Joseph M. Jacobson

Deep generative models for protein structure and sequence are increasingly used to design proteins with therapeutic and industrial applications, but the clinical success of designed therapeutics ultimately depends on their compatibility with the human immune system. Immune response is triggered by a cascade of molecular events, including proteasomal cleavage, peptide elution, and binding to the highly polymorphic Major Histocompatibility Complex (MHC) Class I molecules, yet prior approaches have generally modeled these processes in isolation or restricted attention to a limited set of alleles. In this work, we develop predictors for cleavage, elution, and binding affinity in the MHC Class I pathway, incorporating evidential deep learning to provide unified uncertainty estimates. We first perform supervised fine-tuning of a protein language model on human proteins, and then align the model through group relative policy optimization (GRPO) to reduce MHC Class I epitopes under a curriculum learning framework, in which the curriculum progressively increases the number of masked predicted epitopes and the number of alleles considered during training. This strategy enables the generation of protein candidates that are optimized for immune compatibility across diverse MHC Class I alleles while accounting for predictive uncertainty in modeling the immune response.

Unraveling the dynamical motions of biomolecules is essential for bridging their structure and function, yet it remains a major computational challenge. Molecular dynamics (MD) simulation provides a detailed depiction of biomolecular motion, but its high-resolution temporal evolution comes at significant computational cost, limiting its applicability to timescales of biological relevance. Deep learning approaches have emerged as promising solutions to overcome these computational limitations by learning to predict long-timescale dynamics. However, generalizable kinetics models for proteins remain largely unexplored, and the fundamental limits of achievable acceleration while preserving dynamical accuracy are poorly understood. In this work, we fill this gap with DeepJump, an Euclidean-Equivariant Flow Matching-based model for predicting protein conformational dynamics across multiple temporal scales. We train DeepJump on trajectories of the diverse proteins of mdCATH, systematically studying our model's performance in generalizing to long-term dynamics of fast-folding proteins and characterizing the trade-off between computational acceleration and prediction accuracy. We demonstrate the application of DeepJump to ab initio folding, showcasing prediction of folding pathways and native states. Our results demonstrate that DeepJump achieves significant $\approx$1000$\times$ computational acceleration while effectively recovering long-timescale dynamics, providing a stepping stone for enabling routine simulation of proteins.

Ribonucleic acid (RNA) plays fundamental roles in biological systems, from carrying genetic information to performing enzymatic function. Understanding and designing RNA can enable novel therapeutic application and biotechnological innovation. To enhance RNA design, in this paper we introduce RiboGen, the first deep learning model to simultaneously generate RNA sequence and all-atom 3D structure. RiboGen leverages the standard Flow Matching with Discrete Flow Matching in a multimodal data representation. RiboGen is based on Euclidean Equivariant neural networks for efficiently processing and learning three-dimensional geometry. Our experiments show that RiboGen can efficiently generate chemically plausible and self-consistent RNA samples, suggesting that co-generation of sequence and structure is a competitive approach for modeling RNA.

Mapping the conformational dynamics of proteins is crucial for elucidating their functional mechanisms. While Molecular Dynamics (MD) simulation enables detailed time evolution of protein motion, its computational toll hinders its use in practice. To address this challenge, multiple deep learning models for reproducing and accelerating MD have been proposed drawing on transport-based generative methods. However, existing work focuses on generation through transport of samples from prior distributions, that can often be distant from the data manifold. The recently proposed framework of stochastic interpolants, instead, enables transport between arbitrary distribution endpoints. Building upon this work, we introduce EquiJump, a transferable SO(3)-equivariant model that bridges all-atom protein dynamics simulation time steps directly. Our approach unifies diverse sampling methods and is benchmarked against existing models on trajectory data of fast folding proteins. EquiJump achieves state-of-the-art results on dynamics simulation with a transferable model on all of the fast folding proteins.

Electron density prediction stands as a cornerstone challenge in molecular systems, pivotal for various applications such as understanding molecular interactions and conducting precise quantum mechanical calculations. However, the scaling of density functional theory (DFT) calculations is prohibitively expensive. Machine learning methods provide an alternative, offering efficiency and accuracy. We introduce a novel SE(3)-equivariant architecture, drawing inspiration from Slater-Type Orbitals (STO), to learn representations of molecular electronic structures. Our approach offers an alternative functional form for learned orbital-like molecular representation. We showcase the effectiveness of our method by achieving SOTA prediction accuracy of molecular electron density with 30-70\% improvement over other work on Molecular Dynamics data.

CRISPR enzymes require a defined protospacer adjacent motif (PAM) flanking a guide RNA-programmed target site, limiting their sequence accessibility for robust genome editing applications. In this study, we recombine the PAM-interacting domain of SpRY, a broad-targeting Cas9 possessing an NRN > NYN (R = A or G, Y = C or T) PAM preference, with the N-terminus of Sc + +, a Cas9 with simultaneously broad, efficient, and accurate NNG editing capabilities, to generate a chimeric enzyme with highly flexible PAM preference: SpRYc. We demonstrate that SpRYc leverages properties of both enzymes to specifically edit diverse PAMs and disease-related loci for potential therapeutic applications. In total, the approaches to generate SpRYc, coupled with its robust flexibility, highlight the power of integrative protein design for Cas9 engineering and motivate downstream editing applications that require precise genomic positioning.

