Search

It is imperative to identify the network of residues essential to the allosteric coupling for the purpose of rationally engineering allostery in proteins. Deep mutational scanning analysis has emerged as a function-centric approach for identifying such allostery hotspots in a comprehensive and unbiased fashion, leading to observations that challenge our understanding of allostery at the molecular level. Specifically, a recent deep mutational scanning study of the tetracycline repressor (TetR) revealed an unexpectedly broad distribution of allostery hotspots throughout the protein structure. Using extensive molecular dynamics simulations (up to 50 μs) and free energy computations, we establish the molecular and energetic basis for the strong anti-cooperativity between the ligand and DNA binding sites. The computed free energy landscapes in different ligation states illustrate that allostery in TetR is well described by a conformational selection model, in which the apo state samples a broad set of conformations, and specific ones are selectively stabilized by either ligand or DNA binding. By examining a range of structural and dynamic properties of residues at both local and global scales, we observe that various analyses capture different subsets of experimentally identified hotspots, suggesting that these residues modulate allostery in distinct ways. These results motivate the development of a thermodynamic model that qualitatively explains the broad distribution of hotspot residues and their distinct features in molecular dynamics simulations. The multi-faceted strategy that we establish here for hotspot evaluations and our insights into their mechanistic contributions are useful for modulating protein allostery in mechanistic and engineering studies.

Numerical simulation of fluid is a great challenge as it contains extremely complicated variations with a high Reynolds number. Usually, very high-resolution grids are required to capture the very fine changes during the physical process of the fluid to achieve accurate simulation, which will result in a vast number of computations. This issue will continue to be a bottleneck problem until a deep-learning solution is proposed to utilize large-scale grids with adaptively adjusted coefficients during the spatial discretization procedure—instead of traditional methods that adopt small grids with fixed coefficients—so that the computation cost is dramatically reduced and accuracy is preserved. This breakthrough will represent a significant improvement in the numerical simulation of fluid. However, previously proposed deep-learning-based methods always predict the coefficients considering only the spatial correlation among grids, which provides relatively limited context and thus cannot sufficiently describe patterns along the temporal dimension, implying that the spatiotemporal correlation of coefficients is not well learned. We propose the time-sequence-involved space discretization neural network (TSI-SD) to extract grid correlations from spatial and temporal views together to address this problem. This novel deep neural network is transformed from a classic CONV-LSTM backbone with careful modification by adding temporal information into two-dimensional spatial grids along the x-axis and y-axis separately at the first step and then fusing them through a post-fusion neural network. After that, we combine the TSI-SD with the finite volume format as an advection solver for passive scalar advection in a two-dimensional unsteady flow. Compared with previous methods that only consider spatial context, our method can achieve higher simulation accuracy, while computation is also decreased as we find that after adding temporal data, one of the input features, the concentration field, is redundant and should no longer be adopted during the spatial discretization procedure, which results in a sharp decrease of parameter scale and achieves high efficiency. Comprehensive experiments, including a comparison with SOTA methods and sufficient ablation studies, were carried out to verify the accurate and efficient performance and highlight the advantages of the proposed method.

Automatic vessel segmentation in the fundus images plays an important role in the screening, diagnosis, treatment, and evaluation of various cardiovascular and ophthalmologic diseases. However, due to the limited well-annotated data, varying size of vessels, and intricate vessel structures, retinal vessel segmentation has become a long-standing challenge. In this paper, a novel deep learning model called AACA-MLA-D-UNet is proposed to fully utilize the low-level detailed information and the complementary information encoded in different layers to accurately distinguish the vessels from the background with low model complexity. The architecture of the proposed model is based on U-Net, and the dropout dense block is proposed to preserve maximum vessel information between convolution layers and mitigate the over-fitting problem. The adaptive atrous channel attention module is embedded in the contracting path to sort the importance of each feature channel automatically. After that, the multi-level attention module is proposed to integrate the multi-level features extracted from the expanding path, and use them to refine the features at each individual layer via attention mechanism. The proposed method has been validated on the three publicly available databases, i.e. the DRIVE, STARE, and CHASE _ DB1. The experimental results demonstrate that the proposed method can achieve better or comparable performance on retinal vessel segmentation with lower model complexity. Furthermore, the proposed method can also deal with some challenging cases and has strong generalization ability.

