Deep learning-based compound-protein interaction (CPI) prediction models are promising in the field of molecular biology, particularly for facilitating the drug discovery process. In practical applications, CPI models should achieve a high generalization performance, quantify prediction confidence, and ensure explainability. Here, we propose ChemGLaM, a chemical genomics language model for reliable and explainable CPI predictions, by addressing these three crucial aspects. ChemGLaM integrates independently pre-trained chemical and protein language models through an interaction block with a cross-attention mechanism, achieving state-of-the-art performance in predicting novel CPIs. Incorporating uncertainty estimation and attention visualization enables ChemGLaM to enhance the success rate of virtual screening and to provide molecular insights into CPIs. Furthermore, we demonstrate its practical applicability by constructing a public database for large-scale CPI predictions and enabling drug/target exploration for candidate treatment of amyotrophic lateral sclerosis (ALS). ChemGLaM represents a significant step toward overcoming the challenges of AI-driven drug discovery and addressing unmet medical needs.