yesHayden FieldNone
×

Get access to Protocol

Will be used in accordance with our Privacy Policy

I’m already a subscriber
People

Inside a startup’s pivot to have AI fight coronavirus

Insilico Medicine repurposed its machine learning systems to dream up treatments for coronavirus. Its CEO says it's going well — but the process isn't without hiccups.

Alex Zhavoronkov, the co-founder and CEO of Insilico Medicine

Insilico Medicine's Alex Zhavoronkov is hoping that AI can help speed development of a drug for COVID-19.

Photo: Courtesy of Insilico

With almost half a million reported cases of coronavirus around the world now, the race is on to develop a treatment. Alex Zhavoronkov, the co-founder and CEO of Insilico Medicine, is among those who think that artificial intelligence could help expedite a market-ready drug.

His Hong Kong-based biotech company has repurposed its platforms for the fight against COVID-19. It aims to use "a huge Lego system" of machine learning techniques for drug discovery — and, in this case, Insilico's algorithms have dreamed up tens of thousands of unique molecules that could potentially handicap the protein responsible for the virus' spread.


Get what matters in tech, in your inbox every morning. Sign up for Source Code.


The company's approach isn't without risk. In order to increase the potential drug's selectivity and decrease side effects, Insilico is banking on non-covalent-binding molecules. Unlike other treatments, these will only bind to what they're designed for: one type of COVID-19 protein. That means there's less of a chance of these molecules being successful — but if they do meet their goal, it'll ultimately be more accurate than another approach.

It also isn't without hype: The company has claimed that it can dramatically accelerate the drug development process using machine learning — and that it hopes to begin testing on humans within a couple of months.

Protocol spoke with Zhavoronkov about how Insilico repurposed its platform for virus research, the setbacks the company experienced after the onset of COVID-19, and why he believes machine learning could shorten the timeline for getting coronavirus drugs into clinical trials.

This interview has been edited for length and clarity.

Tell us about the before and after for your company when it comes to the novel coronavirus. What kinds of projects and technologies were you prioritizing before?

Wow, that's a very unusual question because it's an insider's view. We spent more than $10 million on a generative chemistry platform that essentially combines many machine learning techniques together — generative adversarial networks, reinforcement learning, genetic algorithms. It's essentially a huge Lego system of machine learning algorithms that can handle multiple cases.

We were focusing primarily on cancer, fibrosis and many other diseases, and we still are — so we haven't significantly pivoted in terms of our pipeline. However, we've prioritized several projects related to COVID-19 specifically. One of the three parts of our pipeline is focused on mining massive amounts of omics data to be able to find potential therapeutic targets. We've repurposed that for viruses right now.

When news of COVID-19 hit, what was the scramble like?

In early January, we learned about COVID-19. In mid-January, we recognized that there was a problem. In late January, I brought it to my board members and investors and said, "Hey guys, let's work on this." Some of them were not very happy about it because they thought it would go away, just like SARS. (If you remember what happened with SARS, everybody who started drug discovery programs lost because the funding disappeared, and it was really not prioritized as it should have been.) We ended up deciding to use our generative chemistry pipeline — which is ready and specifically designed for these kinds of cases — on some of the most validated, best targets for COVID-19. On Jan. 28, we started the program.

How would you describe that pipeline that you repurposed for this coronavirus?

You know how people make deepfakes — those kinds of imaginative videos, which are sometimes used for all kinds of malicious purposes? There's one type where you can create photographs with specific features and properties. We do the same thing but on molecules — we create molecules with specific properties. In layman's terms, it's essentially imaginative AI. You're creating billions of examples, some virtual, and making deep neural networks imagine new molecular structures that fit into a specific protein target.

Tell us more about how you're using reinforcement learning in this context. I hear you're employing it to encourage the molecules to go after specific objectives?

One approach is when you have a crystal structure of the protein target, so you know the shape and how [the protein] looks. Once we have that, we use AI to "sniff" the shape for binding pockets where a molecule can fit. (When you fit the protein with a small molecule, it disables it.) Once it identifies those pockets, it imagines new molecules — hundreds of thousands of molecules — that could fit onto it. Those molecules do not exist in nature. They are imagined.

And afterward, we have a set of reinforcement learning algorithms that essentially make this AI imagination more robust. You imagine with a specific objective in mind; you want to have very high activity, and you want to have selectivity, and you want to have safety. We generated a bunch of compounds: 100,000 unique molecules, then narrowed it down to 100 and chose seven from there.

How did the onset and spread of COVID-19 affect your lab processes, even as you were researching the virus?

We got into a little bit of trouble because, at that time, the epidemic was very active in Asia. And the way the drug discovery industry is organized … specifically for chemical synthesis, most people do it externally.

It's kind of like Apple, right? They don't assemble their own machines. They send it to Foxconn or some other contract manufacturer, which assembles it for Apple based on its instructions. That's what we're doing at Insilico: We don't have our own lab, but we work with more than 80 other labs worldwide, from which we order experiments.

