In order to speed up drug development and accelerate target identification, biopharma is increasingly turning to artificial intelligence (AI) and machine learning. Most recently, Hong Kong-based Insilico Medicine developed GENTRL, an AI system for drug discovery.
In its tests, GENTRL was able to “ideate and generate” a new molecule from beginning to end in 21 days—six molecules, in fact. In a more surprising move, Insilico has made GENTRL’s source code available as open source. GENTRL stands for general tensorial reinforcement learning. It has a two-step algorithm that maps and explores new compound structures within the scaffolding of chemical parameters. It then uses a machine learning model to “learn” DDR1 and common kinase inhibitors.
“The development of these first six molecules as an experimental validation is just the start,” stated Alex Zhavoronkov, chief executive officer of Insilico Medicine. “By enabling the rapid discovery of novel molecules and by making GENTRL’s source code open source, we are ushering in new possibilities for the creation and discovery of new life-saving medicine for incurable diseases—and making such powerful technology more broadly accessible for the first time to the public.”
Insilico developed GENTRL with WuXI AppTec, a contract research organization (CRO) and drug discovery company, and Alan Aspuru-Guzik, professor of chemistry and computer science at the University of Toronto and founder and chief scientific officer of quantum computing startup Zapata Computing.
Of the six molecules GENTRL developed, four inhibit DDR1 at nanomolar concentration. DDR1 is a protein target associated with a variety of diseases, including fibrosis. Details of the research were published in the journal Nature Biotechnology.
In May, AstraZeneca announced a long-term collaboration deal with BenevolentAI, a UK-based company focused on combining computational medicine and advanced artificial intelligence. The two companies will focus on using AI and machine learning to discover and develop new drugs for chronic kidney disease (CKD) and idiopathic pulmonary fibrosis (IPF).
“The vast amount of data available to research scientists is growing exponentially each year,” stated Mene Pangalo, AstraZeneca’s executive vice president and president BioPharmaceuticals R&D. “By combining AstraZeneca’s disease area expertise and large, diverse datasets with BenevolentAI’s leading AI and machine learning capabilities, we can unlock the potential of this wealth of data to improve our understanding of complex disease biology and identify new targets that could treat debilitating diseases.”
In early April, only a few weeks after Concerto HealthAI inked a deal with Bristol-Myers Squibb, it signed a similar deal with Pfizer. The commonality was Concerto focuses on oncology-specific Real-World Data (RWD) and advanced AI for Real-World Evidence (RWE) generation, an area of increasing interest for biopharma companies.
Concerto HealthAI will collaborate with Pfizer on Precision Oncology using Concerto’s eurekaHealth platform, artificial intelligence (AI) models and Real World Clinical Electronic Medical Record (EMR) and healthcare claims. They will use data from clinical medical practices that participate in the American Society of Clinical Oncology’s CancerLinQ initiative and others throughout the U.S.
In March 2019, Oxford Biomedica announced it had inked a two-year R&D collaboration with Microsoft Research. The goal is to improve the yield and quality of next-generation gene therapy vectors—typically viruses—using AI and machine learning.
Oxford Biomedica will focus on its expertise in vector development and large-scale manufacturing. The team in Microsoft’s Station B initiative will use AI and machine learning to increase the yield and improve the purity of Oxford Biomedica’s lentiviral vectors while cutting costs.
Station B will use the Microsoft Azure intelligent cloud platform to analyze large data sets created by Oxford Biomedical and develop in silico models and novel algorithms to advance cell and gene delivery technology.
And other companies are focusing on AI and machine learning. Recursion Pharmaceuticals, headquartered in Salt Lake City, Utah, is a clinical-stage biotech company that combines AI, experimental biology and automation to discover and develop drugs at scale.
On Jan. 7, 2019, Recursion announced progress in its collaboration with Takeda Pharmaceutical Company on identifying novel preclinical candidates for rare diseases. In 18 months, the partnership had led to the evaluation of Takeda preclinical and clinical compounds in more than 60 unique indications, with new therapeutic candidates identified in more than half-a-dozen diseases. As a result, Takeda exercised its option for drug candidates in two rare diseases and the two companies have extended the partnership.
Also in January, Recursion signed a licensing deal with the Ohio State Innovation Foundation (OSIF), acquiring rights to OSU-HDAC42, a clinical stage compound that will be developed by Recursion for neurofibromatosis type 2 (NF2), a rare tumor syndrome.
And a year ago, in August 2018, the Buck Institute for Research on Aging, Insilico Medicine, and Juvenescence, a human longevity company, founded Napa Therapeutics to develop drugs against a novel aging-related target.
Napa Therapeutics is built on research in NAD metabolism conducted by Eric Verdin, president and chief executive officer of the Buck Institute. His laboratory will collaborate with Napa, using Insilico’s drug development platform to accelerate compound discovery. “This is a unique opportunity to use cutting-edge AI to accelerate drug discovery,” Verdin said in a statement at the time. “The Buck is excited to join forces with Insilico and Juvenescence as we work to eliminate the threat of age-related disease for this and future generations.”
In the most recent news, Insilico’s GENTRL conceptualized and created 30,000 novel small molecules that had the potential to work against fibrosis. Then, it screened those and synthesized the six most promising molecules and then tested them in vitro for both selectivity and metabolic stability. They then tested it in mouse models, where it showed favorable activity.
Credit: Google News