Combinatorial prediction of therapeutic perturbations using causally-inspired neural networks (chemical data)

Dataset supporting "Combinatorial prediction of therapeutic targets using causally-inspired neural networks" (chemical data) Abstract: Phenotype-driven approaches identify disease-counteracting compounds by analyzing the phenotypic signatures that distinguish diseased from healthy states. Here, we introduce PDGrapher, a causally inspired graph neural network (GNN) designed to predict combinatorial perturbagens (sets of therapeutic targets) capable of reversing disease phenotypes. Unlike methods that learn how perturbations alter phenotypes, PDGrapher solves the inverse problem of directly predicting the perturbagens needed to achieve a desired response by embedding disease cell states into networks, learning a latent representation of these states, and identifying optimal combinatorial perturbations. In experiments in nine cell lines with chemical perturbations, PDGrapher identified effective perturbagens in more test samples than competing methods. It also demonstrates competitive performance on ten genetic perturbation datasets. An advantage of PDGrapher is its direct prediction paradigm, in contrast to the indirect and computationally intensive models traditionally employed in phenotype-driven research. This approach accelerates training by up to 25 times compared to existing methods, providing a fast approach for identifying therapeutic perturbations and advancing phenotype-driven drug discovery.支持《基于因果启发神经网络的治疗靶点组合预测》研究的化学数据集。 摘要：基于表型的研究方法通过分析区分疾病状态与健康状态的表型特征，识别可对抗疾病的化合物。本文提出PDGrapher——一款受因果启发的图神经网络（Graph Neural Network, GNN），旨在预测能够逆转疾病表型的组合扰动因子（即治疗靶点集合）。与那些通过学习扰动如何改变表型的现有方法不同，PDGrapher通过将疾病细胞状态嵌入网络、学习这些状态的潜在表征，并识别最优组合扰动因子，直接解决了预测实现预期响应所需扰动因子的逆问题。在针对9种细胞系开展的化学扰动实验中，PDGrapher在更多测试样本中识别出了有效的扰动因子，性能优于同类对比方法；同时在10个遗传扰动数据集上展现出了具有竞争力的性能。PDGrapher的一大优势在于其直接预测范式，与传统表型研究中采用的间接且计算密集型模型形成鲜明对比。相较于现有方法，该方法可将训练速度提升最高达25倍，为识别治疗性扰动因子、推动表型驱动的药物发现提供了一种高效路径。