Skip to content

Instantly share code, notes, and snippets.

@mwalzer
Created June 8, 2016 13:04
Show Gist options
  • Star 0 You must be signed in to star a gist
  • Fork 0 You must be signed in to fork a gist
  • Save mwalzer/a0aa4fca46e12793ca5bce4ceabe7565 to your computer and use it in GitHub Desktop.
Save mwalzer/a0aa4fca46e12793ca5bce4ceabe7565 to your computer and use it in GitHub Desktop.
- old website's workflow -
<?xml version="1.0" encoding="ISO-8859-1"?>
<PARAMETERS version="1.3" xsi:noNamespaceSchemaLocation="http://open-ms.sourceforge.net/schemas/Param_1_3.xsd" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance">
<NODE name="info" description="">
<ITEM name="version" value="1.9.0" type="string" description="" />
<ITEM name="num_vertices" value="5" type="int" description="" />
<ITEM name="num_edges" value="4" type="int" description="" />
<ITEM name="description" value="&lt;![CDATA[&lt;!DOCTYPE HTML PUBLIC &quot;-//W3C//DTD HTML 4.0//EN&quot; &quot;http://www.w3.org/TR/REC-html40/strict.dtd&quot;&gt;
&lt;html&gt;&lt;head&gt;&lt;meta name=&quot;qrichtext&quot; content=&quot;1&quot; /&gt;&lt;style type=&quot;text/css&quot;&gt;
p, li { white-space: pre-wrap; }
&lt;/style&gt;&lt;/head&gt;&lt;body style=&quot; font-family:&apos;Arial&apos;; font-size:12pt; font-weight:400; font-style:normal;&quot;&gt;
&lt;p style=&quot; margin-top:0px; margin-bottom:0px; margin-left:0px; margin-right:0px; -qt-block-indent:0; text-indent:0px;&quot;&gt;&lt;span style=&quot; color:#000000;&quot;&gt;Basic peak picking pipeline using PeakPickerWavelet (use PeakPickerHiRes instead if you have high-resolution data as it is much faster).&lt;/span&gt;&lt;/p&gt;
&lt;p style=&quot;-qt-paragraph-type:empty; margin-top:0px; margin-bottom:0px; margin-left:0px; margin-right:0px; -qt-block-indent:0; text-indent:0px; color:#000000;&quot;&gt;&lt;br /&gt;&lt;/p&gt;
&lt;p style=&quot; margin-top:0px; margin-bottom:0px; margin-left:0px; margin-right:0px; -qt-block-indent:0; text-indent:0px;&quot;&gt;&lt;span style=&quot; color:#000000;&quot;&gt;Using NoiseFilterSGolay (assuming low-res data) and BaselineFilter (for MALDI data).&lt;/span&gt;&lt;/p&gt;
&lt;p style=&quot;-qt-paragraph-type:empty; margin-top:0px; margin-bottom:0px; margin-left:0px; margin-right:0px; -qt-block-indent:0; text-indent:0px; color:#000000;&quot;&gt;&lt;br /&gt;&lt;/p&gt;
&lt;p style=&quot; margin-top:0px; margin-bottom:0px; margin-left:0px; margin-right:0px; -qt-block-indent:0; text-indent:0px;&quot;&gt;&lt;span style=&quot; color:#000000;&quot;&gt;Depending on your data, either of the two filters may be removed or reconfigured with other parameters.&lt;/span&gt;&lt;/p&gt;&lt;/body&gt;&lt;/html&gt;]]&gt;" type="string" description="" />
</NODE>
<NODE name="vertices" description="">
<NODE name="0" description="">
<ITEM name="recycle_output" value="false" type="string" description="" />
<ITEM name="toppas_type" value="input file list" type="string" description="" />
<ITEMLIST name="file_names" type="string" description="">
</ITEMLIST>
<ITEM name="x_pos" value="-320" type="float" description="" />
<ITEM name="y_pos" value="0" type="float" description="" />
</NODE>
<NODE name="1" description="">
<ITEM name="recycle_output" value="false" type="string" description="" />
<ITEM name="toppas_type" value="tool" type="string" description="" />
<ITEM name="tool_name" value="NoiseFilterSGolay" type="string" description="" />
<ITEM name="tool_type" value="" type="string" description="" />
<ITEM name="x_pos" value="-140" type="float" description="" />
<ITEM name="y_pos" value="0" type="float" description="" />
<NODE name="parameters" description="">
<ITEM name="in" value="" type="string" description="input raw data file " tags="input file,required" restrictions="*.mzML" />
<ITEM name="out" value="" type="string" description="output raw data file " tags="output file,required" restrictions="*.mzML" />
<ITEM name="log" value="TOPP.log" type="string" description="Name of log file (created only when specified)" tags="advanced" />
<ITEM name="debug" value="0" type="int" description="Sets the debug level" tags="advanced" />
