Hong Kong-based clinical stage drug discovery company Insilico Medicine just announced the nomination of a novel preclinical drug candidate for treating COVID-19, de novo designed using the company’s artificial intelligence platform Chemistry42. The new drug candidate is a 3CL protease inhibitor which is unique from existing drugs in its class because it can be rapidly produced.
Image credit CROCOTHERY, iStock
The COVID-19 pandemic
According to a technical report by Innophore, the Coronavirus (WHO 2019nCoV) that caused the historical global COVID-19 pandemics is a positive sense, single stranded RNA beta coronavirus, a member of Beta-CoV lineage B (subgenus Sarbecovirus), possessing paramount ability for human-to-human transmission. The RNA sequence is around 30 kb in length.
The unprecedented speed of the pandemics progression led to a healthcare crisis, where hospitals faced a flood of patients with severe forms of COVID-19 disease, while lacking necessary equipment and personnel to meet substantially excessive demand. The world’s inability to react quickly to the pandemics of this size and speed led to a detrimental output: according to WHO, there are more than half a billion cases of COVID-19 globally, of which more than 6 million cases led to death. One of the key reasons for such a tragic output was that antiviral options available at the time the pandemic struck, proved to be of low effectiveness.
The role of Artificial Intelligence in tackling COVID-19 pandemics
Tackling a COVID-19 pandemics, is fighting with time. The amount of infected people grew rapidly and they needed efficient antivirals and vaccines sooner than later. On the other hand, the adoption of artificial intelligence (AI) is a known and widely chased way to accelerate research. When the pandemic struck, many organizations re-focused existing artificial intelligence capabilities towards various needs associated with the health crisis -- from drug discovery and vaccine development, to optimizing production and logistics processes, epidemiologic modeling and prediction, high-throughput diagnostics of patients at scale, and sorting real world data for medical treatment demand forecasting.
A vivid example of a company that managed to demonstrate the effectiveness of research automation and application of AI-driving modeling and predictive analytics is Moderna (NASDAQ: MRNA), one of the most “digitized” biotechs out there. A lucky convergence of technologies, such as mRNA and its delivery method via LNPs, supported by advanced digital tools and AI algorithms, allowed Moderna to develop a successful COVID-19 vaccine with a surprising speed, within months. Moderna’s input in tackling the coronavirus pandemic is impressive, with more than 200 million doses of its vaccine administered in the US alone.
However, being predominantly a prophylactic measure, vaccination alone is not enough to tackle the crisis. Since the beginning of the pandemic, the global healthcare system has been in desperate need for efficient antivirals to treat those patients who got infected by the coronavirus.
There are two main strategies for the application of artificial intelligence technologies in discovering novel efficient antivirals: to use AI to sift through tens of thousands of already known potential therapies to identify successful drug repurposing options (e.g. among known antivirals, relevant compounds from commercial compound catalogs, etc). or to create something completely new (de novo drug design).
The first strategy offers a shorter path to the public, which is important. In fact, most of the immediate drug discovery efforts at the beginning of the COVID-19 pandemics were focused on drug repurposing of known clinically-approved drugs and virtual screening for the molecules available from chemical libraries. In early 2020, London-based BenevolentAI successfully applied their AI system Knowledge Graph to quickly identify a potential COVID-19 treatment baricitinib – a known rheumatology drug. According to Dr. Jackie Hunter, BenevolentAI’s Scientific Advisor, it took only 48 hours to progress an idea to an actionable research discovery. The drug, owned by Eli Lilly (NYSE: LLY), has later entered clinical trials and was granted FDA approval for certain hospitalized patients with COVID-19.
Overall, drug repurposing, however, has limitations. For example, the IC50 of lopinavir, an HIV protease inhibitor, against the 3C-like protease was found to be approximately 50 micromolar, which was far from ideal.
The second strategy, de novo drug design, is a more complicated and long story, but it can provide a more complete solution to the problem eventually -- an efficient first-in-class or best-in-class antiviral. In an attempt to come up with a bold solution for the ongoing pandemic crisis, and potentially for possible future pandemics, Insilico Medicine chose to go this more complicated route and in early 2020 it dedicated a part of its generative chemistry pipeline Chemistry42 to design novel drug-like inhibitors of COVID-19.
Many potential therapeutics aimed at containing the spread of SARS-CoV-2 have targeted the S, or spike, protein, a surface protein that plays a vital role in viral entry into host cells, since that is the approach that was taken with both SARS and MERS coronaviruses. However, according to a study by Insilico Medicine in collaboration with Nanome, published back in 2020, two-thirds of the SARS-CoV-2 genome comprised non-structural proteins, such as the viral protease (the protein necessary for viral replication). It was concluded that C30 Endopeptidase, also referred to as the 3C-like protease (3CLP) or coronavirus main protease (Mpro) was a promising target to focus on.
In designing COVID-19 antivirals, Insilico Medicine combined two molecular design approaches: ligand-based and crystal structure–based and later published a series of representative structures for potential development. The company just announced a new preclinical candidate for the treatment of SARS-CoV-2 -- a novel 3C-like (3CL) protease inhibitor.
A broader goal for AI: preparing for future pandemics
The key danger of highly contagious pathogens, like it was with the devastating plague events in middle ages, the famous Great Influenza epidemic of 1920th and as was the case once again with the ongoing COVID-19 pandemics, is the rapid dynamics of a disease spread in the population, causing high mortality rates. Therefore, the ability to develop novel antiviral drugs or antibiotics rapidly, based on the relevant data about a novel pathogen, is the key necessity. This can potentially be achieved with the AI-driven drug discovery approach, when timelines for the early drug design phase can be realistically shortened down to months or even days (which, of course, does not take away necessity for preclinical and clinical studies, which still take time).
The example of Insilico Medicine is notable in that the company has been able to demonstrate repeatedly the utility of their AI-system Pharma.AI for accelerated drug discovery. In the past 12 months, the company delivered six AI-designed preclinical candidates in a variety of disease areas, including fibrosis, inflammation, and oncology, including one for the QPCTL immuno-oncology target in partnership with Fosun Pharma. The present nomination of the 3CL protease inhibitor to treat COVID-19 is the latest milestone, relevant for the ongoing COVID-19 pandemic. More importantly, this gives hope that such highly integrated AI systems, capable of accelerated target discovery and drug design -- and the new approach to drug discovery they enable -- will give better options to address possible future viral and bacterial outbreaks.
Following up on this idea, on May 24 “digital biotech” Moderna announced that it is already testing potential vaccines against monkeypox in preclinical trials as the disease spreads in the United States and Europe. Most probably, we will see novel antiviral drug candidates against monkeypox fairly soon, too. It is yet unclear what risks this new outbreak is bringing and whether it can grow into a new pandemic, but who knows...?
Topics: Novel Therapeutics