Specollate Model

Model Description

SpeCollate is the first Deep Learning-based peptide-spectrum similarity network. It allows searching a peptide database by generating embeddings for both mass spectra and database peptides. K-nearest neighbor search is performed on a GPU in the embedding space to find the k (usually k=5) nearest peptide for each spectrum.

Architecture

SpeCollate network consists of two branch, i.e., Spectrum Sub-Network (SSN) and Peptide Sub-Network (PSN). SSN processes spectra and generates spectral embeddings while PSN processes peptide sequences and generates peptides embeddings. Both types of embeddings are generated in real space of dimension 256. The network architecture is shown in Fig 1 below.

Model Details

The Specollate model:

Encodes mass spectra into 512-dimensional embeddings
Encodes peptide sequences into matching embedding space
Enables fast cosine similarity search for PSM identification

Citation

Tariq, Muhammad Usman, and Fahad Saeed. "SpeCollate: Deep cross-modal similarity network for mass spectrometry data based peptide deductions." PloS one 16.10 (2021): e0259349.

License

This model and associated code are released under the CC-BY-NC-ND 4.0 license and may only be used for non-commercial, academic research purposes with proper attribution. Any commercial use, sale, or other monetization of this model and its derivatives, which include models trained on outputs from the model or datasets created from the model, is prohibited and requires prior approval. Downloading the model requires prior registration on Hugging Face and agreeing to the terms of use. By downloading this model, you agree not to distribute, publish or reproduce a copy of the model. If another user within your organization wishes to use the model, they must register as an individual user and agree to comply with the terms of use. Users may not attempt to re-identify the deidentified data used to develop the underlying model. If you are a commercial entity, please contact the corresponding author.