Mercurial > repos > geert-vandeweyer > cuffquant
annotate cuffquant_wrapper.xml @ 2:d36af207c24f draft
Deleted selected files
| author | geert-vandeweyer |
|---|---|
| date | Mon, 04 Aug 2014 10:49:36 -0400 |
| parents | e14baafb20bd |
| children |
| rev | line source |
|---|---|
| 0 | 1 <tool id="cuffquant" name="Cuffquant" version="0.0.1"> |
| 2 <!-- Wrapper supports Cuffdiff versions 2.2.1 --> | |
| 3 <description>Precompute gene expression levels</description> | |
| 4 <requirements> | |
| 5 <requirement type="package" version="2.2.1">cufflinks</requirement> | |
| 6 </requirements> | |
| 7 <version_command>cuffquant 2>&1 | head -n 1</version_command> | |
| 8 <command> | |
| 9 cuffquant | |
| 10 --no-update-check | |
| 11 ##--num-threads="\${GALAXY_SLOTS:-4}" | |
| 12 --num-threads=6 | |
| 13 ## Set advanced SE data parameters? | |
| 14 #if $additional.sAdditional == "Yes": | |
| 15 -m $additional.frag_mean_len | |
| 16 -s $additional.frag_len_std_dev | |
| 17 #end if | |
| 18 | |
| 19 ## Multi-read correct? | |
| 20 #if $multiread_correct : | |
| 21 -u | |
| 22 #end if | |
| 23 | |
| 24 ## Bias correction? | |
| 25 #if $bias_correction.do_bias_correction == "Yes": | |
| 26 -b | |
| 27 #if $bias_correction.seq_source.index_source == "history": | |
| 28 ## Custom genome from history. | |
| 29 $bias_correction.seq_source.ref_file | |
| 30 #else: | |
| 31 ## Built-in genome. | |
| 32 ${__get_data_table_entry__('fasta_indexes', 'value', $gtf_input.dbkey, 'path')} | |
| 33 #end if | |
| 34 #end if | |
| 35 | |
| 36 $length_correction | |
| 37 | |
| 38 ## Set advanced parameters for cufflinks | |
| 39 #if $advanced_settings.sAdvanced == "Yes": | |
| 40 #if str($advanced_settings.library_type) != 'auto': | |
| 41 --library-type=$advanced_settings.library_type | |
| 42 #end if | |
| 43 #if $advanced_settings.mask_file: | |
| 44 --mask-file=$advanced_settings.mask_file | |
| 45 #end if | |
| 46 --max-mle-iterations=$advanced_settings.max_mle_iterations | |
| 47 --max-bundle-frags=$advanced_settings.max_bundle_frags | |
| 48 #end if | |
| 49 ## Inputs. | |
| 50 $gtf_input | |
|
1
e14baafb20bd
Added Test description, updated a few lines in the help
geert-vandeweyer
parents:
0
diff
changeset
|
51 #set samplestring = ','.join( [ str( $sample.sample ) for $sample in $samples ] ) |
|
e14baafb20bd
Added Test description, updated a few lines in the help
geert-vandeweyer
parents:
0
diff
changeset
|
52 $samplestring |
| 0 | 53 </command> |
| 54 <inputs> | |
| 55 <param format="gtf,gff3" name="gtf_input" type="data" label="Transcripts" help="A transcript annotation (GFF3 or GTF) file produced by cufflinks, cuffcompare, or other source."/> | |
| 56 | |
|
1
e14baafb20bd
Added Test description, updated a few lines in the help
geert-vandeweyer
parents:
0
diff
changeset
|
57 <repeat name="samples" title="Replicate" min="1"> |
|
e14baafb20bd
Added Test description, updated a few lines in the help
geert-vandeweyer
parents:
0
diff
changeset
|
58 <param name="sample" label="Add replicate" type="data" format="sam,bam"/> |
|
e14baafb20bd
Added Test description, updated a few lines in the help
geert-vandeweyer
parents:
0
diff
changeset
|
59 </repeat> |
| 0 | 60 |
| 61 | |
| 62 <param name="multiread_correct" type="boolean" label="Use multi-read correct" help="Tells Cufflinks to do an initial estimation procedure to more accurately weight reads mapping to multiple locations in the genome." /> | |
| 63 | |
| 64 <conditional name="bias_correction"> | |
| 65 <param name="do_bias_correction" type="select" label="Perform Bias Correction" help="Bias detection and correction can significantly improve accuracy of transcript abundance estimates."> | |
| 66 <option value="No">No</option> | |
| 67 <option value="Yes">Yes</option> | |
| 68 </param> | |
| 69 <when value="Yes"> | |
| 70 <conditional name="seq_source"> | |
| 71 <param name="index_source" type="select" label="Reference sequence data"> | |
| 72 <option value="cached">Locally cached</option> | |
| 73 <option value="history">History</option> | |
| 74 </param> | |
| 75 <when value="cached"> | |
| 76 <param name="index" type="select" label="Using reference genome"> | |
| 77 <options from_data_table="fasta_indexes"> | |
