T Cell Epitope Predictions.

Throughout the body, T cells monitor MHC-bound ligands expressed on the surface of essentially all cell types. MHC ligands that trigger a T cell immune response are referred to as T cell epitopes. Identifying such epitopes enables tracking, phenotyping, and stimulating T cells involved in immune responses in infectious disease, allergy, autoimmunity, transplantation, and cancer. The specific T cell epitopes recognized in an individual are determined by genetic factors such as the MHC molecules the individual expresses, in parallel to the individual's environmental exposure history. The complexity and importance of T cell epitope mapping have motivated the development of computational approaches that predict what T cell epitopes are likely to be recognized in a given individual or in a broader population. Such predictions guide experimental epitope mapping studies and enable computational analysis of the immunogenic potential of a given protein sequence region.

Machine learning interpretable models of cell mechanics from protein images.

Cellular form and function emerge from complex mechanochemical systems within the cytoplasm. Currently, no systematic strategy exists to infer large-scale physical properties of a cell from its molecular components. This is an obstacle to understanding processes such as cell adhesion and migration. Here, we develop a data-driven modeling pipeline to learn the mechanical behavior of adherent cells. We first train neural networks to predict cellular forces from images of cytoskeletal proteins. Strikingly, experimental images of a single focal adhesion (FA) protein, such as zyxin, are sufficient to predict forces and can generalize to unseen biological regimes. Using this observation, we develop two approaches-one constrained by physics and the other agnostic-to construct data-driven continuum models of cellular forces. Both reveal how cellular forces are encoded by two distinct length scales. Beyond adherent cell mechanics, our work serves as a case study for integrating neural networks into predictive models for cell biology.

Neurotransmitter classification from electron microscopy images at synaptic sites in Drosophila melanogaster.

High-resolution electron microscopy of nervous systems has enabled the reconstruction of synaptic connectomes. However, we do not know the synaptic sign for each connection (i.e., whether a connection is excitatory or inhibitory), which is implied by the released transmitter. We demonstrate that artificial neural networks can predict transmitter types for presynapses from electron micrographs: a network trained to predict six transmitters (acetylcholine, glutamate, GABA, serotonin, dopamine, octopamine) achieves an accuracy of 87% for individual synapses, 94% for neurons, and 91% for known cell types across a D. melanogaster whole brain. We visualize the ultrastructural features used for prediction, discovering subtle but significant differences between transmitter phenotypes. We also analyze transmitter distributions across the brain and find that neurons that develop together largely express only one fast-acting transmitter (acetylcholine, glutamate, or GABA). We hope that our publicly available predictions act as an accelerant for neuroscientific hypothesis generation for the fly.

The future of rapid and automated single-cell data analysis using reference mapping.

As the number of single-cell datasets continues to grow rapidly, workflows that map new data to well-curated reference atlases offer enormous promise for the biological community. In this perspective, we discuss key computational challenges and opportunities for single-cell reference-mapping algorithms. We discuss how mapping algorithms will enable the integration of diverse datasets across disease states, molecular modalities, genetic perturbations, and diverse species and will eventually replace manual and laborious unsupervised clustering pipelines.

Discovery of antimicrobial peptides in the global microbiome with machine learning.

Novel antibiotics are urgently needed to combat the antibiotic-resistance crisis. We present a machine-learning-based approach to predict antimicrobial peptides (AMPs) within the global microbiome and leverage a vast dataset of 63,410 metagenomes and 87,920 prokaryotic genomes from environmental and host-associated habitats to create the AMPSphere, a comprehensive catalog comprising 863,498 non-redundant peptides, few of which match existing databases. AMPSphere provides insights into the evolutionary origins of peptides, including by duplication or gene truncation of longer sequences, and we observed that AMP production varies by habitat. To validate our predictions, we synthesized and tested 100 AMPs against clinically relevant drug-resistant pathogens and human gut commensals both in vitro and in vivo. A total of 79 peptides were active, with 63 targeting pathogens. These active AMPs exhibited antibacterial activity by disrupting bacterial membranes. In conclusion, our approach identified nearly one million prokaryotic AMP sequences, an open-access resource for antibiotic discovery.

Proteogenomic analysis of chemo-refractory high-grade serous ovarian cancer.

