AI-Powered Drug Discovery for Covid-19

COVID-19 has become a turning point that could see long-running predictions about how AI will forever change healthcare become a reality. Companies are racing to find treatments for the novel coronavirus, which has infected more than 200,000 people, are turning to artificial intelligence to speed up their drug-discovery efforts.

Developing a drug that makes it to clinical trials often takes more than a year. The hope is that AI, which can spot patterns and make predictions, could identify drug prospects to test on humans within months.

Data is also essential if AI is to help develop treatments for the disease. One technique for identifying possible drug candidates is to use generative design algorithms, which produce a vast number of possible results and then sift through them to highlight those that are worth looking at more closely. This technique can be used to quickly search through millions of biological or molecular structures, for example.

Several research projects are using AI to identify drugs that were developed to fight other diseases but which could now be repurposed to take on coronavirus. By studying the molecular setup of existing drugs with AI, companies want to identify which ones might disrupt the way COVID-19 works. 

In a broad sense, AI could be enormously helpful for initial drug discovery in two main ways: one, screening through millions of chemical compounds for potential drugs in simulation tests, far faster than any human expert; two, identifying targets that new medications can latch onto, either to reduce their impact (making people less sick) or to slow their spread among people.

Leveraging the information with Machine Learning to explore different scenarios and learn from those results could be a game-changer in finding a set of drugs to fight this type of outbreak. Since the world is more connected than ever, having different researchers, hospitals and countries, providing data into the datasets that get processed, could also speed up the results tremendously.

All efforts to curb the situation is worth every praise, but the fight can only be successful when we can develop a vaccine that can immunize everyone against the virus. Developing an antidote or a vaccine is not an easy process as it is lengthy as well as expensive. It is where AI can help to fight Corona by speeding up the process. 

One startup with huge potential to stem the coronavirus crisis is British unicorn, a London-based drug-discovery company, began turning its attentions towards the coronavirus problem in late January. Benevolent AI, the business, which has banked $292m in funding since it was founded in 2013, is known for building artificially intelligent systems the help find drugs to treat chronic diseases. The company’s AI-powered knowledge graph can digest large volumes of scientific literature and biomedical research to find links between the genetic and biological properties of conditions and the composition and action of drugs. Uses AI systems to build drugs that can fight the world’s most hardened diseases and is now helping support the efforts to treat coronavirus, the first time the company focused its product on infectious diseases. Within weeks of the outbreak, it used its predictive capabilities to propose existing drugs that might be useful.  

Companies in the same manner with, BlueDot, Nanox, Vir Biotechnology, SRI International, Exscienta, Atomwise, Sage Health, Healx, AbCellera, BioSymetrics, Mila, DeepMind (acquired by Google)  and Insilico Medicine are among the biotechnology companies employing AI to discover potential coronavirus medicines. They will prove increasingly essential in warding off future coronavirus-style pandemics, and with it, they’ll provide one convincing example of AI being a force for good.

The world’s biggest tech companies have jumped at the opportunity to help. Alphabetthe parent company of Google, put its DeepMind artificial intelligence unit onto the task of finding a vaccine, and its Verily life-sciences research unit is working on virus detection. 

Insilico Medicine hopes to have potential treatments it already began testing in partnership with a pharmaceutical company in April this year. SRI International is collaborating on such an AI tool, which uses deep learning to generate many novel drug candidates that scientists can then assess for efficacy. It is a game-changer for drug discovery, but it can still take many months before a promising candidate becomes a viable treatment. Longevity Vision Fund’s portfolio company Insilico Medicine, which specializes in AI in the area of drug discovery and development, used its AI-based system to identify thousands of new molecules that could serve as potential medications for coronavirus in just four days. The speed and scalability of AI are essential to fast-tracking drug trials and the development of vaccines. Sage Health sponsored an open-source Drug Discovery Competition, where the three top submissions identified potential treatments using machine learning. Several drug discovery companies are also using AI-powered techniques to discover both new and existing molecules that can be used to combat COVID-19. Exscienta has shown. Earlier this year, they became the first company to present an AI designed drug molecule that has gone to human trials. A year is all it took the algorithm to develop the molecular structure compared with the five-year average time that it takes traditional research methods. Cambridge-based Healx has a similar approach, but it uses machine learning to find new uses for existing drugs. Both companies feed their algorithms with information, gleaned from sources such as journals, biomedical databases, and clinical trials to help suggest new treatments for diseases. 

