Efforts to use AI for drug discovery have been underway for about a decade, but industry watchers expect an inflection point to be approaching for investors, who have been looking for ways to determine how drug developers evaluate AI. Artificial intelligence and machine learning offer the potential to accelerate the search for new treatments by more quickly identifying compounds to treat diseases. There’s also a promise to make clinical trial stages more efficient by improving patient enrollment and quickly addressing insights as information flows from studies. More concrete evidence of these capabilities is now being shown. A notable example is the efforts to combat Covid-19, which have forced biotechnology and pharmaceutical companies to use all their capabilities in efforts to discover vaccines and treatments in record time. Lydia Fonseca, chief digital officer of Pfizer, has discussed the role the pandemic has played in accelerating digital developments during several conferences that have appeared over the past year. “We think Covid-19 has developed these trends by as much as five years,” Fonseca said in a virtual fireside chat with McKenzie in January. “It’s not that these are new technologies, it’s that we are applying them extensively.” Key points for investors By Deloitte’s latest estimates, it could cost $2 billion to develop a new property. AI and machine learning promise to lower this cost by reducing development times and increasing success rates. More advanced algorithms, increased computing power, and richer data sets lead to more progress. While most biotech and pharmaceutical companies are using artificial intelligence and machine learning tools, companies that belong to this field are about to reach an inflection point that will help investors appreciate the value of these companies. The Boston Consulting Group said in March that AI drug developers had identified more than 150 small-molecule drugs, with at least 15 already in clinical trials. Fonseca added that the capabilities that will occur when quantum computing is widely adopted are now unimaginable. But even with today’s supercomputing power, Pfizer is able to use modeling and simulation to screen millions of compounds for potential drug targets. Pfizer said the development of Paxlovid, an oral treatment for Covid, within four months has helped deploy various machine learning technologies. ‘Great convergence’ There is a ‘great convergence’ going on across the industry, according to Julia Angelis, portfolio manager for Baillie Gifford’s Health Innovation Fund. “It’s not just one technology that plays a role,” Angelis said. “It’s actually a mix of technologies.” In an interview, she detailed a number of improvements that have occurred with the advanced algorithms used to support machine learning, the richness of data sets that can be examined for information and the efficiency of the computing power needed to hold it together. . But Angelis said the crucial change lies in the scale being made. “A lot of companies can do that,” she said. “We have more data relevant to the biology of the mines, and we have more powerful computers to do this more effectively, and much faster than we have done in the past.” A major component has been the steep decline in the cost of sequencing genetic data over the past 10 years, resulting in a pool of patient information that can be combined with other types of electronic health records. Separately, last year’s release of the AlphaFold2 source code by DeepMind, a UK-based AI project owned by Alphabet, helped visualize the structure of the proteins, which should also aid development in the field in the coming years. So far, technological advances have led to a wave of small-molecule drugs being devised by AI drug discovery companies. Combing through public records, the Boston Consulting Group has identified more than 150 small molecule drugs, with at least 15 already in clinical trials, from the top companies in the field. BCG said the pipeline is growing nearly 40% annually. said Chris Meyer, Managing Director and Partner at BCG. “If the success rate comes back better, of course it becomes very exciting because all of a sudden we have something better than humans. We don’t know yet,” he said. Expected updates from a number of drug candidates over the next 12 to 18 months were a major reason Morgan Stanley analysts said they expect the sector to reach a tipping point. In a research note published in late June, Morgan Stanley said readings from early clinical work will help the market determine a value for AI’s original drug inventory. In the past, the report said, investors have debated whether the group should evaluate a technology platform or a biotech company. In fact, the business models of these companies can vary. Some are similar to the software as a service model, in which companies provide machine learning capabilities to partners for a fee. But many of them also develop their individual projects and collaborate with pharmaceutical companies, where they will receive prominent payments and royalties as the compounds meet targets and are marketed. The value of the rapid failure According to recent estimates by Deloitte, the development of a new drug could cost two billion dollars. This number represents the vast majority of compounds that have been studied, but failed in early clinical trials. Success rates can be less than 5%, and development periods can span a decade or more. Morgan Stanley analysts estimate that a roughly 2% improvement in the pace of preclinical and phase 1 development could lead the industry to create about 50 new treatments over the next 10 years. This could equate to about $50 billion in the net present value of the biopharma industry, they said. One of the main ways AI-assisted drug research can save money is by identifying molecules that have the largest and least potential for success early in the research cycle. By doing so, the cost of failure is greatly reduced. Robert Burns, managing director of HC Wainwright, said Schrödinger described a 10-month time frame for identifying a development candidate, while Exscientia put its average time around 12 months. In comparison, traditional drug discovery can take three to five years. “This is important, especially, you know, a lot of these companies within the big pharmaceutical and biotech companies, they’re all trying to pursue very similar goals,” Burns said. Speed can not only save money, but also provide a competitive advantage. Despite the promises these companies make, stocks have fallen sharply along with the rest of the biotech sector. Most of them are now trading below IPO prices. The Baillie Gifford Health Innovation Fund reflects this trend. It’s down more than 26% since the start of the year, but has gained nearly 7% so far this month, according to FactSet. Within the AI-first space, Angeles owns Exscientia and Recursion Pharmaceuticals, although they don’t rank among the fund’s largest holdings. Exscientia shares are down 39% year-to-date, and are trading 45% below their initial price last September. The company collaborates with the Bill & Melinda Gates Foundation, Bayer, Sanofi, Bristol-Myers Squibb, and others. The immunotherapy drug for tumors, EXS-21546, is Exscientia’s most advanced compound. It is in phase 1b/2 trials to test the drug in patients with solid tumors. Recursion Pharmaceuticals has lost about 45% of its value since its initial public offering in April 2021. It focuses heavily on using imaging technology to discover drug targets, and much of its focus is on rare diseases. It has partnerships with Bayer, Roche, and Takeda, and is already in a phase 2 clinical trial to treat cerebral cavernous malformations, a disorder of the blood vessels in the brain, which can lead to seizures and fatal bleeding in the brain. Burns has a buy rating on Relay Therapeutics, which is down 35% so far this year, and is trading below its $20 IPO price. The company has several breast cancer treatments in the works, and data for its main compound, RLY-4008, is due to be released by the end of this year. Its partners include Roche and Genentech. On Thursday, Relay said it had enough funding to support its operating plan until at least 2025. As of June 30, total cash and investments were approximately $838 million, compared to $958 million at the end of 2021. Schrödinger reported that it had $513 million in cash, cash equivalents, restricted cash and marketable securities, as of June 30, down from $529 million on March 31. At the end of the first quarter, Exscientia had about $719.8 million in cash, while Recursion was at $591.1 million as of March 31. Until these companies provide updates on these programs, the investment case will depend on the potential value of the companies’ platforms. Once investors see progress in clinical trials, there will be more confidence. “I think there has to be some sort of validation here,” Burns said.