Leaders in Pharmaceutical Business Intelligence (LPBI) Group

The Map of human proteins drawn by artificial intelligence and PROTAC (proteolysis targeting chimeras) Technology for Drug Discovery

Curators: Dr. Stephen J. Williams and Aviva Lev-Ari, PhD, RN

UPDATED on 11/5/2021

Introducing Isomorphic Labs

I believe we are on the cusp of an incredible new era of biological and medical research. Last year DeepMind’s breakthrough AI system AlphaFold2 was recognised as a solution to the 50-year-old grand challenge of protein folding, capable of predicting the 3D structure of a protein directly from its amino acid sequence to atomic-level accuracy. This has been a watershed moment for computational and AI methods for biology.
Building on this advance, today, I’m thrilled to announce the creation of a new Alphabet company –  Isomorphic Labs – a commercial venture with the mission to reimagine the entire drug discovery process from the ground up with an AI-first approach and, ultimately, to model and understand some of the fundamental mechanisms of life.

For over a decade DeepMind has been in the vanguard of advancing the state-of-the-art in AI, often using games as a proving ground for developing general purpose learning systems, like AlphaGo, our program that beat the world champion at the complex game of Go. We are at an exciting moment in history now where these techniques and methods are becoming powerful and sophisticated enough to be applied to real-world problems including scientific discovery itself. One of the most important applications of AI that I can think of is in the field of biological and medical research, and it is an area I have been passionate about addressing for many years. Now the time is right to push this forward at pace, and with the dedicated focus and resources that Isomorphic Labs will bring.

An AI-first approach to drug discovery and biology
The pandemic has brought to the fore the vital work that brilliant scientists and clinicians do every day to understand and combat disease. We believe that the foundational use of cutting edge computational and AI methods can help scientists take their work to the next level, and massively accelerate the drug discovery process. AI methods will increasingly be used not just for analysing data, but to also build powerful predictive and generative models of complex biological phenomena. AlphaFold2 is an important first proof point of this, but there is so much more to come. 
At its most fundamental level, I think biology can be thought of as an information processing system, albeit an extraordinarily complex and dynamic one. Taking this perspective implies there may be a common underlying structure between biology and information science – an isomorphic mapping between the two – hence the name of the company. Biology is likely far too complex and messy to ever be encapsulated as a simple set of neat mathematical equations. But just as mathematics turned out to be the right description language for physics, biology may turn out to be the perfect type of regime for the application of AI.
‍
What’s next for Isomorphic Labs
This is just the beginning of what we hope will become a radical new approach to drug discovery, and I’m incredibly excited to get this ambitious new commercial venture off the ground and to partner with pharmaceutical and biomedical companies. I will serve as CEO for Isomorphic’s initial phase, while remaining as DeepMind CEO, partially to help facilitate collaboration between the two companies where relevant, and to set out the strategy, vision and culture of the new company. This will of course include the building of a world-class multidisciplinary team, with deep expertise in areas such as AI, biology, medicinal chemistry, biophysics, and engineering, brought together in a highly collaborative and innovative environment. (We are hiring!) 
As pioneers in the emerging field of ‘digital biology’, we look forward to helping usher in an amazingly productive new age of biomedical breakthroughs. Isomorphic’s mission could not be a more important one: to use AI to accelerate drug discovery, and ultimately, find cures for some of humanity’s most devastating diseases.

SOURCE

https://www.isomorphiclabs.com/blog

DeepMind creates ‘transformative’ map of human proteins drawn by artificial intelligence

DeepMind plans to release hundreds of millions of protein structures for free

James Vincent July 22, 2021 11:00 am

AI research lab DeepMind has created the most comprehensive map of human proteins to date using artificial intelligence. The company, a subsidiary of Google-parent Alphabet, is releasing the data for free, with some scientists comparing the potential impact of the work to that of the Human Genome Project, an international effort to map every human gene.