To improve the understanding of chemo-refractory high-grade serous ovarian cancers (HGSOCs), we characterized the proteogenomic landscape of 242 (refractory and sensitive) HGSOCs, representing one discovery and two validation cohorts across two biospecimen types (formalin-fixed paraffin-embedded and frozen). We identified a 64-protein signature that predicts with high specificity a subset of HGSOCs refractory to initial platinum-based therapy and is validated in two independent patient cohorts. We detected significant association between lack of Ch17 loss of heterozygosity (LOH) and chemo-refractoriness. Based on pathway protein expression, we identified 5 clusters of HGSOC, which validated across two independent patient cohorts and patient-derived xenograft (PDX) models. These clusters may represent different mechanisms of refractoriness and implicate putative therapeutic vulnerabilities.

Sounds emitted by plants under stress are airborne and informative.

Stressed plants show altered phenotypes, including changes in color, smell, and shape. Yet, airborne sounds emitted by stressed plants have not been investigated before. Here we show that stressed plants emit airborne sounds that can be recorded from a distance and classified. We recorded ultrasonic sounds emitted by tomato and tobacco plants inside an acoustic chamber, and in a greenhouse, while monitoring the plant's physiological parameters. We developed machine learning models that succeeded in identifying the condition of the plants, including dehydration level and injury, based solely on the emitted sounds. These informative sounds may also be detectable by other organisms. This work opens avenues for understanding plants and their interactions with the environment and may have significant impact on agriculture.

Automatic cell-type harmonization and integration across Human Cell Atlas datasets.

Harmonizing cell types across the single-cell community and assembling them into a common framework is central to building a standardized Human Cell Atlas. Here, we present CellHint, a predictive clustering tree-based tool to resolve cell-type differences in annotation resolution and technical biases across datasets. CellHint accurately quantifies cell-cell transcriptomic similarities and places cell types into a relationship graph that hierarchically defines shared and unique cell subtypes. Application to multiple immune datasets recapitulates expert-curated annotations. CellHint also reveals underexplored relationships between healthy and diseased lung cell states in eight diseases. Furthermore, we present a workflow for fast cross-dataset integration guided by harmonized cell types and cell hierarchy, which uncovers underappreciated cell types in adult human hippocampus. Finally, we apply CellHint to 12 tissues from 38 datasets, providing a deeply curated cross-tissue database with ∼3.7 million cells and various machine learning models for automatic cell annotation across human tissues.

Better, Faster, Cheaper: Recent Advances in Cryo-Electron Microscopy.

Cryo-electron microscopy (cryo-EM) continues its remarkable growth as a method for visualizing biological objects, which has been driven by advances across the entire pipeline. Developments in both single-particle analysis and in situ tomography have enabled more structures to be imaged and determined to better resolutions, at faster speeds, and with more scientists having improved access. This review highlights recent advances at each stageof the cryo-EM pipeline and provides examples of how these techniques have been used to investigate real-world problems, including antibody development against the SARS-CoV-2 spike during the recent COVID-19 pandemic.

Deep mutational learning predicts ACE2 binding and antibody escape to combinatorial mutations in the SARS-CoV-2 receptor-binding domain.

The continual evolution of SARS-CoV-2 and the emergence of variants that show resistance to vaccines and neutralizing antibodies threaten to prolong the COVID-19 pandemic. Selection and emergence of SARS-CoV-2 variants are driven in part by mutations within the viral spike protein and in particular the ACE2 receptor-binding domain (RBD), a primary target site for neutralizing antibodies. Here, we develop deep mutational learning (DML), a machine-learning-guided protein engineering technology, which is used to investigate a massive sequence space of combinatorial mutations, representing billions of RBD variants, by accurately predicting their impact on ACE2 binding and antibody escape. A highly diverse landscape of possible SARS-CoV-2 variants is identified that could emerge from a multitude of evolutionary trajectories. DML may be used for predictive profiling on current and prospective variants, including highly mutated variants such as Omicron, thus guiding the development of therapeutic antibody treatments and vaccines for COVID-19.

Cell maturation: Hallmarks, triggers, and manipulation.

How cells become specialized, or "mature," is important for cell and developmental biology. While maturity is usually deemed a terminal fate, it may be more helpful to consider maturation not as a switch but as a dynamic continuum of adaptive phenotypic states set by genetic and environment programing. The hallmarks of maturity comprise changes in anatomy (form, gene circuitry, and interconnectivity) and physiology (function, rhythms, and proliferation) that confer adaptive behavior. We discuss efforts to harness their chemical (nutrients, oxygen, and growth factors) and physical (mechanical, spatial, and electrical) triggers in vitro and in vivo and how maturation strategies may support disease research and regenerative medicine.

