Skip to main content


AI, Protein Folding & Amyloidosis

The Protein Folding Problem

Proteins are the building blocks of life. They are large complex molecules, made up of chains of amino acids, and what a protein does largely depends on its unique 3D structure. Figuring out what shapes proteins fold into is known as the “protein folding problem.”  For decades and decades, one of biology’s biggest challenges has been finding a solution for the “protein folding problem” and is explained in the linked video below.

AI, DeepMind and Google Find Answers

Founded in 2010, DeepMind researches and builds safe AI (Artificial Intelligence) systems that learn how to solve problems and advance scientific discovery for all. They joined forces with Google in 2014 to accelerate their work. They’re a team of scientists, engineers, machine learning experts and more, working together to advance the state of the art in AI.

In a major scientific breakthrough, DeepMind’s AI system AlphaFold has been recognized as a solution to this grandest of all biological problems – the “protein folding problem.”  Here is an excellent video explaining AlphaFold and the making of a scientific breakthrough.

According to Professor Venki Ramakrishman, Nobel laureate and President of the Royal Society,

This computational work represents a stunning advance on the protein-folding problem, a 50-year-old grand challenge in biology.  It has occurred decades before many people in the field would have predicted. It will be exciting to see the many ways in which it will fundamentally change biological research.


Potential Impact for Amyloidosis

For diseases which originate with misfolded proteins, such as amyloidosis, “investigators have been doing this exercise by ‘brute force’ until now,” according to Dr. Angela Dispenzieri from the Mayo Clinic.  This AI research is likely to open a whole new world of insight and answers, from which new and more effective treatments can be developed.

Marina Ramirez-Alvarado, Ph.D., whose research laboratory at the Mayo Clinic studies misfolding and amyloid formation in light chain amyloidosis, had this to say.

The protein folding problem, one of the most important scientific questions of the 20th century is making headlines today with the artificial intelligence work from DeepMind. It is clear that DeepMind will provide important basic understanding of the folding process and will significantly benefit those amyloidosis diseases that involve secreted, folded proteins, such as light chain (AL), and Transthyretin (ATTR) amyloidosis.

Dr. Morie Gertz, a hematologist/oncologist from the Mayo Clinic who has decades of clinical experience with amyloidosis, weighs in on some of the possible outcomes from this ground-breaking research.

The ability to predict protein folding in three dimensions may result in the ability to predict which protein sequences are likely to form amyloid fibrils. In light chain amyloidosis this could allow for long-term monitoring of selected patients likely to develop amyloidosis. This would permit extremely early diagnosis long before symptoms developed. It would also allow for the exploration of why wild-type TTR amyloidosis forms amyloid fibrils in the heart in some patients but not in others.


However, it won’t answer all questions …

Dr. Vaishali Sanchorawala, director of Boston University’s Amyloidosis Center offers these words of perspective.

The “protein folding problem” that DeepMind’s AlphaFold is designed to solve is predicting the native, functional state of a protein from just its amino acid sequence. Amyloidosis, though, is caused by our bodies’ failure to solve that problem, resulting in misfolded and aggregated proteins. AlphaFold’s remarkable achievement can definitely help to better understand native structure of amyloidogenic light chain proteins. However, amyloid fibrils are different from the native states of their precursor proteins and therefore the adaptation of AlphaFold to study protein misfolding and aggregation, perhaps by predicting the structures of complex amyloid fibrils, might be better able to predict the effects of mutations that alter people’s risk of developing amyloidosis.


In closing …

AI is rapidly advancing the knowledge of protein misfolding, unlocking answers for amyloidosis which should lead to earlier diagnosis, improved treatment, and better patient survival.






Angela Dispenzieri, M.D.

Morie A. Gertz, M.D., M.A.C.P.

Vaishali Sanchorawala, M.D.

Marina Ramirez-Alvarado, Ph.D.


High Accuracy Protein Structure Prediction Using Deep Learning

John Jumper, Richard Evans, Alexander Pritzel, Tim Green, Michael Figurnov, Kathryn Tunyasuvunakool, Olaf Ronneberger, Russ Bates, Augustin Žídek, Alex Bridgland, Clemens Meyer, Simon A A Kohl, Anna Potapenko, Andrew J Ballard, Andrew Cowie, Bernardino Romera-Paredes, Stanislav Nikolov, Rishub Jain, Jonas Adler, Trevor Back, Stig Petersen, David Reiman, Martin Steinegger, Michalina Pacholska, David Silver, Oriol Vinyals, Andrew W Senior, Koray Kavukcuoglu, Pushmeet Kohli, Demis Hassabis.


In Fourteenth Critical Assessment of Techniques for Protein Structure Prediction (Abstract Book), 30 November – 4 December 2020. Retrieved from here.



