kaks_analysis: kaks_analysis.xml comparison

comparison kaks_analysis.xml @ 27:f174450ebc44 draft

Uploaded

author	greg
date	Fri, 28 Apr 2017 14:23:46 -0400
parents	73db26d39092
children	b807167c1e60

comparison

equal deleted inserted replaced

-:73db26d39092
+:f174450ebc44
 && mv $output_dir/*.components '$output_components'
 #end if
 ]]>
 </command>
 <inputs>
-<param name="coding_sequences_species_1" format="fasta" type="data" label="Coding sequences (CDS) fasta file for species1" />
+<param name="coding_sequences_species_1" format="fasta" type="data" label="Coding sequences for the first species" />
-<param name="proteins_species_1" format="fasta" type="data" label="Aamino acids (proteins) sequences fasta file for species1" />
+<param name="proteins_species_1" format="fasta" type="data" label="Protein sequences for the first species" />
 <conditional name="comparison_cond">
-<param name="comparison" type="select" label="Select method for pairwise sequence comparison to determine homolgous pairs" help="Cross species comparison requires selection of inputs for second species">
+<param name="comparison" type="select" label="Type of sequence comparison">
-<option value="paralogs" selected="true">Self species comparison</option>
+<option value="paralogs" selected="true">Paralogous</option>
-<option value="orthologs">Cross species comparison</option>
+<option value="orthologs">Orthologous</option>
 </param>
 <when value="paralogs" />
 <when value="orthologs">
-<param name="coding_sequences_species_2" format="fasta" type="data" label="Coding sequences (CDS) fasta file for species2" />
+<param name="coding_sequences_species_2" format="fasta" type="data" label="Coding sequences for the second species" />
-<param name="proteins_species_2" format="fasta" type="data" label="Aamino acids (proteins) sequences fasta file for species2" />
+<param name="proteins_species_2" format="fasta" type="data" label="Protein sequences for the second species" />
 </when>
 </conditional>
 <conditional name="options_type">
 <param name="options_type_selector" type="select" label="Options Configuration">
 <option value="basic" selected="true">Basic</option>
 <option value="advanced">Advanced</option>
 </param>
 <when value="basic" />
 <when value="advanced">
 <conditional name="set_min_coverage_cond">
-<param name="set_min_coverage" type="select" label="Specify minimum sequence pairwise coverage length between homologous pairs?">
+<param name="set_min_coverage" type="select" label="Alignment coverage configuration">
 <option value="no" selected="true">No</option>
 <option value="yes">Yes</option>
 </param>
 <when value="no" />
 <when value="yes">
-<param name="min_coverage" type="float" value="0.5" min="0.3" max="1.0" label="Minimum sequence pairwise coverage length between homologous pairs" />
+<param name="min_coverage" type="float" value="0.5" min="0.3" max="1.0" label="match score" />
 </when>
 </conditional>
 <conditional name="recalibrate_cond">
-<param name="recalibrate" type="select" label="Specify evolutionary rate for recalibrating synonymous subsitutions (ks) of species?">
+<param name="recalibrate" type="select" label="Species rates recalibration configuration">
 <option value="no" selected="true">No</option>
 <option value="yes">Yes</option>
 </param>
 <when value="no" />
 <when value="yes">
-<param name="recalibration_rate" type="float" value="0.0" min="0.0" label="Evolutionary rate for recalibrating synonymous subsitutions (ks) of species" />
+<param name="recalibration_rate" type="float" value="0.0" min="0.0" label="Recalibration rate" />
 </when>
 </conditional>
 <conditional name="codeml_ctl_file_cond">
-<param name="codeml_ctl_file_select" type="select" label="Select PAML codeml control file?" help="Used for ML analysis of protein-coding DNA sequences using codon substitution models, select No to use the default control file">
+<param name="codeml_ctl_file_select" type="select" label="PAML codeml configuration">
 <option value="no" selected="true">No</option>
 <option value="yes">Yes</option>
 </param>
 <when value="no" />
 <when value="yes">
 <param name="codeml_ctl_file" format="txt" type="data" label="PAML codeml control file" />
 </when>
 </conditional>
 <conditional name="fit_components_cond">
-<param name="fit_components" type="select" label="Fit a mixture model of multivariate normal components to synonymous (ks) distribution?" help="Used to identify significant duplication events in a genome">
+<param name="fit_components" type="select" label="Rates clustering configuration">
 <option value="no" selected="true">No</option>
 <option value="yes">Yes</option>
 </param>
 <when value="no" />
 <when value="yes">
-<param name="num_of_components" type="integer" value="1" min="1" label="Number of components to fit to synonymous subsitutions (ks) distribution" />
+<param name="num_of_components" type="integer" value="1" min="1" label="Number of components" />
 </when>
 </conditional>
 <conditional name="set_lower_ks_limit_cond">
