<ul><li>De novo molecular design has extensive applications in drug discovery and materials science.</li><li>Efficient molecular generation and screening methods are essential for accelerating drug discovery and reducing costs.</li><li>Direct Preference Optimization (DPO) is adopted from NLP to optimize molecular properties by maximizing the likelihood difference between high- and low-quality molecules.</li><li>The proposed method achieved excellent scores on the GuacaMol Benchmark and demonstrated practical efficacy in target protein binding experiments.</li></ul>

De Novo Molecular Design Enabled by Direct Preference Optimization and Curriculum Learning

Discover more