/tools/ngs_rna/cuffdiff_wrapper.xml
XML | 238 lines | 196 code | 33 blank | 9 comment | 0 complexity | 67bd8b7a5d6b721b410abfa9d9df3f97 MD5 | raw file
1<tool id="cuffdiff" name="Cuffdiff" version="0.0.5"> 2 <!-- Wrapper supports Cuffdiff versions v1.0.0-v1.0.3 --> 3 <description>find significant changes in transcript expression, splicing, and promoter use</description> 4 <requirements> 5 <requirement type="package">cufflinks</requirement> 6 </requirements> 7 <command interpreter="python"> 8 cuffdiff_wrapper.py 9 --FDR=$fdr 10 --num-threads="4" 11 --min-alignment-count=$min_alignment_count 12 13 --isoforms_fpkm_tracking_output=$isoforms_fpkm_tracking 14 --genes_fpkm_tracking_output=$genes_fpkm_tracking 15 --cds_fpkm_tracking_output=$cds_fpkm_tracking 16 --tss_groups_fpkm_tracking_output=$tss_groups_fpkm_tracking 17 --isoforms_exp_output=$isoforms_exp 18 --genes_exp_output=$genes_exp 19 --tss_groups_exp_output=$tss_groups_exp 20 --cds_exp_fpkm_tracking_output=$cds_exp_fpkm_tracking 21 --splicing_diff_output=$splicing_diff 22 --cds_diff_output=$cds_diff 23 --promoters_diff_output=$promoters_diff 24 25 ## Set paired-end data parameters? 26 #if $singlePaired.sPaired == "Yes": 27 -m $singlePaired.mean_inner_distance 28 -s $singlePaired.inner_distance_std_dev 29 #end if 30 31 ## Normalization? 32 #if str($do_normalization) == "Yes": 33 -N 34 #end if 35 36 37 ## Bias correction? 38 #if $bias_correction.do_bias_correction == "Yes": 39 -b 40 #if $bias_correction.seq_source.index_source == "history": 41 --ref_file=$bias_correction.seq_source.ref_file 42 #else: 43 --ref_file="None" 44 #end if 45 --dbkey=${gtf_input.metadata.dbkey} 46 --index_dir=${GALAXY_DATA_INDEX_DIR} 47 #end if 48 49 ## Inputs. 50 --inputA=$gtf_input 51 #if $group_analysis.do_groups == "No": 52 --input1=$aligned_reads1 53 --input2=$aligned_reads2 54 #else: 55 ## Replicates. 56 --labels 57 #for $group in $group_analysis.groups 58 ${group.group} 59 #end for 60 --files 61 #for $group in $group_analysis.groups 62 #for $file in $group.files: 63 ${file.file} 64 #end for 65 , 66 #end for 67 #end if 68 69 </command> 70 <inputs> 71 <param format="gtf" name="gtf_input" type="data" label="Transcripts" help="A transcript GTF file produced by cufflinks, cuffcompare, or other source."/> 72 <conditional name="group_analysis"> 73 <param name="do_groups" type="select" label="Perform replicate analysis" help="Perform cuffdiff with replicates in each group."> 74 <option value="No">No</option> 75 <option value="Yes">Yes</option> 76 </param> 77 <when value="Yes"> 78 <repeat name="groups" title="Group"> 79 <param name="group" title="Group name" type="text" label="Group name (no spaces or commas)"/> 80 <repeat name="files" title="Replicate"> 81 <param name="file" label="Add file" type="data" format="sam,bam"/> 82 </repeat> 83 </repeat> 84 </when> 85 <when value="No"> 86 <param format="sam,bam" name="aligned_reads1" type="data" label="SAM or BAM file of aligned RNA-Seq reads" help=""/> 87 <param format="sam,bam" name="aligned_reads2" type="data" label="SAM or BAM file of aligned RNA-Seq reads" help=""/> 88 </when> 89 </conditional> 90 91 <param name="fdr" type="float" value="0.05" label="False Discovery Rate" help="The allowed false discovery rate."/> 92 <param name="min_alignment_count" type="integer" value="1000" label="Min Alignment Count" help="The minimum number of alignments in a locus for needed to conduct significance testing on changes in that locus observed between samples."/> 93 <param name="do_normalization" type="select" label="Perform quartile normalization" help="Removes top 25% of genes from FPKM denominator to improve accuracy of differential expression calls for low abundance transcripts."> 94 <option value="No">No</option> 95 <option value="Yes">Yes</option> 96 </param> 97 <conditional name="bias_correction"> 98 <param name="do_bias_correction" type="select" label="Perform Bias Correction" help="Bias detection and correction can significantly improve accuracy of transcript abundance estimates."