- Rating
- 2
- Confidence
- 2
- Informativeness
- 2
- Presentation
- 3
- Soundness
- 2
Read review
Paper summary
This paper proposes MOSA, a unified LoRA-based adaptation method for molecular generation and editing. It uses shared and task-specific low-rank branches, with property-conditioned modulation of the shared branch and additional source conditioning for editing. Experiments show encouraging improvements over conventional joint LoRA and task-specific baselines under matched task exposure.
Critical strengths
-
The shared/private LoRA design provides an interesting and well-motivated approach to reducing negative transfer between molecular generation and editing.
-
The experimental results are encouraging. The paper includes several useful ablations and controlled comparisons to support its findings.
Critical weaknesses
-
Comparisons with existing multi-task LoRA methods are missing, making the contribution of the learned controllers less clear.
-
Generalization remains insufficiently evaluated. Without quantifying train/test molecular overlap or testing on OOD molecules and property combinations, it is difficult to assess how well the method generalizes.
Questions for authors
-
Why does the property controller only use a scaling term , whereas the editing controller uses both and ?
-
How does MOSA compare with existing multi-task LoRA approaches under comparable settings?
-
Could the authors provide train/test molecular and scaffold overlap statistics, and evaluate generalization to unseen molecular scaffolds or property combinations?
7 comments
Response to Reviewer AC8v — Part 2/3: W2/Q3 — Overlap and scaffold generalization
W2/Q3. Overlap and scaffold generalization
MOSA reaches 56.0% strict generation success on unseen-reference scaffold requests, exceeding the generation specialist by 11.67 percentage points. The paired 95% interval is [6.97, 16.28] points. We audited molecular and scaffold overlap and evaluated separate scaffold panels to address your generalization concerns. Section 5.3 summarizes the results; Appendix I.2 provides the overlap audit and scaffold evaluation in manuscript Tables 33–34.
(1) We quantified molecular and scaffold overlap with the fine-tuning data. Exact molecular overlap is 0.17% for generation and 0.04% for editing (Table R3). The corresponding scaffold overlap is 50.28% and 40.54%. To evaluate generalization beyond these shared scaffolds, we additionally constructed separate seen- and unseen-scaffold panels with no molecular connectivity overlap with the fine-tuning data (Table R4).
Table R3. Molecular and scaffold overlap with fine-tuning data.
| Evaluated molecules | Molecule overlap (train/test) | Scaffold overlap (train/test) |
|---|---|---|
| Feasibility reference molecules for generation | 10/6,000 (0.17%) | 3,017/6,000 (50.28%) |
| Source molecules for editing | 2/5,000 (0.04%) | 2,024/4,992 (40.54%) |
Source: manuscript Table 33 (Appendix I.2), selected columns. The audited training corpus includes generation targets and both sides of editing pairs. Molecular identity uses canonical isomeric SMILES; scaffolds use nonchiral Bemis–Murcko structures. Eight editing sources with empty scaffolds are excluded from the scaffold denominator.
(2) MOSA improves strict generation success on unseen-reference scaffolds. MOSA achieves 56.0%, compared with 44.3% for the generation specialist. On unseen-source editing, MOSA achieves 67.6%, compared with 64.0% for Joint-24 and 64.2% for the editing specialist. The respective editing gains are 3.60 [−0.63, 7.99] and 3.40 [−0.72, 7.43] percentage points; both intervals cross zero. The editing gain over MOSA-Fixed is 3.20 [0.14, 6.44] points. All intervals are paired 95% cluster intervals.
Table R4. Strict and relaxed success on separate scaffold panels (%).
| Model | Seen | Unseen | Seen | Unseen | Seen | Unseen | Seen | Unseen |
|---|---|---|---|---|---|---|---|---|
| Specialist | 42.7 | 44.3 | 78.2 | 80.2 | 68.4 | 64.2 | 89.8 | 79.8 |
| Joint-24 | 53.8 | 54.7 | 86.7 | 86.8 | 68.2 | 64.0 | 89.8 | 81.0 |
| MOSA-Fixed | 55.5 | 53.3 | 85.2 | 87.0 | 71.0 | 64.4 | 88.2 | 82.0 |
| MOSA | 58.5 | 56.0 | 88.3 | 85.5 | 71.0 | 67.6 | 90.4 | 83.0 |
Source: manuscript Table 34 (Appendix I.2). Training exposure is matched by task. Each group contains 600 generation or 500 editing requests. Strict and relaxed criteria score the same saved outputs using Section 4.3. Bold marks the highest score in each column. These separate panels have no molecular connectivity overlap with fine-tuning data.
(3) The scaffold groups refer to generation reference molecules and editing source molecules. “Unseen” means that the corresponding scaffold is absent from the audited fine-tuning corpus. For generation, the reference molecule supplies the requested property values; the model receives those values, and the grouping places no scaffold constraint on its output. The seen and unseen panels have different request distributions, so comparisons between models are made within each panel. Generalization to unseen combinations of property goals remains a separate, untested setting, acknowledged in Section 6.
