AlphaFold Meets Flow Matching for Generating Protein Ensembles

The biological functions of proteins often depend on dynamic structural ensembles. In this work, we develop a flow-based generative modeling approach for learning and sampling the conformational landscapes of proteins. We repurpose highly accurate single-state predictors such as AlphaFold and ESMFold and fine-tune them under a custom flow matching framework to obtain sequence-conditoned generative models of protein structure called AlphaFlow and ESMFlow. When trained and evaluated on the PDB, our method provides a superior combination of precision and diversity compared to AlphaFold with MSA subsampling. When further trained on ensembles from all-atom MD, our method accurately captures conformational flexibility, positional distributions, and higher-order ensemble observables for unseen proteins. Moreover, our method can diversify a static PDB structure with faster wall-clock convergence to certain equilibrium properties than replicate MD trajectories, demonstrating its potential as a proxy for expensive physics-based simulations. Code is available here: https://github.com/bjing2016/alphaflow

Contributors: Bowen Jing, Bonnie Berger Learn more

Discovery of a structural class of antibiotics with explainable deep learning

The discovery of novel structural classes of antibiotics is urgently needed to address the ongoing antibiotic resistance crisis. Deep learning approaches have aided in exploring chemical spaces; these typically use black box models and do not provide chemical insights. Here we reasoned that the chemical substructures associated with antibiotic activity learned by neural network models can be identified and used to predict structural classes of antibiotics. We tested this hypothesis by developing an explainable, substructure-based approach for the efficient, deep learning-guided exploration of chemical spaces. We determined the antibiotic activities and human cell cytotoxicity profiles of 39,312 compounds and applied ensembles of graph neural networks to predict antibiotic activity and cytotoxicity for 12,076,365 compounds. Using explainable graph algorithms, we identified substructure-based rationales for compounds with high predicted antibiotic activity and low predicted cytotoxicity. We empirically tested 283 compounds and found that compounds exhibiting antibiotic activity against Staphylococcus aureus were enriched in putative structural classes arising from rationales. Of these structural classes of compounds, one is selective against methicillin-resistant S. aureus (MRSA) and vancomycin-resistant enterococci, evades substantial resistance, and reduces bacterial titres in mouse models of MRSA skin and systemic thigh infection. Our approach enables the deep learning-guided discovery of structural classes of antibiotics and demonstrates that machine learning models in drug discovery can be explainable, providing insights into the chemical substructures that underlie selective antibiotic activity.

Contributors: Felix Wong, Erica J. Zheng, Jacqueline A. Valeri, Nina M. Donghia, Melis N. Anahtar, Satotaka Omori, Alicia Li, Andres Cubillos-Ruiz, Aarti Krishnan, Wengong Jin, Abigail L. Manson, Jens Friedrichs, Ralf Helbig, Behnoush Hajian, Dawid K. Fiejtek, Florence F. Wagner, Holly H. Soutter, Ashlee M. Earl, Jonathan M. Stokes, Lars D. Renner Learn more

Particle Guidance: Non-I.I.D. diverse sampling with diffusion models

In light of the widespread success of generative models, a significant amount of research has gone into speeding up their sampling time. However, generative models are often sampled multiple times to obtain a diverse set incurring a cost that is orthogonal to sampling time. We tackle the question of how to improve diversity and sample efficiency by moving beyond the common assumption of independent samples. We propose particle guidance, an extension of diffusion-based generative sampling where a joint-particle time-evolving potential enforces diversity. We analyze theoretically the joint distribution that particle guidance generates, how to learn a potential that achieves optimal diversity, and the connections with methods in other disciplines. Empirically, we test the framework both in the setting of conditional image generation, where we are able to increase diversity without affecting quality, and molecular conformer generation, where we reduce the state-of-the-art median error by 13% on average.

Contributors: Gabriele Corso, Yilun Xu, Valentin de Bortoli Learn more

Improving influenza A vaccine strain selection through deep evolutionary models

Even though vaccines have the potential to significantly alleviate the disease burden of epidemics such as the seasonal flu, current influenza vaccines offer limited protection. According to the Centers for Disease Control and Prevention (CDC), vaccine effectiveness has hovered below 50% for the past decade. Identifying the optimal strains to use in a vaccine is central to increasing its efficacy. However, this task is challenging due to the antigenic drift that occurs during the flu season. In this paper, we propose to select vaccines based on their escapability score, a metric that quantifies the antigenic similarity of vaccine strains with future dominant strains and demonstrates a strong correlation with clinical vaccine effectiveness. We introduce a deep learning-based approach that predicts both the antigenic properties of vaccine strains and the dominance of future circulating viruses, enabling efficient virtual screening of a large number of vaccine compositions. We utilized historical antigenic analysis data from the World Health Organization (WHO) to demonstrate that our model selects vaccine strains that reliably improve over the recommended ones.

Contributors: Wenxian Shi, Rachel Menghua Wu Learn more

Annotating metabolite mass spectra with domain-inspired chemical formula transformers

Metabolomics studies have identified small molecules that mediate cell signaling, competition and disease pathology, in part due to large-scale community efforts to measure tandem mass spectra for thousands of metabolite standards. Nevertheless, the majority of spectra observed in clinical samples cannot be unambiguously matched to known structures. Deep learning approaches to small-molecule structure elucidation have surprisingly failed to rival classical statistical methods, which we hypothesize is due to the lack of in-domain knowledge incorporated into current neural network architectures. Here we introduce a neural network-driven workflow for untargeted metabolomics, Metabolite Inference with Spectrum Transformers (MIST), to annotate tandem mass spectra peaks with chemical structures. Unlike existing approaches, MIST incorporates domain insights into its architecture by encoding peaks with their chemical formula representations, implicitly featurizing pairwise neutral losses and training the network to additionally predict substructure fragments. MIST performs favorably compared with both standard neural architectures and the state-of-the-art kernel method on the task of fingerprint prediction for over 70% of metabolite standards and retrieves 66% of metabolites with equal or improved accuracy, with 29% strictly better. We further demonstrate the utility of MIST by suggesting potential dipeptide and alkaloid structures for differentially abundant spectra found in an inflammatory bowel disease patient cohort.

