"To truly understand a biological system, we must understand its dynamics as any number of factors change"
World's first AI-designed bispecific T cell engager; protein phase separation and novel targets; Dr. Markus Gershater on the Future of AI in Life Sciences; Europe's fastest growing biotech hub
Hi! I am Andrii Buvailo, and this is my weekly newsletter, ‘Where Tech Meets Bio,’ where I talk about technologies, breakthroughs, and great companies moving the industry forward.
If you've received it, then you either subscribed or someone forwarded it to you. If the latter is the case, subscribe by pressing this button:
Now, let’s get to this week’s topics!
The generative AI model helped design the world's first bispecific T cell engager in just 11 months
Recently, British biotech firm Etcembly unveiled the world's first AI-designed bispecific T cell engager, ETC-101, marking a significant leap in next-generation immunotherapies.
ETC-101 targets PRAME, an antigen prevalent in numerous cancers, and boasts a picomolar affinity that's a million times greater than its native counterpart, without any detected cross-reactivity.
Remarkably, Etcembly advanced ETC-101 to this stage in just 11 months, in contrast to the typical 2+ years required for traditional TCR pipelines.
The company's innovative AI platform, EMLy™, employs generative large language models to rapidly predict, design, and validate TCR candidates. This system scans and subsequently engineers hundreds of millions of TCR sequences to achieve low picomolar affinity and remove any cross-reactivity.
A new AI-driven approach to discovering targets for Alzheimer’s and other diseases with protein phase separation
Our cells contain various compartments, or organelles, that manage biological functions. Many of these organelles have a surrounding membrane, but others, known as "membraneless organelles," don't. Examples include the nucleolus, Cajal bodies, stress granules, P-bodies, and so on (see image below).
Such organelles play vital roles in cellular processes like stress response, gene expression regulation, and signal transduction. Moreover, some studies demonstrated involvement of membraneless organelles in age-related disorders, such as amyotrophic lateral sclerosis (ALS), or some cancers.
Now, what is really interesting is that these membraneless organelles, primarily made up of proteins and RNAs, form through a process called protein phase separation. The role of protein phase separation in living cells is a recently discovered phenomenon. I recommend reading the 2018 Cell article 'Protein Phase Separation: A New Phase in Cell Biology' to appreciate this new opportunity.
Liquid-liquid phase separation (LLPS) generates a subtype of colloid known as an emulsion that can coalesce to form large droplets within a liquid. In cells, proteins and RNAs, for example, can form such droplet-like structures via phase separation.
Protein phase separation at the wrong place or time could disrupt key cellular functions or create aggregates of molecules linked to neurodegenerative diseases. It is believed that poorly formed cellular condensates could contribute to cancers and might help explain the aging process.
With this in mind, proteins that are prone to phase separation appear to be of particular interest as targets for drug discovery. This idea is at the heart of recent news by Insilico Medicine and University of Cambridge about the discovery of a novel class of therapeutically relevant targets associated with the phenomenon of protein phase separation.
By merging Insilico’s PandaOmics AI platform with the FuzDrop method from Cambridge, scientists identified proteins prone to phase separation and scored them via multiomics analysis to form a list of potential therapeutic targets. The team confirmed the role of three predicted Alzheimer’s disease targets (MARCKS, CAMKK2, and p62) in two Alzheimer’s cell models, underscoring their therapeutic potential.
So, this proof-of-concept study by Insilico and the University of Cambridge, published in PNAS, demonstrates that AI-driven multiomics analysis can be applied to predict a whole new class of targets linked to protein phase separation (link in the first comment).
The 16th Annual BioInnovation Leaders Summit #BILS 2024 is an exclusive in-person only gathering for up to 250 pre-qualified decision-makers from the global BioManufacturing Space. Use exclusive code for our readers "BIOTREND20" for 20% off at checkout.
