The Economist

66 Science and technology The EconomistAugust 4th 2018

Marine biology

The biter bit

F

ROM the human point of viewPelagia

noctilucais an enemy. It is a jellyfish

abundant in the Mediterranean Sea that

is the chief cause of stings to swimmers

in that popular holidaymakers’ destina-

tion. But as this picture showsPelagia

noctilucahas enemies of its own. The

other creatures in shot are polyps of

Astroides calycularis a type of coral.

NormallyAstroides calycularisfeeds

on small creatures of the plankton. But

researchers led by Tomás Vega Fernández

of the Zoological Station in Naples div-

ingoff the coast ofItalian islandssuch as

Pantelleria have show that individual

coral-polyps sometimes collaborate to

trap and consume jellyfish. They catch

hold of various partsof their prey to stop

it swimming away and slowly dismem-

ber it. As the team describe in a paper in

Ecology each polyp then consumes part

of a tentacle or of the pulsating umbrella

the jellyfish uses to swim.

Corals are essentially sea anemones

with stony cases. Both they and jellyfish

belong to the phylum of animals known

to zoologists as Cnidaria the characteris-

tic feature of which is stinging cells called

nematocysts. Cnidarians use these to

disable their prey. In this example then it

is a case not so much of “the biter bit” as

“the stinger stung”.

Corals eat jellyfish

T

HE number of chemicals that might

come into contact with a human being

is staggering. The European Chemical

Agency (ECHA) recognises over 130000

molecules. Its American counterpart re-

cognises 85000. Testing all of these for tox-

icity is well-nigh impossible. Animal test-

ing in particular is controversial slow

costly and often cruel. Nor is it reliable. Its

results are often irreproducible.

Things would be better if there were

some way to predict the likely toxicity of a

substance before animals get involved.

That would permit the riskiest-looking to

be prioritised. To this end toxicologists like

Thomas Hartung of Johns Hopkins Uni-

versity in Baltimore have been trying for

years to find objective links between a

chemical’s molecular structure and its bio-

logical activity. And now Dr Hartung

thinks he has one. It relies as do so many

advances these days on machine learning.

A way to link molecular structure and

biological activity does already exist. It is

called “read-across” and attempts to infer

the hazards of an untested chemical by

comparison with those of a tested one

with a similar structure. In 2015 read-across

was accepted as an alternative to animal

testing for meeting the ECHA’s Registra-

tion Evaluation Authorisation and Re-

striction of Chemicals (REACH) require-

ments. But read-across depends on expert

analysis and opinion making it subjective

and also difficult to generalise beyond

small well-studied groups of chemicals.

Dr Hartung believes machine learning

with its power to find patterns in large

quantities of data could help close the gap.

His right-hand man in this work is Thomas

Luechtefeld a computer scientist who

joined him as a PhDstudent in 2013. To tap

into machine learning’s capabilities the

two of them first needed lots of good data.

When Mr Luechtefeld started work these

were unavailable. He had adequate data

for only about 250 chemicals. In 2014 how-

ever he began to build a database that

overcame this limitation by downloading

816048 toxicity studies on 9801 com-

pounds registered with REACH.

He spent a year training an algorithm to

read these studies process the text they

contain and extract pertinent information.

This algorithm automatically correlates

chemical features like the presence of par-

ticular groups of atoms with measures of

hazard such as the median lethal dose in

an animal test allowing all chemicals in

the database to be compared. The result

which the two researchers reported in

2016 did indeed provide some insight into

the prevalence of different types of toxicity.

But to make more general predictions they

needed a larger data set still.

Mr Luechtefeld has therefore spent the

past year scouring public data sets like

those from PubChem which is run by

America’s National Institutes of Health. He

now has relevant data on 80908 chemi-

cals and is able to correlate their features

with 74 types of hazard. These are not just

medical threats. They also include such

things as fire hazard and potential to harm

the ozone layer.

His latest algorithms focus on nine

types of toxicity including skin irritation

eye irritation and mutation-causing poten-

tial which are conventionally assessed by

animal trials. Using data from tested sub-

stances these algorithms are able to esti-

mate the toxicity of untested ones. Instead

of a single number such as the median le-

thal dose in an animal test they provide a

probability that a substance is hazardous

enough to worry about. Anything that

scores above 0.8 should be regarded as a

problem without further ado. Anything

below 0.2 can be regarded as safe. Chemi-

cals scoring between those values should

be treated with caution until more data

come in to push their scores up or down.

Mr Luechtefeld is now Dr Luechtefeld

having obtained hisPhDa few weeks ago.

He and Dr Hartung claim in a recent paper

that the algorithm’s assessments are more

accurate than animal testing. By this they

mean that if a given molecule’s toxicity as

predicted by the algorithm is compared

with its read-across result the two are

more likely to coincide than are two inde-

pendent animal tests on that molecule.

They are now waiting to hear from the

authorities whether their method will be

formallyadopted alongside conventional

read-across as a legal alternative to animal

tests. Regardless of whether it is though

what they have come up with should help

understanding of the underlying mecha-

nisms of toxicity. And that will be an im-

portant step forward. 7

Environmental safety

Hazchem or not?

BOSTON

It should soon be easier to find out

without killing animals