# Crux parameter file (generated by Crux version 3.1-f2e7488) # Full documentation available at http://cruxtoolkit.sourceforge.net/ # comet_version 2016.01 rev. 1 # Everything following the '#' symbol is treated as a comment. # Specifies the maximum charge state feature. When set to zero, use the maximum # observed charge state. # Available for make-pin and percolator. max-charge-feature=0 # Path where pin file will be written instead of make-pin.pin. # It is optional for make-pin output-file= # Specify the verbosity of the current processes. Each level prints the # following messages, including all those at lower verbosity levels: 0-fatal # errors, 10-non-fatal errors, 20-warnings, 30-information on the progress of # execution, 40-more progress information, 50-debug info, 60-detailed debug # info. # Available for all crux programs. verbosity=30 # A file containing parameters. # Available for all crux programs. Any options specified on the command line # will override values in the parameter file. parameter-file= # Replace existing files if true or fail when trying to overwrite a file if # false. # Available for all crux programs. Applies to parameter file as well as index, # search, and analysis output files. overwrite=true # The minimum length of peptides to consider. # Used from the command line or parameter file by crux-generate-peptides, and # crux tide-index. min-length=6 # The maximum length of peptides to consider. # Available from command line or parameter file for crux-generate-peptides, crux # tide-index. max-length=50 # The minimum mass (in Da) of peptides to consider. # Available from command line or parameter file for crux-generate-peptides and # crux tide-index. min-mass=200 # The maximum mass (in Da) of peptides to consider. # Available from command line or parameter file for crux-generate-peptides and # crux tide-index. max-mass=7200 # The minimum number of peaks a spectrum must have for it to be searched. # Available for tide-search. min-peaks=20 # Specify the enzyme used to digest the proteins in silico. Available enzymes # (with the corresponding digestion rules indicated in parentheses) include # no-enzyme ([X]|[X]), trypsin ([RK]|{P}), trypsin/p ([RK]|[]), chymotrypsin # ([FWYL]|{P}), elastase ([ALIV]|{P}), clostripain ([R]|[]), cyanogen-bromide # ([M]|[]), iodosobenzoate ([W]|[]), proline-endopeptidase ([P]|[]), # staph-protease ([E]|[]), asp-n ([]|[D]), lys-c ([K]|{P}), lys-n ([]|[K]), # arg-c ([R]|{P}), glu-c ([DE]|{P}), pepsin-a ([FL]|{P}), # elastase-trypsin-chymotrypsin ([ALIVKRWFY]|{P}). Specifying --enzyme no-enzyme # yields a non-enzymatic digest. Warning: the resulting index may be quite # large. # Available for crux-generate-peptides and crux tide-index. enzyme=trypsin # Specify rules for in silico digestion of protein sequences. Overrides the # enzyme option. Two lists of residues are given enclosed in square brackets or # curly braces and separated by a |. The first list contains residues # required/prohibited before the cleavage site and the second list is residues # after the cleavage site. If the residues are required for digestion, they are # in square brackets, '[' and ']'. If the residues prevent digestion, then they # are enclosed in curly braces, '{' and '}'. Use X to indicate all residues. For # example, trypsin cuts after R or K but not before P which is represented as # [RK]|{P}. AspN cuts after any residue but only before D which is represented # as [X]|[D]. To prevent the sequences from being digested at all, use [Z]|[Z]. # custom-enzyme= # Perform a simple deisotoping operation across each MS2 spectrum. For each peak # in an MS2 spectrum, consider lower m/z peaks. If the current peak occurs where # an expected peak would lie for any charge state less than the charge state of # the precursor, within mass tolerance, and if the current peak is of lower # abundance, then the peak is removed. The value of this parameter is the mass # tolerance, in units of parts-per-million. If set to 0, no deisotoping is # performed. # Available for tide-search. deisotope=0 # Specify whether every peptide in the database must have two enzymatic termini # (full-digest) or if peptides with only one enzymatic terminus are also # included (partial-digest). # Available for crux-generate-peptides and crux tide-index. digestion=full-digest # Maximum number of missed cleavages per peptide to allow in enzymatic # digestion. # Available from command line or parameter file for crux-generate-peptides. When # used with enzyme= includes peptides containing # one or more potential cleavage sites. missed-cleavages=0 # Tolerance used for matching peptides to spectra. Peptides must be within +/- # 'precursor-window' of the spectrum value. The precursor window units depend # upon precursor-window-type. # Available for tide-search and crux-generate-peptides. precursor-window=3 # Specify the units for the window that is used to select peptides around the # precursor mass location (mass, mz, ppm). The magnitude of the window is # defined by the precursor-window option, and candidate peptides must fall # within this window. For the mass window-type, the spectrum precursor m+h value # is converted to mass, and the window is defined as that mass +/- # precursor-window. If the m+h value is not available, then the mass is # calculated from the precursor m/z and provided charge. The peptide mass is # computed as the sum of the average amino acid masses plus 18 Da for the # terminal OH group. The mz window-type calculates the window as spectrum # precursor m/z +/- precursor-window and then converts the resulting m/z range # to the peptide mass range using the precursor charge. For the # parts-per-million (ppm) window-type, the spectrum mass is calculated as in the # mass type. The lower bound of the mass window is then defined as the spectrum # mass / (1.0 + (precursor-window / 1000000)) and the upper bound is defined as # spectrum mass / (1.0 - (precursor-window / 1000000)). # Available for search-for-xlinks and tide-search. precursor-window-type=mass # Automatically estimate optimal value for the precursor-window parameter from # the spectra themselves. false=no estimation, warn=try to estimate but use the # default value in case of failure, fail=try to estimate and quit in case of # failure. # Available for tide-search. auto-precursor-window=false # Specify the parser to use for reading in MS/MS spectra. # Available for search-for-xlinks. spectrum-parser=pwiz # Specify whether, when parsing an MS2 spectrum file, Crux obtains the precursor # mass information from the "S" line or the "Z" line. # Available when spectrum-parser = pwiz. use-z-line=true # When creating decoy peptides using decoy-format=shuffle or # decoy-format=peptide-reverse, this option specifies whether the N-terminal and # C-terminal amino acids are kept in place or allowed to be shuffled or # reversed. For a target peptide "EAMPK" with decoy-format=peptide-reverse, # setting keep-terminal-aminos to "NC" will yield "EPMAK"; setting it to "C" # will yield "PMAEK"; setting it to "N" will yield "EKPMA"; and setting it to # "none" will yield "KPMAE". # Available for tide-index. keep-terminal-aminos=NC # Create in the output directory a text file listing of all the peptides in the # database, along with their neutral masses, one per line. If decoys are # generated, then a second file will be created containing the decoy peptides. # Decoys that also appear in the target database are marked with an asterisk in # a third column. # Available for tide-index. peptide-list=false # Stop after the specified pre-processing step. # Available for print-processed-spectra. stop-after=xcorr # Specify the output units for processed spectra. # Available for print-processed-spectra output-units=bin # Outputs an SQT results file to the output directory. Note that if sqt-output # is enabled, then compute-sp is automatically enabled and cannot be overridden. # Available for tide-search. sqt-output=false # Output an mzIdentML results file to the output directory. # Available for tide-search, percolator. mzid-output=false # Output a Percolator input (PIN) file to the output directory. # Available for tide-search. pin-output=false # Output a Percolator pout.xml format results file to the output directory. # Available for percolator. pout-output=false # Output a pepXML results file to the output directory. # Available for tide-search, q-ranker, barista, percolator. pepxml-output=false # Output a tab-delimited results file to the output directory. # Available for tide-search, percolator, q-ranker, barista. txt-output=true # Compute the preliminary score Sp for all candidate peptides. Report this score # in the output, along with the corresponding rank, the number of matched ions # and the total number of ions. This option is recommended if results are to be # analyzed by Percolator or Barista. If sqt-output