Prior-vs-physics benchmark for DL de novo sequencing

benchmark

Prior-vs-physics benchmark for DL de novo sequencing: benchmark. Benchmark that disentangles how much of a DL de novo sequencer’s output reflects MS/MS fragmentation evidence vs learned peptide-sequence priors: important for assessing…

Benchmark that disentangles how much of a DL de novo sequencer’s output reflects MS/MS fragmentation evidence vs learned peptide-sequence priors: important for assessing robustness on out-of-distribution proteomes.

Kind	benchmark
Acquisition	DDA

Papers

• Learning Fragmentation Physics or Exploiting Sequence Priors? Benchmarking Bias in Deep Learning Models for De Novo Peptide Sequencing (2026, bioRxiv, preprint)

Authors (2)

Jiayi Li, Hannes Röst

Seen in the charts

Back to the full map