Response to Reviewer AC8v — Part 3/3: Q1 — Editing shift
Q1. Editing shift
The editing shift adds a source-conditioned offset beyond multiplicative scaling. Both scale and shift depend on the source molecule and property goals. The shift adds a correction independent of the current token feature. Section 3.3 and Appendix I.4 explain this distinction. The fixed-weight controls evaluate the contribution of scale and shift together (Appendix E.2, manuscript Table 27).
(1) Editing must preserve a source as well as meet property goals. Both tasks use shared property scaling. Editing additionally requires source-specific control, which motivates the scale and shift terms in its private block. Shared property scaling reweights low-rank features according to the requested goals, while the editing controller provides an additional source-conditioned adjustment.
(2) The shift can contribute even when the token feature is small. The editing update takes the form
The scale reweights the projected token feature . The shift contributes the additive term , which can remain nonzero even when is small. This gives the editing block an additional way to incorporate source and goal information.
(3) Removing editing modulation lowers strict success by 9.80 percentage points, mostly through source-retention failures. With trained weights fixed, setting and raises structural failures by 7.40 points and lowers relaxed success by 2.38 points (Table R5).
Table R5. Inference-only editing intervention (%).
| Configuration | ↑ | ↑ | ↓ | ↓ | ↓ |
|---|---|---|---|---|---|
| Full MOSA | 71.52 | 86.86 | 15.42 | 10.26 | 2.80 |
| Inference-only intervention (, ) | 61.72 | 84.48 | 22.82 | 12.38 | 3.08 |
Source: manuscript Table 27 (Appendix E.2) and Appendix I.4. Rates (%) use the same 5,000 editing requests. Both success criteria score the same saved outputs. The three failure rates use the strict criterion and sum to 100 with strict editing success. All trained weights remain fixed. For strict success, intervention minus full MOSA is −9.80 percentage points, with a paired 95% source-cluster interval of [−11.08, −8.55].
These controls establish reliance on the combined editing modulation. Isolating the shift’s contribution would require setting only while retaining the learned scale. Whether shared property control would benefit from an additional shift also requires a separate comparison. Appendix I.4 clarifies the scope of the current evidence.
Response to Reviewer AC8v — Part 1/3: Summary and W1/Q2 — MTL-LoRA
Dear Reviewer AC8v,
Thank you for the careful reading and for highlighting the need for a multi-task LoRA comparison and a train/test overlap audit. These requests helped us address gaps in the original evaluation. We have added the matched MTL-LoRA comparison (Tables R1–R2), audited overlap and evaluated connectivity-disjoint panels (Tables R3–R4), and clarified the editing controller’s additive shift. In the matched single-run comparison, MOSA has higher editing success, with the largest reduction in source-retention failures. We hope the new evidence and explanations address your concerns. Our responses are organized into three parts covering W1/Q2, W2/Q3, and Q1.
W1/Q2. Comparison with MTL-LoRA
The matched comparison favors MOSA on editing. Tables R1 and R2 report overall success and editing failure types; Appendix I.1 and manuscript Table 32 give the full comparison.
(1) MOSA gains 2.78 editing points over MTL-LoRA in the matched comparison. Both models use the same backbone, data, and training updates [1]. The paired 95% interval for the editing gain is [1.72, 3.87] percentage points. The generation difference is 1.43 points. Trainable parameter counts are 71.76M for MOSA and 75.39M for MTL-LoRA.
Table R1. Matched MTL-LoRA and MOSA success (%).
Source: manuscript Table 32 (Appendix I.1). Metrics follow Section 4.3. Generation uses 6,000 requests with strict or original SketchMol tolerances. Editing uses 5,000 requests with Tanimoto similarity ≥ 0.65 (strict) or ≥ 0.15 (relaxed). Both criteria score the same saved outputs. Both models use the same backbone, data, and 16,283 updates. Data exposure is matched; rank and compute differ. All entries come from one training run per method.
(2) MOSA produces 139 more successful edits, with all three failure types reduced. Structural failures show the largest reduction, at 1.20 percentage points (Table R2).
Table R2. Editing failure rates (%).
Source: the failure breakdown in Appendix I.1 accompanying manuscript Table 32. Rates use the full 5,000-request panel under strict editing criteria (similarity ≥ 0.65). The three categories are mutually exclusive. Lower is better; bold marks the better result.
(3) MTL-LoRA learns task-specific coefficients; MOSA also adapts coefficients to each request. MOSA uses property goals to adjust its shared update, and source and goal features to adjust its editing update.
The clearest benefit over MTL-LoRA is in editing, with the largest failure reduction in source retention. Section 5.1 and Appendix I.1 discuss this finding. This comparison uses one training run per method, so the 1.43-point generation difference remains descriptive. Differences in rank and architecture also limit attribution to individual components or parameter efficiency.
References
[1] Yang et al. MTL-LoRA: Low-Rank Adaptation for Multi-Task Learning. AAAI, 2025. Paper.