AlphaProteo generates novel proteins for biology and health research
deepmind.google
deepmind.google
That being said, as others have commented, my hopes are that all these advancements lead finally to reliable design methods for novel biocatalysts, an area that has been stalling for decades, compared to protein folds and binders.
David Baker’s lab has recently published on using their own diffusion model (RFdiffusion) to design novel biocatalysts that perform hydrolysis using a catalytic triad of serine, aspartic acid, and histidine, as well as an oxyanion hole, which is much more complex than the binders designed by AlphaProteo [1].
It gives me hope that we’ll soon be able to design biocatalysts as good as natural ones, but for any problem we care about.
1. https://alexcarlin.bearblog.dev/novel-enzymes-from-a-diffusi...
In the whitepaper they mention that they are novel compared to other in silico design techniques, but to my knowledge other binders to VEGF and Covid spike protein exist and would already be found in the PDB database that Deepmind trained the model on.
This is not to minimize the results- if the history of ML is anything to go by, even if AlphaProteo does not currently beat the best affinity found by in vitro screens, I do not doubt that it soon will!
[0] - https://storage.googleapis.com/deepmind-media/DeepMind.com/B...
When you look at these synthetics they often maximize for interactions of hydrophobic areas on the surface.
However, a new fold - that is, the shape that the backbone folds into - would be novel. Potentially also novel would be 'chimeric' structures with parts from other structures, as with chimeric domain swaps.
There was a structure designed by the Baker lab called 'Top7 - https://pubmed.ncbi.nlm.nih.gov/14631033/ that I remember as ground breaking at the time :) (in the ancient days of 2003 it seems ...)
I want more info about how novel these proteins are.
With that level of understanding, its easy to fabricate special medicines that target specific biochem pathways, but more exciting is that we can literally "code in 3d world". We'll be able to print and grow organs in mass. We'll be able to design structures that will bind to target proteins responsible for certain traits. The potential boon to human medicine will be enormous.
I got like goosebumps after watching that video because I understood the implications of being able to predict folds and now generate proteins that will bind to any protein we choose!!!!
We just might have discovered a panacea of sorts and Demis and his team should receive the Nobel Prize.
I'm just ecstatic that we'll see so much drastic improvement in human medicine and importantly how accessible they will be with this new discovery.
you would have to infiltrate an extremely guarded facility
you would somehow have to bypass QA
its not like somebody on the assembly line for a new protein drug sprinkles a dose of PCP
one potential dual use could be somebody modifying a popular fruit with birds and then droppin seeds at the local organic farm fair
and then when those seeds are consumed by birds they produce poop dangerous for other animals to consume
you could absolutely screw around with the ecosystem, like whoever has access to this programmable "bio-wafer" will be able to play god totally undetected.
the problem is that "bio-wafer" manufacturing process will be very tough and regulated like the CNC machines used to manufacture jet engines depriving certain countries from being able to churn out their own jet engines
Nowadays I am pretty sure that a bad actor with enough money get their hands on strains of really bad stuff since many labs created those to do research. With enough $$$ I bet you can get their hands on them and then release them.
Perhaps, the only difference I see is that it could give you the possibility to (at least in the beginning) to somewhat target the spread. However, given enough mutations it is very likely you go back to an uncontrolled pandemic and so there is no difference from what someone could achieve today.
Additionally, IMHO, getting the blueprint in how to build your protein and then make it so that existing virus/bacteria can produce it, carry it, ... sounds harder and costlier than bribing someone to get something out of said labs.
I'm a PhD candidate doing my thesis work on stem cell models and tissue engineering for organ transplant...I think this technology is certainly a large leap forward but I think you are a little overzealous with this claim.
The problem is to find the right target or pathway in the first place. Just go to opentargets.org. There are lots of potential targets by different metrics but for many diseases we haven't identified that single target that let's us improve the life of say, 20% of patients, for disease X.
Arc Institute and others are already looking at whole cell models, i.e. systems biology. It's a totally different level of abstraction.
Working in this area might also be good test of their technological approach, as small-molecule binding can be somewhat challenging, and even evolved biological systems can struggle to achieve high specificity.
