We're sunsetting PodQuest on 2025-07-28. Thank you for your support!
Export Podcast Subscriptions
cover of episode Audio long read: AI has dreamt up a blizzard of new proteins. Do any of them actually work?

Audio long read: AI has dreamt up a blizzard of new proteins. Do any of them actually work?

2024/11/29
logo of podcast Nature Podcast

Nature Podcast

AI Deep Dive AI Insights AI Chapters Transcript
People
A
Anthony Gitter
B
Burkhard Rost
B
Burkhard Rust
C
Clayton Kozanocki
E
Erika de Benedictis
J
Julian Englert
M
Michael Heintinger
N
Noelia Feruth Capope
Topics
Noelia Feruth Capope:蛋白质设计竞赛有助于推动该领域发展,加快验证和标准制定,但需要克服一些障碍,例如确定要解决的问题以及如何客观地选择优胜者。 Burkhard Rust:蛋白质设计竞赛如果执行不当,可能会对该领域造成损害。竞赛的评判标准过窄可能会适得其反。 Burkhard Rost:蛋白质设计竞赛可以像CASP一样推动蛋白质设计领域的发展,需要设计合理的竞赛机制来激励参与者。 Clayton Kozanocki:Bits to Binders竞赛吸引了来自全球各地的众多参赛团队,展现了竞赛的广泛影响力。 Julian Englert:Adaptive Bio公司的竞赛吸引了专业人士和非专业人士的参与,降低了进入门槛,使更多人能够参与蛋白质设计。 Erika de Benedictis:选择蛋白质设计竞赛的优胜者并不容易,需要考虑蛋白质设计的各种失败方式。 Anthony Gitter:参赛者应该公开他们的方法,以便其他人学习。蛋白质设计竞赛可以促进不同领域之间的合作,组织者应该努力创建一个社区。 Michael Heintinger:参加蛋白质设计竞赛的主要动机是节省时间,而不是奖金。 Martin Paceza and Lennart Nickel: 通过开源代码和预印本分享了他们的方法,推动了领域的开放合作。

Deep Dive

Key Insights

Why are AI-designed proteins being created faster than they can be tested?

AI tools like AlphaFold and protein language models have become more powerful and popular, leading to a surge in the generation of designer proteins. However, the pace of creation outstrips the ability to test these proteins in labs, causing confusion about their effectiveness.

What role do protein design competitions play in the field of protein engineering?

Protein design competitions aim to identify functional proteins from the vast number of designs generated by AI. They lower the barrier to entry for newcomers, accelerate validation and standards development, and foster a sense of community among researchers.

What challenges do protein design competitions face?

Key challenges include identifying relevant problems to tackle, selecting winners objectively, and ensuring that competitions do not narrow the field too much or discourage sharing of methods. Proper execution is crucial to avoid damaging the field.

How did the CASP competition influence the development of AI in protein structure prediction?

The CASP competition, launched in 1994, revolutionized protein structure prediction by challenging scientists to predict 3D shapes from amino acid sequences. It directly led to the creation of AlphaFold, which solved the problem of predicting simple protein structures.

What are some examples of recent protein design competitions?

Examples include the Protein Engineering Tournament by Align to Innovate, the Winter Protein Design Games by Liberum Bio and Rosetta Commons, and the Adaptive Bio competition, which focused on designing proteins to target EGFR in cancer.

Who participated in the protein design competitions, and what were the outcomes?

Participants ranged from professional protein engineers to hobbyists with no formal biology experience. Despite high participation, success rates were low, with only a small percentage of designs proving functional in lab tests.

What are the potential benefits of protein design competitions for the scientific community?

Competitions can accelerate the pace of validation, encourage collaboration, and bring together diverse fields like biochemistry and machine learning. They also provide opportunities for learning and community-building within the protein design field.

What was the outcome of the Adaptive Bio competition, and how did it impact participants?

Only 5 out of 147 tested designs successfully bound to the target molecule, reflecting the challenges of protein engineering. Despite the low success rate, participants gained valuable experience and connections, with some continuing to participate in future competitions.

Chapters
The use of AI in protein design has led to a surge in the creation of designer molecules. However, this rapid increase has outpaced the ability to test these proteins, leading to the development of protein design competitions to identify functional proteins. These competitions aim to accelerate validation, standards development, and community building within the field.
  • AI tools like AlphaFold and protein language models are used in protein design competitions.
  • Competitions help to identify functional proteins among many.
  • The competitions aim to quicken the pace of validation and standards development.

Shownotes Transcript

Translations:
中文

Oh my god, it's the coolest thing ever. Hey guys, have you heard of Gold Belly? Well, check this out. It's this amazing site where they ship the most iconic, famous foods from restaurants across the country anywhere nationwide. I've never found a more perfect gift than food. They ship Chicago deep dish pizza, New York bagels, Maine lobster rolls, and even Ina Garten's famous cakes. Seriously.

