An innovative Zn3In2S6/ZnIn2S4 homojunction photocatalyst with enhanced interfacial charge transfer for the highly efficient degradation of tetracycline under visible radiation.

The interfacial charge transfer ability is a decisive factor influencing the photocatalytic performance of composite photocatalysts. Compared with heterojunctions that combine two or more semiconductors with different properties, homojunctions that combine two semiconductors with similar properties can accelerate the interfacial charge shift and achieve higher photocatalyticability. In this study, a Zn3In2S6/ZnIn2S4 homojunction photocatalyst (ZIS-5) with a Zn3In2S6 to ZnIn2S4 molar ratio of 5:1 was synthesized by selecting Zn3In2S6 nano-microspheres as the substrate material and growing ZnIn2S4 flocs on the nano-microspheres. The photocatalytic performance of the ZIS-5 homojunction was assessed by using tetracycline (TC) as a typical pollutant. The photocatalytic performance and mineralization rate of the ZIS-5 homojunction were significantly improved compared with those of Zn3In2S6 and ZnIn2S4, and its photocatalytic performance was increased by 10.2% and 20.9%, compared with Zn3In2S6 and ZnIn2S4, respectively, while the mineralization rate was enhanced by 22.78% and 43.28%, respectively. The results of the comparison experiment revealed that the interfacial electron transfer ability of the ZIS-5 homojunction is 1.6 times that of the g-C3N4/ZnIn2S4-5 heterojunction. The density functional theory (DFT) computation and Mott-Schottky plots verified the formation of an internal electric field. The toxicity analysis showed that the ZIS-5 homojunction system effectively reduced the toxicity of TC. This work supplies a valuable route for inventing catalysts with efficient photocatalytic performances.

First-Principles Investigation of Phosphorus-Doped Graphitic Carbon Nitride as Anchoring Material for the Lithium-Sulfur Battery.

The utilization of lithium-sulfur battery is hindered by various challenges, including the "shuttle effect", limited sulfur utilization, and the sluggish conversion kinetics of lithium polysulfides (LiPSs). In the present work, a theoretical design for the viability of graphitic carbon nitride (g-C3N4) and phosphorus-doping graphitic carbon nitride substrates (P-g-C3N4) as promising host materials in a Li-S battery was conducted utilizing first-principles calculations. The PDOS shows that when the P atom is introduced, the 2p of the N atom is affected by the 2p orbital of the P atom, which increases the energy band of phosphorus-doping substrates. The energy bands of PC and Pi are 0.12 eV and 0.20 eV, respectively. When the lithium polysulfides are adsorbed on four substrates, the overall adsorption energy of PC is 48-77% higher than that of graphitic carbon nitride, in which the charge transfer of long-chain lithium polysulfides increase by more than 1.5-fold. It is found that there are powerful Li-N bonds between lithium polysulfides and P-g-C3N4 substrates. Compared with the graphitic carbon nitride monolayer, the anchoring effect of the LiPSs@P-g-C3N4 substrate is enhanced, which is beneficial for inhibiting the shuttle of high-order lithium polysulfides. Furthermore, the catalytic performance of the P-g-C3N4 substrate is assessed in terms of the S8 reduction pathway and the decomposition of Li2S; the decomposition energy barrier of the P-g-C3N4 substrate decrease by 10% to 18%. The calculated results show that P-g-C3N4 can promote the reduction of S8 molecules and Li-S bond cleavage within Li2S, thus improving the utilization of sulfur-active substances and the ability of rapid reaction kinetics. Therefore, the P-g-C3N4 substrates are a promising high-performance lithium-sulfur battery anchoring material.

Polydopamine-mediated immobilization of BMP-2 onto electrospun nanofibers enhances bone regeneration.

Dealing with bone defects is a significant challenge to global health. Electrospinning in bone tissue engineering has emerged as a solution to this problem. In this study, we designed a PVDF-b-PTFE block copolymer by incorporating TFE, which induced a phase shift in PVDF fromαtoß, thereby enhancing the piezoelectric effect. Utilizing the electrospinning process, we not only converted the material into a film with a significant surface area and high porosity but also intensified the piezoelectric effect. Then we used polydopamine to immobilize BMP-2 onto PVDF-b-PTFE electrospun nanofibrous membranes, achieving a controlled release of BMP-2. The scaffold's characters were examined using SEM and XRD. To assess its osteogenic effectsin vitro, we monitored the proliferation of MC3T3-E1 cells on the fibers, conducted ARS staining, and measured the expression of osteogenic genes.In vivo, bone regeneration effects were analyzed through micro-CT scanning and HE staining. ELISA assays confirmed that the sustained release of BMP-2 can be maintained for at least 28 d. SEM images and CCK-8 results demonstrated enhanced cell viability and improved adhesion in the experimental group. Furthermore, the experimental group exhibited more calcium nodules and higher expression levels of osteogenic genes, including COL-I, OCN, and RUNX2. HE staining and micro-CT scans revealed enhanced bone tissue regeneration in the defective area of the PDB group. Through extensive experimentation, we evaluated the scaffold's effectiveness in augmenting osteoblast proliferation and differentiation. This study emphasized the potential of piezoelectric PVDF-b-PTFE nanofibrous membranes with controlled BMP-2 release as a promising approach for bone tissue engineering, providing a viable solution for addressing bone defects.