In response to the COVID-19 pandemic, where a virus is spreading rapidly, getting more accurate scores faster is critical to speeding up drug development, it’s vital to come up with a vaccine, a reliable diagnostic method, and a drug for treatment fast. 

Part of what has troubled the scientific community is the absence of a definitive cure for the virus. AI can potentially be a game-changer. Current methods involve a lot of trial and error, which takes time. It can take months to isolate even one viable vaccine candidate. Machine learning can speed up this process significantly without sacrificing quality control.

This kind of treatment-discovery will prove vitally important in the future. And in conjunction with screening, it suggests that artificial intelligence will become one of the primary ingredients in ensuring that another coronavirus won’t have an outsized impact on the global economy. 

Already, the COVID-19 coronavirus is likely to cut global GDP growth by $1.1 trillion this year, in addition to having already wiped around $5 trillion off the value of global stock markets. Avoiding such financial destruction in the future would be more than welcome, and artificial intelligence will prove indispensable in this respect, especially as the scale of potential pandemics increases with an increasingly populated and globalized world.

References:

https://towardsdatascience.com/covid-19-and-drug-development-b800d8917b50

https://towardsdatascience.com/fight-covid-19-with-machine-learning-1d1106192d84

https://www.kdnuggets.com/2020/04/data-science-understand-covid-19.html. Accessed 23 Apr. 2020

https://healthitanalytics.com/news/data-scientists-use-machine-learning-to-discover-covid-19-treatments. Accessed 23 Apr. 2020

https://healthitanalytics.com/news/understanding-the-covid-19-pandemic-as-a-big-data-analytics-issue. Accessed 23 Apr. 2020

https://www.bbc.com/news/technology-52120747. Accessed 23 Apr. 2020

https://www.datanami.com/2020/03/23/can-ai-find-a-cure-for-covid-19/ Accessed 22 Apr. 2020

https://thenextweb.com/neural/2020/03/21/why-ai-might-be-the-most-effective-weapon-we-have-to-fight-covid-19/ Accessed 22 Apr. 2020

https://www.wsj.com/articles/supercomputers-help-researchers-speed-drug-discovery-for-covid-19-11586888735. Accessed 22 Apr. 2020

https://singularityhub.com/2020/03/17/how-deepminds-ai-is-working-to-decode-coronavirus/. Accessed 22 Apr. 2020

https://sciencebusiness.net/news/computer-science-versus-covid-19. Accessed 22 Apr. 2020

https://www.wired.com/story/ai-uncovers-potential-treatment-covid-19-patients/. Accessed 22 Apr. 2020

https://www.forbes.com/sites/bernardmarr/2020/03/13/coronavirus-how-artificial-intelligence-data-science-and-technology-is-used-to-fight-the-pandemic/#51d375715f5f. Accessed 22 Apr. 2020

https://www.vox.com/recode/2020/2/7/21125959/artificial-intelligence-coronavirus-benevolent-ai-treatment. Accessed 21 Apr. 2020

https://ourworldindata.org/coronavirus

https://www.worldometers.info/coronavirus/

https://www.sciencedirect.com/science/article/pii/S1359644620301458 Accessed 21 Apr. 2020

https://www.cnbc.com/2020/03/03/bluedot-used-artificial-intelligence-to-predict-coronavirus-spread.html. Accessed 22 Apr. 2020

