Recent surge of Convolutional Neural Networks (CNNs) has brought successes among various applications. However, these successes are accompanied by a significant increase in computational cost and the ...demand for computational resources, which critically hampers the utilization of complex CNNs on devices with limited computational power. In this work, we propose a feature representation based layer-wise pruning method that aims at reducing complex CNNs to more compact ones with equivalent performance. Different from previous parameter pruning methods that conduct connection-wise or filter-wise pruning based on weight information, our method determines redundant parameters by investigating the features learned in the convolutional layers and the pruning process is operated at a layer level. Experiments demonstrate that the proposed method is able to significantly reduce computational cost and the pruned models achieve equivalent or even better performance compared to the original models on various datasets.
The electrolyte additive plays an important role in determining the crucial properties of batteries such as cycling stability and safety. Compared to material development, research on electrolyte and ...interphase is still in the early stage for sodium ion batteries (SIBs). Herein, for the first time, succinic anhydride (SA) is investigated as a synergistic filming additive to fluoroethylene carbonate (FEC), and the lifespan of the dual‐additive Na/Na0.6Li0.15Ni0.15Mn0.55Cu0.15O2 (NLNMC) cell is significantly improved, maintaining capacity retention of 87.2% over 400 cycles at 1 C rate. For comparison, the batteries with only one of the two additives or without any additive show much inferior electrochemical performance. After the addition of SA, the interphase layer on the surface of cycled NLNMC material becomes uniform and stable, which contains more oxygen‐rich organic species and less NaF. Additionally, the addition of SA also has an impact on the interphase layer in the sodium anode part as indicated by electrochemical impedance spectroscopy (EIS) and energy dispersive spectrometer (EDS) results. Moreover, the online differential electrochemical mass spectrometry (OEMS) tests show the dual‐additive cell has less CO2 generation during the initial two cycles compared to that with only FECs which demonstrates another advantage of SA for practical application.
For the first time, succinic anhydride (SA) is applied as a synergistic electrolyte additive for fluoroethylene carbonate (FEC) in sodium ion batteries. The coexistence of SA and FEC regulates the interphase layer both on the cathode and anode. Optimized electrochemical performance of Na/Na0.6Li0.15Ni0.15Mn0.55Cu0.15O2 (NLNMC) is achieved in the dual‐additive cell with 87.2% of capacity retention after 400 cycles at a 1 C rate.
Herein, we describe an energy balance strategy between fluorescence and photoacoustic effects by sulfur substitution to transform existing hemicyanine dyes (Cy) into optimized NIRF/PA dual ...ratiometric scaffolds. Based on this optimized scaffold, we reported the first dual‐ratio response of nitroreductase probe AS‐Cy‐NO2, which allows quantitative visualization of tumor hypoxia in vivo. AS‐Cy‐NO2, composed of a new NIRF/PA scaffold thioxanthene‐hemicyanine (AS‐Cy‐1) and a 4‐nitrobenzene moiety, showed a 10‐fold ratiometric NIRF enhancement (I773/I733) and 2.4‐fold ratiometric PA enhancement (PA730/PA670) upon activation by a biomarker (nitroreductase, NTR) associated with tumor hypoxia. Moreover, the dual ratiometric NIRF/PA imaging accurately quantified the hypoxia extent with high sensitivity and high imaging depth in xenograft breast cancer models. More importantly, the 3D maximal intensity projection (MIP) PA images of the probe can precisely differentiate the highly heterogeneous oxygen distribution in solid tumor. Thus, this study provides a promising NIRF/PA scaffold that may be generalized for the dual ratiometric imaging of other disease‐relevant biomarkers.
We have described a general energy balance approach by sulfur substitution to transform existing hemicyanine dyes (Cy) into optimized NIRF/PA dual ratiometric scaffolds. Based on this optimized platform, the first dual‐ratio NIRF/PA response probe AS‐Cy‐NO2 was designed for quantitatively and precisely monitoring of tumor hypoxia levels in vivo.
Antibody-drug conjugate (ADC) is typically composed of a monoclonal antibody (mAbs) covalently attached to a cytotoxic drug via a chemical linker. It combines both the advantages of highly specific ...targeting ability and highly potent killing effect to achieve accurate and efficient elimination of cancer cells, which has become one of the hotspots for the research and development of anticancer drugs. Since the first ADC, Mylotarg
(gemtuzumab ozogamicin), was approved in 2000 by the US Food and Drug Administration (FDA), there have been 14 ADCs received market approval so far worldwide. Moreover, over 100 ADC candidates have been investigated in clinical stages at present. This kind of new anti-cancer drugs, known as "biological missiles", is leading a new era of targeted cancer therapy. Herein, we conducted a review of the history and general mechanism of action of ADCs, and then briefly discussed the molecular aspects of key components of ADCs and the mechanisms by which these key factors influence the activities of ADCs. Moreover, we also reviewed the approved ADCs and other promising candidates in phase-3 clinical trials and discuss the current challenges and future perspectives for the development of next generations, which provide insights for the research and development of novel cancer therapeutics using ADCs.
