By Christopher Ganatti
July 28, 2022 was a historic day for biology and artificial intelligence (AI). DeepMind, an AI research company owned by Alphabet (GOOG) (GOOGL), has obtained the structural data on more than 200 million proteins from its AlphaFold tool available for free. This represents data on approximately 1 million species and covers the vast majority of known proteins on Earth.1
In proteins, form can determine function
From the late 1990s to the early 2000s, the scientific community was inundated with information about the race to sequence the human genome. This genome contains the instructions embedded in DNA for how cells should build certain structures, usually by forming proteins made from different combinations of amino acids.
In a sense, DNA is the instruction manual, amino acids are the building blocks, and protein is the product. Knowing the code, while important, is not enough.
Figure 1 is instructive on this point. This is the image of a protein that could protect the organism responsible for malaria from attacks by the human immune system. Even if you knew the list and order of all the amino acids, it would be difficult to go from this list to something like Figure 1 in three dimensions.
Figure 1: Protein associated with the malaria parasite
The importance of protein shape cannot be overstated:
- It may correspond to how it might react in the presence of different molecules, such as those associated with various drug therapies.
- Shape variations – sometimes called mutations – could be informative in determining causative factors for certain symptoms or diseases.
- Parts of the shape could be used as targets. Think of the “spike protein” associated with the virus causing the COVID-19 pandemic, specifically targeted in mRNA vaccines.
AlphaFold represents a leap forward
Scientific breakthroughs are difficult, as in many cases one builds on the other and the other and the other. The process can take decades before widespread results impact the lives of the general public.
For example, we sequenced the human genome, but that didn’t necessarily lead to immediate cures for all kinds of diseases or conditions. While mRNA research had been going on for decades, the COVID-19 pandemic was a catalyst that accelerated the process of using mRNA in the specific case of vaccines.
It is therefore unlikely that AlphaFold’s new database will lead to immediate remedies for difficult conditions. The critical element concerns how researchers who would previously have had to undertake a tedious process of X-ray crystallography to determine the shape of a given protein could instead access the database. Experimental techniques would still have their place, but less time should be spent on the equivalent of the blank page.
What is also amazing is that the database of AlphaFold is, in collaboration with the European Institute of Bioinformatics of the European Molecular Biology Laboratory (EMBL-EBI), freely available with a simple interface.
It also provides an accuracy estimate, acknowledging that AI-based predictions don’t always yield perfect results. About 35% of the 214 million predictions are rated as very accurate – about as good as the experimental results. An additional 45% is deemed accurate enough for many applications.2
Drug discovery: better therapies developed more efficiently
Even before inflation began at the levels seen in the summer of 2022, it was widely recognized that drug development is time consuming and expensive. As a result, many drugs carry exorbitant price tags. Any process that could alleviate this pressure without degrading the quality of therapies would be extremely valuable.
Consider the following might be instructive as space continues to progress:3
- Pipeline growth: From 2010 to 2021, 20 small companies focused on AI drug discovery, typically focused on smaller molecules, had development pipelines that were about 50% as robust as those of 20 of the largest big pharma companies. We recognize that pipeline reporting may not be perfect and a molecule in a pipeline is not a finished product, but activity is the first step on the way.
- Composition of the pipeline: It’s not always disclosed, but available information indicates that AI-focused companies tend to focus on well-established biological targets for their therapies, around which much is known. Data is the fuel of AI, and these companies will also want a better chance of success. Big pharma will be more likely to venture into more emerging areas of drug discovery.
- Structures and chemical properties: It is too early to draw strong conclusions about AI drug discovery efforts versus big pharma efforts on this point.
- Discovery calendar: Preliminary data seems to indicate that, while traditional approaches tend to take five or six years in the preclinical phases, AI-driven drug discovery could, in some cases, reduce that time to four years.
We note that this is more of a story of progress than perfection, as we seem to be some distance away from AI capable of fully creating new drugs. But AI represents a whole new set of tools that could have beneficial effects.