https://www.wired.com/story/ai-epidemiologist-wuhan-public-health-warnings/ Accessed 21 Apr. 2020

https://diginomica.com/how-canadian-ai-start-bluedot-spotted-coronavirus-anyone-else-had-clue Accessed 21 Apr. 2020

https://www.technologyreview.com/2020/03/12/905352/ai-could-help-with-the-next-pandemicbut-not-with-this-one/ Accessed 21 Apr. 2020

https://www.utoronto.ca/news/u-t-infectious-disease-expert-s-ai-firm-now-part-canada-s-covid-19-arsenal. Accessed 21 Apr. 2020

https://thenextweb.com/neural/2020/03/21/why-ai-might-be-the-most-effective-weapon-we-have-to-fight-covid-19/. Accessed 21 Apr. 2020

https://fortune.com/2020/03/16/ai-coronavirus-health-technology-pandemic-prediction/. Accessed 21 Apr. 2020

https://betakit.com/canada-commits-192-million-to-covid-19-sif-stream-signs-deal-with-bluedot-to-help-track-make-decisions-on-virus/. Accessed 20 Apr. 2020

https://www.forbes.com/sites/simonchandler/2020/03/05/how-ai-will-prevent-the-next-coronavirus-pandemic/#65d70ddb4ac6. Accessed 20 Apr. 2020

https://www.thelancet.com/journals/landig/article/PIIS2589-7500(20)30054-6/fulltext. Accessed 20 Apr. 2020

https://theconversation.com/predicting-the-coronavirus-outbreak-how-ai-connects-the-dots-to-warn-about-disease-threats-130772. Accessed 20 Apr. 2020

https://www.weforum.org/agenda/2020/03/covid-19-crisis-artificial-intelligence-creativity/. Accessed 20 Apr. 2020

https://singularityhub.com/2020/02/05/how-ai-helped-predict-the-coronavirus-outbreak-before-it-happened/. Accessed 20 Apr. 2020

https://www.brookings.edu/research/a-guide-to-healthy-skepticism-of-artificial-intelligence-and-coronavirus/. Accessed 20 Apr. 2020

https://www.dw.com/en/how-ai-tracks-covid-19-and-why-that-helps-save-lives/av-52864500. Accessed 20 Apr. 2020

https://techcrunch.com/2020/04/14/potential-new-treatment-for-covid-19-uncovered-by-benevolentai-enters-trials/. Accessed 19 Apr. 2020

https://benevolent.ai/news/potential-treatment-for-covid-19-identified-by-benevolentai-using-artificial-intelligence-enters-clinical-testing. Accessed 19 Apr. 2020

https://www.wired.com/story/ai-uncovers-potential-treatment-covid-19-patients/. Accessed 19 Apr. 2020

https://www.fiercepharma.com/pharma/lilly-partners-nih-to-test-olumiant-patients-hospitalized-covid-19. Accessed 19 Apr. 2020

https://www.businessinsider.com/benevolentai-uncovered-potential-coronavirus-treatment-2020-4. Accessed 19 Apr. 2020

https://sciencebusiness.net/news/computer-science-versus-covid-19. Accessed 19 Apr. 2020

https://spectrum.ieee.org/the-human-os/artificial-intelligence/medical-ai/companies-ai-coronavirus. Accessed 19 Apr. 2020

https://www.telegraph.co.uk/technology/2020/03/23/ai-can-help-us-find-drug-treat-coronavirus/. Accessed 19 Apr. 2020

https://www.vox.com/recode/2020/2/7/21125959/artificial-intelligence-coronavirus-benevolent-ai-treatment. Accessed 19 Apr. 2020

https://www.nytimes.com/2020/04/13/health/coronavirus-arthritis-drug-baricitinib.html. Accessed 19 Apr. 2020

https://www.bbc.com/news/technology-52120747. Accessed 19 Apr. 2020

https://www.zdnet.com/article/ai-and-the-coronavirus-fight-how-artificial-intelligence-is-taking-on-covid-19/. Accessed 19 Apr. 2020

