# Philosopher pipeline configuration file # Version 3.6.0 # # The pipeline mode automates the processing done by Philosopher and other tools. First, check # the steps you want to execute in the commands section and change them to # 'yes'. For each selected command, go to its section and adjust the parameters # accordingly to your analysis. # # If you want to include MSFragger and TMT-Integrator into your analysis, you will # have to download them separately, and then add their location in their # configuration section. # # Usage: # philosopher pipeline --config [list_of_data_set_folders] analytics: true # reports when a workspace is created for usage statistics slackToken: # specify the Slack API token (how to generate a token: https://api.slack.com/legacy/custom-integrations/legacy-tokens) slackChannel: # specify the channel name, or slackUserID: # specify a user ID for a direct message Steps: Database Search: yes # peptide to spectrum matching with Comet or MSFragger Peptide Validation: yes # peptide assignment validation with PeptideProphet PTM Localization: no # PTM site localization with PTMProphet Protein Inference: no # protein identification validation with ProteinProphet Label-Free Quantification: yes # precursor label-free quantification inspired by moFF Isobaric Quantification: yes # isobaric labeling-based relative quantification for TMT and iTRAQ Bio Cluster Quantification: no # protein report based on Uniprot protein clusters FDR Filtering: yes # statistical filtering, validation and false discovery r ates assessment Individual Reports: yes # multi-level reporting for both narrow-searches and open-searches Integrated Reports: yes # combined analysis of LC-MS/MS results inspired by Abacus Integrated Isobaric Quantification: yes # integrates channel abundances from multiple isobaric-tagged samples with TMT-Integrator Database Search: # MSFragger 3.2 & Comet protein_database: [database directory] # path to the target-decoy protein database decoy_tag: rev_ # prefix tag used added to decoy sequences contaminant_tag: false # prefix tag used added to decoy sequences search_engine: msfragger # search engine options include "comet" and "msfragger" comet: # Comet v2019011 noindex: true # skip mzML file indexing param: # comet parameter file (default "comet.params.txt") extension: mzML # format of the spectra file msfragger: # MSFragger v3.0 path: bin/MSFragger-3.0.jar # path to MSFragger jar memory: 32 # how much memory in GB to use param: # MSFragger parameter file extension: mzML # spectra format data_type: 0 # 0 for DDA, 1 for DIA, 2 for DIA-narrow-window num_threads: 32 # 0=poll CPU to set num threads; else specify num threads directly (max 64) precursor_mass_lower: -20 # lower bound of the precursor mass window precursor_mass_upper: 20 # upper bound of the precursor mass window precursor_mass_units: 1 # 0=Daltons, 1=ppm precursor_true_tolerance: 20 # true precursor mass tolerance (window is +/- this value) precursor_true_units: 1 # 0=Daltons, 1=ppm fragment_mass_tolerance: 20 # fragment mass tolerance (window is +/- this value) fragment_mass_units: 1 # fragment mass tolerance units (0 for Da, 1 for ppm) calibrate_mass: 2 # 0=Off, 1=On, 2=On and find optimal parameters deneutralloss: 0 # Perform deneutrallossing or not (0=no, 1=yes) deisotope: 1 # activates deisotoping. isotope_error: -1/0/1/2/3 # 0=off, 0/1/2 (standard C13 error) mass_offsets: 0 # allow for additional precursor mass window shifts. Multiplexed with isotope_error. mass_offsets = 0/79.966 can be used as a restricted ‘open’ search that looks for unmodified and phosphorylated peptides (on any residue) precursor_mass_mode: selected # selected or isolated localize_delta_mass: 0 # this allows shifted fragment ions - fragment ions with mass increased by the calculated mass difference, to be included in scoring delta_mass_exclude_ranges: (-1.5,3.5) # exclude mass range for shifted ions searching fragment_ion_series: b,y # ion series used in search ion_series_definitions: # User defined ion series. (Example: b* N -17.026548;b0 N -18.010565) search_enzyme_name: Trypsin # name of enzyme to be written to the pepXML file search_enzyme_cutafter: KR # residues after which the enzyme cuts search_enzyme_butnotafter: P # residues that the enzyme will not cut before num_enzyme_termini: 2 # 2 for enzymatic, 1 for