In CASP15, we used an integrated hierarchical and hybrid approach to predict RNA structures. The approach involves three steps. First, with the use of physics‐based methods, Vfold2D‐MC and VfoldMCPX, ...we predict the 2D structures from the sequence. Second, we employ template‐based methods, Vfold3D and VfoldLA, to build 3D scaffolds for the predicted 2D structures. Third, using the 3D scaffolds as initial structures and the predicted 2D structures as constraints, we predict the 3D structure from coarse‐grained molecular dynamics simulations, IsRNA and RNAJP. Our approach was evaluated on 12 RNA targets in CASP15 and ranked second among all the 34 participating teams. The result demonstrated the reliability of our method in predicting RNA 2D structures with high accuracy and RNA 3D structures with moderate accuracy. Further improvements in RNA structure prediction for the next round of CASP may come from the incorporation of the physics‐based method with machine learning techniques.
With the expansion of college enrollment, college graduates have continued to expand, and the employment situation has become more and more severe. As a new form of employment, innovation and ...entrepreneurship are becoming more and more important in college teaching. Entrepreneurial success is crucial. This paper proposes an entropy-based active learning method (ALPCS), which is divided into three stages: selection, exploration, and consolidation. The main contents are as follows: in the selection stage, the fuzzy c-means algorithm is used to obtain the membership of all samples, then calculate their Shannon entropy, and finally, select the sample with large Shannon entropy to generate an information subset (the larger the Shannon entropy, the greater the uncertainty, and the more information it contains). The distance-first strategy actively selects samples from the information subset to construct a cluster skeleton cluster. If it is equal to the real number of clusters, it enters the consolidation phase; otherwise, the active learning method stops. In the consolidation phase, sequentially from the information, the nonskeleton set points with the largest uncertainty are selected in the subset to form queries with the points in the skeleton set until the must-link constraint is formed. In this stage, the principle of minimum symmetric relative entropy first is used to reduce the number of queries. The ALPCS algorithm is compared and evaluated, and the final experimental results show that the ALPCS algorithm has a good performance when the number of queries is large.
This paper proposes a novel approach to person re-identification, a fundamental task in distributed multi-camera surveillance systems. Although a variety of powerful algorithms have been presented in ...the past few years, most of them usually focus on designing hand-crafted features and learning metrics either individually or sequentially. Different from previous works, we formulate a unified deep ranking framework that jointly tackles both of these key components to maximize their strengths. We start from the principle that the correct match of the probe image should be positioned in the top rank within the whole gallery set. An effective learning-to-rank algorithm is proposed to minimize the cost corresponding to the ranking disorders of the gallery. The ranking model is solved with a deep convolutional neural network (CNN) that builds the relation between input image pairs and their similarity scores through joint representation learning directly from raw image pixels. The proposed framework allows us to get rid of feature engineering and does not rely on any assumption. An extensive comparative evaluation is given, demonstrating that our approach significantly outperforms all the state-of-the-art approaches, including both traditional and CNN-based methods on the challenging VIPeR, CUHK-01, and CAVIAR4REID datasets. In addition, our approach has better ability to generalize across datasets without fine-tuning.
With rapid advances in computer algorithms and hardware, fast and accurate virtual screening has led to a drastic acceleration in selecting potent small molecules as drug candidates. Computational ...modeling of RNA‐small molecule interactions has become an indispensable tool for RNA‐targeted drug discovery. The current models for RNA–ligand binding have mainly focused on the docking‐and‐scoring method. Accurate docking and scoring should tackle four crucial problems: (1) conformational flexibility of ligand, (2) conformational flexibility of RNA, (3) efficient sampling of binding sites and binding poses, and (4) accurate scoring of different binding modes. Moreover, compared with the problem of protein–ligand docking, predicting ligand binding to RNA, a negatively charged polymer, is further complicated by additional effects such as metal ion effects. Thermodynamic models based on physics‐based and knowledge‐based scoring functions have shown highly encouraging success in predicting ligand binding poses and binding affinities. Recently, kinetic models for ligand binding have further suggested that including dissociation kinetics (residence time) in ligand docking would result in improved performance in estimating in vivo drug efficacy. More recently, the rise of deep‐learning approaches has led to new tools for predicting RNA‐small molecule binding. In this review, we present an overview of the recently developed computational methods for RNA–ligand docking and their advantages and disadvantages.
This article is categorized under:
Structure and Mechanism > Computational Biochemistry and Biophysics
RNA‐targeted drug discovery requires the synergy of enhanced sampling and accurate scoring with fast computational speed. The distinct aspects of RNA–ligand docking compared to protein–ligand docking pose unique challenges, which demand a new generation of molecular docking models. This review presents an overview of recently developed RNA–ligand molecular docking methods for RNA‐targeted drug discovery.