Showing papers in "Nature Methods in 2021"

nnU-Net: a self-configuring method for deep learning-based biomedical image segmentation

Abstract: Biomedical imaging is a driver of scientific discovery and a core component of medical care and is being stimulated by the field of deep learning. While semantic segmentation algorithms enable image analysis and quantification in many applications, the design of respective specialized solutions is non-trivial and highly dependent on dataset properties and hardware conditions. We developed nnU-Net, a deep learning-based segmentation method that automatically configures itself, including preprocessing, network architecture, training and post-processing for any new task. The key design choices in this process are modeled as a set of fixed parameters, interdependent rules and empirical decisions. Without manual intervention, nnU-Net surpasses most existing approaches, including highly specialized solutions on 23 public datasets used in international biomedical segmentation competitions. We make nnU-Net publicly available as an out-of-the-box tool, rendering state-of-the-art segmentation accessible to a broad audience by requiring neither expert knowledge nor computing resources beyond standard network training.

Cellpose: a generalist algorithm for cellular segmentation

Abstract: Many biological applications require the segmentation of cell bodies, membranes and nuclei from microscopy images. Deep learning has enabled great progress on this problem, but current methods are specialized for images that have large training datasets. Here we introduce a generalist, deep learning-based segmentation method called Cellpose, which can precisely segment cells from a wide range of image types and does not require model retraining or parameter adjustments. Cellpose was trained on a new dataset of highly varied images of cells, containing over 70,000 segmented objects. We also demonstrate a three-dimensional (3D) extension of Cellpose that reuses the two-dimensional (2D) model and does not require 3D-labeled data. To support community contributions to the training data, we developed software for manual labeling and for curation of the automated results. Periodically retraining the model on the community-contributed data will ensure that Cellpose improves constantly.

Haplotype-resolved de novo assembly using phased assembly graphs with hifiasm.

Abstract: Haplotype-resolved de novo assembly is the ultimate solution to the study of sequence variations in a genome. However, existing algorithms either collapse heterozygous alleles into one consensus copy or fail to cleanly separate the haplotypes to produce high-quality phased assemblies. Here we describe hifiasm, a de novo assembler that takes advantage of long high-fidelity sequence reads to faithfully represent the haplotype information in a phased assembly graph. Unlike other graph-based assemblers that only aim to maintain the contiguity of one haplotype, hifiasm strives to preserve the contiguity of all haplotypes. This feature enables the development of a graph trio binning algorithm that greatly advances over standard trio binning. On three human and five nonhuman datasets, including California redwood with a ~30-Gb hexaploid genome, we show that hifiasm frequently delivers better assemblies than existing tools and consistently outperforms others on haplotype-resolved assembly.

Sensitive protein alignments at tree-of-life scale using DIAMOND.

Abstract: We are at the beginning of a genomic revolution in which all known species are planned to be sequenced. Accessing such data for comparative analyses is crucial in this new age of data-driven biology. Here, we introduce an improved version of DIAMOND that greatly exceeds previous search performances and harnesses supercomputing to perform tree-of-life scale protein alignments in hours, while matching the sensitivity of the gold standard BLASTP.

Martini 3 : A general purpose force field for coarse-grained molecular dynamics

Abstract: The coarse-grained Martini force field is widely used in biomolecular simulations. Here we present the refined model, Martini 3 ( http://cgmartini.nl ), with an improved interaction balance, new bead types and expanded ability to include specific interactions representing, for example, hydrogen bonding and electronic polarizability. The updated model allows more accurate predictions of molecular packing and interactions in general, which is exemplified with a vast and diverse set of applications, ranging from oil/water partitioning and miscibility data to complex molecular systems, involving protein-protein and protein-lipid interactions and material science applications as ionic liquids and aedamers.

Single-cell chromatin state analysis with Signac.

Abstract: The recent development of experimental methods for measuring chromatin state at single-cell resolution has created a need for computational tools capable of analyzing these datasets. Here we developed Signac, a comprehensive toolkit for the analysis of single-cell chromatin data. Signac enables an end-to-end analysis of single-cell chromatin data, including peak calling, quantification, quality control, dimension reduction, clustering, integration with single-cell gene expression datasets, DNA motif analysis and interactive visualization. Through its seamless compatibility with the Seurat package, Signac facilitates the analysis of diverse multimodal single-cell chromatin data, including datasets that co-assay DNA accessibility with gene expression, protein abundance and mitochondrial genotype. We demonstrate scaling of the Signac framework to analyze datasets containing over 700,000 cells.

