -Java Bioinformatics Analyses Web Services (JABAWS) manual - - - - + + +Java Bioinformatics Analyses Web Services (JABAWS) +manual + + +
+ + + + +

JAva Bioinformatics Analysis Web Services

+
-
- Home - Manual - How To - Download - Jalview + +
- -

JABAWS Manual

+

JABAWS Installation

-

JABA web services require Java 6 to function. We recommend using Sun Java Virtual Machine. JABAWS can be deployed on any Servlet 2.4 compatible web application server. We have tested JABA on the Apache-Tomcat version 6 web application container, however, version 5.5 should do as well. To deploy JABAWS follow your web application server specific deployment procedures. For Apache-Tomcat just drop the war file into webapps directory. Tomcat will do the rest. At this point you should have JABA web services up and running on windows machines. There are more steps to do if you are deploying JABAWS on other operation systems.

-

JABA web services depend on the alignment programs to do the actual alignment, so it must have an access to the alignment programs which can be executed on your platform. JABAWS is bundled with native windows executables, native Linux i386 executables, and the source code for all alignment programs JABAWS wraps. If you are installing it on Linux should not worry about installing the alignment programmes, the ones that comes with JABAWS should work. For any other operation systems you need to make the alignment programs available to JABAWS.

-

If you are installing on Linux it may be just a matter of setting executable flag for the binaries bundled with JABAWS. There is a script which would help you with that. To use it cd to <webapplicationpath>/binaries/src and run sh setexecflag.sh script. Restart the Tomcat. That is it JABAWS should work at this point. If not read on... or have a look at deploying on Tomcat tips. You may want to enable logging, see below how to do that.

-

Making Alignment Programs Available to JABAWS

-

There are three possible solutions for this problem

-
    -
  • Reuse the binaries that are already have in your system
    • -
  • Use bundled with JABAWS alignment programs
    • -
  • Obtain the alignment programs for your OS elsewhere
    • -
-

They are described in greater details below

-

If you would like to use the binaries you already have

-

Than you just need to let JABAWS know there they are. For this edit conf/Executable.properties file. Please provide an absolute path to each executable in your system. For example default path for clustalw executable is defined as local.clustalw.bin=binaries/src/clustalw/src/clustalw2 replace it with absolute path to executable in your system. Instead of changing Executable.properties you could replace executables bundled with JABAWS with the once you have. Then the default configuration will work for you. If you like to find out more about Executable.properties file see below.

-

If you would like to use bundled with JABAWS alignment programs

+ +
System Requirements
+ +

JABAWS requires a java web application server compliant with +version 2.4 of the java servlet specification, and a java 6 runtime +environment. We recommend using an official Sun Java 6 runtime +environment, but others may work. We have tested JABAWS with Apache-Tomcat +version 6, however we expect it will also be compatible with version +5.5.

+ + +
Installing the JABAWS WAR file
+ +

JABAWS is distributed as a web application archive (WAR). To +deploy JABAWS in Apache-Tomcat - simply drop the war file into the +webapps directory of a running +Tomcat, and it will do the rest. For any other web application +server, please follow your server's specific deployment procedure +for 'WAR' files. If you are installing on a windows machine, then +at this point your JABAWS installation will already be up and +running, and you can try its services out using the JABAWS test client, but +installations on other operating systems will require a final step +to ensure JABAWS can locate and execute the binary programs it +needs.

+ +

Preparing executables for use with JABAWS

+ +

JABAWS's web services use command line programs to do +the actual analysis, so it must have access to programs +which can be executed on your platform. The native executables +bundled with JABAWS for Windows (32-bit) and Linux (i386) should be +OK for those systems. However, the source code for these +programs is also provided so you can recompile for your own +architecture and exploit any optimisations that your system can +provide. Alternately, if you have already got binaries on your +system, then you can simply change the paths in JABAWS's +configuration files so these are used instead.