is enabled, then compute-sp # is automatically enabled and cannot be overridden. Note that the Sp # computation requires re-processing each observed spectrum, so turning on this # switch involves significant computational overhead. # Available for tide-search. compute-sp=false # Estimate the parameters of the score distribution for each spectrum by fitting # to a Weibull distribution, and compute a p-value for each xlink product. This # option is only available when use-old-xlink=F. # Currently only implemented for XCORR. compute-p-values=false # A single scan number or a range of numbers to be searched. Range should be # specified as 'first-last' which will include scans 'first' and 'last'. # The search range x-y is inclusive of x and y. scan-number= # Before calculation of the XCorr score, the m/z axes of the observed and # theoretical spectra are discretized. This parameter specifies the size of each # bin. The exact formula for computing the discretized m/z value is # floor((x/mz-bin-width) + 1.0 - mz-bin-offset), where x is the observed m/z # value. For low resolution ion trap ms/ms data 1.0005079 and for high # resolution ms/ms 0.02 is recommended. # Available for tide-search and xlink-assign-ions. mz-bin-width=1.0005079 # In the discretization of the m/z axes of the observed and theoretical spectra, # this parameter specifies the location of the left edge of the first bin, # relative to mass = 0 (i.e., mz-bin-offset = 0.xx means the left edge of the # first bin will be located at +0.xx Da). # Available for tide-search. mz-bin-offset=0.4 # Automatically estimate optimal value for the mz-bin-width parameter from the # spectra themselves. false=no estimation, warn=try to estimate but use the # default value in case of failure, fail=try to estimate and quit in case of # failure. # Available for tide-search. auto-mz-bin-width=false # Include flanking peaks around singly charged b and y theoretical ions. Each # flanking peak occurs in the adjacent m/z bin and has half the intensity of the # primary peak. # Available for the tide-search and search-for-xlinks commands. use-flanking-peaks=false # The lowest spectrum m/z to search in the ms2 file. # Available for tide-search. spectrum-min-mz=0 # The highest spectrum m/z to search in the ms2 file. # Available for tide-search. spectrum-max-mz=1e+09 # The spectrum charges to search. With 'all' every spectrum will be searched and # spectra with multiple charge states will be searched once at each charge # state. With 1, 2, or 3 only spectra with that charge state will be searched. # Used by tide-search. spectrum-charge=all # The fileroot string will be added as a prefix to all output file names. # Available for all commands that produce an output directory. fileroot=olsen_100ng_30min_15k_01_7 # The name of the directory where output files will be created. # Available for most commands. output-dir=/home/mark/overfit_test/percolator_comet_proteins # The name of the directory where temporary files will be created. If this # parameter is blank, then the system temporary directory will be used # Available for tide-index. temp-dir= # Specify the number of matches to report for each spectrum. # Available for tide-search and crux percolator top-match=5 # Specify the maximum rank to allow when parsing results files. Matches with # ranks higher than this value will be ignored (a value of zero allows matches # with any rank). # top-match-in=0 # When given a unsigned integer value seeds the random number generator with # that value. When given the string "time" seeds the random number generator # with the system time. # Available for all Crux commands. seed=1 # Specify which isotopes to use in calculating fragment ion mass. # Used by crux-predict-peptide-ions. fragment-mass=mono # Specify the type of isotopic masses to use when calculating the peptide mass. # Used from command line or parameter file by crux-generate-peptides. isotopic-mass=mono # The minimum number of modifications that can be applied to a single peptide. # Available for tide-index. min-mods=0 # The maximum number of modifications that can be applied to a single peptide. # Available for tide-index. max-mods=255 # The maximum number of modified amino acids that can appear in one peptide. # Each aa can be modified multiple times. # max-aas-modified=255 # Specify how sequence modifications are reported in various output files. Each # modification is reported as a number enclosed in square braces following the # modified residue; however, the number may correspond to one of three different # masses: (1) 'mod-only' reports the value of the mass shift induced by the # modification; (2) 'total' reports the mass of the residue with the # modification (residue mass plus modification mass); (3) 'separate' is the same # as 'mod-only', but multiple modifications to a single amino acid are reported # as a comma-separated list of values. For example, suppose amino acid D has an # unmodified mass of 115 as well as two moifications of masses +14 and +2. In # this case, the amino acid would be reported as D[16] with 'mod-only', D[131] # with 'total', and D[14,2] with 'separate'. # Available for generate-peptides. mod-mass-format=mod-only # Set the precision for modifications as written to .txt files. # Also changes mods written to parameter file. By default, this value is set # equal to the maximum modification precision in the specification of # modifications. Available for tide-index, tide-search, search-for-xlinks and # generate-peptides. mod-precision=2 # Consider a-ions in the search? Note that an a-ion is equivalent to a neutral # loss of CO from the b-ion. Peak height is 10 (in arbitrary units). # Available for search-for-xlinks and xlink-score-spectrum. use-a-ions=false # Consider b-ions in the search? Peak height is 50 (in arbitrary units). # Available for search-for-xlinks and xlink-score-spectrum. use-b-ions=true # Consider c-ions in the search? Peak height is 50 (in arbitrary units). # Available for search-for-xlinks and xlink-score-spectrum. use-c-ions=false # Consider x-ions in the search? Peak height is 10 (in arbitrary units). # Available for search-for-xlinks and xlink-score-spectrum. use-x-ions=false # Consider y-ions in the search? Peak height is 50 (in arbitrary units). # Available for search-for-xlinks and xlink-score-spectrum. use-y-ions=true # Consider z-ions in the search? Peak height is 50 (in arbitrary units). # Available for search-for-xlinks and xlink-score-spectrum. use-z-ions=false # Set the precision for scores written to sqt and text files. # Available for all commands. precision=8 # Set the precision for masses and m/z written to sqt and text files. # Available for all commands. mass-precision=4 # Show search progress by printing every n spectra searched. Set to 0 to show no # search progress. # Available for tide-search print-search-progress=1000 # Specify the type of target-decoy search. Using 'auto', percolator attempts to # detect the search type automatically. Using 'separate' specifies two # searches: one against target and one against decoy protein db. Using # 'concatenated' specifies a single search on concatenated target-decoy protein # db. # Available for percolator search-input=auto # When given a unsigned integer value seeds the random number generator with # that value. When given the string "time" seeds the random number generator # with the system time. # Available for all percolator percolator-seed=1 # Output the computed features in tab-delimited Percolator input (.pin) format. # The features will be normalized, using either unit norm or standard deviation # normalization (depending upon the value of the unit-norm option). # Available for percolator and q-ranker. feature-file-out=false # Include decoys (PSMs, peptides, and/or proteins) in the XML output. # Available for crux percolator decoy-xml-output=false # Specifies the prefix of the protein names that indicate a decoy. # Available for percolator decoy-prefix=DECOY_ # Output final weights to a file named "percolator.weights.txt". # Available for crux percolator output-weights=false # Read initial weights from the given file (one per line). # Available for crux percolator init-weights= # Only train Percolator on a subset of PSMs, and use the resulting score vector # to evaluate the other PSMs. Recommended when analyzing huge numbers (>1 # million) of PSMs. When set to 0, all PSMs are used for training as normal. # Available for crux percolator subset-max-train=0 # Penalty for mistakes made on positive examples. If this value is set to 0, # then it is set via cross validation over the values {0.1, 1, 10}, selecting # the value that yields the largest number of PSMs identified at the q-value # threshold set via the --test-fdr parameter. # Available for crux percolator c-pos=0 # Penalty for mistake made on negative examples. If not specified, then this # value is set