WEBVTT

99:59:59.999 --> 99:59:59.999
So how are we going to beat
this novel coronavirus?

99:59:59.999 --> 99:59:59.999
By using our best tools:

99:59:59.999 --> 99:59:59.999
our science and our technology.

99:59:59.999 --> 99:59:59.999
In my lab, we're using
the tools of artificial intelligence

99:59:59.999 --> 99:59:59.999
and synthetic biology

99:59:59.999 --> 99:59:59.999
to speed up the fight
against this pandemic.

99:59:59.999 --> 99:59:59.999
Our work was originally designed

99:59:59.999 --> 99:59:59.999
to tackle the antibiotic
resistance crisis.

99:59:59.999 --> 99:59:59.999
Our project seeks to harness
the power of machine learning

99:59:59.999 --> 99:59:59.999
to replenish our antibiotic arsenal

99:59:59.999 --> 99:59:59.999
and avoid a globally devastating
post-antibiotic era.

99:59:59.999 --> 99:59:59.999
Importantly, the same technology
can be used to search

99:59:59.999 --> 99:59:59.999
for antiviral compounds

99:59:59.999 --> 99:59:59.999
that could help us fight
the current pandemic.

99:59:59.999 --> 99:59:59.999
Machine learning is turning
the traditional model of drug discovery

99:59:59.999 --> 99:59:59.999
on its head.

99:59:59.999 --> 99:59:59.999
With this approach,

99:59:59.999 --> 99:59:59.999
instead of painstakingly testing
thousands of existing molecules

99:59:59.999 --> 99:59:59.999
one by one in a lab
for their effectiveness,

99:59:59.999 --> 99:59:59.999
we can train a computer

99:59:59.999 --> 99:59:59.999
to explore the exponentially larger space

99:59:59.999 --> 99:59:59.999
of essentially all possible molecules
that could be synthesized,

99:59:59.999 --> 99:59:59.999
and thus instead of looking
for a needle in a haystack,

99:59:59.999 --> 99:59:59.999
we can use the giant magnet
of computing power

99:59:59.999 --> 99:59:59.999
to find many needles
in multiple haystacks simultaneously.

99:59:59.999 --> 99:59:59.999
We've already had some early success.

99:59:59.999 --> 99:59:59.999
Recently, we used machine learning

99:59:59.999 --> 99:59:59.999
to discover new antibiotics
that can help us fight off

99:59:59.999 --> 99:59:59.999
the bacterial infections that can occur
alongside SARS-CoV-2 infections.

99:59:59.999 --> 99:59:59.999
Two months ago, TED's Audacious Project

99:59:59.999 --> 99:59:59.999
approved funding for us
to massively scale up our work

99:59:59.999 --> 99:59:59.999
with the goal of discovering
seven new classes of antibiotics

99:59:59.999 --> 99:59:59.999
against seven of the world's
deadly bacterial pathogens

99:59:59.999 --> 99:59:59.999
over the next seven years.

99:59:59.999 --> 99:59:59.999
For context,

99:59:59.999 --> 99:59:59.999
the number of new class of antibiotics

99:59:59.999 --> 99:59:59.999
that have been discovered
over the last three decades is zero.

99:59:59.999 --> 99:59:59.999
While the quest for new antibiotics
is for our medium-term future,

99:59:59.999 --> 99:59:59.999
the novel coronavirus
poses an immediate deadly threat,

99:59:59.999 --> 99:59:59.999
and I'm excited to share that we think
we can use the same technology

99:59:59.999 --> 99:59:59.999
to search for therapeutics
to fight this virus.

99:59:59.999 --> 99:59:59.999
So how are we going to do it?

99:59:59.999 --> 99:59:59.999
Well, we're creating
a compound training library,

99:59:59.999 --> 99:59:59.999
and with collaborators
applying these molecules

99:59:59.999 --> 99:59:59.999
to SARS-CoV-2-infected cells

99:59:59.999 --> 99:59:59.999
to see which of them exhibit
effective activity.

99:59:59.999 --> 99:59:59.999
These data will be use to train
a machine learning model

99:59:59.999 --> 99:59:59.999
that will be applied to a [?]
library of over a billion molecules

99:59:59.999 --> 99:59:59.999
to search for potential
novel antiviral compounds.

99:59:59.999 --> 99:59:59.999
We will synthesize and test
the top predictions

99:59:59.999 --> 99:59:59.999
and advance the most promising
candidates into the clinic.

99:59:59.999 --> 99:59:59.999
Sound too good to be true?

99:59:59.999 --> 99:59:59.999
Well, it shouldn't.

99:59:59.999 --> 99:59:59.999
The Antibiotics AI Project is founded
on our proof of concept research

99:59:59.999 --> 99:59:59.999
that led to the discovery
of a novel broad spectrum antibiotic

99:59:59.999 --> 99:59:59.999
called Halocin.