Mass spectrometry-based metabolomics: a guide for annotation, quantification and best reporting practices

Abstract: Mass spectrometry-based metabolomics approaches can enable detection and quantification of many thousands of metabolite features simultaneously. However, compound identification and reliable quantification are greatly complicated owing to the chemical complexity and dynamic range of the metabolome. Simultaneous quantification of many metabolites within complex mixtures can additionally be complicated by ion suppression, fragmentation and the presence of isomers. Here we present guidelines covering sample preparation, replication and randomization, quantification, recovery and recombination, ion suppression and peak misidentification, as a means to enable high-quality reporting of liquid chromatography- and gas chromatography-mass spectrometry-based metabolomics-derived data.

CryoDRGN: reconstruction of heterogeneous cryo-EM structures using neural networks.

Abstract: Cryo-electron microscopy (cryo-EM) single-particle analysis has proven powerful in determining the structures of rigid macromolecules However, many imaged protein complexes exhibit conformational and compositional heterogeneity that poses a major challenge to existing three-dimensional reconstruction methods Here, we present cryoDRGN, an algorithm that leverages the representation power of deep neural networks to directly reconstruct continuous distributions of 3D density maps and map per-particle heterogeneity of single-particle cryo-EM datasets Using cryoDRGN, we uncovered residual heterogeneity in high-resolution datasets of the 80S ribosome and the RAG complex, revealed a new structural state of the assembling 50S ribosome, and visualized large-scale continuous motions of a spliceosome complex CryoDRGN contains interactive tools to visualize a dataset’s distribution of per-particle variability, generate density maps for exploratory analysis, extract particle subsets for use with other tools and generate trajectories to visualize molecular motions CryoDRGN is open-source software freely available at http://cryodrgncsailmitedu CryoDRGN is an unsupervised machine learning algorithm that reconstructs continuous distributions of three-dimensional density maps from heterogeneous single-particle cryo-EM data

Multi-particle cryo-EM refinement with M visualizes ribosome-antibiotic complex at 3.5 Å in cells

Abstract: Cryo-electron microscopy (cryo-EM) enables macromolecular structure determination in vitro and inside cells. In addition to aligning individual particles, accurate registration of sample motion and three-dimensional deformation during exposures are crucial for achieving high-resolution reconstructions. Here we describe M, a software tool that establishes a reference-based, multi-particle refinement framework for cryo-EM data and couples a comprehensive spatial deformation model to in silico correction of electron-optical aberrations. M provides a unified optimization framework for both frame-series and tomographic tilt-series data. We show that tilt-series data can provide the same resolution as frame-series data on a purified protein specimen, indicating that the alignment step no longer limits the resolution obtainable from tomographic data. In combination with Warp and RELION, M resolves to residue level a 70S ribosome bound to an antibiotic inside intact bacterial cells. Our work provides a computational tool that facilitates structural biology in cells.

Spatial omics and multiplexed imaging to explore cancer biology

Abstract: Understanding intratumoral heterogeneity-the molecular variation among cells within a tumor-promises to address outstanding questions in cancer biology and improve the diagnosis and treatment of specific cancer subtypes. Single-cell analyses, especially RNA sequencing and other genomics modalities, have been transformative in revealing novel biomarkers and molecular regulators associated with tumor growth, metastasis and drug resistance. However, these approaches fail to provide a complete picture of tumor biology, as information on cellular location within the tumor microenvironment is lost. New technologies leveraging multiplexed fluorescence, DNA, RNA and isotope labeling enable the detection of tens to thousands of cancer subclones or molecular biomarkers within their native spatial context. The expeditious growth in these techniques, along with methods for multiomics data integration, promises to yield a more comprehensive understanding of cell-to-cell variation within and between individual tumors. Here we provide the current state and future perspectives on the spatial technologies expected to drive the next generation of research and diagnostic and therapeutic strategies for cancer.

SpaGCN: Integrating gene expression, spatial location and histology to identify spatial domains and spatially variable genes by graph convolutional network.

