comparison w4mclassfilter.xml @ 13:c18040b6e8b9 draft

"planemo upload for repository https://github.com/HegemanLab/w4mclassfilter_galaxy_wrapper/tree/master commit 1a5dd14c3697516bc55950bd6e46c978af7c19cf"
author eschen42
date Thu, 24 Oct 2019 10:21:23 -0400
parents 38f509903a0b
children 87ec0d3c2266
comparison
equal deleted inserted replaced
12:38f509903a0b 13:c18040b6e8b9
1 <tool id="w4mclassfilter" name="W4m Data Subset" version="0.98.13"> 1 <tool id="w4mclassfilter" name="W4m Data Subset" version="0.98.14">
2 <description>Filter W4m data by values or metadata</description> 2 <description>Filter W4m data by values or metadata</description>
3 <!-- Here is the hyphenation standard that I *try* to apply consistently in my documentation: http://www.sandranoonan.com/dont-let-hyphenation-drive-crazy/ --> 3 <!-- Here is the hyphenation standard that I *try* to apply consistently in my documentation: http://www.sandranoonan.com/dont-let-hyphenation-drive-crazy/ -->
4 <requirements> 4 <requirements>
5 <requirement type="package" version="3.6.1">r-base</requirement> 5 <requirement type="package" version="3.6.1">r-base</requirement>
6 <requirement type="package" version="1.1_5">r-batch</requirement> 6 <requirement type="package" version="1.1_5">r-batch</requirement>
7 <requirement type="package" version="0.98.13">w4mclassfilter</requirement> 7 <requirement type="package" version="0.98.14">w4mclassfilter</requirement>
8 </requirements> 8 </requirements>
9 <command detect_errors="aggressive"><![CDATA[ 9 <command detect_errors="aggressive"><![CDATA[
10 unset R_HOME; 10 unset R_HOME;
11 Rscript $__tool_directory__/w4mclassfilter_wrapper.R 11 Rscript $__tool_directory__/w4mclassfilter_wrapper.R
12 dataMatrix_in '$dataMatrix_in' 12 dataMatrix_in '$dataMatrix_in'
21 transformation '$transformation' 21 transformation '$transformation'
22 imputation '$imputation' 22 imputation '$imputation'
23 dataMatrix_out '$dataMatrix_out' 23 dataMatrix_out '$dataMatrix_out'
24 sampleMetadata_out '$sampleMetadata_out' 24 sampleMetadata_out '$sampleMetadata_out'
25 variableMetadata_out '$variableMetadata_out' 25 variableMetadata_out '$variableMetadata_out'
26 order_vrbl '$order_vrbl'
27 order_smpl '$order_smpl'
26 ]]></command> 28 ]]></command>
27 <inputs> 29 <inputs>
28 <param name="dataMatrix_in" format="tabular" label="Data matrix file" type="data" 30 <param name="dataMatrix_in" format="tabular" label="Data matrix file" type="data"
29 help="variables &#10006; samples" /> 31 help="data matrix, with sample names in first row and feature names in first column" />
30 <param name="sampleMetadata_in" format="tabular" label="Sample metadata file" type="data" 32 <param name="sampleMetadata_in" format="tabular" label="Sample metadata file" type="data"
31 help="sample metadata, one row per sample" /> 33 help="sample metadata, with one row per sample" />
32 <param name="variableMetadata_in" format="tabular" label="Variable metadata file" type="data" 34 <param name="variableMetadata_in" format="tabular" label="Variable metadata file" type="data"
33 help="variable metadata, one row per variable" /> 35 help="variable metadata, with one row per feature" />
34 <param name="classnameColumn" label="Column that names the sample-class" type="text" value = "class" 36 <param name="classnameColumn" label="Column that names the sample-class" type="text" value = "class"
35 help="name of the column in sample metadata that has the values to be tested against the 'Names of sample-classes' input parameter - defaults to 'class'"> 37 help="name of the column in sample metadata that has the values to be tested against the 'Names of sample-classes' input parameter">
36 <sanitizer> 38 <sanitizer>
37 <valid initial="string.letters"> 39 <valid initial="string.letters">
38 <add preset="string.digits"/> 40 <add preset="string.digits"/>
39 <add value="&#46;" /> <!-- dot, period --> 41 <add value="&#46;" /> <!-- dot, period -->
40 <add value="&#95;" /> <!-- underscore --> 42 <add value="&#95;" /> <!-- underscore -->
41 </valid> 43 </valid>
42 </sanitizer> 44 </sanitizer>
43 </param> 45 </param>
44 <param name="sampleclassNames" label="Names of sample-classes" type="text" value = "" 46 <param name="sampleclassNames" label="Names of sample-classes" type="text" value = ""
