Wang Meng, Wang Jianmin, Ji Jianxin, Ma Chenjing, Wang Hesong, He Jia, Song Yongzhen, Zhang Xuan, Cao Yong, Dai Yanyan, Hua Menglei, Qin Ruihao, Li Kang, Cao Lei
Department of Biostatistics, Harbin Medical University, Harbin 150081, China.
Department of Integrative Biotechnology, Yonsei University, Incheon 21983, South Korea.
Comput Struct Biotechnol J. 2024 Oct 5;23:3714-3729. doi: 10.1016/j.csbj.2024.10.004. eCollection 2024 Dec.
Identifying novel compound-protein interactions (CPIs) plays a pivotal role in target identification and drug discovery. Although the recent multimodal methods have achieved outstanding advances in CPI prediction, they fail to effectively learn both intra-modality and inter-modality dynamics, which limits their prediction performance. To address the limitation, we propose a novel multimodal tensor fusion CPI prediction framework, named MMTF-CPI, which contains three unimodal learning modules for structure, heterogeneous network and transcriptional profiling modalities, a tensor fusion module and a prediction module. MMTF-CPI is capable of focusing on both intra-modality and inter-modality dynamics with the tensor fusion module. We demonstrated that MMTF-CPI is superior to multiple state-of-the-art multimodal methods across seven datasets. The prediction performance of MMTF-CPI is significantly improved with the tensor fusion module compared to other fusion methods. Moreover, our case studies confirmed the practical value of MMTF-CPI in target identification. Via MMTF-CPI, we also discovered several candidate compounds for the therapy of breast cancer and non-small cell lung cancer.
识别新型化合物 - 蛋白质相互作用（CPI）在靶点识别和药物发现中起着关键作用。尽管最近的多模态方法在CPI预测方面取得了显著进展，但它们未能有效学习模态内和模态间的动态信息，这限制了它们的预测性能。为了解决这一局限性，我们提出了一种新颖的多模态张量融合CPI预测框架，名为MMTF - CPI，它包含用于结构、异质网络和转录谱模态的三个单模态学习模块、一个张量融合模块和一个预测模块。MMTF - CPI能够通过张量融合模块同时关注模态内和模态间的动态信息。我们证明，在七个数据集上，MMTF - CPI优于多种最先进的多模态方法。与其他融合方法相比，张量融合模块显著提高了MMTF - CPI的预测性能。此外，我们的案例研究证实了MMTF - CPI在靶点识别中的实用价值。通过MMTF - CPI，我们还发现了几种用于治疗乳腺癌和非小细胞肺癌的候选化合物。