Background: Chronic postsurgical pain is a significant detriment to postsurgical recovery. Previous studies have shown that nitrous oxide may produce long-term analgesia and may benefit the prevention of chronic postsurgical pain in Asian patients. We tested the hypothesis that nitrous oxide is a protective factor against chronic pain after thoracoscopic lobectomy. Methods: Two groups of patients with and without nitrous oxide inhalation during video-assisted thoracic surgery in Peking Union Medical College Hospital were recruited. Perioperative information was documented, and postsurgical pain was followed up by telephone. The primary outcome was the presence of chronic postsurgical pain at 6 months postoperatively. Odds ratios and their 95% confidence intervals were estimated using a multivariate logistic regression model adjusted for relevant confounding factors. Results: A total of 833 patients were eligible, among whom 33.6% were male and 66.4% were female, with an average age of 56.3 ±11.1 years. A total of 387 (46.5%) patients reported incision-related pain at 6 months after surgery, and 160 (40.0%) out of 400 patients with nitrous oxide inhalation during surgery and 227 (52.4%) out of 433 patients without nitrous oxide inhalation during surgery developed chronic postsurgical pain. After adjusting for confounding factors, nitrous oxide inhalation during surgery was associated with lower odds of chronic postsurgical pain (OR=0.654; 95% CI, 0.480–0.890, P=0.007). Conclusions: Nitrous oxide inhalation during surgery was associated with lower odds of CPSP in VATS patients, and nitrous oxide may benefit the management of chronic pain related to thoracoscopic surgery. Trial registration: This study was registered in ClinicalTrials.gov on January 1, 2018, with registration number of NCT03363672.

Music copyright infringement lawsuits implicate millions of dollars in damages and costs of litigation. There are, however, few objective measures by which to evaluate these claims. Recent music information retrieval research has proposed objective algorithms to automatically detect musical similarity, which might reduce subjectivity in music copyright infringement decisions, but there remains minimal relevant perceptual data despite its crucial role in copyright law. We collected perceptual data from 51 participants for 40 adjudicated copyright cases from 1915-2018 in 7 legal jurisdictions (USA, UK, Australia, New Zealand, Japan, People’s Republic of China, and Taiwan). Each case was represented by three different versions: either full audio, melody only (MIDI), or lyrics only (text). Due to the historical emphasis in legal opinions on melody as the key criterion for deciding infringement, we originally predicted that listening to melody-only versions would result in perceptual judgments that more closely matched actual past legal decisions. However, as in our preliminary study of 17 court decisions (Yuan et al., 2020), our results did not match these predictions. Participants listening to full audio outperformed not only the melody-only condition, but also automated algorithms designed to calculate musical similarity (with maximal accuracy of 83% vs. 75%, respectively). Meanwhile, lyrics-only conditions performed at chance levels. Analysis of outlier cases suggests that music, lyrics, and contextual factors can interact in complex ways difficult to capture using quantitative metrics. We propose directions for further investigation including using larger and more diverse samples of cases, enhanced methods, and adapting our perceptual experiment method to avoid relying on ground truth data only from court decisions (which may be subject to errors and selection bias). Our results contribute data and methods to inform practical debates relevant to music copyright law throughout the world, such as the question of whether, and the extent to which, judges and jurors should be allowed to hear published sound recordings of the disputed works in determining musical similarity. Our results ultimately suggest that while automated algorithms are unlikely to replace human judgments, they may help to supplement them.

