Ava P. Amini

Liquid biopsies enable early detection and monitoring of diseases such as cancer, but their sensitivity remains limited by the scarcity of analytes such as cell-free DNA (cfDNA) in blood. Improvements to sensitivity have primarily relied on enhancing sequencing technology ex vivo. We sought to transiently augment the level of circulating tumor DNA (ctDNA) in a blood draw by attenuating its clearance in vivo. We report two intravenous priming agents given 1 to 2 hours before a blood draw to recover more ctDNA. Our priming agents consist of nanoparticles that act on the cells responsible for cfDNA clearance and DNA-binding antibodies that protect cfDNA. In tumor-bearing mice, they greatly increase the recovery of ctDNA and improve the sensitivity for detecting small tumors.

Abstract Deep generative models are increasingly powerful tools for the in silico design of novel proteins. Recently, a family of generative models called diffusion models has demonstrated the ability to generate biologically plausible proteins that are dissimilar to any actual proteins seen in nature, enabling unprecedented capability and control in de novo protein design. However, current state-of-the-art diffusion models generate protein structures, which limits the scope of their training data and restricts generations to a small and biased subset of protein design space. Here, we introduce a general-purpose diffusion framework, EvoDiff, that combines evolutionary-scale data with the distinct conditioning capabilities of diffusion models for controllable protein generation in sequence space. EvoDiff generates high-fidelity, diverse, and structurally-plausible proteins that cover natural sequence and functional space. We show experimentally that EvoDiff generations express, fold, and exhibit expected secondary structure elements. Critically, EvoDiff can generate proteins inaccessible to structure-based models, such as those with disordered regions, while maintaining the ability to design scaffolds for functional structural motifs. We validate the universality of our sequence-based formulation by experimentally characterizing intrinsically-disordered mitochondrial targeting signals, metal-binding proteins, and protein binders designed using EvoDiff. We envision that EvoDiff will expand capabilities in protein engineering beyond the structure-function paradigm toward programmable, sequence-first design.

The ability to computationally generate novel yet physically foldable protein structures could lead to new biological discoveries and new treatments targeting yet incurable diseases. Despite recent advances in protein structure prediction, directly generating diverse, novel protein structures from neural networks remains difficult. In this work, we present a diffusion-based generative model that generates protein backbone structures via a procedure inspired by the natural folding process. We describe a protein backbone structure as a sequence of angles capturing the relative orientation of the constituent backbone atoms, and generate structures by denoising from a random, unfolded state towards a stable folded structure. Not only does this mirror how proteins natively twist into energetically favorable conformations, the inherent shift and rotational invariance of this representation crucially alleviates the need for more complex equivariant networks. We train a denoising diffusion probabilistic model with a simple transformer backbone and demonstrate that our resulting model unconditionally generates highly realistic protein structures with complexity and structural patterns akin to those of naturally-occurring proteins. As a useful resource, we release an open-source codebase and trained models for protein structure diffusion.

The structural integrity of vaccine antigens is critical to the generation of protective antibody responses, but the impact of protease activity on vaccination in vivo is poorly understood. We characterized protease activity in lymph nodes and found that antigens were rapidly degraded in the subcapsular sinus, paracortex, and interfollicular regions, whereas low protease activity and antigen degradation rates were detected in the vicinity of follicular dendritic cells (FDCs). Correlated with these findings, immunization regimens designed to target antigen to FDCs led to germinal centers dominantly targeting intact antigen, whereas traditional immunizations led to much weaker responses that equally targeted the intact immunogen and antigen breakdown products. Thus, spatially compartmentalized antigen proteolysis affects humoral immunity and can be exploited.

Abstract The advent and success of foundation models such as GPT has sparked growing interest in their application to single-cell biology. Models like Geneformer and scGPT have emerged with the promise of serving as versatile tools for this specialized field. However, the efficacy of these models, particularly in zero-shot settings where models are not fine-tuned but used without any further training, remains an open question, especially as practical constraints require useful models to function in settings that preclude fine-tuning (e.g., discovery settings where labels are not fully known). This paper presents a rigorous evaluation of the zero-shot performance of these proposed single-cell foundation models. We assess their utility in tasks such as cell type clustering and batch effect correction, and evaluate the generality of their pretraining objectives. Our results indicate that both Geneformer and scGPT exhibit limited reliability in zero-shot settings and often underperform compared to simpler methods. These findings serve as a cautionary note for the deployment of proposed single-cell foundation models and highlight the need for more focused research to realize their potential. 2