First Healthy Volunteer Dosed in Trial Testing ISM001-055 for IPF
“We are very pleased to see Insilico Medicine’s first antifibrotic [treatment] candidate entering into the clinic,” Feng Ren, PhD, Insilico’s chief strategy officer, said in a press release.
“We believe this is a significant milestone in the history of AI-powered drug discovery because to our knowledge [ISM001-055] is the first ever AI-discovered novel molecule based on an AI-discovered novel target” to be tested in clinical trials, Ren said.
Michael Levitt, the 2013 Nobel laureate in chemistry and a member of Insilico’s scientific advisory board, said “AI is a way to search for information and look for signals for drug discovery.”
“This achievement didn’t happen by chance and is a reproducible method and procedure which is revolutionary,” Levitt said.
Notably, little more than two years separated target discovery and the initiation of the first-in-human clinical trial, the company noted. According to Alex Zhavoronkov, PhD, Insilico’s founder and CEO, that timeline highlights how Insilico’s Pharma AI platform “can overcome the low probability of getting to this stage” — that of a clinical trial — while shortening time and development costs.
“The failure rates in preclinical target discovery are very high and even after the targets are validated in animal models, over half of Phase 2 clinical trials fail primarily due to the choice of target,” Zhavoronkov added.
“Target discovery is the fundamental grand challenge of the pharmaceutical industry,” Zhavoronkov said, adding that with ISM001-055, researchers used “end-to-end AI connecting biology, chemistry in order to assess activity and safety in multiple preclinical models.”
ISM001-055, given intravenously or directly into the bloodstream, is a potentially first-in-class small molecule inhibitor of a new biological target discovered through the company’s Pharma AI.
The experimental therapy showed promising efficacy in lab-grown human tissue and animal models of IPF, as well as a favorable safety profile in a 14-day repeated dose-finding study in mice.
Notably, ISM001-055 was found to significantly reduce the activation of myofibroblasts, the main driver of lung scarring, or fibrosis.
These positive preclinical data prompted the launch of the first-in-human trial testing microdoses of ISM001-055 in healthy volunteers. The study, being conducted in Australia, will assess the therapy’s pharmacokinetics, or its movement into, through, and out of the body.
“There are very few examples of a pharmaceutical company discovering a new target for a broad range of diseases, designing a novel molecule, and initiating human clinical trials … [and] to my knowledge, nobody has achieved this with AI to-date,” Zhavoronkov said.
Levitt said the use of AI is similar to the historical therapy-development process.
“Many drugs were discovered accidentally when scientists designed a drug for disease A and then they found out that it actually works for some different disease B,” Levitt said.
According to the company’s website, Pharma AI’s PandaOmics domain uses millions of data samples and multiple data types to discover signatures of specific diseases and identify the most promising targets.
If there are no available compounds targeting these molecules, the AI platform’s Chemistry42 domain helps generate new compounds with therapeutic potential through preferred sets of parameters.
Moreover, the platform also includes an InClinico domain, used to predict trials’ success rate and recognize their weak points, while adopting the best practices in the industry.
Insilico said it completed the entire process from target discovery to preclinical candidate nomination within 18 months on a budget of $2.6 million. This was followed by a nine-month period in which the company completed the manufacturing and safety work required for a permission by health authorities to study the compound in people.
ISM001-055’s new target is potentially relevant to a broad range of fibrotic diseases, the company said.