+ +
Using the pre-compiled i386 binaries on Linux
+ +

Before the binaries that are bundled with JABAWS can be used, +they must first be made executable using the provided 'setexecflag.sh' script:

+
    -
  1. Set executable flag for binaries. For this you could use the script provided. cd to binaries/src
    - run setexecflag.sh script.
    2. -
  2. Make sure binaries supplied work under your OS. For this run each binary. You do not need any input or flags. If you see a error message complaining about missing libraries or other problems with an executable itself rather than with an input, you need to (a) recompile the binary. -
      -
    • To recompile all the binaries for your system you could use a script supplied with the JABAWS.
      - For this cd to folder binaries/src execute script compilebin.sh - (either chmod +x it or sh compilebin.sh)
      • -
    • Makes sure everything compiled and work
      - correctly performing first part of a step 2 again.
      • -
    • If not everything compiled then, it may be that your system does not have all the tools required for recompilation. At a very least check that you have gcc, g++ and make installed in your system. If not install these packages and repeat step (a).
      • -
    • If compilation fails with unclear reason, try obtaining the pre compiled binaries for your OS
      • -
    -
    3. -
  3. Consider recompiling all binaries for your platform, this is likely to give you a performance increase.
    4. +
  4. cd to <webapplicationpath>/binaries/src
    5. + +
  5. run sh setexecflag.sh
    6. + +
  6. Make sure binaries supplied work under your OS.
    + For this run each binary, without any command line options or +input files. If you see an error message complaining about missing +libraries or other problems, then you probably need to recompile the binaries. with
    7. + +
  7. Restart the Tomcat.
-

Obtain alignment program for your operation system elsewhere

-

You could search for pre-packaged compiled executable in your system package repository or try downloading compiled version from alignment program's home page. Then, executables supplied with the system can be replaced with downloaded or new path to the executable can be defined in executable.properties as described above.

-

Default JABA Web Services Configuration

-

By default JABAWS configured with local engine enabled and an output directory called "jobsout" within web application itself. This will give you a working copy of JABAWS straight after the deployment. You may be interested to know what is the the war file.

-

JABAWS Configuration Details

-There are three part of the system you can configure. The local and cluster engines and individual executables. + +That's it! JABAWS should work at this point. Try it out using theJABAWS test client. If not, +read on... or have a look at deploying on Tomcat tips.
+ Note: You may want to enable logging, see +below for instructions on how to do that.
+ + +
Recompiling the bundled +programs for your system
+ +

If you have a fully equipped build environment on your +(POSIX-like) system, then you should be able to recompile the +programs from the source distributions which are included +in the JABAWS war file. A script called 'compilebin.sh' is provided +to automate this task.

+ +
    +
  1. In a terminal window, change the working directory to binaries/src
    2. + +
  2. execute the compilebin.sh +script,
    + either use: chmod +x compilebin.sh; +compilebin.sh > compilebin.out;
    + or: sh compilebin.sh > +compilebin.out
    3. + +
  3. Now run sh setexecflag.sh
    + If any of the binaries was not recompiled, then a 'file not found' +error will be raised.
    4. + +
  4. Finally, restart your tomcat (or servlet container), and use +the JABAWS test client to +check that JABAWS can use the new binaries.
    5. +
+ +

If you couldn't compile everthing, then it may be that your system does +not have all the tools required for compiling the programs. At the very +least check that you have gcc, g++ and make installed in your +system. If not install these packages and repeat the compilation +steps again. You should also review the compilebin.sh output - +which was redirected to compilebin.out, and any errors output to +the terminal. Finally, try obtaining the pre +compiled binaries for your OS.

+ +
Reuse the binaries that are +already in your system
+ +

If you would like to use the binaries you already have then you +just need to let JABAWS know there they are. To do this, edit: +conf/Executable.properties +

When specifying paths to executables that already exist on your system, make sure you provide an absolute path, or one relative to the JABAWS directory inside webapps. For example, the default path for clustalw is defined +aslocal.clustalw.bin=binaries/src/clustalw/src/clustalw2 +Alternatively, instead of changing Executable.properties you could also replace +the executables bundled with JABAWS with the ones that you have, or make symlinks to them. +Then the default configuration will work for you. More information +about the +Executable.properties file is given below.

