Prediction of protein-ligand binding affinity (PLA) is a crucial problem in drug discovery. Recently, deep learning (DL) models have emerged as a promising and computationally efficient paradigm for the PLA prediction task, enabling rapid and scalable analysis while circumventing the time-consuming nature of experimental assays and the rigidity of conventional scoring functions. However, a significant domain knowledge gap often prohibits the effective integration of biological and computational insights, making it challenging to design deep learning models that comprehensively capture all relevant aspects. Training such models remains a complex undertaking involving multiple facets, including data heterogeneity, model interpretability, and biological plausibility. This review explores the key considerations for training DL models in PLA prediction task, including the choice of datasets, data processing techniques, model architecture design, model training strategies, and evaluation methodologies. Additionally, we discuss the potential applications of PLA prediction in traditional drug discovery and emerging areas, along with the challenges that currently hinder the optimal utilization of deep learning models in this field. This review aims to bridge the gap between computational biology and deep learning by providing a comprehensive guide for researchers interested in leveraging deep learning for PLA prediction.

Traditional Chinese medicine (TCM) prescription is the most critical form of TCM treatment, and uncovering the complex nonlinear relationship between symptoms and TCM is of great significance for clinical practice and assisting physicians in diagnosis and treatment. Although there have been some studies on TCM prescription generation, these studies consider a single factor and directly model the symptom-prescription generation problem mainly based on symptom descriptions, lacking guidance from TCM knowledge. To this end, we propose a RoBERTa and Knowledge Enhancement model for Prescription Generation of Traditional Chinese Medicine (RoKEPG). RoKEPG is firstly pre-trained by our constructed TCM corpus, followed by fine-tuning the pre-trained model, and the model is guided to generate TCM prescriptions by introducing four classes of knowledge of TCM through the attention mask matrix. Experimental results on the publicly available TCM prescription dataset show that RoKEPG improves the F1metric by about 2% over the baseline model with the best results.

The core of quantitative investment lies in predicting future trends in stock prices. The future trend of a stock is closely related to the industry it belongs to and its relationship with other stocks. Although some research has focused on stock trend prediction in recent years, most studies have only considered the stock’s own time series feature, neglecting the spatial features between stocks. Some research has incorporated spatial information, but typically only considered predefined static relationships. At the same time, capturing dynamic spatial information in the market has been a long-standing challenge. Thus, we propose a spatio-temporal model, Finformer, in order to go beyond traditional time series models. We designed a sparse static-dynamic transformer to capture dynamic market spatial information as it changes over time and combined predefined relationships to extract highly correlated spatial features in the stock market. To effectively integrate spatial and temporal features, we introduced an adaptive spatio-temporal fusion module that dynamically fuses spatio-temporal features based on market conditions at different periods. Experiments on two real-world stock market datasets show that our proposed model outperforms the state-of-the-art baselines in the signal-based and portfolio-based metrics, which are widely concerned in the financial field. Ablation study and hyper-parameter study further reveal the effectiveness of each module in the model and the impact of hyper-parameters. The code will be made publicly available.1