An Enzyme-Cleavable Solubilizing-Tag Facilitates the Chemical Synthesis of Mirror-Image Proteins.

Mirror-image proteins (D-proteins) are useful in biomedical research for purposes such as mirror-image screening for D-peptide drug discovery, but the chemical synthesis of many D-proteins is often low yielding due to the poor solubility or aggregation of their constituent peptide segments. Here, we report a Lys-C protease-cleavable solubilizing tag and its use to synthesize difficult-to-obtain D-proteins. Our tag is easily installed onto multiple amino acids such as DLys, DSer, DThr, and/or the N-terminal amino acid of hydrophobic D-peptides, is impervious to various reaction conditions, such as peptide synthesis, ligation, desulfurization, and transition metal-mediated deprotection, and yet can be completely removed by Lys-C protease under denaturing conditions to give the desired D-protein. The efficacy and practicality of the new method were exemplified in the synthesis of two challenging D-proteins: D-enantiomers of programmed cell death protein 1 IgV domain and SARS-CoV-2 envelope protein, in high yield. This work demonstrates that the enzymatic cleavage of solubilizing tags under denaturing conditions is feasible, thus paving the way for the production of more D-proteins.

Backbone-Installed Split Intein-Assisted Ligation for the Chemical Synthesis of Mirror-Image Proteins.

Membrane-associated D-proteins are an important class of synthetic molecules needed for D-peptide drug discovery, but their chemical synthesis using canonical ligation methods such as native chemical ligation is often hampered by the poor solubility of their constituent peptide segments. Here, we describe a Backbone-Installed Split Intein-Assisted Ligation (BISIAL) method for the synthesis of these proteins, wherein the native L-forms of the N- and C-intein fragments of the unique consensus-fast (Cfa) (i.e. L-CfaN and L-CfaC ) are separately installed onto the two D-peptide segments to be ligated via a removable backbone modification. The ligation proceeds smoothly at micromolar (µM) concentrations under strongly chaotropic conditions (8.0 M urea), and the subsequent removal of the backbone modification groups affords the desired D-proteins without leaving any "ligation scar" on the products. The effectiveness and practicality of the BISIAL method are exemplified by the synthesis of the D-enantiomers of the extracellular domains of T cell immunoglobulin and ITIM domain (TIGIT) and tropomyosin receptor kinase C (TrkC). The BISIAL method further expands the chemical protein synthesis ligation toolkit and provides practical access to challenging D-protein targets.

Tiny Vehicle Detection for Mid-to-High Altitude UAV Images Based on Visual Attention and Spatial-Temporal Information.

Mid-to-high altitude Unmanned Aerial Vehicle (UAV) imagery can provide important remote sensing information between satellite and low altitude platforms, and vehicle detection in mid-to-high altitude UAV images plays a crucial role in land monitoring and disaster relief. However, the high background complexity of images and limited pixels of objects challenge the performance of tiny vehicle detection. Traditional methods suffer from poor adaptation ability to complex backgrounds, while deep neural networks (DNNs) have inherent defects in feature extraction of tiny objects with finite pixels. To address the issue above, this paper puts forward a vehicle detection method combining the DNNs-based and traditional methods for mid-to-high altitude UAV images. We first employ the deep segmentation network to exploit the co-occurrence of the road and vehicles, then detect tiny vehicles based on visual attention mechanism with spatial-temporal constraint information. Experimental results show that the proposed method achieves effective detection of tiny vehicles in complex backgrounds. In addition, ablation experiments are performed to inspect the effectiveness of each component, and comparative experiments on tinier objects are carried out to prove the superior generalization performance of our method in detecting vehicles with a limited size of 5 × 5 pixels or less.

Chemical Synthesis of a Full-Length G-Protein-Coupled Receptor ß2-Adrenergic Receptor with Defined Modification Patterns at the C-Terminus.

