DeepImpute: an accurate, fast, and scalable deep neural network method to impute single-cell RNA-seq data.
Ontology highlight
ABSTRACT:
SUBMITTER: Arisdakessian C
PROVIDER: S-EPMC6798445 | biostudies-literature | 2019 Oct
REPOSITORIES: biostudies-literature
Publications
DeepImpute: an accurate, fast, and scalable deep neural network method to impute single-cell RNA-seq data.
Arisdakessian Cédric C Poirion Olivier O Yunits Breck B Zhu Xun X Garmire Lana X LX
Genome biology 20191018 1
Single-cell RNA sequencing (scRNA-seq) offers new opportunities to study gene expression of tens of thousands of single cells simultaneously. We present DeepImpute, a deep neural network-based imputation algorithm that uses dropout layers and loss functions to learn patterns in the data, allowing for accurate imputation. Overall, DeepImpute yields better accuracy than other six publicly available scRNA-seq imputation methods on experimental data, as measured by the mean squared error or Pearson' ...[more]
Similar Datasets
Project description:BackgroundIn recent years, the introduction of single-cell RNA sequencing (scRNA-seq) has enabled the analysis of a cell's transcriptome at an unprecedented granularity and processing speed. The experimental outcome of applying this technology is a [Formula: see text] matrix containing aggregated mRNA expression counts of M genes and N cell samples. From this matrix, scientists can study how cell protein synthesis changes in response to various factors, for example, disease versus non-disease states in response to a treatment protocol. This technology's critical challenge is detecting and accurately recording lowly expressed genes. As a result, low expression levels tend to be missed and recorded as zero - an event known as dropout. This makes the lowly expressed genes indistinguishable from true zero expression and different than the low expression present in cells of the same type. This issue makes any subsequent downstream analysis difficult.ResultsTo address this problem, we propose an approach to measure cell similarity using consensus clustering and demonstrate an effective and efficient algorithm that takes advantage of this new similarity measure to impute the most probable dropout events in the scRNA-seq datasets. We demonstrate that our approach exceeds the performance of existing imputation approaches while introducing the least amount of new noise as measured by clustering performance characteristics on datasets with known cell identities.ConclusionsccImpute is an effective algorithm to correct for dropout events and thus improve downstream analysis of scRNA-seq data. ccImpute is implemented in R and is available at https://github.com/khazum/ccImpute .
| S-EPMC9306045 | biostudies-literature
Project description:BackgroundSingle-cell RNA-sequencing (scRNA-seq) is becoming indispensable in the study of cell-specific transcriptomes. However, in scRNA-seq techniques, only a small fraction of the genes are captured due to "dropout" events. These dropout events require intensive treatment when analyzing scRNA-seq data. For example, imputation tools have been proposed to estimate dropout events and de-noise data. The performance of these imputation tools are often evaluated, or fine-tuned, using various clustering criteria based on ground-truth cell subgroup labels. This limits their effectiveness in the cases where we lack cell subgroup knowledge. We consider an alternative strategy which requires the imputation to follow a "self-consistency" principle; that is, the imputation process is to refine its results until there is no internal inconsistency or dropouts from the data.ResultsWe propose the use of "self-consistency" as a main criteria in performing imputation. To demonstrate this principle we devised I-Impute, a "self-consistent" method, to impute scRNA-seq data. I-Impute optimizes continuous similarities and dropout probabilities, in iterative refinements until a self-consistent imputation is reached. On the in silico data sets, I-Impute exhibited the highest Pearson correlations for different dropout rates consistently compared with the state-of-art methods SAVER and scImpute. Furthermore, we collected three wetlab datasets, mouse bladder cells dataset, embryonic stem cells dataset, and aortic leukocyte cells dataset, to evaluate the tools. I-Impute exhibited feasible cell subpopulation discovery efficacy on all the three datasets. It achieves the highest clustering accuracy compared with SAVER and scImpute.ConclusionsA strategy based on "self-consistency", captured through our method, I-Impute, gave imputation results better than the state-of-the-art tools. Source code of I-Impute can be accessed at https://github.com/xikanfeng2/I-Impute .
| S-EPMC7677776 | biostudies-literature
Project description:We propose a novel, scalable, and accurate method for detecting neuronal ensembles from a population of spiking neurons. Our approach offers a simple yet powerful tool to study ensemble activity. It relies on clustering synchronous population activity (population vectors), allows the participation of neurons in different ensembles, has few parameters to tune and is computationally efficient. To validate the performance and generality of our method, we generated synthetic data, where we found that our method accurately detects neuronal ensembles for a wide range of simulation parameters. We found that our method outperforms current alternative methodologies. We used spike trains of retinal ganglion cells obtained from multi-electrode array recordings under a simple ON-OFF light stimulus to test our method. We found a consistent stimuli-evoked ensemble activity intermingled with spontaneously active ensembles and irregular activity. Our results suggest that the early visual system activity could be organized in distinguishable functional ensembles. We provide a Graphic User Interface, which facilitates the use of our method by the scientific community.
