Mercurial > repos > iuc > mageck_test

comparison mageck_test.xml @ 2:81bbbddcf285 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-iuc/tree/master/tools/mageck commit 49e456dda49db1f52fc876f406a10273a408b1a2
author iuc
date Wed, 04 Apr 2018 11:03:59 -0400
parents 5e2a28bee02d
children 38073c236d71
comparison
equal deleted inserted replaced
1:5e2a28bee02d 2:81bbbddcf285
22 #end if 22 #end if
23 23
24 -n output 24 -n output
25 25
26 $out.normcounts 26 $out.normcounts
27
27 $out.pdfreport 28 $out.pdfreport
28 29
29 --norm-method $adv.norm_method 30 #if $adv.norm_method:
30 --gene-test-fdr-threshold $adv.fdr_threshold 31 --norm-method $adv.norm_method
31 --adjust-method $adv.adjust_method 32 #end if
33
34 #if $adv.fdr_threshold:
35 --gene-test-fdr-threshold $adv.fdr_threshold
36 #end if
37
38 #if $adv.adjust_method:
39 --adjust-method $adv.adjust_method
40 #end if
41
32 $adv.var_samples 42 $adv.var_samples
33 --sort-criteria $adv.sort_criteria 43
34 44 #if $adv.sort_criteria:
35 --remove-zero $adv.remove_zero 45 --sort-criteria $adv.sort_criteria
46 #end if
47
48 #if $adv.remove_zero:
49 --remove-zero $adv.remove_zero
50 #end if
51
36 #if $adv.remove_zero_threshold: 52 #if $adv.remove_zero_threshold:
37 --remove-zero-threshold $adv.remove_zero_threshold 53 --remove-zero-threshold $adv.remove_zero_threshold
38 #end if 54 #end if
39 55
40 --gene-lfc-method $adv.lfc_method 56 #if $adv.lfc_method:
57 --gene-lfc-method $adv.lfc_method
58 #end if
59
41 #if $adv.control_sgrna: 60 #if $adv.control_sgrna:
42 --control-sgrna $adv.control_sgrna 61 --control-sgrna $adv.control_sgrna
43 #end if 62 #end if
44 63
45 #if $adv.cnv_norm: 64 #if $adv.cnv_norm:
58 help="You can choose to either specify the treated samples or the control"> 77 help="You can choose to either specify the treated samples or the control">
59 <option value="treated">Treated samples</option> 78 <option value="treated">Treated samples</option>
60 <option value="control">Control sample</option> 79 <option value="control">Control sample</option>
61 </param> 80 </param>
62 <when value="treated"> 81 <when value="treated">
63 <param name="treatment_id" argument="--treatment-id" type="text" label="Treated Sample Labels (or Indexes)" help="If sample label is provided, the labels must match the labels in the first line of the count table, separated by comma (,); for example, HL60.final,KBM7.final. For sample index, 0,2 means the 1st and 3rd samples are treatment experiments. See Help below for a detailed description." /> 82 <param name="treatment_id" argument="--treatment-id" type="text" label="Treated Sample Labels (or Indexes)" help="If sample label is provided, the labels must match the labels in the first line of the count table, separated by comma (,); for example, HL60.final,KBM7.final. For sample index, 0,2 means the 1st and 3rd samples are treatment experiments. See Help below for a detailed description.">
83 <validator type="regex" message="Please only use letters, numbers or underscores in sample labels, and separate labels by commas">^[\w,]+$</validator>
84 </param>
64 </when> 85 </when>
65 <when value="control"> 86 <when value="control">
66 <param name="day0_label" argument="--day0-label" type="text" optional="true" value="" label="Control Sample Label" help="Specify the label for the control sample. For every other sample label, the module will treat it as a treatment condition and compare with control sample (usually day 0 or plasmid)" /> 87 <param name="day0_label" argument="--day0-label" type="text" optional="true" value="" label="Control Sample Label" help="Specify the label for the control sample. For every other sample label, the module will treat it as a treatment condition and compare with control sample (usually day 0 or plasmid)">
88 <validator type="regex" message="Please only use letters, numbers or underscores in sample label">^[\w]+$</validator>
89 </param>
67 </when> 90 </when>
68 </conditional> 91 </conditional>
69 <param name="control_id" argument="--control-id" type="text" optional="true" label="Control Sample Labels (or Indexes)" help="If sample label is provided, the labels must match the labels in the first line of the count table, separated by comma (,). Default is all the samples not specified in treatment experiments. See Help below for a detailed description." /> 92 <param name="control_id" argument="--control-id" type="text" optional="true" label="Control Sample Labels (or Indexes)" help="If sample label is provided, the labels must match the labels in the first line of the count table, separated by comma (,). Default is all the samples not specified in treatment experiments. See Help below for a detailed description.">
70 93 <validator type="regex" message="Please only use letters, numbers or underscores in sample labels, and separate labels by commas">^[\w,]+$</validator>
