- Rating
- 3(+1)
- Confidence
- 1
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
This work focuses on target-conditioned cyclic peptide generation and proposes a geometry-aware partially latent flow matching framework (LaCPlow). Specifically, the method explicitly models the rigid frames of amino acid residues, including their spatial positions and rotational orientations, as geometric variables, while employing a variational autoencoder (VAE) to encode amino acid identities and residue-local atomic coordinates into continuous latent variables. Building on this representation, the method constructs a geometrically equivariant vector field that jointly models residue rotations, translations, and latent variables, enabling the joint generation of amino acid sequences and all-atom structures conditioned on a target protein through flow matching. Furthermore, the work introduces a geometry-aligned attention network to capture spatial interactions both within the cyclic peptide and between the peptide and its target protein. It additionally incorporates cyclization-specific supervision and ring-closure geometric constraints to improve the cyclization success rate and stereochemical plausibility of the generated cyclic peptides.
Critical strengths
-
The proposed modeling paradigm demonstrates a certain degree of novelty and practical effectiveness compared to prior work. Specifically, the method explicitly models the flow of residue translations and rotations while encoding residue identities and local atomic structures into latent variables, enabling their joint generation.
-
The experimental evaluation assesses the quality of generated structures before energy minimization or other relaxation procedures. This allows for a more precise assessment of the model’s intrinsic generative capabilities and the additional contributions of post-processing.
-
The algorithmic design and experimental setup effectively distinguish between the geometric generation capabilities of the base model and the specialized generation capabilities tailored to specific chemical constraints.
-
The ablation studies provide strong empirical evidence for the effectiveness of several key design choices. Under the same $(R,x,z) $ representation, the proposed geometric network outperforms the PairBiased Transformer. Furthermore, incorporating cyclization information through latent-variable-based modeling achieves a higher ring-closure success rate than treating cyclization information as an additional explicit flow state.
Critical weaknesses
-
The methodological novelty of LaCPlow is relatively incremental. Its main contribution lies in the targeted integration of explicit residue rigid frames, partially latent flow matching, and a representation-aligned geometric network, rather than the introduction of a fundamentally new generative modeling paradigm.
-
The independent contribution of explicitly modeling residue rotations R has not been rigorously validated. A controlled comparison between and under identical training data, model capacity, and training configurations is needed to isolate the benefits of introducing explicit rotational variables.
-
The contributions of individual components within the proposed geometric network have not been sufficiently investigated. Although Table 4 demonstrates that the complete geometric network outperforms the PairBiased Transformer, it does not adequately examine the individual contributions of its key architectural components.
-
The necessity and effectiveness of independently sampled time variables remain insufficiently validated. The proposed joint flow matching framework employs two independently sampled time variables for geometry and latent representations. However, the experiments do not directly compare shared time scheduling with independent time scheduling . Consequently, the current results do not establish whether independent time scheduling offers advantages over shared scheduling, nor do they clarify its specific contributions to generation quality, training stability, or the coupling between geometric and latent representations.
Questions for authors
-
Sufficiency of existing methods. Can existing protein co-design models achieve performance comparable to LaCPlow after fine-tuning on cyclic peptide data? If so, what is the necessity and additional value of introducing the proposed architecture?
-
Necessity of joint atomic geometry modeling. Why is it necessary to jointly generate residue-local atomic geometry? What are the specific advantages of this approach over a two-stage pipeline that first generates the backbone and then performs all-atom reconstruction and side-chain completion?
Post-Rebuttal Updates: The rebuttal addresses most of my concerns and provides sufficiently interesting and convincing findings to justify raising my rating to 3. However, I am not an expert in this specific area, and I encourage the AC to take my limited expertise into account.