Key speakers Include:
Uwe Gottschalk, Operating Partner, Keensight Capital - Previous CSO of Lonza
Jens Vogel, SVP & Global Head of Biotech at Bayer Pharmaceuticals
Cokey Nguyen, CSO of Atara Biotherapeutics
Paolo G.V. Martini, Chief Scientific Officer of Moderna
Pierre Caloz, COO of uniQure
Cecile Brocard, Head of Downstream Processing at Boehringer Ingelheim
Co-located with: The 7th Annual Cell & Gene Therapy Innovation Summit #CGTI 2024
To register your interests, please contact kenzie.barnett@gbx-events.com
Blending Biology and AI: Dr. Markus Gershater on the Future of Life Sciences
In the dynamic field of life sciences, both biological research and AI are coming together to alter our perspective on life at its most basic level. Dr. Markus Gershater, co-founder and CSO of Synthace, sheds light on the challenges and opportunities this union presents. Synthace, a UK-based no-code platform, allows for the design and execution of experiments, subsequently producing and analyzing structured data.
Andrii: Dr. Gershater, you've got your feet in both biochemistry and synthetic biology while navigating a fast-paced tech world. In your view, what's the most exciting promise that AI holds for biotech?
Markus: The promise is that, quite simply, AI will give us insights into biology that are currently impossible and that we can’t yet begin to imagine. Also exciting, but secondary to this, is how it will prompt changes in the way we work. The reason I say this is because my underlying belief here is that, right now, AI and biological research don’t yet fit together properly.
AI is a technology that fundamentally demands change from the people who want to use it, so for AI to have a fundamental impact on biology, we really have to change the way we approach the process of science in the first place. It seems to me that organizations and teams will have to adopt new mindsets, new processes, and new tooling.
There are some companies who, today, already exhibit many of the required characteristics of companies that are looking to the future in terms of how they think about the way we gather data about biological systems. Think of companies like Recursion and Insitro, that have built whole automated platforms around this. Fully digitized, they are built to systematically create a greater understanding of biological systems.
They give us a glimpse of what the future may look like: the routine generation of high-quality, large, varied, multidimensional data, in the full context of rich metadata. Data that provides the foundation for AI, and a step change in our ability to understand and work with biological systems.
Andrii: Of course, every silver lining has a cloud. What do you see as the biggest challenges in bringing AI into the world of bioengineering? How can the industry, Synthace included, best tackle these hurdles?
Markus: We recently ran some research that found a staggering 43% of R&D decision-makers have low confidence in the quality of their experiment data. This is concerning because it doesn’t just demand we improve our means of recording experiment data, it also demands we perform experiments that generate higher quality data in the first place. It follows that to understand this data correctly we also require a high level of granularity about how it was created: metadata about experimentation should be automatically collected as much as possible.
In the context of AI, this is a problem. The scope of possible uses for AI in biotech is massive and can be applied in a myriad of ways across every aspect of the value chain. Saying “we need to use AI” is like saying “we need to use electricity”: obvious and useless unless you talk specifics. Much more meaningful is “we need to apply large language models to improve the user interfaces for our complex equipment and methodologies,” or “we should use active learning to optimize the development of assays for early discovery.”
“We need to use AI” is in danger of being a kind of an empty call to arms, with no acknowledgment of all the change that will be needed to make the touted revolution come about. In the second industrial revolution, electricity was insufficient by itself to increase productivity. People needed to first realize that it offered a way of changing the way they worked. Factories no longer had to be arranged around massive drive-shafts powered by steam engines. Instead, they could be arranged into production lines. It was the combination of new technology (electrification) and new ways of working (production lines and separation of labor) that enabled the step-change in productivity.
For Synthace, our focus is firmly on the experiment itself. How can we gather, generate, and structure high-quality data for export into systems that are able to make more use of it than the frankly limited and limiting data available today. To continue the above analogy, how can we adapt the factory floor to make the best use of electricity?
Andrii: Speaking of challenges, there's no denying that the complexity of biological systems makes for a dizzying amount of data. What's your take on the best approach to handle this data overload, and where does AI come into the picture?
