Background

In recent years, natural products have been discovered that can extend mammalian lifespan by clearing senescent cells, reducing inflammation, and inhibiting insulin signaling, three central factors during aging. Furthermore, many of these compounds are present in low concentrations in common fruits and vegetables, offering great promise for effective treatments targeting aging that are also safe enough for billions of people to use regularly. However, these natural molecules have extremely poor solubility, bioavailability, and half-life, which are the main hurdles to implementing these discoveries as effective therapeutics.

Platform

We have created a proprietary artificial intelligence (AI) and machine learning (ML) platform based on our findings. The platform designs improved, novel small molecules using training data from natural molecule-based senolytics, molecules that selectively clear senescent cells. In addition, 15 additional criteria related to safety, bioavailability, and metabolism are applied to select the best possible molecules to maximize success probability from the outset. Our platform has been used to design >1000 proprietary small molecules that are predicted to outperform natural molecule senolytics.

Upgrade, Expand, Rejuvenate

Now is the right time to use AI and ML to design therapeutics for aging. Over 100 natural molecule-based senolytics have been published, and more are on the way. We can upgrade and focus our platform with newly published data and with the proprietary real-world data we are obtaining from our newly generated molecules, creating better and better molecules with each new version. We can also expand our platform because natural molecule-based senolytics can also inhibit mTOR and insulin signaling, two additional central areas of aging biology. By using omics data we generate, we can predict which of our molecules decrease biological age in humans the most before they ever need to be tested in patients.