<ITEM name="threads" value="1" type="int" description="Sets the number of threads allowed to be used by the TOPP tool" />
<ITEM name="no_progress" value="false" type="string" description="Disables progress logging to command line" tags="advanced" restrictions="true,false" />
<ITEM name="test" value="false" type="string" description="Enables the test mode (needed for internal use only)" tags="advanced" restrictions="true,false" />
<NODE name="algorithm" description="Algorithm parameters section">
<ITEM name="frame_length" value="11" type="int" description="The number of subsequent data points used for smoothing.#br#This number has to be uneven. If it is not, 1 will be added." />
<ITEM name="polynomial_order" value="3" type="int" description="Order or the polynomial that is fitted." />
</NODE>
</NODE>
</NODE>
<NODE name="2" description="">
<ITEM name="recycle_output" value="false" type="string" description="" />
<ITEM name="toppas_type" value="tool" type="string" description="" />
<ITEM name="tool_name" value="BaselineFilter" type="string" description="" />
<ITEM name="tool_type" value="" type="string" description="" />
<ITEM name="x_pos" value="40" type="float" description="" />
<ITEM name="y_pos" value="0" type="float" description="" />
<NODE name="parameters" description="">
<ITEM name="in" value="" type="string" description="input raw data file " tags="input file,required" restrictions="*.mzML" />
<ITEM name="out" value="" type="string" description="output raw data file " tags="output file,required" restrictions="*.mzML" />
<ITEM name="struc_elem_length" value="3" type="float" description="Length of the structuring element (should be wider than maximal peak width - see documentation)." />
<ITEM name="struc_elem_unit" value="Thomson" type="string" description="Unit of &apos;struc_elem_length&apos; parameter." restrictions="Thomson,DataPoints" />
<ITEM name="method" value="tophat" type="string" description="The name of the morphological filter to be applied. If you are unsure, use the default." restrictions="identity,erosion,dilation,opening,closing,gradient,tophat,bothat,erosion_simple,dilation_simple" />
<ITEM name="log" value="TOPP.log" type="string" description="Name of log file (created only when specified)" tags="advanced" />
<ITEM name="debug" value="0" type="int" description="Sets the debug level" tags="advanced" />
<ITEM name="threads" value="1" type="int" description="Sets the number of threads allowed to be used by the TOPP tool" />
<ITEM name="no_progress" value="false" type="string" description="Disables progress logging to command line" tags="advanced" restrictions="true,false" />
<ITEM name="test" value="false" type="string" description="Enables the test mode (needed for internal use only)" tags="advanced" restrictions="true,false" />
</NODE>
</NODE>
<NODE name="3" description="">
<ITEM name="recycle_output" value="false" type="string" description="" />
<ITEM name="toppas_type" value="tool" type="string" description="" />
<ITEM name="tool_name" value="PeakPickerWavelet" type="string" description="" />
<ITEM name="tool_type" value="" type="string" description="" />
<ITEM name="x_pos" value="220" type="float" description="" />
<ITEM name="y_pos" value="0" type="float" description="" />
<NODE name="parameters" description="">
<ITEM name="in" value="" type="string" description="input profile data file " tags="input file,required" restrictions="*.mzML" />
<ITEM name="out" value="" type="string" description="output peak file " tags="output file,required" restrictions="*.mzML" />
<ITEM name="log" value="TOPP.log" type="string" description="Name of log file (created only when specified)" tags="advanced" />
<ITEM name="debug" value="0" type="int" description="Sets the debug level" tags="advanced" />
<ITEM name="threads" value="1" type="int" description="Sets the number of threads allowed to be used by the TOPP tool" />
<ITEM name="no_progress" value="false" type="string" description="Disables progress logging to command line" tags="advanced" restrictions="true,false" />