Contributors: Samuel Goldman, Jeremy Wohlwend, Martin Stražar, Guy Haroush, Ramnik J. Xavier Learn more

Artificial intelligence for science in quantum, atomistic, and continuum systems

Advances in artificial intelligence (AI) are fueling a new paradigm of discoveries in natural sciences. Today, AI has started to advance natural sciences by improving, accelerating, and enabling our understanding of natural phenomena at a wide range of spatial and temporal scales, giving rise to a new area of research known as AI for science (AI4Science). Being an emerging research paradigm, AI4Science is unique in that it is an enormous and highly interdisciplinary area. Thus, a unified and technical treatment of this field is needed yet challenging. This paper aims to provide a technically thorough account of a subarea of AI4Science; namely, AI for quantum, atomistic, and continuum systems. These areas aim at understanding the physical world from the subatomic (wavefunctions and electron density), atomic (molecules, proteins, materials, and interactions), to macro (fluids, climate, and subsurface) scales and form an important subarea of AI4Science. A unique advantage of focusing on these areas is that they largely share a common set of challenges, thereby allowing a unified and foundational treatment. A key common challenge is how to capture physics first principles, especially symmetries, in natural systems by deep learning methods. We provide an in-depth yet intuitive account of techniques to achieve equivariance to symmetry transformations. We also discuss other common technical challenges, including explainability, out-of-distribution generalization, knowledge transfer with foundation and large language models, and uncertainty quantification. To facilitate learning and education, we provide categorized lists of resources that we found to be useful. We strive to be thorough and unified and hope this initial effort may trigger more community interests and efforts to further advance AI4Science. Learn more

De novo design of protein structure and function with RFdiffusion

Learn more

S(E3) diffusion model with application to protein backbone generation

The design of novel protein structures remains a challenge in protein engineering for applications across biomedicine and chemistry. In this line of work, a diffusion model over rigid bodies in 3D(referred to as frames) has shown success in generating novel, functional protein backbones that have not been observed in nature. However, there exists no principled methodological framework for diffusion on SE(3), the space of orientation preserving rigid motions in R3, that operates on frames and confers the group in variance. We address these shortcomings by developing theoretical foundations of SE(3) invariant diffusion models on multiple frames followed by a novel framework, FrameDiff, for learning the SE(3) equivariant score over multiple frames. We apply Frame Diffon monomer back bone generation and find it can generate designable monomers up to 500 amino acids without relying on a pretrained protein structure prediction network that has been integral to previous methods. We find our samples are capable of generalizing beyond any known protein structure. Code: https://github.com/jasonkyuyim/se3_diffusion

Contributors: Jason Yim, Brian L. Trippe, Valentin De Bortoli, Emile Mathieu, Arnaud Doucet Learn more

Deep learning-guided discovery of an antibiotic targeting Acinetobacter baumannii

Acinetobacter baumannii is a nosocomial Gram-negative pathogen that often displays multidrug resistance. Discovering new antibiotics against A. baumannii has proven challenging through conventional screening approaches. Fortunately, machine learning methods allow for the rapid exploration of chemical space, increasing the probability of discovering new antibacterial molecules. Here we screened ~7,500 molecules for those that inhibited the growth of A. baumannii in vitro. We trained a neural network with this growth inhibition dataset and performed in silico predictions for structurally new molecules with activity against A. baumannii. Through this approach, we discovered abaucin, an antibacterial compound with narrow-spectrum activity against A. baumannii. Further investigations revealed that abaucin perturbs lipoprotein trafficking through a mechanism involving LolE. Moreover, abaucin could control an A. baumannii infection in a mouse wound model. This work highlights the utility of machine learning in antibiotic discovery and describes a promising lead with targeted activity against a challenging Gram-negative pathogen.

Contributors: Gary Liu, Denise B. Catacutan, Khushi Rathod, Kyle Swanson, Wengong Jin, Jody C. Mohammed, Anush Chiappino-Pepe, Saad A. Syed, Meghan Fragis, Kenneth Rachwalski, Jakob Magolan, Michael G. Surette, Brian K. Coombes & Jonathan M. Stokes Learn more

DiffDock: Diffusion Steps, Twists, and Turns for Molecular Docking

Predicting the binding structure of a small molecule ligand to a protein -- a task known as molecular docking -- is critical to drug design. Recent deep learning methods that treat docking as a regression problem have decreased runtime compared to traditional search-based methods but have yet to offer substantial improvements in accuracy. We instead frame molecular docking as a generative modeling problem and develop DiffDock, a diffusion generative model over the non-Euclidean manifold of ligand poses. To do so, we map this manifold to the product space of the degrees of freedom (translational, rotational, and torsional) involved in docking and develop an efficient diffusion process on this space. Empirically, DiffDock obtains a 38% top-1 success rate (RMSD<2A) on PDBBind, significantly outperforming the previous state-of-the-art of traditional docking (23%) and deep learning (20%) methods. Moreover, while previous methods are not able to dock on computationally folded structures (maximum accuracy 10.4%), DiffDock maintains significantly higher precision (21.7%). Finally, DiffDock has fast inference times and provides confidence estimates with high selective accuracy. Learn more
Load More