Proteins are long, complex molecules that perform numerous tasks in the body, from building tissue to fighting disease. Their purpose is dictated by their structure, which folds like origami into complex and irregular shapes. Understanding how a protein folds helps explain its function, which in turn helps scientists with a range of tasks — from pursuing fundamental research on how the body works, to designing new medicines and treatments.
 “the culmination of the entire 10-year-plus lifetime of DeepMind” 
Previously, determining the structure of a protein relied on expensive and time-consuming experiments. But last year DeepMind showed it can produce accurate predictions of a protein’s structure using AI software called AlphaFold. Now, the company is releasing hundreds of thousands of predictions made by the program to the public.
“I see this as the culmination of the entire 10-year-plus lifetime of DeepMind,” company CEO and co-founder Demis Hassabis told The Verge. “From the beginning, this is what we set out to do: to make breakthroughs in AI, test that on games like Go and Atari, [and] apply that to real-world problems, to see if we can accelerate scientific breakthroughs and use those to benefit humanity.”



Two examples of protein structures predicted by AlphaFold (in blue) compared with experimental results (in green). 
Image: DeepMind


There are currently around 180,000 protein structures available in the public domain, each produced by experimental methods and accessible through the Protein Data Bank. DeepMind is releasing predictions for the structure of some 350,000 proteins across 20 different organisms, including animals like mice and fruit flies, and bacteria like 
E. coli. (There is some overlap between DeepMind’s data and pre-existing protein structures, but exactly how much is difficult to quantify because of the nature of the models.) Most significantly, the release includes predictions for 98 percent of all human proteins, around 20,000 different structures, which are collectively known as the human proteome. It isn’t the first public dataset of human proteins, but it is the most comprehensive and accurate.

If they want, scientists can download the entire human proteome for themselves, says AlphaFold’s technical lead John Jumper. “There is a HumanProteome.zip effectively, I think it’s about 50 gigabytes in size,” Jumper tells The Verge. “You can put it on a flash drive if you want, though it wouldn’t do you much good without a computer for analysis!”
 “anyone can use it for anything” 
After launching this first tranche of data, DeepMind plans to keep adding to the store of proteins, which will be maintained by Europe’s flagship life sciences lab, the European Molecular Biology Laboratory (EMBL). By the end of the year, DeepMind hopes to release predictions for 100 million protein structures, a dataset that will be “transformative for our understanding of how life works,” according to Edith Heard, director general of the EMBL.
The data will be free in perpetuity for both scientific and commercial researchers, says Hassabis. “Anyone can use it for anything,” the DeepMind CEO noted at a press briefing. “They just need to credit the people involved in the citation.”

The benefits of protein folding

Understanding a protein’s structure is useful for scientists across a range of fields. The information can help design new medicines, synthesize novel enzymes that break down waste materials, and create crops that are resistant to viruses or extreme weather. Already, DeepMind’s protein predictions are being used for medical research, including studying the workings of SARS-CoV-2, the virus that causes COVID-19.
 “it will definitely have a huge impact for the scientific community” 
New data will speed these efforts, but scientists note it will still take a lot of time to turn this information into real-world results. “I don’t think it’s going to be something that changes the way patients are treated within the year, but it will definitely have a huge impact for the scientific community,” Marcelo C. Sousa, a professor at the University of Colorado’s biochemistry department, told The Verge.
Scientists will have to get used to having such information at their fingertips, says DeepMind senior research scientist Kathryn Tunyasuvunakool. “As a biologist, I can confirm we have no playbook for looking at even 20,000 structures, so this [amount of data] is hugely unexpected,” Tunyasuvunakool told The Verge. “To be analyzing hundreds of thousands of structures — it’s crazy.”

Notably, though, DeepMind’s software produces predictions of protein structures rather than experimentally determined models, which means that in some cases further work will be needed to verify the structure. DeepMind says it spent a lot of time building accuracy metrics into its AlphaFold software, which ranks how confident it is for each prediction.

