Pioneering drug selection software helps find potential type 2 diabetes treatments

A major artificial intelligence biopharmaceutical company called twoXAR has demonstrated a new approach for selecting type 2 diabetes drugs which could be of huge future significance.
The US firm successfully screened 25,000 potential drug candidates for a recent study looking at new type 2 diabetes treatments. The software swiftly selected three which showed to have the best efficacy and safety aspects.
The platform uses twoXAR’s artificial intelligence to analyse biological, chemical, and clinical data to predict and rank potentially relevant drugs.
The company said this strategy “offers a new route to unique intellectual property rights that allow for the rapid development of a drug while maximising the opportunity to identify the most efficacious molecule.”
By applying twoXAR’s model, the molecule TXR-411 was identified which, when tested, was shown to halve blood sugar levels in mice with type 2 diabetes. In fact, it was discovered to yield similar results to the type 2 diabetes drug rosiglitazone (marketed as Actos), but without weight gain.
Dr Isaac Hakim, director of Preclinical Studies at twoXAR, said: “The TXR-411 data […] model is impressive given that the initial examination of our candidate achieved an approximately 50 per cent decrease in blood glucose levels, on par with rosiglitazone, without the weight gain associated with rosiglitazone.
“The reduced glucose and body weight maintenance is exciting in its own right, however, even more compelling is that we selected this disease, identified and shortlisted candidates, and generated efficacious preclinical results in less than three months.”
The twoXAR researchers believe this new strategy could enable the rapid development of a drug that maximizes the effects of molecules deemed to be best suited to treat type 2 diabetes.
Andrew A. Radi, co-founder and CEO of twoXAR, said: “Over the last 12 months we have publicly announced positive preclinical proof-of-concept data in rheumatoid arthritis, liver cancer, and now type 2 diabetes.
“Across these studies we have seen that about 30 per cent of the novel candidates we test in preclinical studies show statistically significant efficacy signals in the in vivo models’ respective endpoints.”