基于Transformer的鲁棒基因表达建模与癌症预后表征学习
Transformer-Based Representation Learning for Robust Gene Expression Modeling and Cancer Prognosis
AI总结：
针对基因表达分析中Transformer应用受限的问题，提出GexBERT框架，通过预训练捕获基因共表达关系学习上下文感知嵌入，在泛癌分类、生存预测和缺失值插补任务中表现优异，具生物学可解释性与转化潜力。
摘要：
基于Transformer的模型在自然语言和视觉任务中取得了显著成功，但由于数据稀疏性、高维度和缺失值问题，其在基因表达分析中的应用仍受限。我们提出GexBERT，一种基于Transformer的自编码器框架，用于基因表达数据的鲁棒表征学习。GexBERT通过在大规模转录组谱上预训练，以掩蔽和恢复为目标捕获数千个基因间的共表达关系，从而学习上下文感知的基因嵌入。我们在癌症研究的三个关键任务中评估GexBERT：泛癌分类、癌症特异性生存预测和缺失值插补。GexBERT在有限基因子集上实现了最先进的泛癌分类准确率，通过恢复预后锚基因的表达提升了癌症特异性生存预测性能，并在高缺失率下优于传统缺失值插补方法。此外，其基于注意力的可解释性揭示了跨癌症类型的生物学意义基因模式。这些发现证明GexBERT是一种可扩展且有效的基因表达建模工具，在基因覆盖有限或不完整的场景中具有转化潜力。
英文摘要：
Transformer-based models have achieved remarkable success in natural language and vision tasks, but their application to gene expression analysis remains limited due to data sparsity, high dimensionality, and missing values. We present GexBERT, a transformer-based autoencoder framework for robust representation learning of gene expression data. GexBERT learns context-aware gene embeddings by pretraining on large-scale transcriptomic profiles with a masking and restoration objective that captures co-expression relationships among thousands of genes. We evaluate GexBERT across three critical tasks in cancer research: pan-cancer classification, cancer-specific survival prediction, and missing value imputation. GexBERT achieves state-of-the-art classification accuracy from limited gene subsets, improves survival prediction by restoring expression of prognostic anchor genes, and outperforms conventional imputation methods under high missingness. Furthermore, its attention-based interpretability reveals biologically meaningful gene patterns across cancer types. These findings demonstrate the utility of GexBERT as a scalable and effective tool for gene expression modeling, with translational potential in settings where gene coverage is limited or incomplete.
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。