Low-Temperature Synthesis of Mesoporous Half-Metallic High-Entropy Spinel Oxide Nanofibers for Photocatalytic CO2 Reduction.

High-entropy oxides (HEOs) exhibit great prospects owing to their varied composition, chemical adaptability, adjustable light-absorption ability, and strong stability. In this study, we report a strategy to synthesize a series of porous high-entropy spinel oxide (HESO) nanofibers (NFs) at a low temperature of 400 °C by a sol-gel electrospinning technique. The key lies in selecting six acetylacetonate salt precursors with similar coordination abilities, maintaining a high-entropy disordered state during the transformation from stable sols to gel NFs. The as-synthesized HESO NFs of (NiCuMnCoZnFe)3O4 show a high specific surface area of 66.48 m2/g, a diverse elemental composition, a dual bandgap, half-metallicity property, and abundant defects. The diverse elements provide various synergistic catalytic sites, and oxygen vacancies act as active sites for electron-hole separation, while the half-metallicity and dual-bandgap structure offer excellent light absorption ability, thus expanding its applicability to a wide range of photocatalytic processes. As a result, the HESO NFs can efficiently convert CO2 into CH4 and CO with high yields of 8.03 and 15.89 µmol g-1 h-1, respectively, without using photosensitizers or sacrificial agents.

The Contact Interface Electronic Coupling of Cobalt and Zirconia Enables Stable and Highly Efficient 4e- Oxygen Reduction Reaction Catalysis.

Cobalt (Co) is an efficient oxygen reduction reaction (ORR) catalyst but suffers from issues of easy deactivation and instability. Here, it shows that ZrO2 can stabilize Co through interface electron coupling and enables highly efficient 4e- ORR catalysis. Porous carbon nanofibers loaded with dispersed Co-nanodots (≈10 nm, 9.63 wt%) and ZrO2 nanoparticles are synthesized as the catalyst. The electron transfer from the metallic Co to ZrO2 causes interface-oriented electron enrichment that promotes the activation and conversion of O2, improving the efficiency of 4e- transfer. Moreover, the simulation results show that ZrO2 acts like an electron reservoir to store electrons from Co and slowly release them to the interface, solving the easy deactivation problem of Co. The catalyst exhibits a high half-wave potential (E1/2) of 0.84 V, which only decreases by 3.6 mV after 10 000 cycles, showing great stability. Particularly, the enhanced spin polarization of Co in a magnetic field reinforces the interface electron coupling that increases the E1/2 to 0.864 V and decreases the energy barrier of ORR from 0.81 to 0.63 eV, confirming that the proposed strategy is effective for constructing efficient and stable ORR catalysts.

Protein-protein interaction site prediction by model ensembling with hybrid feature and self-attention.

BACKGROUND: Protein-protein interactions (PPIs) are crucial in various biological functions and cellular processes. Thus, many computational approaches have been proposed to predict PPI sites. Although significant progress has been made, these methods still have limitations in encoding the characteristics of each amino acid in sequences. Many feature extraction methods rely on the sliding window technique, which simply merges all the features of residues into a vector. The importance of some key residues may be weakened in the feature vector, leading to poor performance. RESULTS: We propose a novel sequence-based method for PPI sites prediction. The new network model, PPINet, contains multiple feature processing paths. For a residue, the PPINet extracts the features of the targeted residue and its context separately. These two types of features are processed by two paths in the network and combined to form a protein representation, where the two types of features are of relatively equal importance. The model ensembling technique is applied to make use of more features. The base models are trained with different features and then ensembled via stacking. In addition, a data balancing strategy is presented, by which our model can get significant improvement on highly unbalanced data. CONCLUSION: The proposed method is evaluated on a fused dataset constructed from Dset186, Dset_72, and PDBset_164, as well as the public Dset_448 dataset. Compared with current state-of-the-art methods, the performance of our method is better than the others. In the most important metrics, such as AUPRC and recall, it surpasses the second-best programmer on the latter dataset by 6.9% and 4.7%, respectively. We also demonstrated that the improvement is essentially due to using the ensemble model, especially, the hybrid feature. We share our code for reproducibility and future research at https://github.com/CandiceCong/StackingPPINet .

