Mercurial > repos > devteam > cufflinks

comparison cufflinks_wrapper.xml @ 10:83bec71c5c9f draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tool_collections/cufflinks/cufflinks commit eb18f691975ef9539b5ebd4f118343c8ad967a1f
author devteam
date Tue, 07 Feb 2017 18:39:22 -0500
parents 5346d5eea8b1
children e04dbae2abe0
comparison
equal deleted inserted replaced
9:a1ea9af8d5f4 10:83bec71c5c9f
1 <tool id="cufflinks" name="Cufflinks" version="@VERSION@.0"> 1 <tool id="cufflinks" name="Cufflinks" version="@VERSION@.1">
2 <description>transcript assembly and FPKM (RPKM) estimates for RNA-Seq data</description> 2 <description>transcript assembly and FPKM (RPKM) estimates for RNA-Seq data</description>
3 <expand macro="requirements" />
4 <expand macro="stdio" />
5 <macros> 3 <macros>
6 <import>cuff_macros.xml</import> 4 <import>cuff_macros.xml</import>
7 </macros> 5 </macros>
6 <requirements>
7 <requirement type="package" version="0.7.3">bx-python</requirement>
8 <requirement type="package" version="1.9.0">six</requirement>
9 <requirement type="package" version="2.2.1">cufflinks</requirement>
10 </requirements>
11 <expand macro="stdio" />
8 <version_command>cufflinks 2>&amp;1 | head -n 1</version_command> 12 <version_command>cufflinks 2>&amp;1 | head -n 1</version_command>
9 <command interpreter="python"> 13 <command>
10 cufflinks_wrapper.py 14 python '$__tool_directory__/cufflinks_wrapper.py'
11 --input=$input 15 --input '$input'
12 --assembled-isoforms-output=$assembled_isoforms 16 --assembled-isoforms-output '$assembled_isoforms'
13 --num-threads="\${GALAXY_SLOTS:-4}" 17 --num-threads "\${GALAXY_SLOTS:-4}"
14 -I $max_intron_len 18 -I $max_intron_len
15 -F $min_isoform_fraction 19 -F $min_isoform_fraction
16 -j $pre_mrna_fraction 20 -j $pre_mrna_fraction
17 $length_correction 21 $length_correction
18 22
19 ## Include reference annotation? 23 ## Include reference annotation?
20 #if $reference_annotation.use_ref == "Use reference annotation": 24 #if $reference_annotation.use_ref == "Use reference annotation":
21 -G $reference_annotation.reference_annotation_file 25 -G '$reference_annotation.reference_annotation_file'
22 $reference_annotation.compatible_hits_norm 26 $reference_annotation.compatible_hits_norm
23 #end if 27 #end if
24 #if $reference_annotation.use_ref == "Use reference annotation guide": 28 #if $reference_annotation.use_ref == "Use reference annotation guide":
25 -g $reference_annotation.reference_annotation_guide_file 29 -g '$reference_annotation.reference_annotation_guide_file'
26 --3-overhang-tolerance=$reference_annotation.three_overhang_tolerance 30 --3-overhang-tolerance $reference_annotation.three_overhang_tolerance
27 --intron-overhang-tolerance=$reference_annotation.intron_overhang_tolerance 31 --intron-overhang-tolerance $reference_annotation.intron_overhang_tolerance
28 $reference_annotation.no_faux_reads 32 $reference_annotation.no_faux_reads
29 #end if 33 #end if
30 34
31 ## Bias correction? 35 ## Bias correction?
32 #if $bias_correction.do_bias_correction == "Yes": 36 #if $bias_correction.do_bias_correction == "Yes":
33 -b 37 -b
34 #if $bias_correction.seq_source.index_source == "history": 38 #if $bias_correction.seq_source.index_source == "history":
35 --ref_file=$bias_correction.seq_source.ref_file 39 --ref_file '$bias_correction.seq_source.ref_file'
36 #else: 40 #else:
37 --index=${bias_correction.seq_source.index.fields.path} 41 --index '${bias_correction.seq_source.index.fields.path}'
38 #end if 42 #end if
39 #end if 43 #end if
40 44
41 ## Multi-read correct? 45 ## Multi-read correct?
42 #if str($multiread_correct) == "Yes": 46 #if str($multiread_correct) == "Yes":
43 -u 47 -u
44 #end if 48 #end if
45 49
46 ## Include global model if available. 50 ## Include global model if available.