Abstract: Recent advances in spatially resolved transcriptomics (SRT) technologies have enabled comprehensive characterization of gene expression patterns in the context of tissue microenvironment. To elucidate spatial gene expression variation, we present SpaGCN, a graph convolutional network approach that integrates gene expression, spatial location and histology in SRT data analysis. Through graph convolution, SpaGCN aggregates gene expression of each spot from its neighboring spots, which enables the identification of spatial domains with coherent expression and histology. The subsequent domain guided differential expression (DE) analysis then detects genes with enriched expression patterns in the identified domains. Analyzing seven SRT datasets using SpaGCN, we show it can detect genes with much more enriched spatial expression patterns than competing methods. Furthermore, genes detected by SpaGCN are transferrable and can be utilized to study spatial variation of gene expression in other datasets. SpaGCN is computationally fast, platform independent, making it a desirable tool for diverse SRT studies.

Deciphering molecular interactions by proximity labeling.

Abstract: Many biological processes are executed and regulated through the molecular interactions of proteins and nucleic acids. Proximity labeling (PL) is a technology for tagging the endogenous interaction partners of specific protein ‘baits’, via genetic fusion to promiscuous enzymes that catalyze the generation of diffusible reactive species in living cells. Tagged molecules that interact with baits can then be enriched and identified by mass spectrometry or nucleic acid sequencing. Here we review the development of PL technologies and highlight studies that have applied PL to the discovery and analysis of molecular interactions. In particular, we focus on the use of PL for mapping protein–protein, protein–RNA and protein–DNA interactions in living cells and organisms. This Review describes proximity labeling methods that make use of peroxidases (APEX) or biotin ligases (TurboID, BioID), and their applications to studying protein–protein and protein–nucleic acid interactions in living systems.

Deep learning and alignment of spatially resolved single-cell transcriptomes with Tangram.

Abstract: Charting an organs' biological atlas requires us to spatially resolve the entire single-cell transcriptome, and to relate such cellular features to the anatomical scale. Single-cell and single-nucleus RNA-seq (sc/snRNA-seq) can profile cells comprehensively, but lose spatial information. Spatial transcriptomics allows for spatial measurements, but at lower resolution and with limited sensitivity. Targeted in situ technologies solve both issues, but are limited in gene throughput. To overcome these limitations we present Tangram, a method that aligns sc/snRNA-seq data to various forms of spatial data collected from the same region, including MERFISH, STARmap, smFISH, Spatial Transcriptomics (Visium) and histological images. Tangram can map any type of sc/snRNA-seq data, including multimodal data such as those from SHARE-seq, which we used to reveal spatial patterns of chromatin accessibility. We demonstrate Tangram on healthy mouse brain tissue, by reconstructing a genome-wide anatomically integrated spatial map at single-cell resolution of the visual and somatomotor areas.

Joint probabilistic modeling of single-cell multi-omic data with totalVI

Abstract: The paired measurement of RNA and surface proteins in single cells with cellular indexing of transcriptomes and epitopes by sequencing (CITE-seq) is a promising approach to connect transcriptional variation with cell phenotypes and functions. However, combining these paired views into a unified representation of cell state is made challenging by the unique technical characteristics of each measurement. Here we present Total Variational Inference (totalVI; https://scvi-tools.org ), a framework for end-to-end joint analysis of CITE-seq data that probabilistically represents the data as a composite of biological and technical factors, including protein background and batch effects. To evaluate totalVI's performance, we profiled immune cells from murine spleen and lymph nodes with CITE-seq, measuring over 100 surface proteins. We demonstrate that totalVI provides a cohesive solution for common analysis tasks such as dimensionality reduction, the integration of datasets with different measured proteins, estimation of correlations between molecules and differential expression testing.

Low-N protein engineering with data-efficient deep learning

Abstract: Protein engineering has enormous academic and industrial potential. However, it is limited by the lack of experimental assays that are consistent with the design goal and sufficiently high throughput to find rare, enhanced variants. Here we introduce a machine learning-guided paradigm that can use as few as 24 functionally assayed mutant sequences to build an accurate virtual fitness landscape and screen ten million sequences via in silico directed evolution. As demonstrated in two dissimilar proteins, GFP from Aequorea victoria (avGFP) and E. coli strain TEM-1 β-lactamase, top candidates from a single round are diverse and as active as engineered mutants obtained from previous high-throughput efforts. By distilling information from natural protein sequence landscapes, our model learns a latent representation of 'unnaturalness', which helps to guide search away from nonfunctional sequence neighborhoods. Subsequent low-N supervision then identifies improvements to the activity of interest. In sum, our approach enables efficient use of resource-intensive high-fidelity assays without sacrificing throughput, and helps to accelerate engineered proteins into the fermenter, field and clinic.

