- Rating
- 2
- Confidence
- 4
- Informativeness
- 2
- Presentation
- 3(+1)
- Soundness
- 2
Read review
Paper summary
The paper proposes a lightweight and cheap generative framework for designing AMPs with multiple desired properties. The paper is well written overall, provides many experiments, and presents some strong results. However, several things need to be addressed. The novelty lies in the addition of the router, which is a small MLP that provides which category of past experience to retrieve and how many records to retrieve from it. The strong results can not be fully supported because several baselines, ablation studies, and justifications are missing.
Critical strengths
- The method is cheap since the generator is frozen. They train only one small MLP.
- Performance is shown for many pathogens across several property subsets.
- The cross-pathogen transfer experiment is very interesting and should be highlighted more in the paper.
Critical weaknesses
-
The only extra component compared to the SOTA is the router, and its type head seems to favor potency failure in many states, as given in the appendix. I believe the authors should explore whether a simple rule that always retrieves potency failure experience could give the same result.
-
The paper claims that the structured experience is what gives the improvement. However, in the ablation they provide comparisons only between full memory and no memory at all. This removes the whole history, not only the structure. I would suggest that the authors give the model the previous sequences and their scores as plain text, without the six fields, without the rationale and without the router. Without this, the results can also be explained by the LLM simply seeing what was already tried.
-
The authors should include in the baselines (i) a protein language model with rejection sampling under the same predictors and budget, and (ii) the same model fine-tuned on AMPs.
-
The thresholds are fixed and they also seem quite low, given that the score is in [0,1]. A sensitivity analysis is needed.
-
All the properties are scored from external predictors and the system keeps editing the sequence until the predictors are satisfied. So the whole method is optimized against them. These predictors also have their own error, and since PepMind makes repeated targeted edits against their scores, part of the improvement may come from exploiting their errors rather than from better peptides. The LLM evaluation does not add much either because the evaluators are asked to look at the features that were deliberately engineered, which is probably why the scores are high.
-
It would also help to compare the generated peptides against a set of known AMPs from DBAASP, on pLDDT, length, net charge, hydrophobicity and amino acid composition, with a statistical test on the distributions.
-
Finally, I would suggest providing an analysis of novelty and diversity to known AMPs and sequence similarity within the generated data. Without those, it is not clear whether the method produces novel peptides or rewrites known ones, and whether the 300 candidates per task are diverse or variations of a few templates. Diversity is mentioned, but it is not discussed how it is computed.
Questions for authors
-
What is the overlap in the training data between the predictors used during the optimization and the ones used for the external validation of the same property?
-
How often is each memory category selected across all decision points?
8 comments
W5, Q1, W6
W5 (a): Whether repeated optimization exploits predictor errors rather than improves peptide quality.
Response: As described in the manuscript, we used an additional external predictor for each property to provide secondary validation. We analyzed correlations between predictors of the same property and quantified overlap between their training datasets.
As shown in Table R5, agreement between optimization and external predictors is limited, with Spearman correlations ranging from 0.0792 to 0.1656. Despite this limited agreement, PepMind-generated sequences consistently achieve the best performance under the external predictors. This consistency supports the robustness of PepMind’s improvements across scoring models and provides evidence against the gains arising solely from exploiting errors specific to the optimization predictors.
| Predictor pair | Spearman ρ | Pearson r |
|---|---|---|
| amPEPpy / AMP-CLIP | NA | NA |
| APEX / AMP-READ | 0.0792 | 0.1405 |
| HemoPI2 / ConsAMPHemo | 0.1052 | 0.0856 |
| ToxinPred3 / ToxTeller LR | 0.1656 | 0.1278 |
Table R5. Correlations between predictors evaluating the same peptide property.
W5 (b): Whether the LLM evaluation provides independent validation.
Response: We redesigned the prompt. It removes explicit feature-based guidance that could favor PepMind’s designs.