47 #if $global_model: 51 #if $global_model:
48 --global_model=$global_model 52 --global_model '$global_model'
49 #end if 53 #end if
50 54
51 ## advanced settings 55 ## advanced settings
52 #if $advanced_settings.use_advanced_settings == "Yes": 56 #if $advanced_settings.use_advanced_settings == "Yes":
53 --library-type=$advanced_settings.library_type 57 --library-type $advanced_settings.library_type
54 #if $advanced_settings.mask_file: 58 #if $advanced_settings.mask_file:
55 --mask-file=$advanced_settings.mask_file 59 --mask-file '$advanced_settings.mask_file'
56 #end if 60 #end if
57 --inner-mean-dist=$advanced_settings.inner_mean_dist 61 --inner-mean-dist $advanced_settings.inner_mean_dist
58 --inner-dist-std-dev=$advanced_settings.inner_dist_std_dev 62 --inner-dist-std-dev $advanced_settings.inner_dist_std_dev
59 --max-mle-iterations=$advanced_settings.max_mle_iterations 63 --max-mle-iterations $advanced_settings.max_mle_iterations
60 --junc-alpha=$advanced_settings.junc_alpha 64 --junc-alpha $advanced_settings.junc_alpha
61 --small-anchor-fraction=$advanced_settings.small_anchor_fraction 65 --small-anchor-fraction $advanced_settings.small_anchor_fraction
62 --overhang-tolerance=$advanced_settings.overhang_tolerance 66 --overhang-tolerance $advanced_settings.overhang_tolerance
63 --max-bundle-length=$advanced_settings.max_bundle_length 67 --max-bundle-length $advanced_settings.max_bundle_length
64 --max-bundle-frags=$advanced_settings.max_bundle_frags 68 --max-bundle-frags $advanced_settings.max_bundle_frags
65 --min-intron-length=$advanced_settings.min_intron_length 69 --min-intron-length $advanced_settings.min_intron_length
66 --trim-3-avgcov-thresh=$advanced_settings.trim_three_avgcov_thresh 70 --trim-3-avgcov-thresh $advanced_settings.trim_three_avgcov_thresh
67 --trim-3-dropoff-frac=$advanced_settings.trim_three_dropoff_frac 71 --trim-3-dropoff-frac $advanced_settings.trim_three_dropoff_frac
68 #end if 72 #end if
69
70 </command> 73 </command>
71 <inputs> 74 <inputs>
72 <param format="sam,bam" name="input" type="data" label="SAM or BAM file of aligned RNA-Seq reads" help=""/> 75 <param format="sam,bam" name="input" type="data" label="SAM or BAM file of aligned RNA-Seq reads" help=""/>
73 <param name="max_intron_len" type="integer" value="300000" min="1" max="600000" label="Max Intron Length" help="ignore alignments with gaps longer than this"/> 76 <param name="max_intron_len" type="integer" value="300000" min="1" max="600000" label="Max Intron Length" help="ignore alignments with gaps longer than this"/>
74 <param name="min_isoform_fraction" type="float" value="0.10" min="0" max="1" label="Min Isoform Fraction" help="suppress transcripts below this abundance level"/> 77 <param name="min_isoform_fraction" type="float" value="0.10" min="0" max="1" label="Min Isoform Fraction" help="suppress transcripts below this abundance level"/>
75 <param name="pre_mrna_fraction" type="float" value="0.15" min="0" max="1" label="Pre MRNA Fraction" help="suppress intra-intronic transcripts below this level"/> 78 <param name="pre_mrna_fraction" type="float" value="0.15" min="0" max="1" label="Pre MRNA Fraction" help="suppress intra-intronic transcripts below this level"/>
76 <conditional name="reference_annotation"> 79 <conditional name="reference_annotation">
77 <param name="use_ref" type="select" label="Use Reference Annotation"> 80 <param name="use_ref" type="select" label="Use Reference Annotation">
78 <option value="No" selected="true">No</option> 81 <option value="No" selected="true">No</option>
79 <option value="Use reference annotation">Use reference annotation</option> 82 <option value="Use reference annotation">Use reference annotation</option>
80 <option value="Use reference annotation guide">Use reference annotation as guide</option> 83 <option value="Use reference annotation guide">Use reference annotation as guide</option>
81 </param> 84 </param>
82 <when value="No"></when> 85 <when value="No" />
83 <when value="Use reference annotation"> 86 <when value="Use reference annotation">
84 <param format="gff3,gtf" name="reference_annotation_file" type="data" label="Reference Annotation" help="Gene annotation dataset in GTF or GFF3 format."/> 87 <param format="gff3,gtf" name="reference_annotation_file" type="data" label="Reference Annotation" help="Gene annotation dataset in GTF or GFF3 format."/>
85 <param name="compatible_hits_norm" type="select" label="Count hits compatible with reference RNAs only" 88 <param name="compatible_hits_norm" type="select" label="Count hits compatible with reference RNAs only"