99:59:59.999 --> 99:59:59.999
Halocin has potent antibacterial activity

99:59:59.999 --> 99:59:59.999
against almost all antibiotic-resistant
bacterial pathogens,

99:59:59.999 --> 99:59:59.999
including untreatable
pan-resistant infections.

99:59:59.999 --> 99:59:59.999
Importantly, in contrast
to current antibiotics,

99:59:59.999 --> 99:59:59.999
the frequency at which bacteria
develop resistance against Halocin

99:59:59.999 --> 99:59:59.999
is remarkably low.

99:59:59.999 --> 99:59:59.999
We tested the ability of bacteria
to evolve resistance against Halocin

99:59:59.999 --> 99:59:59.999
as well as Cipro in the lab.

99:59:59.999 --> 99:59:59.999
In the case of Cipro,

99:59:59.999 --> 99:59:59.999
after just one day, we saw resistance.

99:59:59.999 --> 99:59:59.999
In the case of Halocin,

99:59:59.999 --> 99:59:59.999
after one day we didn't
see any resistance.

99:59:59.999 --> 99:59:59.999
Amazingly, after even 30 days,

99:59:59.999 --> 99:59:59.999
we didn't see any
resistance against Halocin.

99:59:59.999 --> 99:59:59.999
In this pilot project, we first tested
roughly 2,500 compounds against E. coli.

99:59:59.999 --> 99:59:59.999
This training set included
known antibiotics,

99:59:59.999 --> 99:59:59.999
such as Cipro and penicillin,

99:59:59.999 --> 99:59:59.999
as well as many drugs
that are not antibiotics.

99:59:59.999 --> 99:59:59.999
These data we used to train a model

99:59:59.999 --> 99:59:59.999
to learn molecular features
associated with antibacterial activity.

99:59:59.999 --> 99:59:59.999
We then applied this model
to a drug repurposing library

99:59:59.999 --> 99:59:59.999
consisting of several thousand molecules,

99:59:59.999 --> 99:59:59.999
and asked the model to identify molecules

99:59:59.999 --> 99:59:59.999
that are predicted
to have antibacterial properties

99:59:59.999 --> 99:59:59.999
but don't look like existing antibiotics.

99:59:59.999 --> 99:59:59.999
Interestingly, only one molecule
in that library fit these criteria,

99:59:59.999 --> 99:59:59.999
and that molecule
turned out to be Halocin.

99:59:59.999 --> 99:59:59.999
Given that Halocin does not look
like any existing antibiotic,

99:59:59.999 --> 99:59:59.999
it would have been impossible for a human,
including an antibiotic expert,

99:59:59.999 --> 99:59:59.999
to identify Halocin in this manner.

99:59:59.999 --> 99:59:59.999
Imagine now what we could do
with this technology

99:59:59.999 --> 99:59:59.999
against SARS-CoV-2.

99:59:59.999 --> 99:59:59.999
And that's not all.

99:59:59.999 --> 99:59:59.999
We're also using the tools
of synthetic biology,

99:59:59.999 --> 99:59:59.999
tinkering with DNA and other cellular machinery, to serve human purposes like combating COVID-19 [??] we are working to develop a protective mask that can also serve as a rapid diagnostic test. How does that work? Well, we recently showed that you can take the cellular machinery out of a living cell and freeze-dry it along with RNA sensors onto paper in order to create low-cost diagnostics for Ebola and Zika. The sensors are activated when they're rehydrated by a patient sample that could consist of blood or saliva, for example. It turns out this technology is not limited to paper and can be applied to other materials, including cloth. For the COVID-19 pandemic, we're designing RNA sensors to detect the virus and freeze-drying these along with the needed cellular machinery into the fabric of a face mask, where the simple act of breathing, along with the water vapor that comes with it, can activate the test. Now, if the patient is infected with SARS-CoV-2, the mask will produce a fluorescent signal that can be detected by a simple, inexpensive handheld device. In one or two hours, a patient could those be diagnosed safely, remotely and accurately. We're also using synthetic biology to design a candidate vaccine for COVID-19. We are repurposing the BCG vaccine, which has been used against TB for almost a century. It's a live attenuated vaccine, and we're engineering it to express SARS-CoV-2 antigens, which should trigger the production of protective antibodies by the immune system. Importantly, BCG is massively scalable and has a safety profile that's among the best of any reported vaccine. With the tools of synthetic biology and artificial intelligence, we can win the fight against this novel coronavirus. This work is in its very early stages, but the promise is real. Science and technology can give us an important advantage in the battle of human wits versus the genes of superbugs, a battle we can win. Thank you.