Algorithms are already used today in the treatment selection of cancer patients; however, they are not very sophisticated and assume that most patients' tumors are identical based on a few biomarkers. When using these algorithms, between 50-80% of patients either don't respond or recur after treatment and for that reason, we need to improve the treatment selection algorithms used in the clinic.
Today, novel algorithms based on genomic information can improve treatment selection for individual patients by simply analyzing a tumor sample using next-generation sequencing.
This is no longer futuristic; it is precisely what Genomic Expression has been developing since 2017, and their algorithms have now been clinically validated in breast and ovarian cancer. Their RNA Platform, called OneRNA®, is ready for launch as a treatment navigation tool.
How RNA algorithms are translated to individualized cancer treatments
Algorithms can find what you're looking for on Google or suggest your next movie on Netflix. This is, in principle, not different. AI is supercharging the interpretation of massive amounts of data where the human brain and other tools fail simply because of the complexity.
The company Genomic Expression Inc has developed a method for analyzing samples from tumors, where they quantify all RNA’s inside the cancer tissue and use algorithms to find the best treatment regimen.
"In contrast to DNA, which is the hard disc of the cell, RNA is the software – the program the cell is running" Morten Lorentz Pedersen , CTO Genomic Expression, “DNA makes life programable, but what kind of program the cells is running is found in the RNA”.
Data from sequencing RNA is run through multiple data processes to eliminate all bias, and then the data is compared to normal tissue to identify abnormal genes. An algorithm then lists several approved drugs that interrogate the abnormal genes in the tumor based on a proprietary drug database.
Cancer dramatically changes the RNA expression levels; Genomic Expression has demonstrated that it's possible to treat each cancer patient exceptionally accurately with the right intervention by analyzing how RNA changes in the cancer tissue.
The inconvenient truth is that only one out of four cancer treatments prolong life. That is because cancer is incredibly heterogeneous; not two tumors are alike. And yet, patients continue to be treated as if they all have the same disease.
Genomic Expression Inc aims to change this by assisting doctors in selecting the best drug for their patients and pharmaceutical companies select the best patients for their drugs.
“In reality, we won’t be able to cure cancer with only one drug. I have worked on curing cancer my whole life by developing new drugs. Sometimes, it is a novel drug combination uniquely matched to the patient.” Says Jesper Zeuthen, Chief Medical Officer of Genomic Expression and founder of GenMab, a $13B cancer drug company.
“We are not a new type of medicine – we find the best drug for the individual patient instead of trial and error or standard treatment,” says Dr. Morten Middelfart, Chief Information Officer at Genomic Expression.
Right now, Genomic Expression's algorithm has been tested on several cancer types, and the results are truly amazing, explains Gitte Pedersen, CEO at Genomic Expression.
Patient stories
The OneRNA® platform has been tested in more than five types of cancer. Some of the early patients have been in complete remission after having zero treatment options and metastatic disease, e.g., a patient with metastatic thyroid cancer. A fusion driver event was identified for which there was a novel drug in development. The patient enrolled in the clinical study and is +5 years in complete remission. Today, the drug is approved for all solid tumors.
Another patient with Follicular Lymphoma had recurred rapidly after standard treatment, enrolled in a clinical study with a promising bi-specific antibody, which did not work, and then in another study for a vaccine, which also did not work. OneRNA® identified two drugs that, in combination, worked in this patient. The combination is not approved, but the individual drugs were, and this patient has been in complete remission for more than 24 months.
A triple-negative breast cancer patient who went from having a dire prognosis – most of these patients die within two years of diagnosis – was able to identify a handful of drugs that were already approved and 30 clinical trials that matched her tumor.
In Ovarian cancer, OneRNA® identified several fusions that are very rare, e.g., an ALK fusion for which several drugs have been approved for lung cancer.
OneRNA® works by first analyzing a small tumor sample taken at the hospital and then sending it to Genomic Expression to be sequenced. The data is then run through the algorithm, which provides the doctor with an actionable report of possible treatment options.
