In this paper, we introduce Gene Knockout Inference (GenKI), a virtual knockout (KO) tool for gene function prediction using single-cell RNA sequencing (scRNA-seq) data in the absence of KO samples when only wild-type...
In this paper, we introduce Gene Knockout Inference (GenKI), a virtual knockout (KO) tool for gene function prediction using single-cell RNA sequencing (scRNA-seq) data in the absence of KO samples when only wild-type (WT) samples are available. Without using any information from real KO samples, GenKI is designed to capture shifting patterns in gene regulation caused by the KO perturbation in an unsupervised manner and provide a robust and scalable framework for gene function studies. To achieve this goal, GenKI adapts a variational graph autoencoder (VGAE) model to learn latent representations of genes and interactions between genes from the input WT scRNA-seq data and a derived single-cell gene regulatory network (scGRN). The virtual KO data is then generated by computationally removing all edges of the KO gene-the gene to be knocked out for functional study-from the scGRN. The differences between WT and virtual KO data are discerned by using their corresponding latent parameters derived from the trained VGAE model. Our simulations show that GenKI accurately approximates the perturbation profiles upon gene KO and outperforms the state-of-the-art under a series of evaluation conditions. Using publicly available scRNA-seq data sets, we demonstrate that GenKI recapitulates discoveries of real-animal KO experiments and accurately predicts cell type-specific functions of KO genes. Thus, GenKI provides an in-silico alternative to KO experiments that may partially replace the need for genetically modified animals or other genetically perturbed systems.
We have studied the terahertz response of a bulk single crystal of La0.875Sr0.125MnO3at around its Curie temperature, observing large changes in the real and imaginary parts of the optical conductivity as a function o...
详细信息
Metasurfaces are ultrathin planar arrays of carefully tailored subwavelength particles that enable agile and flexible manipulation of the impinging waves. Originally introduced in optics, their application to acoustic...
详细信息
Metasurfaces are ultrathin planar arrays of carefully tailored subwavelength particles that enable agile and flexible manipulation of the impinging waves. Originally introduced in optics, their application to acoustic waves has recently opened exciting opportunities for exotic sound control. In conventional acoustic inclusions, the interactions with the impinging pressure and velocity are decoupled, limiting the functionalities that arrays of them can achieve. While the coupling between these two quantities in symmetry-breaking inclusions, known as Willis coupling, has been discussed for several years, only recently has it been realized that these phenomena can become nonperturbative in suitably tailored resonant scatterers. Here, we explore the opportunities that these Willis meta-atoms open in the context of acoustic metasurfaces, offering additional knobs to manipulate and tailor sound. The general response of Willis metasurface is analytically derived, yielding fundamental bounds and optimal surface responses enabling full control of the impinging acoustic wave front.
In this paper, dual Vienna rectifiers are proposed for Wind Energy Conversion System (WECS) applications with Open-End Winding (OEW) Permanent Magnet Synchronous Generator (PMSG). Due to the reduced number of controll...
详细信息
ISBN:
(数字)9781728158266
ISBN:
(纸本)9781728158273
In this paper, dual Vienna rectifiers are proposed for Wind Energy Conversion System (WECS) applications with Open-End Winding (OEW) Permanent Magnet Synchronous Generator (PMSG). Due to the reduced number of controlled switches, the proposed topologies have reduced costs and high reliability. Besides, they provide a better power quality using the same number of controlled switches than conventional structures presented in the literature, making them very attractive options for industry applications. The system model, space vector modulation, and control strategy are given. Simulation results are provided in order to validate their performance and feasibility.
There is an emerging recognition that successful utilization of chiral degrees of freedom can bring new scientific and technological opportunities to diverse research areas. Hence, methods are being sought for creatin...
详细信息
The internet has become an integral part of our life, we connect daily for informational, social, entertainment and even work and economic purposes. Therefore, it is completely normal to connect to the internet;But it...
详细信息
Complex, learned motor behaviors involve the coordination of large-scale neural activity across multiple brain regions, but our understanding of the population-level dynamics within different regions tied to the same ...
详细信息
Treatments based on Virtual Reality have been successfully used in motor rehabilitation of issues such as Spinal Cord Injury and Stroke. Highly immersive Virtual environments combined with biofeedback can be utilized ...
详细信息
Purpose: To develop a neural ordinary differential equation (ODE) model for visualizing deep neural network behavior during multi-parametric MRI (mp-MRI) based glioma segmentation as a method to enhance deep learning ...
详细信息
Purpose: To develop a neural ordinary differential equation (ODE) model for visualizing deep neural network behavior during multi-parametric MRI (mp-MRI) based glioma segmentation as a method to enhance deep learning explainability. Methods: By hypothesizing that deep feature extraction can be modeled as a spatiotemporally continuous process, we designed a novel deep learning model, neural ODE, in which deep feature extraction was governed by an ODE without explicit expression. The dynamics of 1) MR images after interactions with the deep neural network and 2) segmentation formation can thus be visualized after solving ODE. An accumulative contribution curve (ACC) was designed to quantitatively evaluate each MR image's utilization by the deep neural network towards the final segmentation results. The proposed neural ODE model was demonstrated using 369 glioma patients with a 4-modality mp-MRI protocol: T1, contrast-enhanced T1 (T1-Ce), T2, and FLAIR. Three neural ODE models were trained to segment enhancing tumor (ET), tumor core (TC), and whole tumor (WT), respectively. The key MR modalities with significant utilization by deep neural network were identified based on ACC analysis. Segmentation results by deep neural networks using only the key MR modalities were compared to the ones using all 4 MR modalities in terms of Dice coefficient, accuracy, sensitivity, and specificity. Results: All neural ODE models successfully illustrated image dynamics as expected. ACC analysis identified T1-Ce as the only key modality in ET and TC segmentations, while both FLAIR and T2 were key modalities in WT segmentation. Compared to the U-Net results using all 4 MR modalities, Dice coefficient of ET (0.784→0.775), TC (0.760→0.758), and WT (0.841→0.837) using the key modalities only had minimal differences without significance. Accuracy, sensitivity, and specificity results demonstrated the same patterns. Conclusion: The neural ODE model offers a new tool for optimizing the deep lear
暂无评论