Three-dimensional native states of natural proteins display recurring and hierarchical patterns. Yet, traditional graph-based modeling of protein structures is often limited to operate within a single fine-grained resolution, and lacks hourglass neural architectures to learn those high-level building blocks. We narrow this gap by introducing Ophiuchus, an SO(3)-equivariant coarse-graining model that efficiently operates on all-atom protein structures. Our model departs from current approaches that employ graph modeling, instead focusing on local convolutional coarsening to model sequence-motif interactions with efficient time complexity in protein length. We measure the reconstruction capabilities of Ophiuchus across different compression rates, and compare it to existing models. We examine the learned latent space and demonstrate its utility through conformational interpolation. Finally, we leverage denoising diffusion probabilistic models (DDPM) in the latent space to efficiently sample protein structures. Our experiments demonstrate Ophiuchus to be a scalable basis for efficient protein modeling and generation.

CRISPR enzymes require a defined protospacer adjacent motif (PAM) flanking a guide RNA-programmed target site, limiting their sequence accessibility for robust genome editing applications. In this study, we recombine the PAM-interacting domain of SpRY, a broad-targeting Cas9 possessing an NRN > NYN PAM preference, with the N-terminus of Sc++, a Cas9 with simultaneously broad, efficient, and accurate NNG editing capabilities, to generate a chimeric enzyme with highly flexible PAM preference: SpRYc. We demonstrate that SpRYc leverages properties of both enzymes to specifically edit diverse NNN PAMs and disease-related loci for potential therapeutic applications. In total, the unique approaches to generate SpRYc, coupled with its robust flexibility, highlight the power of integrative protein design for Cas9 engineering and motivate downstream editing applications that require precise genomic positioning.

CRISPR enzymes require a defined protospacer adjacent motif (PAM) flanking a guide RNA-programmed target site, limiting their sequence accessibility for robust genome editing applications. In this study, we recombine the PAM-interacting domain of SpRY, a broad-targeting Cas9 possessing an NRN > NYN PAM preference, with the N-terminus of Sc++, a Cas9 with simultaneously broad, efficient, and accurate NNG editing capabilities, to generate a chimeric enzyme with highly flexible PAM preference: SpRYc. We demonstrate that SpRYc leverages properties of both enzymes to specifically edit diverse NNN PAMs and disease-related loci for potential therapeutic applications. In total, the unique approaches to generate SpRYc, coupled with its robust flexibility, highlight the power of integrative protein design for Cas9 engineering and motivate downstream editing applications that require precise genomic positioning.

CRISPR enzymes require a defined protospacer adjacent motif (PAM) flanking a guide RNA-programmed target site, limiting their sequence accessibility for robust genome editing applications. In this study, we recombine the PAM-interacting domain of SpRY, a broad-targeting Cas9 possessing an NRN > NYN PAM preference, with the N-terminus of Sc++, a Cas9 with simultaneously broad, efficient, and accurate NNG editing capabilities, to generate a chimeric enzyme with highly flexible PAM preference: SpRYc. We demonstrate that SpRYc leverages properties of both enzymes to specifically edit diverse NNN PAMs and disease-related loci for potential therapeutic applications. In total, the unique approaches to generate SpRYc, coupled with its robust flexibility, highlight the power of integrative protein design for Cas9 engineering and motivate downstream editing applications that require precise genomic positioning.

CRISPR enzymes require a defined protospacer adjacent motif (PAM) flanking a guide RNA-programmed target site, limiting their sequence accessibility for robust genome editing applications. In this study, we recombine the PAM-interacting domain of SpRY, a broad-targeting Cas9 possessing an NRN > NYN PAM preference, with the N-terminus of Sc++, a Cas9 with simultaneously broad, efficient, and accurate NNG editing capabilities, to generate a chimeric enzyme with highly flexible PAM preference: SpRYc. We demonstrate that SpRYc leverages properties of both enzymes to specifically edit diverse NNN PAMs and disease-related loci for potential therapeutic applications. In total, the unique approaches to generate SpRYc, coupled with its robust flexibility, highlight the power of integrative protein design for Cas9 engineering and motivate downstream editing applications that require precise genomic positioning.

This paper introduces a study demonstrating the growth of plants robotically, where robots live on the stem of a plant and morph their growth without external artificial scaffolding. The encoded software in the robot maintains interval locomotion over twelve weeks, while triggering on board lighting climbs to direct the growth. Outputs of twelve weeks of growth experiments in total are presented with the final shapes of plants. We also discuss the morphogenetic plasticity of plants and their growth responses to the environment, and other mechanisms of shaping that could be used in the future. Such work may pave a way towards new forms of arbortecture in the future.