86 help="With this option, Cufflinks counts only those fragments compatible with some reference transcript towards the number of mapped hits used in the FPKM denominator. This option can only be used in combination with --GTF."> 89 help="With this option, Cufflinks counts only those fragments compatible with some reference transcript towards the number of mapped hits used in the FPKM denominator. This option can only be used in combination with --GTF.">
87 <option value="" selected="True">No</option> 90 <option value="" selected="True">No</option>
88 <option value="--compatible-hits-norm">Yes</option> 91 <option value="--compatible-hits-norm">Yes</option>
89 </param> 92 </param>
90 </when> 93 </when>
91 <when value="Use reference annotation guide"> 94 <when value="Use reference annotation guide">
92 <param format="gff3,gtf" name="reference_annotation_guide_file" type="data" label="Reference Annotation" help="Gene annotation dataset in GTF or GFF3 format."/> 95 <param format="gff3,gtf" name="reference_annotation_guide_file" type="data" label="Reference Annotation" help="Gene annotation dataset in GTF or GFF3 format."/>
93 <param name="three_overhang_tolerance" type="integer" value="600" label="3prime overhang tolerance" 96 <param name="three_overhang_tolerance" type="integer" value="600" label="3prime overhang tolerance"
94 help="The number of bp allowed to overhang the 3prime end of a reference transcript when determining if an assembled transcript should be merged with it (ie, the assembled transcript is not novel). The default is 600 bp." /> 97 help="The number of bp allowed to overhang the 3prime end of a reference transcript when determining if an assembled transcript should be merged with it (ie, the assembled transcript is not novel). The default is 600 bp." />
95 <param name="intron_overhang_tolerance" type="integer" value="50" label="Intronic overhang tolerance" help="The number of bp allowed to enter the intron of a reference transcript when determining if an assembled transcript should be merged with it (ie, the assembled transcript is not novel). The default is 50 bp." /> 98 <param name="intron_overhang_tolerance" type="integer" value="50" label="Intronic overhang tolerance" help="The number of bp allowed to enter the intron of a reference transcript when determining if an assembled transcript should be merged with it (ie, the assembled transcript is not novel). The default is 50 bp." />
96 <param name="no_faux_reads" type="select" label="Disable tiling of reference transcripts" help="This option disables tiling of the reference transcripts with faux reads. Use this if you only want to use sequencing reads in assembly but do not want to output assembled transcripts that lay within reference transcripts. All reference transcripts in the input annotation will also be included in the output."> 99 <param name="no_faux_reads" type="select" label="Disable tiling of reference transcripts" help="This option disables tiling of the reference transcripts with faux reads. Use this if you only want to use sequencing reads in assembly but do not want to output assembled transcripts that lay within reference transcripts. All reference transcripts in the input annotation will also be included in the output.">
97 <option value="" selected="True">No</option> 100 <option value="" selected="True">No</option>
98 <option value="--no-faux-reads">Yes</option> 101 <option value="--no-faux-reads">Yes</option>
105 <option value="No" selected="true">No</option> 108 <option value="No" selected="true">No</option>
106 <option value="Yes">Yes</option> 109 <option value="Yes">Yes</option>
107 </param> 110 </param>
108 <when value="Yes"> 111 <when value="Yes">
109 <conditional name="seq_source"> 112 <conditional name="seq_source">
110 <param name="index_source" type="select" label="Reference sequence data"> 113 <param name="index_source" type="select" label="Reference sequence data">
111 <option value="cached" selected="true">Locally cached</option> 114 <option value="cached" selected="true">Locally cached</option>
112 <option value="history">History</option> 115 <option value="history">History</option>
113 </param>
114 <when value="cached">
115 <param name="index" type="select" label="Using reference genome">
116 <options from_data_table="fasta_indexes">
117 <filter type="data_meta" ref="input" key="dbkey" column="1" />
118 <validator type="no_options" message="No reference genome is available for the build associated with the selected input dataset" />
119 </options>
120 </param> 116 </param>
121 </when> 117 <when value="cached">
122 <when value="history"> 118 <param name="index" type="select" label="Using reference genome">
123 <param name="ref_file" type="data" format="fasta" label="Using reference file" /> 119 <options from_data_table="fasta_indexes">
124 </when> 120 <filter type="data_meta" ref="input" key="dbkey" column="1" />
