Mike Klein, CEO of genomic health company Genomenon, said GEN Edge that the company’s tracking system identifies about 15,000 newly published, peer-reviewed research articles per week with genomic data – or about 750,000 per year!
But Klein said one of the things that researchers, both in industry and academia, haven’t been able to take advantage of very well is the millions of dollars of data that are captured in genetics papers because scientific publications are not well organized. Although people are able to create a lot of data by sequencing a lot of patients, the question Klein focuses on is: what does this data mean?
As a data curator, Genomenon tries to keep up with the constant advances in genetics and genomics to be in a position to serve the drug discovery market and help diagnose and treat patients with rare genetic diseases and cancer.
To do this, Genomenon recently acquired Boston Genetics, a genomic interpretation and curation company, in late June 2023 as part of its plan to curate the entire human genome. The goal is to combine Genomenon’s AI-powered platform for genomic knowledge and technology-enabled scientific expertise with Boston Genetics’ team of genetic scientists to take the leadership position and be the first company to curate the entire human genome.
Born of necessity
Mark Kiel, MD, PhD, was working at the University of Michigan when he became frustrated with the slow pace and large time commitment of manual genome curation, which led him to found Genomenon, whose name means “born of necessity.” in ancient Greek. . The manual effort required to search and analyze the rapidly expanding body of medical literature for disease-related genes and variants has made interpreting next-generation sequencing (NGS) data inefficient and error-prone.
Kiel launched Genomenon to meet the growing demand for accurate and timely variant interpretation, combining human curation with new machine learning approaches that can keep up with the rapid pace of publication and reveal the most pertinent data to researchers.
In 2017, Genomenon launched its first product – the Mastermind Genomic Search Engine – to help researchers in their quest to search for multiple diseases, genes and variants in order to fill gaps in genomic evidence.
According to CEO Klein, they developed Mastermind after discovering that most companies used natural language processing repeatedly in research papers without any success. As a result, they developed their own language processor using a technique they called “genomic language processing” (GLP).
According to Klein, “We often find that authors can describe a single variant in 200 different ways. Genes can be described using legacy nomenclature in dozens of different ways. So being able to build a custom set of algorithms that can analyze and recognize the hundreds of ways that all of these criteria are used to describe variants and genes can describe variants, and then be sure that we’re actually capturing disease variants. relationships in the right way, we had to add some biological logic to our genomic language processing to really make sure we were getting solid results.”
GLP has the underlying indexing capability that gives Genomenon the ability to find these genetic disease associations, extract that information, and normalize all of that. When accessing Mastermind, you can enter dozens of different ways to describe a variant.
But Klein said that in 2019, pharmaceutical companies approached them because they didn’t want to click on individual genetic variants — they really wanted to understand the entire genetic landscape of a specific disease. In other words, pharmaceutical companies wanted to provide datasets and have Genomenon curate those datasets for them.
“They wanted us to tell them every variant and every gene associated with a specific disease and give us an indication of pathogenicity through clinical guidelines,” Klein said of pharmaceutical companies. “Give us the functional consequences: is it a gain of function or a loss of function? What are the protein domains that these variants are driving?”
At this point, Genomenon began developing curated genomic landscapes. Over time, Klein began to recognize that this was a powerful solution, especially when it came to stratifying clinical trials.
“If you think about finding the most likely responders, well, if you know the genetic drivers of the disease, you have the opportunity to increase the likelihood of success by selecting the right patients with the right genomic biomarkers and then leveraging that same data in the world of companion diagnostics (CDx) to the development of CDx,” said Klein.
“As this market shifts from the platform side to an information market, what the real world really needs is a curator.”
Genomenon has leveraged AI in developing its curation and indexing capabilities, as well as building a search engine. In the process, Klein realized that Genomenon had the opportunity to curate “the entire” human genome. By this, Klein means that he wants to identify each variant in each gene for each disease and the pathogenicity and functional consequences of each of these variants. He wants to put this information at the fingertips of pharmaceutical researchers to go beyond not just stratifying clinical trials and developing companion diagnostics, but actually getting into drug discovery, being able to provide insights into the gene-disease relationship and actually , down to the variant level they can use as they seek to truly understand the genetic drivers of diseases.
Klein believes the NGS market is moving from what he calls a “platform game” to a “content game.”
“Netflix talked about its network reach and delivery vehicles, but when you talk about streaming today, we talk about content, content, content,” Klein said. “In the NGS market, we see a number of platform boxes coming. Illumina is seeing market pressure from MGI, PacBio, Element Biosciences and Ultima, which are reducing the cost of sequencing and reagents. As a result, the cost of turning whole genome sequencing – the actual chemistry – into data has fallen dramatically, and we are seeing many more patients getting whole genome sequencing.”
To date, Genomenon has indexed the text of all identifiable articles on genomics. Klein said there are about 9.2 million published and peer-reviewed research articles and 3 million supplementary datasets that contain genomic data, and Genomenon has been able to extract more than 22 million biomarkers or genomic variants and their associations with diseases, phenotypes. and therapies.
Klein said Mastermind has 100 times more genomic evidence and 50 times more variants than any other resource.
According to Klein, Genomenon has come to the conclusion that it cannot rely on AI alone to curate the entire human genome and keep it up to date. “AI can give some bad information and have a high false positive rate, so we need to have expertise on the back end,” Klein said.
Curating the human genome needed a human element. In 2019, Genomenon began bringing in some of the Boston Genetics team to begin doing some genetic curation and ended up becoming its largest client in late 2022. Now, the two have come together as a single entity.
“They approached us and asked what we thought about combining the two companies,” Klein said. “It makes perfect sense to combine AI with experts in genetics and genomics to define the curation of the entire genome. It will have the people and technology to accomplish this mission.”
Klein expects that Genomenon’s larger team and greater understanding of genomics will allow it to immediately better help its clinical, diagnostic and pharmaceutical customers in their efforts to better understand the genomic drivers of genetic diseases and cancer. The acquisition expanded Genomenon’s genetic science team fivefold.
Today, Genomenon’s workforce consists of software developers, bioinformaticians and genetic scientists. The acquisition also gives Genomenon the ability to offer affordable variant curation team extensions to genetic testing laboratories, which should reduce turnaround times.
“Boston Genetics performs interpretation for some of the largest clinical laboratories in the United States,” said Klein. “We’re continuing this business – we’re not going to throw it away. In fact, we have the ability to accelerate interpretation services by leveraging some of the AI technologies we have developed. We will continue to add an additional revenue stream to the company, but we look to leverage and expand this.”
Therefore, this acquisition not only puts Genomenon ahead in the race to curate the entire human genome, but also brings unprecedented actionable genomic insights to drug development programs as well as clinical diagnostics and newborn sequencing programs. .
While all this is happening, Klein said they have been incorporating machine learning and large language models (LLMs). This doesn’t mean they’re throwing ChatGPT at the data to provide answers; what Genomenon is doing is using LLMs to classify information in the right way so that their experts can get the right information very quickly to make the right decisions to select the data and be able to populate their database and provide it to the its Users.
“We have developed the technology and the AI platform, but the technology alone does not lead to the true answers that researchers and clinicians need; it needs to be combined with scientific experience,” said Klein. “What this acquisition has given us is 75 more people – scientific experts and genetic scientists – that we can bring into the company immediately. That was the real added value. This really enables our genome curation mission and puts us in a really strong position to be the first company to curate the entire genome.”