Detecting novel cell type in single-cell chromatin accessibility data via open-set domain adaptation.

Recent advances in single-cell technologies enable the rapid growth of multi-omics data. Cell type annotation is one common task in analyzing single-cell data. It is a challenge that some cell types in the testing set are not present in the training set (i.e. unknown cell types). Most scATAC-seq cell type annotation methods generally assign each cell in the testing set to one known type in the training set but neglect unknown cell types. Here, we present OVAAnno, an automatic cell types annotation method which utilizes open-set domain adaptation to detect unknown cell types in scATAC-seq data. Comprehensive experiments show that OVAAnno successfully identifies known and unknown cell types. Further experiments demonstrate that OVAAnno also performs well on scRNA-seq data. Our codes are available online at https://github.com/lisaber/OVAAnno/tree/master.

Identifying spatial domain by adapting transcriptomics with histology through contrastive learning.

Recent advances in spatial transcriptomics have enabled measurements of gene expression at cell/spot resolution meanwhile retaining both the spatial information and the histology images of the tissues. Accurately identifying the spatial domains of spots is a vital step for various downstream tasks in spatial transcriptomics analysis. To remove noises in gene expression, several methods have been developed to combine histopathological images for data analysis of spatial transcriptomics. However, these methods either use the image only for the spatial relations for spots, or individually learn the embeddings of the gene expression and image without fully coupling the information. Here, we propose a novel method ConGI to accurately exploit spatial domains by adapting gene expression with histopathological images through contrastive learning. Specifically, we designed three contrastive loss functions within and between two modalities (the gene expression and image data) to learn the common representations. The learned representations are then used to cluster the spatial domains on both tumor and normal spatial transcriptomics datasets. ConGI was shown to outperform existing methods for the spatial domain identification. In addition, the learned representations have also been shown powerful for various downstream tasks, including trajectory inference, clustering, and visualization.

A parameter-free deep embedded clustering method for single-cell RNA-seq data.

Clustering analysis is widely used in single-cell ribonucleic acid (RNA)-sequencing (scRNA-seq) data to discover cell heterogeneity and cell states. While many clustering methods have been developed for scRNA-seq analysis, most of these methods require to provide the number of clusters. However, it is not easy to know the exact number of cell types in advance, and experienced determination is not always reliable. Here, we have developed ADClust, an automatic deep embedding clustering method for scRNA-seq data, which can accurately cluster cells without requiring a predefined number of clusters. Specifically, ADClust first obtains low-dimensional representation through pre-trained autoencoder and uses the representations to cluster cells into initial micro-clusters. The clusters are then compared in between by a statistical test, and similar micro-clusters are merged into larger clusters. According to the clustering, cell representations are updated so that each cell will be pulled toward centers of its assigned cluster and similar clusters, while cells are separated to keep distances between clusters. This is accomplished through jointly optimizing the carefully designed clustering and autoencoder loss functions. This merging process continues until convergence. ADClust was tested on 11 real scRNA-seq datasets and was shown to outperform existing methods in terms of both clustering performance and the accuracy on the number of the determined clusters. More importantly, our model provides high speed and scalability for large datasets.

A robust and scalable graph neural network for accurate single-cell classification.

Single-cell RNA sequencing (scRNA-seq) techniques provide high-resolution data on cellular heterogeneity in diverse tissues, and a critical step for the data analysis is cell type identification. Traditional methods usually cluster the cells and manually identify cell clusters through marker genes, which is time-consuming and subjective. With the launch of several large-scale single-cell projects, millions of sequenced cells have been annotated and it is promising to transfer labels from the annotated datasets to newly generated datasets. One powerful way for the transferring is to learn cell relations through the graph neural network (GNN), but traditional GNNs are difficult to process millions of cells due to the expensive costs of the message-passing procedure at each training epoch. Here, we have developed a robust and scalable GNN-based method for accurate single-cell classification (GraphCS), where the graph is constructed to connect similar cells within and between labelled and unlabeled scRNA-seq datasets for propagation of shared information. To overcome the slow information propagation of GNN at each training epoch, the diffused information is pre-calculated via the approximate Generalized PageRank algorithm, enabling sublinear complexity over cell numbers. Compared with existing methods, GraphCS demonstrates better performance on simulated, cross-platform, cross-species and cross-omics scRNA-seq datasets. More importantly, our model provides a high speed and scalability on large datasets, and can achieve superior performance for 1 million cells within 50 min.

Spatial transcriptomics prediction from histology jointly through Transformer and graph neural networks.

