MultiVI: deep generative model for the integration of multimodal data.
Ontology highlight
ABSTRACT:
SUBMITTER: Ashuach T
PROVIDER: S-EPMC10406609 | biostudies-literature | 2023 Aug
REPOSITORIES: biostudies-literature
Publications
MultiVI: deep generative model for the integration of multimodal data.
Ashuach Tal T Gabitto Mariano I MI Koodli Rohan V RV Saldi Giuseppe-Antonio GA Jordan Michael I MI Yosef Nir N
Nature methods 20230629 8
Jointly profiling the transcriptome, chromatin accessibility and other molecular properties of single cells offers a powerful way to study cellular diversity. Here we present MultiVI, a probabilistic model to analyze such multiomic data and leverage it to enhance single-modality datasets. MultiVI creates a joint representation that allows an analysis of all modalities included in the multiomic input data, even for cells for which one or more modalities are missing. It is available at scvi-tools. ...[more]
Similar Datasets
Project description:BackgroundWith the development of single-cell technology, many cell traits can be measured. Furthermore, the multi-omics profiling technology could jointly measure two or more traits in a single cell simultaneously. In order to process the various data accumulated rapidly, computational methods for multimodal data integration are needed.ResultsHere, we present inClust+, a deep generative framework for the multi-omics. It's built on previous inClust that is specific for transcriptome data, and augmented with two mask modules designed for multimodal data processing: an input-mask module in front of the encoder and an output-mask module behind the decoder. InClust+ was first used to integrate scRNA-seq and MERFISH data from similar cell populations, and to impute MERFISH data based on scRNA-seq data. Then, inClust+ was shown to have the capability to integrate the multimodal data (e.g. tri-modal data with gene expression, chromatin accessibility and protein abundance) with batch effect. Finally, inClust+ was used to integrate an unlabeled monomodal scRNA-seq dataset and two labeled multimodal CITE-seq datasets, transfer labels from CITE-seq datasets to scRNA-seq dataset, and generate the missing modality of protein abundance in monomodal scRNA-seq data. In the above examples, the performance of inClust+ is better than or comparable to the most recent tools in the corresponding task.ConclusionsThe inClust+ is a suitable framework for handling multimodal data. Meanwhile, the successful implementation of mask in inClust+ means that it can be applied to other deep learning methods with similar encoder-decoder architecture to broaden the application scope of these models.
| S-EPMC10809631 | biostudies-literature
Project description:Recent technological advancements in single-cell genomics have enabled joint profiling of gene expression and alternative modalities at unprecedented scale. Consequently, the complexity of multi-omics data sets is increasing massively. Existing models for multi-modal data are typically limited in functionality or scalability, making data integration and downstream analysis cumbersome. We present multiDGD, a scalable deep generative model providing a probabilistic framework to learn shared representations of transcriptome and chromatin accessibility. It shows outstanding performance on data reconstruction without feature selection. We demonstrate on several data sets from human and mouse that multiDGD learns well-clustered joint representations. We further find that probabilistic modeling of sample covariates enables post-hoc data integration without the need for fine-tuning. Additionally, we show that multiDGD can detect statistical associations between genes and regulatory regions conditioned on the learned representations. multiDGD is available as an scverse-compatible package on GitHub.
| S-EPMC11579284 | biostudies-literature
Project description:Super-resolving the coarse outputs of global climate simulations, termed downscaling, is crucial in making political and social decisions on systems requiring long-term climate change projections. Existing fast super-resolution techniques, however, have yet to preserve the spatially correlated nature of climatological data, which is particularly important when we address systems with spatial expanse, such as the development of transportation infrastructure. Herein, we show an adversarial network-based machine learning enables us to correctly reconstruct the inter-regional spatial correlations in downscaling with high magnification of up to 50 while maintaining pixel-wise statistical consistency. Direct comparison with the measured meteorological data of temperature and precipitation distributions reveals that integrating climatologically important physical information improves the downscaling performance, which prompts us to call this approach
| S-EPMC10130044 | biostudies-literature
Project description:Across diverse domains of science and technology, electromagnetic (EM) inversion problems benefit from the ability to account for multimodal prior information to regularize their inherent ill-posedness. Indeed, besides priors that are formulated mathematically or learned from quantitative data, valuable prior information may be available in the form of text or images. Besides handling semantic multimodality, it is furthermore important to minimize the cost of adapting to a new physical measurement operator and to limit the requirements for costly labeled data. Here, these challenges are tackled with a frugal and multimodal semantic-EM inversion technique. The key ingredient is a multimodal generator of reconstruction results that can be pretrained, being agnostic to the physical measurement operator. The generator is fed by a multimodal foundation model encoding the multimodal semantic prior and a physical adapter encoding the measured data. For a new physical setting, only the lightweight physical adapter is retrained. The authors' architecture also enables a flexible iterative step-by-step solution to the inverse problem where each step can be semantically controlled. The feasibility and benefits of this methodology are demonstrated for three EM inverse problems: a canonical two-dimensional inverse-scattering problem in numerics, as well as three-dimensional and four-dimensional compressive microwave meta-imaging experiments.