+ +
Obtaining alignment +programs for your operation system from elsewhere
+ +

You could search for pre-packaged compiled executable in your +system package repository or alternately, download pre-compiled +binaries from each alignment program's home page. Then, either +replace the executables supplied with the downloaded ones, or +modify the paths in executable.properties as described above.

+ +

Configuring JABAWS

+ +

There are three parts of the system you can configure. The local +and cluster engines, and the paths to individual executables for +each engine. These settings are stored in configuration files +within the web application directory (for an overview, then take a +look at the war file content table).

+ +
Default JABA Web Services Configuration
+ +

Initially, JABAWS is configured with only the local engine +enabled, with job output written to directory called "jobsout" +within the web application itself. This means that JABAWS will work +out of the box, but may not be suitable for serving a whole lab or +instute.

+

Local Engine Configuration

-

-Local engine configuration is achieved by changing settings in the properties file conf/Engine.local.properties. -Supported configuration settings are: -
-engine.local.enable=true - # enable or disable local engine, valid values true | false -
-local.tmp.directory=D:\\clusterengine\\testoutput - a directory to use for temporary files storage, optional, defaults to java temporary directory -
-engine.local.thread.number=4 - Number of threads for tasks execution (valid values between 1 and 2x cpu. Where x is a number of cores available in the system). Optional defaults to the number of cores for core number <=4 and number of cores-1 for greater core numbers.

-

If you are planning to use local engine (which you have to if you do not have a cluster) it is a good idea to increase the amount of memory available for the web application server. Apache-Tomcat will be happy to take its memory settings from JAVA_OPTS environmental variable. We would recommend using Sun Java Virtual Machine (JVM) in preference to Open JDK. To specify which JVM to use for Apache-Tomcat just define a JAVA_HOME environmental variable. Below is an example of code which can be added to <tomcat_dir>/bin/setenv.sh script to define which JVM to use and a memory settings for Tomcat server. Tomcat server startup script (catalina.sh) will execute setenv.sh on each server start automatically.
- export JAVA_HOME=/homes/ws-dev2/jdk1.6.0_17/
- export JAVA_OPTS="-server -Xincgc -Xms512m -Xmx1024m"

+ +

The Local execution engine configuration is defined in the +properties file conf/Engine.local.properties. The supported +configuration settings are:
+ engine.local.enable=true - # +enable or disable local engine, valid values true | false
+ local.tmp.directory=D:\\clusterengine\\testoutput +- a directory to use for temporary files storage, optional, +defaults to java temporary directory
+ engine.local.thread.number=4 - +Number of threads for tasks execution (valid values between 1 and +2x cpu. Where x is a number of cores available in the system). +Optional defaults to the number of cores for core number <=4 and +number of cores-1 for greater core numbers.

+ +

If you are planning to heavily use the local engine (which you +have to if you do not have a cluster) it is a good idea to increase +the amount of memory available for the web application server. If +you are using Apache-Tomcat, then you can define its memory +settings in the JAVA_OPTS environment variable. To specify which +JVM to use for Apache-Tomcat, put the full path to the JRE +installation in the JAVA_HOME environment variable (We would +recommend using Sun Java Virtual Machine (JVM) in preference to +Open JDK). Below is an example of code which can be added to <tomcat_dir>/bin/setenv.sh script +to define which JVM to use and a memory settings for Tomcat server. +Tomcat server startup script (catalina.sh) will execute setenv.sh on each server start +automatically.
+ export +JAVA_HOME=/homes/ws-dev2/jdk1.6.0_17/
+ export JAVA_OPTS="-server -Xincgc -Xms512m -Xmx1024m"

+

Cluster Engine Configuration

-

Supported configuration settings:
-engine.cluster.enable=true - # enable or disable local engine true | false, defaults to false -
-cluster.tmp.directory=/homes/clustengine/testoutput- a directory to use for temporary files storage. The value must be an absolute path to the temporary directory. Required. The value must be different from what is defined for local engine. This directory must be accessible from all cluster nodes.
-For the cluster engine to work SGE_ROOT and LD_LIBRARY_PATH environmental variable have to be defined. They tell the cluster engine where to find DRMAA libraries. These environmental variables should be defined on the web application server e.g.