Not Just A Game: Protein Structure Prediction

Michael Rosen, an admired and respected investor for decades, penned this excellent blog that summarizes the state of protein structure prediction and how it has evolved since 1994 to today. So well written, below we offer his article in its entirety, along with our heartfelt thanks.


There are twenty amino acids in the human body. Amino acids are the chemical links that make up proteins. Proteins perform all sorts of essential tasks. Hemoglobin, for example, is the protein molecule in red blood cells that carries oxygen from the lungs to the body’s tissues and returns carbon dioxide from the tissues back to the lungs. Keratin is the type of protein that makes up your hair, skin, and nails. The spike (S) protein plays a key role in the receptor recognition and cell membrane fusion process in SARS-CoV-2.

There are approximately 30 trillion cells in the human body. Each cell contains between one billion and three billion proteins. How can a mere 20 amino acids make billions of proteins?

The answer is how each protein folds on itself to form its final shape. We can see this through X-ray crystallography, which sends electromagnetic radiation to interact with molecular crystals that reveal each atom of a molecule. This is great, but X-ray crystallography is time-consuming and very expensive.

The great molecular biologist, Cyrus Levinthal, estimated that there are 10300 possible configurations of a typical protein. Brute calculation of each variation is impossible: it would take longer than the age of the universe (almost 14 billion years) to identify each combination. Another approach is required if we hope to know the structure of proteins.

Every two years since 1994, scientists have gathered for a competition to see who could create an algorithm that could accurately predict the shape of proteins using only a list of its amino acids. The competition is called the Critical Assessment of Protein Structure Prediction, and the answer is no one. Participants are given 43 proteins to model, and the best programs were able to get two or three right. Until 2018, when DeepMind’s AlphaFold program successfully predicted 25 of the 43 proteins (the second-place program got three right). The competition was held again last month, and DeepMind’s newer version, AlphaFold2, achieved an astonishing accuracy of 92.4%.

A folded protein can be thought of as a “spatial graph”, and DeepMind (based in the UK and owned by Alphabet) built a neural network that uses evolutionarily related sequences, multiple sequence alignment (MSA), and a representation of amino acid residue pairs to refine and interpret this graph while reasoning over the implicit graph that it’s building. By iterating this process over a few days, AlphaFold developed strong predictions of the underlying physical structure of the protein and was able to calculate which parts of each predicted protein structure are reliable using an internal confidence measure.



This is an extraordinary accomplishment: from a list of the 20 amino acids that comprise a protein, AlphaFold was able to predict the shape of that protein, out of 10300 possibilities, to an accuracy of 92.4%. Earlier this year, AlphaFold predicted several protein structures of the SARS-CoV-2 virus, including ORF3a and another coronavirus protein, ORF8, whose structures were previously unknown. Experimentalists have confirmed the existence of both these structures.

The implications of this achievement cannot be overstated. A misshapen protein is thought to be the cause of Alzheimer’s and many other diseases. If we could only identify the shape of that protein, we could have a chance to correct it. For the first time, with AlphaFold, we now have that chance. We will be better able to determine which drugs are likely to bind to a particular protein and to effectively design proteins to catalyze chemical reactions.

In 2003, the Human Genome Project (and Celera Genomics) successfully mapped the entire human genome. Since then, the Universal Protein database has collected 180 million protein sequences, but only 170,000 have had their structures determined because of the time and expense required to do so. AlphaFold represents an exponential leap forward in being able to determine protein structures, and thus is a huge step toward the effective treatment of diseases.

As investors, we obsess over the vicissitudes of our political discourse (such as it is) as if it were a sporting contest. We scrutinize each economic release and infer the hidden meanings of a central banker’s pronouncements. Most of what fills our working days is noise, and we are easily distracted from the achievements that will profoundly determine our future. AlphaFold’s success is one such achievement.

This is not the first time we have heard from DeepMind. Three years ago I wrote about AlphaGo, DeepMind’s game program that defeated world champion Lee Sedol in Go (https://www.angelesinvestments.com/insights/investment-insights/3rd-quarter-2017-ghost-moves). I noted that there are 10170 legal arrangements of the stones on a Go board, more than there are atoms in the universe. Like the placement of Go pieces, the number of protein shapes are too massive to crunch through every combination. And as with AlphaGo, AlphaFold found a shortcut. DeepMind took its champion gaming skills and applied them to unlocking the mysteries of biochemistry.

It’s not just a game; it is how our civilization advances.





If you’d like to read more of Michael’s excellent blogs, on topics wide-ranging, please visit www.angelesinvestments.com

If you’d like to read more about the competition, bi-annual results, and the organization behind the project, please visit www.predictioncenter.org

This website uses cookies

This site uses cookies to provide more personalized content, social media features, and ads, and to analyze our traffic. We might share information about your use of our site with our social media, advertising, and analytics partners who may combine it with other information that you’ve provided to them or that they’ve collected from your use of their services. We will never sell your information or share it with unaffiliated entities.

Newsletter Icon