The company uses artificial intelligence to decode genomic diversity.

Artificial intelligence (AI) has many applications and in most cases is undetectable. From scanned items at self-checkout kiosks to detecting soil texture for crop growth, the applications of AI are expanding rapidly.

Funding for AI in healthcare has tripled. In 2021, McKinsey reported that biotech companies raised more than $34 billion worldwide. In Q1 2024, just 20 healthcare-focused biotech companies collectively raised $2.9 billion.

Also, in Q1 2024, Moonwalk Biosciences Raises $57M in Funding for Epigenetic Profiling Epigenetics studies how environment and behavior can change how genes work without changing the DNA sequence.

In 2003, the Human Genome Project completed work begun in 1990 to generate and decode the first sequence of the human genome. This work generated fundamental knowledge about the human blueprint, opening the door to personalized medicine, accelerated studies of human biology, and clinical discoveries in neurological conditions, cancer, and heart disease.

“Today, we understand how one percent of the human genome works. That leaves 99 percent of the human genome that we know exists, but we don't understand how it works,” Dr. said Jennifer Hintsche, CEO and Co-Founder. Feral Fertility Science. “It was originally called “junk DNA,” but it's far from junk.

“There must be a biological reason that has been maintained throughout human evolution; we don't understand that reason yet,” Hintzsche said. “Decoding 1% of the human genome has already eradicated diseases that used to kill us.”

“If we can figure out the purpose of the other 99% of the human genome, how many other diseases are waiting to be eradicated? It will help change medicine and, most importantly, the knowledge we gain.” “Every cent will help save lives. Our own DNA,” Hintsche added.

Artificial intelligence

Genialis is an RNA Biomarker company that has raised $13M to date. It uses machine learning and AI to examine the underlying disease biology. AI, particularly machine learning, is good at detecting patterns in large amounts of data, which is essential for genomic interpretation, says Raphael Rosengarten, CEO and co-founder of Genialis.

“Each human genome is ~6 billion base pairs (three billion long x two copies of each chromosome),” Rosengarten said. “In each of our bodies, we develop millions of genomic changes (mutations) over our lifetimes, and there are millions of variations from person to person. And often, no single mutation is the cause; rather, it's a combination of mutations. is, so it's a data space that's well-suited to the strengths of AI.”

The challenge of decoding the genome, says Rosengarten, is understanding which changes are meaningful. “This could mean looking at the changes that occur in our bodies and trying to understand which of them are pathogenic and/or druggable.”

“It can also mean looking for differences in genome sequence between people or groups of people in a population and trying to understand which of those genomic differences we see, especially as its The connection is to health, longevity, drug response, and other medical issues,” added Rosengarten.

Genomic distribution

AI algorithms could close the genetic health care access gap.

The Genealis team is analyzing large genomic datasets to uncover patterns of disease prevalence and genetic predisposition within small populations.

Each dataset can be as small as dozens or as large as a few thousand patient samples. “The data sets themselves range from being produced by microarray technologies in the late 2000s to various sequencing technologies from the early 2010s,” Rosengarten added.

“No one person's genomic data is exactly the same, and we see clear differences between ethnic groups and between men and women,” Rosengarten said. “There is no single central genomic database for the world, but between 60-80 percent of the world's patient datasets come from people of European ancestry.”

Rosengarten says this poses a huge problem when developing a therapy for one group — for example, in rural India — but trained on data from people from different backgrounds.

Rosengarten cites Carolyn Credo-Perez's book, The invisible womanwho notes that medical researchers have previously tried to avoid female subjects, when possible, due to biological heterogeneity, at least in part, from the menstrual or estrous cycle.

“Such misguided attempts to reduce the complexity of an experimental or clinical design intentionally fail to account for variables that often prove relevant to the scientific question or clinical need,” Rosengarten said.

Rosengarten says it's worth noting that since 2014, the National Institutes of Health has required grant applicants to include plans to achieve gender parity among clinical, experimental models, but that the sex of the organism is always public. or even not clear from the metadata associated with the data. Proprietary database

Genialis says it is tackling this disparity by working with institutions around the world, including Qatar and India, to create what it believes to be the world's most ethnically and geographically diverse. Cancer will have data sets and find solutions that will work in the world. desired patient.

“Genialis has been very intentional in sourcing datasets from our global network of clinical partners, such as the data we use to train and validate our biomarker algorithms,” said Rosengarten. are comprehensive and reflect the population being treated at large.” This is the intention. This is critical because relying on data that narrows the population too narrowly will be full of gaps and biases, which AI and machine learning algorithms will learn from.”

Understanding genomic diversity

“So the first genome was done on a man. One,” Hintsche said. “For a long time, most clinical research into things like cancer has been comparing tumors to the small datasets we had access to—the genomes of only a handful of people, lacking genetic diversity. Is.”

Hintzsche says we need to think about how underrepresented these genomes should be.

“Most clinical research has focused on comparing DNA to the DNA of only a handful of people,” Hintsche said. “For example, if we're looking at tumor DNA and comparing it to this small data set of DNA from a few people – how do we know that a change in DNA causes cancer? Causing or perhaps common among people of certain backgrounds, most of the time, we don't.”

“We understand almost zero about the genomic diversity that can explain the many different reasons why people respond differently to treatments or even diseases. It's all hidden in the deep recesses of DNA. has happened which we have not yet begun to understand.