PepPr

algorithm · Transformer (AR)

PepPr: algorithm · Transformer (AR). A peptide language model fitted to a reference proteome, fused through a small learned head with the next-residue logits of an autoregressive sequencer (Casanovo or…

A peptide language model fitted to a reference proteome, fused through a small learned head with the next-residue logits of an autoregressive sequencer (Casanovo or ContraNovo) before beam search, so reference context fills gaps in incomplete spectra without excluding variants.

Kind algorithm
Deep learning yes
Acquisition DDA
Family Transformer (AR)

Code

Live stars, open issues and last-push figures are on the Code activity chart.

Checkpoints

Version Trained on Host Licence Size Checked
bioRxiv v1 priors: reference proteomes and immunoglobulin germline alleles (IMGT); fusion heads: a subset of Casanovo’s MassIVE-KB v1 training split Zenodo archival CC-BY-4.0 11.3 GB live 2026-10-29

Data

What the papers describing this method trained it on and reported its results on, as each paper states it. A version is named only where the paper names one.

Trained on

Evaluated on

Deposited

Paper describing it

Authors (5)

Samuel Khan, Daniela Klaproth-Andrade, Yanik Bruns, Mathias Wilhelm, Julien Gagneur

Seen in the charts

Back to the full map

Back to top