| S-EPMC8323916 | biostudies-literature
Project description:Acoustic signals serve communication within and across species throughout the animal kingdom. Studying the genetics, evolution, and neurobiology of acoustic communication requires annotating acoustic signals: segmenting and identifying individual acoustic elements like syllables or sound pulses. To be useful, annotations need to be accurate, robust to noise, and fast. We here introduce DeepAudioSegmenter (DAS), a method that annotates acoustic signals across species based on a deep-learning derived hierarchical presentation of sound. We demonstrate the accuracy, robustness, and speed of DAS using acoustic signals with diverse characteristics from insects, birds, and mammals. DAS comes with a graphical user interface for annotating song, training the network, and for generating and proofreading annotations. The method can be trained to annotate signals from new species with little manual annotation and can be combined with unsupervised methods to discover novel signal types. DAS annotates song with high throughput and low latency for experimental interventions in realtime. Overall, DAS is a universal, versatile, and accessible tool for annotating acoustic communication signals.
| S-EPMC8560090 | biostudies-literature
Project description:Drug response differs substantially in cancer patients due to inter- and intra-tumor heterogeneity. Particularly, transcriptome context, especially tumor microenvironment, has been shown playing a significant role in shaping the actual treatment outcome. In this study, we develop a deep variational autoencoder (VAE) model to compress thousands of genes into latent vectors in a low-dimensional space. We then demonstrate that these encoded vectors could accurately impute drug response, outperform standard signature-gene based approaches, and appropriately control the overfitting problem. We apply rigorous quality assessment and validation, including assessing the impact of cell line lineage, cross-validation, cross-panel evaluation, and application in independent clinical data sets, to warrant the accuracy of the imputed drug response in both cell lines and cancer samples. Specifically, the expression-regulated component (EReX) of the observed drug response achieves high correlation across panels. Using the well-trained models, we impute drug response of The Cancer Genome Atlas data and investigate the features and signatures associated with the imputed drug response, including cell line origins, somatic mutations and tumor mutation burdens, tumor microenvironment, and confounding factors. In summary, our deep learning method and the results are useful for the study of signatures and markers of drug response.
| S-EPMC7979803 | biostudies-literature
Project description:PurposeA major challenge for accurate quantitative SPECT imaging of some radionuclides is the inadequacy of simple energy window-based scatter estimation methods, widely available on clinic systems. A deep learning approach for SPECT/CT scatter estimation is investigated as an alternative to computationally expensive Monte Carlo (MC) methods for challenging SPECT radionuclides, such as 90Y.MethodsA deep convolutional neural network (DCNN) was trained to separately estimate each scatter projection from the measured 90Y bremsstrahlung SPECT emission projection and CT attenuation projection that form the network inputs. The 13-layer deep architecture consisted of separate paths for the emission and attenuation projection that are concatenated before the final convolution steps. The training label consisted of MC-generated "true" scatter projections in phantoms (MC is needed only for training) with the mean square difference relative to the model output serving as the loss function. The test data set included a simulated sphere phantom with a lung insert, measurements of a liver phantom, and patients after 90Y radioembolization. OS-EM SPECT reconstruction without scatter correction (NO-SC), with the true scatter (TRUE-SC) (available for simulated data only), with the DCNN estimated scatter (DCNN-SC), and with a previously developed MC scatter model (MC-SC) were compared, including with 90Y PET when available.ResultsThe contrast recovery (CR) vs. noise and lung insert residual error vs. noise curves for images reconstructed with DCNN-SC and MC-SC estimates were similar. At the same noise level of 10% (across multiple realizations), the average sphere CR was 24%, 52%, 55%, and 67% for NO-SC, MC-SC, DCNN-SC, and TRUE-SC, respectively. For the liver phantom, the average CR for liver inserts were 32%, 73%, and 65% for NO-SC, MC-SC, and DCNN-SC, respectively while the corresponding values for average contrast-to-noise ratio (visibility index) in low-concentration extra-hepatic inserts were 2, 19, and 61, respectively. In patients, there was high concordance between lesion-to-liver uptake ratios for SPECT reconstruction with DCNN-SC (median 4.8, range 0.02-13.8) compared with MC-SC (median 4.0, range 0.13-12.1; CCC = 0.98) and with 90Y PET (median 4.9, range 0.02-11.2; CCC = 0.96) while the concordance with NO-SC was poor (median 2.8, range 0.3-7.2; CCC = 0.59). The trained DCNN took ~ 40 s (using a single i5 processor on a desktop computer) to generate the scatter estimates for all 128 views in a patient scan, compared to ~ 80 min for the MC scatter model using 12 processors.ConclusionsFor diverse 90Y test data that included patient studies, we demonstrated comparable performance between images reconstructed with deep learning and MC-based scatter estimates using metrics relevant for dosimetry and for safety. This approach that can be generalized to other radionuclides by changing the training data is well suited for real-time clinical use because of the high speed, orders of magnitude faster than MC, while maintaining high accuracy.