| S-EPMC11558082 | biostudies-literature
Project description:Hemodynamic responses, in general, and the blood oxygenation level-dependent (BOLD) fMRI signal, in particular, provide an indirect measure of neuronal activity. There is strong evidence that the BOLD response correlates well with post-synaptic changes, induced by changes in the excitatory and inhibitory (E-I) balance between active neuronal populations. Typical BOLD responses exhibit transients, such as the early-overshoot and post-stimulus undershoot, that can be linked to transients in neuronal activity, but they can also result from vascular uncoupling between cerebral blood flow (CBF) and venous cerebral blood volume (venous CBV). Recently, we have proposed a novel generative hemodynamic model of the BOLD signal within the dynamic causal modeling framework, inspired by physiological observations, called P-DCM (Havlicek et al., 2015). We demonstrated the generative model's ability to more accurately model commonly observed neuronal and vascular transients in single regions but also effective connectivity between multiple brain areas (Havlicek et al., 2017b). In this paper, we additionally demonstrate the versatility of the generative model to jointly explain dynamic relationships between neuronal and hemodynamic physiological variables underlying the BOLD signal using multi-modal data. For this purpose, we utilized three distinct data-sets of experimentally induced responses in the primary visual areas measured in human, cat, and monkey brain, respectively: (1) CBF and BOLD responses; (2) CBF, total CBV, and BOLD responses (Jin and Kim, 2008); and (3) positive and negative neuronal and BOLD responses (Shmuel et al., 2006). By fitting the generative model to the three multi-modal experimental data-sets, we showed that the presence or absence of dynamic features in the BOLD signal is not an unambiguous indication of presence or absence of those features on the neuronal level. Nevertheless, the generative model that takes into account the dynamics of the physiological mechanisms underlying the BOLD response allowed dissociating neuronal from vascular transients and deducing excitatory and inhibitory neuronal activity time-courses from BOLD data alone and from multi-modal data.
| S-EPMC5715391 | biostudies-literature
Project description:MotivationAccurate disease phenotype prediction plays an important role in the treatment of heterogeneous diseases like cancer in the era of precision medicine. With the advent of high throughput technologies, more comprehensive multi-omics data is now available that can effectively link the genotype to phenotype. However, the interactive relation of multi-omics datasets makes it particularly challenging to incorporate different biological layers to discover the coherent biological signatures and predict phenotypic outcomes. In this study, we introduce omicsGAN, a generative adversarial network model to integrate two omics data and their interaction network. The model captures information from the interaction network as well as the two omics datasets and fuse them to generate synthetic data with better predictive signals.ResultsLarge-scale experiments on The Cancer Genome Atlas breast cancer, lung cancer and ovarian cancer datasets validate that (i) the model can effectively integrate two omics data (e.g. mRNA and microRNA expression data) and their interaction network (e.g. microRNA-mRNA interaction network). The synthetic omics data generated by the proposed model has a better performance on cancer outcome classification and patients survival prediction compared to original omics datasets. (ii) The integrity of the interaction network plays a vital role in the generation of synthetic data with higher predictive quality. Using a random interaction network does not allow the framework to learn meaningful information from the omics datasets; therefore, results in synthetic data with weaker predictive signals.Availability and implementationSource code is available at: https://github.com/CompbioLabUCF/omicsGAN.Supplementary informationSupplementary data are available at Bioinformatics online.
| S-EPMC10060730 | biostudies-literature
Project description:Inferring missing links based on the currently observed network is known as link prediction, which has tremendous real-world applications in biomedicine, e-commerce, social media, and criminal intelligence. Numerous methods have been proposed to solve the link prediction problem. Yet, many of these methods are designed for undirected networks only and based on domain-specific heuristics. Here we developed a new link prediction method based on deep generative models, which does not rely on any domain-specific heuristic and works for general undirected or directed complex networks. Our key idea is to represent the adjacency matrix of a network as an image and then learn hierarchical feature representations of the image by training a deep generative model. Those features correspond to structural patterns in the network at different scales, from small subgraphs to mesoscopic communities. When applied to various real-world networks from different domains, our method shows overall superior performance against existing methods.
