Insilico Medicine (“Insilico”), a clinical-stage genetic artificial intelligence (AI)-driven biotechnology company, today announced that the company has achieved a breakthrough collaboration with Inimmune, which will use Chemistry42, its proprietary genetic artificial intelligence technology artificial intelligence (AI) of Insilico to accelerate the discovery and development of next-generation immunotherapeutics.
Chemistry42, a multifactorial reinforcement learning system designed with pharmaceutical chemists in mind, is designed to address key challenges in small molecule drug discovery, such as novelty, diversity, property prediction, and multiparameter optimization. By incorporating more than 42 advanced machine learning technologies, including generative autoencoders, adversarial networks, and evolutionary algorithms, as well as approximately 500 pre-trained models, Chemistry42 enables the creation and design of drug molecules with tailored physicochemical properties from scratch. It also supports the evaluation of multidimensional characteristics such as pharmacological efficacy, metabolic stability, synthetic difficulty, ADME properties and selectivity of the produced molecules.
In the initial phase of their collaboration, Inimmune leveraged Chemistry42’s capabilities to address specific challenges in its drug discovery efforts. The platform’s ability to generate new template molecules and evaluate multiple key characteristics, including metabolic stability, synthetic difficulty, and ADME (Absorption, Distribution, Metabolism, and Excretion) properties proved invaluable. Chemistry42 enabled the rapid generation and screening of molecules with high potential efficacy against targeted biological pathways, enabling Inimmune to efficiently identify promising lead compounds. Synthetic feasibility assessment of the platform provided critical insights, helping to prioritize candidates that were efficient and synthetically accessible, further streamlining the drug development process. By integrating Chemistry42’s capabilities, Inimmune has significantly enhanced research strategies and decision-making, leading to greater efficiency and accuracy in its drug discovery efforts.
Inimmune’s highly skilled chemists were able to take the software and quickly provide insights into new compounds with improved potency and pharmacodynamic properties. This collaboration has led to significant improvements in the efficiency of Inimmune’s drug discovery process. This initial success laid a strong foundation for continued collaboration, demonstrating the value of integrating AI-based platforms such as Chemistry42 into the drug discovery pipeline. Improvements in efficiency and the creation of high-potential hit streaks have highlighted the transformative impact of advanced computing tools on pharmaceutical research and development.
Having completed our trial and initial round of compound production, we are now moving into the synthesis and biological testing phase. We are pleased to maintain our access to Chemistry42 as it allows us to efficiently evaluate and prioritize compounds for synthesis. We look forward to accelerating the delivery of innovative vaccines and immunotherapies for unmet medical needs through transformative AI-based approaches that streamline the drug discovery process and improve compound quality.”
Ahmad Junaid, PhD., senior scientist at Inimmune
“It has been a pleasure working with Inimmune,” said Hugo de Almeida, PhD, Application Scientist and CADD Specialist at Chemistry42. “It’s clear to me that they are very dedicated to incorporating cutting-edge tools to discover new compounds and improve patients’ lives. Their interest in artificial intelligence and genetic chemistry led to good communication, allowing us to identify their challenges and to provide solutions to generate new ideas that will hopefully help them discover new drugs.”
Building on the initial success achieved in the first round of compound generation, Inimmune researchers plan to further optimize the Hit series identified by Chemistry42. The goal is to refine these compounds through an additional 2-3 rounds of iterative optimization, focusing on enhancing their desired properties to develop lead compounds suitable for advancement to the next stages of synthesis and testing.
During these rounds of optimization, Inimmune will use Chemistry42’s advanced algorithms to refine various molecular features, ensuring that lead compounds exhibit optimal properties. By leveraging the platform’s capabilities, researchers at Inimmune also aim to overcome any challenges in current SAR campaigns and improve the overall drug-like properties of current assets.
The importance of collaboration lies in its potential to significantly enhance the efficiency and effectiveness of drug discovery processes. Traditional methods of drug development are often time-consuming and expensive, with a high failure rate. The use of artificial intelligence and machine learning in Chemistry42 offers a promising solution to these challenges, enabling the rapid production and evaluation of new compounds with desirable properties. This approach not only speeds up the drug discovery process but also increases the likelihood of identifying successful therapeutic candidates.
Alan Joslyn, PhD., CEO of Inimmune said, “The initial success we’ve seen with Chemistry42 is just the beginning. By leveraging their cutting-edge technology, we are able to further improve our lead compounds and address key challenges in our SAR campaigns, ultimately bringing us closer to bringing innovative treatments to patients.”
In 2016, Insilico first described the idea of using genetic artificial intelligence to design new molecules in a peer-reviewed journal, which laid the foundation for its commercially available Pharma.AI platform. Since then, Insilico has continued to integrate technical breakthroughs into the Pharma.AI platform, which is currently an artificial intelligence-based manufacturing solution that spans across biology, chemistry and clinical development. Backed by Pharma.AI, Insilico has proposed 18 preclinical candidates in its integrated portfolio of more than 30 assets as of 2021 and has received IND approval for 9 molecules.
