Insilico Medicine has validated its new GENTRL AI system

Register for free to listen to this article
Listen with Speechify
HONG KONG—In early September, Insilico Medicine announced the development and validation of GENTRL, a new artificial intelligence (AI) system with what it says is the capability to dramatically accelerate the drug discovery process from years to days. Insilico successfully tested the technology by creating a series of entirely new molecules capable of combating disorders like fibrosis.
Traditional drug discovery starts with the testing of thousands of small molecules in order to get to just a few promising molecules, but only about one in 10 of these molecules passes clinical trials in human patients. Insilico was able to ideate and generate a novel molecule from start to finish in 21 days.
With a similar technique used by DeepMind to outcompete human Go players, GENTRL—powered by generative chemistry that utilizes modern AI techniques—can rapidly generate novel molecular structures with specified properties.
Insilico developed GENTRL in collaboration with WuXi AppTec and Alán Aspuru-Guzik, an authority in quantum computing and artificial intelligence in chemistry. GENTRL generated six novel molecules in 21 days, four of which could specifically inhibit DDR1 at nanomolar concentration. DDR1 is a detrimental protein target implicated in a wide range of diseases, such as fibrosis. The creation of the new molecules marks the industry’s first scientific validation of using of generative and reinforcement learning AI for the successful discovery and generation of new molecules.
“The development of these first six molecules as an experimental validation is just the start,” said Alex Zhavoronkov, CEO of Insilico Medicine. “By enabling the rapid discovery of novel molecules and by making GENTRL’s source code open source, we are ushering in new possibilities for the creation and discovery of new life-saving medicine for incurable diseases—and making such powerful technology more broadly accessible for the first time to the public.”
GENTRL uses Insilico’s academic research from 2016 about using modern AI techniques of generative adversarial networks (GAN) and generative reinforcement learning (RL) to accelerate drug discovery. That seminal research led the way for other scientists worldwide to begin developing the theoretical base for GANs and other machine-learning techniques to accelerate and improve the drug discovery process.
“When we first proposed the idea of using the AI technique of generative adversarial networks to accelerate drug discovery in 2016, most of the industry was skeptical. With GENTRL’s successful experimentation and validation, Insilico has moved the use of AI for drug discovery from academic theory to reality, from what many thought was scientifically impossible to now possible,” Zhavoronkov explained.
More details about Insilico’s scientific research and GENTRL can be found in a recently released article in Nature Biotechnology, entitled “Deep learning enables rapid identification of potent DDR1 kinase inhibitors.”
Back in January, Insilico also announced two partnerships, the first of which was with Elevian for research and development of oral medications targeting the GDF11 pathway and associated targets. The collaboration will take advantage of Insilico’s GANs and RL AI to discover novel small molecules that target the GDF11 pathway, which has been demonstrated to play an important role in aging and age-related disease.
“We are excited to partner with Insilico Medicine,” noted Dr. Mark Allen, CEO of Elevian, in a press release. “Not only will we leverage Insilico’s advanced AI technology to accelerate drug development, but we also share a common mission: to eliminate age-related disease and promote healthy longevity.”
Based on biological and structural target data from Elevian, Insilico will identify small molecules that produce the intended biological actions utilizing deep-learning technology. The scientists will begin with existing libraries of compounds and molecular building blocks, based upon iterations of virtual and biological screenings, and narrow down the list of potential candidates. Then Insilico will also provide a selection of novel de novo compound candidates, based on the results of previous iterations, which will be synthesized by WuXi AppTec.
The second partnership, with TARA Biosystems Inc., plans to discover and develop novel therapies for cardiac disease and diseases associated with cardiac muscle aging. Insilico and TARA will combine Insilico Medicine’s rapid discovery capabilities with the power of TARA’s human-relevant tissue models, in the hopes of shaving off years and associated expenses, and incorporating clinically relevant physiology early and consistently throughout preclinical development.
“At TARA, we engineer human cardiac tissue to mimic specific human disease phenotypes which are used to validate novel targets and rapidly evaluate new compounds for positive effects on cardiac function. Partnering with Insilico Medicine further maximizes TARA’s cardiac drug discovery platform. We feel privileged to be working with Insilico Medicine and have been duly impressed by their technical, scientific and business expertise,” Dr. Misti Ushio, CEO of TARA Biosystems, stated in a press release.
“At Insilico Medicine, we interrogate hundreds of disease-relevant assays on a regular basis to identify those biological systems that we can trust to validate the targets and molecules identified using our end-to-end drug discovery pipelines. TARA’s cardiac tissue models are the next best thing to a human heart,” Zhavoronkov pointed out. “Serendipitously, they have one of the most professional and agile management teams that we have encountered during our quest for the best assays. This kind of partnership between AI companies and engineered biology companies is very new and we are extremely excited to partner with TARA Biosystems, a team with a good heart.”

Published In:

Subscribe to Newsletter
Subscribe to our eNewsletters

Stay connected with all of the latest from Drug Discovery News.

DDN July 2024 Magazine Issue

Latest Issue  

• Volume 20 • Issue 4 • July 2024

July 2024

July 2024 Issue