121 <validator type="no_options" message="No reference genome is available for the build associated with the selected input dataset" />
122 </options>
123 </param>
124 </when>
125 <when value="history">
126 <param name="ref_file" type="data" format="fasta" label="Using reference file" />
127 </when>
125 </conditional> 128 </conditional>
126 </when> 129 </when>
127 <when value="No"></when> 130 <when value="No" />
128 </conditional> 131 </conditional>
129 132
130 <param name="multiread_correct" type="select" label="Use multi-read correct" 133 <param name="multiread_correct" type="select" label="Use multi-read correct"
131 help="Tells Cufflinks to do an initial estimation procedure to more accurately weight reads mapping to multiple locations in the genome."> 134 help="Tells Cufflinks to do an initial estimation procedure to more accurately weight reads mapping to multiple locations in the genome.">
132 <option value="No" selected="true">No</option> 135 <option value="No" selected="true">No</option>
133 <option value="Yes">Yes</option> 136 <option value="Yes">Yes</option>
134 </param> 137 </param>
135 138
136 <param name="length_correction" type="select" label="Apply length correction" help="Mode of length normalization to transcript FPKM."> 139 <param name="length_correction" type="select" label="Apply length correction" help="Mode of length normalization to transcript FPKM.">
137 <option value="" selected="true">Cufflinks Effective Length Correction</option> 140 <option value="" selected="true">Cufflinks Effective Length Correction</option>
138 <option value="--no-effective-length-correction">Standard Length Correction</option> 141 <option value="--no-effective-length-correction">Standard Length Correction</option>
139 <option value="--no-length-correction">No Length Correction at all (use raw counts)</option> 142 <option value="--no-length-correction">No Length Correction at all (use raw counts)</option>
140 </param> 143 </param>
141 144
142 <param name="global_model" type="hidden_data" label="Global model (for use in Trackster)" optional="True"/> 145 <param name="global_model" type="hidden_data" label="Global model (for use in Trackster)" optional="True"/>
143 146
144 <!-- advanced settings --> 147 <!-- advanced settings -->
145 <conditional name="advanced_settings"> 148 <conditional name="advanced_settings">
146 <param name="use_advanced_settings" type="select" label="Set advanced Cufflinks options" help=""> 149 <param name="use_advanced_settings" type="select" label="Set advanced Cufflinks options" help="">
147 <option value="No" selected="true">No</option> 150 <option value="No" selected="true">No</option>
148 <option value="Yes" >Yes</option> 151 <option value="Yes" >Yes</option>
149 </param> 152 </param>
150 <when value="No"></when> 153 <when value="No" />
151 <when value="Yes"> 154 <when value="Yes">
152 155 <param type="select" name="library_type" label="Library prep used for input reads" help="">
153 <param type="select" name="library_type" label="Library prep used for input reads" help=""> 156 <option value="auto" selected="True">Auto Detect</option>
154 <option value="auto" selected="True">Auto Detect</option> 157 <option value="ff-firststrand">ff-firststrand</option>
155 <option value="ff-firststrand">ff-firststrand</option> 158 <option value="ff-secondstrand">ff-secondstrand</option>
156 <option value="ff-secondstrand">ff-secondstrand</option> 159 <option value="ff-unstranded">ff-unstranded</option>
157 <option value="ff-unstranded">ff-unstranded</option> 160 <option value="fr-firststrand">fr-firststrand</option>
158 <option value="fr-firststrand">fr-firststrand</option> 161 <option value="fr-secondstrand">fr-secondstrand</option>
159 <option value="fr-secondstrand">fr-secondstrand</option> 162 <option value="fr-unstranded" >fr-unstranded</option>
160 <option value="fr-unstranded" >fr-unstranded</option> 163 <option value="transfrags">transfrags</option>
161 <option value="transfrags">transfrags</option> 164 </param>
162 </param> 165 <param name="mask_file" type="data" format="gff3,gtf" label="Mask File" help="Ignore all alignment within transcripts in this file " optional="True" />
163 166 <param name="inner_mean_dist" type="integer" value="45" label="Inner mean distance" help="This is the expected (mean) inner distance between mate pairs. For, example, for paired end runs with fragments selected at 300bp,where each end is 50bp, you should set it as 200. The default is 45bp." />
164 <param name="mask_file" type="data" format="gff3,gtf" label="Mask File" help="Ignore all alignment within transcripts in this file " optional="True" /> 167 <param name="inner_dist_std_dev" type="integer" value="20" label="Inner distance standard deviation" help="The standard deviation for the distribution on inner distances between mate pairs. The default is 20bp." />
