- Rating
- 1
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 1
Read review
Paper summary
This paper introduces Neopep, a diffusion-based model for predicting the structures of peptides containing non-canonical amino acids (ncAAs). The model follows the AlphaFold3/Boltz architecture and is first pretrained on PDB-derived protein fragments. It is subsequently fine-tuned using DRaFT-K to minimize energies predicted by the SO3LR machine-learned force field. A differentiable hydrogen-placement module enables energy gradients to propagate through the predicted heavy-atom coordinates. The method is evaluated on 34 non-canonical and 24 canonical peptides. On the non-canonical set, fine-tuning improves minimum Cα-RMSD from 2.271 Å to 1.565 Å and average Cα-RMSD from 3.236 Å to 2.546 Å compared with the pretrained model. Additional comparisons are provided against Boltz-2 and Protenix-v1.
Critical strengths
1. Relevant problem with a practical motivation.
Accurate structure prediction for peptides containing ncAAs is challenging because experimental structural data are limited. Using a machine-learned force field to provide additional supervision is a reasonable direction, and the differentiable hydrogen-placement implementation is a potentially useful engineering contribution.
2. Encouraging improvements over the pretrained model.
The reported reductions in both Cα-RMSD and heavy-atom RMSD are meaningful. The improvements are not restricted to one example, and the pretrained-versus-fine-tuned comparison provides evidence that energy-guided optimization can improve the model's predictions on the proposed benchmark.
Critical weaknesses
1. Questionable physical assumptions. The model minimizes isolated-peptide energy without accounting for solvent or receptor interactions, although some test structures are receptor-bound. It is unclear whether this objective reliably favors experimentally observed conformations.
2. Potential error in hydrogen placement. Equation (12) appears inconsistent with the stated methylene geometry and may produce incorrect hydrogen bond angles. Since hydrogen coordinates directly affect the force-field gradients, this raises concerns about the reliability of the training signal.
3. Limited methodological novelty and missing baselines. The method primarily combines existing Boltz/AF3 architectures, DRaFT-K, and a pretrained force field. Comparisons against direct energy minimization or inference-time energy guidance are missing, making it difficult to establish the benefit of the proposed fine-tuning strategy.
4. Insufficient experimental validation. The benchmark contains only 34 non-canonical peptides, with Protenix evaluated on just 29. The emphasis on best-of-25 RMSD, lack of statistical significance tests, and absence of evaluation on unseen ncAA types weaken the claims of accuracy and generalization.
Questions for authors
Q1 Can the authors clarify Equation (12) and confirm whether the implementation follows the stated formula? What are the distributions of hydrogen bond-length and bond-angle errors after protonation, particularly for ncAAs?
Q2 Since several test peptides are extracted from receptor-bound complexes, how do the authors justify optimizing isolated-peptide energy to recover their bound conformations? Can the results be separated into bound versus unbound and cyclic versus linear peptides?
Q3 How does Neopep compare with applying SO3LR-based energy minimization or inference-time guidance directly to the pretrained model, under comparable computational budgets?
Q4 Can the authors provide paired statistical comparisons on the common 29-peptide subset, results across independent training seeds, and evaluations on genuinely unseen ncAA types? Can they also report stereochemical validity and cyclic bond-closure accuracy?
15 comments
Response to Reviewer H5sz
We thank the reviewer for taking the time to read our manuscript and for the constructive feedback. Below, we respond to the reviewers first question (Part 2 of 2):
What are the distributions of hydrogen bond-length and bond-angle errors after protonation, particularly for ncAAs?
The SO3LR reward is evaluated on all-atom structures, so every prediction is protonated by the differentiable rule-based protonator of Section C.4 before its energy is computed. In the appendix section E.2 (Hydrogen Bond-Length and Bond-Angle Error of the Protonator), we quantify the geometric error of that protonation directly against the CCD, for every non-canonical residue type that occurs in the test set.
For each of the 95 non-canonical residue types present in the 34 non-canonical test peptides, we take the residue’s ideal CCD conformer, which carries CCD-assigned hydrogen positions, discard its hydrogens, and run the protonator on the remaining heavy atoms exactly as it is run during fine-tuning.
Each hydrogen placed by the protonator is then compared with the corresponding CCD hydrogen. Both hydrogen sets are built on identical heavy-atom coordinates, so any difference reflects the protonator’s placement rules alone and not the structure predictor. We compare (i) the X–H bond length to the parent heavy atom X and (ii) the H–X–Y bond angle for every heavy neighbour Y of X. Leaving atoms (OXT, HXT, and the second amine hydrogen of a free N-terminus) are not placed by the protonator and are excluded, as our current protonator protonates residues as if they are within the peptide chain. Figure 9 in appendix section E.2 of the updated manuscript shows the distribution of angle errors. 98.2% of angles are within 5◦. The bond-length error is identically zero. The protonator takes every X–H distance from the CCD and determines only the direction of the bond, so this comparison is satisfied by construction.
Response to Reviewer H5sz
We thank the reviewer for taking the time to read our manuscript and for the constructive feedback. Below, we respond to the reviewers second question:
Since several test peptides are extracted from receptor-bound complexes, how do the authors justify optimizing isolated-peptide energy to recover their bound conformations?
We agree with the reviewer that solvent and receptor interactions (bound vs. unbound states) are important things our model should take into account. We acknowledge that simply training on isolated peptide energies might not be able to model bound/unbound states, and do not claim that it does so. What we do hope, is that the model has learned a rough prior on what structures of peptides in solution, or bound/unbound conformations look like during phase-1 training on the PDB, and is able to refine this prior with the additional energy training (and not stray away too much from it, but just enough so that the predicted structures with ncAAs are plausible). Of course, this is only testable once we curate a more comprehensive benchmark with the limited data that we have. We would also like to note that one could, in principle, replace the phase-1 prior with a more SOTA structure predictor like Protenix or AF3.
