<?xml version="1.0" encoding="utf-8"?>
<!DOCTYPE knimeNode PUBLIC "-//UNIKN//DTD KNIME Node 2.0//EN" "http://www.knime.org/Node.dtd">
<knimeNode icon="generic_node.png" type="Manipulator">
    <name>IDFilter</name>
    
    <shortDescription>
        Filters results from protein or peptide identification engines based on different criteria.
    </shortDescription>
    
    <fullDescription>
        <intro><p>Filters results from protein or peptide identification engines based on different criteria.</p>
		<p>
			<a href="http://ftp.mi.fu-berlin.de/OpenMS/release-documentation/html/TOPP_IDFilter.html">Web Documentation for IDFilter</a>
		</p>

        </intro>
        
		<option name="version">Version of the tool that generated this parameters file.</option>
		<option name="min_length">Keep only peptide hits with a length greater or equal this value. Value 0 will have no filter effect.</option>
		<option name="max_length">Keep only peptide hits with a length less or equal this value. Value 0 will have no filter effect. Value is overridden by min_length, i.e. if max_length &lt; min_length, max_length will be ignored.</option>
		<option name="min_charge">Keep only peptide hits for tandem spectra with charge greater or equal this value.</option>
		<option name="var_mods">Keep only peptide hits with variable modifications (fixed modifications from SearchParameters will be ignored).</option>
		<option name="unique">If a peptide hit occurs more than once per PSM, only one instance is kept.</option>
		<option name="unique_per_protein">Only peptides matching exactly one protein are kept. Remember that isoforms count as different proteins!</option>
		<option name="keep_unreferenced_protein_hits">Proteins not referenced by a peptide are retained in the ids.</option>
		<option name="remove_decoys">Remove proteins according to the information in the user parameters. Usually used in combination with 'delete_unreferenced_peptide_hits'.</option>
		<option name="delete_unreferenced_peptide_hits">Peptides not referenced by any protein are deleted in the ids. Usually used in combination with 'score:prot' or 'thresh:prot'.</option>
		<option name="log">Name of log file (created only when specified)</option>
		<option name="debug">Sets the debug level</option>
		<option name="threads">Sets the number of threads allowed to be used by the TOPP tool</option>
		<option name="no_progress">Disables progress logging to command line</option>
		<option name="force">Overwrite tool specific checks.</option>
		<option name="test">Enables the test mode (needed for internal use only)</option>
		<option name="rt">Retention time range to extract.</option>
		<option name="mz">Mass-to-charge range to extract.</option>
		<option name="allow_missing">When filtering by precursor RT or m/z, keep peptide IDs with missing precursor information ('RT'/'MZ' meta values)?</option>
		<option name="pep">The score which should be reached by a peptide hit to be kept. The score is dependent on the most recent(!) preprocessing - it could be Mascot scores (if a MascotAdapter was applied before), or an FDR (if FalseDiscoveryRate was applied before), etc.</option>
		<option name="prot">The score which should be reached by a protein hit to be kept. Use in combination with 'delete_unreferenced_peptide_hits' to remove affected peptides.</option>
		<option name="pep">Keep a peptide hit only if its score is above this fraction of the peptide significance threshold.</option>
		<option name="prot">Keep a protein hit only if its score is above this fraction of the protein significance threshold. Use in combination with 'delete_unreferenced_peptide_hits' to remove affected peptides.</option>
		<option name="by_seq_only">Match peptides with FASTA file by sequence instead of accession and disable protein filtering.</option>
		<option name="ignore_modifications">Compare blacklisted peptides by sequence only.#br#</option>
		<option name="p_value">Retention time filtering by the p-value predicted by RTPredict.</option>
		<option name="p_value_1st_dim">Retention time filtering by the p-value predicted by RTPredict for first dimension.</option>
		<option name="error">Filtering by deviation to theoretical mass (disabled for negative values).</option>
		<option name="unit">Absolute or relative error.</option>
		<option name="n_peptide_hits">Keep only the 'n' highest scoring peptide hits per spectrum (for n&gt;0).</option>
		<option name="n_protein_hits">Keep only the 'n' highest scoring protein hits (for n&gt;0).</option>
		<option name="strict">Keep only the highest scoring peptide hit.#br#Similar to n_peptide_hits=1, but if there are two or more highest scoring hits, none are kept.</option>
		<option name="n_to_m_peptide_hits">peptide hit rank range to extracts</option>

    </fullDescription>
    
    <ports>
		<inPort index="0" name="in [idXML]">input file  [idXML]</inPort>
		<inPort index="1" name="proteins [fasta]">filename of a FASTA file containing protein sequences.#br#All peptides that are not a substring of a sequence in this file are removed#br#All proteins whose accession is not present in this file are removed. [fasta,opt.]</inPort>
		<inPort index="2" name="peptides [idXML]">Peptides having the same sequence and modification assignment as any peptide in this file will be filtered out. Use with blacklist:ignore_modification flag to only compare by sequence.#br# [idXML,opt.]</inPort>
		<outPort index="0" name="out [idXML]">output file  [idXML]</outPort>
 </ports>
    <views>
        <view index="0" name="IDFilter Std Output">The text sent to standard out during the execution of IDFilter.</view>
        <view index="1" name="IDFilter Error Output">The text sent to standard error during the execution of IDFilter. (If it appears in gray, it's the output of a previously failing run which is preserved for your trouble shooting.)</view>
    </views>    
</knimeNode>
