Beyond Expression Prediction: Benchmarking Differential Expression Classification in Single-Cell Perturbation Models
Sun, J.; He, Y.; Zhu, O.; Chen, Y. T.
Show abstract
Accurate predictions of transcriptomic responses to genetic perturbations could unlock our understanding of gene functions and regulatory networks. While a growing number of methods and benchmarks target this task, existing evaluations focus on mean expression accuracy alone. This overlooks differential expression (DE), which captures both mean and variance and forms the basis for biological interpretation and experimental follow-up. Here, we systematically evaluate a diverse set of deep learning and non-deep-learning methods for their ability to predict DE outcomes under two generalization regimes: unseen perturbations within the same cell line, and unseen cellular contexts across cell lines. We find that simple baselines, such as embedding-based nearest neighbors, are competitive and often outperform specialized deep learning models for DE classification across datasets and evaluation metrics. We further show that sparsity calibration, motivated by the structure of single-cell data, substantially improves DE classification for deep learning models that do not explicitly account for sparsity. Together, our findings establish practical baselines and evaluation principles for benchmarking perturbation models on DE prediction.
Matching journals
The top 6 journals account for 50% of the predicted probability mass.
Similar papers in this journal
- Sampling from Disentangled Representations of Single-Cell Data Using Generative Adversarial Networks 96%
- Enhancement of network architecture alignment in comparative single-cell studies 96%
- scDesign2: a transparent simulator that generates high-fidelity single-cell gene expression count data with gene correlations captured 95%
Similar papers in this journal
- Learning Genetic Perturbation Effects with Variational Causal Inference 96%
- Highly Accurate Cancer Phenotype Prediction with AKLIMATE, a Stacked Kernel Learner Integrating Multimodal Genomic Data and Pathway Knowledge 95%
- Optimal transport reveals dynamic gene regulatory networks via gene velocity estimation 95%
Similar papers in this journal
- ARTEMIS integrates autoencoders and schrodinger bridges to predict continuous dynamics of gene expression, cell population and perturbation from time-series single-cell data 96%
- Supervised-learning is an accurate method for network-based gene classification 95%
- Gemini: Memory-efficient integration of hundreds of gene networks with high-order pooling 95%
"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.