Example protein structures predicted by AlphaFold.
Image: DeepMind
Predictions of protein structures are still hugely useful, though. Determining a protein’s structure through experimental methods is expensive, time-consuming, and relies on a lot of trial and error. That means even a low-confidence prediction can save scientists years of work by pointing them in the right direction for research.
Helen Walden, a professor of structural biology at the University of Glasgow, tells The Verge that DeepMind’s data will “significantly ease” research bottlenecks, but that “the laborious, resource-draining work of doing the biochemistry and biological evaluation of, for example, drug functions” will remain.
Sousa, who has previously used data from AlphaFold in his work, says for scientists the impact will be felt immediately. “In our collaboration we had with DeepMind, we had a dataset with a protein sample we’d had for 10 years, and we’d never got to the point of developing a model that fit,” he says. “DeepMind agreed to provide us with a structure, and they were able to solve the problem in 15 minutes after we’d been sitting on it for 10 years.”

Why protein folding is so difficult

Proteins are constructed from chains of amino acids, which come in 20 different varieties in the human body. As any individual protein can be comprised of hundreds of individual amino acids, each of which can fold and twist in different directions, it means a molecule’s final structure has an incredibly large number of possible configurations. One estimate is that the typical protein can be folded in 10^300 ways — that’s a 1 followed by 300 zeroes.

 Protein folding has been a “grand challenge” of biology for decades 

Because proteins are too small to examine with microscopes, scientists have had to indirectly determine their structure using expensive and complicated methods like nuclear magnetic resonance and X-ray crystallography. The idea of determining the structure of a protein simply by reading a list of its constituent amino acids has been long theorized but difficult to achieve, leading many to describe it as a “grand challenge” of biology.
In recent years, though, computational methods — particularly those using artificial intelligence — have suggested such analysis is possible. With these techniques, AI systems are trained on datasets of known protein structures and use this information to create their own predictions.

DeepMind’s AlphaFold software has significantly increased the accuracy of computational protein-folding, as shown by its performance in the CASP competition. 
Image: DeepMind
Many groups have been working on this problem for years, but DeepMind’s deep bench of AI talent and access to computing resources allowed it to accelerate progress dramatically. Last year, the company competed in an international protein-folding competition known as CASP and blew away the competition. Its results were so accurate that computational biologist John Moult, one of CASP’s co-founders, said that “in some sense the problem [of protein folding] is solved.”

DeepMind’s AlphaFold program has been upgraded since last year’s CASP competition and is now 16 times faster. “We can fold an average protein in a matter of minutes, most cases seconds,” says Hassabis.

@@@@@@@

The company also released the underlying code for AlphaFold last week as open-source, allowing others to build on its work in the future.

@@@@@@@

Liam McGuffin, a professor at Reading University who developed some of the UK’s leading protein-folding software, praised the technical brilliance of AlphaFold, but also noted that the program’s success relied on decades of prior research and public data. “DeepMind has vast resources to keep this database up to date and they are better placed to do this than any single academic group,” McGuffin told The Verge. “I think academics would have got there in the end, but it would have been slower because we’re not as well resourced.”

Why does DeepMind care?

Many scientists The Verge spoke to noted the generosity of DeepMind in releasing this data for free. After all, the lab is owned by Google-parent Alphabet, which has been pouring huge amounts of resources into commercial healthcare projects. DeepMind itself loses a lot of money each year, and there have been numerous reports of tensions between the company and its parent firm over issues like research autonomy and commercial viability.

Hassabis, though, tells The Verge that the company always planned to make this information freely available, and that doing so is a fulfillment of DeepMind’s founding ethos. He stresses that DeepMind’s work is used in lots of places at Google — “almost anything you use, there’s some of our technology that’s part of that under the hood” — but that the company’s primary goal has always been fundamental research.
 “There’s many ways value can be attained.” 

“The agreement when we got acquired is that we are here primarily to advance the state of AGI and AI technologies and then use that to accelerate scientific breakthroughs,” says Hassabis. “[Alphabet] has plenty of divisions focused on making money,” he adds, noting that DeepMind’s focus on research “brings all sorts of benefits, in terms of prestige and goodwill for the scientific community. There’s many ways value can be attained.”
Hassabis predicts that AlphaFold is a sign of things to come — a project that shows the huge potential of artificial intelligence to handle messy problems like human biology.