As shown in Table R6, under the revised prompt, PepMind receives the highest mean scores from GLM-5.2 Kimi-K2.6 and GPT-5.6-Luna, while AMP-Designer leads under Qwen3.5-Plus. These results show that PepMind remains competitive. We therefore use LLM scores alongside external predictor analyses as supplementary checks to reduce reliance on the optimization predictors and mitigate the risk of exploiting their scoring biases.
Prompt:
{
Please rate this antimicrobial peptides sequence on a scale from 0 to 10.
Sequence: {sequence}
Return only a single number.
}
| Methods | GLM-5.2 | Kimi-K2.6 | Qwen3.5-Plus | GPT-5.6-Luna |
|---|---|---|---|---|
| PepMind | 7.7516 | 6.5219 | 8.0528 | 8.4884 |
| AMP-Designer | 7.7275 | 6.4980 | 8.2657 | 8.2580 |
| BroadAMP-GPT | 7.2456 | 6.1659 | 7.9468 | 8.4783 |
| PepGAN | 7.4722 | 6.4176 | 7.9358 | 8.4210 |
| diff-AMP | 6.8625 | 6.1567 | 7.6281 | 6.7104 |
Table R6. Mean LLM evaluation scores under the revised prompt without explicit feature criteria.
Q1: The extent of training-data overlap between optimization and external-validation predictors for the same property.
Response: The overlap in the training data between the predictors:
| Predictor pair (A / B) | Sequences in A | Sequences in B | Shared | Shared / A | Shared / B |
|---|---|---|---|---|---|
| amPEPpy / AMP-CLIP | 6,335 | 45,731 | 2,910 | 45.94% | 6.36% |
| APEX / AMP-READ | Unavailable | 7,434 | NA | NA | NA |
| HemoPI2 / ConsAMPHemo | 1,540 | 1,786 | 143 | 9.29% | 8.01% |
| ToxinPred3 / ToxTeller LR | 8,828 | 4,129 | 1,786 | 20.23% | 43.26% |
Table R7. Overlap in the training data between the predictors.
As shown in Table R7, most sequences in each available dataset are not shared with its paired predictor. Overlap is relatively low for HemoPI2/ConsAMPHemo (9.29%/8.01%) and asymmetric for amPEPpy/AMP-CLIP (45.94%/6.36%) and ToxinPred3/ToxTeller LR (20.23%/43.26%). These results show substantial distinct sequence coverage, although the datasets are not fully independent.
W6: Do generated peptides differ significantly from DBAASP AMPs in structural and physicochemical properties?
Response: As shown in Table R8, PepMind candidates share the short, positively charged, and hydrophobic character of the 2,859 curated DBAASP reference peptides, supporting their physicochemical plausibility. PepMind favors somewhat shorter, more positively charged, and more hydrophobic sequences, with higher mean predicted structural confidence (pLDDT: 83.17 versus 78.34). Figure 15 in Appendix S further presents the property distributions and amino acid composition.
| Property | PepMind mean | DBAASP mean |
|---|---|---|
| Length (residues) | 15.56 | 18.27 |
| Net charge (pH 7.4) | 6.12 | 4.14 |
| Hydrophobic residue fraction | 0.5125 | 0.4463 |
| pLDDT | 83.17 | 78.34 |
Table R8. Peptides generated by Pepmind compared to peptides from dbaasp.
We obtained 2,859 unique DBAASP reference sequences by screening 4,923 initially selected records for monomeric peptides of 8–35 standard amino acids, with no recorded terminal modifications or crosslinks, at least one MIC measurement against a species in our seven-species panel, and a publication reference.
W7, Q2
W7: How are novelty and diversity quantified, and do the 300 candidates per task extend beyond a few sequence templates?
