- Rating
- 2
- Confidence
- 4
- Informativeness
- 2
- Presentation
- 3
- Soundness
- 2
Read review
Paper summary
This paper proposes SynTrace, a pocket-conditioned molecular generation framework that jointly models synthesis decisions and 3D molecular geometry. It employs supervised route–pose alignment and a shared geometric network to generate molecules with explicit synthesis routes. Experiments on CrossDocked2020 demonstrate competitive docking performance and synthetic accessibility.
Critical strengths
-
The paper integrates synthesis planning and pocket-conditioned 3D molecular generation into a unified framework.
-
SynTrace achieves a 45.49% retrosynthesis solve rate and competitive molecular diversity compared with existing baselines.
Critical weaknesses
-
Joint synthesis and 3D molecular generation have already been explored in CGFlow/3DSynthFlow and SynCoGen. The paper does not sufficiently establish its methodological advantages over these approaches.
-
SynTrace does not consistently outperform existing methods, particularly in docking and direct-pose quality. The evaluation is limited to 100 pockets from CrossDocked2020, with single-seed experiments. Additional independent benchmarks and stronger SOTA comparisons are needed.
-
Although synthesis decisions respond to spatial information, the experiments do not convincingly demonstrate that geometric conditioning improves pocket-specific chemical quality.
Questions for authors
-
Can the authors include additional benchmarks and stronger comparisons with 3DSynthFlow and SynCoGen?
-
Can the authors clarify the methodological novelty over existing joint synthesis–structure generation frameworks?
-
Can the authors provide stronger evidence that geometric coupling improves pocket-specific molecular quality?
3 comments
Response to Reviewer W73u (2/3)
W2 / Q1 (1/3). Direct-pose quality
We added receptor-aware PoseBusters (PB complex), which checks the generated pose against its receptor before any minimization or redocking, for every method that emits receptor-frame coordinates (Table 1):
| Method | Produces a route | PB complex (%) |
|---|---|---|
| MolCRAFT | no | |
| DecompDiff | no | |
| SynTrace | yes | |
| TargetDiff | no | |
| 3DSynthFlow (retrained) | yes | |
| Pocket2Mol | no | |
| RxnFlow | yes | no coordinates |
| SynCoGen (uncond.) | yes | own frame, not verifiable |
| SynCoGen (cond.) | yes | own frame, not verifiable |
MolCRAFT and DecompDiff are ahead of us, and MolCRAFT also has the better direct Score ( against ). The explanation is the constraint we accept: those models place atoms freely, so only the pocket limits their geometry, whereas every SynTrace molecule must in addition be reachable by an executable two- or three-step route from catalogue building blocks. That constraint restricts the graph and, through it, the geometry — and it is also what produces the solve rate we lead on, , against for MolCRAFT and for DecompDiff. And among the methods that accept the same constraint, SynTrace is the only one whose emitted pose passes a receptor-aware check more often than not.
For redocking, the size effect is a major factor: the larger the molecule, the better the score it tends to receive — a point MolCRAFT's own evaluation makes about Vina Dock (Qu et al., 2024). The synthesis-aware baselines all generate larger molecules than we do, with a median of heavy atoms for RxnFlow and for the retrained 3DSynthFlow against for SynTrace, and in this evaluation the median redocking score falls monotonically across five heavy-atom windows for all three methods built on our library (Appendix B.2, Table 4). Matching the heavy-atom distributions exactly within each pocket removes that confound (Appendix B.2, Table 5):
| Baseline | Paired advantage to SynTrace (kcal/mol) | 95% CI | Pockets favouring SynTrace |
|---|---|---|---|
| RxnFlow | |||
| 3DSynthFlow (retrained) | |||
| SynCoGen (uncond.) |
W2 / Q1 (2/3). Independent training seeds
The ablation results quoted above are no longer single-seed: Full, NoRel and Separate were each trained three times, and the table in W1 reports the mean and standard deviation across those runs, with all six metrics for all nine runs in Appendix C.6, Table 10. On every metric the separation between the full model and either ablation is several times the run-to-run spread. On the size of the evaluation, the generation pockets come from the official CrossDocked2020 test split and span pocket families, none shared with the training families (Appendix A.3).
W2 / Q1 (3/3). A second benchmark: LIT-PCBA
We evaluated fixed checkpoints on the LIT-PCBA targets used for pocket-specific optimization by RxnFlow and 3DSynthFlow, with the same receptors, boxes and scoring code for every method, and redocked the benchmark's own known actives under that protocol as a reference point (Appendix C.5, Table 8):
| Dock (kcal/mol) | LE (kcal/mol per atom) | HA | PB ligand (%) | AiZynth ZINC (%) | |
|---|---|---|---|---|---|
| SynTrace | |||||
| RxnFlow | — | ||||
| 3DSynthFlow (retrained) | |||||
| SynCoGen (cond.) | |||||
| Known actives | — |
The size effect appears again: RxnFlow leads on raw redocking with molecules a third larger. Per heavy atom, SynTrace has the better ligand efficiency on every one of the targets, and is the only method whose ligand efficiency exceeds that of the known actives (per-target values in Appendix C.5, Table 9). Against the retrained 3DSynthFlow it is points on intramolecular validity () and points on ZINC-stock solve rate (). Against RxnFlow it has the higher solve rate under both stocks, against with Enamine and against with ZINC. Matching heavy-atom counts within each target, as on CrossDocked, also favours SynTrace on redocking: by kcal/mol over the retrained 3DSynthFlow () and by over conditional SynCoGen ().