Identification of plant vacuole proteins by using graph neural network and contact maps.

Plant vacuoles are essential organelles in the growth and development of plants, and accurate identification of their proteins is crucial for understanding their biological properties. In this study, we developed a novel model called GraphIdn for the identification of plant vacuole proteins. The model uses SeqVec, a deep representation learning model, to initialize the amino acid sequence. We utilized the AlphaFold2 algorithm to obtain the structural information of corresponding plant vacuole proteins, and then fed the calculated contact maps into a graph convolutional neural network. GraphIdn achieved accuracy values of 88.51% and 89.93% in independent testing and fivefold cross-validation, respectively, outperforming previous state-of-the-art predictors. As far as we know, this is the first model to use predicted protein topology structure graphs to identify plant vacuole proteins. Furthermore, we assessed the effectiveness and generalization capability of our GraphIdn model by applying it to identify and locate peroxisomal proteins, which yielded promising outcomes. The source code and datasets can be accessed at https://github.com/SJNNNN/GraphIdn .

Prediction of Membrane Protein Amphiphilic Helix Based on Horizontal Visibility Graph and Graph Convolution Network.

Membrane protein amphiphilic helices play an important role in many biological processes. Based on the graph convolution network and the horizontal visibility graph the prediction method of membrane protein amphiphilic helix structure is proposed in this paper. The new dataset of amphiphilic helix is constructed. In this paper, we propose the novel feature extraction method, which characterize the amphiphilicity of membrane protein. We also extract three commonly used protein features together with the new features as protein node features. The neighbor information and long-distance dependence information of proteins are further extracted by sliding window and bidirectional long-short term memory network respectively. From the perspective of horizontal visibility algorithm, we transform protein sequences into complex networks to obtain the graph features of proteins. Then, graph convolutional network model is employed to predict the amphiphilic helix structure of membrane protein. A rigorous ten-fold cross-validation shows that the proposed method outperforms other AH prediction methods on the newly constructed dataset.

Preparation of lignin nanoparticles via ultra-fast microwave-assisted fractionation of lignocellulose using ternary deep eutectic solvents.

Lignin separation from natural lignocellulose for the preparation of lignin nanoparticles (LNPs) is often challenging owing to the recalcitrant and complex structure of lignocellulose. This paper reports a strategy for the rapid synthesis of LNPs via microwave-assisted lignocellulose fractionation using ternary deep eutectic solvents (DESs). A novel ternary DES with strong hydrogen bonding was prepared using choline chloride, oxalic acid, and lactic acid in a 1:0.5:1 ratio. Efficient fractionation of rice straw (0.5 × 2.0 cm) (RS) was realized by the ternary DES under microwave irradiation (680 W) within only 4 min, and 63.4% of lignin could be separated from the RS to prepare LNPs with a high lignin purity (86.8%), an average particle size of 48-95 nm, and a narrow size distribution. The mechanism of lignin conversion was also investigated, which revealed that dissolved lignin aggregated into LNPs via π-π stacking interactions.

Stabilizing High Density Cu Active Sites with ZrO2 Quantum Dots as Chemical Ligand in N-doped Porous Carbon Nanofibers for Efficient ORR.

The emerging transition metal-nitrogen-carbon (MNC) materials are considered as a promising oxygen reduction reaction (ORR) catalyst system to substitute expensive Pt/C catalysts due to their high surface area and potential high catalytic activity. However, MNC catalysts are easy to be attacked by the ORR byproducts that easily lead to the deactivation of metal active sites. Moreover, a high metal loading affects the mass transfer and stability, but a low loading delivers inferior catalytic activity. Here, a new strategy of designing ZrO2 quantum dots and N-complex as dual chemical ligands in N-doped bubble-like porous carbon nanofibers (N-BPCNFs) to stabilize copper (Cu) by forming CuZrO3-x /ZrO2 heterostructures and CuN ligands with a high loading of 40.5 wt.% is reported. While the highly porous architecture design of N-BPCNFs builds a large solidelectrolytegas phase interface and promotes mass transfer. The preliminary results show that the half-wave potential of the catalyst reaches 0.856 V, and only decreases 0.026 V after 10 000 cycles, exhibiting excellent stability. The proposed strategy of stabilizing metal active sites with both heterostructures and CuN ligands is feasible and scalable for developing high metal loading ORR catalyst.