4 comments
[W2&W3] The independent contribution of representation and network components
Assessing the contribution of explicit residue orientations is important. Table 4 compares non-equivariant and equivariant architectures, two widely used approaches to protein generation. We thank the reviewer for pointing out that this broad comparison makes individual architectural contributions difficult to isolate. In LaCPlow, however, provides the coordinate frames used for geometric interactions and local reconstruction, rather than simply an additional input. Relative positions, relative rotations, and atom reconstruction depend on these frames. Removing therefore requires either estimating frames separately or replacing these operations with frame-independent alternatives. Our control uses the latter approach. A simple on/off comparison that leaves every other operation unchanged is consequently not well-defined.
| Chirality | Rama allowed | Rama favored | dG | energy | ||||
|---|---|---|---|---|---|---|---|---|
| A | 57.0 | 61.1 | 44.5 | -17.4 | 88.5 | |||
| B | w/ equation (14) | 15.9 | 84.8 | 100 | 87.9 | |||
| C | w/ equation (8) | 17.7 | 90.0 | 100 | 89.4 | 75.2 | ||
| D (=LaCPlow) | w/ IPA | 25.8 | 95.5 | 100 | 95.3 | 83.5 | -22 | 97.2 |
Construction of control A.
Control A uses the generative state (x,z). Its peptide–peptide geometric features are reduced as follows: .
Observed target frames remain available. PP and PT therefore use distance features only, TP retains directional features expressed in the target frame, and TT remains unchanged.
For peptide to target atom conditioning, local directional vectors are likewise replaced with distances: .
The network uses a PairBiased Transformer, which does not require explicit peptide frames. The translational readout and atomic decoder construct vectors as weighted sums of relative position vectors, using invariant scalar coefficients. This preserves SE(3)-equivariance without peptide frames.
In B, C, and D, the components of the network were evaluated.
[W4] comparison between shared training time and independent training time
We additionally trained a shared training time variant by sampling a single time and setting for each training example.
| model | chirality | Rama allowed | Rama Favored | ||
|---|---|---|---|---|---|
| LaCPlow | 29.20 | 97.00 | 100 | 95.65 | 84.14 |
| shared training time | 100 |
Both models were evaluated using LaCPlow’s default sampling schedule at inference (Appendix A.4), following the evaluation protocol of Table 8, with 100 samples for each of 128 CPCore validation pockets.
[Q2] Advantages of joint modeling over a two-stage pipeline
In a conventional two-stage pipeline, the backbone is generated first and held fixed during side-chain packing. This constrains subsequent side-chain placement and can limit the ability to satisfy closure geometry, leaving greater corrections to post refinement. For example, MuCO follows this two-stage pipeline, whereas LaCPlow jointly generates backbone and side-chain information. Table 3 shows that MuCO requires larger adjustments especially in closure distance to achieve the required cyclization geometry.
The table below directly compares LaCPlow and MuCO in Table 3.
| model | BB | SC | BB bond | SC bond | BB tor | SC tor | ||
|---|---|---|---|---|---|---|---|---|
| LaCPlow-Base | 2.15 | 2.57 | 5 | 6.7 | 0.87 | |||
| LaCPlow-Cyc | 37 | 46.7 | 0.26 | |||||
| MuCO | 1.26 | 1.53 | 12.1 | 31.9 | 45.4 | 57.3 | 3.7 | 1.29 |
The table below compares overall structural quality.
| model | chirality | Rama allowed | Rama Favored | ||
|---|---|---|---|---|---|
| LaCPlow-Base | 95.5 | 100 | |||
| LaCPlow-Cyc | 61 | 100 | 94.5 | ||
| MuCO | 2.8 | 78.7 | 96.2 | 89.4 |
Thanks for the Rebuttal
Thank you to the authors for the detailed rebuttal and additional experiments.
I find the consolidated evaluation for Q1 particularly interesting and convincing. Although the fine-tuned Proteína-Complexa produces more candidates passing the strict joint filtering criteria, LaCPlow-Cyc achieves broader target coverage, less concentration of valid candidates, and greater structural diversity across targets. These results strengthen the practical value of the proposed architecture.
I am therefore willing to raise my rating from 2 to 3.
My remaining concern is whether the Proteína-Complexa baseline has been sufficiently fine-tuned. Could full-parameter supervised fine-tuning, rather than LoRA, yield better results? Were alternative fine-tuning strategies explored?
