AI-Driven Drug Discovery: Finally Living up to its Promise?


Generative Artificial Intelligence (AI) has grabbed a lot of media attention in recent months following the launch of chatbot ChatGPT, but the pharmaceutical industry has long been trying – and struggling – to better integrate AI into the long and failure-fraught drug discovery process. While AI-enabled drug discovery may not have fully delivered on its promise, one company, Insilico Medicine, is closer than most to proving the value of AI, with its AI-designed and discovered candidate becoming the first such molecule to reach Phase II human clinical trials.


AI Boom

Drug discovery is an expensive and time-consuming process with pre-clinical stages that can take up to six years and cost hundreds of millions to billions of dollars. AI tools have the potential revolutionise everything from target identification to molecular simulations and drug property predictions, speeding up timelines while impacting the economics of drug discovery. That potential, in Morgan Stanley’s view, could result in an additional 50 novel therapies over a 10-year period and represent a more than USD 50 billion opportunity. The possibilities presented by AI have also led investors to pile assets into AI-enabled drug discovery and third-party investments to more than double for five consecutive years, reaching over USD 5.2 billion in 2021.

Big Pharma companies like Bristol Myers Squibb, AstraZeneca and Merck have jumped into the AI game mainly through partnerships with AI start-ups, although many pharma giants are also building their own in-house AI efforts. And AI start-ups abound. According to the Boston Consulting Group, in 2022 biotechs with an AI-first approach had over 150 small-molecule drugs in discovery and more than 15 in clinical trials.

While certain AI drug discovery companies went public, including Benevolent AI, Recursion, and Ex Scientia, the sector later underwent considerable consolidation, says Alex Zhavoronkov, founder and CEO of Hong Kong-based AI-drug discovery biotech Insilico Medicine. “In 2020 there were hundreds of companies claiming to do ‘AI drug discovery,’ but there are only perhaps less than ten companies with a tangible offering left.”


First AI Candidate to Reach Phase II Human Trials

Insilico is one of the AI drug discovery companies that persevered, having evolved from an AI algorithm and software provider to focus entirely to drug discovery with the help of GSK veteran and now co-CEO Dr Feng Ren. Today, Insilico has four clinical stage assets both in Phase I and – in a first for an AI-designed and discovered candidate – Phase II human clinical trials. “This is the first true example of a drug reaching Phase II trials where AI has been used for target discovery, chemistry, and prediction of clinical trial outcomes,” Zhavoronkov asserts.

Alex Zhavoronkov


This is the first true example of a drug reaching Phase II trials where AI has been used for target discovery, chemistry, and prediction of clinical trial outcomes

Alex Zhavoronkov, founder and CEO, Insilico Medicine


Insilico developed its Phase II candidate in-house. “We started with target identification. Through this synthetic route planning, we completed in vivo and in vitro studies to nominate two preclinical candidates for kidney fibrosis and for lung fibrosis.” he explains. “We are now running two Phase II arms, with 60 patients in China and 60 in the US.”



For Zhavoronkov AI can greatly increase productivity with respect to traditional drug discovery models. “Big Pharma, utilizing its traditional model can generally generate four or five preclinical candidates in the same amount of time that our AI-driven approach is able to generate nine,” he claims. “Generative AI allows us to rapidly discover targets, formulate the shortest path from the target to the patient, and generate chemistry with the right properties from scratch instead of searching for a compound with those said properties.”

Yet, Insilico’s CEO warns, “while we are able to accelerate preclinical development, it is impossible to accelerate late-stage clinical, development.” Using an analogy to illustrate his point, Zhavoronkov claims that the company is “able to make a better bullet with a higher probability of reaching its target and aim it more precisely, but once it is fired, we cannot make it travel any faster.”


Partnering with Big Pharma

Zhavoronkov believes that Big Pharma should rely on partnerships to develop its AI capabilities. “Instead of hiring armies of AI scientists, they should realise where their key strengths are and where they need to rely on partners.” To this effect, both Sanofi and Fosun Pharma have made a partnership deals with Insilico. Under the Sanofi agreement, the biotech received USD 21.5 million up front, with up to USD 1.2 billion in milestones, and single- to double-digit royalties.

But partnerships, Zhavoronkov argues, must be well-chosen. “Our Big Pharma partnership strategy has been influenced by the fact that management changes in these companies often have a seismic impact on R&D strategy,” he affirms. “For this reason, our business model is now based only around partnering on assets that have already progressed. To use another analogy, we bake the cookies, and then sell them, instead of helping other people bake them.”

In Zhavoronkov’s view, partnerships should focus on the preclinical stage. “I want to evangelise the partnering model, where the partnering is done at the preclinical candidate stage,” he avows, because “pharma companies are usually better at clinical study design than AI drug discovery companies.”

Related Content

Latest Report