PhysNovo

algorithm · Diffusion

PhysNovo: algorithm · Diffusion. Discrete-diffusion de novo peptide sequencer that folds in physical mass-constraint terms at inference time, so generated sequences respect the observed precursor mass…

Discrete-diffusion de novo peptide sequencer that folds in physical mass-constraint terms at inference time, so generated sequences respect the observed precursor mass rather than relying purely on the learned amino-acid prior.

Kind algorithm
Deep learning yes
Family Diffusion

Code

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

Checkpoints

Version Trained on Host Licence Size Checked
nine-species — Zenodo archival CC-BY-4.0 1.7 GB live 2026-10-02

Reported comparisons (9)

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)

Discrete Diffusion with Physical Mass Constraints for De Novo Peptide Sequencing, page 7: Comparison with state-of-the-art methods on Nine-species, Seven-species, and HC-PT datasets in amino acid-level and peptidelevel performance. The best results are marked in bold, and the second best are underlined.

ProteomeTools
HC-PT (NovoBench) 		Amino acid precision Amino acid recall Peptide precision Peptide AUC
DeepNovo · retrained 0.531 0.534 0.313 0.255
PointNovo · retrained 0.623 0.622 0.419 0.373
InstaNovo · retrained 0.289 0.285 0.057 0.034
Casanovo · retrained 0.442 0.453 0.211 0.177
AdaNovo · retrained 0.442 0.451 0.212 0.178
π-HelixNovo · retrained 0.588 0.582 0.356 0.318
LIPNovo · retrained 0.637 0.643 0.458 0.427
ReNovo 0.651 0.648 0.467 0.436
PhysNovo 0.649 0.652 0.473 0.444

Table1 (Nine-species)

Discrete Diffusion with Physical Mass Constraints for De Novo Peptide Sequencing, page 7: Comparison with state-of-the-art methods on Nine-species, Seven-species, and HC-PT datasets in amino acid-level and peptidelevel performance. The best results are marked in bold, and the second best are underlined.

Nine-species benchmark
revised (balanced) 		Amino acid precision Amino acid recall Peptide precision Peptide AUC
PEAKS 0.748 0.428
DeepNovo · retrained 0.696 0.638 0.428 0.376
PointNovo · retrained 0.740 0.671 0.480 0.436
InstaNovo · retrained 0.420 0.395 0.164 0.123
Casanovo · retrained 0.697 0.696 0.481 0.439
AdaNovo · retrained 0.698 0.709 0.505 0.469
π-HelixNovo · retrained 0.765 0.758 0.517 0.453
LIPNovo · retrained 0.797 0.797 0.582 0.547
π-PrimeNovo 0.790
ReNovo 0.770 0.769 0.568 0.528
PhysNovo 0.815 0.814 0.588 0.553

Table1 (Seven-species)

Discrete Diffusion with Physical Mass Constraints for De Novo Peptide Sequencing, page 7: Comparison with state-of-the-art methods on Nine-species, Seven-species, and HC-PT datasets in amino acid-level and peptidelevel performance. The best results are marked in bold, and the second best are underlined.

Seven-species benchmark Amino acid precision Amino acid recall Peptide precision Peptide AUC
DeepNovo · retrained 0.492 0.433 0.204 0.136
PointNovo · retrained 0.196 0.169 0.022 0.007
InstaNovo · retrained 0.192 0.176 0.031 0.009
Casanovo · retrained 0.322 0.327 0.119 0.084
AdaNovo · retrained 0.379 0.385 0.174 0.135
π-HelixNovo · retrained 0.481 0.472 0.234 0.173
LIPNovo · retrained 0.557 0.560 0.327 0.281
ReNovo 0.512 0.514 0.278 0.228
PhysNovo 0.568 0.569 0.346 0.290

Table2 (HC-PT)

Discrete Diffusion with Physical Mass Constraints for De Novo Peptide Sequencing, page 7: Comparison with state-of-the-art methods on Nine-species, Seven-species, and HC-PT datasets in PTM-level performance.

ProteomeTools
HC-PT (NovoBench) 		Ptm precision Ptm recall
DeepNovo · retrained 0.626 0.615
PointNovo · retrained 0.676 0.740
InstaNovo · retrained 0.350 0.261
Casanovo · retrained 0.501 0.460
AdaNovo · retrained 0.552 0.482
π-HelixNovo · retrained 0.568 0.667
LIPNovo · retrained 0.732 0.745
PhysNovo 0.763 0.770

Table2 (Nine-species)

Discrete Diffusion with Physical Mass Constraints for De Novo Peptide Sequencing, page 7: Comparison with state-of-the-art methods on Nine-species, Seven-species, and HC-PT datasets in PTM-level performance.