Exploiting Sparse Self-Representation and Particle Swarm Optimization for CNN Compression.

Structured pruning has received ever-increasing attention as a method for compressing convolutional neural networks. However, most existing methods directly prune the network structure according to the statistical information of the parameters. Besides, these methods differentiate the pruning rates only in each pruning stage or even use the same pruning rate across all layers, rather than using learnable parameters. In this article, we propose a network redundancy elimination approach guided by the pruned model. Our proposed method can easily tackle multiple architectures and is scalable to the deeper neural networks because of the use of joint optimization during the pruning procedure. More specifically, we first construct a sparse self-representation for the filters or neurons of the well-trained model, which is useful for analyzing the relationship among filters. Then, we employ particle swarm optimization to learn pruning rates in a layerwise manner according to the performance of the pruned model, which can determine optimal pruning rates with the best performance of the pruned model. Under this criterion, the proposed pruning approach can remove more parameters without undermining the performance of the model. Experimental results demonstrate the effectiveness of our proposed method on different datasets and different architectures. For example, it can reduce 58.1% FLOPs for ResNet50 on ImageNet with only a 1.6% top-five error increase and 44.1% FLOPs for FCN_ResNet50 on COCO2017 with a 3% error increase, outperforming most state-of-the-art methods.

Transfer-Learning-Based Gaussian Mixture Model for Distributed Clustering.

Distributed clustering based on the Gaussian mixture model (GMM) has exhibited excellent clustering capabilities in peer-to-peer (P2P) networks. However, more iterative numbers and communication overhead are required to achieve the consensus in existing distributed GMM clustering algorithms. In addition, the truth that it cannot find a closed form for the update of parameters in GMM causes the imprecise clustering accuracy. To solve these issues, by utilizing the transfer learning technique, a general transfer distributed GMM clustering framework is exploited to promote the clustering performance and accelerate the clustering convergence. In this work, each node is treated as both the source domain and the target domain, and these nodes can learn from each other to complete the clustering task in distributed P2P networks. Based on this framework, the transfer distributed expectation-maximization algorithm with the fixed learning rate is first presented for data clustering. Then, an improved version is designed to obtain the stable clustering accuracy, in which an adaptive transfer learning strategy is adopted to adjust the learning rate automatically instead of a fixed value. To demonstrate the extensibility of the proposed framework, a representative GMM clustering method, the entropy-type classification maximum-likelihood algorithm, is further extended to the transfer distributed counterpart. Experimental results verify the effectiveness of the presented algorithms in contrast with the existing GMM clustering approaches.

ProSE-Pero: Peroxisomal Protein Localization Identification Model Based on Self-Supervised Multi-Task Language Pre-Training Model.

BACKGROUND: Peroxisomes are membrane-bound organelles that contain one or more types of oxidative enzymes. Aberrant localization of peroxisomal proteins can contribute to the development of various diseases. To more accurately identify and locate peroxisomal proteins, we developed the ProSE-Pero model. METHODS: We employed three methods based on deep representation learning models to extract the characteristics of peroxisomal proteins and compared their performance. Furthermore, we used the SVMSMOTE balanced dataset, SHAP interpretation model, variance analysis (ANOVA), and light gradient boosting machine (LightGBM) to select and compare the extracted features. We also constructed several traditional machine learning methods and four deep learning models to train and test our model on a dataset of 160 peroxisomal proteins using tenfold cross-validation. RESULTS: Our proposed ProSE-Pero model achieves high performance with a specificity (Sp) of 93.37%, a sensitivity (Sn) of 82.41%, an accuracy (Acc) of 95.77%, a Matthews correlation coefficient (MCC) of 0.8241, an F1 score of 0.8996, and an area under the curve (AUC) of 0.9818. Additionally, we extended our method to identify plant vacuole proteins and achieved an accuracy of 91.90% on the independent test set, which is approximately 5% higher than the latest iPVP-DRLF model. CONCLUSIONS: Our model surpasses the existing In-Pero model in terms of peroxisomal protein localization and identification. Additionally, our study showcases the proficient performance of the pre-trained multitasking language model ProSE in extracting features from protein sequences. With its established validity and broad generalization, our model holds considerable potential for expanding its application to the localization and identification of proteins in other organelles, such as mitochondria and Golgi proteins, in future investigations.

Disease-related compound identification based on deeping learning method.