165 <param name="inner_mean_dist" type="integer" value="45" label="Inner mean distance" help="This is the expected (mean) inner distance between mate pairs. For, example, for paired end runs with fragments selected at 300bp,where each end is 50bp, you should set it as 200. The default is 45bp." /> 168 <param name="max_mle_iterations" type="integer" value="5000" label="Max MLE iterations" help="Sets the number of iterations allowed during maximum likelihood estimation of abundances. Default: 5000" />
166 <param name="inner_dist_std_dev" type="integer" value="20" label="Inner distance standard deviation" help="The standard deviation for the distribution on inner distances between mate pairs. The default is 20bp." /> 169 <param name="junc_alpha" type="float" value="0.001" min="0" max="1" label="Alpha value for the binomial test used during false positive spliced alignment filtration" help="Default: 0.001" />
167 <param name="max_mle_iterations" type="integer" value="5000" label="Max MLE iterations" help="Sets the number of iterations allowed during maximum likelihood estimation of abundances. Default: 5000" /> 170 <param name="small_anchor_fraction" type="float" value="0.09" min="0" max="1" label="percent read overhang taken as suspiciously small" help="Spliced reads with less than this percent of their length on each side of the junction are considered suspicious and are candidates for filtering prior to assembly. Default: 0.09." />
168 <param name="junc_alpha" type="float" value="0.001" min="0" max="1" label="Alpha value for the binomial test used during false positive spliced alignment filtration" help="Default: 0.001" /> 171 <param name="overhang_tolerance" type="integer" value="8" label="Intronic overhang tolerance" help="The number of bp allowed to enter the intron of a transcript when determining if a read or another transcript is mappable to/compatible with it. The default is 8 bp based on the default bowtie/TopHat parameters." />
169 <param name="small_anchor_fraction" type="float" value="0.09" min="0" max="1" label="percent read overhang taken as suspiciously small" help="Spliced reads with less than this percent of their length on each side of the junction are considered suspicious and are candidates for filtering prior to assembly. Default: 0.09." /> 172 <param name="max_bundle_length" type="integer" value="3500000" label="Maximum genomic length of a given bundle" help="Default: 3,500,000bp" />
170 <param name="overhang_tolerance" type="integer" value="8" label="Intronic overhang tolerance" help="The number of bp allowed to enter the intron of a transcript when determining if a read or another transcript is mappable to/compatible with it. The default is 8 bp based on the default bowtie/TopHat parameters." /> 173 <param name="max_bundle_frags" type="integer" value="1000000" label="Maximum number of fragments per locus" help="Sets the maximum number of fragments a locus may have before being skipped. Skipped loci are listed in skipped.gtf. Default: 1,000,000" />
171 <param name="max_bundle_length" type="integer" value="3500000" label="Maximum genomic length of a given bundle" help="Default: 3,500,000bp" /> 174 <param name="min_intron_length" type="integer" value="50" label="Minimal allowed intron size" help="Default: 50bp" />
172 <param name="max_bundle_frags" type="integer" value="1000000" label="Maximum number of fragments per locus" help="Sets the maximum number of fragments a locus may have before being skipped. Skipped loci are listed in skipped.gtf. Default: 1,000,000" /> 175 <param name="trim_three_avgcov_thresh" type="integer" value="10" label="Minimum average coverage required to attempt 3prime trimming." help="Default: 10" />
173 <param name="min_intron_length" type="integer" value="50" label="Minimal allowed intron size" help="Default: 50bp" /> 176 <param name="trim_three_dropoff_frac" type="float" value="0.1" min="0" max="1" label="The fraction of average coverage below which to trim the 3prime end of an assembled transcript." help="Default: 0.1"/>
174 <param name="trim_three_avgcov_thresh" type="integer" value="10" label="Minimum average coverage required to attempt 3prime trimming." help="Default: 10" />
175 <param name="trim_three_dropoff_frac" type="float" value="0.1" min="0" max="1" label="The fraction of average coverage below which to trim the 3prime end of an assembled transcript." help="Default: 0.1"/>
176 </when> 177 </when>
177 </conditional> 178 </conditional>
178 </inputs> 179 </inputs>
179 <outputs> 180 <outputs>