The emerging landscape of single-molecule protein sequencing technologies

Abstract: Single-cell profiling methods have had a profound impact on the understanding of cellular heterogeneity. While genomes and transcriptomes can be explored at the single-cell level, single-cell profiling of proteomes is not yet established. Here we describe new single-molecule protein sequencing and identification technologies alongside innovations in mass spectrometry that will eventually enable broad sequence coverage in single-cell profiling. These technologies will in turn facilitate biological discovery and open new avenues for ultrasensitive disease diagnostics. This Perspective describes new single-molecule protein sequencing and identification technologies alongside innovations in mass spectrometry that will eventually enable broad sequence coverage in single-cell proteomics.

Critical assessment of protein intrinsic disorder prediction

Abstract: Intrinsically disordered proteins, defying the traditional protein structure-function paradigm, are a challenge to study experimentally. Because a large part of our knowledge rests on computational predictions, it is crucial that their accuracy is high. The Critical Assessment of protein Intrinsic Disorder prediction (CAID) experiment was established as a community-based blind test to determine the state of the art in prediction of intrinsically disordered regions and the subset of residues involved in binding. A total of 43 methods were evaluated on a dataset of 646 proteins from DisProt. The best methods use deep learning techniques and notably outperform physicochemical methods. The top disorder predictor has Fmax = 0.483 on the full dataset and Fmax = 0.792 following filtering out of bona fide structured regions. Disordered binding regions remain hard to predict, with Fmax = 0.231. Interestingly, computing times among methods can vary by up to four orders of magnitude.

High-accuracy long-read amplicon sequences using unique molecular identifiers with Nanopore or PacBio sequencing.

Abstract: High-throughput amplicon sequencing of large genomic regions remains challenging for short-read technologies. Here, we report a high-throughput amplicon sequencing approach combining unique molecular identifiers (UMIs) with Oxford Nanopore Technologies (ONT) or Pacific Biosciences circular consensus sequencing, yielding high-accuracy single-molecule consensus sequences of large genomic regions. We applied our approach to sequence ribosomal RNA operon amplicons (~4,500 bp) and genomic sequences (>10,000 bp) of reference microbial communities in which we observed a chimera rate <0.02%. To reach a mean UMI consensus error rate <0.01%, a UMI read coverage of 15× (ONT R10.3), 25× (ONT R9.4.1) and 3× (Pacific Biosciences circular consensus sequencing) is needed, which provides a mean error rate of 0.0042%, 0.0041% and 0.0007%, respectively. This work presents a sequencing strategy based on unique molecular identifiers that improves long-read consensus sequence accuracy of targeted amplicons as well as shotgun whole-genome fragments.

Screening for functional circular RNAs using the CRISPR-Cas13 system.

Abstract: Circular RNAs (circRNAs) produced from back-spliced exons are widely expressed, but individual circRNA functions remain poorly understood owing to the lack of adequate methods for distinguishing circRNAs from cognate messenger RNAs with overlapping exons. Here, we report that CRISPR–RfxCas13d can effectively discriminate circRNAs from mRNAs by using guide RNAs targeting sequences spanning back-splicing junction (BSJ) sites featured in RNA circles. Using a lentiviral library that targets sequences across BSJ sites of highly expressed human circRNAs, we show that a group of circRNAs are important for cell growth mostly in a cell-type-specific manner and that a common oncogenic circRNA, circFAM120A, promotes cell proliferation by preventing the mRNA for family with sequence similarity 120A (FAM120A) from binding the translation inhibitor IGF2BP2. Further application of RfxCas13d–BSJ-gRNA screening has uncovered circMan1a2, which has regulatory potential in mouse embryo preimplantation development. Together, these results establish CRISPR–RfxCas13d as a useful tool for the discovery and functional study of circRNAs at both individual and large-scale levels. This paper describes a CRISPR–Cas13 system to effectively target circRNAs and screen their functions in vitro and in vivo, which enables the study of relevant circRNA phenotypes in human cell proliferation and in mouse embryogenesis.

