- Rating
- 2
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
This paper introduces PI2L, a generative model for whole-transcriptome expression that incorporates PPI-derived gene relationships into linear attention. Spherical PPI embeddings modulate attention through a corruption-dependent gate and determine static expert routing, while a hurdle decoder models zero and positive expression. Experiments on PBMC, heart, and brain datasets demonstrate improved marginal expression fidelity and gains over a Performer baseline.
Critical strengths
Incorporating biological structure into scalable whole-transcriptome generation is an interesting and important direction.
Critical weaknesses
- The evaluation does not sufficiently evaluate the generation using biologically relevant metrics, eg the pearson and spearman compare population-average gene expression. Although the MMD and coverage has some evaluation on the population, it is still unclear whether the model can perserve bioological property such as cell-type proportion, pathway scores, and within-cell-type coexpression etc. This is particularly concerning given its relatively low coverage compared with existing baselines (Table 1).
- Related to last point, the parse PBMC dataset contains 12 donors, but the evaluation does not investigate whether the generated population captures donor level heterogeneity, an important source of biological variation in PBMCs.
- PI2L is partly motivated by the limitations of sequence compression in Lingshu-Cell, yet no direct comparison is provided.
- From the ablation experiments (page 9), removing MoE actually improves all five reported generation metrics. While I understand that MoE is introduced to reduce FLOPs rather than improve accuracy, theoretical FLOP reductions do not necessarily translate into faster inference, particularly for a relatively small model with only six layers and fixed expert routing. How does this impact the acutal inference time (ie token/cell per second)?
Questions for authors
- See the weakness
- How could the biological prior adapt to cell identity or experimental conditions, particularly when disease or perturbation changes gene relationships relative to the association network (ie preparing to model the perturbation part of the parse PBMC dataset, while cytokine perturbation can change the PPI substantially)?
2 comments
Thanks for the detailed response and additional experiments. The biological validation still does not assess donor-level heterogeneity, and the MoE component does not show better generation quality or faster inference. I will maintain my original assessment.
Rebuttal follow-up
Dear Reviewer 7qQ7,
We hope this message finds you well. As the discussion period is nearing its end, we would like to kindly check whether our responses have addressed your concerns. Your feedback is very important to us, and we are happy to clarify anything further.
Thank you again for your insightful comments, which have greatly improved our paper.
Best regards,
The Authors