Mercurial > repos > florianbegusch > qiime2_suite
view qiime2/qiime_quality-control_evaluate-composition.xml @ 14:a0a8d77a991c draft
Uploaded
author | florianbegusch |
---|---|
date | Thu, 03 Sep 2020 09:51:29 +0000 |
parents | f190567fe3f6 |
children |
line wrap: on
line source
<?xml version="1.0" ?> <tool id="qiime_quality-control_evaluate-composition" name="qiime quality-control evaluate-composition" version="2020.8"> <description>Evaluate expected vs. observed taxonomic composition of samples</description> <requirements> <requirement type="package" version="2020.8">qiime2</requirement> </requirements> <command><![CDATA[ qiime quality-control evaluate-composition --i-expected-features=$iexpectedfeatures --i-observed-features=$iobservedfeatures --p-depth=$pdepth #if str($ppalette) != 'None': --p-palette=$ppalette #end if #if $pnoplottar: --p-no-plot-tar #end if #if $pnoplottdr: --p-no-plot-tdr #end if #if $pplotrvalue: --p-plot-r-value #end if #if $pnoplotrsquared: --p-no-plot-r-squared #end if #if $pplotbraycurtis: --p-plot-bray-curtis #end if #if $pplotjaccard: --p-plot-jaccard #end if #if $pplotobservedfeatures: --p-plot-observed-features #end if #if $pnoplotobservedfeaturesratio: --p-no-plot-observed-features-ratio #end if # if $input_files_mmetadatafile: # def list_dict_to_string(list_dict): # set $file_list = list_dict[0]['additional_input'].__getattr__('file_name') # for d in list_dict[1:]: # set $file_list = $file_list + ' --m-metadata-file=' + d['additional_input'].__getattr__('file_name') # end for # return $file_list # end def --m-metadata-file=$list_dict_to_string($input_files_mmetadatafile) # end if #if '__ob__' in str($mmetadatacolumn): #set $mmetadatacolumn_temp = $mmetadatacolumn.replace('__ob__', '[') #set $mmetadatacolumn = $mmetadatacolumn_temp #end if #if '__cb__' in str($mmetadatacolumn): #set $mmetadatacolumn_temp = $mmetadatacolumn.replace('__cb__', ']') #set $mmetadatacolumn = $mmetadatacolumn_temp #end if #if 'X' in str($mmetadatacolumn): #set $mmetadatacolumn_temp = $mmetadatacolumn.replace('X', '\\') #set $mmetadatacolumn = $mmetadatacolumn_temp #end if #if '__sq__' in str($mmetadatacolumn): #set $mmetadatacolumn_temp = $mmetadatacolumn.replace('__sq__', "'") #set $mmetadatacolumn = $mmetadatacolumn_temp #end if #if '__db__' in str($mmetadatacolumn): #set $mmetadatacolumn_temp = $mmetadatacolumn.replace('__db__', '"') #set $mmetadatacolumn = $mmetadatacolumn_temp #end if #if str($mmetadatacolumn): --m-metadata-column=$mmetadatacolumn #end if --o-visualization=ovisualization #if str($examples) != 'None': --examples=$examples #end if ; cp odatabase.qza $odatabase ; qiime tools export ovisualization.qzv --output-path out && mkdir -p '$ovisualization.files_path' && cp -r out/* '$ovisualization.files_path' && mv '$ovisualization.files_path/index.html' '$ovisualization' ]]></command> <inputs> <param format="qza,no_unzip.zip" label="--i-expected-features: ARTIFACT FeatureTable[RelativeFrequency] Expected feature compositions [required]" name="iexpectedfeatures" optional="False" type="data" /> <param format="qza,no_unzip.zip" label="--i-observed-features: ARTIFACT FeatureTable[RelativeFrequency] Observed feature compositions [required]" name="iobservedfeatures" optional="False" type="data" /> <param label="--p-depth: INTEGER Maximum depth of semicolon-delimited taxonomic ranks to test (e.g., 1 = root, 7 = species for the greengenes reference sequence database). [default: 7]" name="pdepth" optional="True" type="integer" value="7" /> <param label="--p-palette: " name="ppalette" optional="True" type="select"> <option selected="True" value="None">Selection is Optional</option> <option value="Set1">Set1</option> <option value="Set2">Set2</option> <option value="Set3">Set3</option> <option value="Pastel1">Pastel1</option> <option value="Pastel2">Pastel2</option> <option value="Paired">Paired</option> <option value="Accent">Accent</option> <option value="Dark2">Dark2</option> <option value="tab10">tab10</option> <option value="tab20">tab20</option> <option value="tab20b">tab20b</option> <option value="tab20c">tab20c</option> <option value="viridis">viridis</option> <option value="plasma">plasma</option> <option value="inferno">inferno</option> <option value="magma">magma</option> <option value="terrain">terrain</option> <option value="rainbow">rainbow</option> </param> <param label="--p-no-plot-tar: Do not plot taxon accuracy rate (TAR) on score plot. TAR is the number of true positive features divided by the total number of observed features (TAR = true positives / (true positives + false positives)). [default: True]" name="pnoplottar" selected="False" type="boolean" /> <param label="--p-no-plot-tdr: Do not plot taxon detection rate (TDR) on score plot. TDR is the number of true positive features divided by the total number of expected features (TDR = true positives / (true positives + false negatives)). [default: True]" name="pnoplottdr" selected="False" type="boolean" /> <param label="--p-plot-r-value: --p-plot-r-value: / --p-no-plot-r-value Plot expected vs. observed linear regression r value on score plot. [default: False]" name="pplotrvalue" selected="False" type="boolean" /> <param label="--p-no-plot-r-squared: Do not plot expected vs. observed linear regression r-squared value on score plot. [default: True]" name="pnoplotrsquared" selected="False" type="boolean" /> <param label="--p-plot-bray-curtis: --p-plot-bray-curtis: / --p-no-plot-bray-curtis Plot expected vs. observed Bray-Curtis dissimilarity scores on score plot. [default: False]" name="pplotbraycurtis" selected="False" type="boolean" /> <param label="--p-plot-jaccard: --p-plot-jaccard: / --p-no-plot-jaccard Plot expected vs. observed Jaccard distances scores on score plot. [default: False]" name="pplotjaccard" selected="False" type="boolean" /> <param label="--p-plot-observed-features: --p-plot-observed-features: / --p-no-plot-observed-features Plot observed features count on score plot. [default: False]" name="pplotobservedfeatures" selected="False" type="boolean" /> <param label="--p-no-plot-observed-features-ratio: Do not plot ratio of observed:expected features on score plot. [default: True]" name="pnoplotobservedfeaturesratio" selected="False" type="boolean" /> <repeat name="input_files_mmetadatafile" optional="True" title="--m-metadata-file"> <param format="tabular,qza,no_unzip.zip" label="--m-metadata-file: METADATA" name="additional_input" optional="True" type="data" /> </repeat> <param label="--m-metadata-column: COLUMN MetadataColumn[Categorical] Optional sample metadata that maps observed-features sample IDs to expected-features sample IDs. [optional]" name="mmetadatacolumn" optional="False" type="text" /> <param label="--examples: Show usage examples and exit." name="examples" optional="False" type="data" /> </inputs> <outputs> <data format="html" label="${tool.name} on ${on_string}: visualization.html" name="ovisualization" /> </outputs> <help><![CDATA[ Evaluate expected vs. observed taxonomic composition of samples ############################################################### This visualizer compares the feature composition of pairs of observed and expected samples containing the same sample ID in two separate feature tables. Typically, feature composition will consist of taxonomy classifications or other semicolon-delimited feature annotations. Taxon accuracy rate, taxon detection rate, and linear regression scores between expected and observed observations are calculated at each semicolon- delimited rank, and plots of per-level accuracy and observation correlations are plotted. A histogram of distance between false positive observations and the nearest expected feature is also generated, where distance equals the number of rank differences between the observed feature and the nearest common lineage in the expected feature. This visualizer is most suitable for testing per-run data quality on sequencing runs that contain mock communities or other samples with known composition. Also suitable for sanity checks of bioinformatics pipeline performance. Parameters ---------- expected_features : FeatureTable[RelativeFrequency] Expected feature compositions observed_features : FeatureTable[RelativeFrequency] Observed feature compositions depth : Int, optional Maximum depth of semicolon-delimited taxonomic ranks to test (e.g., 1 = root, 7 = species for the greengenes reference sequence database). palette : Str % Choices('Set1', 'Set2', 'Set3', 'Pastel1', 'Pastel2', 'Paired', 'Accent', 'Dark2', 'tab10', 'tab20', 'tab20b', 'tab20c', 'viridis', 'plasma', 'inferno', 'magma', 'terrain', 'rainbow'), optional Color palette to utilize for plotting. plot_tar : Bool, optional Plot taxon accuracy rate (TAR) on score plot. TAR is the number of true positive features divided by the total number of observed features (TAR = true positives / (true positives + false positives)). plot_tdr : Bool, optional Plot taxon detection rate (TDR) on score plot. TDR is the number of true positive features divided by the total number of expected features (TDR = true positives / (true positives + false negatives)). plot_r_value : Bool, optional Plot expected vs. observed linear regression r value on score plot. plot_r_squared : Bool, optional Plot expected vs. observed linear regression r-squared value on score plot. plot_bray_curtis : Bool, optional Plot expected vs. observed Bray-Curtis dissimilarity scores on score plot. plot_jaccard : Bool, optional Plot expected vs. observed Jaccard distances scores on score plot. plot_observed_features : Bool, optional Plot observed features count on score plot. plot_observed_features_ratio : Bool, optional Plot ratio of observed:expected features on score plot. metadata : MetadataColumn[Categorical], optional Optional sample metadata that maps observed_features sample IDs to expected_features sample IDs. Returns ------- visualization : Visualization ]]></help> <macros> <import>qiime_citation.xml</import> </macros> <expand macro="qiime_citation"/> </tool>