+ +

Supported configuration settings:
+ engine.cluster.enable=true - # +enable or disable local engine true | false, defaults to +false
+ cluster.tmp.directory=/homes/clustengine/testoutput- +a directory to use for temporary files storage. The value must be +an absolute path to the temporary directory. Required. The value +must be different from what is defined for local engine. This +directory must be accessible from all cluster nodes.
+ For the cluster engine to work, the SGE_ROOT and LD_LIBRARY_PATH +environment variables have to be defined. They tell the cluster +engine where to find DRMAA libraries. These variables +should be defined when the web application server starts up, e.g.

+

SGE_ROOT=/gridware/sge
- LD_LIBRARY_PATH=/gridware/sge/lib/lx24-amd64

-

Finally, do not forget to configure executables for the cluster execution, they may be the same as for the local execution but may be different. Please refer to the executable configuration section for further details.

+ LD_LIBRARY_PATH=/gridware/sge/lib/lx24-amd64

+ +

Finally, do not forget to configure executables for the cluster +execution, they may be the same as for the local execution but may +be different. Please refer to the executable configuration section +for further details.

+

Executable Configuration

-

All executables, the binary multiple sequence alignment programs are configured in conf/Executable.properties file. Each executable configured with a number of options they are: - - local.X.bin.windows=<path to executable under windows system, optional> -
local.X.bin=<path to the executable under non-windows system, optional> -
cluster.X.bin=<path to the executable on the cluster, all cluster nodes must see it, optional> -
X.bin.env=<semicolon separated list of environmental variables for executable, use hash symbol as name value separator, optional> -
X.--aamatrix.path=<path to the directory containing substitution matrices, optional> -
X.presets.file=<path to the preset configuration file, optional > -
X.parameters.file=<path to the parameters configuration file, optional> -
X.limits.file=<path to the limits configuration file, optional> -
X.cluster.settings=<list of the cluster specific options, optional>

-

- Where X is a short executable wrapper class name.

-

Default JABAWS configuration includes path to local executables to be run by the local engine only, all cluster related settings are commened out, but they are there for you as example. Cluster engine is disabled by default. To configure executable for cluster execution uncomment the X.cluster settings and change them appropriately.
- For example a complete Mafft configuration may look like this: local.mafft.bin.windows= -
- local.mafft.bin=binaries/mafft -
cluster.mafft.bin=/homes/cengine/mafft -
mafft.bin.env=MAFFT_BINARIES#/homes/cengine/mafft;FASTA_4_MAFFT#/bin/fasta34; -
mafft.--aamatrix.path=binaries/matrices -
mafft.presets.file=conf/settings/MafftPresets.xml -
mafft.parameters.file=conf/settings/MafftParameters.xml -
mafft.limits.file=conf/settings/MafftLimits.xml -
mafft.cluster.settings=-q bigmem.q -l h_cpu=24:00:00 -l h_vmem=6000M -l ram=6000M -

Please not that relative paths must only be specified for the files that reside inside web application directory, all other paths must be supplied as absolute!

-

Unfortunately, it is unsafe to modify environmental variable values, thus you need to specify the absolute path to anything defined as environment variable.

-

If you are using JABAWS to submit jobs to the cluster (with cluster engine enabled), executables must be available from all cluster nodes the task can be sent to, also paths to the executables on the cluster e.g. cluster.<exec_name>.bin must be absolute.

-

Executables can be located anywhere in your system, they do not have to reside on the server as long as the web application server can access and execute them.

