comparison kaks_analysis.xml @ 15:01278db07d6f draft

Uploaded
author greg
date Thu, 02 Mar 2017 10:03:03 -0500
parents 4e23c98465e9
children f5f97d8c4207
comparison
equal deleted inserted replaced
14:4e23c98465e9 15:01278db07d6f
74 && mv $output_dir/*.components '$output_components' 74 && mv $output_dir/*.components '$output_components'
75 #end if 75 #end if
76 ]]> 76 ]]>
77 </command> 77 </command>
78 <inputs> 78 <inputs>
79 <param name="coding_sequences_species_1" format="fasta" type="data" label="Coding sequences (CDS) fasta file for the species" /> 79 <param name="coding_sequences_species_1" format="fasta" type="data" label="Coding sequences (CDS) fasta file for species1" />
80 <param name="proteins_species_1" format="fasta" type="data" label="Aamino acids (proteins) sequences fasta file for the species" /> 80 <param name="proteins_species_1" format="fasta" type="data" label="Aamino acids (proteins) sequences fasta file for species1" />
81 <conditional name="comparison_cond"> 81 <conditional name="comparison_cond">
82 <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"> 82 <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">
83 <option value="paralogs" selected="true">Self species comparison</option> 83 <option value="paralogs" selected="true">Self species comparison</option>
84 <option value="orthologs">Cross species comparison</option> 84 <option value="orthologs">Cross species comparison</option>
85 </param> 85 </param>
86 <when value="paralogs" /> 86 <when value="paralogs" />
87 <when value="orthologs"> 87 <when value="orthologs">
88 <param name="coding_sequences_species_2" format="fasta" type="data" label="Coding sequences (CDS) fasta file for the second species" /> 88 <param name="coding_sequences_species_2" format="fasta" type="data" label="Coding sequences (CDS) fasta file for species2" />
89 <param name="proteins_species_2" format="fasta" type="data" label="Aamino acids (proteins) sequences fasta file for the second species" /> 89 <param name="proteins_species_2" format="fasta" type="data" label="Aamino acids (proteins) sequences fasta file for species2" />
90 </when> 90 </when>
91 </conditional> 91 </conditional>
92 <param name="scaffold" type="select" label="Orthogroups or gene families proteins scaffold" help="Selection specifies default configuration files"> 92 <param name="scaffold" type="select" label="Orthogroups or gene families proteins scaffold" help="Selection specifies default configuration files">
93 <options from_data_table="plant_tribes_scaffolds" /> 93 <options from_data_table="plant_tribes_scaffolds" />
94 <validator type="no_options" message="No PlantTribes scaffolds are available. Use the PlantTribes Scaffolds Download Data Manager tool in Galaxy to install and populate the PlantTribes scaffolds data table."/> 94 <validator type="no_options" message="No PlantTribes scaffolds are available. Use the PlantTribes Scaffolds Download Data Manager tool in Galaxy to install and populate the PlantTribes scaffolds data table."/>
142 <param name="max_ks" type="float" value="0.0" min="0.0" label="Upper limit of synonymous subsitutions (ks)" help="Excludes likey ancient paralogous pairs" /> 142 <param name="max_ks" type="float" value="0.0" min="0.0" label="Upper limit of synonymous subsitutions (ks)" help="Excludes likey ancient paralogous pairs" />
143 </when> 143 </when>
144 </conditional> 144 </conditional>
145 </when> 145 </when>
146 </conditional> 146 </conditional>
147 <!-- Required due to the Emmix license -->
147 <param name="non_commercial_use" label="I certify that I am not using this tool for commercial purposes." type="boolean" truevalue="NON_COMMERCIAL_USE" falsevalue="COMMERCIAL_USE" checked="False"> 148 <param name="non_commercial_use" label="I certify that I am not using this tool for commercial purposes." type="boolean" truevalue="NON_COMMERCIAL_USE" falsevalue="COMMERCIAL_USE" checked="False">
148 <validator type="expression" message="This tool is only available for non-commercial use.">value == True</validator> 149 <validator type="expression" message="This tool is only available for non-commercial use.">value == True</validator>
149 </param> 150 </param>
150 </inputs> 151 </inputs>
151 <outputs> 152 <outputs>
183 184
184 ----- 185 -----
185 186
186 **Options** 187 **Options**
187 188
188 * **Required options** 189 * **Required**
189 190
190 - **Coding sequences (CDS) fasta file for the species** - Coding sequences (CDS) fasta file for the first species. 191 - **Coding sequences (CDS) fasta file for species1** - Coding sequences (CDS) fasta file for species1.
191 - **Aamino acids (proteins) sequences fasta file for the species** - Aamino acids (proteins) sequences fasta file for the first species 192 - **Aamino acids (proteins) sequences fasta file for species1** - Aamino acids (proteins) sequences fasta file for species1
192 - **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 second species). 193 - **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).
193 - **Orthogroups or gene families proteins scaffold** - PlantTribes scaffolds data installed into Galaxy by the PlantTribes Scaffolds Download Data Manager tool. 194 - **Orthogroups or gene families proteins scaffold** - PlantTribes scaffolds data installed into Galaxy by the PlantTribes Scaffolds Download Data Manager tool.
194 195
195 * **Other (optional) options** 196 * **Optional**
196 197
197 - **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. 198 - **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.
198 - **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). 199 - **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).
199 - **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. 200 - **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.
200 - **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. 201 - **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.