by cross validation over {0.1, 1, 10}. # Available for crux percolator c-neg=0 # False discovery rate threshold to define positive examples in training. # Available for crux percolator train-fdr=0.01 # False discovery rate threshold used in selecting hyperparameters during # internal cross-validation and for reporting the final results. # Available for crux percolator. test-fdr=0.01 # Apply the specified threshold to PSM, peptide and protein probabilities to # obtain a faster estimate of the alpha, beta and gamma parameters. # Available for crux percolator. fido-fast-gridsearch=0 # Do not approximate the posterior distribution by allowing large graph # components to be split into subgraphs. The splitting is done by duplicating # peptides with low probabilities. Splitting continues until the number of # possible configurations of each subgraph is below 2^18 # Available for crux percolator fido-no-split-large-components=false # To speed up inference, proteins for which none of the associated peptides has # a probability exceeding the specified threshold will be assigned probability = # 0. # Available for crux percolator fido-protein-truncation-threshold=0.01 # Use target-decoy competition to assign q-values and PEPs. When set to F, the # mix-max method, which estimates the proportion pi0 of incorrect target PSMs, # is used instead. # Available for crux percolator tdc=true # Maximum number of iterations for training. # Available for crux percolator maxiter=10 # Quicker execution by reduced internal cross-validation. # Available for crux percolator quick-validation=false # In its initial round of training, Percolator uses one feature to induce a # ranking of PSMs. By default, Percolator will select the feature that produces # the largest set of target PSMs at a specified FDR threshold (cf. --train-fdr). # This option allows the user to specify which feature is used for the initial # ranking, using the name as a string. The name can be preceded by a hyphen # (e.g. "-XCorr") to indicate that a lower value is better. # Available for crux percolator default-direction= # Use unit normalization (i.e., linearly rescale each PSM's feature vector to # have a Euclidean length of 1), instead of standard deviation normalization. # Available for crux percolator. unitnorm=false # Measure performance on test set each iteration. # Available for crux percolator. test-each-iteration=false # Use the picked protein-level FDR to infer protein probabilities, provide the # fasta file as the argument to this flag. # Available for crux percolator picked-protein= # Type of enzyme # Available for crux percolator protein-enzyme=trypsin # By default, if the peptides associated with protein A are a proper subset of # the peptides associated with protein B, then protein A is eliminated and all # the peptides are considered as evidence for protein B. Note that this # filtering is done based on the complete set of peptides in the database, not # based on the identified peptides in the search results. Alternatively, if this # option is set and if all of the identified peptides associated with protein B # are also associated with protein A, then Percolator will report a # comma-separated list of protein IDs, where the full-length protein B is first # in the list and the fragment protein A is listed second. Not available for # Fido. # Available for crux percolator protein-report-fragments=false # If multiple database proteins contain exactly the same set of peptides, then # Percolator will randomly discard all but one of the proteins. If this option # is set, then the IDs of these duplicated proteins will be reported as a # comma-separated list. Not available for Fido. # Available for crux percolator protein-report-duplicates=true # Use the Fido algorithm to infer protein probabilities. Must be true to use any # of the Fido options. # Available for crux percolator protein=true # Specify the probability with which a present protein emits an associated # peptide. Set by grid search (see --fido-gridsearch-depth parameter) if not # specified. # Available for crux percolator if --protein T is set. fido-alpha=0 # Specify the probability of the creation of a peptide from noise. Set by grid # search (see --fido-gridsearch-depth parameter) if not specified. # Available for crux percolator if --protein T is set. fido-beta=0 # Specify the prior probability that a protein is present in the sample. Set by # grid search (see --fido-gridsearch-depth parameter) if not specified. # Available for crux percolator if --protein T is set. fido-gamma=0 # Estimate empirical p-values and q-values for proteins using target-decoy # analysis. # Available for crux percolator if --protein T is set. fido-empirical-protein-q=true # Set depth of the grid search for alpha, beta and gamma estimation. # Available for crux percolator if --protein T is set. fido-gridsearch-depth=0 # Q-value threshold that will be used in the computation of the MSE and ROC AUC # score in the grid search. # Available for crux percolator if --protein T is set. fido-gridsearch-mse-threshold=0.05 # By default, Percolator will examine the learned weights for each feature, and # if the weight appears to be problematic, then percolator will discard the # learned weights and instead employ a previously trained, static score vector. # This switch allows this error checking to be overriden. # Available for crux percolator. override=false # Use retention time features calculated as in "Improving tandem mass spectrum # identification using peptide retention time prediction across diverse # chromatography conditions" by Klammer AA, Yi X, MacCoss MJ and Noble WS. # (Analytical Chemistry. 2007 Aug 15;79(16):6111-8.). # Available for crux percolator klammer=false # Do not remove redundant peptides; keep all PSMs and exclude peptide level # probability. # Available for crux percolator only-psms=false # Enforce that, for each spectrum, at most one PSM is included in the positive # set during each training iteration. Note that if the user only provides one # PSM per spectrum, then this option will have no effect. # Available for crux percolator train-best-positive=false # Report the number of unique PSMs and total (including shared peptides) PSMs as # two extra columns in the protein tab-delimited output. # Available for crux percolator spectral-counting-fdr=0 # Include a decoy version of every peptide by shuffling or reversing the target # sequence or protein. In shuffle or peptide-reverse mode, each peptide is # either reversed or shuffled, leaving the N-terminal and C-terminal amino acids # in place. Note that peptides appear multiple times in the target database are # only shuffled once. In peptide-reverse mode, palindromic peptides are # shuffled. Also, if a shuffled peptide produces an overlap with the target or # decoy database, then the peptide is re-shuffled up to 5 times. Note that, # despite this repeated shuffling, homopolymers will appear in both the target # and decoy database. The protein-reverse mode reverses the entire protein # sequence, irrespective of the composite peptides. # Available for tide-index decoy-format=shuffle # Expression for static and variable mass modifications to include. Specify a # comma-separated list of modification sequences of the form: # C+57.02146,2M+15.9949,1STY+79.966331,... # Available for tide-index and search-for-xlinks. mods-spec=C+57.02146 # Specifies N-terminal static and variable mass modifications on peptides. # Specify a comma-separated list of N-terminal modification sequences of the # form: 1E-18.0106,C-17.0265 # Available for tide-index nterm-peptide-mods-spec= # Specifies C-terminal static and variable mass modifications on peptides. # Specify a comma-separated list of C-terminal modification sequences of the # form: X+21.9819 # Available for tide-index cterm-peptide-mods-spec= # Specify the name of the file where the binarized fragmentation spectra will be # stored. Subsequent runs of crux tide-search will execute more quickly if # provided with the spectra in binary format. The filename is specified relative # to the current working directory, not the Crux output directory (as specified # by --output-dir). This option is not valid if multiple input spectrum files # are given. # Available for tide-search store-spectra= # Enable the calculation of exact p-values for the XCorr score. Calculation of # p-values increases the running time but increases the number of # identifications at a fixed confidence threshold. The p-values will be reported # in a new column with header "exact p-value", and the "xcorr score" column will # be replaced with a "refactored xcorr" column. Note that, currently, p-values # can only be computed when the mz-bin-width parameter is set to its default # value. Variable and static mods are allowed on non-terminal residues in # conjunction with p-value computation, but currently