Toward a fine-scale population health monitoring system.

Understanding population health disparities is an essential component of equitable precision health efforts. Epidemiology research often relies on definitions of race and ethnicity, but these population labels may not adequately capture disease burdens and environmental factors impacting specific sub-populations. Here, we propose a framework for repurposing data from electronic health records (EHRs) in concert with genomic data to explore the demographic ties that can impact disease burdens. Using data from a diverse biobank in New York City, we identified 17 communities sharing recent genetic ancestry. We observed 1,177 health outcomes that were statistically associated with a specific group and demonstrated significant differences in the segregation of genetic variants contributing to Mendelian diseases. We also demonstrated that fine-scale population structure can impact the prediction of complex disease risk within groups. This work reinforces the utility of linking genomic data to EHRs and provides a framework toward fine-scale monitoring of population health.

Deciphering cell signaling networks with massively multiplexed biosensor barcoding.

Genetically encoded fluorescent biosensors are powerful tools for monitoring biochemical activities in live cells, but their multiplexing capacity is limited by the available spectral space. We overcome this problem by developing a set of barcoding proteins that can generate over 100 barcodes and are spectrally separable from commonly used biosensors. Mixtures of barcoded cells expressing different biosensors are simultaneously imaged and analyzed by deep learning models to achieve massively multiplexed tracking of signaling events. Importantly, different biosensors in cell mixtures show highly coordinated activities, thus facilitating the delineation of their temporal relationship. Simultaneous tracking of multiple biosensors in the receptor tyrosine kinase signaling network reveals distinct mechanisms of effector adaptation, cell autonomous and non-autonomous effects of KRAS mutations, as well as complex interactions in the network. Biosensor barcoding presents a scalable method to expand multiplexing capabilities for deciphering the complexity of signaling networks and their interactions between cells.

Whole-body integration of gene expression and single-cell morphology.

Animal bodies are composed of cell types with unique expression programs that implement their distinct locations, shapes, structures, and functions. Based on these properties, cell types assemble into specific tissues and organs. To systematically explore the link between cell-type-specific gene expression and morphology, we registered an expression atlas to a whole-body electron microscopy volume of the nereid Platynereis dumerilii. Automated segmentation of cells and nuclei identifies major cell classes and establishes a link between gene activation, chromatin topography, and nuclear size. Clustering of segmented cells according to gene expression reveals spatially coherent tissues. In the brain, genetically defined groups of neurons match ganglionic nuclei with coherent projections. Besides interneurons, we uncover sensory-neurosecretory cells in the nereid mushroom bodies, which thus qualify as sensory organs. They furthermore resemble the vertebrate telencephalon by molecular anatomy. We provide an integrated browser as a Fiji plugin for remote exploration of all available multimodal datasets.

A Chromatin Accessibility Atlas of the Developing Human Telencephalon.

To discover regulatory elements driving the specificity of gene expression in different cell types and regions of the developing human brain, we generated an atlas of open chromatin from nine dissected regions of the mid-gestation human telencephalon, as well as microdissected upper and deep layers of the prefrontal cortex. We identified a subset of open chromatin regions (OCRs), termed predicted regulatory elements (pREs), that are likely to function as developmental brain enhancers. pREs showed temporal, regional, and laminar differences in chromatin accessibility and were correlated with gene expression differences across regions and gestational ages. We identified two functional de novo variants in a pRE for autism risk gene SLC6A1, and using CRISPRa, demonstrated that this pRE regulates SCL6A1. Additionally, mouse transgenic experiments validated enhancer activity for pREs proximal to FEZF2 and BCL11A. Thus, this atlas serves as a resource for decoding neurodevelopmental gene regulation in health and disease.

Determinants of Base Editing Outcomes from Target Library Analysis and Machine Learning.

