Uncertainty Aware Quality-Diversity Optimization For Offline Biological Sequence Design
cs.LG
Submitted: 2026-10-31
Updated: 2026-10-31
License: http://creativecommons.org/licenses/by/4.0/
The gist: Designing sequences such as nucleic acids and proteins with desired properties is a fundamental challenge in biology.
Abstract
Designing sequences such as nucleic acids and proteins with desired properties is a fundamental challenge in biology. Due to the vast, discrete nature of sequence spaces and the high cost of experimental evaluation, offline computational sequence design plays a crucial role in proposing novel sequences before costly wet-lab validation. In practice, it is also essential that proposed designs are diverse to increase the likelihood of downstream experimental success. This motivates methods that balance performance, novelty, and diversity, whilst mitigating against uncertainty inherent to offline optimization. Quality-Diversity optimization (QD) can discover diverse, high-performing solutions, making it well suited to this problem, but its elitist nature makes reliable exploration under uncertainty challenging. To address this, we introduce Prior-guided Offline MAP-Elites (POME), an uncertainty-aware QD framework explicitly adapted to the offline regime. Our method leverages foundation models as priors to guide search toward biologically plausible regions and enable robust exploration under uncertainty. Across three sequence design tasks, POME consistently improves both performance and diversity over prior offline QD methods, and achieves the most reliable balance compared to offline MBO baselines, obtaining the best performance on two tasks and the second-best on the third, while maintaining high diversity and novelty.
Sources
- Deep Ensembles: A Loss Landscape Perspective
- BOP-Elites, a Bayesian Optimisation Approach to Quality Diversity Search with Black-Box descriptor functions
- Offline Model-Based Optimization: Comprehensive Review
- Illuminating search spaces by mapping elites
- HyenaDNA: Long-Range Genomic Sequence Modeling at Single Nucleotide Resolution
- Intriguing properties of neural networks
- The reparameterization trick for acquisition functions
- Helix-mRNA: A Hybrid Foundation Model For Full Sequence mRNA Therapeutics
- Neural Architecture Search with Reinforcement Learning
Related papers
- A Physics-Regulated Neural Framework for Learning 3D Grain Growth Dynamics
- FlexMoE: Learning One-for-All Multi-Budget Expert Pruning for Flexible MoE Deployment
- OptiMind: Improving Small Language Models for Optimization Modeling through Formulation Guidance and Multi-Turn Learning
- Staying in the Sweet Spot: Boost Reasoning Evolution via Responsive Rollout Difficulty Manipulation
- Examining the Impact of Data and Training Methods on Emergent and Subliminal Misalignment
- Rethinking Black-Box On-Policy Distillation: A Rubric-based Analysis