180 <data format="tabular" name="genes_expression" label="${tool.name} on ${on_string}: gene expression" from_work_dir="genes.fpkm_tracking"/> 181 <data format="tabular" name="genes_expression" label="${tool.name} on ${on_string}: gene expression" from_work_dir="genes.fpkm_tracking"/>
181 <data format="tabular" name="transcripts_expression" label="${tool.name} on ${on_string}: transcript expression" from_work_dir="isoforms.fpkm_tracking"/> 182 <data format="tabular" name="transcripts_expression" label="${tool.name} on ${on_string}: transcript expression" from_work_dir="isoforms.fpkm_tracking"/>
182 <data format="gtf" name="assembled_isoforms" label="${tool.name} on ${on_string}: assembled transcripts"/> 183 <data format="gtf" name="assembled_isoforms" label="${tool.name} on ${on_string}: assembled transcripts"/>
183 <data format="txt" name="total_map_mass" label="${tool.name} on ${on_string}: total map mass" hidden="true" from_work_dir="global_model.txt"/> 184 <data format="txt" name="total_map_mass" label="${tool.name} on ${on_string}: total map mass" hidden="true" from_work_dir="global_model.txt"/>
184 <data format="gtf" name="skipped" label="${tool.name} on ${on_string}: Skipped Transcripts" from_working_dir="skipped.gtf"/> 185 <data format="gtf" name="skipped" label="${tool.name} on ${on_string}: Skipped Transcripts" from_work_dir="skipped.gtf"/>
185 </outputs> 186 </outputs>
186 187
187 <trackster_conf> 188 <trackster_conf>
188 <action type="set_param" name="global_model" output_name="total_map_mass"/> 189 <action name="global_model" output_name="total_map_mass"/>
189 </trackster_conf> 190 </trackster_conf>
190 <tests> 191 <tests>
191 <!-- 192 <!--
192 Simple test that uses test data included with cufflinks. 193 Simple test that uses test data included with cufflinks.
193 --> 194 -->
199 <param name="use_ref" value="No"/> 200 <param name="use_ref" value="No"/>
200 <param name="do_bias_correction" value="No"/> 201 <param name="do_bias_correction" value="No"/>
201 <param name="multiread_correct" value="No"/> 202 <param name="multiread_correct" value="No"/>
202 <param name="length_correction" value=""/> 203 <param name="length_correction" value=""/>
203 <param name="use_advanced_settings" value="No" /> 204 <param name="use_advanced_settings" value="No" />
204 <output name="genes_expression" format="tabular" lines_diff="2" file="cufflinks_out3.fpkm_tracking"/> 205 <output name="genes_expression" ftype="tabular" lines_diff="2" file="cufflinks_out3.fpkm_tracking"/>
205 <output name="transcripts_expression" format="tabular" lines_diff="2" file="cufflinks_out2.fpkm_tracking"/> 206 <output name="transcripts_expression" ftype="tabular" lines_diff="2" file="cufflinks_out2.fpkm_tracking"/>
206 <output name="assembled_isoforms" file="cufflinks_out1.gtf"/> 207 <output name="assembled_isoforms" file="cufflinks_out1.gtf"/>
207 <output name="global_model" file="cufflinks_out4.txt"/> 208 <output name="global_model" file="cufflinks_out4.txt"/>
208 <output name="skipped" file="cufflinks_out4.gtf"/> 209 <output name="skipped" file="cufflinks_out4.gtf"/>
209 </test> 210 </test>
210 </tests> 211 </tests>
211 212
212 <help> 213 <help>
213 **Cufflinks Overview** 214 **Cufflinks Overview**
232 233
233 Cufflinks takes a text file of SAM alignments as input. The RNA-Seq read mapper TopHat produces output in this format, and is recommended for use with Cufflinks. However Cufflinks will accept SAM alignments generated by any read mapper. Here's an example of an alignment Cufflinks will accept:: 234 Cufflinks takes a text file of SAM alignments as input. The RNA-Seq read mapper TopHat produces output in this format, and is recommended for use with Cufflinks. However Cufflinks will accept SAM alignments generated by any read mapper. Here's an example of an alignment Cufflinks will accept::
234 235
235 s6.25mer.txt-913508 16 chr1 4482736 255 14M431N11M * 0 0 \ 236 s6.25mer.txt-913508 16 chr1 4482736 255 14M431N11M * 0 0 \
236 CAAGATGCTAGGCAAGTCTTGGAAG IIIIIIIIIIIIIIIIIIIIIIIII NM:i:0 XS:A:- 237 CAAGATGCTAGGCAAGTCTTGGAAG IIIIIIIIIIIIIIIIIIIIIIIII NM:i:0 XS:A:-
237 238
238 Note the use of the custom tag XS. This attribute, which must have a value of "+" or "-", indicates which strand the RNA that produced this read came from. While this tag can be applied to any alignment, including unspliced ones, it must be present for all spliced alignment records (those with a 'N' operation in the CIGAR string). 239 Note the use of the custom tag XS. This attribute, which must have a value of "+" or "-", indicates which strand the RNA that produced this read came from. While this tag can be applied to any alignment, including unspliced ones, it must be present for all spliced alignment records (those with a 'N' operation in the CIGAR string).