The ß2-adrenergic receptor (ß2AR) is a G-protein-coupled receptor (GPCR) that responds to the hormone adrenaline and is an important drug target in the context of respiratory diseases, including asthma. ß2AR function can be regulated by post-translational modifications such as phosphorylation and ubiquitination at the C-terminus, but access to the full-length ß2AR with well-defined and homogeneous modification patterns critical for biochemical and biophysical studies remains challenging. Here, we report a practical synthesis of differentially modified, full-length ß2AR based on a combined native chemical ligation (NCL) and sortase ligation strategy. An array of homogeneous samples of full-length ß2ARs with distinct modification patterns, including a full-length ß2AR bearing both monoubiquitination and octaphosphorylation modifications, were successfully prepared for the first time. Using these homogeneously modified full-length ß2AR receptors, we found that different phosphorylation patterns mediate different interactions with ß-arrestin1 as reflected in different agonist binding affinities. Our experiments also indicated that ubiquitination can further modulate interactions between ß2AR and ß-arrestin1. Access to full-length ß2AR with well-defined and homogeneous modification patterns at the C-terminus opens a door to further in-depth mechanistic studies into the structure and dynamics of ß2AR complexes with downstream transducer proteins, including G proteins, arrestins, and GPCR kinases.

One-pot multi-segment condensation strategies for chemical protein synthesis.

With the growing requirement for otherwise-difficult-to-obtain proteins, it is necessary to develop more efficient chemical protein synthesis methods for rapid access to designed protein samples. In particular, a one-pot multi-segment condensation method, with only one purification step to obtain the final product, is expected to demonstrate unique benefits in chemical protein synthesis, such as the requirement of fewer handling procedures and the higher efficiency in obtaining aimed protein samples. The utilization of the one-pot multi-segment condensation strategy is demonstrated via the synthesis of a series of post-translational modification (PTM) or disease-associated peptides or proteins for basic and advanced scientific research. This review summarizes the recent one-pot multi-segment condensation methods utilized in chemical protein synthesis, in which two aspects of drive-strategies will be mainly included: a kinetically controlled strategy and a protecting group-removal strategy, respectively. On one hand, the activities of peptides in N-terminal thiol amino acids or C-terminal acyl donors can be largely different based on the differences in properties, such as steric hindrance, migration rates, electrophilicity, and introduction of active elements such as selenium, etc. Using the different activities, regio-selective peptide ligation can be performed in a kinetically controlled manner. On the other hand, the protecting group-removal strategy involves various moieties, which can block the activity of functional groups arising from N-terminal thiol amino acids or C-terminal acyl donors, and they can be removed by using additives, and pH- or photo-stimulation conditions with further achievement of chemical protein synthesis by the one-pot strategy.

Ligation of Soluble but Unreactive Peptide Segments in the Chemical Synthesis of Haemophilus Influenzae DNA Ligase.

During the total chemical synthesis of the water-soluble globular Haemophilus Influenzae DNA ligase (Hin-Lig), we observed the surprising phenomenon of a soluble peptide segment that failed to undergo native chemical ligation. Based on dynamic light scattering and transmission electron microscopy experiments, we determined that the peptide formed soluble colloidal particles in a homogeneous solution containing 6 m guanidine hydrochloride. Conventional peptide performance-improving strategies, such as installation of a terminal/side-chain Arg tag or O-acyl isopeptide, failed to enable the reaction, presumably because of their inability to disrupt the formation of soluble colloidal particles. However, a removable backbone modification strategy recently developed for the synthesis of membrane proteins did disrupt the formation of the colloids, and the desired ligation of this soluble but unreactive system was eventually accomplished. This work demonstrates that an appropriate solution dispersion state, in addition to good peptide solubility, is a prerequisite for successful peptide ligation.

Superpixel-Based Feature for Aerial Image Scene Recognition.

Image scene recognition is a core technology for many aerial remote sensing applications. Different landforms are inputted as different scenes in aerial imaging, and all landform information is regarded as valuable for aerial image scene recognition. However, the conventional features of the Bag-of-Words model are designed using local points or other related information and thus are unable to fully describe landform areas. This limitation cannot be ignored when the aim is to ensure accurate aerial scene recognition. A novel superpixel-based feature is proposed in this study to characterize aerial image scenes. Then, based on the proposed feature, a scene recognition method of the Bag-of-Words model for aerial imaging is designed. The proposed superpixel-based feature that utilizes landform information establishes top-task superpixel extraction of landforms to bottom-task expression of feature vectors. This characterization technique comprises the following steps: simple linear iterative clustering based superpixel segmentation, adaptive filter bank construction, Lie group-based feature quantification, and visual saliency model-based feature weighting. Experiments of image scene recognition are carried out using real image data captured by an unmanned aerial vehicle (UAV). The recognition accuracy of the proposed superpixel-based feature is 95.1%, which is higher than those of scene recognition algorithms based on other local features.

