PepNet

A fully Convolutional Neural Network for De novo Peptide Sequencing

View Pulication (coming soon)
Try Online Prediction

About PepNet

The SOTA de novo sequencing model.

  • High accuracy sequencing.
  • Support multiple charges.

Code

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

PepNet on Github

Dataset

Training and testing dataset for PepNet.

Datasets
-->

More Information

PepNet

The state of the art Deep CNN neural network for de novo sequencing of tandem mass spectra, currently works on unmodified HCD spectra of charges 1+ to 4+.

Also, Visit https://www.predfull.com/ to check our previous project on full spectrum prediction

Update History

Method

Based on the structure of the residual convolutional networks. Current precision (bin size): 0.1 Th.

model

How to use

After clone this project, you should download the pre-trained model (model.h5) from zenodo.org and place it into PepNet's folder.

Important Notes

Required Packages

Recommend to install dependency via Anaconda

Output format

Sample output looks like:

TITLE DENOVO Score PPM Difference Positional Score
spectra 1 LALYCHQLNLCSK 1.0000 -3.8919184 [1.0, 0.9999956, 1.0, 1.0, 1.0, 1.0, 0.99999976, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0]
spectra 2 HEELMLGDPCLK 1.0000 4.207922 [1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 0.99999976, 1.0]
spectra 3 AGLVGPEFHEK 1.0000 0.54602236 [1.0, 1.0, 1.0, 1.0, 1.0, 0.99999917, 1.0, 1.0, 1.0, 1.0, 1.0]

Usage

Simply run:

python denovo.py --input example.mgf --model model.h5 --output example_prediction.tsv

The output file is in MGF format

Prediction Examples

We provide sample data on zenodo for you to evaluate the sequencing performance. The example.mgf file on google drive contains ground truth spectra (randomly sampled from NIST Human Synthetic Peptide Spectral Library), while the example.tsv file contains pre-run predictions.