Growth in the artificial intelligence (AI) healthcare market is expected to reach $6.6 billion by 2021—that’s a compound annual growth rate of 40% from just a few years ago.
One expression for why this matters can be found in a startup that is innovating in AI with the promise to accelerate drug design, discovery, and testing industry. The laborious task to test thousands of molecules over several years to eventually distill a few novel molecules for human trials is about to change. Hong Kong-based, AI-based Insilico Medicine is scaling its technology to generate, synthesize, and preclinically validate a series of promising compounds from scratch in less than two months.
The company has developed a deep generative model, generative tensorial reinforcement learning (GENTRL), for de novo small-molecule design. Specifically, GENTRL uses modern AI techniques of generative adversarial networks (GAN) and generative reinforcement learning (RL) to accelerate drug discovery. Insilico says it was the first company to explore using GAN and RL for drug discovery. The company released its source code as open source.
Last year, Insilico demonstrated it could conceptualize more than 30,000 novel small molecules using its machine learning approach, narrow them down to six potential candidates for a fibrosis target and then test them preclinically in less than two months. The company’s paper was published in Nature Biotechnology. And in January, the company announced a research collaboration with Pfizer Inc. to use Insilico’s generative machine learning technology and proprietary Pandomics Discovery Platform with the aim of identifying real-world evidence for potential therapeutic targets implicated in a variety of diseases.
COVID-19 appears to be accelerating Insilico’s technology. In April, the company announced another research collaboration with Boehringer Ingelheim to use its Pandomics Discovery Platform with the aim of identifying potential therapeutic targets implicated in a variety of diseases.
Since its inception in 2014, Insilico has raised over $52 million, published over 70 peer-reviewed papers, applied for over 20 patents, and received multiple industry awards. Alex Zhavoronkov founded Insilico as an alternative to animal testing for research and development programs in the pharmaceutical industry. The company developed GENTRL in collaboration with WuXi AppTec, a provider of a broad portfolio of R&D and manufacturing services that enable companies in the pharmaceutical, biotech and medical device industries to advance discoveries and deliver treatments to patients, and Alán Aspuru-Guzik, an authority in quantum computing and artificial intelligence in chemistry.