ILLUSTRATION: V. ALTOUNIAN/SCIENCE804 12 NOVEMBER 2021 • VOL 374 ISSUE 6569 science.org SCIENCET
he artificial intelligence (AI) revolu-
tion in protein structure prediction
continues. Only 1 year ago, software
programs first succeeded in modeling
the 3D shapes of individual proteins
as accurately as decades-old experi-
mental techniques can determine them. This
summer, researchers used those AI programs
to assemble a near-complete catalog of hu-
man protein structures. Now, researchers
have upped the ante once again, unveiling a
combination of programs that can determine
which proteins are likely to interact with one
another and what the resulting complexes—
crucial engines of the cell—look like.
“It’s a really cool result,” says Michael
Snyder, a systems biologist at Stanford Uni-
versity. “Everything in biology works in com-
plexes. So, knowing who works with who is
critical.” Those relationships were hard to
reach with previous techniques. The new
ability to predict them, he says, should yield
an array of insights into cell biology and pos-
sibly reveal new targets for the next genera-
tion of therapeutic drugs.
Mapping proteins’ shapes down to the
atomic scale has until recently required costly
and slow experimental techniques, such asx-ray crystallography and nuclear magnetic
resonance spectroscopy. Those experimental
techniques, if they work at all, typically only
produce individual protein structures.
Computer modeling experts have worked
for decades to speed things up. Their recent
success has depended on deep learning
algorithms, which use databases of experi-
mentally solved protein structures to train
software programs how to predict struc-
tures for proteins based on their amino
acid sequences.
Last year, two groups, one from a U.K.
company called DeepMind and the other led
by David Baker at the University of Wash-
ington, Seattle, created rival AI programs
that both now churn out predicted protein
structures by the thousands (Science, 30 July,
p. 478). The software also produced struc-
tures for a handful of known protein com-
plexes, mostly in bacteria (Science, 16 July,
p. 262). But in eukaryotes—organisms from
yeast to people—the interacting partners are
often unknown. Identifying them and pre-
dicting how they come together in a complex
was too high a bar for the original programs.
Now, both research groups have tweaked
their programs so they can solve structures
of protein complexes by the hundreds. On-
line this week in Science, Baker and his col-leagues use a combination of AI techniques
to solve the structures of 712 complexes
in eukaryotes.
To find proteins that may form complexes
together, the team began by comparing the
amino acid sequence of all 6000 yeast pro-
teins to those from 2026 other fungi and
4325 other eukaryotes. The comparisons
allowed the researchers to track how those
proteins changed over the course of evolu-
tion and identify sequences that appeared
to change in tandem in different proteins.
The researchers reasoned that those pro-
teins might form complexes, and that they
changed in step to maintain their interac-
tions. Then the team used its AI program,
called RoseTTAFold, along with DeepMind’s
AlphaFold, which is publicly available, to at-
tempt to solve the 3D structures of each set
of candidates. Out of 8.3 million identified
coevolving yeast protein pairs, the AI pro-
grams identified 1506 proteins that were
likely to interact and successfully mapped
the 3D structures of 712, or about half.
“These interactions span all processes of
eukaryotic cells,” says team member Qian
Cong, a biomedical informatics expert at
the University of Texas Southwestern Medi-
cal Center. Among the highlights, Cong and
Baker say, are structures for protein com-
plexes that allow cells to repair damage to
their DNA, translate RNA into proteins in
ribosomes, pull chromosomes apart dur-
ing cell reproduction, and ferry molecules
through the cell membrane.
“It’s a great example of the promise” of 3D
structures, says DeepMind’s John Jumper,
one of AlphaFold’s lead developers. By re-
vealing precisely how proteins interact
with one another, the models should help
biologists visualize how previously unknown
complexes carry out a multitude of jobs
within the cell.
“These models give hypotheses for experi-
mentalists to test,” Cong says. And because
disrupting these interactions could offer
new ways to intervene in a wide variety of
diseases, she adds, “it also gives you a lot of
potential new drug targets.”
More are likely on the way. Last month,
Jumper and his colleagues posted a pre-
print on the bioRxiv server describing a
new version of their AI, dubbed AlphaFold-
Multimer, which mapped structures of 4433
protein complexes. Analyses within the AI
program that gauge the confidence level of
each fold suggest the structures were accu-
rate up to 69% of the time. The bottom line,
Baker says: “It’s really an exciting time for
structural biology.” jThese two proteins form a complex involved
in DNA repair in yeast; artificial intelligence software
predicted both proteins’ structures.AI reveals structures of
protein complexes
Software extends protein mapping to complexes
that govern the breadth of cell biology
By Robert F. ServiceSTRUCTURAL BIOLOGYNEWS | IN DEPTH