Scalable Inference-Time Steering in Molecular Design with Multimodal Meta Flow Maps

Biological design problems naturally have continuous (e.g. molecular structures), discrete (e.g. DNA residue types) and often both modalities (e.g. protein structure-sequence co-design). Diffusion and CTMC-based methods have been developed for multimodal generation, and, for cross-modal tasks, the two are typically combined. However, it remains challenging to adapt these methods at inference-time to fulfill design constraints. Recent developments of one-shot samplers such as Meta Flow Maps (MFM) have demonstrated high controllability for image generation, showcasing the power of inference-time steering with accurately estimated reward gradients. Here, we adapt Meta Flow Maps to biological domains, developing an MFM framework for both continuous (molMFM) and discrete modalities (dMFM). In latent continuous molecular generation, molMFM-SS achieves the best median absolute error across six QM9 property-targeting tasks among the compared methods, and molMFM improves over prior inference-time steering methods on overlapping molecular benchmarks. In the discrete domain, we develop the discrete analogue to MFM, enabling us to generalize it to the multimodal domain (multiMFM). We demonstrate dMFM by designing DNA sequences with a target mechanical property. In both cases, our steering algorithms achieve high accuracy with a single trained backbone, outperforming fine-tuning methods adapted for task-specific ends.