In this study, the Al2O3/ZrO2 supersaturated solid solution powders with different ZrO2 contents were successfully synthesized by a novel combustion synthesis combined with water cooling (CS-WC) method. The solid solubility and formation mechanism of solid solution under the extremely non-equilibrium solidification condition were discussed in details. The ultra-high cooling rate greatly improves the solubility limit of Al2O3 in ZrO2. When ZrO2 content is 30 mol%, the Al2O3 has been almost dissolved into the ZrO2 lattice. The formation mechanism of solid solution can be attributed to solute interception caused by the huge degree of supercooling. During the sintering process, the solid solution powders precipitate ZrO2 particles and the Al2O3 matrix, which forms a fine and uniform nanostructure. Due to the synergistic effect of t-m phase transformation toughening and ZrO2 nanoparticles toughening, the Al2O3/ZrO2 nanoceramics exhibit excellent mechanical properties when ZrO2 contents are at the range of 25–37 mol%.

Al2O3/ZrO2 supersaturated solid solution micro-powders (AZ-SSP) with three components were successfully obtained by combustion synthesis assisted rapid water cooling, and their nanoprecipitation mechanism and microstructure evolution were studied by phase field simulation and hot-press sintering. The results show that AZ-SSP could be used to fabricate Al2O3/ZrO2 nanocomposite ceramics (AZNC) with intragranular-intercrystalline microstructures by high-density nanoprecipitation, consistent with microstructures of heat-treated AZ-SSP via the phase field simulation. There were three simulated nanostructures of spherical and elongated particles in A57Z-SSP or A15Z-SSP and interlocking structures in A36Z-SSP. The submicro-crystals of A57ZNC and A15ZNC contain high-density nano- and supra-nano-particles, and the fracture toughness of these two ceramics can reach up to 10.37 ± 0.37 MPa·m1/2 and 12.63 ± 0.36 MPa·m1/2, respectively. Hence, the preparation method of ultra-fine structures by supersaturated solid solution has far-reaching guiding significance for various nanoceramics.

Tool wear will reduce workpieces’ quality and accuracy. In this paper, the vibration signals of the milling process were analyzed, and it was found that historical fluctuations still have an impact on the existing state. First of all, the linear fractional alpha-stable motion (LFSM) was investigated, along with a differential iterative model with it as the noise term is constructed according to the fractional-order Ito formula; the general solution of this model is derived by semimartingale approximation. After that, for the chaotic features of the vibration signal, the time-frequency domain characteristics were extracted using principal component analysis (PCA), and the relationship between the variation of the generalized Hurst exponent and tool wear was established using multifractal detrended fluctuation analysis (MDFA). Then, the maximum prediction length was obtained by the maximum Lyapunov exponent (MLE), which allows for analysis of the vibration signal. Finally, tool condition diagnosis was carried out by the evolving connectionist system (ECoS). The results show that the LFSM iterative model with semimartingale approximation combined with PCA and MDFA are effective for the prediction of vibration trends and tool condition. Further, the monitoring of tool condition using ECoS is also effective.

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.

Machine Learning has been studied worldwide for its functions in data science and artificial intelligence (AI) fields. Previous works have shown the excellent performance of machine learning methods in image classification. This paper uses various machine learning methods for fashion product classification. This paper aims to analyze the result of predictions for all classes and the first three ranked classes, and meanwhile, compare and discuss Support Vector Machine (SVM), K Nearest Neighbor (KNN), Convolution Neural Network (CNN), Contrastive Language-Image Pre-training (CLIP) methods’ performance. The results show that the F-Score is increased if just predicted for the first three ranked classes, and among SVM, KNN, and CNN models, CNN is the best in both conditions. From the performance of all four models, CLIP was the best model with better learning ability. Besides, the results suggest that an imbalanced dataset may harm predictions, and the CLIP method yields the best result. In the future, CLIP methods may be more likely recommended in an image classification problem with lots of classes, and an imbalanced dataset adjusted will provide new insights into unsolved and unimproved classification problems.

This study adopted the combination of activated sludge treatment and catalytic ozonation technology to efficiently remove the high concentration of ammonia nitrogen from landfill leachate. Through optimizing the parameters continuously, the COD, NH

Allostery is a fundamental regulatory mechanism of protein function. Despite notable advances, understanding the molecular determinants of allostery remains an elusive goal. Our current knowledge of allostery is principally shaped by a structure-centric view which makes it difficult to understand the decentralized character of allostery. We present a function-centric approach using deep mutational scanning to elucidate the molecular basis and underlying functional landscape of allostery. We show that allosteric signaling exhibits a high-degree of functional plasticity and redundancy through myriad mutational pathways. Residues critical for allosteric signaling are surprisingly poorly conserved while those required for structural integrity are highly conserved, suggesting evolutionary pressure to preserve fold over function. Our results suggest multiple solutions to the thermodynamic conditions of cooperativity, in contrast to the common view of a finely-tuned allosteric residue network maintained under selection.

