The development of new drugs is both expensive and time-consuming, but SciLifeLab’s Drug Discovery and Development (DDD) platform is working to revolutionize this process. By enhancing early-stage hit identification with DNA-encoded chemical libraries (DECLs) and utilizing machine learning to analyze 4.4 billion in-house DECL compounds, DDD aims to optimize drug discovery pipelines through advanced ML and deep-learning techniques. At SciLifeLab’s Drug Discovery and Development (DDD) platform, we actively support Swedish academic communities in advancing drug discovery projects by providing expertise, infrastructure, and innovative methodologies. Recently, we have received several data-rich projects (from HitGen, USA), each containing up to 2.2 billion molecules with experimental data from DNA-encoded libraries (DEL) for Aurora Kinase, DXS model targets. This influx of high-quality data enables us to develop robust predictive models using machine learning and deep learning techniques. By leveraging these predictive models, we can efficiently screen billions of molecules on the REAL Enamine database—a vast, make-on-demand chemical library containing approximately 2.3 trillion compounds. This approach significantly enhances the hit identification process, allowing us to identify promising drug candidates with greater accuracy and speed.