239 The SAM file supplied to Cufflinks must be sorted by reference position. If you aligned your reads with TopHat, your alignments will be properly sorted already. If you used another tool, you may want to make sure they are properly sorted as follows:: 240 The SAM file supplied to Cufflinks must be sorted by reference position. If you aligned your reads with TopHat, your alignments will be properly sorted already. If you used another tool, you may want to make sure they are properly sorted as follows::
240 241
241 sort -k 3,3 -k 4,4n hits.sam > hits.sam.sorted 242 sort -k 3,3 -k 4,4n hits.sam > hits.sam.sorted
242 243
261 5 end 77712009 The rightmost coordinate of this record, inclusive. 262 5 end 77712009 The rightmost coordinate of this record, inclusive.
262 6 score 77712009 The most abundant isoform for each gene is assigned a score of 1000. Minor isoforms are scored by the ratio (minor FPKM/major FPKM) 263 6 score 77712009 The most abundant isoform for each gene is assigned a score of 1000. Minor isoforms are scored by the ratio (minor FPKM/major FPKM)
263 7 strand + Cufflinks' guess for which strand the isoform came from. Always one of '+', '-' '.' 264 7 strand + Cufflinks' guess for which strand the isoform came from. Always one of '+', '-' '.'
264 7 frame . Cufflinks does not predict where the start and stop codons (if any) are located within each transcript, so this field is not used. 265 7 frame . Cufflinks does not predict where the start and stop codons (if any) are located within each transcript, so this field is not used.
265 8 attributes See below 266 8 attributes See below
266 267
267 Each GTF record is decorated with the following attributes:: 268 Each GTF record is decorated with the following attributes::
268 269
269 Attribute Example Description 270 Attribute Example Description
270 ----------------------------------------- 271 -----------------------------------------
271 gene_id CUFF.1 Cufflinks gene id 272 gene_id CUFF.1 Cufflinks gene id
273 FPKM 101.267 Isoform-level relative abundance in Reads Per Kilobase of exon model per Million mapped reads 274 FPKM 101.267 Isoform-level relative abundance in Reads Per Kilobase of exon model per Million mapped reads
274 frac 0.7647 Reserved. Please ignore, as this attribute may be deprecated in the future 275 frac 0.7647 Reserved. Please ignore, as this attribute may be deprecated in the future
275 conf_lo 0.07 Lower bound of the 95% confidence interval of the abundance of this isoform, as a fraction of the isoform abundance. That is, lower bound = FPKM * (1.0 - conf_lo) 276 conf_lo 0.07 Lower bound of the 95% confidence interval of the abundance of this isoform, as a fraction of the isoform abundance. That is, lower bound = FPKM * (1.0 - conf_lo)
276 conf_hi 0.1102 Upper bound of the 95% confidence interval of the abundance of this isoform, as a fraction of the isoform abundance. That is, upper bound = FPKM * (1.0 + conf_lo) 277 conf_hi 0.1102 Upper bound of the 95% confidence interval of the abundance of this isoform, as a fraction of the isoform abundance. That is, upper bound = FPKM * (1.0 + conf_lo)
277 cov 100.765 Estimate for the absolute depth of read coverage across the whole transcript 278 cov 100.765 Estimate for the absolute depth of read coverage across the whole transcript
278
279 279
280 Transcripts only: 280 Transcripts only:
281 This file is simply a tab delimited file containing one row per transcript and with columns containing the attributes above. There are a few additional attributes not in the table above, but these are reserved for debugging, and may change or disappear in the future. 281 This file is simply a tab delimited file containing one row per transcript and with columns containing the attributes above. There are a few additional attributes not in the table above, but these are reserved for debugging, and may change or disappear in the future.