The rapid development of spatial transcriptomics allows the measurement of RNA abundance at a high spatial resolution, making it possible to simultaneously profile gene expression, spatial locations of cells or spots, and the corresponding hematoxylin and eosin-stained histology images. It turns promising to predict gene expression from histology images that are relatively easy and cheap to obtain. For this purpose, several methods are devised, but they have not fully captured the internal relations of the 2D vision features or spatial dependency between spots. Here, we developed Hist2ST, a deep learning-based model to predict RNA-seq expression from histology images. Around each sequenced spot, the corresponding histology image is cropped into an image patch and fed into a convolutional module to extract 2D vision features. Meanwhile, the spatial relations with the whole image and neighbored patches are captured through Transformer and graph neural network modules, respectively. These learned features are then used to predict the gene expression by following the zero-inflated negative binomial distribution. To alleviate the impact by the small spatial transcriptomics data, a self-distillation mechanism is employed for efficient learning of the model. By comprehensive tests on cancer and normal datasets, Hist2ST was shown to outperform existing methods in terms of both gene expression prediction and spatial region identification. Further pathway analyses indicated that our model could reserve biological information. Thus, Hist2ST enables generating spatial transcriptomics data from histology images for elucidating molecular signatures of tissues.

Identifying B-cell epitopes using AlphaFold2 predicted structures and pretrained language model.

MOTIVATION: Identifying the B-cell epitopes is an essential step for guiding rational vaccine development and immunotherapies. Since experimental approaches are expensive and time-consuming, many computational methods have been designed to assist B-cell epitope prediction. However, existing sequence-based methods have limited performance since they only use contextual features of the sequential neighbors while neglecting structural information. RESULTS: Based on the recent breakthrough of AlphaFold2 in protein structure prediction, we propose GraphBepi, a novel graph-based model for accurate B-cell epitope prediction. For one protein, the predicted structure from AlphaFold2 is used to construct the protein graph, where the nodes/residues are encoded by ESM-2 learning representations. The graph is input into the edge-enhanced deep graph neural network (EGNN) to capture the spatial information in the predicted 3D structures. In parallel, a bidirectional long short-term memory neural networks (BiLSTM) are employed to capture long-range dependencies in the sequence. The learned low-dimensional representations by EGNN and BiLSTM are then combined into a multilayer perceptron for predicting B-cell epitopes. Through comprehensive tests on the curated epitope dataset, GraphBepi was shown to outperform the state-of-the-art methods by more than 5.5% and 44.0% in terms of AUC and AUPR, respectively. A web server is freely available at http://bio-web1.nscc-gz.cn/app/graphbepi. AVAILABILITY AND IMPLEMENTATION: The datasets, pre-computed features, source codes, and the trained model are available at https://github.com/biomed-AI/GraphBepi.

scAdapt: virtual adversarial domain adaptation network for single cell RNA-seq data classification across platforms and species.

In single cell analyses, cell types are conventionally identified based on expressions of known marker genes, whose identifications are time-consuming and irreproducible. To solve this issue, many supervised approaches have been developed to identify cell types based on the rapid accumulation of public datasets. However, these approaches are sensitive to batch effects or biological variations since the data distributions are different in cross-platforms or species predictions. In this study, we developed scAdapt, a virtual adversarial domain adaptation network, to transfer cell labels between datasets with batch effects. scAdapt used both the labeled source and unlabeled target data to train an enhanced classifier and aligned the labeled source centroids and pseudo-labeled target centroids to generate a joint embedding. The scAdapt was demonstrated to outperform existing methods for classification in simulated, cross-platforms, cross-species, spatial transcriptomic and COVID-19 immune datasets. Further quantitative evaluations and visualizations for the aligned embeddings confirm the superiority in cell mixing and the ability to preserve discriminative cluster structure present in the original datasets.

Metasurface-based Fourier lens fed by compact plasmonic optical antennas for wide-angle beam steering.

A Fourier lens can perform the Fourier transform of an incident wavefront at the focal plane. This paper reports a metasurface-based Fourier lens fed by compact plasmonic optical antennas for wide-angle beam steering. The metasurface, composed of six elements with different configurations covering the 2π phase range, features a large field-of-view (FOV) of ±50°. A novel plasmonic optical antenna for broadside radiation is then designed as the feed source of the metasurface. The proposed antenna has ultra-compact size of 0.77λ × 1.4λ, and achieves a high directivity of 9.6 dB and radiation efficiency of over 80% at the wavelength of 1550 nm. Full-wave simulations are carried out to evaluate the performances of the designed metasurface-assisted beam steering device. The results show that this device can achieve a maximum directivity of 21.5 dB at broadside radiation. Compared to conventional Yagi-Uda antenna feed, a directivity enhancement of about 2.7 dB can be obtained, exhibiting a great superiority of the proposed feed antenna. In addition, a large beam steering range of ±50° can be achieved with an acceptable gain drop of 2.83 dB. With the advantages of wide beam steering range, good radiation characteristics, small footprint, and ease of integration, the proposed metasurface-assisted beam steering device would be a promising candidate for integrated photonic applications, including wireless optical communications, light detection and ranging, and augmented reality.

