PhAME: Phenotype-Aware Molecular Editing via Latent Diffusion
For drug discovery researchers, PhAME provides a method to precisely control the tradeoff between phenotype conditioning and structural similarity, enabling more effective molecular optimization.
PhAME introduces a latent diffusion framework for small-molecule drug discovery that simultaneously optimizes toward desired phenotypic signatures while maintaining structural similarity to a known hit, achieving state-of-the-art results in docking score optimization and multimodal phenotypic generation with high chemical validity and novelty.
Small-molecule drug discovery requires simultaneous optimization of numerous properties of candidate molecules. These properties can be investigated through the analysis of high-dimensional biological signatures, such as cell morphology and transcriptomic perturbations, which provide a rich perspective on the underlying biological mechanisms. However, existing generative methods, which use those signatures for optimization, fail to meet two key requirements: providing precise guidance toward desired phenotypic signatures while maintaining structural proximity to a known hit. We introduce PhAME (Phenotype-Aware Molecular Editing), a latent diffusion framework that overcomes this challenge by recasting molecular optimization as editing in the latent space of a pretrained graph-based VAE. Our central contribution is a compositional classifier-free guidance scheme with two independent scales, one for the phenotype-conditioning and one for similarity to the seed structure, allowing practitioners to control the tradeoff between these two objectives. Empirical evaluations across diverse benchmarks, including docking score optimization and multimodal phenotypic generation, demonstrate that PhAME achieves state-of-the-art results while maintaining high chemical validity and novelty.