Thu. Aug 18th, 2022


Credit: CC0 Public Domain

Within the microscopic boundaries of a single human cell, the intricate folds and arrangements of protein and DNA bundles dictate a person’s fate: which genes are expressed, which are repressed and – most importantly – whether they remain healthy or develop disease.

Despite the potential impact these bundles have on human health, science knows little about how folding occurs in the cell nucleus and how it affects the way genes are expressed. But a new algorithm developed by a team at Carnegie Mellon University’s Computational Biology Department offers a powerful tool for illustrating the process in an unprecedented resolution.

The algorithm, known as Higashi, is based on hypergraphical presentation learning – the form of machine learning that can recommend music in an app and perform 3D object recognition.

School of Computer Science doctoral student Ruochi Zhang led the project with Ph.D. graduate Tianming Zhou and Jian Ma, Ray and Stephanie Lane Professor of Computational Biology. Zhang named Higashi after a traditional Japanese sweet, and continued a tradition he began with other algorithms he developed.

“He approaches research with passion, but also with a sense of humor sometimes,” Ma said.

Their research was published in Natural Biotechnology and was conducted as part of a multi-institution research center that sought a better understanding of both the three-dimensional structure of cell nuclei and how changes in this structure affect cell functions in health and disease. The $ 10 million center was funded by the National Institutes of Health and headed by the CMU, with Ma as principal researcher.

The algorithm is the first tool to use sophisticated neural networks on hypergraphs to deliver a high-definition analysis of genome organization in single cells. Where an ordinary graph connects two corners to a single intersection point, known as an edge, a hypergraph connects several corners to the edge.

Chromosomes consist of a DNA-RNA-protein complex called chromatin that folds and arranges to fit into the cell nucleus. The process affects the way genes are expressed by bringing the functional elements of each ingredient closer together so that they can activate or suppress a particular genetic trait.

The Higashi algorithm works with a new technology known as single-cell Hi-C, which creates snapshots of chromatin interactions that occur simultaneously in a single cell. Higashi provides a more detailed analysis of the organization of chromatin in individual cells in complex tissues and biological processes, as well as how its interactions vary from cell to cell. This analysis allows researchers to see detailed variations in the folding and organization of chromatin from cell to cell – including those that may be subtle yet important in identifying health consequences.

“The variation in genome organization has strong implications for gene expression and cellular state,” Ma said.

The Higashi algorithm also allows researchers to simultaneously analyze other genomic signals that are profiled in conjunction with single-celled Hi-C. Eventually, this feature will allow for the expansion of Higashi’s capabilities, which is timely given the expected growth in single-cell data Ma expects to see in the coming years through projects such as the NIH 4D Nucleome program to which his center belongs. This data stream will create additional opportunities to design more algorithms that will advance scientific understanding of how the human genome is organized in the cell and its function in health and disease.

“This is an area in rapid motion,” Ma said. “Experimental technology is advancing rapidly, and so is computational development.”

AI identifies individual diseased cells

More information:
Jian Ma, multiscale and integrated single-cell Hi-C analysis with Higashi, Natural Biotechnology (2021). DOI: 10.1038 / s41587-021-01034-y.

Provided by Carnegie Mellon University

Citation: Machine learning provides a glimpse of high definition of how genomes organize themselves into single cells (2021, October 11) retrieved October 11, 2021 from -genomes- cells.html

This document is subject to copyright. Apart from any fair trade for the purpose of private investigation or research, no part may be reproduced without written permission. The content is provided for informational purposes only.

Leave a Reply

Your email address will not be published.