-

Cluster settings are treated as a black box, the system will just pass whatever is specified in this line directly to the cluster submission library. This is how DRMAA itself treats this settings. More exactly DRMAA JobTemplate.setNativeSpecification() function will be called.

-
Defining Environmental Variables for Executable
-

Environmental variables can be defined in property x.bin.env Where x is one of five executables supported by JABAWS. Several environmental variables can be specified in the same line. For example.
- mafft.bin.env=MAFFT_BINARIES#/homes/cengine/mafft;FASTA_4_MAFFT#/bin/fasta34;

-

The example above define two environmental variables with names MAFFT-BINARIES and FASTA_4_MAFFT and values /homes/cengine/mafft and /bin/fasta34 respectively. Semicolon is used as a separator between different environment variables whereas hash is used as a separator for name and value of the variable.

-

Configure JABAWS to Work with Mafft

-

If you use default configuration you do not need to read any further. The default configuration will work for you without any changes, however, if you want to install Mafft yourself then there is a couple of more steps to do.

-

Mafft executable needs to know the location of other files supplied with Mafft. In addition some Mafft functions depends on the fasta executable, which is not supplied with Mafft, but is a separate package. Mafft needs to know the location of fasta34 executable.

-

To let Mafft know where the other files from its package are change the value of MAFFT-BINARIES environmental variable. To let Mafft know where is the fasta34 executable set the value of FASTA_4_MAFFT environment variable to point to a location of fasta34 program. The latter can be added to the PATH variable instead. If you are using executables supplied with JABAWS, the path to Mafft binaries would be like <relative path to web application directory>/binaries/src/mafft/binaries and the path to fasta34 binary would be <relative path to web application directory>/binaries/src/fasta34/fasta34. You can specify the location of Mafft binaries as well as fasta34 program elsewhere by providing an absolute path to them. All these settings are defined in conf/Executable.properties file.

+ +

All the executable programs +are configured in conf/Executable.properties file. Each executable +is configured with a number of options. They are: local.X.bin.windows=<path to executable under windows +system, optional>
+ local.X.bin=<path to the executable under non-windows system, +optional>
+ cluster.X.bin=<path to the executable on the cluster, all +cluster nodes must see it, optional>
+ X.bin.env=<semicolon separated list of environment variables +for executable, use hash symbol as name value separator, +optional>
+ X.--aamatrix.path=<path to the directory containing +substitution matrices, optional>
+ X.presets.file=<path to the preset configuration file, optional +>
+ X.parameters.file=<path to the parameters configuration file, +optional>
+ X.limits.file=<path to the limits configuration file, +optional>
+ X.cluster.settings=<list of the cluster specific options, +optional>

+ +

Where X is a short executable wrapper class name.

+ +

Default JABAWS configuration includes path to local executables +to be run by the local engine only, all cluster related settings +are commened out, but they are there for you as example. Cluster +engine is disabled by default. To configure executable for cluster +execution uncomment the X.cluster settings and change them +appropriately.
+ For example a complete Mafft configuration may look like +this:local.mafft.bin.windows=
+ local.mafft.bin=binaries/mafft
+ cluster.mafft.bin=/homes/cengine/mafft
+ mafft.bin.env=MAFFT_BINARIES#/homes/cengine/mafft;FASTA_4_MAFFT#/bin/fasta34;
+ mafft.--aamatrix.path=binaries/matrices
+ mafft.presets.file=conf/settings/MafftPresets.xml
+ mafft.parameters.file=conf/settings/MafftParameters.xml
+ mafft.limits.file=conf/settings/MafftLimits.xml
+ mafft.cluster.settings=-q bigmem.q -l h_cpu=24:00:00 -l +h_vmem=6000M -l ram=6000M

+ +

Please not that relative paths must only be specified for the +files that reside inside web application directory, all other paths +must be supplied as absolute!

+ +

Furthermore, you should avoid using environment variables within the paths or options - since these will not be evaluated correctly. Instead, please explicitly +specify the absolute path to anything +normally evaluated from an environment variable at execution time.