282 282
283 Genes only: 283 Genes only:
284 This file contains gene-level coordinates and expression values. 284 This file contains gene-level coordinates and expression values.
285 285
286 ------- 286 -------
287 287
288 **Cufflinks settings** 288 **Cufflinks settings**
289 289
290 All of the options have a default value. You can change any of them. Most of the options in Cufflinks have been implemented here. 290 All of the options have a default value. You can change any of them. Most of the options in Cufflinks have been implemented here.
298 -m INT This is the expected (mean) inner distance between mate pairs. For, example, for paired end runs with fragments selected at 300bp, where each end is 50bp, you should set -r to be 200. The default is 45bp. 298 -m INT This is the expected (mean) inner distance between mate pairs. For, example, for paired end runs with fragments selected at 300bp, where each end is 50bp, you should set -r to be 200. The default is 45bp.
299 -s INT The standard deviation for the distribution on inner distances between mate pairs. The default is 20bp. 299 -s INT The standard deviation for the distribution on inner distances between mate pairs. The default is 20bp.
300 -I INT The minimum intron length. Cufflinks will not report transcripts with introns longer than this, and will ignore SAM alignments with REF_SKIP CIGAR operations longer than this. The default is 300,000. 300 -I INT The minimum intron length. Cufflinks will not report transcripts with introns longer than this, and will ignore SAM alignments with REF_SKIP CIGAR operations longer than this. The default is 300,000.
301 -F After calculating isoform abundance for a gene, Cufflinks filters out transcripts that it believes are very low abundance, because isoforms expressed at extremely low levels often cannot reliably be assembled, and may even be artifacts of incompletely spliced precursors of processed transcripts. This parameter is also used to filter out introns that have far fewer spliced alignments supporting them. The default is 0.05, or 5% of the most abundant isoform (the major isoform) of the gene. 301 -F After calculating isoform abundance for a gene, Cufflinks filters out transcripts that it believes are very low abundance, because isoforms expressed at extremely low levels often cannot reliably be assembled, and may even be artifacts of incompletely spliced precursors of processed transcripts. This parameter is also used to filter out introns that have far fewer spliced alignments supporting them. The default is 0.05, or 5% of the most abundant isoform (the major isoform) of the gene.
302 -j Some RNA-Seq protocols produce a significant amount of reads that originate from incompletely spliced transcripts, and these reads can confound the assembly of fully spliced mRNAs. Cufflinks uses this parameter to filter out alignments that lie within the intronic intervals implied by the spliced alignments. The minimum depth of coverage in the intronic region covered by the alignment is divided by the number of spliced reads, and if the result is lower than this parameter value, the intronic alignments are ignored. The default is 5%. 302 -j Some RNA-Seq protocols produce a significant amount of reads that originate from incompletely spliced transcripts, and these reads can confound the assembly of fully spliced mRNAs. Cufflinks uses this parameter to filter out alignments that lie within the intronic intervals implied by the spliced alignments. The minimum depth of coverage in the intronic region covered by the alignment is divided by the number of spliced reads, and if the result is lower than this parameter value, the intronic alignments are ignored. The default is 5%.
303 -G Tells Cufflinks to use the supplied reference annotation to estimate isoform expression. It will not assemble novel transcripts, and the program will ignore alignments not structurally compatible with any reference transcript. 303 -G Tells Cufflinks to use the supplied reference annotation to estimate isoform expression. It will not assemble novel transcripts, and the program will ignore alignments not structurally compatible with any reference transcript.
304 -N With this option, Cufflinks excludes the contribution of the top 25 percent most highly expressed genes from the number of mapped fragments used in the FPKM denominator. This can improve robustness of differential expression calls for less abundant genes and transcripts. 304 -N With this option, Cufflinks excludes the contribution of the top 25 percent most highly expressed genes from the number of mapped fragments used in the FPKM denominator. This can improve robustness of differential expression calls for less abundant genes and transcripts.
305 </help> 305 </help>
306 <citations> 306 <citations>
307 <citation type="doi">10.1038/nbt.1621</citation> 307 <citation type="doi">10.1038/nbt.1621</citation>
308 </citations> 308 </citations>