dleamse model's econding and embedding method.
# DLEAMSE A Deep LEArning-based Mass Spectra Embedder for spectral similarity scoring.
DLEAMSE (based on Siamese Network) is trained and tested with a larger dataset from PRIDE Cluster.
# Requirements Python3 (or Anaconda3) torch-1.0.0 (cpu or gpu version) pyteomics-3.5.1 numpy-1.13.3 numba-0.45.0
- # Scripts
- useFADLEAMSE.py: encode and embed spectra, take one file (.mgf) as input and output a .csv file which contains 32d vectors.
- ndp_usetime.py: calculate computing time of normalized dot product (square-root tansformed, intensity normalization, top 100 peaks), and use @njit accelaration.
- dleamse_usetime_cpu.py: calculate conputing time of dleamse based similarity scoring with CPU, use @njit accelaration.
- dleamse_usetime_gpu.py: calculate computing time of dleamse based similarity socring with GPU, use @njit accelaration.
- # Example
- 1. python useFASLEAMSE.py ../siamese_modle_reference/080802_20_1000_NM500R_model.pkl –input ./data/130402_08.mgf –output ./data/test.csv 2. 3.
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
|Filename, size||File type||Python version||Upload date||Hashes|
|Filename, size dleamse-0.1.5.tar.gz (5.5 kB)||File type Source||Python version None||Upload date||Hashes View hashes|