Automatic Modulation Classification Based on Deep Learning for Unmanned Aerial Vehicles.

Deep learning has recently attracted much attention due to its excellent performance in processing audio, image, and video data. However, few studies are devoted to the field of automatic modulation classification (AMC). It is one of the most well-known research topics in communication signal recognition and remains challenging for traditional methods due to complex disturbance from other sources. This paper proposes a heterogeneous deep model fusion (HDMF) method to solve the problem in a unified framework. The contributions include the following: (1) a convolutional neural network (CNN) and long short-term memory (LSTM) are combined by two different ways without prior knowledge involved; (2) a large database, including eleven types of single-carrier modulation signals with various noises as well as a fading channel, is collected with various signal-to-noise ratios (SNRs) based on a real geographical environment; and (3) experimental results demonstrate that HDMF is very capable of coping with the AMC problem, and achieves much better performance when compared with the independent network.

Flexible TAM requirement of TnpB enables efficient single-nucleotide editing with expanded targeting scope.

TnpBs encoded by the IS200/IS605 family transposon are among the most abundant prokaryotic proteins from which type V CRISPR-Cas nucleases may have evolved. Since bacterial TnpBs can be programmed for RNA-guided dsDNA cleavage in the presence of a transposon-adjacent motif (TAM), these nucleases hold immense promise for genome editing. However, the activity and targeting specificity of TnpB in homology-directed gene editing remain unknown. Here we report that a thermophilic archaeal TnpB enables efficient gene editing in the natural host. Interestingly, the TnpB has different TAM requirements for eliciting cell death and for facilitating gene editing. By systematically characterizing TAM variants, we reveal that the TnpB recognizes a broad range of TAM sequences for gene editing including those that do not elicit apparent cell death. Importantly, TnpB shows a very high targeting specificity on targets flanked by a weak TAM. Taking advantage of this feature, we successfully leverage TnpB for efficient single-nucleotide editing with templated repair. The use of different weak TAM sequences not only facilitates more flexible gene editing with increased cell survival, but also greatly expands targeting scopes, and this strategy is probably applicable to diverse CRISPR-Cas systems.

Synchronous Spatiotemporal Graph Transformer: A New Framework for Traffic Data Prediction.

Modeling the spatiotemporal relationship (STR) of traffic data is important yet challenging for existing graph networks. These methods usually capture features separately in temporal and spatial dimensions or represent the spatiotemporal data by adopting multiple local spatial-temporal graphs. The first kind of method mentioned above is difficult to capture potential temporal-spatial relationships, while the other is limited for long-term feature extraction due to its local receptive field. To handle these issues, the Synchronous Spatio-Temporal grAph Transformer (S2TAT) network is proposed for efficiently modeling the traffic data. The contributions of our method include the following: 1) the nonlocal STR can be synchronously modeled by our integrated attention mechanism and graph convolution in the proposed S2TAT block; 2) the timewise graph convolution and multihead mechanism designed can handle the heterogeneity of data; and 3) we introduce a novel attention-based strategy in the output module, being able to capture more valuable historical information to overcome the shortcoming of conventional average aggregation. Extensive experiments are conducted on PeMS datasets that demonstrate the efficacy of the S2TAT by achieving a top-one accuracy but less computational cost by comparing with the state of the art.

SiMaN: Sign-to-Magnitude Network Binarization.

