Spectrum representation ablation study

benchmark

Spectrum representation ablation study: benchmark. MSc thesis ablation of how MS/MS peaks should be represented for a Transformer de novo sequencer. Holds a Casanovo-style encoder-decoder backbone fixed and varies only…

MSc thesis ablation of how MS/MS peaks should be represented for a Transformer de novo sequencer. Holds a Casanovo-style encoder-decoder backbone fixed and varies only the peak embedding: additive m/z-intensity, separated/concatenated m/z and intensity, precursor-normalised (relative) m/z, learnable relative m/z, zero-vector controls, and probability-aware embeddings fed with DpNovo’s signal-vs-noise peak probabilities. Finds that separating peak features beats the additive baseline, relative m/z adds a further gain, and the best result combines external signal probability with intensity and mass features: evidence that input representation, not just architecture, moves the needle on Transformer de novo accuracy.

Kind benchmark
Deep learning yes

Papers

Authors (1)

Xinlue Shen

Seen in the charts

Back to the full map

Back to top