+ +

If you are using JABAWS to submit jobs to the cluster (with +cluster engine enabled), executables must be available from all +cluster nodes the task can be sent to, also paths to the +executables on the cluster e.g. cluster.<exec_name>.bin must be +absolute.

+ +

Executables can be located anywhere in your system, they do not +have to reside on the server as long as the web application server +can access and execute them.

+ +

Cluster settings are treated as a black box, the system will +just pass whatever is specified in this line directly to the +cluster submission library. This is how DRMAA itself treats this +settings. More exactly DRMAA JobTemplate.setNativeSpecification() +function will be called.

+ +
Defining Environment Variables for +Executables
+ +

Environment variables can be defined in property x.bin.env Where x is +one of five executables supported by JABAWS. Several environment +variables can be specified in the same line. For example.
+ mafft.bin.env=MAFFT_BINARIES#/homes/cengine/mafft;FASTA_4_MAFFT#/bin/fasta34;

+ +

The example above defines two environment variables with names +MAFFT-BINARIES and FASTA_4_MAFFT and values /homes/cengine/mafft +and /bin/fasta34 respectively. Semicolon is used as a separator +between different environment variables whereas hash is used as a +separator for name and value of the variable.

+ +

Configure JABAWS to Work +with Mafft

+ +

If you use default configuration you do not need to read any +further. The default configuration will work for you without any +changes, however, if you want to install Mafft yourself then there +is a couple of more steps to do.

+ +

Mafft executable needs to know the location of other files +supplied with Mafft. In addition some Mafft functions depends on +the fasta executable, which is not supplied with Mafft, but is a +separate package. Mafft needs to know the location of fasta34 +executable.

+ +

To let Mafft know where the other files from its package are +change the value of MAFFT-BINARIES environment variables. To let +Mafft know where is the fasta34 executable set the value of +FASTA_4_MAFFT environment variable to point to a location of +fasta34 program. The latter can be added to the PATH variable +instead. If you are using executables supplied with JABAWS, the +path to Mafft binaries would be like <relative path to web application +directory>/binaries/src/mafft/binaries and the path to +fasta34 binary would be <relative path +to web application +directory>/binaries/src/fasta34/fasta34. You can specify +the location of Mafft binaries as well as fasta34 program elsewhere +by providing an absolute path to them. All these settings are +defined in conf/Executable.properties file.

+

Testing JABA Web Services

-

You can use a command line client (part of the client only package) to test you JABAWS installation as described here. If you downloaded a JABAWS server package, you can use <your_jaba_context_name>/WEB-INF/lib/jaba-client.jar to test JABAWS installation as described in how-to. If you downloaded the source code, then you could run a number of test suits defined in the build.xml ant build file.

- -

JABAWS Log Files

-

JABAWS can be configured to log what it is doing. This comes handy if you would like to see who is using your web services or need to chase some problems. JABAWS uses log4j to do the logging, the example of log4j configuration is bundled with JABAWS war file. You will find it in the /WEB-INF/classes/log4j.properties file. All the lines in this file are commented out. The reason why the logging is disabled by default it simple, log4j have to know the exact location where the log files should be stored. This is not known up until the deployment time. To enable the logging you need to define logDir property in the log4j.properties and uncomment section of the file which corresponds to your need. More information is given in the log4j.properties file itself. Restart the tomcat or the JABAWS web application to apply the settings.

-

After you have done this, assuming that you did not change the log4j.properties file yourself, you should see the application log file called activity.log. The amount of information logged can be adjusted using different logging levels, it is reduced in the following order of log levels TRACE, DEBUG, INFO, WARN, ERROR, FATAL.

-

If you would like to know who is using your services, you might want to enable tomcat access logging.

