Skip to main content

dleamse model's econding and embedding method.

Project description

# 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
  1. useFADLEAMSE.py: encode and embed spectra, take one file (.mgf) as input and output a .csv file which contains 32d vectors.
  2. ndp_usetime.py: calculate computing time of normalized dot product (square-root tansformed, intensity normalization, top 100 peaks), and use @njit accelaration.
  3. dleamse_usetime_cpu.py: calculate conputing time of dleamse based similarity scoring with CPU, use @njit accelaration.
  4. 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.

Project details


Release history Release notifications

Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Files for dleamse, version 0.1.5
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

Supported by

Elastic Elastic Search Pingdom Pingdom Monitoring Google Google BigQuery Sentry Sentry Error logging AWS AWS Cloud computing DataDog DataDog Monitoring Fastly Fastly CDN DigiCert DigiCert EV certificate StatusPage StatusPage Status page