Insilico Medicine recently closed a $37m Series B funding round led by the Chinese venture capital firm Qiming Venture Partners.
Qiming was joined by Eight Roads, F-Prime Capital, Lilly Asia Ventures, Sinovation Ventures, Baidu Ventures, Pavilion Capital, BOLD Capital Partners, and other investors, including series A investors.
Headquartered in Hong Kong, Insilico will expand its senior management team to further develop its pipeline in cancer, fibrosis, NASH, immunology, and CNS, and plans to partner with pharma on specific therapeutic programs.
The Series B funding also will be used to commercialize the company’s validated generative chemistry and target identification technology, the capabilities of which were recently exemplified in a new scientific paper published in Nature Biotechnology.
The paper describes a challenge in which the artificial intelligence (AI) system – Generative Tensorial Reinforcement Learning (GENTRL) – was able to design six novel DDR1 inhibitors in 21 days.
According to the company, four compounds were active in biochemical assays and two were validated in cell-based assays. Additionally, one lead candidate was tested and demonstrated ‘favorable’ pharmacokinetics in mice.
As part of this work, Insilico collaborated with the Shanghai-headquartered contract services provider, WuXi AppTec, as well as Alán Aspuru-Guzik, a quantum computing and AI expert.
‘Just the beginning’
The publication of Insilico’s paper is expected to have a big effect on the whole pharmaceutical industry, said Margaretta Colangelo, managing partner, Deep Knowledge Ventures, which provided Insilico with seed funding in 2014. She also expects it to create an incentive for large pharma companies to integrate AI.
“This news may even create the beginning of an arms race in drug development, where the largest pharma and tech companies compete to acquire the strongest AI for drug discovery companies,” she told us, adding that the achievement “demonstrates the true power of AI to accelerate the pace of scientific R&D.”
Said Colangelo, “When Insilico first proposed the idea of using GANs to accelerate drug discovery in 2016, most of the industry was skeptical. The GAN-RL technique itself is very new and was only proposed in 2017. It has now moved from theory to reality.”
However, Colangelo said the development of these first six molecules is “just the beginning.”
“By enabling the rapid discovery of novel molecules and by making the source code open source, Insilico is creating possibilities for the discovery of new life-saving medicines for incurable diseases,” she explained.
Colangelo, who, with Deep Knowledge Ventures, are following other players in this space, said she has not heard about any other group achieving “the desired activity in enzymatic assay.”
“Insilico's study is the closest that the industry has come to demonstrating the real-world potential of AI for drug discovery in a tangible way,” she said.
Michael Levitt, PhD, professor of structural biology, Stanford University, commented that the work could be applicable to other problems facing drug-design. “Based on state-of-the-art reinforcement learning, I am also very impressed by the breadth of this study involving as it does molecular modeling, affinity measurements, and animal studies," he said.
Dr. Charles Cantor, a professor at Boston University, co-founder of Retrotope, and former chief scientist of the Human Genome Project with the US Department of Energy also spoke to the results which he said are significant for two reasons:
“The AI procedures replaced the role normally played by medicinal chemists, and these individuals are in limited supply. The acceleration in rate translates into longer patent coverage that improves the economics of drug development. If this approach can be generalized it could become a widely adopted method in the pharmaceutical industry."
Though “much hyperbole exists about the promise of AI in improving medical care and in the development of new medical tools,” Cantor said Insilico’s work “is indeed important.”
Title: Deep learning enables rapid identification of potent DDR1 kinase inhibitors
Authors: Alex Zhavoronkov, et, al
DOI: 10.1038/s41587-019-0224-x
Source: Nature Biotechnology