-

JABAWS War File Content

- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - + +

You can use a command line client (part of the client only +package) to test you JABAWS installation as described here. If you downloaded a JABAWS +server package, you can use <your_jaba_context_name>/WEB-INF/lib/jaba-client.jar +to test JABAWS installation as described in how-to. If you downloaded the source +code, then you could run a number of test suits defined in the +build.xml ant build file.

+ +

JABAWS Log Files

+ +

JABAWS can be configured to log what it is doing. This comes +handy if you would like to see who is using your web services or +need to chase some problems. JABAWS uses log4j to do the logging, +the example of log4j configuration is bundled with JABAWS war file. +You will find it in the /WEB-INF/classes/log4j.properties file. All the +lines in this file are commented out. The reason why the logging is +disabled by default it simple, log4j have to know the exact +location where the log files should be stored. This is not known up +until the deployment time. To enable the logging you need to +definelogDir property in the log4j.properties and uncomment section of +the file which corresponds to your need. More information is given +in the log4j.properties file +itself. Restart the tomcat or the JABAWS web application to apply +the settings.

+ +

After you have done this, assuming that you did not change the +log4j.properties file yourself, you should see the application log +file called activity.log. The +amount of information logged can be adjusted using different +logging levels, it is reduced in the following order of log levels +TRACE, DEBUG, INFO, WARN, ERROR, FATAL.

+ +

If you would like to know who is using your services, you might +want to enable tomcat access +logging.

+ +

JABAWS War File Content

+ +
DirectoryContent description
conf/ contains configuration files such as Executable.properties, Engine.local.properties, Engine.cluster.properties
conf/settingsContains individual executable description files. In particular XXXParameters.xml, XXXPresets.xml, XXXLimits.xml where XXX is the name of the executable
jobsout/Individual executables input, output and some other task related files are stored. (optional)
binaries/Directory contains native executables - alignment programs, windows binaries (optional)
binaries/srcContains source of native executables and Linux i386 binaries.
binaries/matricesSubstitution matrices
WEB-INFWeb application descriptor
WEB-INF/libWeb application libraries
WEB-INF/classeslog4j.properties - log configuration file (optional)
Help Pages
/ help pages, index.html is the starting page
dm_javadocjavadoc for JABAWS client (the link is available from How To pages)
prog_docsdocumentation for programmes that JABAWS uses
imagesimages referenced by html pages
+ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + +
DirectoryContent description
conf/contains configuration files such as Executable.properties, +Engine.local.properties, Engine.cluster.properties
conf/settingsContains individual executable description files. In particular +XXXParameters.xml, XXXPresets.xml, XXXLimits.xml where XXX is the +name of the executable
jobsout/Contains directories generated when running an individual executable. E.g. input and output files and some other task +related data. (optional)
binaries/Directory contains native executables - programs, +windows binaries (optional)
binaries/srcContains source of native executables and Linux i386 +binaries.
binaries/matricesSubstitution matrices
WEB-INFWeb application descriptor
WEB-INF/libWeb application libraries
WEB-INF/classeslog4j.properties - log configuration file (optional)
Help Pages
/help pages, index.html is the starting page
dm_javadocjavadoc for JABAWS client (the link is available from How To +pages)
prog_docsdocumentation for programmes that JABAWS uses
imagesimages referenced by html pages
+

 

