One of the great disappointments of biologists after the sequencing of the human genome is that access to this “big book of life” and its approximately 22,000 genes does not provide all the keys to understanding how our DNA, inherited from two parental cells, leads to the formation of an individual with all the tissue diversity that constitutes him. Our complex constitution, but also part of our diseases, depends on a language that regulates the expression of genes – activated or repressed – whose grammar still defies human understanding. Even in this area, artificial intelligence (AI), crowned at the beginning of October with two Nobel prizes, for physics and chemistry, seems to be able to make its contribution. As highlighted by a study published on October 24 in Nature.
“Gene expression is regulated in many different ways”recalls Sager Gosai (Broad Institute, MIT and Harvard), first author of the study. Together with his colleagues from two other American laboratories, he became interested in the so-called “cis-regulatory elements” (CRE). These small fragments of DNA, or promoters, generally located upstream of the genes they regulate, are intended to bind to proteins, called “transcription factors”, which trigger or not the translation of a given gene into a protein. The researchers describe having designed, thanks to machine learning – which aims to give machines the ability to “learn” through mathematical models – active CREs in certain cells with greater specificity than those found in nature. Even when they were tested not only in vitro, but also on transgenic animals, such as zebrafish.
Synthesizing CREs at random to find the most suitable ones is not an option: the number of possible 200-nucleotide combinations – the length of the DNA sequences tested by researchers – “it would exceed that of atoms in the observable universe”remember in Nature. They therefore started with a powerful molecular biology tool, which makes it possible to test the activity of hundreds of thousands of CREs in different cell types – in this case, nerve, blood and liver cells.
“Emerging field”
This large data set was used to train artificial neural networks to recognize those that might be active in one cell type, but not the other two. The researchers then asked these models to create new sequences that could regulate the expression of a gene in a specific cell. These artificial CREs have proven to be very efficient.
Interview Between Time.news Editor and Sager Gosai
Time.news Editor: Welcome, Sager! It’s great to have you here today. Your recent study published in Nature has generated a lot of buzz. Can you start by explaining what sparked this research on gene expression and cis-regulatory elements?
Sager Gosai: Thank you for having me! The inspiration for our research comes from the fact that the sequencing of the human genome, while groundbreaking, left many questions unanswered about how those genes function in the body. We realize that understanding gene expression—how genes are activated or repressed—is essential for comprehension of not only our individual identities but also many diseases.
Editor: Absolutely, that makes sense. One of the intriguing things about gene expression is its complexity. You mentioned “cis-regulatory elements” in your study—can you elaborate on what these are and their role in gene expression?
Sager: Sure! Cis-regulatory elements are specific DNA sequences located near genes that help control the expression of those genes. They act like switches, enabling us to fine-tune the activity of our genes in response to various signals. Understanding these elements is crucial because they offer insights into the grammar of our gene expression language, which is still largely a mystery.
Editor: It sounds like you’re diving deep into the intricate mechanisms of our DNA’s operation. How has artificial intelligence played a role in advancing your research in this area?
Sager: AI has become an invaluable tool for us. With its capacity to analyze large datasets and identify patterns, AI can help us model the interactions between genes and their cis-regulatory elements. By using AI to predict gene expression outcomes based on variations in these regulatory sequences, we’re getting closer to decoding this complex language.
Editor: That’s fascinating! It must be thrilling to be at the intersection of biology and technology. Given the recent Nobel prizes awarded for AI in physics and chemistry, do you think we’re entering a new era of research where AI will unravel more biological mysteries?
Sager: Definitely! The success of AI in other scientific fields suggests that its potential in biology is just beginning to be realized. We need to harness this technology not just for analysis, but also for hypothesis generation and experimental design. As AI tools become more sophisticated, I believe we will start to see more breakthroughs in our understanding of genetics and its implications for health care.
Editor: It sounds like there is immense potential on the horizon! Considering the crucial role of gene expression in diseases, how might your findings contribute to better diagnosis or treatment strategies in the future?
Sager: That’s the hope! By better understanding how gene expression is regulated, we can identify specific pathways that malfunction in various diseases. This could lead to more targeted therapies that address the root cause of a condition rather than just treating the symptoms. In essence, our aim is to move towards personalized medicine that takes individual genetic differences into account.
Editor: It’s exciting to think about the possibilities. As we wrap up, what do you hope the broader scientific community takes away from your research?
Sager: I hope our work encourages more interdisciplinary collaboration between biologists and data scientists. The complexities of gene regulation will likely require diverse expertise and innovative approaches. The more we engage with new technologies, the closer we’ll get to cracking the code of our genetic blueprint.
Editor: Thank you for sharing your insights with us today, Sager! It’s clear that the future of genetics is bright, especially with experts like you at the helm. We look forward to seeing how your research continues to evolve!
Sager: Thank you for having me! I’m excited to share more discoveries in the future.