45 help="comma-separated names (or regular expressions to match names) of sample-classes to filter in or out; defaults to no names"> 47 help="comma-separated names (or regular expressions to match names) of sample-classes to filter in or out (Leave empty to match no names.)">
46 <sanitizer> 48 <sanitizer>
47 <valid initial="string.letters"> 49 <valid initial="string.letters">
48 <add preset="string.digits"/> 50 <add preset="string.digits"/>
49 <add value="&#123;" /> <!-- l-cube, left-curly-bracket --> 51 <add value="&#123;" /> <!-- l-cube, left-curly-bracket -->
50 <add value="&#124;" /> <!-- pipe --> 52 <add value="&#124;" /> <!-- pipe -->
67 <add value="&#95;" /> <!-- underscore --> 69 <add value="&#95;" /> <!-- underscore -->
68 </valid> 70 </valid>
69 </sanitizer> 71 </sanitizer>
70 </param> 72 </param>
71 <param name="wildcards" label="Use 'wild cards' or 'regular expressions'" type="select" 73 <param name="wildcards" label="Use 'wild cards' or 'regular expressions'" type="select"
72 help="'wild-cards' (the default) - use '*' and '?' to match class names; 'regular-expressions' - use regular expressions to match class names"> 74 help="'wild-cards' - use '*' and '?' to match class names; &#160;&#160; 'regular-expressions' - use regular expressions to match class names">
73 <option value="TRUE" selected="true">wild-cards</option> 75 <option value="TRUE" selected="true">wild-cards</option>
74 <option value="FALSE">regular-expressions</option> 76 <option value="FALSE">regular-expressions</option>
75 </param> 77 </param>
76 <param name="inclusive" label="Exclude/include named classes" type="select" 78 <param name="inclusive" label="Exclude/include named classes" type="select"
77 help="'filter-out' (the default) - exclude only the named sample-classes; 'filter-in' - include only the named sample-classes"> 79 help="'filter-out' - exclude only the named sample-classes; &#160;&#160; 'filter-in' - include only the named sample-classes">
78 <option value="TRUE">filter-in</option> 80 <option value="TRUE">filter-in</option>
79 <option value="FALSE" selected="true">filter-out</option> 81 <option value="FALSE" selected="true">filter-out</option>
80 </param> 82 </param>
81 <param name="variableRangeFilter" label="Variable-range filters" type="text" value = "" 83 <param name="variableRangeFilter" label="Variable-range filters" type="text" value = ""
82 help="comma-separated filters, each specified as 'variableMetadataColumnName:min:max'; default is no filters. (See help below.)"> 84 help="comma-separated filters, each specified as 'variableMetadataColumnName:min:max' (leave empty for no filtering, as described in help below.)">
83 <sanitizer> 85 <sanitizer>
84 <valid initial="string.letters"> 86 <valid initial="string.letters">
85 <add preset="string.digits"/> 87 <add preset="string.digits"/>
86 <add value="&#44;" /> <!-- comma --> 88 <add value="&#44;" /> <!-- comma -->
87 <add value="&#46;" /> <!-- dot, period --> 89 <add value="&#46;" /> <!-- dot, period -->
89 <add value="&#95;" /> <!-- underscore --> 91 <add value="&#95;" /> <!-- underscore -->
90 </valid> 92 </valid>
91 </sanitizer> 93 </sanitizer>
92 </param> 94 </param>
93 <param name="transformation" label="Data-transformation" type="select" 95 <param name="transformation" label="Data-transformation" type="select"
94 help="'none' (the default) - do not transform data; 'log2' - log base 2 of data; 'log10' - log base 10 of data; in all cases, negative and missing values are imputed to zero"> 96 help="'none' - do not transform data; &#160;&#160; 'log2' - log base 2 of data; &#160;&#160; 'log10' - log base 10 of data; &#160;&#160; in all cases, negative and missing values are imputed to zero">
95 <option value="none" selected="true">none</option> 97 <option value="none" selected="true">none</option>
96 <option value="log2">log2</option> 98 <option value="log2">log2</option>
97 <option value="log10">log10</option> 99 <option value="log10">log10</option>
98 </param> 100 </param>
99 <param name="imputation" label="Imputation of missing values" type="select" 101 <param name="imputation" label="Imputation of missing values" type="select"
100 help="'zero' (the default) - replace missing values with zero; 'center' - replace missing values with feature-median; 'none' - perform no imputation"> 102 help="'zero' - replace missing values with zero; &#160;&#160; 'center' - replace missing values with feature-median; &#160;&#160; 'none' - perform no imputation">
