用注意力归因法解析DNABERT-2，发现其解释可揭示已知生物学规律。
Evaluating Post-hoc Explanations of the Transformer-based Genome Language Model DNABERT-2
- 将AttnLRP方法拓展至Transformer模型，实现从词元到核苷酸的解释传递
- 在多个基因组数据集上验证，解释结果与已知生物模式高度一致
- 首次对比了gLM与CNN的解释能力，推动跨架构可比性研究
深度神经网络对基因组序列的预测解释能带来生物学洞察与假说生成，其价值常超过预测性能本身。尽管卷积神经网络（CNN）的解释已被证明能捕捉基因组中的相关模式，但这种能力是否适用于更强大的基于Transformer的基因组语言模型（gLMs）仍不清楚。为此，我们采用AttnLRP——一种针对注意力机制的层间相关性传播扩展方法，并将其应用于当前最先进的gLM DNABERT-2。我们提出策略，实现从词元到核苷酸层级的解释迁移。通过多种指标，在多个基因组数据集上评估AttnLRP的适配效果。此外，我们还对DNABERT-2与基准CNN的解释进行了全面比较。结果表明，AttnLRP能生成与已知生物模式相符的可靠解释。因此，与CNN类似，gLMs同样可用于推导生物学洞见。本工作推进了gLM的可解释性研究，并解决了不同模型架构间归因可比性的关键问题。
原文摘要 · Abstract (English)
Explaining deep neural network predictions on genome sequences enables biological insight and hypothesis generation-often of greater interest than predictive performance alone. While explanations of convolutional neural networks (CNNs) have been shown to capture relevant patterns in genome sequences, it is unclear whether this transfers to more expressive Transformer-based genome language models (gLMs). To answer this question, we adapt AttnLRP, an extension of layer-wise relevance propagation to the attention mechanism, and apply it to the state-of-the-art gLM DNABERT-2. Thereby, we propose strategies to transfer explanations from token and nucleotide level. We evaluate the adaption of AttnLRP on genomic datasets using multiple metrics. Further, we provide an extensive comparison between the explanations of DNABERT-2 and a baseline CNN. Our results demonstrate that AttnLRP yields reliable explanations corresponding to known biological patterns. Hence, like CNNs, gLMs can also help derive biological insights. This work contributes to the explainability of gLMs and addresses the comparability of relevance attributions across different architectures.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。