The low fracture toughness of equiaxed nanocrystalline ceramics is the main bottleneck of its wide range of commercial applications. Here, the authors report a method to overcome this limitation for preparing ultra-tough nanoceramics from using amorphous and supersaturated Al

Blocking PD-1/PD-L1 signaling transforms cancer therapy and is assumed to unleash exhausted tumor-reactive CD8

Alumina toughened zirconia (ATZ) nanoceramics with high-strength, high-toughness and high-hardness were prepared by in-situ nanoprecipitation from solid solution micro-powders. The submicron Al2O3 (~ 450 nm) and ZrO2 (~ 350 nm) grains contained low-density precipitated nano-ZrO2 (~ 40 nm) and nano-Y4Al2O9 (YAM, ~ 90 nm) particles, respectively, making high-performance nano-ATZ ceramics with ultrafine intracrystalline nanostructure yet achieved. There was a parallel or eutectic lattice orientation relationship between the submicrocrystals and its internal nanoparticles of their crystal planes, which is very conducive to the improvement of the mechanical properties of nano-ATZ ceramics. The fracture toughness and hardness of 30wt%Al2O3/70wt%ZrO2(3mol%Y2O3) can be as high as 5.68 ± 0.17 MPa·m1/2 (single-edge V-notched beam method, SEVNB) and 16.32 ± 0.45 GPa, respectively, which are improved by ~ 25 % and ~ 20 % compared with those of 3Y-TZP ceramics. Therefore, this method can be used to prepare nano-ATZ ceramics contained ultrafine nanoparticles and uniform distribution of Al2O3 phases.

To meet the demand for ever-increasing energy storage and conversion, it is most important to fabricate high-performance electrodes by matching the electrode materials to nanostructural design. In this research, for the first time, unique hierarchical NiSe@Co2(CO3)(OH)2 heterogeneous nanowire arrays were successfully constructed onto the nickel foam by a simple two-step soft-chemical approach for application as electrodes of supercapacitors. NiSe nanowires with superior conductivity were designed for builting in situ onto the Ni foam to exert their electrochemical properties, and more importantly, to serve as a bridge for high-speed electron transport between the electroactive material and the current collector. Furthermore, Co2(CO3)(OH)2 nanowires were horizontally constructed onto a vertical NiSe precursor to form a 1-D heterostructure, which provided more electrochemically active sites and significantly increased the space utilization of the current collector surface. In particular, abundant pores and heterogeneous interfaces existed in the heterogeneous network that were composed of interlaced nanowires, which worked well with the inherently superior conductivity of the selenide material to provide a fast dual-channel for electrolyte penetration and electron transportation. Moreover, the hierarchical electrode achieved an outstanding areal specific capacitance of 9.56 F cm−2 (at 4 mA cm−2) and a rare capacitance retention of 68.1% (current density increased from 4 to 80 mA cm−2). A hybrid supercapacitor of NiSe@Co2(CO3)(OH)2//AC was assembled and exhibited competitive energy density and power density, confirming its potential as a promising electrode for next-generation electrochemical energy storage.

An essential yet challenging issue in crowd counting is the diverse background variations under complicated real-life environments, which makes attention based methods favorable in recent years. However, most existing methods only rely on first-order attention schemes (e.g. 2D position-wise attention), while ignoring the higher-order information within the congested scenes completely. In this paper, we propose a hybrid attention-aware network (HANet) with a high-order attention module (HAM) and an adaptive compensation loss (ACLoss) to tackle this problem. On the one hand, the HAM applies 3D attention to capture the subtle discriminative features around each people in the crowd. On the other hand, with the distributed supervision, the ACLoss exploits the prior knowledge from higher-level stages to guide the density map prediction at a lower level. The proposed HANet is then established with HAM and ACLoss working as different roles and promoting each other. Extensive experimental results show the superiority of our HANet against the state-of-the-arts on three challenging benchmarks.

