TransCDR: a deep learning model for enhancing the generalizability of cancer drug response prediction through transfer learning and multimodal data fusion for drug representation
作者: Xiaoqiong Xia, Chaoyu Zhu, Yuqi Shan, Fan Zhong, Lei Liu
分类: q-bio.QM, cs.AI, cs.LG
发布日期: 2023-11-17
备注: 8 figures
🔗 代码/项目: GITHUB
💡 一句话要点
提出TransCDR以解决癌症药物反应预测的泛化问题
🎯 匹配领域: 支柱九:具身大模型 (Embodied Foundation Models)
关键词: 癌症药物反应预测 迁移学习 多模态融合 自注意力机制 精准医学
📋 核心要点
- 现有模型在药物反应预测中存在数据模态不足和泛化能力差的问题,影响了预测的准确性和可靠性。
- TransCDR通过迁移学习和自注意力机制融合多模态特征,旨在提升药物反应预测的泛化能力。
- 实验结果显示,TransCDR在新化合物和细胞系上的泛化能力优于8个先进模型,并在GDSC数据集上表现出色。
📝 摘要(中文)
准确且稳健的药物反应预测在精准医学中至关重要。尽管已有多种模型利用药物和癌细胞系的表征来预测癌症药物反应,但其性能仍可通过解决数据模态不足、融合算法次优和新药或细胞系的泛化能力差等问题来提升。我们提出了TransCDR,该模型通过迁移学习学习药物表征,并通过自注意力机制融合药物和细胞系的多模态特征,以预测药物在细胞系上的IC50值或敏感状态。TransCDR在对新化合物骨架和细胞系簇的泛化能力上进行了系统评估,表现优于8个最先进的模型,并在多种场景下超越了5个从头训练药物编码器的变体。TransCDR在GDSC数据集上训练,且在外部测试集CCLE上表现出强大的预测性能。
🔬 方法详解
问题定义:本论文旨在解决癌症药物反应预测中存在的泛化能力不足的问题,现有方法在面对新药物和细胞系时表现不佳,导致预测结果的可靠性降低。
核心思路:TransCDR通过迁移学习来学习药物的表征,并利用自注意力机制融合多模态特征,以提高模型对新数据的适应能力和预测准确性。
技术框架:TransCDR的整体架构包括数据预处理、特征提取、迁移学习模块和自注意力融合模块。首先,模型从多种数据源提取特征,然后通过迁移学习优化药物表征,最后利用自注意力机制进行特征融合以进行预测。
关键创新:TransCDR的主要创新在于首次系统评估了药物反应预测模型对新化合物骨架和细胞系簇的泛化能力,且其自注意力机制显著提升了预测性能。
关键设计:模型采用Extended Connectivity Fingerprint和基因突变作为关键特征,损失函数设计为适应药物反应预测的特定需求,网络结构则结合了RNN和自注意力机制以增强学习能力。
📊 实验亮点
TransCDR在新化合物和细胞系上的泛化能力显著优于8个最先进的模型,且在GDSC数据集上训练后,在外部测试集CCLE上表现出强大的预测性能,显示出其在药物反应预测中的有效性和可靠性。
🎯 应用场景
TransCDR在癌症药物反应预测领域具有广泛的应用潜力,能够为精准医学提供支持,帮助医生制定个性化的治疗方案。未来,该模型可扩展至其他疾病的药物反应预测,推动药物研发和临床应用的进步。
📄 摘要(原文)
Accurate and robust drug response prediction is of utmost importance in precision medicine. Although many models have been developed to utilize the representations of drugs and cancer cell lines for predicting cancer drug responses (CDR), their performances can be improved by addressing issues such as insufficient data modality, suboptimal fusion algorithms, and poor generalizability for novel drugs or cell lines. We introduce TransCDR, which uses transfer learning to learn drug representations and fuses multi-modality features of drugs and cell lines by a self-attention mechanism, to predict the IC50 values or sensitive states of drugs on cell lines. We are the first to systematically evaluate the generalization of the CDR prediction model to novel (i.e., never-before-seen) compound scaffolds and cell line clusters. TransCDR shows better generalizability than 8 state-of-the-art models. TransCDR outperforms its 5 variants that train drug encoders (i.e., RNN and AttentiveFP) from scratch under various scenarios. The most critical contributors among multiple drug notations and omics profiles are Extended Connectivity Fingerprint and genetic mutation. Additionally, the attention-based fusion module further enhances the predictive performance of TransCDR. TransCDR, trained on the GDSC dataset, demonstrates strong predictive performance on the external testing set CCLE. It is also utilized to predict missing CDRs on GDSC. Moreover, we investigate the biological mechanisms underlying drug response by classifying 7,675 patients from TCGA into drug-sensitive or drug-resistant groups, followed by a Gene Set Enrichment Analysis. TransCDR emerges as a potent tool with significant potential in drug response prediction. The source code and data can be accessed at https://github.com/XiaoqiongXia/TransCDR.