Bioinspired Metamaterials: Multibands Electromagnetic Wave Adaptability and Hydrophobic Characteristics.

Although various photonic devices inspired by natural materials have been developed, there is no research focusing on multibands adaptability, which is not conducive to the advancement of materials science. Herein, inspired by the moth eye surface model, state-of-the-art hierarchical metamaterials (MMs) used as tunable devices in multispectral electromagnetic-waves (EMWs) frequency range, from microwave to ultraviolet (UV), are designed and prepared. Experimentally, the robust broad bandwidth of microwave absorption greater than 90% (reflection loss (RL) < -10 dB) covering almost entire X and Ku bands (8.04-17.88 GHz) under a deep sub-wavelength thickness (1 mm) is demonstrated. The infrared emissivity is reduced and does not affect the microwave absorption simultaneously, further realizing anti-reflection and camouflage via the strong visible light scattering by the microstructure, and can prevent degradation by reducing the transmittance to less than 10% over the whole near UV band, as well as having hydrophobic abilities. The mechanism explored via simulation model is that topological effects are found in the bio-structure. This discovery points to a pathway for using natural models to overcome physical limits of MMs and has promising prospect in novel photonic materials.

Accurately predicting enzyme functions through geometric graph learning on ESMFold-predicted structures.

Enzymes are crucial in numerous biological processes, with the Enzyme Commission (EC) number being a commonly used method for defining enzyme function. However, current EC number prediction technologies have not fully recognized the importance of enzyme active sites and structural characteristics. Here, we propose GraphEC, a geometric graph learning-based EC number predictor using the ESMFold-predicted structures and a pre-trained protein language model. Specifically, we first construct a model to predict the enzyme active sites, which is utilized to predict the EC number. The prediction is further improved through a label diffusion algorithm by incorporating homology information. In parallel, the optimum pH of enzymes is predicted to reflect the enzyme-catalyzed reactions. Experiments demonstrate the superior performance of our model in predicting active sites, EC numbers, and optimum pH compared to other state-of-the-art methods. Additional analysis reveals that GraphEC is capable of extracting functional information from protein structures, emphasizing the effectiveness of geometric graph learning. This technology can be used to identify unannotated enzyme functions, as well as to predict their active sites and optimum pH, with the potential to advance research in synthetic biology, genomics, and other fields.

Deciphering cell types by integrating scATAC-seq data with genome sequences.

The single-cell assay for transposase-accessible chromatin using sequencing (scATAC-seq) technology provides insight into gene regulation and epigenetic heterogeneity at single-cell resolution, but cell annotation from scATAC-seq remains challenging due to high dimensionality and extreme sparsity within the data. Existing cell annotation methods mostly focus on the cell peak matrix without fully utilizing the underlying genomic sequence. Here we propose a method, SANGO, for accurate single-cell annotation by integrating genome sequences around the accessibility peaks within scATAC data. The genome sequences of peaks are encoded into low-dimensional embeddings, and then iteratively used to reconstruct the peak statistics of cells through a fully connected network. The learned weights are considered as regulatory modes to represent cells, and utilized to align the query cells and the annotated cells in the reference data through a graph transformer network for cell annotations. SANGO was demonstrated to consistently outperform competing methods on 55 paired scATAC-seq datasets across samples, platforms and tissues. SANGO was also shown to be able to detect unknown tumor cells through attention edge weights learned by the graph transformer. Moreover, from the annotated cells, we found cell-type-specific peaks that provide functional insights/biological signals through expression enrichment analysis, cis-regulatory chromatin interaction analysis and motif enrichment analysis.

Imputing spatial transcriptomics through gene network constructed from protein language model.

Image-based spatial transcriptomic sequencing technologies have enabled the measurement of gene expression at single-cell resolution, but with a limited number of genes. Current computational approaches attempt to overcome these limitations by imputing missing genes, but face challenges regarding prediction accuracy and identification of cell populations due to the neglect of gene-gene relationships. In this context, we present stImpute, a method to impute spatial transcriptomics according to reference scRNA-seq data based on the gene network constructed from the protein language model ESM-2. Specifically, stImpute employs an autoencoder to create gene expression embeddings for both spatial transcriptomics and scRNA-seq data, which are used to identify the nearest neighboring cells between scRNA-seq and spatial transcriptomics datasets. According to the neighbored cells, the gene expressions of spatial transcriptomics cells are imputed through a graph neural network, where nodes are genes, and edges are based on cosine similarity between the ESM-2 embeddings of the gene-encoding proteins. The gene prediction uncertainty is further measured through a deep learning model. stImpute was shown to consistently outperform state-of-the-art methods across multiple datasets concerning imputation and clustering. stImpute also demonstrates robustness in producing consistent results that are insensitive to model parameters.