Music copyright lawsuits often result in multimillion dollar damage awards or settlements, yet there are few objective guidelines for applying copyright law in in-fringement claims involving musical works. Recent re-search has attempted to develop objective methods based on automated similarity algorithms, but there remains almost no data on the role of perceived similarity in mu-sic copyright decisions despite its crucial role in copy-right law. We collected perceptual data from 20 partici-pants for 17 adjudicated copyright cases from the USA and Japan after editing the disputed sections to contain either full audio, melody only, or lyrics only. Due to the historical emphasis in legal opinions on melody as the key criterion for deciding infringement, we predicted that listening to melody-only versions would result in percep-tual judgements that more closely matched actual past legal decisions. Surprisingly, however, we found no sig-nificant differences between the three conditions, with participants matching past decisions in between 50-60% of cases in all three conditions. Automated algorithms designed to calculate melodic and audio similarity pro-duced comparable results: both algorithms were able to match past decisions with identical accuracy of 71% (12/17 cases). Analysis of cases that were difficult to classify suggests that melody, lyrics, and other factors sometimes interact in complex ways difficult to capture using quantitative metrics. We propose directions for fur-ther investigation of the role of similarity in music copy-right law using larger and more diverse samples of cases and enhanced methods, and adapting our perceptual ex-periment method to avoid relying for ground truth data only on court decisions (which may be subject to selec-tion bias). Our results contribute to important practical debates, such as whether jury members should be allowed to listen to full audio recordings during copyright cases.

Music copyright lawsuits often result in multimillion dollar damage awards or settlements, yet there are few objective guidelines for applying copyright law in infringement claims involving musical works. Recent re-search has attempted to develop objective methods based on automated similarity algorithms, but there remains almost no data on the role of perceived similarity in mu-sic copyright decisions despite its crucial role in copy-right law. We collected perceptual data from 20 participants for 17 adjudicated copyright cases from the USA and Japan after editing the disputed sections to contain either full audio, melody only, or lyrics only. Due to the historical emphasis in legal opinions on melody as the key criterion for deciding infringement, we predicted that listening to melody-only versions would result in perceptual judgements that more closely matched actual past legal decisions. Surprisingly, however, we found no significant differences between the three conditions, with participants matching past decisions in between 50-60% of cases in all three conditions. Automated algorithms designed to calculate melodic and audio similarity produced comparable results: both algorithms were able to match past decisions with identical accuracy of 71% (12/17 cases). Analysis of cases that were difficult to classify suggests that melody, lyrics, and other factors sometimes interact in complex ways difficult to capture using quantitative metrics. We propose directions for further investigation of the role of similarity in music copy-right law using larger and more diverse samples of cases and enhanced methods, and adapting our perceptual experiment method to avoid relying for ground truth data only on court decisions (which may be subject to selection bias). Our results contribute to important practical debates, such as whether jury members should be allowed to listen to full audio recordings during copyright cases.

In recent saliency detection research, many graph-based algorithms have applied boundary priors as background queries, which may generate completely "reversed" saliency maps if the salient objects are on the image boundaries. Moreover, these algorithms usually depend heavily on pre-processed superpixel segmentation, which may lead to notable degradation in image detail features. In this paper, a novel saliency detection method is proposed to overcome the above issues. First, we propose a saliency reversion correction process, which locates and removes the boundary-adjacent foreground superpixels, and thereby increases the accuracy and robustness of the boundary prior-based saliency estimations. Second, we propose a regularized random walk ranking model, which introduces prior saliency estimation to every pixel in the image by taking both region and pixel image features into account, thus leading to pixel-detailed and superpixel-independent saliency maps. Experiments are conducted on four well-recognized data sets; the results indicate the superiority of our proposed method against 14 state-of-the-art methods, and demonstrate its general extensibility as a saliency optimization algorithm. We further evaluate our method on a new data set comprised of images that we define as boundary adjacent object saliency, on which our method performs better than the comparison methods.