<ITEM name="test" value="false" type="string" description="Enables the test mode (needed for internal use only)" tags="advanced" restrictions="true,false" />
<NODE name="algorithm" description="Algorithm parameters section">
<ITEM name="signal_to_noise" value="1" type="float" description="Minimal signal to noise ratio for a peak to be picked." restrictions="0:" />
<ITEM name="centroid_percentage" value="0.8" type="float" description="Percentage of the maximum height that the raw data points must exceed to be taken into account for the calculation of the centroid. If it is 1 the centroid position corresponds to the position of the highest intensity." tags="advanced" restrictions="0:1" />
<ITEM name="peak_width" value="0.15" type="float" description="Approximate fwhm of the peaks." restrictions="0:" />
<ITEM name="estimate_peak_width" value="false" type="string" description="Flag if the average peak width shall be estimated. Attention: when this flag is set, the peak_width is ignored." restrictions="true,false" />
<ITEM name="fwhm_lower_bound_factor" value="0.7" type="float" description="Factor that calculates the minimal fwhm value from the peak_width. All peaks with width smaller than fwhm_bound_factor * peak_width are discarded." tags="advanced" restrictions="0:" />
<ITEM name="fwhm_upper_bound_factor" value="20" type="float" description="Factor that calculates the maximal fwhm value from the peak_width. All peaks with width greater than fwhm_upper_bound_factor * peak_width are discarded." tags="advanced" restrictions="0:" />
<ITEM name="optimization" value="no" type="string" description="If the peak parameters position, intensity and left/right widthshall be optimized set optimization to one_dimensional or two_dimensional." tags="advanced" restrictions="no,one_dimensional,two_dimensional" />
<NODE name="thresholds" description="">
<ITEM name="peak_bound" value="10" type="float" description="Minimal peak intensity." tags="advanced" restrictions="0:" />
<ITEM name="peak_bound_ms2_level" value="10" type="float" description="Minimal peak intensity for MS/MS peaks." tags="advanced" restrictions="0:" />
<ITEM name="correlation" value="0.5" type="float" description="minimal correlation of a peak and the raw signal. If a peak has a lower correlation it is skipped." tags="advanced" restrictions="0:1" />
<ITEM name="noise_level" value="0.1" type="float" description="noise level for the search of the peak endpoints." tags="advanced" restrictions="0:" />
<ITEM name="search_radius" value="3" type="int" description="search radius for the search of the maximum in the signal after a maximum in the cwt was found" tags="advanced" restrictions="0:" />
</NODE>
<NODE name="wavelet_transform" description="">
<ITEM name="spacing" value="0.001" type="float" description="spacing of the cwt." tags="advanced" restrictions="0:" />
</NODE>
<NODE name="optimization" description="">
<ITEM name="iterations" value="15" type="int" description="maximal number of iterations for the fitting step" tags="advanced" restrictions="1:" />
<ITEM name="delta_abs_error" value="9.99999974737875e-05" type="float" description="if the absolute error gets smaller than this value the fitting is stopped." tags="advanced" restrictions="0:" />
<ITEM name="delta_rel_error" value="9.99999974737875e-05" type="float" description="if the relative error gets smaller than this value the fitting is stopped" tags="advanced" restrictions="0:" />
<NODE name="penalties" description="">
<ITEM name="position" value="0" type="float" description="penalty term for the fitting of the position:If it differs too much from the initial one it can be penalized " tags="advanced" restrictions="0:" />
<ITEM name="left_width" value="1" type="float" description="penalty term for the fitting of the left width:If the left width differs too much from the initial one during the fitting it can be penalized." tags="advanced" restrictions="0:" />
<ITEM name="right_width" value="1" type="float" description="penalty term for the fitting of the right width:If the right width differs too much from the initial one during the fitting it can be penalized." tags="advanced" restrictions="0:" />