Binary neural networks (BNNs) have attracted broad research interest due to their efficient storage and computational ability. Nevertheless, a significant challenge of BNNs lies in handling discrete constraints while ensuring bit entropy maximization, which typically makes their weight optimization very difficult. Existing methods relax the learning using the sign function, which simply encodes positive weights into +1s, and -1s otherwise. Alternatively, we formulate an angle alignment objective to constrain the weight binarization to {0,+1} to solve the challenge. In this article, we show that our weight binarization provides an analytical solution by encoding high-magnitude weights into +1s, and 0s otherwise. Therefore, a high-quality discrete solution is established in a computationally efficient manner without the sign function. We prove that the learned weights of binarized networks roughly follow a Laplacian distribution that does not allow entropy maximization, and further demonstrate that it can be effectively solved by simply removing the l2 regularization during network training. Our method, dubbed sign-to-magnitude network binarization (SiMaN), is evaluated on CIFAR-10 and ImageNet, demonstrating its superiority over the sign-based state-of-the-arts. Our source code, experimental settings, training logs and binary models are available at https://github.com/lmbxmu/SiMaN.

Learning From Architectural Redundancy: Enhanced Deep Supervision in Deep Multipath Encoder-Decoder Networks.

Deep encoder-decoders are the model of choice for pixel-level estimation due to their redundant deep architectures. Yet they still suffer from the vanishing supervision information issue that affects convergence because of their overly deep architectures. In this work, we propose and theoretically derive an enhanced deep supervision (EDS) method which improves on conventional deep supervision (DS) by incorporating variance minimization into the optimization. A new structure variance loss is introduced to build a bridge between deep encoder-decoders and variance minimization, and provides a new way to minimize the variance by forcing different intermediate decoding outputs (paths) to reach an agreement. We also design a focal weighting strategy to effectively combine multiple losses in a scale-balanced way, so that the supervision information is sufficiently enforced throughout the encoder-decoders. To evaluate the proposed method on the pixel-level estimation task, a novel multipath residual encoder is proposed and extensive experiments are conducted on four challenging density estimation and crowd counting benchmarks. The experimental results demonstrate the superiority of our EDS over other paradigms, and improved estimation performance is reported using our deeply supervised encoder-decoder.

A Survey on Human Cancer Categorization Based on Deep Learning.

In recent years, we have witnessed the fast growth of deep learning, which involves deep neural networks, and the development of the computing capability of computer devices following the advance of graphics processing units (GPUs). Deep learning can prototypically and successfully categorize histopathological images, which involves imaging classification. Various research teams apply deep learning to medical diagnoses, especially cancer diseases. Convolutional neural networks (CNNs) detect the conventional visual features of disease diagnoses, e.g., lung, skin, brain, prostate, and breast cancer. A CNN has a procedure for perfectly investigating medicinal science images. This study assesses the main deep learning concepts relevant to medicinal image investigation and surveys several charities in the field. In addition, it covers the main categories of imaging procedures in medication. The survey comprises the usage of deep learning for object detection, classification, and human cancer categorization. In addition, the most popular cancer types have also been introduced. This article discusses the Vision-Based Deep Learning System among the dissimilar sorts of data mining techniques and networks. It then introduces the most extensively used DL network category, which is convolutional neural networks (CNNs) and investigates how CNN architectures have evolved. Starting with Alex Net and progressing with the Google and VGG networks, finally, a discussion of the revealed challenges and trends for upcoming research is held.

Self-Supervised monocular depth and ego-Motion estimation in endoscopy: Appearance flow to the rescue.

Recently, self-supervised learning technology has been applied to calculate depth and ego-motion from monocular videos, achieving remarkable performance in autonomous driving scenarios. One widely adopted assumption of depth and ego-motion self-supervised learning is that the image brightness remains constant within nearby frames. Unfortunately, the endoscopic scene does not meet this assumption because there are severe brightness fluctuations induced by illumination variations, non-Lambertian reflections and interreflections during data collection, and these brightness fluctuations inevitably deteriorate the depth and ego-motion estimation accuracy. In this work, we introduce a novel concept referred to as appearance flow to address the brightness inconsistency problem. The appearance flow takes into consideration any variations in the brightness pattern and enables us to develop a generalized dynamic image constraint. Furthermore, we build a unified self-supervised framework to estimate monocular depth and ego-motion simultaneously in endoscopic scenes, which comprises a structure module, a motion module, an appearance module and a correspondence module, to accurately reconstruct the appearance and calibrate the image brightness. Extensive experiments are conducted on the SCARED dataset and EndoSLAM dataset, and the proposed unified framework exceeds other self-supervised approaches by a large margin. To validate our framework's generalization ability on different patients and cameras, we train our model on SCARED but test it on the SERV-CT and Hamlyn datasets without any fine-tuning, and the superior results reveal its strong generalization ability. Code is available at: https://github.com/ShuweiShao/AF-SfMLearner.

