Leaps in technology enable AI-guided drug design, such as fully robotic workstations that can purify proteins and move liquids. **Nature**
This is perhaps the most compelling change in healthcare: digital biology and generative artificial intelligence (AI) are helping to reshape the drug discovery process.
The use of AI to develop new drugs is still in its infancy, but AI-designed drugs have entered the early stages of clinical trials in the past few years, and some AI pharmaceutical pioneers have already made some progress in this field. However, the British "Nature" published an article saying that the potential of AI to accelerate drug discovery still needs to be tested in practice.
Development of antibiotics in the form of bacteriophages
The human body is overrun by a large number of microorganisms, including viruses, and these virus groups are collectively known as the human virome. Stefan N. Lukanov, CEO of Salve Therapeutics, an American AI pharmaceutical company, pointed out that viruses that occur naturally in human tissues are an ideal way to carry genetic **payload** diseases.
Salve is combining machine learning with computer-aided design to develop antibiotics in the form of bacteriophages. The method allows for a virtual assessment of the attributes, outcomes, and risks of a drug invention through extensive iterative analysis of various models.
Lukanov said they are working on genetically engineering bacteriophages to achieve greater potency and host range. He expects phage antibiotics to improve the lives of transplant, burn and immunocompromised patients.
Lukanov stressed that since bacteriophages target only bacteria, this antibiotic does not pose a significant risk to patients, except for a slight immune response in the body due to the presence of foreign body particles.
Development of oral small molecule drugs
Biolexis Therapeutics, an American AI drug discovery company, specializes in the development of oral small molecule drugs for cancer and various metabolic, inflammatory, and neurodegenerative diseases.
The Company discovers and develops novel clinical drug candidates through its proprietary MoleculeRN process. The process can target any kind of protein, identify new chemical entities with drug-like characteristics, and validate it with laboratory data, reducing the time to discover and develop new drugs from years to months. One of their drugs, SLX-0528, is currently in a Phase Ib trial in pancreatic cancer. The drug is designed to control the cell differentiation, function, and interleukin release of helper T cell 17.
Launched a generative AI drug discovery platform
Anthony Costa is the global head of developer relations for life sciences at NVIDIA. He points out that much of generative AI is built on top of the underlying model of a large language model. These models are improving their ability to drug properties and interactions.
To help realize this potential, NVIDIA developed BioONEMO, a cloud service for generative AI in biology that provides a variety of AI models for small molecules and proteins. Costa asserts that with BioONEMO, developers can leverage AI models with proprietary data to rapid** the 3D structure and function of proteins and biomolecules, which will accelerate the generation of new drug candidates.
Evozyne, a Chicago-based start-up, recently used Bionemo to design a new protein to **phenylketonuria. Phenylketonuria is a rare condition characterized by elevated levels of the amino acid phenylalanine. Lab tests have conclusively proven that some AI-developed protein variants are more effective than natural forms.
AI drug discovery requires clinical validation
Drug development involves a number of specific steps. It typically starts with identifying biological targets that cause a disease (which may include DNA, RNA, protein receptors, or enzymes) and then screens for molecules that may interact with it. This is known as the "discovery" stage.
New drugs must be rigorous, safe, effective and credible, and companies must find the right path to that goal. Even if AI does reduce the time and cost it takes for compounds to enter preclinical testing, most drug candidates will still fail at a later stage. But as long as the process can be accelerated, it is a victory. Industry and academia must leverage each other's strengths to determine how AI can be best leveraged.
Lukanov said AI and machine learning represent an exciting new approach to improve efficacy and safety, and bring more drugs to market. He noted that the use of AI and machine learning in drug discovery is still in its early stages and should be validated in the lab to ensure that only the best drug candidates make it to clinical trials.
In addition, various safety features are being incorporated into AI-based drug development. For example, Biolexis uses a variety of approaches to prioritize molecules with high safety profiles. David J. Beers, the company's chief executive, said the safety and potential unintended consequences of the molecules developed by machine learning are important issues that need to be addressed.
*:Technology**.