Dr. Daniel Cohen is a world-renowned geneticist and a pioneer in modern genetics. His work at the Généthon laboratory in France made an outstanding contribution to the release of the human genome map. He then introduced big data and automation to genomics research, and he and his team demonstrated for the first time that ultra-fast calculations could be used to speed up the analysis of DNA samples.

However, 25 years after the emergence of genomics, the revolutionary medical breakthrough it brought to the world is not as good as many people expected. Today, Dr. Cohen is the CEO of a French pharmaceutical company called Pharnext. In his view, genetic pleiotropy is one of the reasons why drug developers can't do anything when they are trying to overcome the illnesses of the world. Dr. Cohen is not only aware of the importance of genetic pleiotropy, but he believes that with the aid of artificial intelligence (AI), Pharnext and other pharmaceutical companies will be able to develop innovative drug combinations to treat a variety of diseases in the near future.

AI promotes new use of old drugs and helps develop innovative combination therapy for rare diseases.

At Pharnext, Dr. Cohen and his team used AI to promote the new use of those old drugs we are familiar with. They can find innovative combinations of drugs from existing drugs, allowing combination therapies to provide treatments that are not achievable with individual ingredients. Their long-term goal is to use machine learning to streamline the drug development process and build drug discovery pipelines more effectively.

Companies with the same philosophy as Pharnext include technology giants like Google and IBM, as well as startups like Insilico Medicine, Recursion Pharmaceuticals, and BenevolentAI. They all invest heavily in AI as tools to analyze millions of drug samples and patient data, in a hope to find certain important patterns that could be taken use of.

Pharnext's efforts to apply AI to solve medical problems have lasted for more than 10 years and recently reach an important milestone. In October last year, Pharnext developed the combination therapy PXT3003, which yielded positive results in a phase 3 clinical trial of the Charcot-Marie-Tooth disease (CMT1A). CMT1A is a neurodegenerative disease. The main cause of this disease is the expansion of the PMP22 gene carried by the patient, resulting in an increase in the level of PMP22 protein. This leads to damage to the myelin sheath that protects the nerves, and then the nerves will gradually die and the muscles will shrink.

Phase 3 clinical trial results show that PXT3003 can not only stabilize the condition of CMT patients, but also help cell regeneration. There were statistically significant improvements in the patient's two disability test indicators, while other existing therapies only slowed the rate of patient decline. Based on these results, the FDA granted this therapy a fast-track qualification in February this year, and this innovative combination therapy is expected to be available in 2020.

This is not only an important step in the treatment of CMT, but the ability of AI to shorten the drug development process has far-reaching implications. Preclinical testing and clinical trials usually take 8-10 years, and developing an innovative drug from scratch may add more than seven years to the process. The development process of PXT3003 is much simpler than that. AI helped Pharnext o choose three existing drugs to form a new combination: baclofen is a muscle relaxant; naltrexone is used for the treatment of opioid dependence; and sorbitol is commonly used as a laxative. Because these drugs have been widely used, Pharnext can skip the phase 1 clinical trials that test safety and eliminate the “from scratch” drug development phase.

In addition to this research and development project, Pharnext will also conduct two Phase 2 clinical trials, in which Alzheimer's disease and amyotrophic lateral sclerosis (ALS) are being studied. These two treatments are also a new combination therapy built from existing drugs using AI. If these trials are successful, this drug development model may set off a new pattern as well as a wave of "old drugs for new use."

Author's Bio: 

BOC Sciences is a traditionally chemical supplier, and starting last year, it has become a highly proved provider of comprehensive drug discovery services, which includes various screening libraries like Fragment Library and Custom Libraries as well as services like Hit to Lead, Lead Optimization, Chemical Resynthesis, drug testing service, building block synthesis, synthesis service, hit identification service, and more.