Page 21 - Abacoa Community News - January '24

Abacoa, Page 21
Science On The Cutting Edge

One-third of all oversimplification, too general to train AI, Martemyanov said.
drugs work by binding To document the signaling in a comprehensive way, they
Scientists Train AI To to cell-surface receptors turned to a useful technology called bioluminescence resonance
energy transfer. It involved engineering a small bioluminescent
called G protein-coupled
Illuminate Drugs’ Impact On receptors, or GPCRs. tag into the cells’ proteins and documenting the change to the
These are complexes that
luminescence as the cell was exposed to molecules that activate
Largest Family Of Cellular cross the cell membrane, GPCRs.
They gathered the data, attached ranks for binding preference
with a “docking station”

Targets on the cell’s exterior and a branch that extends into the cell. When and saw patterns emerge. The data resembled something like an
a drug pulls into its GPCR dock, the branch moves, triggering EKG, with measurements for the activation rate, amplitude and
An ideal medicine for one a G protein inside the cell and setting off a cascade of changes, selectivity. They added common genetic variants for the GPCRs
person may prove ineffective or like falling dominoes. humans carry, and documented significant differences in how
harmful for someone else, and The result of activating or blocking this process might be these mutated receptors responded when activated.
predicting who could benefit anything from pain relief, quieting allergies or reducing blood When Correia’s group in Switzerland trained the algorithm
from a given drug has been pressure. Besides medications, other things like hormones, to make predictions based on this more nuanced data, the
difficult. Now, an international neurotransmitters and even scents dock with GPCRs to direct researchers were excited by the results. They found it to be correct
team led by neuroscientist biological activities. more than 80% of the time.
Kirill Martemyanov, Ph.D., Scientists have catalogued about 800 GPCRs in humans. The scientists hope their results encourage drug developers
based at The Herbert About half are dedicated to senses, especially smell. About to adopt a more sophisticated understanding of GPCRs, their
Wertheim UF Scripps Institute 250 more receive medicines or other known molecules. G proteins and their activities in a way that ultimately benefits
for Biomedical Innovation Martemyanov’s team had to invent a new protocol to observe patients with safer medicines, created more quickly and at
& Technology, is training and document them. They found many surprises. Some GPCRs lower cost. Going forward, they intend to explore more deeply
artificial intelligence to assist. Kirill Martemyanov, Ph.D. worked as expected, but others didn’t, notably those for how genetic variation affects the way GPCR-acting drug-like
Martemyanov’s group neurotransmitters called glutamate. compounds work.
used a powerful molecular tracking technology to profile Martemyanov’s collaborators on the project included his “Our ultimate goal is to be able to predict how individual
the action of more than 100 prominent cellular drug targets, postdoctoral researcher and later staff scientist, Ikuo Masuho, variants that people carry respond to drugs,” Martemyanov said,
including their more common genetic variations. The scientists Ph.D., who now heads his own lab at Sanford Research in “allowing for the custom tailoring of prescriptions and paving
then used that data to develop and train an AI-anchored platform. Sioux Falls, Iowa, as well as computational protein designer the way for precision medicine.”
In a study that appears in the Oct. 31 issue of the journal Cell Bruno E. Correia, Ph.D., who is based at the Swiss Institute of In addition to Martemyanov, Correia and Masuho, the co-
Reports, Martemyanov and colleagues report that their algorithm Bioinformatics, in Lausanne, Switzerland, and was instrumental authors of the study,“Rules and mechanisms governing G protein
predicted with more than 80% accuracy how cell surface in creating the AI algorithm. Their collaboration grew from a coupling selectivity of GPCRs,” were Ee Von Moo, Ph.D., Xiaona
receptors would respond to drug-like molecules. lecture Correia gave at the Jupiter campus in Florida many years Li, Ph.D. and Hideko Wakasugi-Masuho, of The Wertheim UF
The data used to train the algorithm was gathered over a ago, Martemyanov said. Scripps Institute; Ryoji Kise, Ph.D., and Ryosuke Tany, Ph.D., of
decade of experimentation. Their long-range goal is to refine Martemyanov was struck by the fact that for an artificial Sanford Research, and Pablo Gainza of the École Polytechnique
the tool and use it to help power the design of true precision intelligence algorithm to be useful, it must be trained with Fédérale de Lausanne and Swiss Institute of Bioinformatics,
medications, said Martemyanov, who chairs the institute’s accurate data and clear rules. It was early days in GPCR research Lausanne, Switzerland.
neuroscience department. when they started, Martemyanov said, and they lacked that type Support for the research was provided by the National
“We all think of ourselves as more or less normal, but we are of broad, sophisticated data on GPCR activity. Institutes of Health, grants DA036596 and MH105482; the
not. We are all basically mutants. We have tremendous variability “If you’ve only looked at one leg of the elephant you may Swiss National Science Foundation, the Swiss National Centre
in our cell receptors,” Martemyanov said. “If doctors don’t know not have the right idea of how to describe it; you may not see of Competence in Research (NCCR) in Chemical Biology, the
what exact genetic alteration you have, you just have this one- that it’s actually an elephant,” he said. NCCR in Molecular Systems Engineering, an EPFL-Fellows
size-fits-all approach to prescribing, so you have to experiment Classifying GPCRs solely by their best-known activity grant funded by an H2020 Marie Sklodowska-Curie, and startup
to find what works for you.” was akin to seeing one leg of an elephant, he said. It was an funding from Sanford Research.
FAU Harbor Branch
Announces 2024 Ocean

Science Lecture Series

Florida Atlantic
University’s Harbor
Branch Oceanographic
Institute announced
the lineup for its
annual “John & Barbara Ferrera Ocean Science Lecture
Series.” All lectures begin at 4 p.m. at FAU Harbor Branch,
Johnson Marine Education Center Auditorium, 5600 U.S.
1 North, Fort Pierce.
The free public education events provide a forum for
the community to learn about the most recent discoveries
and innovations at FAU Harbor Branch directly from the
scientists and engineers who make them.
“Our speakers are all experts in their fields and enjoy
sharing their work with the public,” said Dennis Hanisak,
Ph.D., research professor and director of education at FAU
Harbor Branch. “They will share their diverse experiences
on ocean science that help solve practical problems and make
informed decisions for the better management of our ocean
and coastal waters.”
The 2024 lecture series schedule is as follows:
• Jan. 10: “The Quest for a Marine Sponge Cell Line:
A Retrospective of Sponge Biotechnology at FAU Harbor
Branch,” presented by Shirley Pomponi, Ph.D.
• Jan. 17: “Clam Culture in a Changing Environment,”
presented by Susan Laramore, Ph.D.
• Jan. 24: “Stealing Sharks and Ravaging Rays? A Scientific
Delve into Their Impacts on Florida Fisheries,” presented by
Matt Ajemian, Ph.D.
• Jan. 31: “A Bath Sponges Fable: Sponge Painting and
the Lobster Season,” presented by Andia Chaves Fonnegra,
Ph.D.
• Feb. 7: “Coral Exploration, Conservation and Restoration,”
presented by Joshua Voss, Ph.D.
• Feb. 14: “Remembering Mark Littler and His Contributions
to Marine Plants and Coral Reef Ecology,” presented by Brian
LaPointe, Ph.D., and M. Dennis Hanisak, Ph.D.
• Feb. 21: “Health and Disease in Bottlenose Dolphins
Inhabiting the Indian River Lagoon,” presented by Annie
Page, DVM, Ph.D.
• Feb. 28: “Anti-Cancer Drug Discovery at FAU Harbor

2024 Ocean Science Lecture Series on page 22