annotate imputation.xml @ 1:2e7d47c0b027 draft

"planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
author malex
date Mon, 08 Mar 2021 22:04:06 +0000
parents
children caba07f41453
Ignore whitespace changes - Everywhere: Within whitespace: At end of lines:
rev   line source
1
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
1 <tool id="secimtools_imputation" name="Imputation (Mean, Median, K-Nearest Neighbours, Stochastic)" version="@WRAPPER_VERSION@">
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
2 <description>of missing values using selected algorithm.</description>
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
3 <macros>
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
4 <import>macros.xml</import>
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
5 </macros>
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
6 <expand macro="requirements" />
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
7 <stdio>
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
8 <exit_code range="1:" level="warning" description="UserWarning"/>
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
9 <exit_code range="1:" level="warning" description="VisibleDeprecationWarning"/>
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
10 </stdio>
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
11 <command detect_errors="exit_code"><![CDATA[
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
12 imputation.py
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
13 --input $input
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
14 --design $design
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
15 --ID $uniqID
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
16 --group $group
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
17
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
18 --output $imputed
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
19
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
20 --knn $k
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
21 --strategy $imputation
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
22 --row_cutoff $rowCutoff
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
23 --col_cutoff $colCutoff
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
24 --distribution $distribution
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
25
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
26 #if $noZero
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
27 --no_zero
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
28 #end if
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
29
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
30 #if $noNeg
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
31 --no_negative
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
32 #end if
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
33
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
34 #if $exclude
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
35 --exclude $exclude
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
36 #end if
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
37 ]]></command>
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
38 <inputs>
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
39 <param name="input" type="data" format="tabular" label="Wide Dataset" help="Input your tab-separated wide format dataset. If file is not tab separated see TIP below."/>
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
40 <param name="design" type="data" format="tabular" label="Design File" help="Input your design file (tab-separated). Note you need a 'sampleID' column. If not tab separated see TIP below."/>
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
41 <param name="uniqID" type="text" size="30" value="" label="Unique Feature ID" help="Name of the column in your wide dataset that has unique identifiers.."/>
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
42 <param name="group" type="text" size="30" label="Group/Treatment" help="Name of the column in your design file that contains group classifications."/>
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
43 <param name="imputation" size="30" type="select" value="" label="Imputation Strategy" help="Choose an imputation strategy.">
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
44 <option value="knn" selected="true">K-Nearest Neighbors</option>
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
45 <option value="bayesian" selected="true">Stochastic</option>
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
46 <option value="mean" selected="true">Mean</option>
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
47 <option value="median" selected="true">Median</option>
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
48 </param>
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
49 <param name="noZero" type="boolean" label="Count Zeroes as missing" help="Zeroes can be counted as missing or left as data."/>
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
50 <param name="noNeg" type="boolean" label="Count Negative as missing" help="Negatives can be counted as missing or left as data."/>
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
51 <param name="exclude" type="text" size="30" value="" label="Additional values to treat as missing [Optional]" help="Separate additional values to treat as missing data with commas."/>
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
52 <param name="rowCutoff" type="text" size="30" value=".5" label="Row Percent Cutoff Value" help="Proportion of missing values allowed per group per row. If the proportion of missing values for each feature is greater than the specifed value, then the sample mean is imputed instead of values from the K-Nearest Neighbors algorithm. Default: 0.5 (50%)."/>
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
53 <param name="k" type="text" size="30" value="5" label="K value" help="Only for K-Nearest Neighbors Imputation, ignore for other imputation methods. K value is the number of neighbors to search. Default: 5. If less then 5 neighbours are available, all are used."/>
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
54 <param name="colCutoff" type="text" size="30" value=".8" label="Column Percent Cutoff Value" help="Only for K-Nearest Neighbors Imputation, ignore for other imputation methods. If the proportion of missing values is greater than the specified value, the imputation stops and the tool returns an error. Default: 0.8 (80%)."/>
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
55 <param name="distribution" size="30" type="select" value="" label="Bayesian Distribution" help="Only for Stochastic Imputation, ignore for other imputation methods. Choose between normal and Poisson distributions.">
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
56 <option value="Poisson" selected="true">Poisson</option>
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
57 <option value="Normal" selected="true">Normal</option>
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
58 </param>
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
59 </inputs>
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
60 <outputs>
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
61 <data format="tabular" name="imputed" label="${tool.name} on ${on_string}"/>
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
62 </outputs>
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
63 <tests>
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
64 <test>
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
65 <param name="input" value="ST000006_data.tsv"/>
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
66 <param name="design" value="ST000006_design.tsv"/>
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
67 <param name="uniqID" value="Retention_Index" />
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
68 <param name="group" value="White_wine_type_and_source" />
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
69 <param name="imputation" value="knn" />
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
70 <output name="imputed" file="ST000006_imputation_output_KNN.tsv" />
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
71 </test>
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
72 </tests>
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
73 <help><![CDATA[
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
74
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
75 @TIP_AND_WARNING@
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
76
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
77 **Tool Description**
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
78
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
79 The tool performs an imputation procedure for missing data based on three conceptually different methods:
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
80
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
81 (1) naive imputation (mean, median),
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
82 (2) K-nearest neighbor imputation (KNN) and
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
83 (3) stochastic imputation (based on normal and Poisson distributions)
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
84
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
85 Imputations are performed separately for each sample group since treatment groups are expected to be different.
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
86 If only a single sample (column) is available for a given group, nothing is imputed and the sample is kept intact.
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
87 An option to select which values should be treated as missing is included.
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
88 The default value for missing data is an empty cell in the dataset with the option to treat zeroes, negative values and user-defined value(s) as missing and subsequently impute missing values.