> 99 <option value="Yes">Yes</option> 100 <option value="No">No</option> 101 </param> 102 <when value="Yes"> 103 <conditional name="seq_source"> 104 <param name="index_source" type="select" label="Reference sequence data"> 105 <option value="cached">Locally cached</option> 106 <option value="history">History</option> 107 </param> 108 <when value="cached"></when> 109 <when value="history"> 110 <param name="ref_file" type="data" format="fasta" label="Using reference file" /> 111 </when> 112 </conditional> 113 </when> 114 <when value="No"></when> 115 </conditional> 116 <conditional name="singlePaired"> 117 <param name="sPaired" type="select" label="Set Parameters for Paired-end Reads? (not recommended)"> 118 <option value="No">No</option> 119 <option value="Yes">Yes</option> 120 </param> 121 <when value="No"></when> 122 <when value="Yes"> 123 <param name="mean_inner_distance" type="integer" value="20" label="Mean Inner Distance between Mate Pairs"/> 124 <param name="inner_distance_std_dev" type="integer" value="20" label="Standard Deviation for Inner Distance between Mate Pairs"/> 125 </when> 126 </conditional> 127 </inputs> 128 129 <outputs> 130 <data format="tabular" name="splicing_diff" label="${tool.name} on ${on_string}: splicing differential expression testing"/> 131 <data format="tabular" name="promoters_diff" label="${tool.name} on ${on_string}: promoters differential expression testing"/> 132 <data format="tabular" name="cds_diff" label="${tool.name} on ${on_string}: CDS overloading diffential expression testing"/> 133 <data format="tabular" name="cds_exp_fpkm_tracking" label="${tool.name} on ${on_string}: CDS FPKM differential expression testing"/> 134 <data format="tabular" name="cds_fpkm_tracking" label="${tool.name} on ${on_string}: CDS FPKM tracking"/> 135 <data format="tabular" name="tss_groups_exp" label="${tool.name} on ${on_string}: TSS groups differential expression testing"/> 136 <data format="tabular" name="tss_groups_fpkm_tracking" label="${tool.name} on ${on_string}: TSS groups FPKM tracking" /> 137 <data format="tabular" name="genes_exp" label="${tool.name} on ${on_string}: gene differential expression testing"/> 138 <data format="tabular" name="genes_fpkm_tracking" label="${tool.name} on ${on_string}: gene FPKM tracking"/> 139 <data format="tabular" name="isoforms_exp" label="${tool.name} on ${on_string}: transcript differential expression testing"/> 140 <data format="tabular" name="isoforms_fpkm_tracking" label="${tool.name} on ${on_string}: transcript FPKM tracking"/> 141 </outputs> 142 143 <tests> 144 <test> 145 <!-- 146 cuffdiff cuffcompare_out5.gtf cuffdiff_in1.sam cuffdiff_in2.sam 147 --> 148 <param name="gtf_input" value="cuffcompare_out5.gtf" ftype="gtf" /> 149 <param name="do_groups" value="No" /> 150 <param name="aligned_reads1" value="cuffdiff_in1.sam" ftype="sam" /> 151 <param name="aligned_reads2" value="cuffdiff_in2.sam" ftype="sam" /> 152 <!-- Defaults. --> 153 <param name="fdr" value="0.05" /> 154 <param name="min_alignment_count" value="0" ftype="sam" /> 155 <param name="do_bias_correction" value="No" /> 156 <param name="do_normalization" value="No" /> 157 <param name="sPaired" value="single" ftype="sam" /> 158 <!-- 159 Line diffs are needed because cuffdiff does not produce deterministic output. 160 TODO: can we find datasets that lead to deterministic behavior? 161 --> 162 <output name="splicing_diff" file="cuffdiff_out9.txt"/> 163 <output name="promoters_diff" file="cuffdiff_out10.txt"/> 164 <output name="cds_diff" file="cuffdiff_out11.txt"/> 165 <output name="cds_exp_fpkm_tracking" file="cuffdiff_out4.txt"/> 166 <output name="cds_fpkm_tracking" file="cuffdiff_out8.txt"/> 167 <output name="tss_groups_exp" file="cuffdiff_out3.txt"/> 168 <output name="tss_groups_fpkm_tracking" file="cuffdiff_out7.txt"/> 169 <output name="genes_exp" file="cuffdiff_out2.txt" lines_diff="200"/> 170 <output name="genes_fpkm_tracking" file="cuffdiff_out6.txt" lines_diff="200"/> 171 <output name="isoforms_exp" file="cuffdiff_out1.txt" lines_diff="200"/> 172 <output name="isoforms_fpkm_tracking" file="cuffdiff_out5.txt" lines_diff="200"/> 173 </test> 174 </tests> 175 176 <help> 177**Cuffdiff Overview** 178 179Cuffdiff is part of Cufflinks_. Cuffdiff find significant changes in transcript expression, splicing, and promoter use. 