Whole-brain tissue mapping toolkit using large-scale highly multiplexed immunofluorescence imaging and deep neural networks.
Ontology highlight
ABSTRACT:
SUBMITTER: Maric D
PROVIDER: S-EPMC7946933 | biostudies-literature |
REPOSITORIES: biostudies-literature
Similar Datasets
Project description:Intra-tumoral heterogeneity can wreak havoc on current precision medicine strategies due to challenges in sufficient sampling of geographically separated areas of biodiversity distributed across centimeter-scale tumor distances. In particular, modern tissue profiling approaches are still largely designed to only interrogate small tumor fragments; which may constitute a minute and non-representative fraction of the overall neoplasm. To address this gap, we developed a pipeline that leverages deep learning to define topographic histomorphologic fingerprints of tissue and create Histomic Atlases of Variation Of Cancers (HAVOC). Importantly, using a number of spatially-resolved readouts, including mass-spectrometry-based proteomics and immunohistochemisy, we demonstrate that these personalized atlases of histomic variation can define regional cancer boundaries with distinct biological programs. Using larger tumor specimens, we show that HAVOC can map spatial organization of cancer biodiversity spanning tissue coordinates separated by multiple centimeters. By applying this tool to guide profiling of 19 distinct geographic partitions from 6 high-grade gliomas, HAVOC revealed that distinct states of differentiation can often co-exist and be regionally distributed across individual tumors. Finally,to highlight generalizability, we further benchmark HAVOC on additional tumor types and experimental models of heterogeneity. Together, we establish HAVOC as a versatile and accessible tool to generate small-scale maps of tissue heterogeneity and guide regional deployment of molecular resources to relevant and biodiverse tumor niches.
2023-08-23 | PXD037548 | Pride
Project description:We present a physically-motivated topology of a deep neural network that can efficiently infer extensive parameters (such as energy, entropy, or number of particles) of arbitrarily large systems, doing so with scaling. We use a form of domain decomposition for training and inference, where each sub-domain (tile) is comprised of a non-overlapping focus region surrounded by an overlapping context region. The size of these regions is motivated by the physical interaction length scales of the problem. We demonstrate the application of EDNNs to three physical systems: the Ising model and two hexagonal/graphene-like datasets. In the latter, an EDNN was able to make total energy predictions of a 60 atoms system, with comparable accuracy to density functional theory (DFT), in 57 milliseconds. Additionally EDNNs are well suited for massively parallel evaluation, as no communication is necessary during neural network evaluation. We demonstrate that EDNNs can be used to make an energy prediction of a two-dimensional 35.2 million atom system, over 1.0 μm2 of material, at an accuracy comparable to DFT, in under 25 minutes. Such a system exists on a length scale visible with optical microscopy and larger than some living organisms.
| S-EPMC6460955 | biostudies-literature
Project description:SIGNIFICANCE:Advanced genetic characterization has informed cancer heterogeneity and the challenge it poses to effective therapy; however, current methods lack spatial context, which is vital to successful cancer therapy. Conventional immunolabeling, commonplace in the clinic, can provide spatial context to protein expression. However, these techniques are spectrally limited, resulting in inadequate capacity to resolve the heterogenous cell subpopulations within a tumor. AIM:We developed and optimized oligonucleotide conjugated antibodies (Ab-oligo) to facilitate cyclic immunofluorescence (cyCIF), resulting in high-dimensional immunostaining. APPROACH:We employed a site-specific conjugation strategy to label antibodies with unique oligonucleotide sequences, which were hybridized in situ with their complementary oligonucleotide sequence tagged with a conventional fluorophore. Antibody concentration, imaging strand concentration, and configuration as well as signal removal strategies were optimized to generate maximal staining intensity using our Ab-oligo cyCIF strategy. RESULTS:We successfully generated 14 Ab-oligo conjugates and validated their antigen specificity, which was maintained in single color staining studies. With the validated antibodies, we generated up to 14-color imaging data sets of human breast cancer tissues. CONCLUSIONS:Herein, we demonstrated the utility of Ab-oligo cyCIF as a platform for highly multiplexed imaging, its utility to measure tumor heterogeneity, and its potential for future use in clinical histopathology.
