20/15 Visioneers and StableBody Technologies Partner to Reduce Expression Failure in Enzyme Production

HEREFORD, PA, UNITED STATES, October 12, 2026 /CourierPR/ -- 20/15 Visioneers and StableBody Technologies have partnered to commercialize a computational tool aimed at reducing the risk of expression failure in industrial enzyme production. This collaboration is particularly significant as expression failure remains one of the most expensive points of failure in enzyme programs, often leading to substantial financial losses.

The new platform, developed by the two companies, assesses the risk of ribosome stalling, codon rarity transitions, co-translational folding bottlenecks, aggregation patches, and proteolysis risk in one comprehensive analysis. It accepts DNA, protein, FASTA, and PDB inputs, is parameterized for major industrial hosts and native sources, and returns component-level diagnostics and prioritized variant designs. Core analyses execute locally, ensuring that the platform does not require calls to paid third-party annotation services.

The platform's solubility module has been calibrated on experimental eSOL solubility data, achieving a held-out split accuracy of 68.4% (95% CI 52.5-80.9%). This accuracy, while useful for triage, is not intended for titer prediction. The sensitivity is 56.5% (36.8-74.4%), the specificity is 86.7% (62.1-96.3%), and the Matthews Correlation Coefficient (MCC) is 0.43 (0.15-0.69).

The platform's performance is based on a small and project-enriched set of 294 experimental eSOL solubility data points, and it has been tested against a collaborator wet-lab set of 38 labeled constructs. The accuracy on this set was 68.4% (95% CI 52.5-80.9%). The companies are clear about the limitations of the platform, stating that the set is small and project-enriched rather than an independent benchmark. The intervals are wide, and sensitivity is only modestly above chance. The co-translational modules have not yet been tested against external wet-lab outcomes. Platform output is pre-synthesis decision support and does not replace experimental expression testing.

The Beta Program, which opens on [START DATE], is limited to [COHORT SIZE] organizations in the first cohort. Participants will submit candidate sequences under written confidentiality terms, receive full platform reports, and work with the joint scientific team on interpretation. In return, they are asked to share expression outcomes, where their agreements permit, so the model can be evaluated against host-matched industrial data. Terms, including sequence ownership and any use of shared outcomes for recalibration, are set out in the participation agreement; reports carry no warranty of expression outcome.

The companies will discuss the technology and the program at Paperless Lab Academy USA 2026, the conference series owned and hosted by 20/15 Visioneers, held Oct. 12-14 at The Charles Hotel in Cambridge, Mass.

The platform, which is a program of the AD-Venture.bio joint venture, is designed to provide decision support for industrial enzyme design, potentially saving significant costs associated with expression failure. While the platform is not a replacement for experimental expression testing, it offers a valuable tool for pre-synthesis decision-making.