I will maintain my original confidence score, as cyclic peptide generation is not my primary research area, and I encourage the Area Chair to take this into account.
Dear Reviewer HQq7,
We sincerely thank you for raising your rating, and for the follow-up question on full-parameter fine-tuning.
Following Proteina-Complexa’s original training setup, we kept the released autoencoder frozen and fine-tuned only the flow model in both variants.
We additionally applied full-parameter fine-tuning on the same CPCore training split, and evaluated the epoch-2 checkpoint, selected by validation loss, using the protocols in our Consolidated Evaluation. We report only the additional rows below to avoid repeating the full comparison tables.
| Model | number of attempts | Generation success | F1 | F2 | F3 | F4 | F5 | F6 | F7 | F8 | F9 | R1 | R2 | R3 | R4 | R5 | R6 |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Proteina-Complexa (full-param tuning) | 8400 | 8400 | 1905 | 1873 | 807 | 156 | 109 | 108 | 108 | 108 | 105 | 39 | 1.250 | 32.4 | 51.4 | 1.308 | 0.607 |
LaCPlow-Cyc achieves broader target coverage and a higher mean number of distinct passing structural clusters.
| Model | generated samples/target | samples retained after filtering/target | structural diversity (clusters/target) | sequence diversity (clusters/target) |
|---|---|---|---|---|
| Proteina-Complexa (full-param tuning) | 9 | 2.03 | 1.11 | 1.46 |
LaCPlow-Cyc produces more distinct structural and sequence clusters under the matched sampling-time budget, supporting its practical advantage.
Once again, we sincerely thank you for your time and for raising your rating, and we hope these additional results fully address your remaining concern. Thank you very much!
Dear reviewer HQq7, we sincerely thank you for the constructive feedback.
[W1] The novelty of LaCPlow is incremental
The central scientific novelty of this work is to question whether existing peptide or protein generation architectures provide a sufficient foundation for cyclic peptide modeling, even when augmented with cyclization-specific components. LaCPlow-Base already achieves better cyclic peptide generation than models incorporating such components. This finding shows why the underlying generative architecture deserves attention alongside the mechanisms added to enforce cyclization.
Accurate cyclic peptide modeling requires an appropriate representation of residue orientations and a geometric network that can use this information effectively. Fully explicit approaches represent orientations directly, but can still struggle when orientation, conformation, and sequence are tightly coupled. Fully latent and other partially latent approaches handle residue orientations indirectly. LaCPlow explicitly transports residue frames, represents sequence and intra-residue geometry in latent variables, and uses a geometric network aligned with this representation. Its performance challenges the assumption that a linear-peptide generator can serve as a sufficient foundation, leaving additional cyclization-specific mechanisms to account for cyclic peptide geometry.
We also examine how post-generation refinement can blur the distinction between a generator’s intrinsic geometric quality and the corrections made by an energy minimizer. Evaluating structures before refinement allows us to assess what the generator itself has learned. This distinction also matters for optimization. Existing approaches, including APCyc, GeoCycler, and CP-Composer, pursue cyclic peptide optimization using underlying generative architectures whose ability to represent cyclic peptides remains limited. LaCPlow offers an alternative foundation for these workflows by combining an architecture designed to capture cyclic peptide geometry with a latent-space optimization interface. The contribution is therefore broader than an additional optimization strategy. It provides a generative substrate on which future cyclic peptide generation and optimization methods can be built, and shows why the representation and processing of cyclic peptide geometry are themselves important architectural choices.
[Q1] Comparison with an existing protein co-design model fine-tuned on cyclic peptide data
In the paper, we compared against protein and peptide co-design models retrained on cyclic peptide data. We additionally fine-tuned the official pretrained Proteina-Complexa model on cyclic peptide data using LoRA with the authors' official fine-tuning code. We evaluated the epoch-2 checkpoint, selected by validation loss.
The same Proteina-Complexa architecture trained from scratch on cyclic peptide data achieves better closure geometry. These results suggest that strong performance on properties shared with proteins does not necessarily transfer to cyclic peptide specific geometry.