- Rating
- 2
- Confidence
- 4
- Informativeness
- 1
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
This paper proposes Trust-VC, an unsupervised multi-view clustering framework for paired single-cell multi-omics data. It integrates non-trainable scRNA reference representation with observed auxiliary modality and single-cell foundation model embeddings via gated residual adjustments that combines cross-modal consistency, latent dispersion and self-supervised clustering assignment-confidence.
Critical strengths
- With the accumulation of single-cell pretrained foundation-models, it is timely to design proper methods to quantify reliability weights of different pretrained foundation-model representations when incorporating them for paired multi-omics integration.
- The authors conducted extensive benchmark over eight datasets spanning diverse biological tissues, five single-cell foundation models, and ten baseline paired multi-omics integration algorithms.
- Fixed-checkpoint permutation experiments show the critical role of prior gates.
Critical weaknesses
- Both the RNA reference and the FM representation are deterministic transformations of the exact same RNA expression profiles. Why bifurcating the same biological signal into a static PCA baseline and an additive neural prior? In particular, since the authors utilize from multiple foundation models, why not treat as a new one? Moreover, the authors directly added non-linear MLP-generated residuals into PCA-reduced space, which seems to be unprincipled since Euclidean displacements in unconstrained neural latent spaces do not directly correspond to semantic shift vectors within a linear PCA space.
- I am quite confused about how the virtual encoder is framed as learning a diagonal Gaussian distribution to capture latent dispersion. Since the encoders of fixed pretrained foundation models are deterministic maps and no stochastic reparameterization or sampling is performed, is merely a parallel feedforward output constrained only by a standard Gaussian KL regularizer and an ad-hoc dispersion score. Hence, it would be unsubstantiated to claim that this captures model uncertainty or reliability. I consider it essentially an uncalibrated, deterministic heuristic dressed in variational notation.
- The clustering are based on a predefined cluster number optimized via DEC-style t-distribution sharpening, which is not practical in real single-cell analysis. Why not evaluating with more widely-used graph-based methods like Leiden clustering? Also, the main manuscript contains no manifold visualizations (like UMAP or t-SNE), and I do not observe clear benefits of Trust-VC in the UMAPs in the appendix. In fact, the representation quality of Trust-VC appears poor in Fig. 17, where the clusters are excessively dispersed as small, isolated spheres. This is likely due to the DEC-style approach forcing an overfitted contraction toward cluster centers, thereby losing the continuity of the true single-cell biological manifold.
- Benchmark seems to be comparing against some very rare methods while ignoring standard tools, such as Seurat, scVI, totalVI, MultiVI, MOFA+, etc.
Questions for authors
Does Figure 2 report standalone foundation model clustering on transcriptomics alone, or Trust-VC using each model as a prior? If former, it conflates algorithmic design with the data advantage of including complementary measured modalities; if latter, what are the standalone clustering scores without auxiliary modalities or fusion?
How does Trust-VC perform under misspecified cluster numbers or Leiden clustering? Is the performance robust?
I am also confused on the simple addition of latent vectors and the validity of dispersion that need the authors to clarify (see weakness).