Connect with us


With new funding, Atomic AI envisions RNA as the next frontier in drug discovery TechCrunch


The biotech industry is seeing a proliferation of AI-powered tools for many aspects of the complex drug discovery process. But one that flies under the radar, increasingly thought to be key to certain diseases, but terribly understudied, is RNA. His newly raised $35 million in funding, Atomic AI, aims to do to RNA what AlphaFold did to proteins, and find entirely new treatments in the process.

If you can remember high school biology, you probably remember RNA as something of a mediator between DNA (the long-term storage of information) and proteins (the machinery of cellular life at the molecular level). . But like most things in nature, it doesn’t seem that simple, explains Raphael Townshend, CEO and founder of Atomic AI.

“There is a central dogma that DNA becomes RNA and RNA becomes protein. said in “If you look at the human genome, at some point about 2% will be protein. But 80% will be RNA.

Compared to DNA and proteins, little research has been done in this area. Academia has turned its attention to other pieces of the puzzle, and the pharmaceutical industry, in part as a result, has pursued proteins as mechanisms of medicine. .

But Atomic AI argues that RNA is functional and worth pursuing as a therapeutic. The secret lies in the “non-coding” regions of RNA, such as document headers and footers. They act like proteins, but they are not proteins and are not the only examples.

An RNA strand can be thought of as a necklace of beads. It’s much more string than beads. The strings are “floppy” and more or less detractors think of it as a middleman. As with proteins, being able to figure out their structure goes a long way toward understanding what proteins do and how they are affected.

“The key is to find those beads, those bits that are structured. They’re informative, they’re highly targeted, and they’re probably also functional,” Townshend said. “It is seen as an important new frontier in drug discovery.”

Perhaps an interesting idea for a senior thesis (and it was for Townsend), but how do you build a business around it?

First, there is a lot of value in building study methods if the field becomes more and more important in the future. Then create these methods and you can use them first. Atomic AI is doing both at the same time.

A rotated 3D model of the RNA strand structure predicted by PARSE.

At the core of Atomic’s IP, which is a simplification, is AlphaFold for RNA. The biology is different, the models work differently, but the idea is the same. A machine learning model trained on a limited set of molecules of one class can make accurate predictions about the structures of other molecules of that class.

Remarkably, Townshend’s team created a model that far outperformed others by giving structural signatures to just 18 RNA molecules “published between 1994 and 2006.” am. In 2021, this completely barebones model wiped the floor with other models, as he revealed in his front-page article published in Science.

Since then, Townshend quickly adds that the company has greatly enhanced its models and methods with more raw materials, many of which it makes on its own in its own wet lab. They call their updated set of tools PARSE (AI-Driven RNA Structure Discovery Platform).

“The Science paper was the first breakthrough, but it actually generated a lot of … structural adjacency data,” he explained. “The data associated with the structure, tens of millions of data points, rather than the full structure itself. The same scale of data required to train a large language model. We were able to dramatically improve both the speed and accuracy of

So Atomic AI is, at least publicly, the only company with a system that can take raw data of an RNA molecule and spew out a reasonably reliable estimate of its structure. This will be useful for anyone doing RNA research inside or outside medicine, and gene therapy and mRNA vaccines are definitely increasing this field.

Another RNA structure (but rendered differently).

With such a tool, you can do one of two things: Either license it as a “structure-as-a-service” platform or use it yourself, as Townshend puts it. Atomic chose the latter and is pursuing its own drug discovery program.

This approach is very different from many AI discovery processes out there. The general idea is that you have a protein, say something you want to inhibit its expression in the human body, but what you don’t have is a chemical that binds reliably and exclusively to that protein. cheaper if possible).

AI drug discovery efforts generate thousands, millions, or even billions of candidate molecules that might work, rank them, and wet labs start processing the list as quickly as possible. tend to. If we can find something that meets the above properties, we can manufacture new drugs or replace more expensive drugs on the market. But importantly, we find new binders to known proteins. We are competing for

“We’re not just finding binders, we’re finding things we can target in the first place. The interesting reason is, at the end of the day, these big pharma companies are more interested in new biology than new molecules.” Finding this new target, rather than increasing the number of molecules available for targeting, allows us to do things we couldn’t do before,” said Townshend.