94 </param>
71 <section name="out" title="Output Options"> 95 <section name="out" title="Output Options">
72 <param name="normcounts" argument="--normcounts-to-file" type="boolean" truevalue="--normcounts-to-file" falsevalue="" checked="false" optional="true" label="Output normalized counts file" help="Default: No" /> 96 <param name="normcounts" argument="--normcounts-to-file" type="boolean" truevalue="--normcounts-to-file" falsevalue="" checked="false" optional="true" label="Output normalized counts file" help="Default: No" />
73 <param name="pdfreport" argument="--pdf-report" type="boolean" truevalue="--pdf-report" falsevalue="" checked="false" optional="true" label="Output PDF report" help="Generate pdf report of the input file. Default: No" /> 97 <param name="pdfreport" argument="--pdf-report" type="boolean" truevalue="--pdf-report" falsevalue="" checked="false" optional="true" label="Output plots" help="Generate PDF of the plots. Default: No" />
74 <param name="rscriptOpt" type="boolean" truevalue="True" falsevalue="" checked="false" optional="true" label="Output R script" help="Output the R script used to generate the plots in the pdf report. Default: No" /> 98 <param name="rfilesOpt" type="boolean" truevalue="True" falsevalue="" checked="false" optional="true" label="Output R files" help="Output the .R and .Rnw files to generate the PDF report. The gene summary file will also be output as it is required to regenerate the report. Default: No" />
75 <param name="out_log" type="boolean" truevalue="True" falsevalue="" checked="false" label="Output Log file" help="This file includes the logging information during the execution. Default: No" /> 99 <param name="out_log" type="boolean" truevalue="True" falsevalue="" checked="false" label="Output Log file" help="This file includes the logging information during the execution. Default: No" />
76 </section> 100 </section>
77 101
78 <section name="adv" title="Advanced Options"> 102 <section name="adv" title="Advanced Options">
79 <param name="norm_method" argument="--norm-method" type="select" label="Method for normalization" 103 <param name="norm_method" argument="--norm-method" optional="true" type="select" label="Method for normalization" help="If control is specified, the size factor will be estimated using control sgRNAs specified in --control-sgrna option. Default: Median" >
80 help="If control is specified, the size factor will be estimated using control sgRNAs specified in --control-sgrna option. Default: Median" > 104 <option value="median" selected="True">Median</option>
81 <option value="none">None</option> 105 <option value="none">None</option>
82 <option value="median" selected="True">Median</option>
83 <option value="total">Total</option> 106 <option value="total">Total</option>
84 <option value="control">Control</option> 107 <option value="control">Control</option>
85 </param> 108 </param>
86 <param name="fdr_threshold" argument="--gene-test-fdr-threshold" type="float" value="0.25" min="0" max="1" label="Gene test FDR-adjusted Threshold" help="FDR threshold for gene test. Default: 0.25"/> 109 <param name="fdr_threshold" argument="--gene-test-fdr-threshold" type="float" min="0" max="1" optional="true" label="Gene test FDR-adjusted Threshold" help="FDR threshold for gene test. Default: 0.25"/>
87 <param name="adjust_method" argument="--adjust-method" type="select" label="P-Value Adjustment Method" help="Method for sgRNA-level p-value adjustment, including False Discovery Rate (FDR), Holm's method (Holm), or Pounds's method (Pounds). Default: FDR"> 110 <param name="adjust_method" argument="--adjust-method" type="select" optional="true" label="P-Value Adjustment Method" help="Method for sgRNA-level p-value adjustment, including False Discovery Rate (FDR), Holm's method (Holm), or Pounds's method (Pounds). Default: FDR">
88 <option value="fdr" selected="True">FDR</option> 111 <option value="fdr" selected="True">FDR</option>
89 <option value="holm">Holm</option> 112 <option value="holm">Holm</option>
90 <option value="pounds">Pounds</option> 113 <option value="pounds">Pounds</option>
91 </param> 114 </param>
92 <param name="var_samples" argument="--variance-from-all-samples" type="boolean" truevalue="--variance-from-all-samples" falsevalue="" checked="false" optional="true" label="Estimate the variance from all samples, instead of from only control samples" help="Use this option only if you believe there are relatively few essential sgRNAs or genes between control and treatment samples" /> 115 <param name="var_samples" argument="--variance-from-all-samples" type="boolean" truevalue="--variance-from-all-samples" falsevalue="" checked="false" optional="true" label="Estimate the variance from all samples, instead of from only control samples" help="Use this option only if you believe there are relatively few essential sgRNAs or genes between control and treatment samples" />