- - -
-
+ + + + + + + + + + + diff --git a/website/print.css b/website/print.css index fbc3556..b6a9071 100644 --- a/website/print.css +++ b/website/print.css @@ -57,11 +57,12 @@ font-family:"Courier New", Courier, monospace; border: 1px dashed black; } + .box { - font-size-adjust:0.4; + font-size-adjust:0.5; color:black; background-color:#F5F5F5; - font-family:Verdana, Arial, Helvetica, sans-serif + font-family:Arial, Helvetica, sans-serif; font-style:normal; margin:1em 0; padding: 0.5em; @@ -173,7 +174,6 @@ color:#993333; } body { - margin: 1em; font-family:Arial, Helvetica, sans-serif; font-size: 9pt; background-color: white; diff --git a/website/template.html b/website/template.html index e13c0bb..3fdb7c9 100644 --- a/website/template.html +++ b/website/template.html @@ -12,8 +12,15 @@
+
diff --git a/website/ws.css b/website/ws.css index 99fa834..4208e7c 100644 --- a/website/ws.css +++ b/website/ws.css @@ -1,17 +1,11 @@ -#banner { - background-position:left bottom; - background-image:url("images/banner_bg.gif"); - background-repeat: repeat-x; - background-color:transparent; - padding: 0.1em; - text-align:center; - color:white; - /* 0.1em 0.1em 0.2em black - 0.1em 0.1em 0.05em black - */ -} +#banner { background-color:white; } +/* +See index.html banner commented out code for an example of use +.uniicon { overflow: hidden; display:inline; padding:0; margin:0; float:right; position:relative; top:1em; } +.uniicon a img {border:none;} +*/ #panel { width:150px; background:url("images/panel_bg.gif") repeat-y ; float:left; font-family:Verdana, Arial, Helvetica, sans-serif; } @@ -27,7 +21,7 @@ line-height:1em; } -#wrapper { background:url("images/panel_bg.gif") repeat-y left top; } +#wrapper { background:url("images/panel_bg.gif") repeat-y left top; } ul { list-style-type: circle; @@ -39,7 +33,6 @@ ul { line-height: 1em; padding:10px; color:#000000; - text-decoration:none; } #panel a:hover { @@ -83,12 +76,12 @@ font-family:"Courier New", Courier, monospace; } .box { - font-size-adjust:0.4; color:black; background-color:#F5F5F5; - font-family:Verdana, Arial, Helvetica, sans-serif + font-family:Arial, Helvetica, sans-serif; font-style:normal; margin:1em 0; + font-size:0.9em; padding: 0.5em; border: 1px solid black; display:block; @@ -97,17 +90,19 @@ font-family:"Courier New", Courier, monospace; .u { text-decoration: underline; } /* .headeru { text-shadow: #CCCCCC 15px -14px 2px;} font-size-adjust:+0.7 */ /*.headeru { text-shadow: 1px 0 black, 0 -1px black;} */ - .headeru { text-shadow: black 0.05em 0.05em 0.01em ;} +.headeru { text-shadow: black 0.05em 0.05em 0.01em ;} /* .headeru { border-bottom:1px solid white; } */ /* Table styles */ -table { + + +#wrapper table { border-collapse: collapse; border: 1px solid #666; margin: 20px 0 20px 0; width: 100%; } -th, td { +#wrapper th, #wrapper td { margin: 2px 4px 2px 4px; padding: 0 5px; text-align: left; @@ -115,24 +110,18 @@ th, td { border: 1px solid #666; } -table caption { +#wrapper table caption { font: 1.5em Georgia, "Times New Roman", Times, serif; padding: 1em; background-color: #9c9; } -.mainheader { - font: 1.5em Georgia, "Times New Roman", Times, serif; - background-color: #9c9; - text-align:center; - line-height:1em; -} -tr { +#wrapper tr { background-color: #eee; } -tr:nth-child(odd) { +#wrapper tr:nth-child(odd) { background-color: #ccc; } @@ -197,9 +186,40 @@ color:#993333; } body { - margin: 1em; font-family:Arial, Helvetica, sans-serif; font-size: 9pt; background-color: white; line-height: 2em; + min-width:35em; } + + +#banner table { + border-collapse: collapse; + border: none; + padding:0; + margin:0; + color:white; + text-align:center; + vertical-align:middle; + line-height:1.5em; + width: 100%; +} + +#banner td.bg { + border-collapse: collapse; + background-image:url("images/banner_bg.gif"); + background-repeat: repeat-x; + background-color:transparent; + background-position:inherit; +} + +img.logo { + border-top:1px solid #003b62; + border-left:1px solid #003b62; + border-right:none; + border-bottom: none; + margin:0; + padding:0; + display:inline +} \ No newline at end of file