发表机构
Millennium Nucleus for Social Data Science (SODAS); Millennium Nucleus in Data Science for Plant Resilience (PhytoLearning)（社会数据科学千年核（SODAS）; 植物抗逆性数据科学千年核（PhytoLearning））
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
该研究在拟南芥ISR数据集上比较连续代理模型（RF、MLP）和离散机制模型（TBN），用滚动原点一步预测等方法评估。结果显示局部数值准确性和全局定性动态保真度不一定一致，二者应作为模拟生物调控的互补工具。
AI 中文摘要
基因调控网络建模通常需要平衡预测准确性和机制可解释性。在这项工作中，我们在相同的拟南芥诱导系统抗性（ISR）数据集上比较连续代理模型和离散机制模型，使用原始连续基因表达测量及其符号二值化表示。该研究考虑了在九个时间点测量的八个防御相关基因，并针对阈值布尔网络（TBN）评估了两个连续预测器，随机森林（RF）回归和多层感知器（MLP）。使用滚动原点一步预测、递归多步展开和可解释性分析对模型进行评估。RF在连续域中实现了最佳的平均一步数值性能，MAE为1.910，RMSE为2.836，而MLP分别为2.089和3.106。在二元域中，TBN获得了最佳的平均一步定性性能，二元准确率为0.550，汉明距离为3.600，而RF分别为0.500和4.000，MLP分别为0.495和4.040。在递归展开中，TBN准确再现了观察到的二值化轨迹，而MLP也显示出近乎完美的保真度，轨迹二元准确率为0.986，RF积累了更大的偏差，轨迹二元准确率为0.708。这些结果表明局部数值准确性和全局定性动态保真度不一定一致，并建议连续代理模型和阈值布尔网络应被视为模拟生物调控的互补工具。
英文摘要
Gene regulatory network modeling often requires balancing predictive accuracy and mechanistic interpretability. In this work, we compare continuous surrogate models and a discrete mechanistic model on the same \textit{Arabidopsis thaliana} induced systemic resistance (ISR) dataset, using both the raw continuous gene-expression measurements and their sign-binarized representation. The study considers eight defense-related genes measured over nine time points and evaluates two continuous predictors, Random Forest (RF) regression and a Multi-Layer Perceptron (MLP), against a threshold Boolean network (TBN). The models are assessed using rolling-origin one-step prediction, recursive multi-step rollout, and interpretability analysis. RF achieved the best average one-step numerical performance in the continuous domain, with an MAE of 1.910 and an RMSE of 2.836, compared with 2.089 and 3.106 for the MLP. In the binary domain, the TBN obtained the best average one-step qualitative performance, with a binary accuracy of 0.550 and a Hamming distance of 3.600, compared with 0.500 and 4.000 for RF, and 0.495 and 4.040 for the MLP. In recursive rollout, the TBN exactly reproduced the observed binarized trajectory, while the MLP also showed near-perfect fidelity, with a trajectory binary accuracy of 0.986, and RF accumulated substantially larger deviation, with a trajectory binary accuracy of 0.708. These results highlight that local numerical accuracy and global qualitative dynamical fidelity are not necessarily aligned, and suggest that continuous surrogates and threshold Boolean networks should be viewed as complementary tools for modeling biological regulation.
CommentsTo be published in IEEE CIBCB 2026
