New Scientist - USA (2021-12-18)

CO

UR

TE
SY
OF

SA

NA
TE
CH
SE

ED

They may look ordinary, but

in September these tomatoes

became the first CRISPR-edited

food to go on sale to the public.

The tomatoes were developed

by Hiroshi Ezura (pictured) at

the University of Tsukuba in

Japan. They are available only

in Japan and have five times

the normal amount of the

nutrient GABA.

A lot more CRISPR foods

could soon start to arrive on

supermarket shelves in many

countries. Next up could be

a red sea bream edited to

produce more flesh. Others

in development include

wheat that produces less

of a carcinogenic substance

when toasted, a lettuce that

stays greener for longer and

strawberries that are less likely

to go mushy if damaged.

CRISPR-

edited food

goes on sale

Biotechnology

RIG

HT

:^ BE

N^ P

ET

ER

CA

TC

HP

OL

E;^ T

OP

:^ DE

EPM

IND

IT TOOK decades for scientists to

unlock the structure of just 17 per

cent of the proteins in the human

body. But UK-based AI company

DeepMind raised the bar to

98.5 per cent in July when it

announced that its AlphaFold

model could quickly and reliably

calculate the way proteins fold. This

could lead to targeted drugs that

bind to specific parts of molecules.

We caught up with Pushmeet

Kohli at DeepMind to see how work

is progressing with mapping almost

every one of the more than

100 million known proteins that

have been sequenced from across

the tree of life.

Were you surprised at the

success of AlphaFold, considering

that figuring out protein folding

previously required vast

supercomputers?

We went in with the thesis that

machine learning and AI had a role

to play. But a lot of the team were

uncertain as to whether this

problem was solvable. It came

as a very pleasant surprise.

You plan to release many more

protein structures. Why not leave

the problem with scientists who

now have access to AlphaFold?

We open-sourced the model and

the code so anyone on the planet

can find the structure of any protein

that they want. We’re already seeing

universities and labs across the

world using our code. But the reason

we’re expanding the database

release is because there’s a lot

of time and investment involved,

and you don’t want different people

finding the structure of the same

protein again and again, right? It

Investigating protein-folding

becomes easier with AI

DeepMind released 3D models of the

human proteome, and there is more

to come, finds Matthew Sparkes

Interview

A 3D model of a

fruit fly protein

from DeepMind

will be very useful if we actually just

do it once and for all, for everyone.

Which are you working on first?

We’ve received feedback from the

community as to which organisms

and which types of proteins we

should prioritise next. So we’re

working along that road map,

eventually moving into what

we have committed to, which

is releasing the structure of

the entire protein universe.

Does that involve new work, or

just applying AlphaFold at scale?

The team has been constantly

improving the accuracy of the

model. But we also want to expand

what AlphaFold can do. So, we’d

worked on single proteins, but

complexes are important because

when you look at the biological

Profile

Pushmeet Kohli heads the

Robust and Reliable AI and AI

for Science teams at DeepMind

mechanisms at play, it’s very

infrequent that there will be a

single protein just interacting with

some other sort of small molecule

in isolation. So, composite

structures – that’s what we have

been expanding AlphaFold to do.

Will you ever reach a point where

you have mapped everything,

and AlphaFold can retire?

Proteins will change, life changes.

As evolution operates, you will see

different types of proteins coming

into play. And so AlphaFold will

have a life, not only in complexes,

but also in thinking about how

the structure is evolving.

And what about covid-19?

Very early on, we found the

structure of all the SARS-CoV-2

proteins. Some had been

experimentally validated, but

many were very difficult to figure

out by experimental methods.

When scientists actually found the

structures, it was interesting to see

that ours were nicely consistent.

Now, with variants, again there

is an element that these small

mutations lead to changes in the

structure, but AlphaFold is not

currently sensitive to very small

changes. So we want to make sure

that future versions of AlphaFold

are able to really be sensitive

to mutations. ❚

Michael Le Page

18/25 December 2021 | New Scientist | 23