| S-EPMC7245007 | biostudies-literature
Project description:Single-cell analysis reveals aspects of cellular physiology not evident from population-based studies, particularly in the case of highly multiplexed methods such as mass cytometry (CyTOF) able to correlate the levels of multiple signalling, differentiation and cell fate markers. Immunofluorescence (IF) microscopy adds information on cell morphology and the microenvironment that are not obtained using flow-based techniques, but the multiplicity of conventional IF is limited. This has motivated development of imaging methods that require specialized instrumentation, exotic reagents or proprietary protocols that are difficult to reproduce in most laboratories. Here we report a public-domain method for achieving high multiplicity single-cell IF using cyclic immunofluorescence (CycIF), a simple and versatile procedure in which four-colour staining alternates with chemical inactivation of fluorophores to progressively build a multichannel image. Because CycIF uses standard reagents and instrumentation and is no more expensive than conventional IF, it is suitable for high-throughput assays and screening applications.
| S-EPMC4587398 | biostudies-literature
Project description:Mapping the complex biogeography of microbial communities in situ with high taxonomic and spatial resolution poses a major challenge because of the high density1 and rich diversity2 of species in environmental microbiomes and the limitations of optical imaging technology3-6. Here we introduce high-phylogenetic-resolution microbiome mapping by fluorescence in situ hybridization (HiPR-FISH), a versatile technology that uses binary encoding, spectral imaging and decoding based on machine learning to create micrometre-scale maps of the locations and identities of hundreds of microbial species in complex communities. We show that 10-bit HiPR-FISH can distinguish between 1,023 isolates of Escherichia coli, each fluorescently labelled with a unique binary barcode. HiPR-FISH, in conjunction with custom algorithms for automated probe design and analysis of single-cell images, reveals the disruption of spatial networks in the mouse gut microbiome in response to treatment with antibiotics, and the longitudinal stability of spatial architectures in the human oral plaque microbiome. Combined with super-resolution imaging, HiPR-FISH shows the diverse strategies of ribosome organization that are exhibited by taxa in the human oral microbiome. HiPR-FISH provides a framework for analysing the spatial ecology of environmental microbial communities at single-cell resolution.
| S-EPMC8050837 | biostudies-literature
Project description:Skeletal muscle myofibers are large syncytial cells comprising hundreds of myonuclei, and in situ hybridization experiments have reported a range of transcript localization patterns within them. Although some transcripts are uniformly distributed throughout myofibers, proximity to specialized regions can affect the programming of myonuclei and functional compartmentalization of transcripts. Established techniques are limited by a lack of both sensitivity and spatial resolution, restricting the ability to identify different patterns of gene expression. In this study, we adapted RNAscope fluorescent in situ hybridization technology for use on whole-mount mouse primary myofibers, a preparation that isolates single myofibers with their associated muscle stem cells remaining in their niche. This method can be combined with immunofluorescence, enabling an unparalleled ability to visualize and quantify transcripts and proteins across the length and depth of skeletal myofibers and their associated stem cells. Using this approach, we demonstrate a range of potential uses, including the visualization of specialized transcriptional programming within myofibers, tracking activation-induced transcriptional changes, quantification of stem cell heterogeneity and evaluation of stem cell niche factor transcription patterns.
| S-EPMC6826044 | biostudies-literature
Project description:Applications of generative models for genomic data have gained significant momentum in the past few years, with scopes ranging from data characterization to generation of genomic segments and functional sequences. In our previous study, we demonstrated that generative adversarial networks (GANs) and restricted Boltzmann machines (RBMs) can be used to create novel high-quality artificial genomes (AGs) which can preserve the complex characteristics of real genomes such as population structure, linkage disequilibrium and selection signals. However, a major drawback of these models is scalability, since the large feature space of genome-wide data increases computational complexity vastly. To address this issue, we implemented a novel convolutional Wasserstein GAN (WGAN) model along with a novel conditional RBM (CRBM) framework for generating AGs with high SNP number. These networks implicitly learn the varying landscape of haplotypic structure in order to capture complex correlation patterns along the genome and generate a wide diversity of plausible haplotypes. We performed comparative analyses to assess both the quality of these generated haplotypes and the amount of possible privacy leakage from the training data. As the importance of genetic privacy becomes more prevalent, the need for effective privacy protection measures for genomic data increases. We used generative neural networks to create large artificial genome segments which possess many characteristics of real genomes without substantial privacy leakage from the training dataset. In the near future, with further improvements in haplotype quality and privacy preservation, large-scale artificial genome databases can be assembled to provide easily accessible surrogates of real databases, allowing researchers to conduct studies with diverse genomic data within a safe ethical framework in terms of donor privacy.
