User:Birulik/Insilico Medicine (rework)

Insilico Medicine is a biotechnology company headquartered in Hong Kong. It applies deep learning, generative adversarial networks and reinforcement learning for biomarker development, clinical trials analysis, in silico drug discovery and other fields of digital medicine.

History
Insilico Medicine was founded by computer scientist and biotechnologist Alex Zhavoronkov in 2014. Zhavoronkov's studies in John Hopkins University and Moscow State University were focused on applying machine learning to biological research and Insilico was started up as a company that used deep neural networks to mine biological data to find potential drug targets. Later Zhavoronkov applied Ian Goodfellow's works on machine learning employing generative adversarial networks (GANs) and AI imagination to devise molecules with desired properties de novo instead of screening databases of chemical compounds. Insilico published its first peer-reviewed article in this field in 2016. Following that research the company developed a drug discovery engine based on generative tensorial reinforcement learning (GENTRL). Since its establishment the company has raised over $50 million from venture funds and longevity-focused investors such as British philanthropist and entrepreneur Jim Mellon. Its largest $37 million Series B investment round in September 2019 was led by Qiming Venture Partners joined by Eight Roads Ventures, F-Prime Capital, Lilly Asia Ventures, Sinovation Ventures, Baidu Ventures, Pavilion Capital, BOLD Capital Partners, Juvenescence and other companies.

Recognition
Insilico's AI-based approach has brough it industry recognition. It was called "the most promising company" at Palo Alto Personalized Medicine World Conference in 2015. In 2018 Insilico was granted the Frost & Sullivan North American Technology Innovation Award for advances in aging research and drug development. In 2020 the company was also included in Fierce Biotech's list of top biotechnological companies and was listed as key player in the field of generative molecule design in MIT Technology Review list of breakthrough technologies.

Drug discovery
Insilico Medicine pioneered the use of generative adversarial networks (GANs) and reinforcement learning (RL) in the field of drug discovery. Its drug discovery engine is built on AI imagination and can generate molecules with intended properties using information on patented compounds with proven efficiency against specific biological targets. In 2016 Insilico published the proof-of-concept for the deep learned prediction of chemicals' therapeutic use. In another research it proposed the use of generative adversarial autoencoders trained on molecular fingerprints to identify potential drug candidates in PubChem. In 2019 Insilico and its collaborators from the University of Toronto published a proof-of-concept paper on the use generative tensorial reinforcement learning (GENTRL) for drug discovery in Nature journal. In 21 days the AI trained on known inhibitors of DDR1 kinase involved in progression of fibrosis generated potential ligands that went through sorting, scoring and review. The most promising ones went through in vitro and in vivo in the following 25 days, and the best molecule was found stable and potent against DDR1. The experiment was generally considered a substantial advance in generative drug design. Insilico respond to 2019—2020 coronavirus outbreak by using its AI methods to generate potential inhibitors of 3C-like protease, an enzyme critical for coronavirus reproduction, and providing open access to research data. As of the beginning of 2020 the company also had drug discovery programs for cancer, aging, fibrosis, Parkinson's disease, Alzheimer's disease, amyotrophic lateral sclerosis, diabetes and other conditions.

Biomarkers of Aging and Disease
Insilico Medicine works on biological aging clocks based on biomarkers in the blood, gut microbiome and other sources of data, and uses deep learning models to predict individual's biological age. If validated, such models may be used to track response in clinial trials of anti-aging medication. In 2015 and 2016 the company worked on "hematologic aging clocks" using a dataset composed of blood biochemistry and cell count test to train a neural network to estimate a person's age within a timeframe of 10 years with 83,5% accuracy and determining a person's sex with 99% accuracy without measureing hormone levels. The research paper was published in Aging journal and became the second most popular publication in its history. Future research allowed Insilico to improve precision withing 6 years. Insilico also managed to build a reliable method to determine smoking status using its age-prediction model to measure accelerated of biological aging due to tobacco consumption. In 2019 Insilico Medicine proposed a "microbiome aging clock" based on analysis of individual's gut microbiome. The algorithms trained on 1,165 samples was able to predict an individual's age within a margin of 4 years.

Partnerships and Associations
Insilico Medicine had over 150 academic and industry partnerships focused on validation and application of its technologies and clinical studies. Insilico's partners in big pharma include Pfizer, Jiangsu Chia Tai Fenghai Pharmaceutical,, and GlaxoSmithKline. Academic partners include the University of Copenhagen, Gachon University, Ageing Research at King's. It also has joint ventures with Juvenescence, Buck Institute for Research on Aging, A2A Pharmaceuticals, Bitfury Group. In 2018 Insilico Medicine together with AWS, Bayer, GE Healthcare, GlaxoSmithKline, Johnson & Johnson and other firms working on AI application in healthcare announced the creation of an industry-wide collaborative coalition named Alliance for Artificial Intelligence in Healthcare (AAIH). The Alliance is aimed at increasing education outreach on AI, promoting investments in AI R&D and developing policies and regulation in cooperation with governmental bodies in EU, US and beyond.

Locations and management
Insilico Medicine is headquartered in Hong Kong and employs 85 AI experts and scientists in research and development facilities in Belgium, Russia, South Korea, Taiwan, UK and the US. Insilico's founder Alex Zhavoronkov is the CEO. Insilico's research team has over 120 peer-reviewed publications with over 3,300 citations.