<ITEM name="height" value="1" type="float" description="penalty term for the fitting of the intensity (only used in 2D Optimization):If it gets negative during the fitting it can be penalized." tags="advanced" restrictions="0:" />
</NODE>
<NODE name="2d" description="">
<ITEM name="tolerance_mz" value="2.2" type="float" description="mz tolerance for cluster construction" tags="advanced" restrictions="0:" />
<ITEM name="max_peak_distance" value="1.2" type="float" description="maximal peak distance in mz in a cluster" tags="advanced" restrictions="0:" />
</NODE>
</NODE>
<NODE name="deconvolution" description="">
<ITEM name="deconvolution" value="false" type="string" description="If you want heavily overlapping peaks to be separated set this value to &quot;true&quot;" tags="advanced" restrictions="true,false" />
<ITEM name="asym_threshold" value="0.3" type="float" description="If the symmetry of a peak is smaller than asym_thresholds it is assumed that it consists of more than one peak and the deconvolution procedure is started." tags="advanced" restrictions="0:" />
<ITEM name="left_width" value="2" type="float" description="1/left_width is the initial value for the left width of the peaks found in the deconvolution step." tags="advanced" restrictions="0:" />
<ITEM name="right_width" value="2" type="float" description="1/right_width is the initial value for the right width of the peaks found in the deconvolution step." tags="advanced" restrictions="0:" />
<ITEM name="scaling" value="0.12" type="float" description="Initial scaling of the cwt used in the seperation of heavily overlapping peaks. The initial value is used for charge 1, for higher charges it is adapted to scaling/charge." tags="advanced" restrictions="0:" />
<NODE name="fitting" description="">
<ITEM name="fwhm_threshold" value="0.7" type="float" description="If the fwhm of a peak is higher than fwhm_thresholds it is assumed that it consists of more than one peak and the deconvolution procedure is started." tags="advanced" restrictions="0:" />
<ITEM name="eps_abs" value="9.99999974737875e-06" type="float" description="if the absolute error gets smaller than this value the fitting is stopped." tags="advanced" restrictions="0:" />
<ITEM name="eps_rel" value="9.99999974737875e-06" type="float" description="if the relative error gets smaller than this value the fitting is stopped." tags="advanced" restrictions="0:" />
<ITEM name="max_iteration" value="10" type="int" description="maximal number of iterations for the fitting step" tags="advanced" restrictions="1:" />
<NODE name="penalties" description="">
<ITEM name="position" value="0" type="float" description="penalty term for the fitting of the peak position:If the position changes more than 0.5Da during the fitting it can be penalized as well as discrepancies of the peptide mass rule." tags="advanced" restrictions="0:" />
<ITEM name="height" value="1" type="float" description="penalty term for the fitting of the intensity:If it gets negative during the fitting it can be penalized." tags="advanced" restrictions="0:" />
<ITEM name="left_width" value="0" type="float" description="penalty term for the fitting of the left width:If the left width gets too broad or negative during the fitting it can be penalized." tags="advanced" restrictions="0:" />
<ITEM name="right_width" value="0" type="float" description="penalty term for the fitting of the right width:If the right width gets too broad or negative during the fitting it can be penalized." tags="advanced" restrictions="0:" />
</NODE>
</NODE>
</NODE>
<NODE name="SignalToNoiseEstimationParameter" description="">
<ITEM name="max_intensity" value="-1" type="int" description="maximal intensity considered for histogram construction. By default, it will be calculated automatically (see auto_mode). Only provide this parameter if you know what you are doing (and change &apos;auto_mode&apos; to &apos;-1&apos;)! All intensities EQUAL/ABOVE &apos;max_intensity&apos; will not be added to the histogram. If you choose &apos;max_intensity&apos; too small, the noise estimate might be too small as well. If chosen too big, the bins become quite large (which you could counter by increasing &apos;bin_count&apos;, which increases runtime)." tags="advanced" restrictions="-1:" />