| S-EPMC10635570 | biostudies-literature
Project description:We introduce AtacWorks (https://github.com/clara-genomics/AtacWorks), a method to denoise and identify accessible chromatin regions from low-coverage or low-quality ATAC-seq data. AtacWorks uses a deep neural network to learn a mapping between noisy ATAC-seq data and corresponding higher-coverage or higher-quality data. We apply this approach to as few as 50 hematopoietic stem cells to identify regulatory elements that are differentially-accessible between rare lineage-primed cell subpopulations.
2021-01-11 | GSE147113 | GEO
Project description:The analysis of electrical impulse phenomena in cardiac muscle tissue is important for the diagnosis of heart rhythm disorders and other cardiac pathophysiology. Cardiac mapping techniques acquire local temporal measurements and combine them to visualize the spread of electrophysiological wave phenomena across the heart surface. However, low spatial resolution, sparse measurement locations, noise and other artifacts make it challenging to accurately visualize spatio-temporal activity. For instance, electro-anatomical catheter mapping is severely limited by the sparsity of the measurements, and optical mapping is prone to noise and motion artifacts. In the past, several approaches have been proposed to create more reliable maps from noisy or sparse mapping data. Here, we demonstrate that deep learning can be used to compute phase maps and detect phase singularities in optical mapping videos of ventricular fibrillation, as well as in very noisy, low-resolution and extremely sparse simulated data of reentrant wave chaos mimicking catheter mapping data. The self-supervised deep learning approach is fundamentally different from classical phase mapping techniques. Rather than encoding a phase signal from time-series data, a deep neural network instead learns to directly associate phase maps and the positions of phase singularities with short spatio-temporal sequences of electrical data. We tested several neural network architectures, based on a convolutional neural network (CNN) with an encoding and decoding structure, to predict phase maps or rotor core positions either directly or indirectly via the prediction of phase maps and a subsequent classical calculation of phase singularities. Predictions can be performed across different data, with models being trained on one species and then successfully applied to another, or being trained solely on simulated data and then applied to experimental data. Neural networks provide a promising alternative to conventional phase mapping and rotor core localization methods. Future uses may include the analysis of optical mapping studies in basic cardiovascular research, as well as the mapping of atrial fibrillation in the clinical setting.
| S-EPMC8718715 | biostudies-literature
Project description:Subject categories of scholarly papers generally refer to the knowledge domain(s) to which the papers belong, examples being computer science or physics. Subject category classification is a prerequisite for bibliometric studies, organizing scientific publications for domain knowledge extraction, and facilitating faceted searches for digital library search engines. Unfortunately, many academic papers do not have such information as part of their metadata. Most existing methods for solving this task focus on unsupervised learning that often relies on citation networks. However, a complete list of papers citing the current paper may not be readily available. In particular, new papers that have few or no citations cannot be classified using such methods. Here, we propose a deep attentive neural network (DANN) that classifies scholarly papers using only their abstracts. The network is trained using nine million abstracts from Web of Science (WoS). We also use the WoS schema that covers 104 subject categories. The proposed network consists of two bi-directional recurrent neural networks followed by an attention layer. We compare our model against baselines by varying the architecture and text representation. Our best model achieves micro- F1 measure of 0.76 with F1 of individual subject categories ranging from 0.50 to 0.95. The results showed the importance of retraining word embedding models to maximize the vocabulary overlap and the effectiveness of the attention mechanism. The combination of word vectors with TFIDF outperforms character and sentence level embedding models. We discuss imbalanced samples and overlapping categories and suggest possible strategies for mitigation. We also determine the subject category distribution in CiteSeerX by classifying a random sample of one million academic papers.
| S-EPMC8025978 | biostudies-literature