Our machine learning technology enables a clear route to drugs that safely reset cells and tissues to a youthful state.

The science

Cell reprogramming offers a path to comprehensive rejuvenation but has a goldilocks problem. Too little and you have no rejuvenation, too much and you risk cancer. To fulfil its potential, cell-reprogramming must be made safe. Based on a novel application of machine learning, we have the opportunity to tame cell reprogramming and safely reset cells and tissues back to a youthful state.

"The technique (of cellular reprogramming) has an indisputable, repeatable effect in laboratory experiments when applied to individual cells. You can take a cell from an 80-year old and, in vitro, reverse the age by 40 years. There is no other technology that can do that. What’s more, reprogramming is also recognized as a key process that occurs naturally when a fertilized egg turns into an embryo and, nine months later, leads to a fresh-faced baby. Somehow, the DNA of the parents is scrubbed, renewed and restarted. Reprogramming is one of the experiments that has been reproduced the most.”– Alejandro Ocampo, MIT Technology Review, Sep 2021

We are using public and proprietary gene expression data from cell reprogramming studies to identify the contributions that different genes make to the rejuvenation process. We have developed a machine learning framework using genes – the Shift DC1 driver clock - with meaningful accuracy. This technology is protected by our EP4120278 patent application filed in July 2021 with the European patent office. Our novel machine learning approach enables a more complete understanding of the causes of cellular rejuvenation:

• Combine public and proprietary gene expression data from cell reprogramming and focus on pathways to enrich causal information
• Use machine learning ‘enrichment’ to better differentiate rejuvenation pathways. Based on results, rank gene contributions

Our method identifies targets for safe rejuvenation

The advantages of the DC1 approach are threefold:

• Enriches causal biology
• Rapid testing of gene causality via over-expression or CRISPR
• Intervene precisely with mRNA or small molecules

The next step

We are now validating gene causality and weeding out unsafe genes, the final step before interventions.

Our development timeline