So if you're looking for a gift for the food lover in your life, head to goldbelly.com and get 20% off your first order with promo code GIFT.

This is an ad by BetterHelp. What's your perfect night? Is it curling up on the couch for a cozy, peaceful night in? Therapy can feel a bit like that. Your comfort place where you replenish your energy. With BetterHelp, get matched with a therapist based on your needs entirely online. It's convenient and suited to your schedule. Find comfort this season with BetterHelp. Visit BetterHelp.com today to get 10% off your first month.

That's BetterHelpHELP.com.

Powered by his laptop, some coffee, and, at one point, about 80 cloud-based artificial intelligence or AI processors, he generated scores of computer-engineered proteins designed to block a cell receptor that is mutated in some tumors.

Naka, who on weekdays is a protein engineer at a medical technology company in Alameda, California, entered his 10 most promising creations into a newly launched protein design competition and watched them climb to the top of the leaderboard.

The contest, run by a biotechnology start-up firm called Adaptive Bio in Lausanne, Switzerland, is one of at least five to have popped up over the past year or so. Most of the people entering the competitions are wielding AI tools such as AlphaFold and chatbot-inspired protein language models that have exploded both in popularity and in power.

Three of the researchers behind some of these tools were awarded this year's Nobel Prize in Chemistry for their efforts. The accolades come, in part, from the hope that newly created proteins could serve as more effective drugs, industrial enzymes or laboratory reagents. But the boom in designer proteins has mostly sown confusion, say scientists.

People are churning them out faster than they can be made and tested in labs, making it hard to tell which approaches are truly effective. Contests have driven key scientific advances in the past, particularly for the field of protein structure prediction. This latest crop of competitions is drawing people from all around the world into the related field of protein design by lowering the barrier to entry.

It could also quicken the pace of validation and standards development, and perhaps help to foster community. "It will help push the field forward and test methods more quickly," says Noelia Feruth Capope, a computational biologist at the Centre for Genomic Regulation in Barcelona, Spain. But the competitions will have to overcome some hurdles, say scientists, such as identifying which problems to tackle and working out how to select winners objectively.

Getting the formula right is important. Quote, these competitions can do damage, end quote, to a field if they are not executed properly, says Burkhard Rust, a computational biologist at the Technical University of Munich in Germany. The protein design contests are partly inspired by a 30-year-old competition that helped to kick off the revolution in biological AI.

Since 1994, the Critical Assessment of Structure Prediction, or CASP, has been challenging scientists to predict the 3D shape of proteins from their amino acid sequences.

Winners of the competition, founded by computational biologist John Moult at the University of Maryland in Rockville, and Christoph Fidelis, a computational biologist at the University of California, Davis, are determined by comparing the computational predictions with unpublished structural models. In 2018, London-based DeepMind, now Google DeepMind, won CASP with its first version of the protein structure prediction tool, AlphaFold.

Its next iteration, AlphaFold2, performed so well in 2020 that Malt declared the problem of predicting simple protein structures largely solved. The competition has since shifted its focus to other emerging challenges, such as predicting the structure of multiple interacting proteins in a complex.

Now, many hope that these competitions can push the protein design field forwards, just as CASP helped to spur a revolution in protein structure prediction. There would not have been an AlphaFold had it not been for CASP, says Rost. We need these competitions to do the job right and motivate people.

In June, Rost and several of his colleagues won the Protein Engineering Tournament, run by Align to Innovate, an international open science non-profit organization. The event included two parts. First, participants tried to predict the properties of different enzyme variants. The best-performing teams in this round then re-engineered an enzyme that breaks down starch, with the best designs determined by lab experiments.

A 2025 tournament is now in the works. A winter protein design games contest that announced its winner in April was run by Liberum Bio, a biotechnology company in Kitchener, Canada, and Rosetta Commons, a collaboration of mostly academic scientists that maintains protein modelling tools.

The contest tasked entrants with re-engineering an existing protein, a plant virus enzyme used widely in protein purification, to make the molecule more efficient. Two other contests asked participants to come up with entirely new proteins. Adaptives was looking for proteins capable of attaching to a growth hormone receptor called EGFR that is overactive in many cancers.

The 90 entrants submitted more than 700 designs. And in bits to binders, researchers are vying to create small proteins that could be used in a T-cell cancer therapy. Run by the BioML Society, a graduate student-led group at the University of Texas at Austin, it attracted 64 teams from 42 countries, including Nigeria, Colombia, Iran and India.

Around 18,000 designs are now being tested, with results due in early 2025. "We were quite surprised with the turnout," says co-organiser Clayton Kozanocki, a biochemistry PhD student at the university. Julian Englert, chief executive and co-founder of Adaptiv, says that many of the participants in its contest work in protein engineering and design.

However, the competition has also received promising entries from people with no professional experience in biology. An entrant from Iran made his predictions using a gaming computer because he didn't have access to more powerful systems.