only static mods are # allowed on the N-terminus, and no mods on the C-terminus. # Available for tide-search exact-p-value=false # When providing a FASTA file as the index, the generated binary index will be # stored at the given path. This option has no effect if a binary index is # provided as the index. # Available for tide-search store-index= # When set to T, target and decoy search results are reported in a single file, # and only the top-scoring N matches (as specified via --top-match) are reported # for each spectrum, irrespective of whether the matches involve target or decoy # peptides.Note that when used with search-for-xlinks, this parameter only has # an effect if use-old-xlink=F. # Available for tide-search and search-for-xlinks concat=false # Include the file column in tab-delimited output. # Available for tide-search file-column=true # If true, all peaks around the precursor m/z will be removed, within a range # specified by the --remove-precursor-tolerance option. # Available for tide-search. remove-precursor-peak=false # This parameter specifies the tolerance (in Th) around each precursor m/z that # is removed when the --remove-precursor-peak option is invoked. # Available for print-processed spectra and tide-search. remove-precursor-tolerance=1.5 # When set to T, for each protein that begins with methionine, tide-index will # put two copies of the leading peptide into the index, with and without the # N-terminal methionine. # Available for tide-index. clip-nterm-methionine=false # Prevent duplicate peptides between the target and decoy databases. When set to # "F", the program keeps all target and previously generated decoy peptides in # memory. A shuffled decoy will be re-shuffled multiple times to avoid # duplication. If a non-duplicated peptide cannot be generated, the decoy is # skipped entirely. When set to "T", every decoy is added to the database # without checking for duplication. This option reduces the memory requirements # significantly. # Available for tide-index. allow-dups=false # Controls whether neutral loss ions are considered in the search. Two types of # neutral losses are included and are applied only to singly charged b- and # y-ions: loss of ammonia (NH3, 17.0086343 Da) and H2O (18.0091422). Each # neutral loss peak has intensity 1/5 of the primary peak. # Available for tide-search. use-neutral-loss-peaks=true # The maximum charge state of a spectra to consider in search. # Available for tide-search. max-precursor-charge=5 # Carries out a peptide-centric search. For each peptide the top-scoring spectra # are reported, in contrast to the standard spectrum-centric search where the # top-scoring peptides are reported. Note that in this case the "xcorr rank" # column will contain the rank of the given spectrum with respect to the given # candidate peptide, rather than vice versa (which is the default). # Available for tide-search. peptide-centric-search=false # Skip preprocessing steps on spectra. Default = F. # Available for tide-search skip-preprocessing=false # Function used for scoring PSMs. 'xcorr' is the original scoring function used # by SEQUEST; 'residue-evidence' is designed to score high-resolution MS2 # spectra; and 'both' calculates both scores. The latter requires that # exact-p-value=T. # Available for tide-search. score-function=xcorr # Mass tolerance (in Da) for scoring pairs of peaks when creating the residue # evidence matrix. This parameter only makes sense when score-function is # 'residue-evidence' or 'both'. # Available for tide-search. fragment-tolerance=0.02 # When exact-pvalue=T, this parameter controls the granularity of the entries in # the dynamic programming matrix. Smaller values make the program run faster # but give less exact p-values; larger values make the program run more slowly # but give more exact p-values. # Available for tide-search evidence-granularity=25 # List of positive, non-zero integers. # Isotope errors to include. Specify a comma-separated list of isotope errors of # the form: 1,2,3,...Available for tide-search isotope-error= # 0=poll CPU to set num threads; else specify num threads directly. # Available for tide-search tab-delimited files only. num-threads=0 # Analysis begins with a pre-processsing step that creates a set of lookup # tables which are then used during training. Normally, these lookup tables are # deleted at the end of the analysis, but setting this option to T prevents the # deletion of these tables. Subsequently, analyses can be repeated more # efficiently by specifying the --re-run option. # Available for q-ranker and barista. skip-cleanup=false # Re-run a previous analysis using a previously computed set of lookup tables. # For this option to work, the --skip-cleanup option must have been set to true # when the program was run the first time. # Available for q-ranker and barista. re-run= # Use an enriched feature set, including separate features for each ion type. # Available for q-ranker and barista. use-spec-features=true # If the target and decoy searches were run separately, rather than using a # concatenated database, then the program will assume that the database search # results provided as a required argument are from the target database search. # This option then allows the user to specify the location of the decoy search # results. Like the required arguments, these search results can be provided as # a single file, a list of files or a directory. However, the choice (file, list # or directory) must be consistent for the MS2 files and the target and decoy # tab-delimited files. Also, if the MS2 and tab-delimited files are provided in # directories, then Q-ranker will use the MS2 filename (foo.ms2) to identify # corresponding target and decoy tab-delimited files with names like # foo*.target.txt and foo*.decoy.txt. This naming convention allows the target # and decoy txt files to reside in the same directory. # Available for q-ranker and barista. separate-searches= # Specify that the search results are provided as lists of files, rather than as # individual files. # Available for barista and percolator. list-of-files=false # Specifies whether to do optimization at the protein, peptide or psm level. # Available for barista. optimization=protein # Specify the method used to estimate q-values. The mix-max procedure or # target-decoy competition apply to PSMs. The peptide-level option eliminates # any PSM for which there exists a better scoring PSM involving the same # peptide, and then uses decoys to assign confidence estimates. # Used by assign-confidence. estimation-method=tdc # Adjust the score using the Sidak adjustment and reports them in a new column # in the output file. Note that this adjustment only makes sense if the given # scores are p-values, and that it requires the presence of the "distinct # matches/spectrum" feature for each PSM. # Used by assign-confidence. sidak=false # Specify the column (for tab-delimited input) or tag (for XML input) used as # input to the q-value estimation procedure. If this parameter is unspecified, # then the program searches for "xcorr score", "evalue" (comet), "exact p-value" # score fields in this order in the input file. # Used by assign-confidence. score= # Specify this parameter to T in order to combine charge states with peptide # sequencesin peptide-centric search. Works only if estimation-method = # peptide-level. # Used by assign-confidence. combine-charge-states=false # Specify this parameter to T in order to treat peptides carrying different or # no modifications as being the same. Works only if estimation = peptide-level. # Used by assign-confidence. combine-modified-peptides=false # The q-value threshold used by cascade search. Each spectrum identified in one # search with q-value less than this threshold will be excluded from all # subsequent searches. Note that the threshold is not applied to the final # database in the cascade. # Used by cascade-search. q-value-threshold=0.01 # Predict the specified primary ion series. 