Cellino uses AI and machine learning to increase production of stem cell therapies – TechCrunch
Cellino, a company developing a platform to automate stem cell production, presented today at TechCrunch Disrupt 2021’s Startup Battlefield to detail how its system works, which combines AI technology, machine learning. , hardware, software – and yes, lasers! – could ultimately democratize access to cell therapy. It aims to reduce the costs associated with the manufacture of human cells, while increasing yields.
Founded by a team whose backgrounds include physics, stem cell biology and machine learning, Cellino operates in the regenerative medicine industry. This space is currently undergoing a revolution, where new developments in gene and cell therapies could lead to revolutionary treatments for a number of major diseases. For example, the use of personalized human retinal cells could be transplanted to stop or reverse age-related macular degeneration, which can lead to blindness. But today, these cell therapies are out of reach for most people because the cell production process has not been automated or made scalable and efficient.
Instead, the human cells currently used in these clinical trials are mostly handcrafted by scientists who examine the cells and assess – using their many years of training and expertise – which cells are of poor quality. and should be deleted. They then scrape off these unwanted cells with a pipette tip. The process, as you can imagine, is time consuming and produces little return. In this manual process, you would see a yield of around 10% to 20% of cells that would be able to pass the final quality assurance tests required for human transplantation.
Cellino is working to improve this process in order to produce more and better cells. His goal is to push the yield to at least 80% over the next three years.
To do this, Cellino’s system automates all human stages of the production process using machine learning techniques.
To identify high or low quality cells, the company collects large training data sets where it teaches algorithms to determine cell quality based on various factors. This includes cell morphology, that is, the shape, size and density of cells. Fluorescence-based surface markers can also be used to identify other factors important to the cell line produced, such as the location of proteins on the cell, for example.
By using machine learning and AI to perform identification based on standard and well accepted bioassays used by the FDA, the system could move away from human annotation and the variability that creeps into the process of producing human cells.
Once Cellino’s software identifies the low-quality cells to be eliminated, it then uses a laser to target them. The laser creates cavitation bubbles large enough to kill the cell, but it’s done in a very localized way where you don’t harm neighboring cells because thermal heat does not dissipate to neighboring cells. It is also a more precise technique than the manual method. (Cellino’s system has a resolution of 5 microns, while cells are 10 to 15 microns in size). This results in a throughput of about 5,000 cells per minute, which is very efficient compared to manual techniques.
Over time, this automation and efficiency could lower the cost of nearly a million dollars per patient, which clinicians must pay today to conduct a clinical trial, when they outsource cell production. Cellino aims to reduce the cost to tens of thousands of dollars over time.
By increasing cell production, personalized cell therapies could also help a wider range of patients compared to other techniques relying on stem cell banks. These are not always genetically diverse samples, leaving small ethnic groups outside the progress made in this space. Banked cells also require recipients to take immunosuppressants because the cells are not yours and the body may reject them.
Using lasers was an idea developed by Cellino co-founder and CEO Nabiha Saklayen, who patented an invention in cell laser editing while she was working at Harvard to earn her doctorate in physics. She was encouraged to turn the technology into a startup by her collaborators, which included leading biologists like George Church and David Scadden.
âNot all scientists become entrepreneurs, and I became an entrepreneur because I had an incredible support network around me,â Saklayen notes of the push to join the startup space. She immediately recruited Marinna Madrid, an applied physicist with whom she had worked for years on co-inventing intracellular laser delivery techniques, as her other co-founder. To get more mentorship on growing a startup, Saklayen turned to the Boston-area startup ecosystem.
âI didn’t know anything about startups. I wanted to work with people who knew how to build businesses, how to commercialize technology, how to build instruments – and the Boston ecosystem is fantastic that way. So I started connecting with a lot of people in those first few weeks – anyone who was in the biotech field or Harvard Business School, âsays Saklayen.
This brought her to Cellino and CTO co-founder Mattias Wagner, who had previously established companies in the field of optics and instrumentation.
âThis is how the founding team was formed. It was very complementary because Marina and I were co-inventors of the original technology that inspired the platform and Mattias brought this tremendous experience in semiconductors and optical instrumentation, âexplains Saklayen.
Since its founding in 2017, Cellino has raised $ 16 million in seed funding through a cycle co-led by The Engine and Khosla Ventures, with participation from Humboldt Fund and 8VC.
The company is now collaborating with the NIH on compatibility studies. Currently, that means Cellino is making stem cells on his system which he then compares to those made at NIH that are already being tested in humans for personalized cell therapies for retinal disease. Cellino later hopes to use his system to treat areas like Parkinson’s disease, muscle disorders, and skin transplants, among others.
The company wanted to present to TechCrunch Disrupt to learn more about what it is building and look for new talent.
âFor me, it’s about talking about this idea around the democratization and industrialization of cell therapy. I really want to get this message across because this is the movement we need to lead over the next decade to make all of these cell therapies available to all patients, âsaid Saklayen.
“The Cellino angle is also very unique in the sense that, because we have this automated system to make human cells, our system could make cells for every human being – in this country, in the world,” he continues. she. âAnd there are a lot of cell therapy approaches that seek to use standard cells and therapies, which will only work for certain parts of the population. As the United States becomes more and more ethnically diverse, we need personalized solutions for everyone. “