semi-enzymatic, 0 for nonspecific digestion allowed_missed_cleavage: 2 # maximum value is 5 clip_nTerm_M: 1 # specifies the trimming of a protein N-terminal methionine as a variable modification (0 or 1) variable_mod_01: 15.99490 M 3 # variable modification variable_mod_02: 42.01060 [^ 1 # variable modification variable_mod_03: 229.162932 n^ 1 # variable modification variable_mod_04: 229.162932 S 1 # variable modification variable_mod_05: # variable modification variable_mod_06: # variable modification variable_mod_07: # variable modification allow_multiple_variable_mods_on_residue: 0 # static mods are not considered max_variable_mods_per_peptide: 3 # maximum of 5 max_variable_mods_combinations: 5000 # maximum of 65534, limits number of modified peptides generated from sequence output_file_extension: pepXML # file extension of output files output_format: pepXML # file format of output files (pepXML or tsv) write_calibrated_mgf: 0 # Write calibrated MS2 scan to a MGF file (0 for No, 1 for Yes) output_report_topN: 1 # reports top N PSMs per input spectrum output_max_expect: 50 # suppresses reporting of PSM if top hit has expectation greater than this threshold report_alternative_proteins: 0 # 0=no, 1=yes precursor_charge: 1 6 # assume range of potential precursor charge states. Only relevant when override_charge is set to 1 override_charge: 0 # 0=no, 1=yes to override existing precursor charge states with precursor_charge parameter digest_min_length: 7 # minimum length of peptides to be generated during in-silico digestion digest_max_length: 50 # maximum length of peptides to be generated during in-silico digestion digest_mass_range: 500.0 5000.0 # mass range of peptides to be generated during in-silico digestion in Daltons max_fragment_charge: 2 # maximum charge state for theoretical fragments to match (1-4) track_zero_topN: 0 # in addition to topN results, keep track of top results in zero bin zero_bin_accept_expect: 0 # boost top zero bin entry to top if it has expect under 0.01 - set to 0 to disable zero_bin_mult_expect: 1 # disabled if above passes - multiply expect of zero bin for ordering purposes (does not affect reported expect) add_topN_complementary: 0 # inserts complementary ions corresponding to the top N most intense fragments in each experimental spectra minimum_peaks: 15 # required minimum number of peaks in spectrum to search (default 10) use_topN_peaks: 300 # pre-process experimental spectrum to only use top N peaks min_fragments_modelling: 2 # minimum number of matched peaks in PSM for inclusion in statistical modeling min_matched_fragments: 4 # minimum number of matched peaks for PSM to be reported minimum_ratio: 0.01 # filters out all peaks in experimental spectrum less intense than this multiple of the base peak intensity clear_mz_range: 125.5 131.5 # for iTRAQ/TMT type data; will clear out all peaks in the specified m/z range remove_precursor_peak: 0 # remove precursor peaks from tandem mass spectra. 0=not remove; 1=remove the peak with precursor charge; 2=remove the peaks with all charge states. remove_precursor_range: -1.5,1.5 # m/z range in removing precursor peaks. Unit: Da. intensity_transform: 0 # transform peaks intensities with sqrt root. 0=not transform; 1=transform using sqrt root. mass_diff_to_variable_mod: 0 # Put mass diff as a variable modification. 0 for no; 1 for yes and change the original mass diff and the calculated mass accordingly; 2 for yes but do not change the original mass diff. labile_search_mode: off # type of search (nglycan, labile, or off). Off means non-labile/typical search. restrict_deltamass_to: all # Specify amino acids on which delta masses (mass offsets or search modifications) can occur. Allowed values are single letter codes (e.g. ACD), must diagnostic_intensity_filter: 0 # [nglycan/labile search_mode only]. Minimum relative intensity for SUM of all detected oxonium ions to achieve for spectrum to contain diagnostic fragment evidence. Calculated relative to spectrum base peak. 0 <= value. Y_type_masses: 0 # [nglycan/labile search_mode only]. Specify fragments of labile mods that are commonly retained on intact peptides (e.g. Y ions for glycans). Only used if 'Y' is included in fragment_ion_series. diagnostic_fragments: 0 # [nglycan/labile search_mode only]. Specify diagnostic fragments of labile mods that appear in the