PrefixMol: Target- and Chemistry-aware Molecule Design via Prefix Embedding
This work addresses the challenge of customized molecule design for drug discovery, though it is incremental by building on multi-task learning from NLP.
The authors tackled the problem of designing molecules that simultaneously satisfy target binding and chemical property constraints by introducing PrefixMol, a unified generative model using prefix embeddings. Their model outperformed previous structure-based drug design methods and demonstrated controllability in single- and multi-conditional generation.
Is there a unified model for generating molecules considering different conditions, such as binding pockets and chemical properties? Although target-aware generative models have made significant advances in drug design, they do not consider chemistry conditions and cannot guarantee the desired chemical properties. Unfortunately, merging the target-aware and chemical-aware models into a unified model to meet customized requirements may lead to the problem of negative transfer. Inspired by the success of multi-task learning in the NLP area, we use prefix embeddings to provide a novel generative model that considers both the targeted pocket's circumstances and a variety of chemical properties. All conditional information is represented as learnable features, which the generative model subsequently employs as a contextual prompt. Experiments show that our model exhibits good controllability in both single and multi-conditional molecular generation. The controllability enables us to outperform previous structure-based drug design methods. More interestingly, we open up the attention mechanism and reveal coupling relationships between conditions, providing guidance for multi-conditional molecule generation.