Predicting drug-target interactions (DTIs) with precision is a crucial challenge in the quest for efficient and cost-effective drug discovery. Existing DTI prediction models often require significant computational resources because of the intricate and exceptionally lengthy protein target sequences. This study introduces MMF-DTI, a lightweight model that uses multimodal fusion, to improve the generalizability of DTI predictions without sacrificing computational efficiency. The MMF-DTI model combines four distinct modalities: molecular sequence, molecular properties, target sequence, and target function description. This approach is noteworthy because it is the first to use natural language-based target function descriptions in predicting DTIs. The effectiveness of MMF-DTI has been confirmed through benchmark data sets, demonstrating its comparable performance in terms of generalizability, especially in scenarios with limited information about the drug or target. Remarkably, MMF-DTI accomplishes this using only half of the parameters and 17% of the VRAM compared with previous state-of-the-art models. This allows it to function even in constrained computational environments. The combination of performance and efficiency highlights the potential of multimodal data fusion in improving the overall applicability of models, providing promising opportunities for future drug discovery endeavors.

中文翻译：

---

基于多模态融合的轻量级模型，用于增强药物-靶点相互作用预测的泛化。


精确预测药物-靶标相互作用 （DTI） 是寻求高效且具有成本效益的药物发现的关键挑战。现有的 DTI 预测模型通常需要大量的计算资源，因为蛋白质靶序列复杂且异常冗长。本研究引入了 MMF-DTI，这是一种使用多模态融合的轻量级模型，可以在不牺牲计算效率的情况下提高 DTI 预测的泛化性。MMF-DTI 模型结合了四种不同的模式：分子序列、分子特性、靶序列和靶功能描述。这种方法值得注意，因为它是第一个使用基于自然语言的目标函数描述来预测 DTI 的方法。MMF-DTI 的有效性已通过基准数据集得到证实，证明了其在泛化性方面的可比性能，尤其是在有关药物或靶点信息有限的情况下。值得注意的是，与以前的先进模型相比，MMF-DTI 仅使用一半的参数和 17% 的 VRAM 就实现了这一目标。这使得它即使在受限的计算环境中也能运行。性能和效率的结合凸显了多模态数据融合在提高模型整体适用性方面的潜力，为未来的药物发现工作提供了有希望的机会。