Despite the success and fast adaptation of deep learning models in biomedical domains, their lack of interpretability remains an issue. Here, we introduce Enhanced Integrated Gradients (EIG), a method to identify significant features associated with a specific prediction task. Using RNA splicing prediction as well as digit classification as case studies, we demonstrate that EIG improves upon the original Integrated Gradients method and produces sets of informative features. We then apply EIG to identify A1CF as a key regulator of liver-specific alternative splicing, supporting this finding with subsequent analysis of relevant A1CF functional (RNA-seq) and binding data (PAR-CLIP).

中文翻译：

---

Enhanced Integrated Gradients：以拼接代码为案例研究提高深度学习模型的可解释性

尽管深度学习模型在生物医学领域取得了成功和快速适应，但它们缺乏可解释性仍然是一个问题。在这里，我们介绍了增强集成梯度 (EIG)，这是一种识别与特定预测任务相关的重要特征的方法。使用 RNA 剪接预测以及数字分类作为案例研究，我们证明 EIG 改进了原始的集成梯度方法并产生了一组信息特征。然后，我们应用 EIG 将 A1CF 鉴定为肝脏特异性选择性剪接的关键调节因子，通过随后对相关 A1CF 功能（RNA-seq）和结合数据（PAR-CLIP）的分析来支持这一发现。