In 2017, fresh off a PhD on theoretical chemistry, John Jumper heard rumors that Google DeepMind had moved on from building AI that played games with superhuman skill and was starting up a secret project to predict the structures of proteins. He applied for a job. Just three years later, Jumper celebrated a stunning win that few had seen coming. With CEO Demis Hassabis, he had co-led the development of an AI system called AlphaFold 2 that was able to predict the structures of proteins to within the width of an atom, matching the accuracy of painstaking techniques used in the lab, and doing it many times faster--returning results in hours instead of months. AlphaFold 2 had cracked a 50-year-old grand challenge in biology.

Recent advances in protein structure prediction, such as AlphaFold, have demonstrated the power of deep neural architectures like the Evoformer for capturing complex spatial and evolutionary constraints on protein conformation. However, the depth of the Evoformer, comprising 48 stacked blocks, introduces high computational costs and rigid layerwise discretization. Inspired by Neural Ordinary Differential Equations (Neural ODEs), we propose a continuous-depth formulation of the Evoformer, replacing its 48 discrete blocks with a Neural ODE parameterization that preserves its core attention-based operations. This continuous-time Evoformer achieves constant memory cost (in depth) via the adjoint method, while allowing a principled trade-off between runtime and accuracy through adaptive ODE solvers. Benchmarking on protein structure prediction tasks, we find that the Neural ODE-based Evoformer produces structurally plausible predictions and reliably captures certain secondary structure elements, such as alpha-helices, though it does not fully replicate the accuracy of the original architecture. However, our model achieves this performance using dramatically fewer resources, just 17.5 hours of training on a single GPU, highlighting the promise of continuous-depth models as a lightweight and interpretable alternative for biomolecular modeling. This work opens new directions for efficient and adaptive protein structure prediction frameworks.

Deep generative models have recently been proposed for sampling protein conformations from the Boltzmann distribution, as an alternative to often prohibitively expensive Molecular Dynamics simulations. However, current state-of-the-art approaches rely on fine-tuning pre-trained folding models and evolutionary sequence information, limiting their applicability and efficiency, and introducing potential biases. In this work, we propose a flow matching model for sampling protein conformations based solely on backbone geometry. We introduce a geometric encoding of the backbone equilibrium structure as input and propose to condition not only the flow but also the prior distribution on the respective equilibrium structure, eliminating the need for evolutionary information. The resulting model is orders of magnitudes faster than current state-of-the-art approaches at comparable accuracy and can be trained from scratch in a few GPU days. In our experiments, we demonstrate that the proposed model achieves competitive performance with reduced inference time, across not only an established benchmark of naturally occurring proteins but also de novo proteins, for which evolutionary information is scarce.

Scientific research faces high costs and inefficiencies with traditional methods, but the rise of deep learning and large language models (LLMs) offers innovative solutions. This survey reviews LLM applications across scientific fields such as biology, medicine, chemistry, and meteorology, underscoring their role in advancing research. However, the continuous expansion of model size has led to significant memory demands, hindering further development and application of LLMs for science. To address this, we review memory-efficient training techniques for LLMs based on the transformer architecture, including distributed training, mixed precision training, and gradient checkpointing. Using AlphaFold 2 as an example, we demonstrate how tailored memory optimization methods can reduce storage needs while preserving prediction accuracy. We also discuss the challenges of memory optimization in practice and potential future directions, hoping to provide valuable insights for researchers and engineers.

A day after recognizing former Google vice president and engineering fellow Geoffrey Hinton for his contributions to the field of physics, the Royal Swedish Academy of Sciences has honored a pair of current Google employees. On Wednesday, DeepMind CEO Demis Hassabis and senior research scientist John Jumper won half of the 2024 Nobel Prize in Chemistry, with the other half going to David Baker, a professor at the University of Washington. Baker, Hassabis and Jumper all advanced our understanding of those essential building blocks of life that are responsible for functions both inside and outside the human body. The Nobel Committee cited Baker's seminal work in computational protein design. Since 2003, Baker and his research team have been using amino acids and computers to design entirely new proteins.

While monomer protein structure prediction tools boast impressive accuracy, the prediction of protein complex structures remains a daunting challenge in the field. This challenge is particularly pronounced in scenarios involving complexes with protein chains from different species, such as antigen-antibody interactions, where accuracy often falls short. Limited by the accuracy of complex prediction, tasks based on precise protein-protein interaction analysis also face obstacles. In this report, we highlight the ongoing advancements of our protein complex structure prediction model, HelixFold-Multimer, underscoring its enhanced performance. HelixFold-Multimer provides precise predictions for diverse protein complex structures, especially in therapeutic protein interactions. Notably, HelixFold-Multimer achieves remarkable success in antigen-antibody and peptide-protein structure prediction, greatly surpassing AlphaFold 3. HelixFold-Multimer is now available for public use on the PaddleHelix platform, offering both a general version and an antigen-antibody version. Researchers can conveniently access and utilize this service for their development needs.

While the previous model, released in 2020, amazed the research community with its ability to predict proteins structures, researchers have been clamoring for the tool to handle more than just proteins. Now, DeepMind says, AlphaFold 3 can predict the structures of DNA, RNA, and molecules like ligands, which are essential to drug discovery. DeepMind says the tool provides a more nuanced and dynamic portrait of molecule interactions than anything previously available. "Biology is a dynamic system," DeepMind CEO Demis Hassabis told reporters on a call. "Properties of biology emerge through the interactions between different molecules in the cell, and you can think about AlphaFold 3 as our first big sort of step toward [modeling] that."

Recent research in machine learning (ML) has led to significant progress in various fields, including scientific applications. However, there are limitations that need to be addressed to ensure the validity of new models, the quality of testing and validation procedures, and the actual applicability of the developed models to real-world problems. These limitations include unfair, subjective, and unbalanced evaluations, not necessarily intentional yet there, the use of datasets that don't properly reflect real-world use cases (for example that are "too easy"), incorrect ways to split datasets into training, testing, and validation subsets, etc. In this article I will discuss all these points, using examples from the domain of biology which is being revolutionized by ML methodologies. Along the way I will also briefly touch on the interpretability of ML models, which is today very limited but very important because it could help clarify many of the aspects discussed in the first part of the article regarding the limitations that need to be addressed.

That means I'm usually sorted into Generation X. But these days, looking back at the past 57 years, I think we should really rename it to Generation AI. It has been my generation having witnessed AI from its infancy to the breakthroughs we've seen in the past few years. And with a bit of luck most of us will witness how AI will be reshaping our societies – for good or bad – in the next 20 years. So let me give a recount of my encounters with AI throughout the decades.

Then in the adjacent field of chemistry, I've presented how both DeepMind and Google are working on accelerating quantum calculations. Even TikTok seems to have plans to assist quantum calculations with ML methods, as it was recently hiring people formed in these areas.