ReNovo

algorithm · Transformer (AR)

ReNovo: algorithm · Transformer (AR). Retrieval-based sequencing

Retrieval-based sequencing

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

Reported comparisons (3)

The comparison tables this method’s own papers print, standardised: every value on a 0-1 scale, methods down the side, the measure and then the species across. These are numbers papers report about themselves and their baselines. They are not a leaderboard, and they do not compare across tables: each was produced by a different group, on the dataset named in its corner, with each baseline either retrained, run from released weights or quoted from another paper. Where the paper says which, it follows the method’s name (hover it for the sentence); most papers do not say. Bold is the best value in a column and underline the runner-up, our ranking rather than the paper’s own marks.

Table1 (HC-PT)

ReNovo: Retrieval-Based De Novo Mass Spectrometry Peptide Sequencing, page 7: Empirical comparison of de novo peptide sequencing models. The best and the second best are highlighted with bold and underline, respectively.

ProteomeTools
HC-PT (NovoBench) 		Peptide precision Peptide AUC Amino acid precision Amino acid recall
DeepNovo 0.313 0.255 0.531 0.534
PointNovo 0.419 0.373 0.623 0.622
Casanovo 0.211 0.177 0.442 0.453
π-HelixNovo 0.356 0.318 0.588 0.582
AdaNovo 0.212 0.178 0.442 0.451
ReNovo 0.467 0.436 0.651 0.648

Table1 (Nine-species)

ReNovo: Retrieval-Based De Novo Mass Spectrometry Peptide Sequencing, page 7: Empirical comparison of de novo peptide sequencing models. The best and the second best are highlighted with bold and underline, respectively.

Nine-species benchmark Peptide precision Peptide AUC Amino acid precision Amino acid recall
DeepNovo 0.428 0.376 0.696 0.638
PointNovo 0.480 0.436 0.740 0.671
Casanovo 0.481 0.439 0.697 0.696
π-HelixNovo 0.517 0.453 0.765 0.758
AdaNovo 0.505 0.469 0.698 0.709
ReNovo 0.568 0.528 0.770 0.769

Table1 (Seven-species)

ReNovo: Retrieval-Based De Novo Mass Spectrometry Peptide Sequencing, page 7: Empirical comparison of de novo peptide sequencing models. The best and the second best are highlighted with bold and underline, respectively.

Seven-species benchmark Peptide precision Peptide AUC Amino acid precision Amino acid recall
DeepNovo 0.204 0.136 0.492 0.433
PointNovo 0.022 0.007 0.196 0.169
Casanovo 0.119 0.084 0.322 0.327
π-HelixNovo 0.234 0.173 0.481 0.472
AdaNovo 0.174 0.135 0.379 0.385
ReNovo 0.278 0.228 0.512 0.514

Paper describing it

Authors (9)

Shaorong Chen, Jun Xia, Jingbo Zhou, Lecheng Zhang, Zhangyang Gao, Bozhen Hu, Cheng Tan, Wenjie Du, Stan Z. Li

Seen in the charts

Back to the full map

Back to top