| 78 <filter type="data_meta" ref="gtf_input" key="dbkey" column="1" /> | |
| 79 <validator type="no_options" message="No reference genome is available for the build associated with the selected input dataset" /> | |
| 80 </options> | |
| 81 </param> | |
| 82 </when> | |
| 83 <when value="history"> | |
| 84 <param name="ref_file" type="data" format="fasta" label="Using reference file" /> | |
| 85 </when> | |
| 86 </conditional> | |
| 87 </when> | |
| 88 <when value="No"></when> | |
| 89 </conditional> | |
| 90 | |
| 91 <param name="length_correction" type="select" label="apply length correction" help="mode of length normalization to transcript fpkm."> | |
| 92 <option value="" selected="true">cufflinks effective length correction</option> | |
| 93 <option value="--no-effective-length-correction">standard length correction</option> | |
| 94 <option value="--no-length-correction">no length correction at all (use raw counts)</option> | |
| 95 </param> | |
| 96 | |
| 97 <conditional name="additional"> | |
| 98 <param name="sAdditional" type="select" label="Set Additional Parameters for single end reads? (not recommended for paired-end reads)"> | |
| 99 <option value="No" selected="True">No</option> | |
| 100 <option value="Yes">Yes</option> | |
| 101 </param> | |
| 102 <when value="No"></when> | |
| 103 <when value="Yes"> | |
| 104 <param name="frag_mean_len" type="integer" value="200" label="Average Fragment Length"/> | |
| 105 <param name="frag_len_std_dev" type="integer" value="80" label="Fragment Length Standard Deviation"/> | |
| 106 </when> | |
| 107 </conditional> | |
| 108 | |
| 109 <conditional name="advanced_settings"> | |
| 110 <param name="sAdvanced" type="select" label="Set Advanced Cuffquant parameters? "> | |
| 111 <option value="No" selected="True">No</option> | |
| 112 <option value="Yes">Yes</option> | |
| 113 </param> | |
| 114 <when value="No"></when> | |
| 115 <when value="Yes"> | |
| 116 <param type="select" name="library_type" label="Library prep used for input reads" help=""> | |
| 117 <option value="auto" selected="True">Auto Detect</option> | |
| 118 <option value="ff-firststrand">ff-firststrand</option> | |
| 119 <option value="ff-secondstrand">ff-secondstrand</option> | |
| 120 <option value="ff-unstranded">ff-unstranded</option> | |
| 121 <option value="fr-firststrand">fr-firststrand</option> | |
| 122 <option value="fr-secondstrand">fr-secondstrand</option> | |
| 123 <option value="fr-unstranded" >fr-unstranded</option> | |
| 124 <option value="transfrags">transfrags</option> | |
| 125 </param> | |
| 126 <param name="mask_file" type="data" format="gtf,gff3" label="Mask File" help="Ignore all alignment within transcripts in this file" optional="True" /> | |
| 127 <param name="max_mle_iterations" value="5000" type="integer" label="Max MLE iterations" help="Maximum iterations allowed for Maximal Likelyhood Estimation calculations" /> | |
|
1
e14baafb20bd
Added Test description, updated a few lines in the help
geert-vandeweyer
parents:
0
diff
changeset
|
128 <param name="max_bundle_frags" type="integer" value="500000" label="Maximum number of fragments per locus" help="Sets the maximum number of fragments a locus may have before being skipped. Default: 500,000" /> |
| 0 | 129 |
| 130 </when> | |
| 131 </conditional> | |
| 132 </inputs> | |
| 133 | |
| 134 <stdio> | |
| 135 <regex match="Error" source="both" level="fatal" description="Error"/> | |
| 136 <regex match=".*" source="both" level="log" description="tool progress"/> | |
| 137 </stdio> | |
| 138 | |
| 139 <outputs> | |
| 140 | |
| 141 <!-- Standard datasets. --> | |
| 142 <data format="cxb" name="out_file" label="${tool.name} on ${on_string}: Abundances.cxb" from_work_dir="abundances.cxb" /> | |
| 143 </outputs> | |
| 144 | |
| 145 <tests> | |
| 146 <test> | |
| 147 <!-- | |
|
1
e14baafb20bd
Added Test description, updated a few lines in the help
geert-vandeweyer
parents:
0
diff
changeset
|
148 cuffquant cuffcompare_out5.gtf cuffdiff_in1.sam,cuffdiff_in2.sam |
| 0 | 149 --> |
|
1
e14baafb20bd
Added Test description, updated a few lines in the help
geert-vandeweyer
parents:
0
diff
changeset
|
150 <param name="gtf_input" value="cuffquant_in.gtf" ftype="gtf" /> |
|
e14baafb20bd