Can the results be separated into bound versus unbound and cyclic versus linear peptides?
In appendix section E.3 (Results Split by Binding State and Cyclisation) of the updated manuscript, we split the main-text results for the ncAA peptides (from Section 4.4, tables 1 and 2) along both axes. We also provide statistical tests for this in appendix section F.2 (tables 16 and 17). Cyclisation is taken from the inference input (17 cyclic, 17 linear); binding state from the deposited entry, where 28 of the 34 peptides are resolved bound to a receptor and 6 are unbound. We share the tables below:
Table 6. CA-RMSD (Å) on the non-canonical test set, split by cyclic versus linear peptides. Mean ± std across peptides. Bold indicates the best value in each column. Protenix does not support 5 of the 34 peptides and is evaluated on fewer peptides in each group ( given in the row).
| Cyclic () | Linear () | |||
|---|---|---|---|---|
| Model | Min CA-RMSD | Avg CA-RMSD | Min CA-RMSD | Avg CA-RMSD |
| Boltz-2 | 4.677 ± 1.680 | 8.302 ± 3.818 | 4.219 ± 1.520 | 9.793 ± 6.865 |
| Protenix-v1 † | 1.964 ± 1.299 | 2.529 ± 1.375 | 2.573 ± 1.316 | 3.183 ± 1.474 |
| Neopep Pretrained | 1.889 ± 0.503 | 2.747 ± 0.478 | 2.653 ± 0.938 | 3.725 ± 1.075 |
| + SO3LR relaxation | 1.900 ± 0.515 | 2.770 ± 0.492 | 2.687 ± 0.950 | 3.757 ± 1.092 |
| Neopep Finetuned | 1.228 ± 0.746 | 1.942 ± 0.757 | 1.901 ± 1.046 | 3.150 ± 1.195 |
† Evaluated on cyclic and linear peptides.
Table 7. CA-RMSD (Å) on the non-canonical test set, split by bound versus unbound peptides. Mean ± std across peptides. Bold indicates the best value in each column. Protenix does not support 5 of the 34 peptides and is evaluated on fewer peptides in each group ( given in the row).
| Bound () | Unbound () | |||
|---|---|---|---|---|
| Model | Min CA-RMSD | Avg CA-RMSD | Min CA-RMSD | Avg CA-RMSD |
| Boltz-2 | 4.366 ± 1.495 | 9.513 ± 5.897 | 4.831 ± 2.122 | 6.877 ± 2.570 |
| Protenix-v1 † | 2.261 ± 1.301 | 2.892 ± 1.386 | 2.248 ± 1.522 | 2.665 ± 1.750 |
| Neopep Pretrained | 2.094 ± 0.715 | 2.990 ± 0.644 | 3.099 ± 0.929 | 4.384 ± 1.377 |
| + SO3LR relaxation | 2.112 ± 0.724 | 3.014 ± 0.660 | 3.140 ± 0.956 | 4.428 ± 1.385 |
| Neopep Finetuned | 1.319 ± 0.806 | 2.248 ± 0.934 | 2.711 ± 0.793 | 3.934 ± 1.170 |
† Evaluated on bound and unbound peptides.
Table 8. Minimum heavy-atom RMSD (FA-RMSD, Å) on the non-canonical test set, split by cyclic versus linear peptides. Mean ± std across peptides. Bold indicates the best value in each column.
| Model | Cyclic () | Linear () |
|---|---|---|
| Boltz-2 | 5.971 ± 1.543 | 5.666 ± 1.398 |
| Protenix-v1 † | 3.412 ± 1.420 | 3.725 ± 1.722 |
| Neopep Pretrained | 3.434 ± 0.666 | 4.035 ± 0.835 |
| + SO3LR relaxation | 3.485 ± 0.677 | 4.094 ± 0.852 |
| Neopep Finetuned | 2.918 ± 0.725 | 3.470 ± 1.072 |
† Evaluated on cyclic and linear peptides.
Table 9. Minimum heavy-atom RMSD (FA-RMSD, Å) on the non-canonical test set, split by bound versus unbound peptides. Mean ± std across peptides. Bold indicates the best value in each column.
| Model | Bound () | Unbound () |
|---|---|---|
| Boltz-2 | 5.855 ± 1.399 | 5.648 ± 1.847 |
| Protenix-v1 † | 3.633 ± 1.455 | 3.293 ± 2.018 |
| Neopep Pretrained | 3.583 ± 0.739 | 4.441 ± 0.767 |
| + SO3LR relaxation | 3.636 ± 0.747 | 4.505 ± 0.812 |
| Neopep Finetuned | 2.974 ± 0.845 | 4.219 ± 0.702 |
† Evaluated on bound and unbound peptides.
Response to Reviewer H5sz
We thank the reviewer for taking the time to read our manuscript and for the constructive feedback. Below, we respond to the reviewers first question, and address the related weaknesses (Part 1 of 2):
We thank the reviewer for catching this error in the manuscript. The previous form of Eq. 12,
h1,2=C+d(sinαu±cosαv),
did not match the implementation. Because u points toward the two heavy-atom substituents, the positive u coefficient placed both hydrogens on the wrong side of the carbon. With α defined as the half-opening angle, the sine and cosine terms were also swapped, which does not give tetrahedral angles. We have corrected Eq. 12 in the paper to
h1,2=C+d(−cosαu±sinαv),
where α is still the half-opening angle derived from the ideal H–C–H angle. We confirm that the implementation in the code is correct (no changes needed), and only correct the formula in the manuscript. This updated equation places the geminal hydrogens opposite the substituents, symmetric about the −u axis, and recovers tetrahedral geometry.