-<param name="set_lower_ks_limit" type="select" label="Set lower limit of synonymous subsitutions (ks)?" help="Reduces background noise from young paralogous pairs due to normal gene births and deaths in a genome">
+<param name="set_lower_ks_limit" type="select" label="Lower limit synonymous subsitution rates configuration">
 <option value="no" selected="true">No</option>
 <option value="yes">Yes</option>
 </param>
 <when value="no" />
 <when value="yes">
-<param name="min_ks" type="float" value="0.0" min="0.0" label="Lower limit of synonymous subsitutions (ks)" />
+<param name="min_ks" type="float" value="0.0" min="0.0" label="Minimum rate" />
 </when>
 </conditional>
 <conditional name="set_upper_ks_limit_cond">
-<param name="set_upper_ks_limit" type="select" label="Set upper limit of synonymous subsitutions (ks)?" help="Excludes likey ancient paralogous pairs">
+<param name="set_upper_ks_limit" type="select" label="Upper limit synonymous subsitution rates configuration">
 <option value="no" selected="true">No</option>
 <option value="yes">Yes</option>
 </param>
 <when value="no" />
 <when value="yes">
-<param name="max_ks" type="float" value="0.0" min="0.0" label="Upper limit of synonymous subsitutions (ks)" />
+<param name="max_ks" type="float" value="0.0" min="0.0" label="Maximum rate" />
 </when>
 </conditional>
 </when>
 </conditional>
 <!-- Required due to the Emmix license -->
 <tests>
 <test>
 </test>
 </tests>
 <help>
-This tool is one of the PlantTribes collection of automated modular analysis pipelines that utilize objective classifications of
+This tool is one of the PlantTribes collection of automated modular analysis pipelines for comparative and evolutionary analyses
-complete protein sequences from sequenced plant genomes to perform comparative evolutionary studies. This tool performs orthologous
+of genome-scale gene families and transcriptomes.  This tool estimates paralogous and orthologous pairwise synonymous (Ks) and
-or paralogous ks analyses of coding sequences and amino acid sequences.
+non-synonymous (Ka) substitution rates for a set of gene coding sequences either produced by the AssemblyPostProcessor tool or
+from an external source.  Optionally, the resulting set of estimated Ks values can be clustered into components using a mixture
+of multivariate normal distributions to identify significant duplication event(s) in a species or a pair of species.
 -----
 **Options**
 * **Required**
-- **Coding sequences (CDS) fasta file for species1** - Coding sequences (CDS) fasta file for species1.
+- **Coding sequences for the first species** - coding sequence fasta file for for the first species either produced by the AssemblyPostProcessor tool or an external source selected from your history.
-- **Aamino acids (proteins) sequences fasta file for species1** - Aamino acids (proteins) sequences fasta file for species1
+- **Protein sequences for the first species** - corresponding protein sequence fasta files for the first species either produced by the AssemblyPostProcessor tool or an external source selected from your history.
-- **Select method for pairwise sequence comparison to determine homolgous pairs** - Pairwise sequence comparison to determine homolgous pairs (cross species comparison requires selection of inputs for species2).
+- **Type of sequence comparison** - pairwise sequence comparison to determine homolgous pairs.  This can be either paralogous for self-species comparison or orthologous for cross-species comparison.  Cross species comparision requires data selected for the second species.
 * **Optional**
-- **Minimum sequence pairwise coverage length between homologous pairs** - Minimum sequence pairwise coverage length between homologous pairs (e.g., 0.5 results in 50% coverage.  Legal values lie between 0.3 and 1.0.
+- **Coding sequences for the second species** - coding sequence fasta file for for the second species either produced by the AssemblyPostProcessor tool or an external source selected from your history.  Required only for orthologous comparison.
-- **Evolutionary rate for recalibrating synonymous subsitutions (ks) of species** - (applies to paralogous ks analysis) Recalibrate synonymous subsitutions (ks) of species using a predetermined evoutionary rate that can be determined from a species tree inferred from a collection single copy genes from taxa of interest (Cui et al., 2006).
+- **Protein sequences for the second species** - corresponding protein sequence fasta files for the second species either produced by the AssemblyPostProcessor tool or an external source selected from your history.  Required only for orthologous comparison.
-- **Select PAML codeml control file?** - Select PAML's codeml control file from your history.  This file is used to to perfom ML analysis of protein-coding DNA sequences using codon substitution models.  Selecting No uses the default file which does not include input (seqfile, treefile) and output (outfile) parameters of codeml.
+- **Alignment coverage configuration** - select 'Yes' to set the minimum allowable alignment coverage length between homologous pairs.  PlantTribes uses global codon alignment match score to determine the pairwise alignment coverage.  By default, the match score is set to 0.5 if 'No' is selected.