Added Test description, updated a few lines in the help
geert-vandeweyer
parents:
0
diff
changeset
|
151 <param name="sample1" value="cuffquant_in1.sam" ftype="sam" /> |
|
e14baafb20bd
Added Test description, updated a few lines in the help
geert-vandeweyer
parents:
0
diff
changeset
|
152 <param name="sample2" value="cuffquant_in2.sam" ftype="sam" /> |
|
e14baafb20bd
Added Test description, updated a few lines in the help
geert-vandeweyer
parents:
0
diff
changeset
|
153 <param name="length_correction" value="cufflinks effective length correction" /> |
| 0 | 154 <param name="do_bias_correction" value="No" /> |
| 155 <param name="multiread_correct" value="No"/> | |
| 156 <param name="sAdditional" value="No"/> | |
|
1
e14baafb20bd
Added Test description, updated a few lines in the help
geert-vandeweyer
parents:
0
diff
changeset
|
157 <param name="sAdvanced" value="No" /> |
|
e14baafb20bd
Added Test description, updated a few lines in the help
geert-vandeweyer
parents:
0
diff
changeset
|
158 <output name="out_file" file="cuffquant_out1.cxb"/> |
| 0 | 159 </test> |
| 160 </tests> | |
| 161 | |
| 162 <help> | |
| 163 **Cuffquant Overview** | |
| 164 | |
| 165 Cuffquant is part of Cufflinks_. Cuffquant provides pre-calculation of gene expression levels. The resulting file can be provided to cuffdiff or cuffnorm for further processing. Please cite: Trapnell C, Williams BA, Pertea G, Mortazavi AM, Kwan G, van Baren MJ, Salzberg SL, Wold B, Pachter L. Transcript assembly and abundance estimation from RNA-Seq reveals thousands of new transcripts and switching among isoforms. Nature Biotechnology doi:10.1038/nbt.1621 | |
| 166 | |
| 167 .. _Cufflinks: http://cufflinks.cbcb.umd.edu/ | |
| 168 | |
| 169 ------ | |
| 170 | |
| 171 **Know what you are doing** | |
| 172 | |
| 173 .. class:: warningmark | |
| 174 | |
| 175 There is no such thing (yet) as an automated gearshift in expression analysis. It is all like stick-shift driving in San Francisco. In other words, running this tool with default parameters will probably not give you meaningful results. A way to deal with this is to **understand** the parameters by carefully reading the `documentation`__ and experimenting. Fortunately, Galaxy makes experimenting easy. | |
| 176 | |
| 177 .. __: http://cufflinks.cbcb.umd.edu/manual.html#cuffdiff | |
| 178 | |
| 179 ------ | |
| 180 | |
| 181 **Input format** | |
| 182 | |
| 183 Cuffquant takes Cufflinks or Cuffcompare GTF files as input along with two or more SAM files containing the fragment alignments for two or more samples. | |
| 184 | |
| 185 ------ | |
| 186 | |
| 187 **Outputs** | |
| 188 | |
| 189 Cuffquant produces one output file: | |
| 190 | |
| 191 1. Transcript expression values in binary format. | |
| 192 | |
| 193 ------- | |
| 194 | |
| 195 **Settings** | |
| 196 | |
| 197 All of the options have a default value. You can change any of them. Most of the options in Cuffdiff have been implemented here. | |
| 198 | |
| 199 ------ | |
| 200 | |
| 201 **Cuffdiff parameter list** | |
| 202 | |
| 203 This is a list of implemented Cuffdiff options:: | |
| 204 | |
| 205 -m INT Average fragment length (SE reads); default 200 | |
| 206 -s INT Fragment legnth standard deviation (SE reads); default 80 | |
| 207 --max-mle-iterations INT Sets the number of iterations allowed during maximum likelihood estimation of abundances. Default: 5000 | |
| 208 -u Multi read correction tells Cufflinks to do an initial estimation procedure to more accurately weight reads mapping to multiple locations in the genome. | |
| 209 -b ref.fasta bias correction. Bias detection and correction can significantly improve accuracy of transcript abundance estimates. | |
| 210 --no-effective-length-correction Use standard length correction | |
| 211 --no-length-correction Disable all length correction. | |
| 212 --library-type ff-firststrand,ff-secondstrand,ff-unstranded,fr-firstrand,fr-secondstrand,fr-unstranded,transfrags | |
| 213 --mask-file (gff3/gtf) Ignore all alignment within transcripts in this file | |
| 214 --max-bundle-frags Sets the maximum number of fragments a locus may have before being skipped. Skipped loci are listed in skipped.gtf. | |
| 215 </help> | |
| 216 </tool> |