- Rating
- 3
- Confidence
- 2(+1)
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
This paper proposes ABLE, an all-atom biomolecular trajectory generation framework for virtual screening, aiming to address the limited ability of existing models to distinguish active ligands from decoys due to their reliance on MD trajectories of active protein–ligand complexes for training. ABLE learns molecular dynamics through a variational bridge matching framework and introduces the Interfacial Expansion Rate as a reward signal for on-policy reinforcement learning (RL). Experiments on the ATLAS, MISATO, and DUDE-Z datasets evaluate the model’s trajectory generation and virtual screening capabilities. Notably, RL improves the EF 1% on DUDE-Z from 0.524 to 2.807, demonstrating the method’s effectiveness in enhancing early enrichment of active ligands.
Critical strengths
-
This paper extends generative molecular dynamics beyond conventional trajectory modeling to virtual screening based on dynamical behavior. It addresses the limitation that existing training datasets predominantly consist of active protein–ligand complexes and lack decoy trajectories, presenting a clear research objective and a corresponding solution.
-
This paper introduces the Interfacial Expansion Rate, defined based on the entropy growth of local tracer particles, and leverages the divergence of the velocity field to construct an optimizable reinforcement learning signal. The proposed method enables post-training using only static cross-docked complexes, without requiring additional MD trajectories of decoy complexes, demonstrating a degree of novelty in both methodological design and data requirements.
-
This paper conducts experiments on the ATLAS, MISATO, and DUDE-Z datasets to evaluate protein trajectory generation, protein–ligand trajectory generation, and virtual screening performance, respectively. Notably, reinforcement learning improves the EF 1% on DUDE-Z from 0.524 to 2.807, providing direct empirical evidence supporting the effectiveness of the proposed post-training approach.
Critical weaknesses
-
The proposed Interfacial Expansion Rate is central to the reinforcement learning approach, but its effectiveness is primarily validated indirectly through downstream virtual screening performance. The paper lacks direct quantitative evidence establishing its relationship with actual ligand dissociation dynamics. Therefore, the reliability of this metric as a physically meaningful descriptor of molecular dynamics remains insufficiently validated.
-
Although the paper evaluates trajectory generation quality before reinforcement learning, it does not provide an equally systematic assessment of the physical plausibility and dynamical fidelity of the generated trajectories after RL fine-tuning. Given that the authors have observed abnormally large ligand RMSD values for certain targets, further analysis is needed to determine whether reinforcement learning introduces non-physical motions and whether KL regularization effectively constrains such deviations.
Questions for authors
None
4 comments
Rebuttal 2
Table A: Physical fidelity of generated trajectories on the DUDE-Z test set.
| Models | Ligand Validity: Bond Length (↑) | Ligand Validity: Bond Angle (↑) | Ligand Validity: Aromatic (↑) | Ligand Validity: Double Bond (↑) | Steric Clashes: intra (↓) | Steric Clashes: inter (↓) | Protein Validity (↑) |
|---|---|---|---|---|---|---|---|
| NeuralMD-SDE | 1.000/0.000 | 1.000/0.000 | 1.000/0.000 | 1.000/0.000 | 0.000/0.000 | 0.000/0.000 | - |
| PVB | 0.978/0.010 | 0.991/0.004 | 0.957/0.028 | 0.980/0.022 | 0.026/0.010 | 0.000/0.000 | 0.724/0.154 |
| ABLE (ref) | 0.926/0.042 | 0.949/0.026 | 0.890/0.038 | 0.978/0.022 | 0.072/0.039 | 0.000/0.000 | 0.990/0.013 |
| ABLE (rl, ) | 0.838/0.125 | 0.863/0.128 | 0.908/0.080 | 0.981/0.020 | 0.168/0.131 | 0.000/0.000 | 0.812/0.192 |
| ABLE (rl, ) | 0.906/0.070 | 0.939/0.067 | 0.949/0.041 | 0.981/0.020 | 0.146/0.107 | 0.000/0.000 | 0.979/0.056 |
| ABLE (rl, ) | 0.925/0.042 | 0.960/0.024 | 0.960/0.015 | 0.982/0.018 | 0.131/0.065 | 0.000/0.000 | 0.991/0.025 |
References
[1] Guterres, H., & Im, W. (2020). Improving protein-ligand docking results with high-throughput molecular dynamics simulations. Journal of chemical information and modeling, 60(4), 2189.
Thanks for the Rebuttal
Thank you for the detailed rebuttal and additional experiments. Given that my initial rating was already favorable and that this topic is outside my primary area of expertise, I will maintain my rating and increase my confidence score from 1 to 2.
We sincerely thank the reviewer for their positive assessment of our work and for carefully considering our responses and additional experiments. We greatly appreciate the time and effort devoted to reviewing our manuscript, as well as the constructive feedback that has helped us improve its quality. We wish the reviewer all the best in their research and future endeavors.
Rebuttal 1
We are grateful to the reviewer for the insightful comments and helpful suggestions. In the following, we respond to each point individually and clarify the corresponding revisions.
Thank you for raising this important concern. We agree that the proposed interfacial expansion rate does not directly represent real ligand dissociation kinetics. Its design is motivated by the empirical observation that active ligands generally maintain more stable binding poses and protein-ligand contacts during MD simulations, whereas decoys tend to exhibit less stable interactions [1]. Accordingly, we measure the instantaneous entropy growth of an auxiliary tracer distribution near the protein-ligand interface and use it as a physically motivated surrogate reward to encourage interfacial expansion for decoys while preserving the reference dynamics for active ligands.
Importantly, our primary objective is not to faithfully reproduce ligand dissociation pathways, which would likely require additional MD trajectories of protein-decoy complexes for training. Instead, we aim to introduce active-decoy discrimination into trajectory generation models using only readily available static cross-docked structures. Beyond the downstream screening metrics, Appendix D.2 (Figure 5) also provides qualitative evidence that RL finetuning induces the intended differences in generated trajectories: active ligands generally exhibit lower RMSD and retain more initial protein-ligand contacts than decoys. These findings support the use of the proposed interfacial expansion rate as an empirically effective optimization signal for trajectory-based virtual screening, without requiring faithful reproduction of real ligand dissociation dynamics.
Thank you for this important suggestion. We agree that reinforcement learning may introduce non-physical motions, as improved active-decoy discrimination does not necessarily guarantee the physical fidelity of generated trajectories. To address this concern, we have added a systematic physical fidelity assessment in Appendix D.4 (Table 8), covering ligand geometric validity, intra- and intermolecular steric clashes, and protein Cα validity on the DUDE-Z test set. For convenience, we also provide the results in Table A below. To avoid confounding effects from pre-existing structural violations, we restrict the evaluation to trajectories whose initial structures pass all physical plausibility checks.
The results reveal the importance of path-space KL regularization in preserving physical fidelity after RL. Without KL regularization ($\beta=0), RL substantially degrades ligand bond-length, bond-angle, and protein validity, while increasing intramolecular steric clashes from 0.072 in the reference model to 0.168. Introducing KL regularization progressively mitigates these distortions as β increases from 0 to 0.4. Specifically, protein validity improves from 0.812 to 0.991, while intramolecular clashes decrease from 0.168 to 0.131. Moreover, At β=0.4, most physical validity metrics reach levels comparable to or better than those of the reference model, providing practical guidance for hyperparameter selection. Overall, these findings demonstrate that appropriate path-space KL regularization can effectively mitigate RL-induced structural distortions, allowing ABLE to substantially improve virtual screening performance while largely preserving the physical plausibility of generated trajectories.
(to be continued)