An AI-powered cloud biofoundry for autonomous biological research

Chen, J.; Volk, M.; Shafaei, S.; Tan, S.-I.; Upadhyay, V.; Singh, N.; Zhong, X.; Arneson, K.; He, W.; Wang, C.; Lu, J.; Sharma, A.; McLaughlin, J.; Berry, M.; Harmon, S.; Reyes, S.; Heintz, G.; Zhao, H.

doi:10.64898/2026.09.30.750244

bioRxiv · 10.64898/2026.09.30.750244

An AI-powered cloud biofoundry for autonomous biological research

Chen, J.·Volk, M.·Shafaei, S.·Tan, S.-I.·Upadhyay, V.·Singh, N.·Zhong, X.·Arneson, K.·He, W.·Wang, C.·Lu, J.·Sharma, A.·McLaughlin, J.·Berry, M.·Harmon, S.·Reyes, S.·Heintz, G.·Zhao, H.

View original source ↗Export metadata ↓

Abstract

Autonomous experimentation, where an automated system designs, performs, analyzes, and iteratively improves experiments with minimal human intervention represents a transformative scientific research paradigm. However, it remains hampered by the disconnect between computational design and experimental execution. Here we present iCloudBiofoundry, a cloud-accessible, scalable, and self-evolving platform that bridges this divide. A scientific multi-agent system, iBioGenie, plans research workflows by converting natural language research objectives into testable hypotheses and experimentally grounded protocols using literature, databases, and computational tools. A physical AI layer, BiofoundryAI, translates them into executable workflows that run autonomously on distributed robotic biofoundries, and collects the data for iterative design. We demonstrate the end-to-end capabilities of iCloudBiofoundry across three representative case studies spanning enzyme retrieval, protein engineering, and metabolic engineering. By integrating agentic AI with physical AI, iCloudBiofoundry provides a cloud accessible platform that unifies computational design and robotic execution, enabling autonomous biological research.

Explore related subjects

synthetic biology Preprint

Keep this discovery

Explore connections, maps & timelines

BibTeX RIS

Chen, J., Volk, M., Shafaei, S., Tan, S.-I., Upadhyay, V., Singh, N., Zhong, X., Arneson, K., He, W., Wang, C., Lu, J., Sharma, A., McLaughlin, J., Berry, M., Harmon, S., Reyes, S., Heintz, G., Zhao, H.. 2026-10-01. An AI-powered cloud biofoundry for autonomous biological research. https://doi.org/10.64898/2026.09.30.750244

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

KEEP EXPLORING

Related preprints

bioRxiv2026

Heterologous engineering of receptors using OrthoRep (HERO) for directed evolution of GPCRs in yeast

Engineering G protein-coupled receptors (GPCRs) for biosensing applications remains challenging due to structural and functional constraints when such proteins are expressed in a heterologous host. OrthoRep offers the continuous accumulation and selection of signal-enhancing mutations in yeast, yet it has not been applied to GPCR evolution. We apply OrthoRep-driven mutagenesis to evolve opioid GPCRs and improve yeast-based biosensors: first, we express the human -opioid receptor (OPRM1) on the OrthoRep p1 plasmid and couple ligand activation to growth. Serial cell passaging of the biosensor generated functionally diverse mutants. However, mutations that decouple receptor activation from selection arose over longer passaging campaigns, halting evolution. We resolve this issue using a site-specific recombinase that re-introduces evolved variants onto the p1 landing pad of an unmutated biosensor, allowing continued selection. This led to an ~18-fold improvement in sensitivity of a mutant OPRM1 over wt-OPRM1. Additional polymerases were added to the platform, broadening the mutational profiles available. Assembling these components forms the platform we call HERO (Heterologous Engineering of Receptors using OrthoRep). Lastly, we deploy HERO using automation to improve the human {delta}-opioid receptor's weak response to an agonist by ~40-fold. Sensitivity also improved for a structurally dissimilar ligand assayed on the same evolved variants.

synthetic biology↗

bioRxiv2026

Design-Evolution Synergy Enables New-to-Nature Enzyme Chemistry

Directed evolution and machine-learning-assisted evolution have transformed biocatalysis by enabling rapid optimisation of catalytic performance within compatible protein scaffolds. In parallel, advances in deep-learning-driven de novo protein design have expanded accessible protein architectural space, enabling the generation of functional catalysts for increasingly challenging transformations. We herein report a synergistic design-evolution strategy to encode new-to-nature regio- and enantioselective C-H amination reactions using engineered de novo haemproteins to synthesise chiral piperidines, a privileged pharmacophore in drug discovery. By integrating motif scaffolding, computational re-design, and directed evolution, we demonstrate de novo enzyme design can enable challenging, high-energy-barrier enzyme chemistry with programmable regio- and enantioselectivity, high catalytic efficiency, excellent enzyme stability, and scaffold diversity.

synthetic biology↗

bioRxiv2026

Rational mRNA Structure -guided Attenuation Enables Embryo-safe in-ovo NDV Vaccination and Protection

Newcastle disease virus (NDV) continues to cause major economic losses in poultry, driving many recent virulent outbreaks. Maternally derived antibodies (MDA) can interfere with the development of active immunity following vaccination in young chicks. NDV vaccine strains that are safe for day-old chicks are not safe for administration to embryos. Here, we combined a computationally guided attenuation strategy with an in-ovo vaccination and challenge study to develop and evaluate an embryo-safe NDV vaccine candidate. Using a large NDV sequence compendium, we applied a local RNA folding energy based algorithm to identify folding selected clusters within the NDV fusion protein; we introduced targeted synonymous substitutions within the first ~900 nucleotides to modulate local RNA structure while preserving the encoded protein sequence. The recombinant attenuated variant was propagated in embryonated chicken eggs to generate vaccine stocks for in-ovo vaccination. After 18 days of embryonation, the synthetic variants were well tolerated, achieving more than 97% hatchability, with no pre-challenge morbidity or mortality, while unvaccinated challenge controls showed complete mortality. Together, these data support a model in which structure-aware synonymous modifications can yield an embryo-safe NDV backbone suitable for in-ovo delivery, with protective efficacy exhibiting a clear dose window under high MDA conditions.

synthetic biology↗