'a' indicates a-ions only, 'b' # indicates b-ions only, 'y' indicates y-ions only, 'by' indicates both b and y, # 'bya' indicates b, y, and a. # Only available for crux-predict-peptide-ions. Set automatically to 'by' for # searching. primary-ions=by # Predict the precursor ions, and all associated ions (neutral losses, multiple # charge states) consistent with the other specified options. # Only available for crux-predict-peptide-ions. precursor-ions=false # Predict the given number of isotope peaks (0|1|2). # Only available for crux-predict-peptide-ion. Automatically set to 0 for Sp # scoring and 1 for xcorr scoring. isotope=0 # Predict flanking peaks for b- and y ions. # Only available for crux-predict-peptide-ion. flanking=false # Predict theoretical ions up to max charge state (1, 2, ... ,6) or up to the # charge state of the peptide ("peptide"). If the max-ion-charge is greater than # the charge state of the peptide, then the maximum is the peptide charge. # Available for predict-peptide-ions and search-for-xlinks. Set to 'peptide' for # search. max-ion-charge=peptide # Include among the predicted peaks b/y ions with up to n losses of nh3. For # example, for --nh3 2, predict a peak for each b- and y-ion with the loss of # one nh3 group and predict a second peak for each b- and y-ion with the loss of # two nh3 groups. These peaks will have 1 and 2, respectively, in the NH3 column # of the output. # Only available for crux-predict-peptide-ions. nh3=0 # Include in the predicted peaks, b/y ions with the loss of 1 to n water # molecules. See --nh3 for an example. # Only available for crux-predict-peptide-ions. h2o=0 # The name of the file in FASTA format. # Option for spectral-counts protein-database= # Type of analysis to make on the match results: (RAW|NSAF|dNSAF|SIN|EMPAI). # With exception of the RAW metric, the database of sequences need to be # provided using --protein-database. # Available for spectral-counts. RAW is raw counts, NSAF is Normalized Spectral # Abundance Factor, dNSAF is Distributed Spectral Abundance Factor, SIN is # Spectral Index Normalized and EMPAI is Exponentially Modified Protein # Abundance Index measure=NSAF # Ignore peptides that map to multiple proteins. # Available for spectral-counts. unique-mapping=false # Quantification at protein or peptide level. # Available for spectral-counts and either NSAF and SIN. quant-level=protein # Perform a parsimony analysis on the proteins, and report a "parsimony rank" # column in the output file. This column contains integers indicating the # protein's rank in a list sorted by spectral counts. If the parsimony analysis # results in two proteins being merged, then their parsimony rank is the same. # In such a case, the rank is assigned based on the largest spectral count of # any protein in the merged meta-protein. The "simple" parsimony algorithm only # merges two proteins A and B if the peptides identified in protein A are the # same as or a subset of the peptides identified in protein B. The "greedy" # parsimony algorithm does additional merging, using the peptide q-values to # greedily assign each peptide to a single protein. # Available for spectral-counts. parsimony=none # Determines what type of threshold to use when filtering matches. none : read # all matches, qvalue : use calculated q-value from percolator or q-ranker, # custom : use --custom-threshold-name and --custom-threshold-min parameters. # used for crux spectral-counts threshold-type=qvalue # Only consider PSMs with a threshold value. By default, q-values are # thresholded using a specified threshold value. This behavior can be changed # using the --custom-threshold and --threshold-min parameters. # Available for spectral-counts. All PSMs with higher (or lower) than this will # be ignored. threshold=0.01 # Specify which field to apply the threshold to. The direction of the threshold # (<= or >=) is governed by --custom-threshold-min. By default, the threshold # applies to the q-value, specified by "percolator q-value", "q-ranker q-value", # "decoy q-value (xcorr)", or "barista q-value". # Available for spectral-counts. custom-threshold-name= # When selecting matches with a custom threshold, custom-threshold-min # determines whether to filter matches with custom-threshold-name values that # are greater-than or equal (F) or less-than or equal (T) than the threshold. # Available for spectral-counts. custom-threshold-min=true # MS2 file corresponding to the psm file. Required to measure the SIN. Ignored # for NSAF, dNSAF and EMPAI. # Available for spectral-counts with measure=SIN. input-ms2= # Use mzid's passThreshold attribute to filter matches. # Used when parsing mzIdentML files. mzid-use-pass-threshold=false # Change the mass of all amino acids 'A' by the given amount. # A=0 # Change the mass of all amino acids 'C' by the given amount. # C=57.021464 # Change the mass of all amino acids 'D' by the given amount. # D=0 # Change the mass of all amino acids 'E' by the given amount. # E=0 # Change the mass of all amino acids 'F' by the given amount. # F=0 # Change the mass of all amino acids 'G' by the given amount. # G=0 # Change the mass of all amino acids 'H' by the given amount. # H=0 # Change the mass of all amino acids 'I' by the given amount. # I=0 # Change the mass of all amino acids 'K' by the given amount. # K=0 # Change the mass of all amino acids 'L' by the given amount. # L=0 # Change the mass of all amino acids 'M' by the given amount. # M=0 # Change the mass of all amino acids 'N' by the given amount. # N=0 # Change the mass of all amino acids 'P' by the given amount. # P=0 # Change the mass of all amino acids 'Q' by the given amount. # Q=0 # Change the mass of all amino acids 'R' by the given amount. # R=0 # Change the mass of all amino acids 'S' by the given amount. # S=0 # Change the mass of all amino acids 'T' by the given amount. # T=0 # Change the mass of all amino acids 'V' by the given amount. # V=0 # Change the mass of all amino acids 'W' by the given amount. # W=0 # Change the mass of all amino acids 'Y' by the given amount. # Y=0 # Legal values are auto, tsv, sqt, pepxml or mzidentml format. # option, for psm-convert input-format=auto # Whether matches/ion are distinct (as opposed to total). # option, for psm-convert. distinct-matches=true # Rather than the spectrum, output summary statistics to standard output. Each # statistic is placed on a separate line, in the format : (e.g. # "TIC:1000.0"). # Available only for crux-get-ms2-spectrum. Does not affect contents of the # output file. stats=false # write out the weibull training points for thespectrum,charge # Available for crux search-for-xlinks write-weibull-points=false # Print the theoretical spectrum # Available for xlink-predict-peptide-ions. print-theoretical-spectrum=false # Use the old version of xlink-searching algorithm. When false, a new version of # the code is run. The new version supports variable modifications and can # handle more complex databases. This new code is still in development and # should be considered a beta release. # Available for search-for-xlinks. use-old-xlink=true # Score method for xlink {composite, modification, concatenated}. # Available for xlink-score-spectrum. xlink-score-method=composite # Provides a list of isotopic windows to search. For example, -1,0,1 will search # in three disjoint windows: (1) precursor_mass - neutron_mass +/- window, (2) # precursor_mass +/- window, and (3) precursor_mass + neutron_mass +/- window. # The window size is defined from the precursor-window and precursor-window-type # parameters. This option is only available when use-old-xlink=F. # Available for search-for-xlinks isotope-windows=0 # Provides a list of amino acids and their mass modifications to consider as # candidate for mono-/dead- links. Format is the same as mods-spec. # Available for search-for-xlinks (new code) mono-link= # Specify the number of open-mod peptides to consider in the second pass. A # value of 0 will search all candiates. # Available for search-for-xlinks xlink-top-n=250 # If there is no cross-link candidate found, then don't bother looking for # linear, self-loop, and dead-link candidates. # Available for search-for-xlinks. require-xlink-candidate=false # Include linear peptides in the search. # Available for search-for-xlinks. xlink-include-linears=true # Include dead-end peptides in the search. # Available for search-for-xlinks. xlink-include-deadends=true # Include self-loop peptides in the search. # Available for search-for-xlinks. xlink-include-selfloops=true # Include intra-protein cross-link candiates within the search. # Available for search-for-xlinks. xlink-include-intra=true # Include inter-protein cross-link candidates within the search. # Available for search-for-xlinks. xlink-include-inter=true # Include crosslink candidates that are both inter and intra. # Available for search-for-xlinks. xlink-include-inter-intra=true # List of amino acids for which the cross-linker can prevent cleavage. This # option is only available when use-old-xlink=F. # Available for search-for-xlinks program. xlink-prevents-cleavage=K # Specify the maximum number of modifications allowed on a crosslinked peptide. # This option is only available when use-old-xlink=F. # Available for crux search-for-xlinks max-xlink-mods=255 # Search decoy peptides within +/- precursor-window-weibull of the precursor # mass. The resulting scores are used only for fitting the Weibull distribution # Available for crux search-for-xlinks. precursor-window-weibull=20 # Window type to use in conjunction with the precursor-window-weibull parameter. # Available for crux search-for-xlinks precursor-window-type-weibull=mass # Keep shuffling and collecting XCorr scores until the minimum number