93 <expand macro="sort_criteria" /> 116 <expand macro="sort_criteria" />
94 <param name="remove_zero" argument="--remove-zero" type="select" label="Remove zero" help="Remove sgRNAs whose mean value is zero in Control, Treatment, Both control/treatment, or Any control/treatment sample. Default: Both (remove those sgRNAs that are zero in both control and treatment samples)" > 117 <param name="remove_zero" argument="--remove-zero" type="select" optional="true" label="Remove zero" help="Remove sgRNAs whose mean value is zero in Control, Treatment, Both control/treatment, or Any control/treatment sample. Default: Both (remove those sgRNAs that are zero in both control and treatment samples)" >
95 <option value="none" >None</option> 118 <option value="none" >None</option>
96 <option value="control">Control</option> 119 <option value="control">Control</option>
97 <option value="treatment">Treatment</option> 120 <option value="treatment">Treatment</option>
98 <option value="both" selected="True">Both</option> 121 <option value="both" selected="True">Both</option>
99 <option value="any">Any</option> 122 <option value="any">Any</option>
100 </param> 123 </param>
101 <param name="remove_zero_threshold" argument="--remove-zero-threshold" type="float" value="0" label="Remove zero Threshold" help="sgRNA normalized count threshold to be considered removed in the --remove-zero option. Default: 0"/> 124 <param name="remove_zero_threshold" argument="--remove-zero-threshold" type="float" optional="true" label="Remove zero Threshold" help="sgRNA normalized count threshold to be considered removed in the --remove-zero option. Default: 0"/>
102 <param name="lfc_method" argument="--gene-lfc-method" type="select" label="Gene Log-Fold Change Method." help="Method to calculate gene log fold changes (LFC) from sgRNA LFCs. Available methods include the median/mean of all sgRNAs (median/mean), or the median/mean sgRNAs that are ranked in front of the alpha cutoff in RRA (alphamedian/alphamean), or the sgRNA that has the second strongest LFC (secondbest). In the alphamedian/alphamean case, the number of sgRNAs correspond to the goodsgrna column in the output, and the gene LFC will be set to 0 if no sgRNA is in front of the alpha cutoff. Default: Median. (new since v0.5.5)"> 125 <param name="lfc_method" argument="--gene-lfc-method" type="select" optional="true" label="Gene Log-Fold Change Method." help="Method to calculate gene log fold changes (LFC) from sgRNA LFCs. Available methods include the median/mean of all sgRNAs (median/mean), or the median/mean sgRNAs that are ranked in front of the alpha cutoff in RRA (alphamedian/alphamean), or the sgRNA that has the second strongest LFC (secondbest). In the alphamedian/alphamean case, the number of sgRNAs correspond to the goodsgrna column in the output, and the gene LFC will be set to 0 if no sgRNA is in front of the alpha cutoff. Default: Median. (new since v0.5.5)">
103 <option value="median" selected="True">Median</option> 126 <option value="median" selected="True">Median</option>
104 <option value="alphamedian">Alphamedian</option> 127 <option value="alphamedian">Alphamedian</option>
105 <option value="mean">Mean</option> 128 <option value="mean">Mean</option>
106 <option value="alphamean">Alphamean</option> 129 <option value="alphamean">Alphamean</option>
107 <option value="secondbest">Secondbest</option> 130 <option value="secondbest">Secondbest</option>
119 <filter>out['out_log'] is True</filter> 142 <filter>out['out_log'] is True</filter>
120 </data> 143 </data>
121 <data name="normcounts" format="tabular" from_work_dir="output.normalized.txt" label="${tool.name} on ${on_string}: sgRNA Normalized Counts"> 144 <data name="normcounts" format="tabular" from_work_dir="output.normalized.txt" label="${tool.name} on ${on_string}: sgRNA Normalized Counts">
122 <filter>out['normcounts'] is True</filter> 145 <filter>out['normcounts'] is True</filter>
123 </data> 146 </data>
124 <data name="pdfreport" format="pdf" from_work_dir="output.pdf" label="${tool.name} on ${on_string}: PDF Report"> 147 <data name="plots" format="pdf" from_work_dir="output.pdf" label="${tool.name} on ${on_string}: PDF Report">
125 <filter>out['pdfreport'] is True</filter> 148 <filter>out['pdfreport'] is True</filter>
126 </data> 149 </data>
127 <data name="rscript" format="txt" from_work_dir="output.R" label="${tool.name} on ${on_string}: RScript"> 150 <data name="rscript" format="txt" from_work_dir="output.R" label="${tool.name} on ${on_string}: R file" >
128 <filter>out['rscriptOpt'] is True</filter> 151 <filter>out['rfilesOpt'] is True</filter>
