- Rating
- 2(+1)
- Confidence
- 2
- Informativeness
- 2
- Presentation
- 3
- Soundness
- 1
Read review
Paper summary
The paper addresses unsupervised bulk-to-single-cell drug response prediction: training on labelled GDSC cell lines and predicting on unlabelled scRNA-seq data. It argues that ranking cells by sensitivity and deciding where to cut that ranking are separate problems. scRA-DRP starts from a shared domain-adversarial model and adapts two copies independently: The ranking branch pulls target features into class-specific regions around selected source anchors, using a bidirectional hinge loss The classification branch uses class-weighted adversarial alignment, plus target-specific BN statistics at inference Both branches use SAM on the source loss At inference, the number of cells the classification branch scores ≥ 0.5 sets k, and the top-k cells by ranking score are labelled sensitive
Critical strengths
- The results are transparent and details The authors provide: per-dataset means +- SD (Table 5) a common-subset comparison with DREEP (Table 6) cell-level corrections and new errors (Fig. 3) an explicit note that EpiSen pairs reuse the same cells (App. A.3)
Critical weaknesses
-
The central claim is not supported. The paper claims the classification branch adapts the sensitive-cell count to the target population, but the evidence doesn’t show this. 1.1 k₀ (Eq. 15) counts cells scored >= 0.5 by a classifier trained on class-balanced batches (Section 3). This builds in a 50 percent prior. The branch’s own adaptation term has little effect, even at β = 0 (Fig. 2c). 1.2 11 of the 18 targets are exactly 50 50 (Table 4). On these, a fixed 50 percent rule already gives the correct count, so they cannot show adaptation. 1.3 On the only strongly imbalanced target (Gefitinib/GSE112274, 37 of 507 sensitive), AUROC is almost 1 but accuracy is 0.73 (Table 5). This implies a count nearly five times too high. 1.4 Model selection is not described, and the defaults match the best test-set values (Section 4.4, Fig. 2).
-
Limited novelty, with weak evidence for individual components.
2.1 The regional loss (Eqs. 6–8) is a hinge-based form of support alignment, which is not cited: Adversarial Support Alignment (ICLR 2022) and CASUAL (AAAI 2025) . 2.2 The count is “classify and count”, which is known to be biased when class proportions shift. Standard corrections are not discussed or compared, including adjusted counting, EM prior re-estimation (Saerens et al., 2002) and BBSE (Lipton et al., 2018). 2.3 The class weights (Eq. 11) and target BN statistics (Eq. 14) are never ablated separately.
Questions for authors
How were the hyperparameters (M, κ, α, β, ρ, number of epochs) chosen? Were target labels used at any stage, including for Fig. 2 and Table 7? What is the predicted count k versus the true count for each dataset? For Gefitinib/GSE112274 (Table 5), is the accuracy gap caused by an overestimated k?
How does the ranking branch perform with each of these counts:k = n_t/2, the true k, a prior-corrected count (e.g., adjusted classify-and-count or EM) Do the main results hold when all hyperparameters are selected on source validation data only? What do the class weights (Eq. 11) and the target-specific BN statistics (Eq. 14) each contribute when ablated separately?
5 comments
W1.2–W1.4, Q1, and Q2: Target class composition and evaluation settings
W1.2: Applicability to balanced and imbalanced target datasets
As explained in W1.1, our method does not assume that 50% of target cells are sensitive. The count is determined by per-cell classification outputs, , where 0.5 is the classification threshold. Although 11 targets in Table 4 have a true sensitive proportion of 50%, predictions are made without target response labels or a preset 50% counting rule.
We compare scRA-DRP with SCAD and DAGFormer separately on the 11 balanced targets (50% sensitive cells) and the seven imbalanced targets. SCAD and DAGFormer are the strongest baselines for overall ranking and classification performance, respectively, in the main experiment. The tables report mean results across datasets within each group and three random seeds. scRA-DRP achieves higher mean AUROC, AUPR, ACC, and Weighted-F1 than both baselines in both groups, showing that its performance advantage extends to targets with unequal sensitive/resistant proportions.
