LLMDTA: Improving Cold-Start Prediction in Drug-Target Affinity With Biological LLM

Drug-target affinity (DTA) prediction plays a crucial role in accelerating the drug development process. Although deep learning-based models achieve strong performance in benchmark datasets, their predictive accuracy declines sharply in cold-start scenarios, i.e., when encountering drugs or proteins absent from the training set. This limitation arises from the restricted scale of training datasets, leading to features learned by end-to-end DTA models lacking sufficient generalization. To address this challenge, we propose a novel approach named LLMDTA (Large Language Model for DTA), leveraging the power of biological language models to tackle the cold-start problem in DTA prediction. Specifically, we use Mol2Vec, a molecular pre-training model, and ESM2, a protein language model, as feature extractors. To seamlessly integrate these pre-trained features into downstream DTA prediction, we employ a 1D-CNN-based encoder to extract independent molecular features. In addition, a bilinear attention module is designed to capture interactive molecular features between drugs and proteins. Finally, independent and interactive features are fused to predict binding affinities. Experimental results in three benchmark datasets demonstrate that LLMDTA consistently outperforms state-of-the-art baselines in both warm-start and cold-start scenarios, with notable improvements in novel-protein and novel-pair settings. Furthermore, a case study involving the epidermal growth factor receptor illustrates the ability of LLMDTA to identify novel binding affinities between previously unseen drugs and the target protein, validated through molecular docking. In general, LLMDTA represents a promising and practical tool for advancing DTA prediction in real-world applications.