arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2602.16696q-bio.GNcs.LGq-bio.QM
收藏

无需参数的表示方法在下游基准测试中优于单细胞基础模型

Simple models outperform single-cell foundation models on downstream benchmarks

Department of Physics, Boston University, Boston, MA, 02215, USA；Faculty of Computing；Data Science, Boston University, \ , MA, 02215, USA

Huan Souza, Pankaj Mehta

阅读 PDF
arXiv 页面 ↗HTML 原文 ↗

AI总结：

无需参数的表示方法在单细胞基础模型的下游任务中表现优异，通过简单线性方法超越传统深度学习模型。

摘要：

单细胞RNA测序（scRNA-seq）数据表现出强烈且可重复的统计结构。这推动了大规模基础模型的发展，例如TranscriptFormer，这些模型使用基于变压器的架构来学习基因表达的生成模型，通过将基因嵌入到潜在向量空间中。这些嵌入已被用于在细胞类型分类、疾病状态预测和跨物种学习等下游任务上获得最先进的（SOTA）性能。在此，我们询问是否可以在不利用计算密集型深度学习表示的情况下实现类似性能。使用简单、可解释的流程，依赖于仔细的标准化和线性方法，我们在多个常用于评估单细胞基础模型的基准测试中获得SOTA或接近SOTA的性能，包括在涉及新细胞类型和训练数据中未出现的生物体的分布外任务中超越基础模型。我们的发现突显了严格基准测试的必要性，并表明细胞身份的生物学可以通过单细胞基因表达数据的简单线性表示来捕捉。

英文摘要：

Single-cell RNA sequencing (scRNA-seq) data exhibit strong and reproducible statistical structure. This has motivated the development of large-scale foundation models, such as TranscriptFormer, that use transformer-based architectures to learn a generative model for gene expression by embedding genes into a latent vector space. These embeddings have been used to obtain state-of-the-art (SOTA) performance on downstream tasks such as cell-type classification, disease-state prediction, and cross-species learning. Here, we ask whether similar performance can be achieved without utilizing computationally intensive deep learning-based representations. Using simple, interpretable pipelines that rely on careful normalization and linear methods, we obtain SOTA or near SOTA performance across multiple benchmarks commonly used to evaluate single-cell foundation models, including outperforming foundation models on out-of-distribution tasks involving novel cell types and organisms absent from the training data. Our findings highlight the need for rigorous benchmarking and suggest that the biology of cell identity can be captured by simple linear representations of single cell gene expression data.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。

↑