Li Kunshi, Shen Bihan, Feng Fangyoumin, Li Xueliang, Wang Yue, Feng Na, Tang Zhixuan, Ma Liangxiao, Li Hong
CAS Key Laboratory of Computational Biology, Shanghai Institute of Nutrition and Health, University of Chinese Academy of Sciences, Chinese Academy of Sciences, Shanghai, 200031, China.
Molecular Pathology Laboratory, National Center for Liver Cancer, Eastern Hepatobiliary Surgery Hospital, Shanghai, 201800, China.
J Pharm Anal. 2025 Jun;15(6):101128. doi: 10.1016/j.jpha.2024.101128. Epub 2024 Oct 24.
Personalized drug response prediction from molecular data is an important challenge in precision medicine for treating cancer. Computational methods have been widely explored and have become increasingly accurate in recent years. However, the clinical application of prediction methods is still in its infancy due to large discrepancies between preclinial models and patients. We present a novel disentangled synthesis transfer network (DiSyn) for drug response prediction specifically designed for transfer learning from preclinical models to clinical patients. DiSyn uses a domain separation network (DSN) to disentangle drug response related features, employs data synthesis technology to increase the sample size and iteratively trains for better feature disentanglement. DiSyn is pretrained on large-scale unlabeled cancer samples and validated by three datasets, The Cancer Genome Atlas (TCGA), Investigation of Serial Studies to Predict Your Therapeutic Response With Imaging And moLecular Analysis 2 (I-SPY2) and Novartis Institutes for Biomedical Research Patient-Derived Xenograft Encyclopedia (NIBR PDXE), achieving competitive performance with the state-of-the-art methods on cancer patients and mice. Furthermore, the application of DiSyn to thousands of breast cancer patients show the heterogeneity in drug responses and demonstrate its potential value in biomarker discovery and drug combination prediction.
从分子数据预测个性化药物反应是癌症精准治疗中的一项重要挑战。近年来，计算方法已得到广泛探索且准确性不断提高。然而，由于临床前模型与患者之间存在较大差异，预测方法的临床应用仍处于起步阶段。我们提出了一种新颖的解缠合成转移网络（DiSyn）用于药物反应预测，该网络专门为从临床前模型到临床患者的迁移学习而设计。DiSyn使用域分离网络（DSN）来解缠与药物反应相关的特征，采用数据合成技术增加样本量，并进行迭代训练以实现更好的特征解缠。DiSyn在大规模未标记的癌症样本上进行预训练，并通过三个数据集进行验证，即癌症基因组图谱（TCGA）、影像和分子分析2预测治疗反应系列研究（I-SPY2）以及诺华生物医学研究所患者来源异种移植百科全书（NIBR PDXE），在癌症患者和小鼠上与现有最先进方法相比具有竞争力。此外，将DiSyn应用于数千名乳腺癌患者显示了药物反应的异质性，并证明了其在生物标志物发现和药物联合预测中的潜在价值。