low m/z region. Only used if diagnostic_intensity_filter > 0. add_Cterm_peptide: 0.000000 # c-term peptide fixed modifications add_Cterm_protein: 0.000000 # c-term protein fixed modifications add_Nterm_peptide: 0.000000 # n-term peptide fixed modifications add_Nterm_protein: 0.000000 # n-term protein fixed modifications add_A_alanine: 0.000000 # alanine fixed modifications add_C_cysteine: 57.021464 # cysteine fixed modifications add_D_aspartic_acid: 0.000000 # aspartic acid fixed modifications add_E_glutamic_acid: 0.000000 # glutamic acid fixed modifications add_F_phenylalanine: 0.000000 # phenylalanine fixed modifications add_G_glycine: 0.000000 # glycine fixed modifications add_H_histidine: 0.000000 # histidine fixed modifications add_I_isoleucine: 0.000000 # isoleucine fixed modifications add_K_lysine: 229.162932 # lysine fixed modifications add_L_leucine: 0.000000 # leucine fixed modifications add_M_methionine: 0.000000 # methionine fixed modifications add_N_asparagine: 0.000000 # asparagine fixed modifications add_P_proline: 0.000000 # proline fixed modifications add_Q_glutamine: 0.000000 # glutamine fixed modifications add_R_arginine: 0.000000 # arginine fixed modifications add_S_serine: 0.000000 # serine fixed modifications add_T_threonine: 0.000000 # threonine fixed modifications add_V_valine: 0.000000 # valine fixed modifications add_W_tryptophan: 0.000000 # tryptophan fixed modifications add_Y_tyrosine: 0.000000 # tyrosine fixed modifications Peptide Validation: # PeptideProphet v5.2 concurrent: false # Concurrent execution of multiple instaces extension: pepXML # pepXML file extension clevel: 0 # set Conservative Level in neg_stdev from the neg_mean, low numbers are less conservative, high numbers are more conservative accmass: true # use Accurate Mass model binning decoyprobs: true # compute possible non-zero probabilities for Decoy entries on the last iteration enzyme: trypsin # enzyme used in sample (optional) exclude: false # exclude deltaCn*, Mascot*, and Comet* results from results (default Penalize * results) expectscore: true # use expectation value as the only contributor to the f-value for modeling forcedistr: false # bypass quality control checks, report model despite bad modeling glyc: false # enable peptide Glyco motif model icat: false # apply ICAT model (default Autodetect ICAT) instrwarn: false # warn and continue if combined data was generated by different instrument models leave: false # leave alone deltaCn*, Mascot*, and Comet* results from results (default Penalize * results) maldi: false # enable MALDI mode masswidth: 5 # model mass width (default 5) minpeplen: 7 # minimum peptide length not rejected (default 7) minpintt: 2 # minimum number of NTT in a peptide used for positive pI model (default 2) minpiprob: 0.9 # minimum probability after first pass of a peptide used for positive pI model (default 0.9) minprob: 0.05 # report results with minimum probability (default 0.05) minrtntt: 2 # minimum number of NTT in a peptide used for positive RT model (default 2) minrtprob: 0.9 # minimum probability after first pass of a peptide used for positive RT model (default 0.9) neggamma: false # use Gamma distribution to model the negative hits noicat: false # do no apply ICAT model (default Autodetect ICAT) nomass: false # disable mass model nonmc: false # disable NMC missed cleavage model nonparam: true # use semi-parametric modeling, must be used in conjunction with --decoy option nontt: false # disable NTT enzymatic termini model optimizefval: false # (SpectraST only) optimize f-value function f(dot,delta) using PCA phospho: false # enable peptide Phospho motif model pi: false # enable peptide pI model ppm: true # use PPM mass error instead of Dalton for mass modeling zero: false # report results with minimum probability 0 PTM Localization: # PTMProphet v6.0 autodirect: false # use direct evidence when the lability is high, use in combination with LABILITY cions: # use specified C-term ions, separate multiple ions by commas (default: y for CID, z for ETD) direct: false # use only direct evidence for evaluating PTM site probabilities em: 2 # set EM models to 0 (no EM), 1 (Intensity EM Model Applied) or 2 (Intensity and Matched Peaks EM Models Applied) static: false # use static fragppmtol for all PSMs instead of dynamically estimates offsets and