Search bioRxiv⌕ Search
Home/Archive/bioRxiv

bioRxiv · 10.1101/2024.06.20.599727

Deep generative models generate mRNA sequences with enhanced translation capacity and stability

Zhang, H.·Liu, H.·Xu, Y.·Liu, Y.·Wang, J.·Qin, Y.·Wang, H.·Ma, L.·Xun, Z.·Lu, T. K.·Cao, J.
View original source ↗Export metadata ↓

Abstract

Despite the tremendous success of messenger RNA (mRNA) COVID-19 vaccines, the extension of this modality to a broader spectrum of diseases necessitates substantial enhancements, particularly in the design of mRNAs with elevated expression levels and extended durability. Here we present GEMORNA, a deep generative model designed to generate novel mRNA coding sequences (CDSs) and untranslated regions (UTRs) with superior translation capacity, comparable to the sophisticated task of language translation and free-form poetry composition with accurate grammar and semantics. Our AI model was trained on an extensive collection of RNA sequences from diverse families, further enhanced with labeled data to refine its performance. Remarkably, we demonstrate that our AI-generated mRNAs exhibited 8.2-fold and 15.9-fold increases in firefly luciferase expression compared to benchmark mRNAs in two different cell types. Additionally, Our AI- designed COVID-19 mRNA vaccine elicited a 4-fold increase in anti-COVID antibody titer in mice relative to BNT162b2. Furthermore, GEMORNAs versatility extends to circular mRNA design, which we facilitated a 27-fold increase in human erythropoietin protein expression in vivo than a systematically optimized benchmark sequence. We also created circular mRNAs with substantial improvements in expression levels, durability and anti-tumor cell cytotoxicity in mRNA-transduced CAR-T cells compared with an experimentally validated benchmark. In summary, GEMORNA generates novel mRNA sequences with significant performance improvements and has the potential to enable a wide range of therapeutic and vaccine applications.

Source connections

Explore related subjects

synthetic biologyPreprint

Keep this discovery

Explore connections, maps & timelines

BibTeXRIS

Zhang, H., Liu, H., Xu, Y., Liu, Y., Wang, J., Qin, Y., Wang, H., Ma, L., Xun, Z., Lu, T. K., Cao, J.. 2024-06-20. Deep generative models generate mRNA sequences with enhanced translation capacity and stability. https://doi.org/10.1101/2024.06.20.599727

Cite the original work for its findings. Save a collection to share your selection of sources.

KEEP EXPLORING

Related preprints

bioRxiv2026

Associative Learning and Memory Erasure in a Synthetic Multicellular System

Learning is a basic form of adaptation that organisms display from neural systems to single cells. In associative learning, the pairing of two stimuli lets one of them evoke the response to the other. Engineering this behavior in a living cell is difficult, because coincidence detection, memory, and conditional readout must be wired into a single regulatory network. Here we build a consortium of five E. coli strains that distributes the operations of associative learning and communicates through one diffusible quorum-sensing signal. The same signal acts as the memory trace. One strain detects the coincidence of the two inputs, a second maintains the memory through positive feedback in the shared medium, a third reads it out on the conditioned stimulus, a fourth reports the unconditioned response, and a fifth erases the memory on command. We show experimentally that the assembled consortium learns the association, since a stimulus that is silent before training evokes a strong response after pairing. Memory is retained through a medium exchange in which both stimuli are removed, and then the conditioned stimulus alone evokes the response. The reporter is not produced without its input. An erase command returns the response to the background. A population model of the consortium accounts for the sequence of responses and gives design rules for writing, retention, and erasure, and a trade-off in storing memory in a shared extracellular signal. Distributing the operations over strains makes each of them separately tunable and testable and provides a route to microbial communities that learn from their history.

synthetic biology↗
bioRxiv2026

Self-organized criticality in a mammalian RNA-interference circuit

Living systems have been argued to operate near critical points, but their relevance at the cellular level is poorly understood. Critical states allow for a high sensitivity to external inputs and maximal information transfer and display fluctuations at all scales. Critical points are very special, and require the fine tuning of a control parameter, which is hard to reconcile with the robustness of living cells. Self-organized criticality (SOC) proposes that feedback, rather than tuning, brings a system to its critical point. Here we show that RNA interference, in which messenger RNAs compete for shared silencing machinery and so queue for service, together with negative feedback gives rise to SOC in mammalian cells. In a synthetic circuit, a protein repressor whose mRNA competes with the mRNA of a fluorescent reporter that it represses senses the congestion of the queue, closing the feedback loop. Theory and stochastic simulations show that the loop holds the queue near its critical point despite changes in its parameters, and that expression becomes intermittent, with scale-free bursts. Measurements in human cell lines show the predicted power-law distributions of single-cell fluorescence. RNA interference could thus support engineered SOC in animal cells and may also contribute to SOC in natural systems.

synthetic biology↗
bioRxiv2026

An anaerobic cell-free protein synthesis formulation for the in vitro study of oxygen sensitive proteins

Anaerobic microbes harbor unique enzymes and metabolic pathways with potential biotechnological applications, yet these microbes remain difficult to study and engineer. Research is limited by the labor-intensive workflows required to maintain anoxic environments and the lack of genetic tools available for non-model anaerobes. Here, we present an anaerobic cell-free protein synthesis (CFPS) platform for the in vitro study of oxygen-sensitive enzymes. This study establishes two methods for conducting anaerobic CFPS, achieving an anoxic environment by (1) sparging with inert gas or (2) lyophilizing to remove oxygenated water. We show the functionality of our anaerobic CFPS formulation by producing oxygen-independent fluorescent protein reporters and a [4Fe-4S] cluster pyruvate:ferredoxin oxidoreductase (PFOR) with a specific activity of 5.2 {+/-} 0.3 x 10-4 U/{micro}L cell-free extract. This highly modular platform will allow study of diverse oxygen-sensitive proteins and requires only minor modifications to commonly used CFPS workflows.

synthetic biology↗