About 90% of our chemistry is synthesized in China by contract research organizations. And it turned out that when we published our structures, it was still the middle of the Chinese New Year — and right afterward, the government extended the new year. Nobody was working. Nobody could synthesize it for us.

So we decided to publish the molecules. Previously, our generative chemistry approach was sometimes criticized for not making diverse enough molecules. This time, many medicinal chemists looked at the molecules, and they liked them.

How will you continue the process?

We've synthesized one molecule so far. Later on, we'll send it for the ultimate test: to see if it works in virus-infected cells. And after that, we need to do an animal test. Only after that can we test on humans. Technically this process, even though we've accelerated it, might take nine months to get the molecule into humans — maybe sooner, depending on how quickly we can ramp it up.

We've [also] identified a couple of other really promising targets, so we're going to publish more molecules.

You've said you hope to have something ready for clinical trials as soon as April. It usually takes more than a year to ready a prospective drug for human testing. How has AI whittled it down to months?

They'll probably be ready for human testing in a couple of months. But in about two weeks, we'll have the results from the assays, or experimental systems — we'll know whether those molecules worked. If you go the standard route, after you've proven the efficacy in vitro and in mice, then you have to apply for the phase one clinical study — and even the application takes a long time. It's more of a bureaucracy than anything else. And bureaucracy is there for a very good reason, so we aren't going to break any rules.

But when our system spits out the molecules, they are usually very druglike — they require either minimal modifications or none at all. The chances are very high that we can make the claim that they are ready because they have all the properties of a good drug. That's the beauty of AI versus everything else: We don't need to have many cycles of synthesis.


Get in touch with us: Share information securely with Protocol via encrypted Signal or WhatsApp message, at 415-214-4715 or through our anonymous SecureDrop.


So the reason the process usually takes about a year is that you typically need many cycles of synthesis, but since you're using these new techniques, you believe they'll likely be ready in just a few months?

That's absolutely correct. Also, here we took a little bit of a riskier approach. There are two ways of designing those molecules. We know other companies are working on what's called covalent inhibitors; they're inhibitors that bind to the main protease strongly as well as many other things, so they're less selective and there might be side effects. But we designed noncovalent binders. So far, there are no known noncovalent binders for the main protease.

In our case, it's really kind of like when you bet $1 million on a boxer. You're waiting for a match. My next two weeks are that: I'm waiting on those molecules to see which one works and which one performs better.

Protocol | Fintech

Plaid’s COO is riding fintech’s choppy waves

He's a striking presence on the beach. If he navigates Plaid's data challenges, Eric Sager will loom large in the financial world as well.

Plaid COO Eric Sager is an avid surfer.

Photo: Plaid

Eric Sager is an avid surfer. It's a fitting passion for the No. 2 executive at Plaid, a startup that's riding fintech's rough waters — including a rogue wave on the horizon that could cause a wipeout.

As Plaid's chief operating officer, Sager has been helping the startup navigate that choppiness, from an abandoned merger with Visa to a harsh critique by the CEO of a top Wall Street bank.

Keep Reading Show less
Benjamin Pimentel

Benjamin Pimentel ( @benpimentel) covers fintech from San Francisco. He has reported on many of the biggest tech stories over the past 20 years for the San Francisco Chronicle, Dow Jones MarketWatch and Business Insider, from the dot-com crash, the rise of cloud computing, social networking and AI to the impact of the Great Recession and the COVID crisis on Silicon Valley and beyond. He can be reached at bpimentel@protocol.com or via Signal at (510)731-8429.

Sponsored Content

The future of computing at the edge: an interview with Intel’s Tom Lantzsch

An interview with Tom Lantzsch, SVP and GM, Internet of Things Group at Intel

An interview with Tom Lantzsch

Senior Vice President and General Manager of the Internet of Things Group (IoT) at Intel Corporation

Edge computing had been on the rise in the last 18 months – and accelerated amid the need for new applications to solve challenges created by the Covid-19 pandemic. Tom Lantzsch, Senior Vice President and General Manager of the Internet of Things Group (IoT) at Intel Corp., thinks there are more innovations to come – and wants technology leaders to think equally about data and the algorithms as critical differentiators.

In his role at Intel, Lantzsch leads the worldwide group of solutions architects across IoT market segments, including retail, banking, hospitality, education, industrial, transportation, smart cities and healthcare. And he's seen first-hand how artificial intelligence run at the edge can have a big impact on customers' success.

Protocol sat down with Lantzsch to talk about the challenges faced by companies seeking to move from the cloud to the edge; some of the surprising ways that Intel has found to help customers and the next big breakthrough in this space.

What are the biggest trends you are seeing with edge computing and IoT?