Qu, Y. et al. MolCRAFT: Structure-Based Drug Design in Continuous Parameter Space. ICML 2024, PMLR 235, 41749–41768.
Response to Reviewer W73u (3/3)
W3 / Q3. Evidence that geometric conditioning improves pocket-specific molecular quality
We added two experiments that score the completed products of the blocks the policy selects. The first asks whether the choice follows the pocket, using intermediates that occur in more than one test protein; the second compares the full model with NoRel on intermediates the model generates itself.
We collected every pair where the same intermediate and the same reaction slot appear in two different pockets, A and B — pairs in all (Appendix C.4). In of them the model picks one block for A and a different one for B; for NoRel this happens in only . We then built all four products, both blocks in both pockets, and scored each one with that pocket's own docked reference core held in place. If the model is responding to the pocket, the block it picked for A should beat the other one in A, and the same should hold in B. Adding the two differences, that is what we see in of the pairs that returned all four scores, by a key-weighted mean of kcal/mol (). Figure 5 shows one such pair: for COAA, a pantothenate kinase with a polar site, the model picks a basic piperidine; for PTGIS, a P450 with a lipophilic heme-lined channel, an apolar phenyl; and the constrained scores reverse between the two ( against , and against kcal/mol).
The second experiment runs on intermediates the full model generated itself, rather than on poses taken from docked reference complexes, and compares it with NoRel — the same network with the action head's view of the relative geometry switched off, at an unchanged parameter count (Section 4.5). At each intermediate both models choose from the same legal blocks at the same reaction slot, and we complete the products of the four each one prefers. To score them we dock the intermediate separately and hold its pose fixed, so only the newly added extension can move (Figure 3a–c; protocol in Appendix C.6). Across equally weighted pocket families the mean Full-minus-NoRel difference is kcal/mol (), with the full model scoring lower in of them (Figure 3d).
Concluding remarks
We thank the reviewer again for the time and for the detailed requests, which shaped most of the revision: a second benchmark on LIT-PCBA, three independent training runs for every ablation, receptor-aware PoseBusters for every method that emits receptor-frame coordinates, a retrained 3DSynthFlow, and two experiments that score the pocket-specific choices the policy makes. We hope these additions address the concerns raised, and we would be grateful if the reviewer could reconsider the score in light of them. We are of course happy to provide any further details or analyses that would help.
Response to Reviewer W73u (1/3)
We thank the reviewer for the constructive feedback. For the baselines, we retrained 3DSynthFlow on our building-block library and added both released SynCoGen checkpoints under one protocol, together with receptor-aware PoseBusters and a size-matched redocking comparison. For the evaluation, we added a second benchmark and trained every ablation with three independent seeds. On whether the geometry improves pocket-specific choices, we added two experiments that score the building blocks the policy selects. Changes in the revised PDF are marked in magenta, and the new analyses are in Appendices A.3, B.2, C.4, C.5 and C.6.
W1 / Q2. Methodological advantages over CGFlow / 3DSynthFlow and SynCoGen
3DSynthFlow trains a coordinate model first and freezes it while the construction policy is learned by reward, so the synthesis decision and the 3D placement are never optimized together. SynCoGen does optimize them together, but it conditions on pharmacophore points taken from a reference ligand rather than on the receptor itself. Its coordinates are also generated in their own frame rather than in the pocket, and we could not verify a transformation into the receptor frame, so its output has no pose to check against the protein. SynTrace does both at once: one network learns the synthesis decision and the 3D placement together, conditioned directly on receptor atoms. The route–pose supervision is what makes that affordable: a single docked pose of the final product supervises every step of the route, so no intermediate ever has to be docked and no reward model is needed. One pass therefore returns a molecule, an executable route for it, and a pose that can be evaluated as it stands.
Two sets of results support this. The first removes the coupling inside SynTrace. Separate trains the action and coordinate predictions as two independent networks that share nothing; NoRel keeps the shared network but stops the action head from reading the ligand's position relative to the pocket, at an unchanged parameter count. Both use the same data and training budget as the full model, and all three were trained three times (Table 2; per-run values in Appendix C.6, Table 10):
Splitting the two predictions costs 0.65 kcal/mol of direct score and 9.5 points of receptor-aware PoseBusters, at twice the parameters; keeping one network but hiding the relative geometry still costs 0.55 kcal/mol and 3.1 points. Both are several times the run-to-run spread, and both appear on the pose the model emits rather than after redocking, where all three lie within 0.17 kcal/mol.
The second set compares complete systems. We retrained 3DSynthFlow on the 274k Enamine library we share with RxnFlow, and scored it and both SynCoGen checkpoints on the same 100 pockets with our own pipeline (Table 1; its SynTrace row is run 1 of the three above):
Redocking re-searches the pose, so all four rows land within 0.14 kcal/mol of each other there. The gap opens once the pose is taken as the model emits it — 67.19% against 19.00% on receptor-aware PoseBusters — and again on usable output, where 99.41% of our molecules are distinct against 3DSynthFlow's 17.73% and AiZynthFinder solves more than twice as many of ours as of any baseline in the table.