You Only Train Once: Differentiable Subset Selection for Omics Data

TL;DR

YOTO is an end-to-end differentiable framework that jointly selects gene subsets and predicts outcomes from single-cell transcriptomic data, improving interpretability and performance without additional classifiers.

Contribution

The paper introduces YOTO, a novel end-to-end differentiable method for joint gene subset selection and prediction, enabling more effective biomarker discovery from single-cell RNA-seq data.

Findings

YOTO outperforms state-of-the-art baselines on two single-cell RNA-seq datasets.

The method produces compact gene subsets that generalize across tasks.

End-to-end training improves predictive accuracy and interpretability.

Abstract

Selecting compact and informative gene subsets from single-cell transcriptomic data is essential for biomarker discovery, improving interpretability, and cost-effective profiling. However, most existing feature selection approaches either operate as multi-stage pipelines or rely on post hoc feature attribution, making selection and prediction weakly coupled. In this work, we present YOTO (you only train once), an end-to-end framework that jointly identifies discrete gene subsets and performs prediction within a single differentiable architecture. In our model, the prediction task directly guides which genes are selected, while the learned subsets, in turn, shape the predictive representation. This closed feedback loop enables the model to iteratively refine both what it selects and how it predicts during training. Unlike existing approaches, YOTO enforces sparsity so that only the selected genes contribute to inference, eliminating the need to train additional downstream classifiers. Through a multi-task learning design, the model learns shared representations across related objectives, allowing partially labeled datasets to inform one another, and discovering gene subsets that generalize across tasks without additional training steps. We evaluate YOTO on two representative single-cell RNA-seq datasets, showing that it consistently outperforms state-of-the-art baselines. These results demonstrate that sparse, end-to-end, multi-task gene subset selection improves predictive performance and yields compact and meaningful gene subsets, advancing biomarker discovery and single-cell analysis.