tolerances fragppmtol: 15 # when computing PSM-specific mass_offset and mass_tolerance, use specified default +/- MS2 mz tolerance on fragment ions ifrags: false # use internal fragments for localization keepold: false # retain old PTMProphet results in the pepXML file lability: false # compute Lability of PTMs massdiffmode: false # use the Mass Difference and localize excludemassdiffmin: 0 # Minimum mass difference excluded for MASSDIFFFMODE analysis (default=0) excludemassdiffmax: 0 # Maximun mass difference excluded for MASSDIFFFMODE analysis (default=0) massoffset: 0 # adjust the massdiff by offset (0 = use default) maxfragz: 0 # limit maximum fragment charge (default: 0=precursor charge, negative values subtract from precursor charge) maxthreads: 4 # use specified number of threads for processing mino: 0 # use specified number of pseudo-counts when computing Oscore (0 = use default) minprob: 0 # use specified minimum probability to evaluate peptides mods: # specify modifications nions: # use specified N-term ions, separate multiple ions by commas (default: a,b for CID, c for ETD) nominofactor: false # disable MINO factor correction when MINO= is set greater than 0 (default: apply MINO factor correction) ppmtol: 1 # use specified +/- MS1 ppm tolerance on peptides which may have a slight offset depending on search parameters verbose: false # produce Warnings to help troubleshoot potential PTM shuffling or mass difference issues Protein Inference: # ProteinProphet v5.2 accuracy: false # equivalent to --minprob 0 allpeps: false # consider all possible peptides in the database in the confidence model confem: false # use the EM to compute probability given the confidence delude: false # do NOT use peptide degeneracy information when assessing proteins excludezeros: false # exclude zero prob entries fpkm: false # model protein FPKM values glyc: false # highlight peptide N-glycosylation motif icat: false # highlight peptide cysteines instances: false # use Expected Number of Ion Instances to adjust the peptide probabilities prior to NSP adjustment iprophet: false # input is from iProphet logprobs: false # use the log of the probabilities in the Confidence calculations maxppmdiff: 20 # maximum peptide mass difference in PPM (default 20) minprob: 0.05 # peptideProphet probabilty threshold (default 0.05) mufactor: 1 # fudge factor to scale MU calculation (default 1) nogroupwts: false # check peptide's Protein weight against the threshold (default: check peptide's Protein Group weight against threshold) nonsp: false # do not use NSP model nooccam: false # non-conservative maximum protein list noprotlen: false # do not report protein length normprotlen: false # normalize NSP using Protein Length protmw: false # get protein mol weights softoccam: false # peptide weights are apportioned equally among proteins within each Protein Group (less conservative protein count estimate) unmapped: false # report results for UNMAPPED proteins Label-Free Quantification: # Freequant peakTimeWindow: 0.4 # specify the time windows for the peak (minute) (default 0.4) retentionTimeWindow: 3 # specify the retention time window for xic (minute) (default 3) tolerance: 10 # m/z tolerance in ppm (default 10) raw: false # read raw files instead of converted mzML, or mzXML faims: false # use FAIMS information for the quantification Isobaric Quantification: # Labelquant bestPSM: true # select the best PSMs for protein quantification level: 2 # ms level for the quantification minProb: 0.7 # only use PSMs with a minimum probability score plex: 11 # number of channels purity: 0.5 # ion purity threshold (default 0.5) removeLow: 0.05 # ignore the lower 3% PSMs based on their summed abundances tolerance: 20 # m/z tolerance in ppm (default 20) uniqueOnly: false # report quantification based on only unique peptides brand: tmt # isobaric labeling brand (tmt, itraq) raw: false # read raw files instead of converted mzML, or mzXML Bio Cluster Quantification: # BioQuant organismUniProtID: # UniProt proteome ID level: 0.9 # cluster identity level (default 0.9) FDR Filtering: # Filter psmFDR: 0.01 # psm FDR level (default 0.01) peptideFDR: 0.01 # peptide FDR level (default 0.01) ionFDR: 0.01 # peptide ion FDR level (default 0.01) proteinFDR: 0.01 # protein FDR level (default 0.01) peptideProbability: 0.7 # top peptide probability