Evaluation and development of deep neural networks for image super-resolution in optical microscopy

Abstract: Deep neural networks have enabled astonishing transformations from low-resolution (LR) to super-resolved images However, whether, and under what imaging conditions, such deep-learning models outperform super-resolution (SR) microscopy is poorly explored Here, using multimodality structured illumination microscopy (SIM), we first provide an extensive dataset of LR-SR image pairs and evaluate the deep-learning SR models in terms of structural complexity, signal-to-noise ratio and upscaling factor Second, we devise the deep Fourier channel attention network (DFCAN), which leverages the frequency content difference across distinct features to learn precise hierarchical representations of high-frequency information about diverse biological structures Third, we show that DFCAN's Fourier domain focalization enables robust reconstruction of SIM images under low signal-to-noise ratio conditions We demonstrate that DFCAN achieves comparable image quality to SIM over a tenfold longer duration in multicolor live-cell imaging experiments, which reveal the detailed structures of mitochondrial cristae and nucleoids and the interaction dynamics of organelles and cytoskeleton

Spatially resolved transcriptomics adds a new dimension to genomics.

Abstract: As single-cell omics continue to advance, the field of spatially resolved transcriptomics has emerged with a set of experimental and computational methods to map out the positions of cells and their gene expression profiles in space. Here we summarize current transcriptome-wide and sequencing-based methodologies and their applications in genomics research.

Defining the carrier proteome limit for single-cell proteomics.

Abstract: Single-cell proteomics by mass spectrometry (SCoPE-MS) is a recently introduced method to quantify multiplexed single-cell proteomes. While this technique has generated great excitement, the underlying technologies (isobaric labeling and mass spectrometry (MS)) have technical limitations with the potential to affect data quality and biological interpretation. These limitations are particularly relevant when a carrier proteome, a sample added at 25-500× the amount of a single-cell proteome, is used to enable peptide identifications. Here we perform controlled experiments with increasing carrier proteome amounts and evaluate quantitative accuracy, as it relates to mass analyzer dynamic range, multiplexing level and number of ions sampled. We demonstrate that an increase in carrier proteome level requires a concomitant increase in the number of ions sampled to maintain quantitative accuracy. Lastly, we introduce Single-Cell Proteomics Companion (SCPCompanion), a software tool that enables rapid evaluation of single-cell proteomic data and recommends instrument and data analysis parameters for improved data quality.

Joint profiling of histone modifications and transcriptome in single cells from mouse brain.

Abstract: Genome-wide profiling of histone modifications can reveal not only the location and activity state of regulatory elements, but also the regulatory mechanisms involved in cell-type-specific gene expression during development and disease pathology. Conventional assays to profile histone modifications in bulk tissues lack single-cell resolution. Here we describe an ultra-high-throughput method, Paired-Tag, for joint profiling of histone modifications and transcriptome in single cells to produce cell-type-resolved maps of chromatin state and transcriptome in complex tissues. We used this method to profile five histone modifications jointly with transcriptome in the adult mouse frontal cortex and hippocampus. Integrative analysis of the resulting maps identified distinct groups of genes subject to divergent epigenetic regulatory mechanisms. Our single-cell multiomics approach enables comprehensive analysis of chromatin state and gene regulation in complex tissues and characterization of gene regulatory programs in the constituent cell types.

SpaceM reveals metabolic states of single cells

Abstract: A growing appreciation of the importance of cellular metabolism and revelations concerning the extent of cell-cell heterogeneity demand metabolic characterization of individual cells. We present SpaceM, an open-source method for in situ single-cell metabolomics that detects >100 metabolites from >1,000 individual cells per hour, together with a fluorescence-based readout and retention of morpho-spatial features. We validated SpaceM by predicting the cell types of cocultured human epithelial cells and mouse fibroblasts. We used SpaceM to show that stimulating human hepatocytes with fatty acids leads to the emergence of two coexisting subpopulations outlined by distinct cellular metabolic states. Inducing inflammation with the cytokine interleukin-17A perturbs the balance of these states in a process dependent on NF-κB signaling. The metabolic state markers were reproduced in a murine model of nonalcoholic steatohepatitis. We anticipate SpaceM to be broadly applicable for investigations of diverse cellular models and to democratize single-cell metabolomics.

