For the general use of computer simulation in medicine, see In silico medicine.
This article may have been created or edited in return for undisclosed payments, a violation of Wikipedia's terms of use. It may require cleanup to comply with Wikipedia's content policies, particularly neutral point of view. (January 2023)
In 2011, Alex Zhavoronkov published an article in the journal PLOS One with Dr. Charles Cantor, previously director of the Human Genome Project at the Department of Energy (DOE) and founder of Sequenom on the International Aging Research Portfolio (IARP), establishing a public data set tracking government research funding and outcomes.[6] This work formed the basis for an artificial intelligence (AI) pharmacological analysis platform.
Zhavoronkov assertedly founded Insilico Medicine in 2014, as an alternative to animal testing for research and development programs in the pharmaceutical industry, using AI and deep-learning techniques to analyze how a compound will affect cells and what drugs can be used to treat the cells in addition to possible side effects. Through its Pharma.AI division, the company provides machine learning services to different pharmaceutical, biotechnology, and skin care companies.[7][8] Insilico is known for hiring mainly through hackathons such as their own MolHack online hackathon.[9]
The company has multiple collaborations in the applications of next-generation artificial intelligence technologies such as the generative adversarial networks (GANs) and reinforcement learning to the generation of novel molecular structures with desired properties.[10][11] In 2016, Insilico published an algorithm that it called the "Insilico Pathway Activation Network Decomposition Analysis" or "iPANDA" algorithm, asserted to allow researchers "to quickly and efficiently analyze signaling and metabolic pathway perturbation states using gene expression data".[12] In conjunction with Alan Aspuru-Guzik's group at Harvard, they published a journal article about an improved GAN architecture for molecular generation which combines GANs, reinforcement learning, and a differentiable neural computer.[13]
In 2017, Insilico was named one of the Top five AI companies by NVIDIA for its potential for social impact.[14] Insilico has R&D resources in Belgium, Russia, and the UK and hires talent through hackathons and other local competitions.[15] By mid-2017, Insilico had raised $8.26 million in funding from investors including Deep Knowledge Ventures, JHU A-Level Capital,[16]Jim Mellon,[17] and Juvenescence.[1][18][19][20] In 2019 it raised another $37 million from Fidelity Investments, Eight Roads Ventures, Qiming Venture Partners, WuXi AppTec, Baidu, Sinovation, Lilly Asia Ventures, Pavilion Capital, BOLD Capital, and other investors.[21]
The company "focused exclusively on drug discovery until 2019 when it began developing its own therapeutics".[22] In January 2021, Insilico entered into a partnership with Fosun Pharma, to facilitate entry into the Chinese market.[22] Later in 2021 after developing a novel preclinical candidate molecule for a novel target,[23] the company announced a series C $255 million megaround [24] from Warburg Pincus, Sequoia Capital, Orbimed, Mirae Asset Financial Group, and over 25 biotechnology, AI, and pharmaceutical investors.[25][26] By mid-2021, it claimed to have nominated eight preclinical candidates.[22] Another $60 million in new Series D financing was raised in 2022.[22] As of 2023[update] it was reported that over $400 million had been invested in the company.[27] In 2023, Zhavoronkov stated that he "moved the company's R&D to China to capitalize on 'half a trillion dollars' worth of infrastructure and hundreds of thousands of scientists [provided by the government] to enable AI-designed drugs".[28] In November 2024, Insilico was named one of the top 50 AI innovators by Fortune magazine.[29]
Research
The company "applies DL, big data, and genomis for in silico drug discovery" for various conditions.[2] It has sought to develop AI to "identify novel drug targets for untreated diseases", and has pursued dual-purpose therapeutics, "going after a specific disease or several diseases while targeting ageing at the same time".[27]
In 2019, the company in partnership with researchers at the University of Toronto, used AI to design potential new drugs. One was reported to have shown promising initial results when tested in mice.[30][31] Research areas for therapeutics have included fibrosis, immunology, oncology and the central nervous system.[22] To demonstrate the capacity of their proprietary AI platforms, the company published two projects on identifying therapeutic targets for ageing[32] and amyotrophic lateral sclerosis[33] in 29 March and 28 June 2022, respectively.[citation needed]
^Kadurin A, Nikolenko S, Khrabrov K, Aliper A, Zhavoronkov A (September 2017). "druGAN: An Advanced Generative Adversarial Autoencoder Model for de Novo Generation of New Molecules with Desired Molecular Properties in Silico". Molecular Pharmaceutics. 14 (9): 3098–3104. doi:10.1021/acs.molpharmaceut.7b00346. PMID28703000.
