comparison eics_first_extraction.xml @ 3:4e9b2d0c010b draft

Uploaded

3:4e9b2d0c010b

<tool id="2021_05_mz_eics_first_extraction" name="MS-centroid -> EICs-individual"  version="0.0.2">

  <description>   </description>
  
  <requirements>
      <requirement type="package" >scilab</requirement>
  </requirements>
  
  
  <stdio>
      <exit_code range="1:" level="fatal" />
  </stdio>
  
  
  <command>
  <![CDATA[ 
  $__root_dir__/packages/scilab-*/bin/scilab-cli -nb -quit -f ${script_file} 
  ]]>
  </command>
  

  <configfiles>
    <configfile name="script_file">
       <![CDATA[ exec("$__tool_directory__/src/mz_3_extract_all_mz2.sci",-1); ...
        exec("$__tool_directory__/src/mz_4_scan_mz_raw6.sci",-1); ...
        exec("$__tool_directory__/src/mz_5_tr_matrix6bis.sci",-1); ...
        exec("$__tool_directory__/src/mz_6bis_durbin_watson.sci",-1); ...
        exec("$__tool_directory__/src/mz_6_rescan_mz2.sci",-1); ...
        exec("$__tool_directory__/src/mz_7_dwcleaning.sci",-1); ...
        exec("$__tool_directory__/src/mz_eic5_step2.sci",-1); ...
        lasterror(); ...
        load("${resbary}"); ...
        if ~isdef('resbary'); ...
           error('resbary is not defined'); ...
        end; ...
        diffmz=${diffmz}; ...
        set=${signaleicthresh}; ...
        dw=${dw}; ...
        x_tr_mz3=mz_eic5_step2(resbary,diffmz,set,dw); ...
        ... //save("${x_tr_mz3}",'x_tr_mz3'); ...
        div2tab(x_tr_mz3,"${x_tr_mz3}"); ...  // 22avril21
        if ~isempty(lasterror(%f)); ...
            write(0,lasterror()); ... 
        end; ]]>
  </configfile>
  </configfiles>


  <inputs>
    <param name="resbary"         format="mat"       type="data"      label="MS-centroid"    />
    <param name="diffmz"          value="0.0024"     type="float"     label="Threshold for the m/z values" />
    <param name="signaleicthresh" value="30000"      type="integer"   label="Threshold for the signals"  />
    <param name="dw"              value="1"          type="float"     label="Threshold for Durbin-Watson"  help="to remove noisy EICs" />
  </inputs>
  
  
  <outputs>
    <data name="x_tr_mz3"   format="tabular"     label="EICs-individual"  />
  </outputs>
  
  
  <tests>
    
      <test>
       <param name="resbary" value="VI2016_AC_4Acentroide-1_k_3mean.mat"/>
       <param name="diffmz" value="0.0024"/>
       <param name="signaleicthresh" value="30000"/>
       <param name="dw" value="1"/>
       <output name="x_tr_mz3"   file="EICs-individual-1_k3mean.tab" compare="sim_size" delta="1000" />
    </test>
    
  </tests>


<help>


**Author**  Jean-Claude Boulet (INRAE).


---------------------------------------------------

==========================================
EXTRACTION OF EICS FROM A CENTROID MS DATA
==========================================

-----------
Description
-----------

The HRMS analysis of a samples yields a MS data.  

From a centroid MS data, a matrix of (RT x m/z) is extracted.

Each column of this matrix is an EIC = Extracted Ion Chromatogram, i.e. the signals of a given m/z value along the retention times. 

------
Inputs
------

**MS-centroid**

It is an HDF5-Scilab structure obtained by the previous processings and containing the fields: 

- resbary.time: the retention times;

- resbary.mzdata: the mass spectra associated to the RTs.



----------
Parameters
----------

Three thresholds have to be determined. 


**Threshold for the m/z values** 

The difference between two m/z values is compared to the threshold; if lower, the m/z values are considered as the same and merged; if higher the m/z values are considered as different. 

Default value: 0.0024. 


**Threshold for the signals**

The EICs whose global signal is under this threshold are dropped from the EIC matrix. 

Default value: 30000.


**Threshold for Durbin-Watson**

Durbin-Watson values can range between 0 and 2. 

EICs with a DW value higher than the threshold are considered as noise and therefore dropped. 

Default value: 1.



-----
Oupts
-----

**EIC-individual matrix**

A matrix of signal intensities obtained from a single MS: 

- rows are the retention times;

- columns are the m/z values determined by the processing.

The file is a .dat HDF5-Scilab format.  

</help>


<citations>

</citations>


</tool>