Papers for
synthetic biology engineers
Papers whose findings have a practical use for this group, as judged from the abstract. Open a paper to read what it means in practice.
Amortized approach improves thompson sampling for design simulators
Amortized Thompson Sampling and Efficient Information-Directed Sampling for Simulator-Based Design
Abstract: Thompson sampling is a widely used strategy for sequential decision-making under uncertainty, offering a principled way to balance exploration and exploitation. This strategy involves maximizing a target objective under a single sample drawn from the current belief over unknown quantities. Conventionally, this optimization is performed once the belief has been inferred from data, and it becomes computationally burdensome when many Thompson samples are required, especially in continuous action spaces. In this work, we introduce an approach that amortizes this process ahead of time, before any data is collected, so that an approximation of the full Thompson sampling distribution is available immediately once observations arrive. We employ this approach to solve the multi-round setting, involving sequential data acquisition and Thompson-sample recommendation across rounds. Beyond accelerating Thompson sampling, our approach enables efficient estimation of expected information gain about the optimal action. This can be used to select more informative Thompson samples or to obtain maximally informative designs with optimization. Combining this estimate of expected information gain with immediate regret supports information-directed sampling (IDS), which can outperform Thompson sampling by explicitly balancing these two quantities. We demonstrate our approach on two simulator-based design problems in synthetic biology, where the simulators have intractable likelihoods.
Encoding information on DNA using enzyme-created label patterns
Representing Information on DNA using Patterns Induced by Enzymatic Labeling
Abstract: Enzymatic DNA labeling is a powerful tool with applications in biochemistry, molecular biology, biotechnology, medical science, and genomic research. This paper contributes to the evolving field of DNA-based data storage by presenting a formal framework for modeling DNA labeling in strings, specifically tailored for data storage purposes. Our approach involves a known DNA molecule as a template for labeling, employing patterns induced by a set of designed labels to represent information. One hypothetical implementation can use CRISPR-Cas9 and gRNA reagents for labeling. Various aspects of the general labeling channel, including fixed-length labels, are explored, and upper bounds on the maximum size of the corresponding codes are given. The study includes the development of an efficient encoder-decoder pair that is proven to be optimal in terms of maximum code size under specific conditions. The codewords for this framework are codesets, i.e., each codeword is a collection of a few labels. Of special interest are codes whose codesets contain fixed-length labels. Their construction and analysis are tied to de Bruijn sequences and constrained coding.
Tango improves RNA design by combining shape and pairing rules
TANGO: RNA Topology and Geometry Co-Design
Abstract: Designing RNA sequences that satisfy target tertiary-structure objectives is an important problem in RNA engineering, with broad applications in synthetic biology and therapeutics. Existing 3D RNA design methods have made substantial progress, but they largely treat the target fold as a geometry-only objective. This is incomplete for RNA, whose functional folds are specified not only by tertiary geometry but also by secondary base-pairing topology. We therefore formulate RNA inverse design as a topology-and-geometry co-design problem and propose TANGO, a multi-objective multi-agent reinforcement learning framework for this task. TANGO adopts a staged curriculum: it first learns a topology-aware policy from secondary-structure targets, then transfers this policy to tertiary-structure targets to train a general co-design model, and finally applies frontier-guided fine-tuning to refine target-specific trade-offs among secondary-structure fidelity, tertiary-structure fidelity, and sequence diversity. Experiments show that TANGO generates diverse and novel designs, improving tertiary- and secondary-structure performance by 18.3% and 52.7%, respectively, over the strongest baseline.
Agentic program search finds DNA design methods that generalize well
AutoNovo: Agentic Program Search Discovers Transferable Nucleic Acid Design Algorithms
Abstract: In-silico optimization of nucleic acids relies on predictive oracles that imperfectly capture biological function, so sequences optimized against one model may exploit model-specific artifacts and fail to generalize to independent models. Recent studies have shown that not all designers generalize equally well to independent models. In this work, we use agentic program search to iteratively propose, execute, evaluate, and revise code for nucleic-acid designers. We describe the successful strategies used to prompt the search. AutoNovo designers achieved the best observed mean among the evaluated methods on 3/3 DNA-design tasks in terms of in-silico performance, and 6/6 transfer tasks in terms of independent models. The designers come from a family of discovered nucleic acid designers rather than a single universal best designer. We plan to release the resulting designers. These results are the first steps in creating nucleic acid designers that maximize cross-model generalization, and thus improving the odds that in-silico designed sequences reflect real biology.
Continuous variational synthesis enables diverse designed dna production
Continuous Variational Synthesis
Abstract: Biological machine learning was long bottlenecked by the ability to synthesize designed DNA. Variational synthesis models control chemical reactions to physically manufacture quadrillions of designed sequences in DNA. However, training these generative models is challenging: constraints on chemical synthesis can force many parameters into a discrete space, limiting the ability to pre-train and fine-tune. In this article we train ``free'' variational synthesis models using stochastic gradient descent in continuous space, and then discretize with post-training quantization to impose hardware and wetware constraints. This enables variational synthesis models to satisfy stringent reward criteria, while still synthesizing diverse designs, achieving a strictly dominating quality-diversity Pareto frontier. We demonstrate by training variational synthesis models of enzymes, peptides, antibody CDRH3s, and regulatory DNA elements. In silico performance is maintained in vitro.