An Automatic Method for Epileptic Seizure Detection Based on Deep Metric Learning.

Electroencephalography (EEG) is a commonly used clinical approach for the diagnosis of epilepsy which is a life-threatening neurological disorder. Many algorithms have been proposed for the automatic detection of epileptic seizures using traditional machine learning and deep learning. Although deep learning methods have achieved great success in many fields, their performance in EEG analysis and classification is still limited mainly due to the relatively small sizes of available datasets. In this paper, we propose an automatic method for the detection of epileptic seizures based on deep metric learning which is a novel strategy tackling the few-shot problem by mitigating the demand for massive data. First, two one-dimensional convolutional embedding modules are proposed as a deep feature extractor, for single-channel and multichannel EEG signals respectively. Then, a deep metric learning model is detailed along with a stage-wise training strategy. Experiments are conducted on the publicly-available Bonn University dataset which is a benchmark dataset, and the CHB-MIT dataset which is larger and more realistic. Impressive averaged accuracy of 98.60% and specificity of 100% are achieved on the most difficult classification of interictal (subset D) vs ictal (subset E) of the Bonn dataset. On the CHB-MIT dataset, an averaged accuracy of 86.68% and specificity of 93.71% are reached. With the proposed method, automatic and accurate detection of seizures can be performed in real time, and the heavy burden of neurologists can be effectively reduced.

Fast Class-Wise Updating for Online Hashing.

Online image hashing has received increasing research attention recently, which processes large-scale data in a streaming fashion to update the hash functions on-the-fly. To this end, most existing works exploit this problem under a supervised setting, i.e., using class labels to boost the hashing performance, which suffers from the defects in both adaptivity and efficiency: First, large amounts of training batches are required to learn up-to-date hash functions, which leads to poor online adaptivity. Second, the training is time-consuming, which contradicts with the core need of online learning. In this paper, a novel supervised online hashing scheme, termed Fast Class-wise Updating for Online Hashing (FCOH), is proposed to address the above two challenges by introducing a novel and efficient inner product operation. To achieve fast online adaptivity, a class-wise updating method is developed to decompose the binary code learning and alternatively renew the hash functions in a class-wise fashion, which well addresses the burden on large amounts of training batches. Quantitatively, such a decomposition further leads to at least 75 percent storage saving. To further achieve online efficiency, we propose a semi-relaxation optimization, which accelerates the online training by treating different binary constraints independently. Without additional constraints and variables, the time complexity is significantly reduced. Such a scheme is also quantitatively shown to well preserve past information during updating hashing functions. We have quantitatively demonstrated that the collective effort of class-wise updating and semi-relaxation optimization provides a superior performance comparing to various state-of-the-art methods, which is verified through extensive experiments on three widely-used datasets.

Memory Attention Networks for Skeleton-Based Action Recognition.

Skeleton-based action recognition has been extensively studied, but it remains an unsolved problem because of the complex variations of skeleton joints in 3-D spatiotemporal space. To handle this issue, we propose a newly temporal-then-spatial recalibration method named memory attention networks (MANs) and deploy MANs using the temporal attention recalibration module (TARM) and spatiotemporal convolution module (STCM). In the TARM, a novel temporal attention mechanism is built based on residual learning to recalibrate frames of skeleton data temporally. In the STCM, the recalibrated sequence is transformed or encoded as the input of CNNs to further model the spatiotemporal information of skeleton sequence. Based on MANs, a new collaborative memory fusion module (CMFM) is proposed to further improve the efficiency, leading to the collaborative MANs (C-MANs), trained with two streams of base MANs. TARM, STCM, and CMFM form a single network seamlessly and enable the whole network to be trained in an end-to-end fashion. Comparing with the state-of-the-art methods, MANs and C-MANs improve the performance significantly and achieve the best results on six data sets for action recognition. The source code has been made publicly available at https://github.com/memory-attention-networks.