Influence of Retrogression Time on the Fatigue Crack Growth Behavior of a Modified AA7475 Aluminum Alloy.

This paper investigates the effect of retrogression time on the fatigue crack growth of a modified AA7475 aluminum alloy. Tests including tensile strength, fracture toughness, and fatigue limits were performed to understand the changes in properties with different retrogression procedures at 180 °C. The microstructure was characterized using scanning electron microscopy (SEM) and transmission electron microscopy (TEM). The findings indicated that as the retrogression time increased, the yield strength decreased from 508 MPa to 461 MPa, whereas the fracture toughness increased from 48 MPa√m to 63.5 MPa√m. The highest fracture toughness of 63.5 MPa√m was seen after 5 h of retrogression. The measured diameter of η' precipitates increased from 6.13 nm at the retrogression 1 h condition to 6.50 nm at the retrogression 5 h condition. Prolonged retrogression also increased the chance of crack initiation, with slower crack growth rate in the long transverse direction compared to the longitudinal direction. An empirical relationship was established between fracture toughness and the volume fraction of age-hardening precipitates, with increasing number density of precipitates seen with increasing retrogression time.

Anisotropic Composition and Mechanical Behavior of a Natural Thin-Walled Composite: Eagle Feather Shaft.

Flight feather shafts are outstanding bioinspiration templates due to their unique light weight and their stiff and strong characteristics. As a thin wall of a natural composite beam, the keratinous cortex has evolved anisotropic features to support flight. Here, the anisotropic keratin composition, tensile response, dynamic properties of the cortex, and fracture behaviors of the shafts are clarified. The analysis of Fourier transform infrared (FTIR) spectra indicates that the protein composition of calamus cortex is almost homogeneous. In the middle and distal shafts (rachis), the content of the hydrogen bonds (HBs) and side-chain is the highest within the dorsal cortex and is consistently lower within the lateral wall. The tensile responses, including the properties and dominant damage pattern, are correlated with keratin composition and fiber orientation in the cortex. As for dynamic properties, the storage modulus and damping of the cortex are also anisotropic, corresponding to variation in protein composition and fibrous structure. The fracture behaviors of bent shafts include matrix breakage, fiber dissociation and fiber rupture on compressive dorsal cortex. To clarify, 'real-time' damage behaviors, and an integrated analysis between AE signals and fracture morphologies, are performed, indicating that calamus failure results from a straight buckling crack and final fiber rupture. Moreover, in the dorsal and lateral walls of rachis, the matrix breakage initially occurs, and then the propagation of the crack is restrained by 'ligament-like' fiber bundles and cross fiber, respectively. Subsequently, the further matrix breakage, interface dissociation and induced fiber rupture in the dorsal cortex result in the final failure.

Dahl Friction Model for Driving Characteristics of V-Shape Linear Ultrasonic Motors.

The contact process of stator and slider described by the Coulomb friction model is basically in a pure sliding friction state, and a mechanical model based on the Dahl friction theory was proposed to describe the contact process between stator and slider of V-shape linear ultrasonic motor. With consideration for the tangential compliance of stator and slider, the dynamic contact and friction processes of stator and slider were addressed in stages. The simulation results show that the ratio of the friction positive work decreases with the increase of the preload, and the vibration amplitude of the stator increases the proportion of positive work of the friction force. Improving the contact stiffness of the stator and slider is conducive to improving the output performance of the ultrasonic motor. The asymmetry of the left and right performance of the V-shaped vibrator will cause a difference in the left and right running speeds of the ultrasonic motor. The improved Dahl friction-driving model makes up for the discontinuity of tangential contact force calculated by the Coulomb friction model. This study demonstrates that the friction-driving model based on the Dahl theory is reliable and reasonable for linear ultrasonic motors according to the experimental results.

All-plasmonic Optical Phased Array Integrated on a Thin-film Platform.

Optical phased arrays have been demonstrated to enable a variety of applications ranging from high-speed on-chip communications to vertical surface emitting lasers. Despite the prosperities of the researches on optical phased arrays, presently, the reported designs of optical phased arrays are based on silicon photonics while plasmonic-based optical phased arrays have not been demonstrated yet. In this paper, a passive plasmonic optical phased array is proposed and experimentally demonstrated. The beam of the proposed plasmonic optical phased array is steerable in the far-field area and a high directivity can be achieved. In addition, radio frequency phased array theory is demonstrated to be applicable to the description of the coupling conditions of the delocalized surface plasmons in optical phased arrays and thus the gap between the phased arrays at two distinctly different wavelengths can be bridged. The potential applications of the proposed plasmonic phased arrays include on-chip optical wireless nanolinks, optical interconnections and integrated plasmonic lasers.