Response: Table R9 shows substantial within-task sequence variation: candidates are 100% unique, with a mean pairwise distance of 0.4169 and 4.31 sequence families per task. Global uniqueness is 80.36%. These results support sequence diversity while revealing family-level clustering. Detailed analyses have been added to Appendix R, Table 15, and Figure 27.
| Novelty/diversity measure | PepMind |
|---|---|
| Exact matches to DBAASP | 0.00% |
| Mean nearest-DBAASP sequence similarity | 0.5377 |
| Sequences with nearest-DBAASP similarity <0.8 | 99.95% |
| Within-task unique sequences | 100.00% |
| Mean within-task pairwise sequence distance | 0.4169 |
| Mean sequence families per task (similarity ≥0.8) | 4.31 |
| Global unique-sequence fraction | 80.36% |
Table R9. Novelty relative to DBAASP and sequence diversity of PepMind-generated peptides.
Q2: How often is each memory category selected across all decision points?
Response: PepMind draws on complementary failure experiences to guide refinement across antimicrobial activity, potency, and safety:
| Experience category | Calls receiving this category |
|---|---|
| Activity-failure experience | 16.41% |
| Hemolysis-failure experience | 36.69% |
| Toxicity-failure experience | 63.32% |
| Potency-failure experience | 55.28% |
Table R10. Failure-experience retrieval frequencies across conditional-retrieval decisions.
As shown in Table R10, Potency-related guidance appears in 55.28% of calls, while toxicity and hemolysis evidence appears in 63.32% and 36.69%. This demonstrates PepMind’s ability to bring both efficacy-related and safety-related experience into refinement decisions, providing evidence for anticipating trade-offs when improving a peptide.
We thank the reviewer for suggesting these meaningful experiments. The additional analyses strengthen our assessment of PepMind’s robustness, novelty, and diversity. We will incorporate these experiments and findings into the revised main text.
W1, W2, W3, W4
We appreciate your constructive feedback. We will incorporate the additional discussion and results into the revised manuscript.
W1&W2: Whether the router outperforms a simple rule that always retrieves potency-failure experience. Whether the improvement comes from structured experience rather than access to history, requiring a plain-text baseline with previous sequences and scores but no six-field structure, rationale, or router.
Response: We compared PepMind with two alternatives: unstructured, text-only experience and fixed retrieval of potency-failure experience (Table R1). PepMind achieves higher HV in all seven species against both alternatives, supporting the benefits of structured experience representation and adaptive category selection for multi-objective design. Fixed potency-failure retrieval also produces higher predicted hemolysis and toxicity than PepMind, indicating that potency-focused experience alone does not ensure safety.
Table R1. Ablation of structured experience representation and adaptive category selection.
W3: The authors should include in the baselines (i) a protein language model with rejection sampling under the same predictors and budget, and (ii) the same model fine-tuned on AMPs.
Response: PepMind can generate peptides with stronger predicted antimicrobial activity and potency while keeping predicted hemolysis and toxicity lower than both ESM-2 baselines. As shown in Table R2, it achieves the best seven-species means across all four properties, with a four-objective HV of 0.6895, compared with 0.1854 for base ESM-2 and 0.4254 for AMP-tuned ESM-2.
Table R2. Comparison of PepMind with base and AMP-tuned ESM-2 before and after rejection sampling.
W4: The thresholds are fixed and they also seem quite low, given that the score is in [0,1]. A sensitivity analysis is needed. Response: We evaluated sensitivity on fixed candidate sets by varying property cutoffs from 0.3 to 0.9 and MIC-scale multipliers from 0.5 to 2. Tables R3 and R4 summarize the results; further details are provided in Appendix Q and Appendix S, Figure 28.
Table R3. Sensitivity of PepMind’s seven-species mean four-objective HV to MIC-scale multipliers.
As shown in Table R3, PepMind maintains the highest four-objective HV across all tested MIC scales, supporting the robustness of its ranking to MIC normalization.
Table R4. PepMind’s single-property passing fractions under stricter cutoffs.
As shown in Table R4, stricter cutoffs substantially reduce activity and hemolysis passing fractions, while the toxicity passing fraction remains comparatively stable.