annotate test-data/mysettings_galaxy.ini @ 1:c1a9c990d4b0 draft

planemo upload for repository https://github.com/RECETOX/galaxytools/tree/master/tools/rmassbank commit b1cc1aebf796f170d93e3dd46ffcdefdc7b8018a

# Sample configuration file for RMassBank.
# Adapt this file to your needs.
# NOTE: Do not indent with TAB characters! Use only spaces.
# (If your editor converts TAB to a certain number of spaces, it's OK.)
# Use a space after the colon.

# Deprofile input data?
# Leave empty if input data is already in "centroid" mode.
# Use values deprofile.spline, deprofile.fwhm or deprofile.localMax to convert the input data with the
# corresponding algorithm. See ?deprofile
deprofile: 

# Deviation (in minutes) allowed the for retention time
rtMargin: 0.4
# Systematic retention time shift
rtShift: 0.0

# Directory to OpenBabel. Required for creating molfiles for MassBank export.
# If no OpenBabel directory is given, RMassBank will attempt to use the CACTUS webservice
# for SDF generation. You really should install OpenBabel though; the CACTUS structures
# have explicit hydrogen atoms...
# Points to the directory where babel.exe (or the Linux "babel" equivalent) lies.
babeldir: '/home/debian/galaxy/database/dependencies/_conda/envs/mulled-v1-43859fe15e1521a7d623c43fc3f4525ebe6dbf17b1890fad8281284c7ee7581a/bin/'

# Which MassBank record version to use; version 2 is advised.
use_version: 2

# Include reanalyzed peaks?
use_rean_peaks: TRUE

# annotate the spectra files with (putative) molecular formulas for fragments?
add_annotation: TRUE

# Annotations for the spectrum:
annotations:
    # Author etc. annotation
    authors: Nomen Nescio, The Unseen University
    copyright: Copyright (C) XXX
    publication: 
    license: CC BY
    instrument: LTQ Orbitrap XL Thermo Scientific
    instrument_type: LC-ESI-ITFT
    confidence_comment: standard compound
    compound_class: N/A; Environmental Standard
    internal_id_fieldname: INTERNAL_ID
    #
    # HPLC annotations:
    #
    # example: lc_gradient: 90/10 at 0 min, 50/50 at 4 min, 5/95 at 17 min, 5/95 at 25 min, 90/10 at 25.1 min, 90/10 at 30 min
    lc_gradient: 
    # example: lc_flow: 200 uL/min
    lc_flow: 
    # example: lc_solvent_a: water with 0.1% formic acid
    lc_solvent_a: 
    lc_solvent_b: 
    # example: lc_column: XBridge C18 3.5um, 2.1x50mm, Waters
    lc_column: 
    # Prefix for MassBank accession IDs
    entry_prefix: XX
    ms_type: MS2
    ionization: ESI
    ms_dataprocessing:
        RECALIBRATE: loess on assigned fragments and MS1

include_sp_tags: FALSE

# Annotator:
# by default, "annotator.default" is used.
# If you want to build your custom annotator (check ?annotator.default and the source code),
# select it here by using e.g.
# annotator: annotator.myown
# for a function annotator.myown(annotation)

# List of data-dependent scans in their order (relative to the parent scan), for annotation of the MassBank records
# For every data-dependent scan event, specify an element with:
# mode: fragmentation mode, e.g. CID
# ces: "short" format collision energy (for record title)
# ce: "long" format collision energy (for annotation field)
# res: FT resolution
spectraList:
 # First scan: CID 35% NCE, resolution 7500 
- mode: CID
  ces: 35%
  ce: 35 % (nominal)
  res: 7500
 # Second scan: HCD 15% NCE, resolution 7500
- mode: HCD
  ces: 15%
  ce: 15 % (nominal)
  res: 7500
 # Third scan, etc.
- mode: HCD
  ces: 30%
  ce: 30 % (nominal)
  res: 7500
- mode: HCD
  ces: 45%
  ce: 45 % (nominal)
  res: 7500
- mode: HCD
  ces: 60%
  ce: 60 % (nominal)
  res: 7500
- mode: HCD
  ces: 75%
  ce: 75 % (nominal)
  res: 7500
- mode: HCD
  ces: 90%
  ce: 90 % (nominal)
  res: 7500
- mode: HCD
  ces: 15%
  ce: 15 % (nominal)
  res: 15000
- mode: HCD
  ces: 30%
  ce: 30 % (nominal)
  res: 15000
- mode: HCD
  ces: 45%
  ce: 45 % (nominal)
  res: 15000
- mode: HCD
  ces: 60%
  ce: 60 % (nominal)
  res: 15000
- mode: HCD
  ces: 75%
  ce: 75 % (nominal)
  res: 15000
- mode: HCD
  ces: 90%
  ce: 90 % (nominal)
  res: 15000
- mode: CID
  ces: 35%
  ce: 35 % (nominal)
  res: 15000

