AlphaFold, the revolutionary, Nobel prize-winning tool for predicting protein structures, has a problem: it's running low on data.
The latest version of the artificial intelligence (AI) model, AlphaFold 3, has been touted as a game-changer for drug discovery, because it can model the interaction of proteins with other molecules, including drugs.
But a lack of examples of these interactions in the data underpinning AlphaFold -- hundreds of thousands of publicly available protein structures -- is holding the tool back for the applications that drug companies are most interested in, say scientists.
A consortium of leading pharmaceutical companies announced plans today to make their own AlphaFold-3-inspired AI model using thousands of protein structures that are currently secreted away in company vaults. This is in addition to the more than 200,000 protein structures freely available in the Protein Data Bank (PDB).
"The data that's missing from the PDB is exactly the data that's present in our internal data," says John Karanicolas, head of computational drug discovery at the pharma company AbbVie in Chicago, Illinois, and part of the effort, called the AI Structural Biology Consortium.
The consortium's model will be based on OpenFold 3, a fully open-source reproduction of AlphaFold 3 that has been developed by academic researchers (using only publicly available data) and is due to be released in April. But there are no plans to make the consortium's model available beyond member companies, which include AbbVie, Johnson & Johnson, Sanofi and Boehringer Ingelheim.
Google DeepMind, the London-based company that developed AlphaFold, is not involved in the project and did not wish to comment. Its spin-off company, Isomorphic Labs, is using AlphaFold 3 as part of collaborations with drug companies, including Novartis and Eli Lilly.
AlphaFold's ability to predict proteins' 3D shapes from their sequences relies on access to the PDB's huge collection of protein structures mapped with experimental methods, such as X-ray crystallography. Many of these structures include interacting molecules -- but they tend to involve biological partners such as the cellular energy source ATP, rather than drug compounds, says Karanicolas.
As a result, AlphaFold 3 does an adequate job of predicting how proteins interact with would-be drugs, but "it's still a very open problem", says Mohammed AlQuraishi, a computational biologist at Columbia University in New York City who is leading the development of OpenFold.
It's possible that pharma-company protein structures, which are rarely deposited in the PDB, could help. As part of drug-development campaigns, firms routinely determine multiple structures for the same protein bound to many different drug candidates.
The full extent of these proprietary protein-structure data isn't known. But the data could equal or even exceed those of the PDB, says Stephen K. Burley, a director of one of the organizations that hosts the repository and a structural biologist at Rutgers University in Piscataway, New Jersey. AbbVie alone is contributing more than 9,000 structures to the consortium's AI model. "It's kind of crazy how much data there is sitting behind these walled gardens," says AlQuraishi.
Drug companies won't be sharing actual protein structures with each other -- or with AlQuraishi -- to develop the new model. Instead, the effort will use a platform developed by Apheris, a Berlin-based start-up company, that will allow OpenFold 3 to be retrained using proprietary data and without the structures ever leaving a company's digital walls. Karanicolas says it will not be possible to reverse engineer the model to identify the secret structures it was trained on.
Whether the extra data will boost AlphaFold's ability to model how proteins and drugs interact is unclear, says AlQuraishi. "That's going to be the key question -- what will the gains look like?" His team will evaluate the model, for example by comparing its predictions with experimental results, and make a detailed analysis public.
"I do think the experiment, negative or positive, is incredibly valuable," he says. Some scientists and funding agencies are looking to create structural databases like those of the pharma companies with which to feed AI models, says AlQuraishi, and it will be worth knowing whether having more data is actually useful.
Secret pharma-company data on their own probably won't help AlphaFold to improve its typically excellent accuracy with proteins, says Stephanie Wankowicz, a computational structural biologist at Vanderbilt University in Nashville, Tennessee. But the chemical diversity represented in company troves is likely to "drastically improve" predictions of drug interactions, she adds.
Brian Shoichet, a pharmaceutical chemist at the University of California, San Francisco, isn't sure that drug companies have enough data for AlphaFold to make substantial gains. "There's only so much novelty they're going to be able to squeeze out of that lemon," he says.
But even a small improvement could be valuable, adds Shoichet, such as the ability to more accurately predict whether or not a drug will bind to a particular protein, which could indicate whether or not a drug will work. His own team conducts 'virtual docking' campaigns in which software -- conventionally programs based on physical principles -- predicts which of billions of chemicals can bind to a protein. The predictions are then tested in laboratory experiments. "If 20% of predictions work, we're happy. If you could raise to 50%, that would be a big change," Shoichet says.
Access to the model will be restricted to consortium members at first, and Karanicolas hopes that more drug companies will sign up. He says the consortium first wants to see how its model performs before considering expanding access to academic scientists.
Wankowicz would also like to see companies make more of their structural data public in the first place. Just 6% of the PDB's 233,000 structures were submitted by drug companies, says Burley.
Shoichet agrees that there's a strong case for drug companies to share more structures, but he isn't holding his breath. "I've been part of these conversations for 30 years and it's never happened. I don't even bring it up any more."
Burley is more optimistic that companies will see the benefits of greater openness, such as better tools for drug discovery. "In the post-AlphaFold-2 and AlphaFold-3 era, companies will be much more inclined to make the leap of faith."