Although base editors are widely used to install targeted point mutations, the factors that determine base editing outcomes are not well understood. We characterized sequence-activity relationships of 11 cytosine and adenine base editors (CBEs and ABEs) on 38,538 genomically integrated targets in mammalian cells and used the resulting outcomes to train BE-Hive, a machine learning model that accurately predicts base editing genotypic outcomes (R ≈ 0.9) and efficiency (R ≈ 0.7). We corrected 3,388 disease-associated SNVs with ≥90% precision, including 675 alleles with bystander nucleotides that BE-Hive correctly predicted would not be edited. We discovered determinants of previously unpredictable C-to-G, or C-to-A editing and used these discoveries to correct coding sequences of 174 pathogenic transversion SNVs with ≥90% precision. Finally, we used insights from BE-Hive to engineer novel CBE variants that modulate editing outcomes. These discoveries illuminate base editing, enable editing at previously intractable targets, and provide new base editors with improved editing capabilities.

A Deep Learning Approach to Antibiotic Discovery.

Due to the rapid emergence of antibiotic-resistant bacteria, there is a growing need to discover new antibiotics. To address this challenge, we trained a deep neural network capable of predicting molecules with antibacterial activity. We performed predictions on multiple chemical libraries and discovered a molecule from the Drug Repurposing Hub-halicin-that is structurally divergent from conventional antibiotics and displays bactericidal activity against a wide phylogenetic spectrum of pathogens including Mycobacterium tuberculosis and carbapenem-resistant Enterobacteriaceae. Halicin also effectively treated Clostridioides difficile and pan-resistant Acinetobacter baumannii infections in murine models. Additionally, from a discrete set of 23 empirically tested predictions from >107 million molecules curated from the ZINC15 database, our model identified eight antibacterial compounds that are structurally distant from known antibiotics. This work highlights the utility of deep learning approaches to expand our antibiotic arsenal through the discovery of structurally distinct antibacterial molecules.

Directed Evolution of a Selective and Sensitive Serotonin Sensor via Machine Learning.

Serotonin plays a central role in cognition and is the target of most pharmaceuticals for psychiatric disorders. Existing drugs have limited efficacy; creation of improved versions will require better understanding of serotonergic circuitry, which has been hampered by our inability to monitor serotonin release and transport with high spatial and temporal resolution. We developed and applied a binding-pocket redesign strategy, guided by machine learning, to create a high-performance, soluble, fluorescent serotonin sensor (iSeroSnFR), enabling optical detection of millisecond-scale serotonin transients. We demonstrate that iSeroSnFR can be used to detect serotonin release in freely behaving mice during fear conditioning, social interaction, and sleep/wake transitions. We also developed a robust assay of serotonin transporter function and modulation by drugs. We expect that both machine-learning-guided binding-pocket redesign and iSeroSnFR will have broad utility for the development of other sensors and in vitro and in vivo serotonin detection, respectively.

Restoring the Sense of Touch Using a Sensorimotor Demultiplexing Neural Interface.

Paralyzed muscles can be reanimated following spinal cord injury (SCI) using a brain-computer interface (BCI) to enhance motor function alone. Importantly, the sense of touch is a key component of motor function. Here, we demonstrate that a human participant with a clinically complete SCI can use a BCI to simultaneously reanimate both motor function and the sense of touch, leveraging residual touch signaling from his own hand. In the primary motor cortex (M1), residual subperceptual hand touch signals are simultaneously demultiplexed from ongoing efferent motor intention, enabling intracortically controlled closed-loop sensory feedback. Using the closed-loop demultiplexing BCI almost fully restored the ability to detect object touch and significantly improved several sensorimotor functions. Afferent grip-intensity levels are also decoded from M1, enabling grip reanimation regulated by touch signaling. These results demonstrate that subperceptual neural signals can be decoded from the cortex and transformed into conscious perception, significantly augmenting function.

Metabolic Dynamics and Prediction of Gestational Age and Time to Delivery in Pregnant Women.

Metabolism during pregnancy is a dynamic and precisely programmed process, the failure of which can bring devastating consequences to the mother and fetus. To define a high-resolution temporal profile of metabolites during healthy pregnancy, we analyzed the untargeted metabolome of 784 weekly blood samples from 30 pregnant women. Broad changes and a highly choreographed profile were revealed: 4,995 metabolic features (of 9,651 total), 460 annotated compounds (of 687 total), and 34 human metabolic pathways (of 48 total) were significantly changed during pregnancy. Using linear models, we built a metabolic clock with five metabolites that time gestational age in high accordance with ultrasound (R = 0.92). Furthermore, two to three metabolites can identify when labor occurs (time to delivery within two, four, and eight weeks, AUROC ≥ 0.85). Our study represents a weekly characterization of the human pregnancy metabolome, providing a high-resolution landscape for understanding pregnancy with potential clinical utilities.