The organic conductive membrane was prepared by polymerization of 3.4-ethylene dioxythiophene (EDOT) on a PVDF membrane surface via chemical vapor deposition. After modification, the sheet resistance of the organic membrane was 14.07 kΩ/□ and the hydrophilicity of the membrane increased slightly. The adsorption ability of the modified membrane for BSA, sodium humate and sodium alginate decreased, obviously because of the pores being blocked by PEDOT. The solid surface ZETA potential of the modified membrane was much more positive than that of the blank one. The modified membrane showed a certain level of chemical stability during alkali cleaning and NaClO corrosion repeated five times. During the six cycles of short-term filtration, the modified membrane with 1 V/cm of electric field showed stable anti-fouling properties because of less filter cake formation on the membrane surface compared to a blank and modified membrane without electric field. No more divalent cation accumulation on the membrane surface was found under the electric field, which might benefit from its electric neutrality surface.

The YSZ/Al2O3 supersaturated solid solution micro-powders (YAP) were successfully obtained by combustion synthesis assisted rapid water cooling. They were composed of metastable t-ZrxAlyYmOz phase and metastable γ-Al2O3 phase with nano-scale microstructures. There was almost no change in the composition of YAP at the temperature ≤1200 K. The α-Al2O3 phase appeared in YAP after heat-treatment at 1300 K, and the average grain size of the solid solution was about 10 nm and 50 nm in YAP-1300 and YAP-1500, respectively. Because the submicro-grains on the surface of YAP-1700 by in-situ nanoprecipitation, the interfaces between YAP disappeared, making intracrystalline-intercrystalline nanocomposite ceramics yet achieved from YAP. Therefore, this method has a guiding role in the preparation of ceramics with high-density nanoprecipitation from YAP.

In this paper, we propose a novel perspective-guided convolution (PGC) for convolutional neural network (CNN) based crowd counting (i.e. PGCNet), which aims to overcome the dramatic intra-scene scale variations of people due to the perspective effect. While most state-of-the-arts adopt multi-scale or multi-column architectures to address such issue, they generally fail in modeling continuous scale variations since only discrete representative scales are considered. PGCNet, on the other hand, utilizes perspective information to guide the spatially variant smoothing of feature maps before feeding them to the successive convolutions. An effective perspective estimation branch is also introduced to PGCNet, which can be trained in either supervised setting or weakly-supervised setting when the branch has been pre-trained. Our PGCNet is single-column with moderate increase in computation, and extensive experimental results on four benchmark datasets show the improvements of our method against the state-of-the-arts. Additionally, we also introduce Crowd Surveillance, a large scale dataset for crowd counting that contains 13,000+ high-resolution images with challenging scenarios., Comment: Accepted by ICCV 2019

Attention-based learning for fine-grained image recognition remains a challenging task, where most of the existing methods treat each object part in isolation, while neglecting the correlations among them. In addition, the multi-stage or multi-scale mechanisms involved make the existing methods less efficient and hard to be trained end-to-end. In this paper, we propose a novel attention-based convolutional neural network (CNN) which regulates multiple object parts among different input images. Our method first learns multiple attention region features of each input image through the one-squeeze multi-excitation (OSME) module, and then apply the multi-attention multi-class constraint (MAMC) in a metric learning framework. For each anchor feature, the MAMC functions by pulling same-attention same-class features closer, while pushing different-attention or different-class features away. Our method can be easily trained end-to-end, and is highly efficient which requires only one training stage. Moreover, we introduce Dogs-in-the-Wild, a comprehensive dog species dataset that surpasses similar existing datasets by category coverage, data volume and annotation quality. Extensive experiments are conducted to show the substantial improvements of our method on four benchmark datasets.