AlphaFold’s database, for example, can provide drug researchers with important inputs and catalysts for different ideas, even if it doesn’t have the immediate answer or cure in its system.
Focus on AI megatrends and BioRevolution
At WisdomTree, we focus on both the AI Megatrend and the BioRevolution Megatrend. What we see here with the case of AlphaFold is an important case study in that AI is a tool that can potentially boost other megatrends, in this case the BioRevolution.
It is no coincidence that the BioRevolution at the same time increases massive amounts of data, massive amounts of processing power and other things like cloud computing are readily available. It is exciting to see what the coming decades can bring to these areas.
1 Source: Callaway, Ewen, “The Entire Protein Universe: AI Predicts the Shape of Nearly Every Known Protein”, Nature, Volume 608, 8/4/22.2 Source: Callaway, 8/4/22. 3 Source: Jayatunga et al, “AI in small molecule drug discovery: a wave to come?” Nature’s Review: Drug Discovery, Volume 21, 3/22.
Important risks related to this article
Christopher Gannatti is an employee of WisdomTree UK Limited, a European subsidiary of WisdomTree Asset Management, Inc.’s parent company, WisdomTree Investments, Inc.
DeepMind is a subsidiary of Alphabet. As of August 16, 2022, Alphabet was exposed at 1.36% in WTAI and 0% in WDNA.
WTAI: There are risks associated with investing, including possible loss of capital. The Fund invests in companies primarily involved in the investment theme of artificial intelligence (AI) and innovation. Companies engaged in AI typically face intense competition and potentially rapid product obsolescence. These companies are also heavily dependent on intellectual property rights and may be harmed by the loss or degradation of these rights. Additionally, AI companies typically invest large sums in research and development, and there is no guarantee that the products or services produced by these companies will be successful. Companies that capitalize on innovation and develop technologies to replace older technologies or create new markets may not succeed. The Fund invests in securities included in or representative of its index, regardless of their investment merit, and the Fund does not attempt to outperform its index or take defensive positions in declining markets. The composition of the Index is governed by an Index Committee and the Index may not perform as intended. Please read the Fund’s prospectus for specific details regarding the Fund’s risk profile.
WDNA: There are risks associated with investing, including possible loss of capital. The Fund invests in BioRevolution companies, which are companies that have been significantly transformed by advances in genetics and biotechnology. BioRevolution companies face intense competition and potentially rapid product obsolescence. These companies may be adversely affected by the loss or deterioration of intellectual property rights and other proprietary information or by changes in government regulations or policies. In addition, BioRevolution companies may be subject to risks associated with genetic analysis. The Fund invests in securities included in or representative of its index, regardless of their investment merit, and the Fund does not attempt to outperform its index or take defensive positions in declining markets. The composition of the Index is governed by an Index Committee and the Index may not perform as intended. Please read the Fund’s prospectus for specific details regarding the Fund’s risk profile.
Christopher Gannatti, CFA, Global Head of Research
Christopher Gannatti started at WisdomTree as a Research Analyst in December 2010, working directly with Jeremy Schwartz, CFA®, Director of Research. In January 2014, he was promoted to Associate Director of Research where he was responsible for leading various groups of analysts and strategists within WisdomTree’s broader research team. In February 2018, Christopher was promoted to Head of Research for Europe, where he will be based in WisdomTree’s London office and will be responsible for all of WisdomTree’s research efforts in the European market, as well as supporting the UCIT platform on a global scale. Christopher came to WisdomTree from Lord Abbett, where he worked for four and a half years as a regional consultant. He received his MBA in Quantitative Finance, Accounting and Economics from NYU’s Stern School of Business in 2010, and he received his BS in Economics from Colgate University in 2006. Christopher holds a Chartered Financial Analyst designation.
Editor’s note: The summary bullet points for this article were chosen by the Seeking Alpha editors.