<ITEM name="auto_max_stdev_factor" value="3" type="float" description="parameter for &apos;max_intensity&apos; estimation (if &apos;auto_mode&apos; == 0): mean + &apos;auto_max_stdev_factor&apos; * stdev" tags="advanced" restrictions="0:999" />
<ITEM name="auto_max_percentile" value="95" type="int" description="parameter for &apos;max_intensity&apos; estimation (if &apos;auto_mode&apos; == 1): auto_max_percentile th percentile" tags="advanced" restrictions="0:100" />
<ITEM name="auto_mode" value="0" type="int" description="method to use to determine maximal intensity: -1 --&gt; use &apos;max_intensity&apos;; 0 --&gt; &apos;auto_max_stdev_factor&apos; method (default); 1 --&gt; &apos;auto_max_percentile&apos; method" tags="advanced" restrictions="-1:1" />
<ITEM name="win_len" value="200" type="float" description="window length in Thomson" tags="advanced" restrictions="1:" />
<ITEM name="bin_count" value="30" type="int" description="number of bins for intensity values" tags="advanced" restrictions="3:" />
<ITEM name="stdev_mp" value="3" type="float" description="multiplier for stdev" tags="advanced" restrictions="0.01:999" />
<ITEM name="min_required_elements" value="10" type="int" description="minimum number of elements required in a window (otherwise it is considered sparse)" tags="advanced" restrictions="1:" />
<ITEM name="noise_for_empty_window" value="1e+20" type="float" description="noise value used for sparse windows" tags="advanced" />
</NODE>
</NODE>
</NODE>
</NODE>
<NODE name="4" description="">
<ITEM name="recycle_output" value="false" type="string" description="" />
<ITEM name="toppas_type" value="output file list" type="string" description="" />
<ITEM name="x_pos" value="400" type="float" description="" />
<ITEM name="y_pos" value="0" type="float" description="" />
</NODE>
</NODE>
<NODE name="edges" description="">
<NODE name="0" description="">
<NODE name="source/target" description="">
<ITEM name="" value="0/1" type="string" description="" />
</NODE>
<NODE name="source_out_param" description="">
<ITEM name="" value="__no_name__" type="string" description="" />
</NODE>
<NODE name="target_in_param" description="">
<ITEM name="" value="in" type="string" description="" />
</NODE>
</NODE>
<NODE name="1" description="">
<NODE name="source/target" description="">
<ITEM name="" value="1/2" type="string" description="" />
</NODE>
<NODE name="source_out_param" description="">
<ITEM name="" value="out" type="string" description="" />
</NODE>
<NODE name="target_in_param" description="">
<ITEM name="" value="in" type="string" description="" />
</NODE>
</NODE>
<NODE name="2" description="">
<NODE name="source/target" description="">
<ITEM name="" value="2/3" type="string" description="" />
</NODE>
<NODE name="source_out_param" description="">
<ITEM name="" value="out" type="string" description="" />
</NODE>
<NODE name="target_in_param" description="">
<ITEM name="" value="in" type="string" description="" />
</NODE>
</NODE>
<NODE name="3" description="">
<NODE name="source/target" description="">
<ITEM name="" value="3/4" type="string" description="" />
</NODE>
<NODE name="source_out_param" description="">
<ITEM name="" value="out" type="string" description="" />
</NODE>
<NODE name="target_in_param" description="">
<ITEM name="" value="__no_name__" type="string" description="" />
</NODE>
</NODE>
</NODE>
</PARAMETERS>
@mwalzer
Copy link
Author

mwalzer commented Jun 8, 2016

from old website's workflow section:

�Basic peak picking pipeline using PeakPickerWavelet (use PeakPickerHiRes instead if you have high-resolution data as it is much faster).

Using NoiseFilterSGolay (assuming low-res data) and BaselineFilter (for MALDI data).

Depending on your data, either of the two filters may be removed or reconfigured with other parameters.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment