Joint protein, mRNA and DNA sequence design and optimization with nucleotide-level Potts models
- 1Research Group Biomolecular Design, Max Planck Institute of Biochemistry, Martinsried, Germany; Gene Center and Department of Biochemistry, LMU Munich, Munich,
Abstract
Protein design typically generates amino acid sequences first and then translates them into DNA post-hoc limiting control over the nucleotide sequence via codon choice at design time. We introduce NuCaliby, a structure-conditioned model that jointly designs amino acid, mRNA, and DNA sequences of a protein at nucleotide resolution. NuCaliby predicts a Potts model over a nucleotide graph, trained using amino acid supervision by marginalizing over synonymous codons. It preserves residue-level designability on par with the original Caliby model. Its energy-based formulation supports composable inference-time guidance from sequence-level objectives through proposal construction and candidate acceptance, allowing the incorporation of biological proxies into the coding nucleotide sequence. Under organism-specific tRNA adaptation guidance, NuCaliby improves adaptation to host tRNA pools beyond synonymous sequence space, trading-off self-consistency. NuCaliby also embeds specified RNA motif sequences directly into coding sequences, avoiding the combinatorial growth required for the same task at the amino-acid level. In wet lab experiments, NuCaliby produces expressible and soluble proteins on par with state of the art methods, while enabling more complex nucleotide-level control and optimization. Together, these results extend protein design beyond the amino acid level, enabling joint optimization across the central dogma of molecular biology. The code and model weights are available here: https://github.com/blazejba/NuCaliby
Related
- SimpleDesign: A Joint Model for Protein Sequence and Structure Codesign
- Beyond Sequence Optimization in Enzyme Engineering: Protein Maturation and Operational Stability
- Generative AI for controllable protein sequence design: A survey
- EquiDesign: a versatile computational framework for de novo protein sequence design.
- A Generative Neuro‐Symbolic AI for Protein Sequence Design
BibTeX
@misc{banaszewski2026joint,
title = {{Joint protein, mRNA and DNA sequence design and optimization with nucleotide-level Potts models}},
author = {B. Banaszewski and L. J. Dornfeld and D. Chen and K. Borgwardt and L. F. Milles},
howpublished = {bioRxiv},
year = {2026},
month = oct,
doi = {10.64898/2026.10.05.756407},
url = {https://www.biorxiv.org/content/10.64898/2026.10.05.756407v1},
note = {CC BY},
}
RIS
TY - UNPB
TI - Joint protein, mRNA and DNA sequence design and optimization with nucleotide-level Potts models
AU - B. Banaszewski
AU - L. J. Dornfeld
AU - D. Chen
AU - K. Borgwardt
AU - L. F. Milles
PY - 2026
DA - 2026/10/05
PB - bioRxiv
DO - 10.64898/2026.10.05.756407
UR - https://www.biorxiv.org/content/10.64898/2026.10.05.756407v1
AB - Protein design typically generates amino acid sequences first and then translates them into DNA post-hoc limiting control over the nucleotide sequence via codon choice at design time. We introduce NuCaliby, a structure-conditioned model that jointly designs amino acid, mRNA, and DNA sequences of a protein at nucleotide resolution. NuCaliby predicts a Potts model over a nucleotide graph, trained using amino acid supervision by marginalizing over synonymous codons. It preserves residue-level designability on par with the original Caliby model. Its energy-based formulation supports composable inference-time guidance from sequence-level objectives through proposal construction and candidate acceptance, allowing the incorporation of biological proxies into the coding nucleotide sequence. Under organism-specific tRNA adaptation guidance, NuCaliby improves adaptation to host tRNA pools beyond synonymous sequence space, trading-off self-consistency. NuCaliby also embeds specified RNA motif sequences directly into coding sequences, avoiding the combinatorial growth required for the same task at the amino-acid level. In wet lab experiments, NuCaliby produces expressible and soluble proteins on par with state of the art methods, while enabling more complex nucleotide-level control and optimization. Together, these results extend protein design beyond the amino acid level, enabling joint optimization across the central dogma of molecular biology. The code and model weights are available here: https://github.com/blazejba/NuCaliby
ER -