A few years ago, there was a notion that the edge was going to be a simplistic model, where we were going to have everything connected up into the cloud and all the compute was going to happen in the cloud. At Intel, we had a bit of a contrarian view. We thought much of the interesting compute was going to happen closer to where data was created. And we believed, at that time, that camera technology was going to be the driving force – that just the sheer amount of content that was created would be overwhelming to ship to the cloud – so we'd have to do compute at the edge. A few years later – that hypothesis is in action and we're seeing edge compute happen in a big way.

Keep Reading Show less
Saul Hudson
Saul Hudson has a deep knowledge of creating brand voice identity, especially in understanding and targeting messages in cutting-edge technologies. He enjoys commissioning, editing, writing, and business development, in helping companies to build passionate audiences and accelerate their growth. Hudson has reported from more than 30 countries, from war zones to boardrooms to presidential palaces. He has led multinational, multi-lingual teams and managed operations for hundreds of journalists. Hudson is a Managing Partner at Angle42, a strategic communications consultancy.
People

Citizen’s plan to keep people safe (and beat COVID-19) with an app

Citizen CEO Andrew Frame talks privacy, safety, coronavirus and the future of the neighborhood watch.

Citizen added COVID-19 tracking to its app over the summer — but its bigger plans got derailed.

Photo: Citizen

Citizen is an app built on the idea that transparency is a good thing. It's the place users — more than 7 million of them, in 28 cities with many more to come soon — can find out when there's a crime, a protest or an incident of any kind nearby. (Just yesterday, it alerted me, along with 17,900 residents of Washington, D.C., that it was about to get very windy. It did indeed get windy.) Users can stream or upload video of what's going on, locals can chat about the latest incidents and everyone's a little safer at the end of the day knowing what's happening in their city.

At least, that's how CEO Andrew Frame sees it. Critics of Citizen say the app is creating hordes of voyeurs, incentivizing people to run into dangerous situations just to grab a video, and encouraging racial profiling and other problematic behaviors all under the guise of whatever "safety" means. They say the app promotes paranoia, alerting users to things that they don't actually need to know about. (That the app was originally called "Vigilante" doesn't help its case.)

Keep Reading Show less
David Pierce

David Pierce ( @pierce) is Protocol's editor at large. Prior to joining Protocol, he was a columnist at The Wall Street Journal, a senior writer with Wired, and deputy editor at The Verge. He owns all the phones.

Transforming 2021

Blockchain, QR codes and your phone: the race to build vaccine passports

Digital verification systems could give people the freedom to work and travel. Here's how they could actually happen.

One day, you might not need to carry that physical passport around, either.

Photo: CommonPass

There will come a time, hopefully in the near future, when you'll feel comfortable getting on a plane again. You might even stop at the lounge at the airport, head to the regional office when you land and maybe even see a concert that evening. This seemingly distant reality will depend upon vaccine rollouts continuing on schedule, an open-sourced digital verification system and, amazingly, the blockchain.

Several countries around the world have begun to prepare for what comes after vaccinations. Swaths of the population will be vaccinated before others, but that hasn't stopped industries decimated by the pandemic from pioneering ways to get some people back to work and play. One of the most promising efforts is the idea of a "vaccine passport," which would allow individuals to show proof that they've been vaccinated against COVID-19 in a way that could be verified by businesses to allow them to travel, work or relax in public without a great fear of spreading the virus.

Keep Reading Show less
Mike Murphy

Mike Murphy ( @mcwm) is the director of special projects at Protocol, focusing on the industries being rapidly upended by technology and the companies disrupting incumbents. Previously, Mike was the technology editor at Quartz, where he frequently wrote on robotics, artificial intelligence, and consumer electronics.

People

Google vows to do better on DEI and firings. Timnit Gebru is not impressed.

Google AI lead Jeff Dean said Google had concluded its investigation into Timnit Gebru's dismissal in an email to employees Friday.

Google has ended its investigation into the dismissal of prominent AI ethicist Timnit Gebru.

Photo: John Nacion/Getty Images

Google has concluded its investigation into the firing of prominent AI ethics researcher Timnit Gebru, and it announced some changes to its hiring, firing and research policies in an email from AI leader Jeff Dean to employees Friday.

While Dean did not share the results of the investigation into the circumstances surrounding Gebru's dismissal, he said that the company would enact new policies to "review employee exits that are sensitive in nature." His email, which was obtained by Protocol, said the company will also begin linking performance reviews for vice presidents and above, in part regarding diversity and inclusion goals, and it will report DEI goals and progress to the Alphabet board of directors in quarterly reviews.

Keep Reading Show less
Anna Kramer

Anna Kramer is a reporter at Protocol (@ anna_c_kramer), where she helps write and produce Source Code, Protocol's daily newsletter. Prior to joining the team, she covered tech and small business for the San Francisco Chronicle and privacy for Bloomberg Law. She is a recent graduate of Brown University, where she studied International Relations and Arabic and wrote her senior thesis about surveillance tools and technological development in the Middle East.

Latest Stories