11 balanced targets
| Method | AUROC | AUPR | Weighted-F1 | ACC |
|---|---|---|---|---|
| scRA-DRP | 0.8737 | 0.8812 | 0.8048 | 0.8070 |
| SCAD | 0.7892 | 0.7809 | 0.5058 | 0.5793 |
| DAGFormer | 0.7558 | 0.8229 | 0.7363 | 0.7367 |
Seven imbalanced targets
| Method | AUROC | AUPR | Weighted-F1 | ACC |
|---|---|---|---|---|
| scRA-DRP | 0.7810 | 0.7367 | 0.7142 | 0.7043 |
| SCAD | 0.7370 | 0.6849 | 0.6138 | 0.6481 |
| DAGFormer | 0.6676 | 0.5434 | 0.6619 | 0.6513 |
As detailed in our response to Reviewer 2, W5, the original evaluations of SCAD, DAGFormer, scDEAL, scAdaDrug, and FourierDrug cover 6-10 single-cell tasks, 5-9 drugs, and 4-7 cell lines. Our evaluation covers 18 drug-dataset tasks, 14 drugs, and 10 cell lines, extending all three dimensions. GEO includes nine tasks covering seven drugs, eight cell lines, and five cancer types, with true sensitive proportions of approximately 7.3%-60.0%. EpiSen evaluates nine drugs in single-cell populations from JHU006 and SCC47. Adding EpiSen increases total drug coverage from seven drugs in GEO to 14 drugs overall, providing additional evidence across drug conditions. These results support the applicability of scRA-DRP to target datasets with both balanced and imbalanced sensitive/resistant proportions across different drugs and cellular backgrounds.
W1.3: Ranking and classification on Gefitinib/GSE112274
Gefitinib/GSE112274 represents an extreme class-imbalance case in our evaluation. Among the 18 targets, it is the only one with a true sensitive-cell proportion below 10%: 7.30%, compared with 30.15%-60.00% for the other 17 targets.
On this target, scRA-DRP achieves mean AUROC of 0.9949 and AUPR of 0.9528, both higher than all comparison methods, indicating strong response-ranking performance. Its final classification performance is poor on this target. Across the other 17 targets, mean Weighted-F1 and ACC are 0.7683 and 0.7694, respectively, supporting its broader applicability across the evaluated target datasets.
Improving sensitive-cell count estimation and classification calibration under extreme class imbalance is an important direction for our future work.
W1.4, Q1, and Q2: Hyperparameters and source-validation selection
Section 4.1 specifies the default values of the main hyperparameters and training epochs. Section 4.4, Figure 2, and the appendix subsection "Additional Hyperparameter Sensitivity" report the corresponding sensitivity experiments. scRA-DRP uses unsupervised domain adaptation: target response labels are not used as supervision for model training or domain adaptation.
To test whether the main results hold when selection relies exclusively on source validation data, we reselected , , , , , and the numbers of training epochs for both stages. The selection criterion was the mean of source-validation AUROC and balanced accuracy. We froze the configurations before evaluating the target sets.
The table compares scRA-DRP with SCAD and DAGFormer over 18 targets and three random seeds.
| Method | AUROC | AUPR | Weighted-F1 | ACC |
|---|---|---|---|---|
| scRA-DRP | 0.7862 | 0.7736 | 0.6853 | 0.6906 |
| SCAD | 0.7476 | 0.7218 | 0.5672 | 0.6232 |
| DAGFormer | 0.6743 | 0.6729 | 0.6719 | 0.6681 |
Under the configurations shown, scRA-DRP achieves higher mean AUROC, AUPR, Weighted-F1, and ACC than both comparison methods. Relative to DAGFormer, the improvements are 11.19, 10.07, 1.33, and 2.25 percentage points, respectively.
W2.1: Regional alignment versus ASA and CASUAL
Thank you for pointing out Adversarial Support Alignment (ASA) and CASUAL.
Mechanisms. ASA aligns marginal source and target supports through bidirectional nearest-neighbor distances in the learned discriminator-output space, without explicitly constructing class-specific regions. CASUAL combines features with predicted class probabilities and uses entropy weighting to incorporate prediction confidence for conditional support alignment.
Our method constructs local regions directly in normalized feature space. It selects multiple source anchors within each response class and sets each region's radius from the distance to the nearest opposite-class sample, tying region size to source class separation. The target-to-source term encourages target features to enter source regions and becomes zero inside a region, allowing within-region variation. The reverse term encourages coverage of selected source regions by the current target batch. Targets select regions by geometric distance without restricting matches by predicted class. Our contribution is source-label-guided finite-radius region construction and bidirectional alignment, rather than the hinge form itself.
We evaluated ASA and CASUAL both as complete methods and as replacements for the regional alignment term in scRA-DRP, using 18 drug–dataset pairs and three seeds. Full-method comparisons retain the original training objectives; replacements keep the remaining scRA-DRP components and training settings fixed. Values are mean ± sample standard deviation across three seed-level averages, with equal weights for dataset pairs.