of points # for weibull fitting (using targets and decoys) is achieved. # Available for crux search-for-xlinks min-weibull-points=4000 # Determines which spectral feature detection algorithm to use. Different # results are possible with each algorithm, and there are pros and cons to each. # Available for crux hardklor hardklor-algorithm=version1 # Defines alternative averagine models in the analysis that incorporate # additional atoms and/or isotopic enrichments. Modifications are represented as # text strings. Inclusion of additional atoms in the model is done using by # entering an atomic formula, such as: PO2 or Cl. Inclusion of isotopic # enrichment to the model is done by specifying the percent enrichment (as a # decimal) followed by the atom being enriched and an index of the isotope. For # example, 0.75H1 specifies 75% enrichment of the first heavy isotope of # hydrogen. In other words, 75% deuterium enrichment. Two or more modifications # can be combined into the same model, and separated by spaces: B2 0.5B1 # Available for crux hardklor averagine-mod= # Boxcar averaging is a sliding window that averages n adjacent spectra prior to # feature detection. Averaging generally improves the signal-to-noise ratio of # features in the spectra, as well as improving the shape of isotopic envelopes. # However, averaging will also change the observed peak intensities. Averaging # with too wide a window will increase the occurrence of overlapping features # and broaden the chromatographic profiles of observed features. The number # specified is the total adjacent scans to be combined, centered on the scan # being analyzed. Therefore, an odd number is recommended to center the boxcar # window. For example, a value of 3 would produce an average of the scan of # interest, plus one scan on each side. A value of 0 disables boxcar averaging. # Available for crux hardklor boxcar-averaging=0 # This parameter is only functional when boxcar-averaging is used. The filter # will remove any peaks not seen in n scans in the boxcar window. The effect is # to reduce peak accumulation due to noise and reduce chromatographic broadening # of peaks. Caution should be used as over-filtering can occur. The suggested # number of scans to set for filtering should be equal to or less than the # boxcar-averaging window size. A value of 0 disables filtering. # Available for crux hardklor boxcar-filter=0 # This parameter is only functional when boxcar-filter is used. The value # specifies the mass tolerance in ppm for declaring a peak the same prior to # filtering across all scans in the boxcar window. # Available for crux hardklor boxcar-filter-ppm=10 # Indicates whether the data contain profile or centroided peaks. # Available for crux hardklor centroided=false # Choose the charge state determination method. # Available for crux hardklor cdm=Q # Specifies the minimum charge state to allow when finding spectral features. It # is best to set this value to the lowest assumed charge state to be present. If # set higher than actual charge states that are present, those features will not # be identified or incorrectly assigned a different charge state and mass. # Available for crux hardklor min-charge=1 # Specifies the maximum charge state to allow when finding spectral features. It # is best to set this value to a practical number (i.e. do not set it to 20 when # doing a tryptic shotgun analysis). If set higher than actual charge states # that are present, the algorithm will perform significantly slower without any # improvement in results. # Available for crux hardklor max-charge=5 # Sets the correlation threshold (cosine similarity) for accepting each # predicted feature. # Available for crux hardklor corr=0.85 # Sets the depth of combinatorial analysis. For a given set of peaks in a # spectrum, search for up to this number of combined peptides that explain the # observed peaks. The analysis stops before depth is reached if the current # number of deconvolved features explains the observed peaks with a correlation # score above the threshold defined with the correlation parameter. # Available for crux hardklor depth=3 # When reporting each feature, report abundance as the sum of all isotope peaks. # The value reported is the estimate of the correct peak heights based on the # averagine model scaled to the observed peak heights. # Available for crux hardklor distribution-area=false # Specifies an ASCII text file that defines symbols for the periodic table. # Available for crux hardklor hardklor-data-file= # Indicates the type of instrument used to collect data. This parameter, # combined with the resolution parameter, define how spectra will be centroided # (if you provide profile spectra) and the accuracy when aligning observed peaks # to the models. # Available for crux hardklor instrument=fticr # Specifies an ASCII text file that can be read to override the natural isotope # abundances for all elements. # Available for crux hardklor isotope-data-file= # Specifies the maximum number of models to build for a set of peaks being # analyzed. Regardless of the setting, the number of models will never exceed # the number of peaks in the current set. However, as many of the low abundance # peaks are noise or tail ends of distributions, defining models for them is # detrimental to the analysis. # Available for crux hardklor max-features=10 # Filters the spectra prior to analysis for the requested MS/MS level. For # example, if the data contain MS and MS/MS spectra, setting mzxml-filter = 1 # will analyze only the MS scan events. Setting mzxml-filter = 2 will analyze # only the MS/MS scan events. # Available for crux hardklor mzxml-filter=1 # Constrains the search in each spectrum to signals below this value in # Thomsons. Setting to 0 disables this feature. # Available for crux hardklor mz-max=0 # Constrains the search in each spectrum to signals above this value in # Thomsons. Setting to 0 disables this feature. # Available for crux hardklor mz-min=0 # Only used when algorithm = version1. Defines the maximum window size in # Thomsons to analyze when deconvolving peaks in a spectrum into features. # Available for crux hardklor mz-window=4 # Specifies the resolution of the instrument at 400 m/z for the data being # analyzed. # Available for crux hardklor resolution=100000 # Used to restrict analysis to spectra with scan numbers below this parameter # value. A value of 0 disables this feature. # Available for crux hardklor scan-range-max=0 # Used to restrict analysis to spectra with scan numbers above this parameter # value. A value of 0 disables this feature. # Available for crux hardklor scan-range-min=0 # Set the sensitivity level. There are four levels: 0 (low), 1 (moderate), 2 # (high), and 3 (max). Increasing the sensitivity will increase computation # time, but will also yield more isotope distributions. # Available for crux hardklor sensitivity=2 # Filters spectra to remove peaks below this signal-to-noise ratio prior to # finding features. # Available for crux hardklor signal-to-noise=1 # Uses Savitzky-Golay smoothing on profile peak data prior to centroiding the # spectra. This parameter is recommended for low resolution spectra only. # Smoothing data causes peak depression and broadening. Only use odd numbers for # the degree of smoothing (as it defines a window centered on each data point). # Higher values will produce smoother peaks, but with greater depression and # broadening. Setting this parameter to 0 disables smoothing. # Available for crux hardklor smooth=0 # Set the signal-to-noise window length (in m/z). Because noise may be # non-uniform across a spectrum, this value adjusts the segment size considered # when calculating a signal-over-noise ratio. # Available for crux hardklor sn-window=250 # Applies the lowest noise threshold of any sn_window across the entire mass # range for a spectrum. Setting this parameter to 0 turns off this feature, and # different noise thresholds will be used for each local mass window in a # spectrum. # Available for crux hardklor static-sn=true # Ignore PPIDs that persist for longer than this length of time in the MS1 # spectra. The unit of time is whatever unit is used in your data file (usually # minutes). These PPIDs are considered contaminants. # Available for crux bullseye max-persist=2 # When true, require an exact match (as defined by --exact-tolerance) between # the center of the precursor isolation window in the MS2 scan and the base # isotopic peak of the PPID. If this option is set to false and no exact match # is observed, then attempt to match using a wider m/z tolerance. This wider # tolerance is calculated using the PPID's monoisotopic mass and charge (the # higher the charge, the smaller the window). # Available for crux bullseye exact-match=false # Allowed gap size when checking for PPIDs across consecutive MS1 