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 180 181.. _Cufflinks: http://cufflinks.cbcb.umd.edu/ 182 183------ 184 185**Know what you are doing** 186 187.. class:: warningmark 188 189There 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. 190 191.. __: http://cufflinks.cbcb.umd.edu/manual.html#cuffdiff 192 193------ 194 195**Input format** 196 197Cuffdiff takes Cufflinks or Cuffcompare GTF files as input along with two SAM files containing the fragment alignments for two or more samples. 198 199------ 200 201**Outputs** 202 203Cuffdiff produces many output files: 204 2051. Transcript FPKM expression tracking. 2062. Gene FPKM expression tracking; tracks the summed FPKM of transcripts sharing each gene_id 2073. Primary transcript FPKM tracking; tracks the summed FPKM of transcripts sharing each tss_id 2084. Coding sequence FPKM tracking; tracks the summed FPKM of transcripts sharing each p_id, independent of tss_id 2095. Transcript differential FPKM. 2106. Gene differential FPKM. Tests difference sin the summed FPKM of transcripts sharing each gene_id 2117. Primary transcript differential FPKM. Tests difference sin the summed FPKM of transcripts sharing each tss_id 2128. Coding sequence differential FPKM. Tests difference sin the summed FPKM of transcripts sharing each p_id independent of tss_id 2139. Differential splicing tests: this tab delimited file lists, for each primary transcript, the amount of overloading detected among its isoforms, i.e. how much differential splicing exists between isoforms processed from a single primary transcript. Only primary transcripts from which two or more isoforms are spliced are listed in this file. 21410. Differential promoter tests: this tab delimited file lists, for each gene, the amount of overloading detected among its primary transcripts, i.e. how much differential promoter use exists between samples. Only genes producing two or more distinct primary transcripts (i.e. multi-promoter genes) are listed here. 21511. Differential CDS tests: this tab delimited file lists, for each gene, the amount of overloading detected among its coding sequences, i.e. how much differential CDS output exists between samples. Only genes producing two or more distinct CDS (i.e. multi-protein genes) are listed here. 216 217------- 218 219**Settings** 220 221All of the options have a default value. You can change any of them. Most of the options in Cuffdiff have been implemented here. 222 223------ 224 225**Cuffdiff parameter list** 226 227This is a list of implemented Cuffdiff options:: 228 229 -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. 230 -s INT The standard deviation for the distribution on inner distances between mate pairs. The default is 20bp. 231 -c INT The minimum number of alignments in a locus for needed to conduct significance testing on changes in that locus observed between samples. If no testing is performed, changes in the locus are deemed not significant, and the locus' observed changes don't contribute to correction for multiple testing. The default is 1,000 fragment alignments (up to 2,000 paired reads). 232 --FDR FLOAT The allowed false discovery rate. The default is 0.05. 233 --num-importance-samples INT Sets the number of importance samples generated for each locus during abundance estimation. Default: 1000 234 --max-mle-iterations INT Sets the number of iterations allowed during maximum likelihood estimation of abundances. Default: 5000 235 -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. 236 237 </help> 238</tool>