Scalable nonparametric clustering with unified marker gene selection for single-cell RNA-seq data.

Clustering is commonly used in single-cell RNA-sequencing (scRNA-seq) pipelines to characterize cellular heterogeneity. However, current methods face two main limitations. First, they require user-specified heuristics which add time and complexity to bioinformatic workflows; second, they rely on post-selective differential expression analyses to identify marker genes driving cluster differences, which has been shown to be subject to inflated false discovery rates. We address these challenges by introducing nonparametric clustering of single-cell populations (NCLUSION): an infinite mixture model that leverages Bayesian sparse priors to identify marker genes while simultaneously performing clustering on single-cell expression data. NCLUSION uses a scalable variational inference algorithm to perform these analyses on datasets with up to millions of cells. By analyzing publicly available scRNA-seq studies, we demonstrate that NCLUSION (i) matches the performance of other state-of-the-art clustering techniques with significantly reduced runtime and (ii) provides statistically robust and biologically relevant transcriptomic signatures for each of the clusters it identifies. Overall, NCLUSION represents a reliable hypothesis-generating tool for understanding patterns of expression variation present in single-cell populations.

Protein structure generation via folding diffusion.

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.

Priming agents transiently reduce the clearance of cell-free DNA to improve liquid biopsies.

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.

Deep self-supervised learning for biosynthetic gene cluster detection and product classification.

Natural products are chemical compounds that form the basis of many therapeutics used in the pharmaceutical industry. In microbes, natural products are synthesized by groups of colocalized genes called biosynthetic gene clusters (BGCs). With advances in high-throughput sequencing, there has been an increase of complete microbial isolate genomes and metagenomes, from which a vast number of BGCs are undiscovered. Here, we introduce a self-supervised learning approach designed to identify and characterize BGCs from such data. To do this, we represent BGCs as chains of functional protein domains and train a masked language model on these domains. We assess the ability of our approach to detect BGCs and characterize BGC properties in bacterial genomes. We also demonstrate that our model can learn meaningful representations of BGCs and their constituent domains, detect BGCs in microbial genomes, and predict BGC product classes. These results highlight self-supervised neural networks as a promising framework for improving BGC prediction and classification.

A nanoparticle priming agent reduces cellular uptake of cell-free DNA and enhances the sensitivity of liquid biopsies.

Liquid biopsies are enabling minimally invasive monitoring and molecular profiling of diseases across medicine, but their sensitivity remains limited by the scarcity of cell-free DNA (cfDNA) in blood. Here, we report an intravenous priming agent that is given prior to a blood draw to increase the abundance of cfDNA in circulation. Our priming agent consists of nanoparticles that act on the cells responsible for cfDNA clearance to slow down cfDNA uptake. In tumor-bearing mice, this agent increases the recovery of circulating tumor DNA (ctDNA) by up to 60-fold and improves the sensitivity of a ctDNA diagnostic assay from 0% to 75% at low tumor burden. We envision that this priming approach will significantly improve the performance of liquid biopsies across a wide range of clinical applications in oncology and beyond.

Low protease activity in B cell follicles promotes retention of intact antigens after immunization.

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.

Multiscale profiling of protease activity in cancer.

Diverse processes in cancer are mediated by enzymes, which most proximally exert their function through their activity. High-fidelity methods to profile enzyme activity are therefore critical to understanding and targeting the pathological roles of enzymes in cancer. Here, we present an integrated set of methods for measuring specific protease activities across scales, and deploy these methods to study treatment response in an autochthonous model of Alk-mutant lung cancer. We leverage multiplexed nanosensors and machine learning to analyze in vivo protease activity dynamics in lung cancer, identifying significant dysregulation that includes enhanced cleavage of a peptide, S1, which rapidly returns to healthy levels with targeted therapy. Through direct on-tissue localization of protease activity, we pinpoint S1 cleavage to the tumor vasculature. To link protease activity to cellular function, we design a high-throughput method to isolate and characterize proteolytically active cells, uncovering a pro-angiogenic phenotype in S1-cleaving cells. These methods provide a framework for functional, multiscale characterization of protease dysregulation in cancer.