101 <option value="zero" selected="true">zero</option> 103 <option value="zero" selected="true">zero</option>
102 <option value="center">center</option> 104 <option value="center">center</option>
103 <option value="none">none</option> 105 <option value="none">none</option>
106 </param>
107 <param name="order_smpl" label="Column that specifies order for samples" type="text" value = "sampleMetadata"
108 help="name of the column in sample metadata that is used to sort samples">
109 <sanitizer>
110 <valid initial="string.letters">
111 <add preset="string.digits"/>
112 <add value="&#46;" /> <!-- dot, period -->
113 <add value="&#95;" /> <!-- underscore -->
114 </valid>
115 </sanitizer>
116 </param>
117 <param name="order_vrbl" label="Column that specifies order for features" type="text" value = "variableMetadata"
118 help="name of the column in variable metadata that is used to sort features">
119 <sanitizer>
120 <valid initial="string.letters">
121 <add preset="string.digits"/>
122 <add value="&#46;" /> <!-- dot, period -->
123 <add value="&#95;" /> <!-- underscore -->
124 </valid>
125 </sanitizer>
104 </param> 126 </param>
105 </inputs> 127 </inputs>
106 <outputs> 128 <outputs>
107 <data name="dataMatrix_out" format="tabular" label="${dataMatrix_in.name}.subset" ></data> 129 <data name="dataMatrix_out" format="tabular" label="${dataMatrix_in.name}.subset" ></data>
108 <data name="sampleMetadata_out" format="tabular" label="${sampleMetadata_in.name}.subset" ></data> 130 <data name="sampleMetadata_out" format="tabular" label="${sampleMetadata_in.name}.subset" ></data>
550 ----------------------------------------------------------------------------------------------------------------------------------------- 572 -----------------------------------------------------------------------------------------------------------------------------------------
551 573
552 574
553 **Tool updates** 575 **Tool updates**
554 576
555 See the **NEWS** section at the bottom of this page 577 See https://github.com/HegemanLab/w4mclassfilter_galaxy_wrapper#news
556 578
557 --------------------------------------------------- 579 ---------------------------------------------------
558 580
559 =========================================================== 581 ===========================================================
560 "W4m Data Subset" - Filter Workflow4Metabolomics data files 582 "W4m Data Subset" - Filter Workflow4Metabolomics data files
597 This tool also performs several operations to address several data issues that may impede downstream statistical analysis: 619 This tool also performs several operations to address several data issues that may impede downstream statistical analysis:
598 620
599 - Samples that are missing from either sampleMetadata or dataMatrix are eliminated. 621 - Samples that are missing from either sampleMetadata or dataMatrix are eliminated.
600 - Features that are missing from either variableMetadata or dataMatrix are eliminated. 622 - Features that are missing from either variableMetadata or dataMatrix are eliminated.
601 - Features and samples that have zero variance are eliminated. 623 - Features and samples that have zero variance are eliminated.
602 - Samples and features are sorted alphabetically in rows and columns of dataMatrix and in rows of variableMetadata and sampleMetadata. 624 - Samples and features have consistent order in `variableMetadata`, `sampleMetadata`, and `dataMatrix`.
625 (The column for sorting `variableMetadata` or `sampleMetadata` may be specified.)
603 - The names of the first columns of variableMetadata and sampleMetadata are set respectively to "variableMetadata" and "sampleMetadata". 626 - The names of the first columns of variableMetadata and sampleMetadata are set respectively to "variableMetadata" and "sampleMetadata".
604 - If desired, the values in the dataMatrix may be log-transformed. 627 - If desired, the values in the dataMatrix may be log-transformed.
605 - If desired, each missing value in dataMatrix is replaced with zero or the median value observed for the corresponding feature. 628 - If desired, each missing value in dataMatrix is replaced with zero or the median value observed for the corresponding feature.