scans. # Available for crux bullseye gap-tolerance=1 # Only consider PPIDs above this minimum mass in daltons. # Available for crux bullseye bullseye-min-mass=600 # Only consider PPIDs below this maximum mass in daltons. # Available for crux bullseye bullseye-max-mass=8000 # Set the tolerance (+/-ppm) for --exact-match. # Available for crux bullseye exact-tolerance=10 # Set the mass tolerance (+/-ppm) for finding PPIDs in consecutive MS1 scans. # Available for crux bullseye persist-tolerance=10 # Total number of MS1 scans over which a PPID must be observed to be considered # real. Gaps in persistence are allowed by setting --gap-tolerance. # Available for crux bullseye scan-tolerance=3 # Set the tolerance (+/-units) around the retention time over which a PPID can # be matches to the MS2 spectrum. The unit of time is whatever unit is used in # your data file (usually minutes). # Available for crux bullseye retention-tolerance=0.5 # The format to write the output spectra to. If empty, the spectra will be # output in the same format as the MS2 input. # Available for crux bullseye spectrum-format= # Sort in ascending (T) or descending (F) order. # Available for sort-by-column ascending=true # Specify the input and output delimiter to use when processing the delimited # file. The argument can be either a single character or the keyword 'tab.' # Available for the delimited utility programs. delimiter=tab # Print the header line of the file, in addition to the columns that match. # Available for crux extract-columns and extract-rows header=true # Specifies the data type of the column, either an integer (int), a floating # point number (real), or a string. # Available for crux extract-rows column-type=string # Specify the operator that is used to compare an entry in the specified column # to the value given on the command line. # Available for crux extract-rows comparison=eq # Run the Bullseye algorithm on the given MS data, using it to assign # high-resolution precursor values to the MS/MS data. If a spectrum file ends # with .ms2 or .cms2, matching .ms1/.cms1 files will be used as the MS1 file. # Otherwise, it is assumed that the spectrum file contains both MS1 and MS2 # scans. # Available for crux pipeline bullseye=false # Specify which search engine to use. # Available for crux pipeline search-engine=tide-search # Specify which post-processor to apply to the search results. # Available for crux pipeline post-processor=percolator # Minimum precursor m/z value to use in measurement error estimation. # Available for param-medic and tide-search and comet pm-min-precursor-mz=400 # Minimum precursor m/z value to use in measurement error estimation. # Available for param-medic and tide-search and comet pm-max-precursor-mz=1800 # Minimum fragment m/z value to use in measurement error estimation. # Available for param-medic and tide-search and comet pm-min-frag-mz=150 # Maximum fragment m/z value to use in measurement error estimation. # Available for param-medic and tide-search and comet pm-max-frag-mz=1800 # Minimum fragment peaks an MS/MS scan must contain to be used in measurement # error estimation. # Available for param-medic and tide-search and comet pm-min-scan-frag-peaks=40 # Maximum ppm distance between precursor m/z values to consider two scans # potentially generated by the same peptide for measurement error estimation. # Available for param-medic and tide-search and comet pm-max-precursor-delta-ppm=50 # Precursor charge state to consider MS/MS spectra from, in measurement error # estimation. Ideally, this should be the most frequently occurring charge state # in the given data. # Available for param-medic and tide-search and comet pm-charge=2 # Number of most-intense fragment peaks to consider for measurement error # estimation, per MS/MS spectrum. # Available for param-medic and tide-search and comet pm-top-n-frag-peaks=30 # Number of fragment peaks per spectrum pair to be used in fragment error # estimation. # Available for param-medic and tide-search and comet pm-pair-top-n-frag-peaks=5 # Number of the most-intense peaks that two spectra must share in order to # potentially be generated by the same peptide, for measurement error # estimation. # Available for param-medic and tide-search and comet pm-min-common-frag-peaks=20 # Maximum number of scans two spectra can be separated by in order to be # considered potentially generated by the same peptide, for measurement error # estimation. # Available for param-medic and tide-search and comet pm-max-scan-separation=1000 # Minimum number of peak pairs (for precursor or fragment) that must be # successfully paired in order to attempt to estimate measurement error # distribution. # Available for param-medic and tide-search and comet pm-min-peak-pairs=100 # Ignore implied modifications where the absolute value of its mass is below # this value and only score the unmodified peptide. # Available for localize-modification min-mod-mass=0 # Consider modifications on any amino acid in aa list with at most # max-per-peptide in one peptide. The parameter takes the form # ::::. This parameter # may be included with different values multiple times so long as the # total number of mod, cmod, and nmod parameters does not exceed 11. The # "prevents cleavage" and "prevents cross-link" arguments are optional # T/F arguments for describing whether the modification prevents # enzymatic cleavage of cross-linking, respectively. This option is only # available when use-old-xlink=F. Note that this parameter only takes # effect when specified in the parameter file. # Available for search-for-xlinks. mod=NO MODS # Specify a variable modification to apply to N-terminus of peptides. # . Note that this parameter only takes effect when # specified in the parameter file. # Available for search-for-xlinks. nmod=NO MODS # Specify a variable modification to apply to C-terminus of peptides. # . Note that this parameter only takes effect when # specified in the parameter file. # Available for search-for-xlinks. cmod=NO MODS #################### # Comet Parameters # #################### # 0=no, 1=concatenated search, 2=separate search. # Available for comet. decoy_search=0 # 0=poll CPU to set num threads; else specify num threads directly. # Available for comet. num_threads=0 # Controls the mass tolerance value. The mass tolerance is set at +/- the # specified number i.e. an entered value of "1.0" applies a -1.0 to +1.0 # tolerance. The units of the mass tolerance is controlled by the parameter # "peptide_mass_units". # Available for comet. peptide_mass_tolerance=3 # 0=amu, 1=mmu, 2=ppm. # Available for comet. peptide_mass_units=0 # Automatically estimate optimal value for the peptide_mass_tolerancel parameter # from the spectra themselves. false=no estimation, warn=try to estimate but use # the default value in case of failure, fail=try to estimate and quit in case of # failure. # Available for comet. auto_peptide_mass_tolerance=false # 0=average masses, 1=monoisotopic masses. # Available for comet. mass_type_parent=1 # 0=average masses, 1=monoisotopic masses. # Available for comet. mass_type_fragment=1 # 0=singly charged peptide mass, 1=precursor m/z. # Available for comet. precursor_tolerance_type=0 # 0=off, 1=on -1/0/1/2/3 (standard C13 error), 2=-8/-4/0/4/8 (for +4/+8 # labeling). # Available for comet. isotope_error=0 # Specify a search enzyme from the end of the parameter file. # Available for comet. search_enzyme_number=1 # valid values are 1 (semi-digested), 2 (fully digested), 8 N-term, 9 C-term. # Available for comet. num_enzyme_termini=2 # Maximum value is 5; for enzyme search. # Available for comet. allowed_missed_cleavage=2 # Binning to use on fragment ions. # Available for comet. fragment_bin_tol=1.000507 # Offset position to start the binning (0.0 to 1.0). # Available for comet. fragment_bin_offset=0.4 # Automatically estimate optimal value for the fragment_bin_tol parameter from # the spectra themselves. false=no estimation, warn=try to estimate but use the # default value in case of failure, fail=try to estimate and quit in case of # failure. # Available for comet. auto_fragment_bin_tol=false # 0=default peak shape, 1=M peak only. # Available for comet. theoretical_fragment_ions=1 # Controls whether or not A-ions are considered in the search (0 - no, 1 - yes). # Available for comet. use_A_ions=0 # Controls whether or not B-ions are considered in the search (0 - no, 1 - yes). # Available for comet. use_B_ions=1 # Controls whether or not C-ions are considered in the search (0 - no, 1 - yes). # Available for comet. use_C_ions=0 # Controls whether or not X-ions are considered in the search (0 - no, 1 - yes). # Available for comet. use_X_ions=0 # Controls whether or not Y-ions are considered in the search (0 - no, 1 - yes). # Available for comet. use_Y_ions=1 # Controls whether or not Z-ions are considered in the search (0 - no, 