Markus: Biology's complexity emerges from the interactions of its simpler components, giving rise to unique properties and behaviors. These emergent features can't be reliably predicted from individual components, necessitating a comprehensive and interconnected dataset for a deeper understanding of biological systems.
Much of the big data produced in biology are multi-omic studies: highly detailed molecular snapshots of a system. But apart from genomic data, all of these readouts are highly dynamic: they change over time and in response to a multitude of stimuli. To truly understand a biological system, we must understand its dynamics as any number of factors change. We can’t just measure a lot of things, we have to measure them in the context of this multifactorial landscape, systematically running experiments that map the space, and allow AI to “see” what is going on.
Just sequencing something isn’t enough; we must also look at how it works, interacts, and reacts to different stimuli. In our pursuit of comprehending the intricacies of biological processes, it's clear that one-dimensional data alone won't lead us far along this investigative path. Ideally we’d have large, varied, dynamic, high-quality data enriched with as much experimental context as possible, such that future as-yet-unimagined AI-driven analyses can make as much use of today’s data as possible.
Andrii: Finally, the idea that AI might change our whole understanding of the universe is a bit of a head-spinner. Can you delve a bit deeper into that concept? How might AI transform the way we interact with everything from biological systems to the wider world around us?
Markus: The buzz around AI/ML is remarkably strong and, without a doubt, it will be transformational in bringing new insight to biology. But as I’ve said, we have yet to see the full realization of its potential. The work of biology and the data/metadata that it produces is difficult to represent in code and difficult to digitize. If we can’t do it, AI/ML remains a pipe dream that remains the preserve of “big tech.” The volume of data, and also the quality of data we can provide to those artificial intelligence and machine learning tools determines the likelihood of uncovering anything interesting.
Is there a way to enable and control the entire experiment lifecycle from end to end? Is there a way to enable multifactorial experimentation, sophisticated automation, and AI/ML with a single unifying standard? Is there a way to elevate the scientist so they can spend more time on what matters most, applying more of their individual talents to today’s most difficult problems with the full power of modern computing?
In the event that we are able to adapt in the right ways to the possibilities created by these tools, we may begin to map entire biological landscapes overnight, using the resulting data and metadata to predict future outcomes. There will likely come a time in this decade when AI can predict the best possible experiment design before we even step into the lab. Should this come to pass, the upshot will be scientific breakthroughs that defy belief by today’s standards.
How Lithuania's Deep Tech Ecosystem Is Fueling the Country's Life Sciences Boom
Did you know that Prof. Virginijus Šikšnys, Lithuania's scientist from Vilnius University, is recognized for his contributions to the groundbreaking CRISPR-Cas9 gene-editing technology, alongside other CRISPR luminaries like Jennifer Doudna, Emmanuelle Charpentier, Feng Zhang, and Francisco Mojica?
Another interesting fact about Lithuania, a small country in the middle of Europe, is that it is a global supplier of restriction enzymes via its long-history protein manufacturing enterprise Fermentas, acquired in 2010 by Thermo Fisher Scientific. Currently, Thermo Fisher runs its largest R&D facility in the world in Lithuania, employing more than 1800 staff. This center is also one of the catalysts for Lithuania’s blossoming biotech community and the abundance of talent with specialized skills.
Strikingly, Lithuania appears to be Europe's fastest-growing life sciences hub, reaching close to 3% of the country's GDP.
Finally, Lithuania is home to a blossoming deeptech ecosystem focusing on gene editing, AI-driven protein design, 3D bioprinting, organoid development, organ-on-chip systems, next-gen microfluidics, and AI-driven diagnostics. This includes companies like Caszyme, Biomatter, JSC "Froceth", Vital3D Technologies, Delta biosciences, Atrandi Biosciences | Droplet Genomics, Genie Biotech and many others, that fuel the country’s ongoing success story in life sciences industry.
I recently visited Life Sciences Baltics 2023, a leading Baltics conference for biotech and medtech industries, and learned about the rich Lithuanian history of innovation and entrepreneurship in STEM disciplines and some first-hand insights about building and running biotech businesses in this country. Read my editorial for a deep dive.