606 629
607 This tool may be applied several times sequentially, which may be useful for: 630 This tool may be applied several times sequentially, which may be useful for:
636 ---------- 659 ----------
637 Parameters 660 Parameters
638 ---------- 661 ----------
639 662
640 Data matrix file 663 Data matrix file
641 | variable x sample **dataMatrix** (tabular separated values) file of the numeric data matrix, with . as decimal, and NA for missing values; the table must not contain metadata apart from row and column names; the row and column names must be identical, respectively, to the rownames of the sample metadata file and variable metadata file 664 | feature x sample **dataMatrix** (tabular separated values) file of the numeric data matrix, with period-character ('.') as decimal, and 'NA' for missing values; the table must not contain metadata apart from the required row and column names; the row and column names must be identical (with regard to both content or order) to the respective rownames of the sample metadata file and variable metadata file
642 | 665 |
643 666
644 Sample metadata file 667 Sample metadata file
645 | sample x metadata **sampleMetadata** (tabular separated values) file of the numeric and/or character sample metadata, with . as decimal and NA for missing values 668 | sample x metadata **sampleMetadata** (tabular separated values) file of the numeric and/or character sample metadata, with . as decimal and NA for missing values
646 | 669 |
681 | '``none``' - Do not impute data matrix values. 704 | '``none``' - Do not impute data matrix values.
682 | '``zero``' - Negative and missing values are imputed to zero. 705 | '``zero``' - Negative and missing values are imputed to zero.
683 | '``center``' - For each feature, negative and missing values are imputed to the median of other values. 706 | '``center``' - For each feature, negative and missing values are imputed to the median of other values.
684 | 707 |
685 708
709 Column that specifies order for samples (default = 'sampleMetadata')
710 | name of the column in **sampleMetadata** that is used to sort samples; only letters, digits, periods, and underscores are permitted.
711 |
712
713 Column that specifies order for features (default = 'variableMetadata')
714 | name of the column in **variableMetadata** that is used to sort features; only letters, digits, periods, and underscores are permitted.
715 |
686 716
687 ------------ 717 ------------
688 Output files 718 Output files
689 ------------ 719 ------------
690 720
831 +---------------------------------------------+-------------------------------+ 861 +---------------------------------------------+-------------------------------+
832 | Data transforamtion | none | 862 | Data transforamtion | none |
833 +---------------------------------------------+-------------------------------+ 863 +---------------------------------------------+-------------------------------+
834 | Missing-value imputation | center | 864 | Missing-value imputation | center |
835 +---------------------------------------------+-------------------------------+ 865 +---------------------------------------------+-------------------------------+
866 | Sample-sort column | sampleMetadata |
867 +---------------------------------------------+-------------------------------+
868 | Feature-sort column | variableMetadata |
869 +---------------------------------------------+-------------------------------+
836 870
837 **Expected outputs** 871 **Expected outputs**
838 872
839 +-------------------+-------------------------------------------------------------------------------------------------------------------------------------------------+ 873 +-------------------+-------------------------------------------------------------------------------------------------------------------------------------------------+
840 | Expected Output | Download from URL | 874 | Expected Output | Download from URL |
869 | Variable range-filters | FEATMAX:20.93157:,mz:200:,rt::800 | 903 | Variable range-filters | FEATMAX:20.93157:,mz:200:,rt::800 |
870 +---------------------------------------------+-----------------------------------+ 904 +---------------------------------------------+-----------------------------------+
871 | Data transforamtion | log2 | 905 | Data transforamtion | log2 |
872 +---------------------------------------------+-----------------------------------+ 906 +---------------------------------------------+-----------------------------------+
873 | Missing-value imputation | zero | 907 | Missing-value imputation | zero |
908 +---------------------------------------------+-----------------------------------+
909 | Sample-sort column | sampleMetadata |
910 +---------------------------------------------+-----------------------------------+
911 | Feature-sort column | variableMetadata |
874 +---------------------------------------------+-----------------------------------+ 912 +---------------------------------------------+-----------------------------------+
875 913
876 **Expected outputs** 914 **Expected outputs**
877 915
878 +-------------------+---------------------------------------------------------------------------------------------------------------------------------------------------+ 916 +-------------------+---------------------------------------------------------------------------------------------------------------------------------------------------+