| S-EPMC7666660 | biostudies-literature
Project description:MotivationAn important task in the analysis of single-cell RNA-Seq data is the estimation of differentiation potency, as this can help identify stem-or-multipotent cells in non-temporal studies or in tissues where differentiation hierarchies are not well established. A key challenge in the estimation of single-cell potency is the need for a fast and accurate algorithm, scalable to large scRNA-Seq studies profiling millions of cells.ResultsHere, we present a single-cell potency measure, called Correlation of Connectome and Transcriptome (CCAT), which can return accurate single-cell potency estimates of a million cells in minutes, a 100-fold improvement over current state-of-the-art methods. We benchmark CCAT against 8 other single-cell potency models and across 28 scRNA-Seq studies, encompassing over 2 million cells, demonstrating comparable accuracy than the current state-of-the-art, at a significantly reduced computational cost, and with increased robustness to dropouts.Availability and implementationCCAT is part of the SCENT R-package, freely available from https://github.com/aet21/SCENT.Supplementary informationSupplementary data are available at Bioinformatics online.
| S-EPMC8275983 | biostudies-literature
Project description:Background fluorescence, especially when it exhibits undesired spatial features, is a primary factor for reduced image quality in optical microscopy. Structured background is particularly detrimental when analyzing single-molecule images for 3-dimensional localization microscopy or single-molecule tracking. Here, we introduce BGnet, a deep neural network with a U-net-type architecture, as a general method to rapidly estimate the background underlying the image of a point source with excellent accuracy, even when point-spread function (PSF) engineering is in use to create complex PSF shapes. We trained BGnet to extract the background from images of various PSFs and show that the identification is accurate for a wide range of different interfering background structures constructed from many spatial frequencies. Furthermore, we demonstrate that the obtained background-corrected PSF images, for both simulated and experimental data, lead to a substantial improvement in localization precision. Finally, we verify that structured background estimation with BGnet results in higher quality of superresolution reconstructions of biological structures.
| S-EPMC6955367 | biostudies-literature
Project description:In-memory computing using resistive memory devices is a promising non-von Neumann approach for making energy-efficient deep learning inference hardware. However, due to device variability and noise, the network needs to be trained in a specific way so that transferring the digitally trained weights to the analog resistive memory devices will not result in significant loss of accuracy. Here, we introduce a methodology to train ResNet-type convolutional neural networks that results in no appreciable accuracy loss when transferring weights to phase-change memory (PCM) devices. We also propose a compensation technique that exploits the batch normalization parameters to improve the accuracy retention over time. We achieve a classification accuracy of 93.7% on CIFAR-10 and a top-1 accuracy of 71.6% on ImageNet benchmarks after mapping the trained weights to PCM. Our hardware results on CIFAR-10 with ResNet-32 demonstrate an accuracy above 93.5% retained over a one-day period, where each of the 361,722 synaptic weights is programmed on just two PCM devices organized in a differential configuration.
| S-EPMC7235046 | biostudies-literature
Project description:MOTIVATION:Scaling by sequencing depth is usually the first step of analysis of bulk or single-cell RNA-seq data, but estimating sequencing depth accurately can be difficult, especially for single-cell data, risking the validity of downstream analysis. It is thus of interest to eliminate the use of sequencing depth and analyze the original count data directly. RESULTS:We call an analysis method 'scale-invariant' (SI) if it gives the same result under different estimates of sequencing depth and hence can use the original count data without scaling. For the problem of classifying samples into pre-specified classes, such as normal versus cancerous, we develop a deep-neural-network based SI classifier named scale-invariant deep neural-network classifier (SINC). On nine bulk and single-cell datasets, the classification accuracy of SINC is better than or competitive to the best of eight other classifiers. SINC is easier to use and more reliable on data where proper sequencing depth is hard to determine. AVAILABILITY AND IMPLEMENTATION:This source code of SINC is available at https://www.nd.edu/?jli9/SINC.zip. SUPPLEMENTARY INFORMATION:Supplementary data are available at Bioinformatics online.
| S-EPMC7523643 | biostudies-literature