Genentech set up a subsidiary with Corning (the glass company) that owns the IP for this protease and then licensed it to laundry detergent manufacturers; many billions of dollars in revenue. I think this is one of the original patents: https://patentimages.storage.googleapis.com/d9/ca/6f/2fb89ff...
Another consideration is that most protein structure prediction methods only generate the backbone, and the sidechains are modeled in afterwards. Enzyme efficiency requires sub-A level structural precision in the sidechains that are actually doing the chemistry involved in catalysis, so it could also be the case that the current backbone-centric methods aren't good enough to predict these fine-tuned interactions.
- Great for recruitment: You're the most talented $SKILL in the world? Come to the team that is pushing humanity forward in all the ways that matter.
- Larry and Sergei actually care about humanity, and being a billionaire is kind of a side-effect of what they would have done anyway.
I play Go recreationally. I don't think I can use AlphaGo (or its successors) directly, but the published research on AlphaGo has inspired other strong Go AIs. Online Go platforms integrate them to offer AI matches as well as analyze games between humans. I also know that professionally ranked players are adopting things learned from AI into their own play, and a lot of traditional joseki (analogous to chess openings) are being rethought based on insights from AI play.
When I worked at Google I made a case for doing protein design/preliminary drug discovery using Google infrastructure and it was well received by the leadership. The leadership at Google is mostly computer scientists who know about, but can't actually do, leading-edge life sciences research, and they want to contribute some amount of Google's resources to advancing the state of the art. That's the only reason exacycle was permitted- because Urs thought we could maybe help save the world with protein design (and it wasn't a good approach because it wasted enormous amounts of power on unbiased sampling of large proteins).
Honestly I don't think Google proper is really a good place for this work to be applied, though. Their attention is easily diverted, they repeatedly fail to commercialize, and most importantly, potential partners are scared Google will steal their data, and replace their business.
But more immediately this is an interesting and relevant problem to solve, so it servers as a tool to benchmark and improve AI... and the current theory is that at some point AI will {generate unlimited amount of wealth | lead humanity into the post-scarcity society | solve all human problems by eliminating humans}.
I'm very interested in my research at the moment in pleiotropy, namely mapping pleiotropic effects in as many *omics/QTL measurements and complex traits as possible. This is really helpful for determining which genes / proteins to focus on for drug development.
The problem with drugs is in fact pleiotropy! A single protein can do quite a lot of things in your body, either through a causal downstream mechanism (vertical pleiotropy), or seemingly independent processes (horizontal). This limits a lot of possible drug target as the side-effect / detrimental effect may be too large.
So, if these tools can create ultra specific protein structures that somehow only bind in the areas of interest, then that would be a truly massive breakthrough.
But novel binding domain design could be combined with other tools to achieve this effect. You could imagine engineering a lipid nanoparticle coated in antibodies specific to cell types that express particular surface proteins. So you might use this tool to design both the antibody binding domain on the vector and also the protein encoded by the payload mRNA. Not all cell types can be reached and addressed this way, but many can.
The viral life-cycle comprises attachment/entry, replication and maturation/release. These stages are generally well understood to the point where 'disarmed' (replication-incompetent) viruses are routinely used as a delivery vehicle in molecular biology.
The first part, attachment/entry is directly related to protein-protein interactions (between the envelope protein of the virus and the entry receptor of the host cell). This particular interaction determines the tropism of the virus, that is, its capability to infect a particular type of cell. Examples include the interaction of gp120 protein of the HIV virus and CD4 of a helper T cell, or the spike protein of SARS-CoV-2 and ACE2 of nasal ciliated cells.
The parent specifically asked about targeting a group of people - designing an envelope protein (or proteins) targeting a specific HLA haplotype would probably get you halfway there (this is not advice).
The whitepaper depicts some successful cases, determined by X-ray crystallography or cryo-EM.
- Genewiz (Azenta Life Sciences)
- Thermo Fisher Scientific (GeneArt)
- Tierra Biosciences
- NovoPro Labs
However, this category of technologies could potentially be used to develop new prion diseases on purpose. As well as to develop cures for prion diseases that disrupt the misfolding.
That seems quite plausible actually. You'd need something that can target misfolded PrP and bind it up so it can't do anything and then hopefully your targeting protein leaves normal PrP alone. A bit like an antibody.