https://www.forbes.com/sites/simonchandler/2020/03/05/how-ai-will-prevent-the-next-coronavirus-pandemic/#7aeffb5b4ac6. Accessed 19 Apr. 2020

https://mc.ai/ai-update-covid-19-ai-tools-and-ai-breakthroughs/. Accessed 19 Apr. 2020

https://www.itnonline.com/content/nanox-partners-qureai-integrate-ai-based-alg/orithms-medical-imaging. Accessed 19 Apr. 2020

https://www.vir.bio/virus/

https://www.ft.com/content/1ea37c86-6a6c-42b1-a996-ba43365d9e8f

https://www.statnews.com/2020/03/25/vir-biotechnology-reports-early-progress-in-antibody-treatment-for-covid-19/. Accessed 19 Apr. 2020

https://www.fool.com/investing/2020/04/06/glaxosmithkline-and-vir-biotechnology-jump-in-race.aspx. Accessed 19 Apr. 2020

https://www.fiercepharma.com/manufacturing/vir-inks-deal-samsung-to-scale-up-covid-19-antibody-manufacturing Accessed 18 Apr. 2020

https://www.sri.com/iktos-and-sri-international-announce-collaboration-to-combine-artificial-intelligence-and-novel-automated-discovery-platform-for-accelerated-development-of-new-anti-viral-therapies/press-release/ Accessed 18 Apr. 2020

https://www.worldometers.info/

https://www.pharmaceutical-technology.com/news/iktos-sri-covid-19-drug-development/ Accessed 15 Apr. 2020

https://www.exscientia.ai/news-insights/exscientia-announces-joint-initiative-to-identify-covid-19. Accessed 15 Apr. 2020

https://www.theguardian.com/business/2020/mar/31/oxford-firm-to-screen-15000-drugs-in-search-for-coronavirus-treatment. Accessed 15 Apr. 2020

https://www.pharmaceutical-technology.com/news/exscientia-covid-19/. Accessed 14 Apr. 2020

https://www.wsj.com/articles/biotech-companies-tap-ai-to-speed-path-to-coronavirus-treatments-11583451564. Accessed 14 Apr. 2020

https://techcrunch.com/2018/03/07/atomwise-which-uses-ai-to-improve-drug-discovery-raises-45m-series-a/. Accessed 14 Apr. 2020

https://www.pharmaceutical-business-review.com/news/biomotiv-and-atomwise-sign-ai-partnership-to-transform-therapeutic-development/. Accessed 14 Apr. 2020

https://www.wired.com/story/ai-uncovers-potential-treatment-covid-19-patients/. Accessed 12 Apr. 2020

https://techcrunch.com/2018/03/07/atomwise-which-uses-ai-to-improve-drug-discovery-raises-45m-series-a/ Accessed 10 Apr. 2020

https://www.gov.uk/government/groups/scientific-advisory-group-for-emergencies-sage-coronavirus-covid-19-response

https://www.sage-health.org/coronavirus/

https://www.who.int/immunization/policy/sage/en/. Accessed 9 Apr. 2020

https://www.telegraph.co.uk/global-health/science-and-disease/sage-member-jeremy-farrar-warns-covid-19-stay-vaccines-treatments/. Accessed 7 Apr. 2020

https://www.information-age.com/healx-use-ai-platform-healnet-find-covid-19-treatments-123488827/ Accessed 7 Apr. 2020

https://healx.io/wp-content/uploads/2020/04/Healx-COVID-19-Press-Release-06.04.20.pdf

https://www.bbc.com/news/technology-52120747

https://theconversation.com/coronavirus-a-former-member-of-sage-explains-how-the-science-advisory-group-really-works-134077. Accessed 7 Apr. 2020