threshold for the FDR filtering (default 0.7) proteinProbability: 0.5 # protein probability threshold for the FDR filtering (not used with the razor algorithm) (default 0.5) peptideWeight: 1 # threshold for defining peptide uniqueness (default 1) razor: true # use razor peptides for protein FDR scoring picked: true # apply the picked FDR algorithm before the protein scoring mapMods: true # map modifications acquired by an open search models: true # print model distribution sequential: true # alternative algorithm that estimates FDR using both filtered PSM and Protein lists Individual Reports: # Report msstats: false # create an output compatible to MSstats withDecoys: false # add decoy observations to reports mzID: false # create a mzID output Integrated Reports: # Abacus protein: true # global level protein report peptide: true # global level peptide report proteinProbability: 0.9 # minimum protein probability (default 0.9) peptideProbability: 0.5 # minimum peptide probability (default 0.5) uniqueOnly: false # report TMT quantification based on only unique peptides reprint: false # create abacus reports using the Reprint format Integrated Isobaric Quantification: # TMT-Integrator v1.1.10 path: [TMTIntegrator directory] # path to TMT-Integrator jar memory: 32 # memory allocation, in Gb output: [TMTIntegrator output file] # the location of output files channel_num: 11 # number of channels in the multiplex (e.g. 10, 11) ref_tag: Pool # unique tag for identifying the reference channel (Bridge sample added to each multiplex) groupby: -1 # level of data summarization(0: PSM aggregation to the gene level; 1: protein; 2: peptide sequence; 3: PTM site; -1: generate reports at all levels) psm_norm: false # perform additional retention time-based normalization at the PSM level outlier_removal: true # perform outlier removal prot_norm: -1 # normalization (0: None; 1: MD (median centering); 2: GN (median centering + variance scaling); -1: generate reports with all normalization options) min_pep_prob: 0.9 # minimum PSM probability threshold (in addition to FDR-based filtering by Philosopher) min_purity: 0.5 # ion purity score threshold min_percent: 0.05 # remove low intensity PSMs (e.g. value of 0.05 indicates removal of PSMs with the summed TMT reporter ions intensity in the lowest 5% of all PSMs) unique_pep: false # allow PSMs with unique peptides only (if true) or unique plus razor peptides (if false), as classified by Philosopher and defined in PSM.tsv files unique_gene: 0 # additional, gene-level uniqueness filter (0: allow all PSMs; 1: remove PSMs mapping to more than one GENE with evidence of expression in the dataset; 2:remove all PSMs mapping to more than one GENE in the fasta file) best_psm: true # keep the best PSM only (highest summed TMT intensity) among all redundant PSMs within the same LC-MS run prot_exclude: none # exclude proteins with specified tags at the beginning of the accession number (e.g. none: no exclusion; sp|,tr| : exclude protein with sp| or tr|) allow_overlabel: true # allow PSMs with TMT on S (when overlabeling on S was allowed in the database search) allow_unlabeled: true # allow PSMs without TMT tag or acetylation on the peptide n-terminus mod_tag: none # PTM info for generation of PTM-specific reports (none: for Global data; S[167],T[181],Y[243]: for Phospho; K[170]: for K-Acetyl) min_site_prob: -1 # site localization confidence threshold (-1: for Global; 0: as determined by the search engine; above 0 (e.g. 0.75): PTMProphet probability, to be used with phosphorylation only) ms1_int: true # use MS1 precursor ion intensity (if true) or MS2 summed TMT reporter ion intensity (if false) as part of the reference sample abundance estimation top3_pep: true # use top 3 most intense peptide ions as part of the reference sample abundance estimation print_RefInt: false # print individual reference sample abundance estimates for each multiplex in the final reports (in addition to the combined reference sample abundance estimate) add_Ref: -1 # add an artificial reference channel if there is no reference channel (-1: don't add the reference; 0: use summation as the reference; 1: use average as the reference; 2: use median as the reference) max_pep_prob_thres: 0 # the threshold for maximum peptide probability min_ntt: 0 # minimum allowed number of enzymatic termini