Artificial Intelligence (AI) is predicted to be a major driver of growth in the pharmaceutical industry, and drug manufacturers and technology companies are investing billions of dollars in AI due to its promise to make drug discovery more cost effective and efficient. On average, the timespan for taking a drug from research lab to commercialization is 10 years, with a price tag of approximately $2.6 billion. Using AI in drug discovery can provide numerous benefits and address many challenges in the process, and hopefully speed up the time and lower the price that is needed to bring a drug to market. As of the end of February, Toronto-based biotechnology firm BenchSci cited 16 pharmaceutical companies and over 60 startups as using AI for the drug discovery process.

Some of the major challenges in drug discovery lie in the early stages of R&D; specifically, the time it takes to establish a possible disease target, which is usually in the form of a protein within the body, and conduct tests to determine if the drug candidate will be able to reach that disease target. Generally, this process can take 4–6 years. Many AI groups are aiming to lessen that time dramatically such as ATOM, a private-public AI consortium, which is aiming to compress the process into just one year. London-based BenevolentAI, known as the largest AI company in Europe, has estimated that its AI capabilities can slash drug discovery costs by 60% and lessen drug design time from 3 years to 1. AI has also proven to help with effective combination therapies for HIV, hypertension, infectious diseases and cancer.

While the potential of AI is extremely promising, a major challenge that remains is ensuring the data the AI is working with is reliable, as AI is only as good as the data that it processes. Scientists will still have to train the computers on what to look for to ensure that the algorithms the AI is using are actually meaningful.

Source: NBC News MACH