-- **Fit a mixture model of multivariate normal components to synonymous (ks) distribution?** - Fit a mixture model of multivariate normal components to synonymous (ks) distribution to identify significant duplication event(s) in a genome.
-- **Number components to fit to synonymous subsitutions (ks) distribution** - Number components to fit to synonymous subsitutions (ks) distribution.
+- **match score** - number of base matches in a pairwise sequence alignment divided by the length of shorter sequence.  Positions in the alignment corresponding to gaps are not considered.  The score is restricted to the range 0.3 - 1.0.
-- **Lower limit of synonymous subsitutions (ks)** - Lower limit of synonymous subsitutions (ks) - necessary if fitting components to the distribution to reduce background noise from young paralogous pairs due to normal gene births and deaths in a genome.
-- **Upper limit of synonymous subsitutions (ks)** - Upper limit of synonymous subsitutions (ks) - necessary if fitting components to the distribution to exclude likey ancient paralogous pairs.
+- **Species rates recalibration configuration** - select 'Yes' to recalibrate synonymous substitution rates of a species using a predetermined evolutionary rate.  Recalibration evolutionary rate can be determined from a species tree inferred from a collection of conserved single copy genes from taxa of interest as described in Cui et al., 2006.  Applies only to paralogous comparisons.
+- **recalibration rate** - a predetermined evolutionary recalibration rate.
+- **PAML codeml configuration** - select 'Yes' to enable selection of a PAML codeml control file to carry out maximum likelihood analysis of protein-coding DNA sequences using codon substitution models.  Template file "codeml.ctl.args" can be found in the scaffold data installed into Galaxy via the PlantTribes Scaffolds Download Data Manager tool, and are also available at the PlantTribes GitHub `repository`_.  Default settings shown in the template are used if 'No' is selected.
+.. _repository: https://github.com/dePamphilis/PlantTribes/blob/master/config/codeml.ctl.args
+- **Rates clustering configuration** - select 'Yes' to estimate clusters of synonymous substitution rates using a mixture of multivariate normal distributions which represent putative duplication event(s).
+- **Number of components** - number of components to include in the normal mixture model.
+- **Lower limit synonymous subsitution rates configuration** - select 'Yes' to set the minimum allowable synonymous substitution rate to use in the normal mixtures cluster analysis to exclude young paralogs that arise from normal gene births and deaths in a genome.
+- **Minimum rate** - minimum allowable synonymous substitution rate.
+- **Upper limit synonymous subsitution rates configuration** - select 'Yes' to set the maximum allowable synonymous substitution rate to use in the normal mixtures cluster analysis to exclude likely ancient paralogs in a genome.
+- **Maximum rate** - maximum allowable synonymous substitution rate.
 </help>
 <citations>
 <expand macro="citation1" />
-<citation type="doi">10.1093/bioinformatics/btw412</citation>
+<citation type="bibtex">
-<citation type="doi">10.1186/1471-2105-10-421</citation>
+@article{Wall2008,
-<citation type="doi">10.1093/molbev/msm088</citation>
+journal = {Nucleic Acids Research},
-<citation type="doi">10.18637/jss.v004.i02</citation>
+author = {2. Wall PK, Leebens-Mack J, Muller KF, Field D, Altman NS},
+title = {PlantTribes: a gene and gene family resource for comparative genomics in plants},
+year = {2008},
+volume = {36},
+number = {suppl 1},
+pages = {D970-D976},}
+</citation>
+<citation type="bibtex">
+@article{Altschul1990,
+journal = {Journal of molecular biology}
+author = {3. Altschul SF, Gish W, Miller W, Myers EW, Lipman DJ},
+title = {Basic local alignment search tool},
+year = {1990},
+volume = {215},
+number = {3},
+pages = {403-410},}
+</citation>
+<citation type="bibtex">
+@article{Katoh2013,
+journal = {Molecular biology and evolution},
+author = {4. Katoh K, Standley DM},
+title = {MAFFT multiple sequence alignment software version 7: improvements in performance and usability},
+year = {2013},
+volume = {30},
+number = {4},
+pages = {772-780},}
+</citation>
+<citation type="bibtex">
+@article{Yang2007,
+journal = {Molecular biology and evolution},
+author = {5. Yang Z},
+title = {PAML 4: phylogenetic analysis by maximum likelihood},
+year = {2007},
+volume = {24},
+number = {8},
+pages = {1586-1591},}
+</citation>
+<citation type="bibtex">
+@article{McLachlan1999,
+journal = {Journal of Statistical Software},
+author = {6. McLachlan GJ, Peel D, Basford KE, Adams P},
+title = {The EMMIX software for the fitting of mixtures of normal and t-components},
+year = {1999},
+volume = {4},
+number = {2},
+pages = {1-14},}
+</citation>
 </citations>
 </tool>

Mercurial > repos > greg > kaks_analysis

comparison kaks_analysis.xml @ 27:f174450ebc44 draft