Predfull

Full-Spectrum Prediction of Peptides Tandem Mass Spectra using Deep Neural Network

About Predfull

The first complete spectra prediction tool.

  • Complete prediction for all peaks.
  • Support multiple charges and both HCD, ETD.

Code

Predfull is open sourse to everyone, star it on Github now.

PredFull on Github

Dataset

Training and testing dataset for Predfull.

Dataset

More Information

PredFull

Model for Full-Spectrum Prediction of Peptides Tandem Mass Spectra using Deep Neural Network

Kaiyuan Liu, Sujun Li, Lei Wang, Yuzhen Ye, Haixu Tang

Method

Based on the structure of the residual convolutional networks. Current precision: 0.1 Th.

model

How to use

Required Packages

Recommend to install dependency via Anaconda

Input format

The required input format is TSV, with following columns:

Peptide | Charge | Type | NCE ------- | ------ | ---- | --- AAAAAAAAAVSR | 2 | HCD | 25 AAGAAESEEDFLR | 2 | HCD | 25 AAPAPTASSTININTSTSK | 2 | HCD | 25

Apparently, 'Peptide' and 'Charge' columns mean what it says. The 'Type' must be HCD or ETD (in uppercase). NCE means normalized collision energy, set to 25 or 30 if you don't care. Check example.tsv for examples.

Usage

Simply run:

python predfull.py --input .\example.tsv --weights pm.hdf5 --output .\example.mgf

The output file is in MGF format

Prediction Examples

example 1

example 2