20 Mar 20
20 Mar 20
BenevolentAI analyses approved drug as potential Covid-19 treatment

BenevolentAI has used artificial intelligence to identify and analyse an approved drug that may have potential as a coronavirus treatment.

The company, which has R&D premises on Babraham Research Campus, has published research naming its most promising lead.

Baricitinib is approved for treating rheumatoid arthritis, but clinical testing is required to prove it would be safe and effective for use against the Covid-19 virus.

It was identified using BenevolentAI’s knowledge graph, which ingests scientific literature at scale and uses machine learning to derive contextual relationships between genes, diseases, drugs and biological pathways, enabling novel or optimal drug targets to be identified.

The company published its initial findings on several drugs last month, identifying a group of approved drugs that could inhibit a process known as clathrin-mediated endocytosis, which is key to enable viruses to infect cells. Benevolent.AI has now followed this up with further analysis.

Writing in the Lancet journal, its researchers said: “To take this work further in a short timescale, a necessity when dealing with a new human pathogen, we re-examined the affinity and selectivity of all the approved drugs in our knowledge graph to identify those with both antiviral and anti-inflammatory properties.

“Such drugs are predicted to be of particular importance in the treatment of severe cases of COVID-19, when the host inflammatory response becomes a major cause of lung damage and subsequent mortality.”


Examining fedratinib, ruxolitinib and baricitinib, all of which are powerful anti-inflammatories, the company concluded that the latter was likely to be most effective because of its affinitive for AAK1 (adaptor-associated protein kinase 1) - an enzyme that play an important role in regulating the process of endocytosis.

The company explained: “This research found combinations of baricitinib with the directly acting antivirals currently being used in the Covid-19 outbreak could reduce viral infectivity, virus replication and also the aberrant host inflammatory response. The use of an AI-driven knowledge graph facilitated this rapid response.”

Speaking to BBC’s Click programme, Baroness Joanna Shields, CEO of BenevolentAI, said: “A lot of people are looking at anti-virals and how they might potentially treat the disease. We looked at it from a completely different way.

“We said, ‘What are the other types of approved drugs that might inhibit the progression of that disease in the body?’ We surfaced a number of drugs and then did some experimentation based on that, and further research, and then we came up with one drug that we think is best suited.

“It has both anti-inflammatory properties as well as the ability to stop what is called endocitosis, which is what enables the virus to enter the lungs, which is the most potentially dangerous outcome of the coronavirus.”

 Given as an oral once-daily dose, baricitinib has been well-tolerated in arthritis patients and Benevolent.AI said the data suggests “side-effects would be trivial”.

However, only after thorough clinical tests could the drug’s safety for Covid-19 patients be approved.

Source: https://www.cambridgeindependent.co.uk/business/benevolentai-analyses-approved-drug-as-potential-covid-19-treatment-9102147/ 

#ccc, #ccc #ccc-notify p, #ccc h3, #ccc p, #ccc .ccc-notify-button { font-size:14px; } #ccc .ccc-content--light #ccc-notify-accept.ccc-notify-button span { color: #fff !important; } #ccc-end { float: right; margin-top: 0; } #ccc .ccc-content--light .ccc-button-solid span { background: transparent; } #ccc #ccc-notify.ccc-notify__top.ccc-content--dark.ccc-content--highlight{ padding: 16px 12%; width: 100%; margin: 0 auto; } #ccc #ccc-notify h3 { padding-bottom: 15px; font-size: 16px; } h3.ccc-alert-title{ font-size: 15px; } .ccc-notify-text { padding-right: 6rem; } #ccc-notify-reject { display: none; } #ccc .ccc-notify-button.ccc-link.ccc-tabbable.ccc-notify-link{ display: block; background-color: transparent !important; border: 2px solid #ccc !important; min-width: 170px; } #ccc .ccc-notify-button.ccc-accept-button { min-width: 170px; } #ccc-module.ccc-module--slideout.ccc-module--left { top: 0; } #ccc-module.ccc-module--slideout { top: 0; bottom: 0; height: 60%; width: 100%; } #ccc-module.ccc-module--slideout { max-width: 100%; } #ccc-module.ccc-module--slideout.ccc-module--left { left: 0; animation-name: none; animation-name: mymove; /*slide-right*/ animation-duration: .5s; animation-iteration-count: 1; } @keyframes mymove { From {top: -120px;} to {top: 0px;} } #ccc-module { height: 450px; } .ccc-panel { position: absolute; top: 24px; left: 200px; right: 200px; } #ccc p.ccc-intro { padding-right: 200px; margin-top: 0; } #ccc #ccc-recommended-settings { margin-left: 0; float: right; clear: both; position: absolute; top: 30px; right: 0px; } #ccc-title::after { content: none; } label.checkbox-toggle-label { padding-bottom: 0px; } #ccc .checkbox-toggle--light { background-color: #00a4b5; border-color: #00a4b5; } #ccc .checkbox-toggle--light .checkbox-toggle-toggle { background-color: #fff; } #ccc .ccc-content--light .ccc-button-solid { background: #00a4b5; } #ccc .ccc-content--light .ccc-notify-button { color: #000; border-color: #00a4b5; background: #00a4b5; } #ccc .ccc-content--light .ccc-notify-button { color: #fff; background: #00a4b5; } #ccc .ccc-notify-button.ccc-accept-button { font-weight: bold; } #ccc .ccc-content--light #ccc-notify-accept.ccc-notify-button { color: #fff; } #ccc .ccc-notify-button.ccc-link.ccc-tabbable.ccc-notify-link { color: #000; text-decoration: none; } @media only screen and (max-width: 599px) { #ccc .ccc-content--light #ccc-notify-accept.ccc-notify-button{ float: left; } } @media only screen and (max-width: 600px) { .ccc-panel { left: 20px; right: 20px; } #ccc #ccc-recommended-settings { float: none; position: relative; top: 0; right: 0px; } #ccc p.ccc-intro { padding-right: 0; } .ccc-notify-text { padding-right: 20px; } } @media only screen and (min-width: 600px) and (max-width: 1000px) { .ccc-panel { left: 50px; right: 50px; } }