Programmable RNA editing with compact CRISPR-Cas13 systems from uncultivated microbes.

Abstract: Competitive coevolution between microbes and viruses has led to the diversification of CRISPR-Cas defense systems against infectious agents. By analyzing metagenomic terabase datasets, we identified two compact families (775 to 803 amino acids (aa)) of CRISPR-Cas ribonucleases from hypersaline samples, named Cas13X and Cas13Y. We engineered Cas13X.1 (775 aa) for RNA interference experiments in mammalian cell lines. We found Cas13X.1 could tolerate single-nucleotide mismatches in RNA recognition, facilitating prophylactic RNA virus inhibition. Moreover, a minimal RNA base editor, composed of engineered deaminase (385 aa) and truncated Cas13X.1 (445 aa), exhibited robust editing efficiency and high specificity to induce RNA base conversions. Our results suggest that there exist untapped bacterial defense systems in natural microbes that can function efficiently in mammalian cells, and thus potentially are useful for RNA-editing-based research.

The power of imaging to understand extracellular vesicle biology in vivo.

Abstract: Extracellular vesicles (EVs) are nano-sized lipid bilayer vesicles released by virtually every cell type. EVs have diverse biological activities, ranging from roles in development and homeostasis to cancer progression, which has spurred the development of EVs as disease biomarkers and drug nanovehicles. Owing to the small size of EVs, however, most studies have relied on isolation and biochemical analysis of bulk EVs separated from biofluids. Although informative, these approaches do not capture the dynamics of EV release, biodistribution, and other contributions to pathophysiology. Recent advances in live and high-resolution microscopy techniques, combined with innovative EV labeling strategies and reporter systems, provide new tools to study EVs in vivo in their physiological environment and at the single-vesicle level. Here we critically review the latest advances and challenges in EV imaging, and identify urgent, outstanding questions in our quest to unravel EV biology and therapeutic applications.

Exosome detection via the ultrafast-isolation system: EXODUS.

Abstract: Exosomes have shown great potential in disease diagnostics and therapeutics. However, current isolation approaches are burdensome and suffer from low speed, yield and purity, limiting basic research and clinical applications. Here, we describe an efficient exosome detection method via the ultrafast-isolation system (EXODUS) that allows automated label-free purification of exosomes from varied biofluids. We obtained the ultra-efficient purification of exosomes by negative pressure oscillation and double coupled harmonic oscillator–enabled membrane vibration. Our two coupled oscillators generate dual-frequency transverse waves on the membranes, enabling EXODUS to outperform other isolation techniques in speed, purity and yield. We demonstrated EXODUS by purifying exosomes from urine samples of 113 patients and validated the practical relevance in exosomal RNA profiling with the high-resolution capability and high-throughput analysis. EXODUS is a high-speed isolation method for the enrichment of exosome from biological fluids with high purity and yield.

Spatially resolved single-cell genomics and transcriptomics by imaging.

Abstract: The recent advent of genome-scale imaging has enabled single-cell omics analysis in a spatially resolved manner in intact cells and tissues. These advances allow gene expression profiling of individual cells, and hence in situ identification and spatial mapping of cell types, in complex tissues. The high spatial resolution of these approaches further allows determination of the spatial organizations of the genome and transcriptome inside cells, both of which are key regulatory mechanisms for gene expression.

Real-time volumetric reconstruction of biological dynamics with light-field microscopy and deep learning

Abstract: Light-field microscopy has emerged as a technique of choice for high-speed volumetric imaging of fast biological processes However, artifacts, nonuniform resolution and a slow reconstruction speed have limited its full capabilities for in toto extraction of dynamic spatiotemporal patterns in samples Here, we combined a view-channel-depth (VCD) neural network with light-field microscopy to mitigate these limitations, yielding artifact-free three-dimensional image sequences with uniform spatial resolution and high-video-rate reconstruction throughput We imaged neuronal activities across moving Caenorhabditis elegans and blood flow in a beating zebrafish heart at single-cell resolution with volumetric imaging rates up to 200 Hz Reconstruction of light-field microscopy data with a deep-learning network achieves high reconstruction speed and reduces artifacts, as illustrated for moving C elegans and beating zebrafish hearts