scTranslation: A Comprehensive Benchmark for Single-Cell Multi-Omics Modality Translation
2026-06-02 • Artificial Intelligence
Artificial Intelligence
AI summaryⓘ
The authors created scTranslation, a tool to compare different computer methods that guess missing biological data types in single cells. These methods help scientists understand cell functions better without doing expensive experiments. The authors tested these methods using various datasets and conditions, like how many features are used or how good the data is. Their study shows important factors that affect performance and provides useful insights for future improvements. They made their work publicly available to help other researchers.
single-cell multi-omicsmodality translationbenchmarkingfeature selectionfew-shot learningdata qualitycomputational biologymulti-omics datasetsmodel evaluation
Authors
Jiabei Cheng, Jingbo Zhou, Jun Xia, Changkai Li, Zhen Lei, Chang Yu, Stan Z. Li
Abstract
Simultaneous measurement of multiple omics modalities in single cells enables researchers to gain a more comprehensive understanding of cellular states and regulatory mechanisms. However, due to high experimental costs, significant noise, and incomplete modality coverage, a variety of computational methods for modality translation have emerged in recent years. Despite the development of translation models, there is still a lack of systematic benchmark evaluation in terms of datasets, evaluation metrics, and influencing factors. To address this, we present scTranslation, a comprehensive benchmark for single-cell multi-omics modality translation tasks. It includes diverse translation datasets, integrates state-of-the-art models, and provides a comprehensive evaluation metrics. In addition, we assess model performance under different scenarios, such as feature selection, feature quality, and few-shot settings. These factors significantly affect model performance but have rarely been systematically studied before. Leveraging this benchmark, we conduct a large-scale study of current methods, report many insightful findings that open up new possibilities for future development. The benchmark is open-sourced to facilitate future research. The code is anonymously released at https://github.com/Bunnybeibei/scTranslation.