Insilico Medicine launches trial for AI-discovered drug

By Jenni Spinner

- Last updated on GMT

(Sinenkiy/iStock via Getty Images Plus)
(Sinenkiy/iStock via Getty Images Plus)

Related tags Insilico Medicine Artificial intelligence Drug discovery Lung Drug development Clinical trial

The artificial intelligence-driven drug discovery company has dosed its first healthy volunteer in a trial for a candidate to treat idiopathic pulmonary fibrosis.

Insilico Medicine, a company that uses artificial intelligence in drug discovery, has announced the dosing of the first healthy volunteer in a microdose trial of ISM001-055. The drug is a small-molecule inhibitor of a novel biological target discovered via Pharma.AI, the company’s drug discovery platform powered by artificial intelligence (AI).

ISM001-055 is being developed to treat idiopathic pulmonary fibrosis (IPF), a chronic lung disease that results in progressive, irreversible lung-function decline. The trial, which is being conducted in Australia, involves administering ISM001-055 intravenously in healthy volunteers.

Feng Ren, chief scientific officer of Insilico, said the discovery and trial of ISM001-055 marks a “significant milestone” in using AI to discover treatments because the candidate is the first-ever AI-discovered novel molecule based on an AI-discovered target.

We have leveraged our end-to-end AI-powered drug discovery platform, including the usage of generative biology and generative chemistry, to discover novel biological targets and generate novel molecules with drug-like properties​,” Ren said. “ISM001-055 is the first such compound to enter the clinic, and we expect more to come in the near future​.”

Insilico reported that ISM001-055 demonstrated “highly promising​” results in multiple preclinical studies, including in vitro biological, pharmacokinetic, and safety studies. They noted that the compound “significantly​” improved myofibroblast activation, which contributes to the development of fibrosis; ISM001-055’s novel target is potentially relevant to a broad range of fibrotic indications.

Previously, Insilico Medicine reportedly demonstrated the ability to generate drug-like hit molecules using AI with the publication of the Generative Tensorial Reinforcement Learning (GENTRL) system for a well-known target in record time. It also demonstrated the target’s proof of concept by applying deep learning techniques for the identification of novel biological targets; the novel antifibrotic program combined these target discovery and generative chemistry capabilities.

According to Insilico, the company wrapped this discovery process (from target discovery to preclinical candidate nomination) within 18 months on a budget of $2.6m USD. According to Michael Levitt, a member of the company’s scientific advisory board and 2013 Nobel laureate, this constitutes a “breakthrough​” milestone by the company.

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 commented. “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​.”

Bud Mishra (professor of computer science, mathematics, and cell biology at New York University’s Courant Institute and another scientific advisory board member) said, “Insilico Medicine has pioneered combining sub-symbolic AI algorithms with vast amounts of systems biology data to devise an antifibrotic drug candidate moving into the clinic starting with a micro-dose trial​.”

Alex Zhavoronkov, CEO and founder of Insilico Medicine, said, “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. Target discovery is the fundamental grand challenge of the pharmaceutical industry. With ISM001-055 we used end-to-end AI connecting biology, chemistry in order to assess activity and safety in multiple preclinical models​.”

Related news

Show more

Related products

show more

Using Define-XML to build more efficient studies

Using Define-XML to build more efficient studies

Content provided by Formedix | 14-Nov-2023 | White Paper

It is commonly thought that Define-XML is simply a dataset descriptor: a way to document what datasets look like, including the names and labels of datasets...

Increasing the Bioavailability of Oncology Drugs

Increasing the Bioavailability of Oncology Drugs

Content provided by Lonza Small Molecules | 13-Nov-2023 | White Paper

Oral tyrosine kinase inhibitors (TKIs) are a class of cancer drugs that can be highly susceptible to issues with solubility in the gastrointestinal tract

Related suppliers

Follow us


View more