1 - yes). # Available for comet. use_Z_ions=0 # 0=no, 1= yes to consider NH3/H2O neutral loss peak. # Available for comet. use_NL_ions=1 # 0=no, 1=yes write sqt file. # Available for comet. output_sqtfile=0 # 0=no, 1=yes write tab-delimited text file. # Available for comet. output_txtfile=1 # 0=no, 1=yes write pep.xml file. # Available for comet. output_pepxmlfile=1 # 0=no, 1=yes write percolator file. # Available for comet. output_percolatorfile=0 # 0=no, 1=yes write .out files. # Available for comet. output_outfiles=0 # 0=no, 1=yes to replace Sp with expect in out & sqt. # Available for comet. print_expect_score=1 # num peptide results to show. # Available for comet. num_output_lines=5 # 0=no, 1=yes for out files only. # Available for comet. show_fragment_ions=0 # Sample enzyme which is possibly different than the one applied to the search. # Used to calculate NTT & NMC in pepXML output. # Available for comet. sample_enzyme_number=1 # Start and scan scan range to search; 0 as first entry ignores parameter. # Available for comet. scan_range=0 0 # Precursor charge range to analyze; does not override mzXML charge; 0 as first # entry ignores parameter. # Available for comet. precursor_charge=0 0 # Specifies the whether to override existing precursor charge state information # when present in the files with the charge range specified by the # "precursor_charge" parameter. # Available for comet. override_charge=0 # MS level to analyze, valid are levels 2 or 3. # Available for comet. ms_level=2 # Specifies which scan types are searched. # Available for comet. activation_method=ALL # MH+ peptide mass range to analyze. # Available for comet. digest_mass_range=600.0 5000.0 # Number of search hits to store internally. # Available for comet. num_results=50 # For '.out' file output only, 0=search everything again, 1=don't search if .out # exists. # Available for comet. skip_researching=1 # Set maximum fragment charge state to analyze (allowed max 5). # Available for comet. max_fragment_charge=3 # Set maximum precursor charge state to analyze (allowed max 9). # Available for comet. max_precursor_charge=6 # 0=proteinDB, 1-6, 7=forward three, 8=reverse three, 9=all six. # Available for comet. nucleotide_reading_frame=0 # 0=leave sequences as-is; 1=also consider sequence w/o N-term methionine. # Available for comet. clip_nterm_methionine=0 # Maximum number of spectra to search at a time; 0 to search the entire scan # range in one loop. # Available for comet. spectrum_batch_size=0 # Specifies the prefix of the protein names that indicates a decoy. # Available for comet. decoy_prefix=decoy_ # Specifies the suffix string that is appended to the base output name for the # pep.xml, pin.xml, txt and sqt output files. # Available for comet. output_suffix= # Specifies one or more mass offsets to apply. This value(s) are effectively # subtracted from each precursor mass such that peptides that are smaller than # the precursor mass by the offset value can still be matched to the respective # spectrum. # Available for comet. mass_offsets= # Minimum number of peaks in spectrum to search. # Available for comet. minimum_peaks=10 # Minimum intensity value to read in. # Available for comet. minimum_intensity=0 # 0=no, 1=yes, 2=all charge reduced precursor peaks (for ETD). # Available for comet. remove_precursor_peak=0 # +- Da tolerance for precursor removal. # Available for comet. remove_precursor_tolerance=1.5 # For iTRAQ/TMT type data; will clear out all peaks in the specified m/z range. # Available for comet. clear_mz_range=0.0 0.0 # Up to 9 variable modifications are supported. Each modification is specified # using seven entries: " # ." Type is 0 for static mods and non-zero for variable mods. Note that # that if you set the same type value on multiple modification entries, Comet # will treat those variable modifications as a binary set. This means that all # modifiable residues in the binary set must be unmodified or modified. Multiple # binary sets can be specified by setting a different binary modification value. # Max is an integer specifying the maximum number of modified residues possible # in a peptide for this modification entry. Distance specifies the distance the # modification is applied to from the respective terminus: -1 = no distance # contraint; 0 = only applies to terminal residue; N = only applies to terminal # residue through next N residues. Terminus specifies which terminus the # distance constraint is applied to: 0 = protein N-terminus; 1 = protein # C-terminus; 2 = peptide N-terminus; 3 = peptide C-terminus.Force specifies # whether peptides must contain this modification: 0 = not forced to be present; # 1 = modification is required. # Available for comet. variable_mod01=0.0 null 0 4 -1 0 0 # See syntax for variable_mod01. # Available for comet. variable_mod02=0.0 null 0 4 -1 0 0 # See syntax for variable_mod01. # Available for comet. variable_mod03=0.0 null 0 4 -1 0 0 # See syntax for variable_mod01. # Available for comet. variable_mod04=0.0 null 0 4 -1 0 0 # See syntax for variable_mod01. # Available for comet. variable_mod05=0.0 null 0 4 -1 0 0 # See syntax for variable_mod01. # Available for comet. variable_mod06=0.0 null 0 4 -1 0 0 # See syntax for variable_mod01. # Available for comet. variable_mod07=0.0 null 0 4 -1 0 0 # See syntax for variable_mod01. # Available for comet. variable_mod08=0.0 null 0 4 -1 0 0 # See syntax for variable_mod01. # Available for comet. variable_mod09=0.0 null 0 4 -1 0 0 # Specifies the total/maximum number of residues that can be modified in a # peptide. # Available for comet. max_variable_mods_in_peptide=5 # Controls whether the analyzed peptides must contain at least one variable # modification. # Available for comet. require_variable_mod=0 # Specifiy a static modification to the c-terminus of all peptides. # Available for comet. add_Cterm_peptide=0 # Specify a static modification to the n-terminus of all peptides. # Available for comet. add_Nterm_peptide=0 # Specify a static modification to the c-terminal peptide of each protein. # Available for comet. add_Cterm_protein=0 # Specify a static modification to the n-terminal peptide of each protein. # Available for comet. add_Nterm_protein=0 # Specify a static modification to the residue A. # Available for comet. add_A_alanine=0 # Specify a static modification to the residue B. # Available for comet. add_B_user_amino_acid=0 # Specify a static modification to the residue C. # Available for comet. add_C_cysteine=57.021464 # Specify a static modification to the residue D. # Available for comet. add_D_aspartic_acid=0 # Specify a static modification to the residue E. # Available for comet. add_E_glutamic_acid=0 # Specify a static modification to the residue F. # Available for comet. add_F_phenylalanine=0 # Specify a static modification to the residue G. # Available for comet. add_G_glycine=0 # Specify a static modification to the residue H. # Available for comet. add_H_histidine=0 # Specify a static modification to the residue I. # Available for comet. add_I_isoleucine=0 # Specify a static modification to the residue J. # Available for comet. add_J_user_amino_acid=0 # Specify a static modification to the residue K. # Available for comet. add_K_lysine=0 # Specify a static modification to the residue L. # Available for comet. add_L_leucine=0 # Specify a static modification to the residue M. # Available for comet. add_M_methionine=0 # Specify a static modification to the residue N. # Available for comet. add_N_asparagine=0 # Specify a static modification to the residue O. # Available for comet. add_O_ornithine=0 # Specify a static modification to the residue P. # Available for comet. add_P_proline=0 # Specify a static modification to the residue Q. # Available for comet. add_Q_glutamine=0 # Specify a static modification to the residue R. # Available for comet. add_R_arginine=0 # Specify a static modification to the residue S. # Available for comet. add_S_serine=0 # Specify a static modification to the residue T. # Available for comet. add_T_threonine=0 # Specify a static modification to the residue U. # Available for comet. add_U_selenocysteine=0 # Specify a static modification to the residue V. # Available for comet. add_V_valine=0 # Specify a static modification to the residue W. # Available for comet. add_W_tryptophan=0 # Specify a static modification to the residue X. # Available for comet. add_X_user_amino_acid=0 # Specify a static modification to the residue Y. # Available for comet. add_Y_tyrosine=0 # Specify a static modification to the residue Z. # Available for comet. add_Z_user_amino_acid=0 # # COMET_ENZYME_INFO _must_ be at the end of this parameters file # [COMET_ENZYME_INFO] 0. No_enzyme 0 - - 1. Trypsin 1 KR P 2. Trypsin/P 1 KR - 3. Lys_C 1 K P 4. Lys_N 0 K - 5. Arg_C 1 R P 6. Asp_N 0 D - 7. CNBr 1 M - 8. Glu_C 1 DE P 9. PepsinA 1 FL P 10. Chymotrypsin 1 FWYL P