| S-EPMC7575873 | biostudies-literature
Project description:Integration of heterogeneous single-cell sequencing datasets generated across multiple tissue locations, time, and conditions is essential for a comprehensive understanding of the cellular states and expression programs underlying complex biological systems. Here, we present scDREAMER ( https://github.com/Zafar-Lab/scDREAMER ), a data-integration framework that employs deep generative models and adversarial training for both unsupervised and supervised (scDREAMER-Sup) integration of multiple batches. Using six real benchmarking datasets, we demonstrate that scDREAMER can overcome critical challenges including skewed cell type distribution among batches, nested batch-effects, large number of batches and conservation of development trajectory across batches. Our experiments also show that scDREAMER and scDREAMER-Sup outperform state-of-the-art unsupervised and supervised integration methods respectively in batch-correction and conservation of biological variation. Using a 1 million cells dataset, we demonstrate that scDREAMER is scalable and can perform atlas-level cross-species (e.g., human and mouse) integration while being faster than other deep-learning-based methods.
| S-EPMC10682386 | biostudies-literature
Project description:PurposeThis study proposed an end-to-end unsupervised medical fusion generative adversarial network, MedFusionGAN, to fuse computed tomography (CT) and high-resolution isotropic 3D T1-Gd Magnetic resonance imaging (MRI) image sequences to generate an image with CT bone structure and MRI soft tissue contrast to improve target delineation and to reduce the radiotherapy planning time.MethodsWe used a publicly available multicenter medical dataset (GLIS-RT, 230 patients) from the Cancer Imaging Archive. To improve the models generalization, we consider different imaging protocols and patients with various brain tumor types, including metastases. The proposed MedFusionGAN consisted of one generator network and one discriminator network trained in an adversarial scenario. Content, style, and L1 losses were used for training the generator to preserve the texture and structure information of the MRI and CT images.ResultsThe MedFusionGAN successfully generates fused images with MRI soft-tissue and CT bone contrast. The results of the MedFusionGAN were quantitatively and qualitatively compared with seven traditional and eight deep learning (DL) state-of-the-art methods. Qualitatively, our method fused the source images with the highest spatial resolution without adding the image artifacts. We reported nine quantitative metrics to quantify the preservation of structural similarity, contrast, distortion level, and image edges in fused images. Our method outperformed both traditional and DL methods on six out of nine metrics. And it got the second performance rank for three and two quantitative metrics when compared with traditional and DL methods, respectively. To compare soft-tissue contrast, intensity profile along tumor and tumor contours of the fusion methods were evaluated. MedFusionGAN provides a more consistent, better intensity profile, and a better segmentation performance.ConclusionsThe proposed end-to-end unsupervised method successfully fused MRI and CT images. The fused image could improve targets and OARs delineation, which is an important aspect of radiotherapy treatment planning.
| S-EPMC10704723 | biostudies-literature
Project description:AimsMany studies have utilized data sources such as clinical variables, polygenic risk scores, electrocardiogram (ECG), and plasma proteins to predict the risk of atrial fibrillation (AF). However, few studies have integrated all four sources from a single study to comprehensively assess AF prediction.Methods and resultsWe included 8374 (Visit 3, 1993-95) and 3730 (Visit 5, 2011-13) participants from the Atherosclerosis Risk in Communities Study to predict incident AF and prevalent (but covert) AF. We constructed a (i) clinical risk score using CHARGE-AF clinical variables, (ii) polygenic risk score using pre-determined weights, (iii) protein risk score using regularized logistic regression, and (iv) ECG risk score from a convolutional neural network. Risk prediction performance was measured using regularized logistic regression. After a median follow-up of 15.1 years, 1910 AF events occurred since Visit 3 and 229 participants had prevalent AF at Visit 5. The area under curve (AUC) improved from 0.660 to 0.752 (95% CI, 0.741-0.763) and from 0.737 to 0.854 (95% CI, 0.828-0.880) after addition of the polygenic risk score to the CHARGE-AF clinical variables for predicting incident and prevalent AF, respectively. Further addition of ECG and protein risk scores improved the AUC to 0.763 (95% CI, 0.753-0.772) and 0.875 (95% CI, 0.851-0.899) for predicting incident and prevalent AF, respectively.ConclusionA combination of clinical and polygenic risk scores was the most effective and parsimonious approach to predicting AF. Further addition of an ECG risk score or protein risk score provided only modest incremental improvement for predicting AF.
| S-EPMC11750194 | biostudies-literature