“I think we’re at a really exciting moment,” he says. “In the next decade, we, and others in the AI field, are hoping to produce amazing breakthroughs that will genuinely accelerate solutions to the really big problems we have here on Earth.”

SOURCE

https://www.theverge.com/platform/amp/2021/7/22/22586578/deepmind-alphafold-ai-protein-folding-human-proteome-released-for-free?__twitter_impression=true

Potential Use of Protein Folding Predictions for Drug Discovery

PROTAC Technology: Opportunities and Challenges

• Hongying Gao
• Xiuyun Sun
• Yu Rao*

Cite this: ACS Med. Chem. Lett. 2020, 11, 3, 237–240Publication Date:March 12, 2020https://doi.org/10.1021/acsmedchemlett.9b00597Copyright © 2020 American Chemical Society

Abstract

PROTACs-induced targeted protein degradation has emerged as a novel therapeutic strategy in drug development and attracted the favor of academic institutions, large pharmaceutical enterprises (e.g., AstraZeneca, Bayer, Novartis, Amgen, Pfizer, GlaxoSmithKline, Merck, and Boehringer Ingelheim, etc.), and biotechnology companies. PROTACs opened a new chapter for novel drug development. However, any new technology will face many new problems and challenges. Perspectives on the potential opportunities and challenges of PROTACs will contribute to the research and development of new protein degradation drugs and degrader tools.

Although PROTAC technology has a bright future in drug development, it also has many challenges as follows:
(1)
Until now, there is only one example of PROTAC reported for an “undruggable” target; (18) more cases are needed to prove the advantages of PROTAC in “undruggable” targets in the future.
(2)
“Molecular glue”, existing in nature, represents the mechanism of stabilized protein–protein interactions through small molecule modulators of E3 ligases. For instance, auxin, the plant hormone, binds to the ligase SCF-TIR1 to drive recruitment of Aux/IAA proteins and subsequently triggers its degradation. In addition, some small molecules that induce targeted protein degradation through “molecular glue” mode of action have been reported. (21,22) Furthermore, it has been recently reported that some PROTACs may actually achieve target protein degradation via a mechanism that includes “molecular glue” or via “molecular glue” alone. (23) How to distinguish between these two mechanisms and how to combine them to work together is one of the challenges for future research.
(3)
Since PROTAC acts in a catalytic mode, traditional methods cannot accurately evaluate the pharmacokinetics (PK) and pharmacodynamics (PD) properties of PROTACs. Thus, more studies are urgently needed to establish PK and PD evaluation systems for PROTACs.
(4)
How to quickly and effectively screen for target protein ligands that can be used in PROTACs, especially those targeting protein–protein interactions, is another challenge.
(5)
How to understand the degradation activity, selectivity, and possible off-target effects (based on different targets, different cell lines, and different animal models) and how to rationally design PROTACs etc. are still unclear.
(6)
The human genome encodes more than 600 E3 ubiquitin ligases. However, there are only very few E3 ligases (VHL, CRBN, cIAPs, and MDM2) used in the design of PROTACs. How to expand E3 ubiquitin ligase scope is another challenge faced in this area.

PROTAC technology is rapidly developing, and with the joint efforts of the vast number of scientists in both academia and industry, these problems shall be solved in the near future.