Not only that, but some proteins have been found to be nearly drug-resistant for some reason, causing drug-resistant diseases. may enable treatment of

At present, Atomic AI compiles a list of specific cancers that result in pathological protein overproduction (thus a good option for preempting mechanisms) and neuronal cancers that may also benefit from upstream interventions. Focused on degenerative diseases.

Of course, all this work is very expensive and requires both extensive lab work and intensive data science. Fortunately, the company is led by Playground Global, with participation from 8VC, Factory HQ, Greylock, NotBoring, AME Cloud Ventures, and angels Nat Friedman, Doug Mohr, Neal Khosla, and Patrick Hsu, for a $35 million A raised rounds. (The company previously raised $7 million in a seed round.)

“People are picking every fruit that’s readily available in protein land,” Townsend said. “Now there’s a new biology to pursue.”




The mention sources can contact us to remove/changing this article

What Are The Main Benefits Of Comparing Car Insurance Quotes Online

LOS ANGELES, CA / ACCESSWIRE / June 24, 2020, / Compare-autoinsurance.Org has launched a new blog post that presents the main benefits of comparing multiple car insurance quotes. For more info and free online quotes, please visit https://compare-autoinsurance.Org/the-advantages-of-comparing-prices-with-car-insurance-quotes-online/ The modern society has numerous technological advantages. One important advantage is the speed at which information is sent and received. With the help of the internet, the shopping habits of many persons have drastically changed. The car insurance industry hasn't remained untouched by these changes. On the internet, drivers can compare insurance prices and find out which sellers have the best offers. View photos The advantages of comparing online car insurance quotes are the following: Online quotes can be obtained from anywhere and at any time. Unlike physical insurance agencies, websites don't have a specific schedule and they are available at any time. Drivers that have busy working schedules, can compare quotes from anywhere and at any time, even at midnight. Multiple choices. Almost all insurance providers, no matter if they are well-known brands or just local insurers, have an online presence. Online quotes will allow policyholders the chance to discover multiple insurance companies and check their prices. Drivers are no longer required to get quotes from just a few known insurance companies. Also, local and regional insurers can provide lower insurance rates for the same services. Accurate insurance estimates. Online quotes can only be accurate if the customers provide accurate and real info about their car models and driving history. Lying about past driving incidents can make the price estimates to be lower, but when dealing with an insurance company lying to them is useless. Usually, insurance companies will do research about a potential customer before granting him coverage. Online quotes can be sorted easily. Although drivers are recommended to not choose a policy just based on its price, drivers can easily sort quotes by insurance price. Using brokerage websites will allow drivers to get quotes from multiple insurers, thus making the comparison faster and easier. For additional info, money-saving tips, and free car insurance quotes, visit https://compare-autoinsurance.Org/ Compare-autoinsurance.Org is an online provider of life, home, health, and auto insurance quotes. This website is unique because it does not simply stick to one kind of insurance provider, but brings the clients the best deals from many different online insurance carriers. In this way, clients have access to offers from multiple carriers all in one place: this website. On this site, customers have access to quotes for insurance plans from various agencies, such as local or nationwide agencies, brand names insurance companies, etc. "Online quotes can easily help drivers obtain better car insurance deals. All they have to do is to complete an online form with accurate and real info, then compare prices", said Russell Rabichev, Marketing Director of Internet Marketing Company. CONTACT: Company Name: Internet Marketing CompanyPerson for contact Name: Gurgu CPhone Number: (818) 359-3898Email: [email protected]: https://compare-autoinsurance.Org/ SOURCE: Compare-autoinsurance.Org View source version on accesswire.Com:https://www.Accesswire.Com/595055/What-Are-The-Main-Benefits-Of-Comparing-Car-Insurance-Quotes-Online View photos


to request, modification Contact us at Here or [email protected]