GEO
| Setting | AUROC | AUPR | W-F1 | ACC |
|---|---|---|---|---|
| scRA-DRP | 0.7791± 0.0288 | 0.7522± 0.0452 | 0.7240± 0.0114 | 0.7167± 0.0121 |
| ASA (full) | 0.6410± 0.0152 | 0.5906± 0.0210 | 0.4634± 0.0164 | 0.5810± 0.0106 |
| CASUAL (full) | 0.6845± 0.0573 | 0.6765± 0.0259 | 0.6028± 0.0287 | 0.6293± 0.0310 |
| ASA (replacement) | 0.7306± 0.0165 | 0.6812± 0.0165 | 0.6664± 0.0187 | 0.6597± 0.0191 |
| CASUAL (replacement) | 0.6765± 0.0444 | 0.6291± 0.0492 | 0.6392± 0.0302 | 0.6324± 0.0313 |
EpiSen
| Setting | AUROC | AUPR | W-F1 | ACC |
|---|---|---|---|---|
| scRA-DRP | 0.8962± 0.0242 | 0.8979± 0.0248 | 0.8152± 0.0102 | 0.8174± 0.0099 |
| ASA (full) | 0.7333± 0.0256 | 0.7173± 0.0208 | 0.4469± 0.0060 | 0.5512± 0.0042 |
| CASUAL (full) | 0.7080± 0.0165 | 0.6868± 0.0246 | 0.5204± 0.0297 | 0.5763± 0.0209 |
| ASA (replacement) | 0.8178± 0.0235 | 0.8139± 0.0286 | 0.7468± 0.0147 | 0.7494± 0.0146 |
| CASUAL (replacement) | 0.7882± 0.0251 | 0.7834± 0.0176 | 0.7162± 0.0206 | 0.7189± 0.0206 |
Overall
| Setting | AUROC | AUPR | W-F1 | ACC |
|---|---|---|---|---|
| scRA-DRP | 0.8377± 0.0059 | 0.8250± 0.0107 | 0.7696± 0.0057 | 0.7671± 0.0060 |
| ASA (full) | 0.6872± 0.0108 | 0.6539± 0.0142 | 0.4552± 0.0107 | 0.5661± 0.0065 |
| CASUAL (full) | 0.6962± 0.0232 | 0.6816± 0.0067 | 0.5616± 0.0067 | 0.6028± 0.0131 |
| ASA (replacement) | 0.7742± 0.0191 | 0.7475± 0.0176 | 0.7066± 0.0137 | 0.7045± 0.0141 |
| CASUAL (replacement) | 0.7323± 0.0346 | 0.7062± 0.0333 | 0.6777± 0.0252 | 0.6757± 0.0257 |
scRA-DRP achieves higher mean scores on all four metrics than both complete methods and both replacements in GEO and EpiSen. Compared with the ASA and CASUAL replacements, our regional alignment improves overall AUPR by 7.75 and 11.88 percentage points, respectively. These improvements support the contribution of our regional alignment to response ranking and sensitive-cell selection.
W1.1: Class priors, weighted domain adaptation, and target counts
Thank you for your review. After submission, we identified preprocessing inconsistencies between the Docetaxel/Erlotinib datasets and the other GEO pairs. We have unified the preprocessing, rerun the relevant experiments, and updated the affected results. The updated results preserve the main conclusions. Revised text and newly added standard deviations are highlighted in blue in the revised manuscript.
The target sensitive-cell count is determined by the classification predictions for target cells. In Eq. 15, k0=∑j1(cj≥0.5) counts cells whose classification scores reach the threshold. Here, 0.5 is a per-cell classification threshold, not an assumed target sensitive-cell proportion.
The 50% class prior mentioned in the review arises from class-balanced sampling in Source-Supervised Learning, which gives the two classes equal emphasis in the source drug response classification loss. Weighted Domain Adaptation weights the source-side domain loss by πs(y)/qs(y) to correct, at the population-distribution level, the change induced by balanced sampling. Alignment therefore uses the original empirical source distribution as its reference; training uses weights normalized within each batch. Class-balanced classification supervision and domain alignment against the original source distribution are handled separately. Target expression participates in domain adaptation without class-balanced sampling. The weighting corrects the source-side alignment reference, while target sensitive-cell counts are determined by the classification branch's target predictions.
The parameter β controls the weighted domain-adversarial term in the classification branch’s second stage. At β=0, the branch retains the adaptation learned during shared pretraining and uses target-domain batch-normalization statistics at inference. Across 18 pairs and three random seeds with the updated preprocessing, the default β=0.2 improves mean ACC and Weighted-F1 by 0.57 and 0.66 percentage points, respectively, compared with β=0, as shown below. These gains show that the second-stage weighted domain-adversarial term further improves classification, while their modest magnitude may reflect the alignment already established during shared pretraining. AUROC and AUPR remain unchanged because the ranking branch is fixed.