In contrast to DNA panels that typically are limited to max 500 genes, RNA can identify markers for response to the new immune therapies and all other types of therapies as well as novel combinatorial treatments.
The diagnostic yield of OneRNA® is close to 100%, whereas DNA panels only identify one drug in 40% of patients. That number drops to half in low mutation frequency tumors such as breast or ovarian cancer and most internal tumors.
OneRNA® does not use panels; thus, it can optimize the algorithms in real-time and deliver new actionable findings to the doctors by combining the quantitative RNA data with patient data to improve the algorithms.
Genomic Expression clinically validated OneRNA® in a disciplined way and decided to focus first on breast and ovarian cancer, which shares some of the same genetic drivers such as BRCA1/2, expression of hormone receptors, and HER2.
Precise and less expensive cancer treatment
The algorithm uses the identity and quantity of the expressed RNA to calculate a score and list drugs that are approved or in clinical development. The changes in the RNA caused by cancer provide this valuable information.
"Doctors have done well so far – it is not a criticism of them – but the brain can only handle a certain amount of data, while an algorithm can handle an infinite amount of data and thereby figure out which treatment is most promising. It's as if we tried to find specific documents on the Internet: without a search engine, it would take much longer," says Morten Middelfart.
The problem with choosing the right cancer treatment today is that two people can both have breast cancer, but it is not certain that the same treatment works on both patients.
There are lots of examples where doctors see that some cancer patients respond to a treatment while others with the same type of cancer do not. If we create a method that shows the optimal treatment, ultimately, the doctors will need to combine the genomic information with the clinical information to select the treatment. Some patients may not be physically strong enough for a specific treatment due to the side effects"
"If we can get the cancer drugs already on the market to work better, then we will be in a situation where treatment per patient is much cheaper," Tanya Kanigan, COO of Genomic Expression, says.
Algorithms for the greater good
The big question is whether we can trust the algorithms. Morten Middelfart says that we can. Algorithms already control many systems that we trust. "We have, for example, developed control systems such as the autopilot for an Airbus aircraft. There must, of course, be a natural skepticism, but when the system deserves to be trusted, then we need accelerated adoption - especially for patients who don't respond or recur after standard treatment.
It makes sense to talk about credibility because most patients trust their doctor. However, some patients may feel differently about it if the doctor relies on an algorithm," he points out.
He denies, however, that there is a risk in using algorithms. The risk is that they will not be used correctly or not at all because doctors lack an understanding of their potential. The algorithms will never substitute a doctor,” Morten emphasizes, “Algorithms and AI will help doctors and their patients make better treatment decisions.
According to Morten Middelfart, there is no doubt that we will use algorithms to optimize cancer treatment, partly because using such algorithms can save lives and make healthcare more effective.
"I think the future of AI in healthcare is here now.” Our results in some cancers that are not driven by simple mutations are excellent. It has always been my passion to work with big data, where algorithms remove significant steps that otherwise would have been hard to solve. Some of our applications would be impossible to resolve without an algorithm," he says.
“The bottom line is that when we use algorithms for optimizing and individualizing cancer treatment, we are making a huge impact in the lives of these patients. Like most people, my family has been touched by cancer. Our dream is to make cancer a treatable disease and not a death sentence.”
This a sentiment that is shared by the founders of Genomic Expression, Gitte and Morten Pedersen, who lost both their parents to cancer, as well as Jesper Zeuthen, CMO, who arguably spent his whole life on finding better treatment options for cancer patients.
Today, the OneRNA® test is available as a treatment navigation tool for breast and ovarian cancer. Samples are analyzed in Genomic Expression’s clinical laboratory under strict quality control, and the test has to be ordered by the patient's oncologist.
Genomic Expression Inc Is fundraising to launch OneRNA® more broadly, and investors can support them here https://www.startengine.com/offering/genomic-expression