Skip to main content
. Author manuscript; available in PMC: 2021 May 6.
Published in final edited form as: J Am Soc Mass Spectrom. 2020 Apr 8;31(5):1104–1113. doi: 10.1021/jasms.0c00035

Table 1 -.

Description of Features used in Machine Learning

Feature Name Data Type Description
Activation ECD/CID Activation used to generate spectra
Charge Integer Charge of the peaks within the cluster
Votes Integer Number of deconvolution algorithms that called a peak within that cluster
SumIntensity Numeric Sum of the intensity of peaks in the cluster
AverageIntensity Numeric Average intensity of peaks in the cluster
MSDeconv Boolean MS-Deconv called this peak
TopFD Boolean TopFD called this peak
THRASH60 Boolean THRASH with 60% Fit called this peak
THRASH70 Boolean THRASH with 70% Fit called this peak
THRASH80 Boolean THRASH with 80% Fit called this peak
THRASH90 Boolean THRASH with 90% Fit called this peak
SNAP Boolean SNAP called this peak
PrecursorCharge Integer Charge of the precursor
AvgMass Numeric Average Mass of the peaks within the cluster
StdDev Numeric Standard Deviation of the mass of the peaks within the cluster
PrecursorMass Numeric Monoisotopic mass of the precursor
PrecursorMZ Numeric m/z of the precursor