distances between genes. Credit: Generated with DDG
DaVinci2 model from prompt by Nicolas Posunko/Skoltech
PR. Photo/Supplied.
Skoltech
researchers have enlisted generative artificial intelligence
to complete the missing data on the distances between pairs
of genes in DNA. This enables figuring out the 3D
architecture of DNA molecules, which is in turn necessary
for developing treatments and diagnostic approaches for
genetic diseases. Published in the journal Scientific
Reports, the study
is the first successful attempt to flesh out such data using
AI or, in fact, by any means. Previously, scientists had to
make do with incomplete data, hampering progress in medical
genetics and limiting the scientists’ understanding of the
biophysics of chromatin — the stuff of
chromosomes.
To do its job properly, DNA requires more
than the right set of genes: It has to have the correct 3D
architecture, which is traditionally the object of
statistical physics, and polymer physics in particular. The
way the 46 long DNA macromolecules per cell are folded in
space affects which genes are active and whether the cell
will reproduce appropriately and differentiate into
specialized cell types during embryonic development.
Conversely, faulty DNA architecture plays a role in the
development of abnormalities and diseases, such as
cancer.
Advertisement – scroll to continue reading
The more scientists learn about the physical
principles behind the stabilization of the “healthy” 3D
architecture of DNA, the more opportunities for diagnosing
and treating genetic disorders are created. By comparing DNA
spatial structure in health and disease, biomarkers for
diagnosing disorders and personalized treatments can be
found. Scientists can identify new therapeutic targets,
develop drugs that restore normal gene function, and design
precise gene editing interventions.
One of the most
widely used experimental techniques for examining how DNA
molecules are folded in space is fluorescence microscopy.
This refers to a kind of optical microscopy where certain
specific gene sequences — a great number of those, in fact
— are highlighted by staining them with fluorescent
tags.
The problem is that such data is inevitably
fragmentary. To attach a fluorescent tag, scientists
synthesize a short gene sequence that is complementary to
the sequence at the position of interest along the DNA
strand. However, it’s not possible for every sequence. If
it contains repeated nucleobases, such as a string of
letters A, for example, the sequence cannot be stained
selectively, because it is not unique. So researchers have
had to make do with incomplete data. Not
anymore.
“Once you know the distances between a
sufficient number of genes, determining the remaining
distances for which there is no experimental data takes the
form of a mathematical problem with a specific solution,”
the principal investigator of the study, Assistant Professor
Kirill Polovnikov from Skoltech Neuro,
commented. “We have shown for the first time that
generative models are capable of solving such problems. This
is an unconventional application of the kind of AI usually
employed for more ‘creative’ tasks — generating images
and text based on a user prompt. At the same time, this is a
new approach to the study of chromatin structure, where
polymer physics has historically reigned
supreme.”
The implications of the research are
twofold. Practically speaking, the Skoltech team has
proposed and tested a way to process fluorescent microscopy
data that will ultimately enable a better understanding of
DNA spatial structure, which promises better treatments and
diagnostics for genetic diseases. Fundamentally, the study
demonstrates the potential of generative artificial
intelligence beyond the usual scope of its
applications.
The study reported in this story was
supported by Russian Science Foundation Grant No. 25-13-00277.