Englert says that the high-quality entries from people who aren't established researchers reminds him of the garage-tinkering origins of Apple, Microsoft and other tech giants. Quote, it would have taken them two years of studying and joining a lab to get to the point where they can get started.

Here, they can do it over a weekend, end quote. He imagines a future in which freelance protein designers vie for bounties set by companies, academic labs, and others seeking a custom molecule. The competitions can save time in other ways, too.

Getting quick experimental results from contest organisers was a big motivation for Michael Heintinger, a machine learning scientist at the Technical University of Munich, who was part of the winning team with Rost. Otherwise we would have had to put in the time to write a grant, he says. For me, the prize is saving time. In terms of actual prizes, the Align to Innovate tournament didn't offer one, but some others do.

The winners of Bits to Binders will get a 3D printed trophy of their design and some merchandise from the biotech company that is conducting the experiments, called Lear Laboratories in Egan, Minnesota. There will also be opportunities for collaboration.

Adaptive, which sells automated lab testing of molecules created by protein designers, offered a handful of free experiments and some of its own swag. And the winners of the Rosetta Winter Games split US$5,000.

But the standout is the recently launched Evolved 2024 contest, in which the first-place team will take home a $25,000 credit for Amazon Web Services, along with credits from other companies, including OpenAI, worth thousands of dollars.

Its sponsors include Lux Capital, a venture capital firm in New York City that has invested more than $1.5 billion in tech firms, and Evolutionary Scale, a biology AI startup also in New York City that has attracted $142 million in investment. Choosing who will reap these rewards isn't always straightforward.

The Evolved 2024 contest, more of a hackathon in which teams work on broad brush problems such as predicting drug efficacy and safety, will be judged subjectively by a panel of experts. But even for the contests with more clear-cut protein design goals, quote, it's not trivial to figure out who wins, says Erika de Benedictis, a biological engineer and founder of Align2Innovate.

Her organisation's tournament gauged designs on the basis of their activity, stability and how well, or even whether, they could be made. When you design a protein, there are a lot of ways it can fail, she says. And if competitions are to move the needle in protein design, they will need to address the challenges that the wider field is tackling, say scientists.

Unlike structure prediction, protein design can have wildly different criteria from task to task. The approaches to craft a particular type of enzyme might not translate to other proteins, such as vaccine components.

The competition could prove counterproductive if they send the field down a rabbit hole, for example by judging designs too narrowly, warns Rust. Researchers could also fail to reap the full benefit of protein design competitions if contestants keep quiet about their approaches, says Anthony Gitter, a computational biologist at the University of Wisconsin-Madison.

If teams aren't communicating their methods, there's not much opportunity to learn about what works and what fails. So far, this doesn't seem to be happening. Most of the competitions encourage or even require participants to describe their approaches.

The contests could also help to bring together some of the disparate fields that have been drawn to protein design, from biochemistry labs that pioneered protein engineering methods to machine learning scientists who cut their teeth in natural language processing, says Gitter. People organising the competitions, to have maximum impact on the field, should think really hard about how to create a community.

When the adaptive competition results were announced in late September, Naka was disappointed. Although all 10 of his entries looked strong, none of his designs worked in the lab. Only 5 of the 147 designs that were tested actually bound to the target molecule, and more than 50 of them couldn't even be made. That actually isn't bad. Past efforts to design EGFR binders have had much lower success rates.

It's par for the course in protein engineering. You have to be ready to fail a lot, Nacker says. The winners were Martin Paceza and Lennart Nickel, structural biologists at the Swiss Federal Institute of Technology in Lausanne, who posted a preprint describing their approach and made its code open source. Adaptive has now launched a second competition that builds on the first. Nacker wishes he had started working on his entries earlier.

He describes his hackathon as, quote, type 2 fun, end quote. Painful at the time, but enjoyable in retrospect. Through the competition, he forged connections with like-minded scientists, including Gitter. It feels like it lowered the barrier to entry and let a lot of new people participate in protein design, he says. I'll definitely be participating in similar events in the future.

To read more of nature's long-form journalism, head over to nature.com slash news. Hey, guys.

Have you heard of GoldBelly? It's this amazing site where they ship the most iconic, famous foods from restaurants across the country, anywhere, nationwide. I've never found a more perfect gift than food. They ship Chicago deep dish pizza, New York bagels, Maine lobster rolls, and even Ina Garten's famous cakes. So if you're looking for a gift for the food lover in your life, head to GoldBelly.com and get 20% off your first order with promo code GIFT.

What makes a great pair of glasses? At Warby Parker, it's all the invisible extras without the extra cost. Their designer quality frames start at $95, including prescription lenses, plus scratch-resistant, smudge-resistant, and anti-reflective coatings, and UV protection, and free adjustments for life.

To find your next pair of glasses, sunglasses, or contact lenses, or to find the Warby Parker store nearest you, head over to warbyparker.com. That's warbyparker.com.