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
89
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
90 (1) Naive imputation:
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
91
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
92 Computes the mean (or median) of the features within the samples for a given group and uses that value to impute values for that feature among the missing samples.
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
93 Feature values for all missing samples in the group get the same value equal to the mean (median) of the available samples, provided the allowed missing threshold is met.
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
94
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
95 (2) K-Nearest Neighbors (KNN) imputation:
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
96
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
97 Based on the procedure where nearest neighbor samples (K value default = 5) for the given sample within each group are considered.
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
98 The neighboring samples are used to generate the missing value for the current samples.
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
99 If less than the specified K value number of neighbors are available for the current sample in the current group, then the maximum available number of neighbors is used.
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
100 If the proportion of missing values for each row (feature) is greater than the specified Row Percent Cutoff value (default 0.5), then the column (sample) mean is imputed instead of values from the KNN algorithm.
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
101 The proportion of missing values for each column (sample) can be specified (Column Percent Cutoff default = 0.8) and determines whether a sample should be imputed or not.
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
102 If the proportion of missing values for each sample is greater than the specified value, then the missing values are not imputed and the imputation process is interrupted.
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
103 The algorithm is deterministic and always imputes the same missing values for the same settings.
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
104 More details on the algorithm are available via the reference and link below:
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
105
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
106 Olga Troyanskaya, Michael Cantor, Gavin Sherlock, Pat Brown, Trevor Hastie, Robert Tibshirani, David Botstein and Russ B. Altman, Missing value estimation methods for DNA microarrays BIOINFORMATICS Vol. 17 no. 6. 2001 Pages 520-525.
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
107
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
108 https://bioconductor.org/packages/release/bioc/html/impute.html
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
109
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
110 (3) Stochastic imputation:
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
111
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
112 Based on the assumption that each feature within a given group follows some underlying distribution.
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
113 As a result, all missing values are generated from the underlying distribution.
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
114 The parameter(s) of the underlying distribution is (are) estimated from the observed features.
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
115 Two distribution options are available:
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
116
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
117 Normal (recommended for logged and negative data) and Poisson (recommended for nonnegative counts).
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
118 The normal distribution parameters are estimated by the mean and standard deviation of the observed samples for a given feature.
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
119 If all observed values for a feature are the same, then the standard deviation is assumed to be 1/3 the absolute value of the mean.
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
120 The Poisson distribution parameter is estimated by the mean of the observed values for a given feature and is expected to be positive for the imputation procedure to work correctly.
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
121
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
122 --------------------------------------------------------------------------------
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
123
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
124 **Note**
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
125
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
126 - This tool currently treats all variables as continuous numeric
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
127 variables. Running the tool on categorical variables might result in
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
128 incorrect results.
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
129 - Rows containing non-numeric (or missing) data in any
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
130 of the chosen columns will be skipped from the analysis.
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
131
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
132 --------------------------------------------------------------------------------
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
133
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
134 **Input**
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
135
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
136 - Two input datasets are required.
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
137
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
138 @WIDE@
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
139
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
140 **NOTE:** The sample IDs must match the sample IDs in the Design File (below).
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
141 Extra columns will automatically be ignored.
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
142
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
143 @METADATA@
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
144
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
145 @UNIQID@
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
146
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
147 @GROUP@
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
148
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
149 **Imputation Strategy.**
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
150
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
151 - Select an imputation strategy.
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
152
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
153 **Count Zeroes as missing.**
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
154
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
155 - Zeroes can be treated as missing or left as data.
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
156
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
157 **Count Negative as missing.**
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
158
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
159 - Negatives can be treated as missing or left as data.
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
160
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
161 **Additional values to treat missing [Optional].**
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
162
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
163 - Additional values to treat as missing data, separate with commas.
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
164
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
165 **Row Percent Cutoff Value.**
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
166
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
167 - Proportion of missing values allowed per group per row. If the proportion of missing samples in the row is greater than the cutoff value specified, nothing will be imputed for that row. Default: 0.5 (50%).
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
168
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
169 **K value.**
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
170
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
171 - If you are not using the KNN Imputation, then ignore. K value is the number of neighbors to search. Default: 5. If less then 5 neighbours are available, all are used.
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
172
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
173 **Column Percent Cutoff Value.**
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
174
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
175 - If you are not using the KNN Imputation, then ignore. The maximum proportion of missing data allowed in any data column (sample). Default: 0.8 (80%). The imputation will fail if the proportion in the data exceeds this cutoff!
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
176
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
177 **Bayesian Distribution.**
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
178
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
179 - Choose between Normal and Poisson distributions for stochastic imputation.
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
180
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
181 --------------------------------------------------------------------------------
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
182
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
183 **Output**
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
184
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
185 TSV file containing the same column names as the original Wide Dataset where the values in each cell correspond to either the original values or to values obtained during the imputation procedure.
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
186
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
187
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
188 ]]></help>
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
189 <expand macro="citations"/>
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
190 </tool>