Background With the developments of DNA sequencing technology, large amounts of sequencing data have become available in recent years and provide unprecedented opportunities for advanced association studies between somatic point mutations and cancer types/subtypes, which may contribute to more accurate somatic point mutation based cancer classification (SMCC). However in existing SMCC methods, issues like high data sparsity, small volume of sample size, and the application of simple linear classifiers, are major obstacles in improving the classification performance. Results To address the obstacles in existing SMCC studies, we propose DeepGene, an advanced deep neural network (DNN) based classifier, that consists of three steps: firstly, the clustered gene filtering (CGF) concentrates the gene data by mutation occurrence frequency, filtering out the majority of irrelevant genes; secondly, the indexed sparsity reduction (ISR) converts the gene data into indexes of its non-zero elements, thereby significantly suppressing the impact of data sparsity; finally, the data after CGF and ISR is fed into a DNN classifier, which extracts high-level features for accurate classification. Experimental results on our curated TCGA-DeepGene dataset, which is a reformulated subset of the TCGA dataset containing 12 selected types of cancer, show that CGF, ISR and DNN all contribute in improving the overall classification performance. We further compare DeepGene with three widely adopted classifiers and demonstrate that DeepGene has at least 24% performance improvement in terms of testing accuracy. Conclusions Based on deep learning and somatic point mutation data, we devise DeepGene, an advanced cancer type classifier, which addresses the obstacles in existing SMCC studies. Experiments indicate that DeepGene outperforms three widely adopted existing classifiers, which is mainly attributed to its deep learning module that is able to extract the high level features between combinatorial somatic point mutations and cancer types.

Automated prostate diagnoses and treatments have gained much attention due to the high mortality rate of prostate cancer. In particular, unsupervised (automatic) prostate segmentation is an active and challenging research. Most conventional works usually utilize handcrafted (low-level) features for prostate segmentation; however they often fail to extract the intrinsic structure of the prostate, especially on images with blurred boundaries. In this paper, we propose a novel automated prostate segmentation model with learned features from deep network. Specifically, we first generate a set of prostate proposals in transverse plane via recognizing the position and coarse estimate of the shape of the prostate on the global prostate image and using the deep network to extract highly effective features for the boundary refinement in a finer scale. With consideration of the correlations among different sequential images, we then construct a graph to select the best prostate proposals from proposal set for its use in 3D prostate segmentation. Experimental evaluation demonstrates that our proposed deep network and graph based method is superior to state-of-the-art couterparts, in terms of both dice similarity coefficient and Hausdorff distance, on public dataset.

Sentinel lymph node (SLN) biopsy has emerged as a preferred method for axillary lymph node staging of breast cancer, and imaging the SLN in three-dimensional space is a prerequisite for the biopsy. Conventional SLN mapping techniques based on the injection of an organic dye or a suspension of radioactive colloids suffer from invasive surgical operation for visual detection of the dye or hazardous radioactive components and low spatial resolution of Geiger counters in detecting the radioactive colloids. This work systematically investigates the use of gold nanocages (AuNCs) as a novel class of optical tracers for noninvasive SLN imaging by photoacoustic (PA) tomography in a rat model. The transport of AuNCs in a lymphatic system and uptake by the sentinel lymph node were evaluated by PA tomography on the axillary region of a rat. Quantification of AuNCs accumulated in the lymph node was achieved by correlating the data from PA imaging with the results from inductively-coupled plasma mass spectrometry. Several parameters were systematically evaluated and optimized, including the concentration, size, and surface charge of the AuNCs. These results are critical to the further development of this AuNC-based PA tomography system for noninvasive SLN imaging, providing valuable information for metastatic cancer staging.

In the field of saliency detection, many graph-based algorithms heavily depend on the accuracy of the pre-processed superpixel segmentation, which leads to significant sacrifice of detail information from the input image. In this paper, we propose a novel bottom-up saliency detection approach that takes advantage of both region-based features and image details. To provide more accurate saliency estimations, we first optimize the image boundary selection by the proposed erroneous boundary removal. By taking the image details and region-based estimations into account, we then propose the regularized random walks ranking to formulate pixel-wised saliency maps from the superpixel-based background and foreground saliency estimations. Experiment results on two public datasets indicate the significantly improved accuracy and robustness of the proposed algorithm in comparison with 12 state-of-the-art saliency detection approaches.