comparison scanpy-multiplet-scrublet.xml @ 7:2f9517a24c73 draft default tip

planemo upload for repository https://github.com/ebi-gene-expression-group/container-galaxy-sc-tertiary/tree/develop/tools/tertiary-analysis/scanpy commit ee197a80b2d591c393e1662854bc119b2ecab11e-dirty

6:fadc4fbf8025

<?xml version="1.0" encoding="utf-8"?>
<tool id="scanpy_multiplet_scrublet" name="Scanpy Scrublet" version="@TOOL_VERSION@+galaxy93" profile="@PROFILE@">
  <description>remove multiplets from annData objects with Scrublet</description>
  <macros>
    <import>scanpy_macros2.xml</import>
  </macros>
  <expand macro="requirements"/>
  <command detect_errors="exit_code"><![CDATA[
ln -s '${input_obj_file}' input.h5 &&
PYTHONIOENCODING=utf-8 scanpy-multiplet scrublet 
#if $threshold
    --threshold '${threshold}'
#end if
#if $batch_key
  --batch-key '${batch_key}'

  <tests>
    <test>
      <param name="input_obj_file" value="read_10x.h5"/>
      <param name="input_format" value="anndata"/>
      <param name="output_format" value="anndata"/>
      <output name="output_h5" file="scrublet.h5" ftype="h5" compare="sim_size"/>
    </test>
  </tests>

  <help><![CDATA[
    .. class:: infomark

    **What it does**

    Predict cell doublets using a nearest-neighbor classifier of observed transcriptomes and simulated doublets. Works best if the input is a raw (unnormalized) counts matrix from a single sample or a collection of similar samples from the same experiment. This function is a wrapper around functions that pre-process using Scanpy and directly call functions of Scrublet(). 

    This is a wrapper around the Scanpy wrapper for Scrublet- see https://scanpy.readthedocs.io/en/docsearch/external/scanpy.external.pp.scrublet.html.

    **Note**

    Where a threshold is not provided, Scrublet will try to automatically set one based on simulations, but this does not always work. There will be a warning, and no 'threshold' slot will be populated in .uns['scrublet']. The 'predicted_doublets' slot in .obs will be set to False for all cells such that no filtering will occur if this column is supplied to filtering steps. You can use the 'Scanpy Plot Scrublet' tool to plot the distribution of scores yourself and estimate a threshold to override this behaviour. 

7:2f9517a24c73

<?xml version="1.0" encoding="utf-8"?>
<tool id="scanpy_multiplet_scrublet" name="Scanpy Scrublet" version="@TOOL_VERSION@+galaxy0" profile="@PROFILE@">
  <description>remove multiplets from annData objects with Scrublet</description>
  <macros>
    <import>scanpy_macros2.xml</import>
  </macros>
  <expand macro="requirements"/>
  <command detect_errors="exit_code"><![CDATA[
ln -s '${input_obj_file}' input.h5 &&
PYTHONIOENCODING=utf-8 scanpy-cli multiplet scrublet 
#if $threshold
    --threshold '${threshold}'
#end if
#if $batch_key
  --batch-key '${batch_key}'

  <tests>
    <test>
      <param name="input_obj_file" value="read_10x.h5"/>
      <param name="input_format" value="anndata"/>
      <param name="output_format" value="anndata"/>
      <output name="output_h5" file="scrublet.h5" ftype="h5" compare="sim_size" delta_frac="0.1"/>
    </test>
  </tests>

  <help><![CDATA[
    .. class:: infomark

    **What it does**

    Predict cell doublets using a nearest-neighbor classifier of observed transcriptomes and simulated doublets. Works best if the input is a raw (unnormalized) counts matrix from a single sample or a collection of similar samples from the same experiment. This function is a wrapper around functions that pre-process using Scanpy and directly call functions of Scrublet(). 

    This is a wrapper around the Scanpy wrapper for Scrublet- see https://scanpy.readthedocs.io/en/stable/generated/scanpy.external.pp.scrublet.html.

    **Note**

    Where a threshold is not provided, Scrublet will try to automatically set one based on simulations, but this does not always work. There will be a warning, and no 'threshold' slot will be populated in .uns['scrublet']. The 'predicted_doublets' slot in .obs will be set to False for all cells such that no filtering will occur if this column is supplied to filtering steps. You can use the 'Scanpy Plot Scrublet' tool to plot the distribution of scores yourself and estimate a threshold to override this behaviour.