152 </data>
153 <data name="rnwfile" format="txt" from_work_dir="output_summary.Rnw" label="${tool.name} on ${on_string}: Rnw file" >
154 <filter>out['rfilesOpt'] is True</filter>
129 </data> 155 </data>
130 </outputs> 156 </outputs>
131 <tests> 157 <tests>
132 <test><!-- Ensure MAGeCK's default output works --> 158 <!-- Ensure MAGeCK's default output works -->
133 <param name="count_table" value="demo/demo1/sample.txt" ftype="tabular" /> 159 <test expect_num_outputs="2">
134 <param name="treatment_id" value="HL60.final,KBM7.final" /> 160 <param name="count_table" value="in.test.sample.txt" ftype="tabular" />
135 <param name="control_id" value="HL60.initial,KBM7.initial" /> 161 <param name="treatment_id" value="HL60_final,KBM7_final" />
162 <param name="control_id" value="HL60_initial,KBM7_initial" />
136 <output name="gene_summary" file="out.test.gene_summary.txt"/> 163 <output name="gene_summary" file="out.test.gene_summary.txt"/>
137 <output name="sgrna_summary" file="out.test.sgrna_summary.txt"/> 164 <output name="sgrna_summary" file="out.test.sgrna_summary.txt"/>
138 </test> 165 </test>
139 <test><!-- Ensure MAGeCK's additional outputs works --> 166 <!-- Ensure MAGeCK's additional outputs works -->
140 <param name="count_table" value="demo/demo1/sample.txt" ftype="tabular" /> 167 <test expect_num_outputs="7">
141 <param name="treatment_id" value="HL60.final,KBM7.final" /> 168 <param name="count_table" value="in.test.sample.txt" ftype="tabular" />
142 <param name="control_id" value="HL60.initial,KBM7.initial" /> 169 <param name="treatment_id" value="HL60_final,KBM7_final" />
170 <param name="control_id" value="HL60_initial,KBM7_initial" />
143 <param name="out_log" value="True" /> 171 <param name="out_log" value="True" />
144 <param name="normcounts" value="True" /> 172 <param name="normcounts" value="True" />
145 <param name="pdfreport" value="True" /> 173 <param name="pdfreport" value="True" />
146 <param name="rscriptOpt" value="True" /> 174 <param name="rfilesOpt" value="True" />
147 <output name="gene_summary" file="out.test.gene_summary.txt"/> 175 <output name="gene_summary" file="out.test.gene_summary.txt"/>
148 <output name="sgrna_summary" file="out.test.sgrna_summary.txt"/> 176 <output name="sgrna_summary" file="out.test.sgrna_summary.txt"/>
149 <output name="normcounts" file="out.test.normalized.txt"/> 177 <output name="normcounts" file="out.test.normalized.txt"/>
150 <output name="log" file="out.test.log.txt" compare="sim_size"/> 178 <output name="log" file="out.test.log.txt" compare="sim_size"/>
151 <output name="pdfreport" file="out.test.pdf" compare="sim_size"/> 179 <output name="plots" file="out.test.plots.pdf" compare="sim_size"/>
152 <output name="rscript" file="out.test.R" /> 180 <output name="rscript" file="out.test.R" />
181 <output name="rnwfile" file="output_summary.Rnw" />
153 </test> 182 </test>
154 </tests> 183 </tests>
155 184
156 <help><![CDATA[ 185 <help><![CDATA[
157 .. class:: infomark 186 .. class:: infomark
207 The optional Control sgRNA file is used to generate null distribution when calculating the p values. If this option is not specified, MAGeCK generates the null distribution of RRA scores by assuming all of the genes in the library are non-essential. This approach is sometimes over-conservative, and you can improve this if you know some genes are not essential. By providing the corresponding sgRNA IDs in this option, MAGeCK will have a better estimation of p values. To use this option, you need to prepare a text file specifying the IDs of control sgRNAs, one line for one sgRNA ID. 236 The optional Control sgRNA file is used to generate null distribution when calculating the p values. If this option is not specified, MAGeCK generates the null distribution of RRA scores by assuming all of the genes in the library are non-essential. This approach is sometimes over-conservative, and you can improve this if you know some genes are not essential. By providing the corresponding sgRNA IDs in this option, MAGeCK will have a better estimation of p values. To use this option, you need to prepare a text file specifying the IDs of control sgRNAs, one line for one sgRNA ID.
208 237
209 ----- 238 -----
210 239
211 **Outputs** 240 **Outputs**
241
242 This tool outputs
243
244 * a ranked sgRNA Summary file
245 * a ranked Gene Summary file
246
247 Optionally, under **Output Options** you can choose to output
248
249 * a Normalized Counts table
250 * a PDF of the plots
251 * the .R and .Rnw files to generate the report
252 * a Log file of the analysis
212 253
213 **sgRNA Summary file** 254 **sgRNA Summary file**
214 255
215 An example of the sgRNA ranking output is as follows: 256 An example of the sgRNA ranking output is as follows:
216 257