Bontonou Myriam, Haget Anaïs, Boulougouri Maria, Audit Benjamin, Borgnat Pierre, Arbona Jean-Michel
CNRS, ENS de Lyon, Inserm, LBMC, UMR5239, U1293, F-69342 Lyon Cedex 07, France.
CNRS, ENS de Lyon, LPENSL, UMR5672, F-69342 Lyon Cedex 07, France.
Bioinform Adv. 2024 Dec 18;5(1):vbae199. doi: 10.1093/bioadv/vbae199. eCollection 2025.
Many machine learning (ML) models developed to classify phenotype from gene expression data provide interpretations for their decisions, with the aim of understanding biological processes. For many models, including neural networks, interpretations are lists of genes ranked by their importance for the predictions, with top-ranked genes likely linked to the phenotype. In this article, we discuss the limitations of such approaches using integrated gradient, an explainability method developed for neural networks, as an example.
Experiments are performed on RNA sequencing data from public cancer databases. A collection of ML models, including multilayer perceptrons and graph neural networks, are trained to classify samples by cancer type. Gene rankings from integrated gradients are compared to genes highlighted by statistical feature selection methods such as DESeq2 and other learning methods measuring global feature contribution. Experiments show that a small set of top-ranked genes is sufficient to achieve good classification. However, similar performance is possible with lower-ranked genes, although larger sets are required. Moreover, significant differences in top-ranked genes, especially between statistical and learning methods, prevent a comprehensive biological understanding. In conclusion, while these methods identify pathology-specific biomarkers, the completeness of gene sets selected by explainability techniques for understanding biological processes remains uncertain.
Python code and datasets are available at https://github.com/mbonto/XAI_in_genomics.
许多为从基因表达数据中分类表型而开发的机器学习（ML）模型会为其决策提供解释，目的是理解生物过程。对于许多模型，包括神经网络，解释是按基因对预测的重要性排序的基因列表，排名靠前的基因可能与表型相关。在本文中，我们以一种为神经网络开发的可解释性方法——集成梯度为例，讨论此类方法的局限性。
对来自公共癌症数据库的RNA测序数据进行了实验。训练了一组ML模型，包括多层感知器和图神经网络，以按癌症类型对样本进行分类。将集成梯度的基因排名与通过统计特征选择方法（如DESeq2）和其他测量全局特征贡献的学习方法所突出显示的基因进行比较。实验表明，一小部分排名靠前的基因足以实现良好的分类。然而，排名较低的基因也可能实现类似的性能，尽管需要更大的基因集。此外，排名靠前的基因存在显著差异，尤其是在统计方法和学习方法之间，这妨碍了全面的生物学理解。总之，虽然这些方法识别出了病理特异性生物标志物，但通过可解释性技术选择的用于理解生物过程的基因集的完整性仍然不确定。
Python代码和数据集可在https://github.com/mbonto/XAI_in_genomics获取。
