A new test-time search method runs genetic crossover inside a trained generative model by masking the vocabulary to the union of two parents' tokens, improving routing, adversarial prompt, and molecular design generation.
Generative Artificial Intelligence for Navigating Synthesizable Chemical Space
1 Pith paper cite this work. Polarity classification is still indexing.
abstract
We introduce SynFormer, a generative modeling framework designed to efficiently explore and navigate synthesizable chemical space. Unlike traditional molecular generation approaches, we generate synthetic pathways for molecules to ensure that designs are synthetically tractable. By incorporating a scalable transformer architecture and a diffusion module for building block selection, SynFormer surpasses existing models in synthesizable molecular design. We demonstrate SynFormer's effectiveness in two key applications: (1) local chemical space exploration, where the model generates synthesizable analogs of a reference molecule, and (2) global chemical space exploration, where the model aims to identify optimal molecules according to a black-box property prediction oracle. Additionally, we demonstrate the scalability of our approach via the improvement in performance as more computational resources become available. With our code and trained models openly available, we hope that SynFormer will find use across applications in drug discovery and materials science.
fields
cs.NE 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Neural Genetic Search in Discrete Spaces
A new test-time search method runs genetic crossover inside a trained generative model by masking the vocabulary to the union of two parents' tokens, improving routing, adversarial prompt, and molecular design generation.