https://techcrunch.com/2019/10/16/healx/. Accessed 7 Apr. 2020

https://www.sage.com/en-gb/coronavirus/

https://www.abcellera.com/news/2020-03-abcellera-and-lilly-codevelopment

https://www.cnbc.com/video/2020/03/15/eli-lilly-and-abcellera-partner-up-on-covid-19-drugs.html. Accessed 6 Apr. 2020

https://www.wsj.com/articles/biotech-company-uses-machine-learning-to-find-coronavirus-therapies-11584437401. Accessed 6 Apr. 2020

https://www.wired.com/story/darpa-cranks-up-antibody-research-to-stall-coronavirus/. Accessed 6 Apr. 2020

https://www.bloomberg.com/news/articles/2020-03-12/eli-lilly-is-said-to-join-race-to-develop-coronavirus-treatment. Accessed 5 Apr. 2020

https://www.reuters.com/article/health-coronavirus-lilly/update-1-eli-lilly-abcellera-biologics-to-co-develop-coronavirus-therapies-idUSL4N2B55OX. Accessed 5 Apr. 2020

https://www.nature.com/articles/d41587-020-00005-z. Accessed 5 Apr. 2020

https://www.technologyreview.com/2020/04/10/998897/the-race-to-make-a-covid-19-drug-from-the-blood-of-survivors/. Accessed 11 Apr. 2020

https://www.forbes.com/sites/johncumbers/2020/03/25/timeline-shows-3-paths-to-covid-19-treatment-and-prevention-infographic/#45c15cd34789. Accessed 13 Apr. 2020

https://finance.yahoo.com/news/biosymetrics-launches-augusta-architect-faster-143200794.html. Accessed 14 Apr. 2020

https://mila.quebec/en/covid-19/

https://syncedreview.com/2020/03/27/un-who-mila-map-the-ai-vs-covid-19-battlefield/. Accessed 15 Apr. 2020

https://deepmind.com/research/open-source/computational-predictions-of-protein-structures-associated-with-COVID-19

https://www.zdnet.com/article/google-deepminds-effort-on-covid-19-coronavirus-rests-on-the-shoulders-of-giants/. Accessed 16 Apr. 2020

https://singularityhub.com/2020/03/17/how-deepminds-ai-is-working-to-decode-coronavirus/. Accessed 16 Apr. 2020

https://www.wired.com/story/opinion-ai-can-help-find-scientists-find-a-covid-19-vaccine/. Accessed 16 Apr. 2020

https://www.businessinsider.com/google-deepmind-david-silver-ai-covid-19-treatment-medical-2020-4. Accessed 16 Apr. 2020

https://www.psychologytoday.com/us/blog/the-future-brain/202003/deepmind-uses-ai-help-fight-covid-19. Accessed 13 Apr. 2020

https://www.telegraph.co.uk/technology/2020/03/06/deepminds-ai-could-speed-research-coronavirus-vaccine/. Accessed 12 Apr. 2020

https://www.bbc.com/news/technology-51851292. Accessed 11 Apr. 2020

https://thenextweb.com/neural/2020/03/21/why-ai-might-be-the-most-effective-weapon-we-have-to-fight-covid-19/. Accessed 10 Apr. 2020

https://www.bloomberg.com/news/articles/2020-04-07/coronavirus-isn-t-stopping-europe-s-push-to-regulate-ai. Accessed 17 Apr. 2020

https://fortune.com/2020/02/06/ai-identifies-possible-coronavirus-treatment/. Accessed 16 Apr. 2020

https://insilico.com/

https://www.wsj.com/articles/biotech-companies-tap-ai-to-speed-path-to-coronavirus-treatments-11583451564. Accessed 15 Apr. 2020

https://www.thelancet.com/journals/landig/article/PIIS2589-7500(20)30054-6/fulltext. Accessed 14 Apr. 2020

One thought on “AI-Powered Drug Discovery for Covid-19”

  1. Like!! I blog frequently and I really thank you for your content. The article has truly peaked my interest.

Leave a Reply

Your email address will not be published. Required fields are marked *