A multi-scale unsupervised learning for deformable image registration.

PURPOSE: Image registration is a fundamental task in the area of image processing, and it is critical to many clinical applications, e.g., computer-assisted surgery. In this work, we attempt to design an effective framework that gains higher accuracy at a minimal cost of the invertibility of registration field. METHODS: A hierarchically aggregated transformation (HAT) module is proposed. Within each HAT module, we connect multiple convolutions in a hierarchical manner to capture the multi-scale context, enabling small and large displacements between a pair of images to be taken into account simultaneously during the registration process. Besides, an adaptive feature scaling (AFS) mechanism is presented to refine the multi-scale feature maps derived from the HAT module by rescaling channel-wise features in the global receptive field. Based on the HAT module and AFS mechanism, we establish an efficacious and efficient unsupervised deformable registration framework. RESULTS: The devised framework is validated on the dataset of SCARED and MICCAI Instrument Segmentation and Tracking Challenge 2015, and the experimental results demonstrate that our method achieves better registration accuracy with fewer number of folding pixels than three widely used baseline approaches of SyN, NiftyReg and VoxelMorph. CONCLUSION: We develop a novel method for unsupervised deformable image registration by incorporating the HAT module and AFS mechanism into the framework, which provides a new way to obtain a desirable registration field between a pair of images.

iffDetector: Inference-Aware Feature Filtering for Object Detection.

Modern convolutional neural network (CNN)-based object detectors focus on feature configuration during training but often ignore feature optimization during inference. In this article, we propose a new feature optimization approach to enhance features and suppress background noise in both the training and inference stages. We introduce a generic inference-aware feature filtering (IFF) module that can be easily combined with existing detectors, resulting in our iffDetector. Unlike conventional open-loop feature calculation approaches without feedback, the proposed IFF module performs the closed-loop feature optimization by leveraging high-level semantics to enhance the convolutional features. By applying the Fourier transform to analyze our detector, we prove that the IFF module acts as a negative feedback that can theoretically guarantee the stability of the feature learning. IFF can be fused with CNN-based object detectors in a plug-and-play manner with little computational cost overhead. Experiments on the PASCAL VOC and MS COCO datasets demonstrate that our iffDetector consistently outperforms state-of-the-art methods with significant margins.

A Well-Conserved Archaeal B-Family Polymerase Functions as an Extender in Translesion Synthesis.

B-family DNA polymerases (PolBs) of different groups are widespread in Archaea, and different PolBs often coexist in the same organism. Many of these PolB enzymes remain to be investigated. One of the main groups that is poorly characterized is PolB2, whose members occur in many archaea but are predicted to be inactivated forms of DNA polymerase. Here, Sulfolobus islandicus DNA polymerase 2 (Dpo2), a PolB2 enzyme, was expressed in its native host and purified. Characterization of the purified enzyme revealed that the polymerase possesses a robust nucleotide incorporation activity but is devoid of the 3'-5' exonuclease activity. Enzyme kinetics analyses showed that Dpo2 replicates undamaged DNA templates with high fidelity, which is consistent with its inefficient nucleotide insertion activity opposite different DNA lesions. Strikingly, the polymerase is highly efficient in extending mismatches and mispaired primer termini once a nucleotide is placed opposite a damaged site. This extender polymerase represents a novel type of prokaryotic PolB specialized for DNA damage repair in Archaea. IMPORTANCE In this work, we report that Sulfolobus islandicus Dpo2, a B-family DNA polymerase once predicted to be an inactive form, is a bona fide DNA polymerase functioning in translesion synthesis. S. islandicus Dpo2 is a member of a large group of B-family DNA polymerases (PolB2) that are present in many archaea and some bacteria, and they carry variations in well-conserved amino acids in the functional domains responsible for polymerization and proofreading. However, we found that this prokaryotic B-family DNA polymerase not only replicates undamaged DNA with high fidelity but also extends mismatch and DNA lesion-containing substrates with high efficiencies. With these data, we propose this enzyme functions as an extender polymerase, the first prokaryotic enzyme of this type. Our data also suggest this PolB2 enzyme represents a functional counterpart of the eukaryotic DNA polymerase Pol zeta, an enzyme that is devoted to DNA damage repair.