PROTACs have opened a new chapter for the development of new drugs and novel chemical knockdown tools and brought unprecedented opportunities to the industry and academia, which are mainly reflected in the following aspects:
(1)
Overcoming drug resistance of cancer. In addition to traditional chemotherapy, kinase inhibitors have been developing rapidly in the past 20 years. (12) Although kinase inhibitors are very effective in cancer therapy, patients often develop drug resistance and disease recurrence, consequently. PROTACs showed greater advantages in drug resistant cancers through degrading the whole target protein. For example, ARCC-4 targeting androgen receptor could overcome enzalutamide-resistant prostate cancer (13) and L18I targeting BTK could overcome C481S mutation. (14)
(2)
Eliminating both the enzymatic and nonenzymatic functions of kinase. Traditional small molecule inhibitors usually inhibit the enzymatic activity of the target, while PROTACs affect not only the enzymatic activity of the protein but also nonenzymatic activity by degrading the entire protein. For example, FAK possesses the kinase dependent enzymatic functions and kinase independent scaffold functions, but regulating the kinase activity does not successfully inhibit all FAK function. In 2018, a highly effective and selective FAK PROTAC reported by Craig M. Crews’ group showed a far superior activity to clinical candidate drug in cell migration and invasion. (15) Therefore, PROTAC can expand the druggable space of the existing targets and regulate proteins that are difficult to control by traditional small molecule inhibitors.
(3)
Degrade the “undruggable” protein target. At present, only 20–25% of the known protein targets (include kinases, G protein-coupled receptors (GPCRs), nuclear hormone receptors, and iron channels) can be targeted by using conventional drug discovery technologies. (16,17) The proteins that lack catalytic activity and/or have catalytic independent functions are still regarded as “undruggable” targets. The involvement of Signal Transducer and Activator of Transcription 3 (STAT3) in the multiple signaling pathway makes it an attractive therapeutic target; however, the lack of an obviously druggable site on the surface of STAT3 limited the development of STAT3 inhibitors. Thus, there are still no effective drugs directly targeting STAT3 approved by the Food and Drug Administration (FDA). In November 2019, Shaomeng Wang’s group first reported a potent PROTAC targeting STAT3 with potent biological activities in vitro and in vivo. (18) This successful case confirms the key potential of PROTAC technology, especially in the field of “undruggable” targets, such as K-Ras, a tricky tumor target activated by multiple mutations as G12A, G12C, G12D, G12S, G12 V, G13C, and G13D in the clinic. (19)
(4)
Fast and reversible chemical knockdown strategy in vivo. Traditional genetic protein knockout technologies, zinc-finger nuclease (ZFN), transcription activator-like effector nuclease (TALEN), or CRISPR-Cas9, usually have a long cycle, irreversible mode of action, and high cost, which brings a lot of inconvenience for research, especially in nonhuman primates. In addition, these genetic animal models sometimes produce phenotypic misunderstanding due to potential gene compensation or gene mutation. More importantly, the traditional genetic method cannot be used to study the function of embryonic-lethal genes in vivo. Unlike DNA-based protein knockout technology, PROTACs knock down target proteins directly, rather than acting at the genome level, and are suitable for the functional study of embryonic-lethal proteins in adult organisms. In addition, PROTACs provide exquisite temporal control, allowing the knockdown of a target protein at specific time points and enabling the recovery of the target protein after withdrawal of drug treatment. As a new, rapid and reversible chemical knockdown method, PROTAC can be used as an effective supplement to the existing genetic tools. (20)

SOURCE

PROTAC Technology: Opportunities and Challenges

• Hongying Gao
• Xiuyun Sun
• Yu Rao*

Cite this: ACS Med. Chem. Lett. 2020, 11, 3, 237–240

Goal in Drug Design: Eliminating both the enzymatic and nonenzymatic functions of kinase.

Work-in-Progress

Induction and Inhibition of Protein in Galectins Drug Design

Work-in-Progress

Screening Proteins in DeepMind’s AlphaFold DataBase

The company also released the underlying code for AlphaFold last week as open-source, allowing others to build on its work in the future.

Work-in-Progress

Other related research published in this Open Access Online Journal include the following:

Synthetic Biology in Drug Discovery

Synthetic Biology in Drug Discovery

Peroxisome proliferator-activated receptor (PPAR-gamma) Receptors Activation: PPARγ transrepression  for Angiogenesis in Cardiovascular Disease and PPARγ transactivation for Treatment of Diabetes

Peroxisome proliferator-activated receptor (PPAR-gamma) Receptors Activation: PPARγ transrepression for Angiogenesis in Cardiovascular Disease and PPARγ transactivation for Treatment of Diabetes