# Shifts of the starting points for RMassBank accession numbers.
# Change these if you measure different adducts 
accessionNumberShifts:
    pH: 0 # [M+H]+: Accession numbers 1-14
    pM: 16 # [M]+: 17-30
    pNa: 32 # [M+Na]+: 33-46
    mH: 50 # [M-H]-: 51-64
    mFA: 66 # [M+FA]-: 67-80

# A list of known electronic noise peaks
electronicNoise:
- 189.825
- 201.725
- 196.875
# Exclusion width of electronic noise peaks (from unmatched peaks, prior to
# reanalysis)
electronicNoiseWidth: 0.3

# recalibration settings:
# recalibrate by: dppm or dmz
recalibrateBy: dppm

# recalibrate MS1:
# separately (separate)
# with common curve (common)
# do not recalibrate (none)
recalibrateMS1: common
# Window width to look for MS1 peaks to recalibrate (in ppm)
recalibrateMS1Window: 15

# Custom recalibration function: You can overwrite the recal function by
# making any function which takes rcdata$recalfield ~ rcdata$mzFound.
# The settings define which recal function is used.
# Note: if recalibrateMS1 is "common", the setting "recalibrator: MS1" is meaningless
# because the MS1 points will be recalibrated together with the MS2 points with 
# the MS2 recalibration function.
recalibrator:
    MS1: recalibrate.loess
    MS2: recalibrate.loess

# Define the multiplicity filtering level
# Default is 2 (peak occurs at least twice)
# Set this to 1 if you want to turn this option off.
# Set this to anything > 2 if you want harder filtering
multiplicityFilter: 2

# Define the title format.
# You can use all entries from MassBank records as tokens
# plus the additional token RECORD_TITLE_CE, which is a shortened
# version of the collision energy specifically for use in the title.
# Every line is one entry and must have one token in curly brackets
# e.g. {CH$NAME} or {AC$MASS_SPECTROMETRY: MS_TYPE} plus optionally
# additional text in front or behind e.g.
# R={AC$MASS_SPECTROMETRY: RESOLUTION}
# If this is not specified, it defaults to a title of the format
# "Dinotefuran; LC-ESI-QFT; MS2; CE: 35%; R=35000; [M+H]+"
# Note how everything must be in "" here because otherwise the : are getting mangled!
titleFormat:
- "{CH$NAME}"
- "{AC$INSTRUMENT_TYPE}"
- "{AC$MASS_SPECTROMETRY: MS_TYPE}"
- "CE: {RECORD_TITLE_CE}"
- "R={AC$MASS_SPECTROMETRY: RESOLUTION}"
- "{MS$FOCUSED_ION: PRECURSOR_TYPE}"

# Define filter settings.
# For Orbitrap, settings of 15 ppm in low mass range, 10 ppm in high
# mass range, m/z = 120 as mass range division and 5 ppm for recalibrated
# data overall are recommended. 
filterSettings:
    ppmHighMass: 10
    ppmLowMass: 15
    massRangeDivision: 120
    ppmFine: 5
    prelimCut: 1000
    prelimCutRatio: 0.0
    fineCut: 0.0
    fineCutRatio: 0.0
    specOkLimit: 1000
    dbeMinLimit: -0.5
    satelliteMzLimit: 0.5
    satelliteIntLimit: 0.05
    
 # Define raw MS retrieval settings.
findMsMsRawSettings:
    ppmFine: 5
    mzCoarse: 0.5
    # fillPrecursorScan is FALSE for "good" mzML files which have all the info needed.
    # However, for example AB Sciex files will have missing precursor scan information,
    # in which case fillPrecursorScan = TRUE is needed. Try it out.
    fillPrecursorScan: FALSE
    
# Select how to treat unknown compound masses: 
# "charged" (the default, also if no option set) treats unknown (level 5) compound masses as the m/z,
# "neutral" treats unknown (level 5) compound masses as the neutral mass and applies [M+H]+ and [M-H]- calculations accordingly.
unknownMass: charged