Nine-species benchmark
revised (balanced) 		Ptm precision Ptm recall
DeepNovo · retrained 0.576 0.529
PointNovo · retrained 0.629 0.546
InstaNovo · retrained 0.443 0.294
Casanovo · retrained 0.706 0.566
AdaNovo · retrained 0.652 0.570
π-HelixNovo · retrained 0.680 0.598
LIPNovo · retrained 0.765 0.656
PhysNovo 0.793 0.686

Table2 (Seven-species)

Discrete Diffusion with Physical Mass Constraints for De Novo Peptide Sequencing, page 7: Comparison with state-of-the-art methods on Nine-species, Seven-species, and HC-PT datasets in PTM-level performance.

Seven-species benchmark Ptm precision Ptm recall
DeepNovo · retrained 0.391 0.373
PointNovo · retrained 0.117 0.094
InstaNovo · retrained 0.126 0.115
Casanovo · retrained 0.360 0.251
AdaNovo · retrained 0.448 0.321
π-HelixNovo · retrained 0.473 0.366
LIPNovo · retrained 0.604 0.498
PhysNovo 0.654 0.549

Table3

Discrete Diffusion with Physical Mass Constraints for De Novo Peptide Sequencing, page 8: Leave-one-out cross-validation performance on the Ninespecies dataset compared against the state-of-the-art Method.

Nine-species benchmark Amino acid precision
Bacillus subtilis Candidatus Thiodiazotropha endoloripes Apis mellifera Homo sapiens Methanosarcina mazei Mus musculus Vigna mungo Solanum lycopersicum Mean
LIPNovo · retrained 0.806 0.805 0.807 0.805 0.807 0.808 0.794 0.800 0.804
PhysNovo 0.822 0.819 0.825 0.811 0.825 0.827 0.813 0.815 0.820
Nine-species benchmark Amino acid recall
Bacillus subtilis Candidatus Thiodiazotropha endoloripes Apis mellifera Homo sapiens Methanosarcina mazei Mus musculus Vigna mungo Solanum lycopersicum Mean
LIPNovo · retrained 0.807 0.805 0.806 0.805 0.807 0.807 0.796 0.798 0.804
PhysNovo 0.822 0.820 0.825 0.810 0.826 0.827 0.815 0.815 0.820
Nine-species benchmark Peptide precision
Bacillus subtilis Candidatus Thiodiazotropha endoloripes Apis mellifera Homo sapiens Methanosarcina mazei Mus musculus Vigna mungo Solanum lycopersicum Mean
LIPNovo · retrained 0.607 0.591 0.606 0.596 0.596 0.607 0.577 0.577 0.595
PhysNovo 0.614 0.598 0.610 0.600 0.603 0.611 0.585 0.583 0.601
Nine-species benchmark Peptide AUC
Bacillus subtilis Candidatus Thiodiazotropha endoloripes Apis mellifera Homo sapiens Methanosarcina mazei Mus musculus Vigna mungo Solanum lycopersicum Mean
LIPNovo · retrained 0.581 0.563 0.577 0.567 0.565 0.579 0.545 0.544 0.565
PhysNovo 0.589 0.571 0.584 0.575 0.568 0.592 0.549 0.550 0.572
Nine-species benchmark PTM precision
Bacillus subtilis Candidatus Thiodiazotropha endoloripes Apis mellifera Homo sapiens Methanosarcina mazei Mus musculus Vigna mungo Solanum lycopersicum Mean
LIPNovo · retrained 0.855 0.764 0.769 0.772 0.812 0.803 0.764 0.777 0.790
PhysNovo 0.878 0.794 0.800 0.797 0.839 0.828 0.793 0.799 0.816
Nine-species benchmark PTM recall
Bacillus subtilis Candidatus Thiodiazotropha endoloripes Apis mellifera Homo sapiens Methanosarcina mazei Mus musculus Vigna mungo Solanum lycopersicum Mean
LIPNovo · retrained 0.739 0.647 0.675 0.672 0.630 0.667 0.634 0.627 0.661
PhysNovo 0.765 0.685 0.699 0.701 0.664 0.694 0.669 0.658 0.692

Table4

Discrete Diffusion with Physical Mass Constraints for De Novo Peptide Sequencing, page 8: Comparison of parameter efficiency and task performance.

not stated; page mentions Nine-species benchmark, ProteomeTools, Seven-species benchmark Amino acid precision Amino acid recall Peptide precision Peptide AUC
Casanovo · retrained 0.741 0.740 0.529 0.493
LIPNovo · retrained 0.797 0.797 0.582 0.547
PhysNovo 0.815 0.814 0.588 0.553

Table5

Discrete Diffusion with Physical Mass Constraints for De Novo Peptide Sequencing, page 8: Comparison of inference speed and accuracy. PhysNovo enables a flexible speed–accuracy trade-off by adjusting the number of denoising steps (T).

not stated; page mentions Nine-species benchmark, ProteomeTools, Seven-species benchmark Amino acid precision
Casanovo AR · retrained 0.697
π-PrimeNovo NAR 0.790
PhysNovo T =100 0.815
PhysNovo T =50 0.801

Paper describing it

Authors (2)

Zeyu An, Wanyu Lin

Seen in the charts

Back to the full map

Back to top