Acute lung injury (ALI) is a serious respiratory disease, which can lead to acute respiratory failure or death. It is closely related to the pathogenesis of New Coronavirus pneumonia (COVID-19). Many researches showed that traditional Chinese medicine (TCM) had a good effect on its intervention, and network pharmacology could play a very important role. In order to construct "disease-gene-target-drug" interaction network more accurately, deep learning algorithm is utilized in this paper. Two ALI-related target genes (REAL and SATA3) are considered, and the active and inactive compounds of the two corresponding target genes are collected as training data, respectively. Molecular descriptors and molecular fingerprints are utilized to characterize each compound. Forest graph embedded deep feed forward network (forgeNet) is proposed to train. The experimental results show that forgeNet performs better than support vector machines (SVM), random forest (RF), logical regression (LR), Naive Bayes (NB), XGBoost, LightGBM and gcForest. forgeNet could identify 19 compounds in Erhuang decoction (EhD) and Dexamethasone (DXMS) more accurately.

A survey on protein-DNA-binding sites in computational biology.

Transcription factors are important cellular components of the process of gene expression control. Transcription factor binding sites are locations where transcription factors specifically recognize DNA sequences, targeting gene-specific regions and recruiting transcription factors or chromatin regulators to fine-tune spatiotemporal gene regulation. As the common proteins, transcription factors play a meaningful role in life-related activities. In the face of the increase in the protein sequence, it is urgent how to predict the structure and function of the protein effectively. At present, protein-DNA-binding site prediction methods are based on traditional machine learning algorithms and deep learning algorithms. In the early stage, we usually used the development method based on traditional machine learning algorithm to predict protein-DNA-binding sites. In recent years, methods based on deep learning to predict protein-DNA-binding sites from sequence data have achieved remarkable success. Various statistical and machine learning methods used to predict the function of DNA-binding proteins have been proposed and continuously improved. Existing deep learning methods for predicting protein-DNA-binding sites can be roughly divided into three categories: convolutional neural network (CNN), recursive neural network (RNN) and hybrid neural network based on CNN-RNN. The purpose of this review is to provide an overview of the computational and experimental methods applied in the field of protein-DNA-binding site prediction today. This paper introduces the methods of traditional machine learning and deep learning in protein-DNA-binding site prediction from the aspects of data processing characteristics of existing learning frameworks and differences between basic learning model frameworks. Our existing methods are relatively simple compared with natural language processing, computational vision, computer graphics and other fields. Therefore, the summary of existing protein-DNA-binding site prediction methods will help researchers better understand this field.

Automatic classification of nerve discharge rhythms based on sparse auto-encoder and time series feature.

BACKGROUND: Nerve discharge is the carrier of information transmission, which can reveal the basic rules of various nerve activities. Recognition of the nerve discharge rhythm is the key to correctly understand the dynamic behavior of the nervous system. The previous methods for the nerve discharge recognition almost depended on the traditional statistical features, and the nonlinear dynamical features of the discharge activity. The artificial extraction and the empirical judgment of the features were required for the recognition. Thus, these methods suffered from subjective factors and were not conducive to the identification of a large number of discharge rhythms. RESULTS: The ability of automatic feature extraction along with the development of the neural network has been greatly improved. In this paper, an effective discharge rhythm classification model based on sparse auto-encoder was proposed. The sparse auto-encoder was used to construct the feature learning network. The simulated discharge data from the Chay model and its variants were taken as the input of the network, and the fused features, including the network learning features, covariance and approximate entropy of nerve discharge, were classified by Softmax. The results showed that the accuracy of the classification on the testing data was 87.5%, which could provide more accurate classification results. Compared with other methods for the identification of nerve discharge types, this method could extract the characteristics of nerve discharge rhythm automatically without artificial design, and show a higher accuracy. CONCLUSIONS: The sparse auto-encoder, even neural network has not been used to classify the basic nerve discharge from neither biological experiment data nor model simulation data. The automatic classification method of nerve discharge rhythm based on the sparse auto-encoder in this paper reduced the subjectivity and misjudgment of the artificial feature extraction, saved the time for the comparison with the traditional method, and improved the intelligence of the classification of discharge types. It could further help us to recognize and identify the nerve discharge activities in a new way.

Fabrication of Flexible Mesoporous Black Nb2 O5 Nanofiber Films for Visible-Light-Driven Photocatalytic CO2 Reduction into CH4.

Achieving high selectivity and conversion efficiency simultaneously is a challenge for visible-light-driven photocatalytic CO2 reduction into CH4 . Here, a facile nanofiber synthesis method and a new defect control strategy at room-temperature are reported for the fabrication of flexible mesoporous black Nb2 O5 nanofiber catalysts that contain abundant oxygen-vacancies and unsaturated Nb dual-sites, which are efficient towards photocatalytic production of CH4 . The oxygen-vacancy decreases the bandgap width of Nb2 O5 from 3.01-2.25 eV, which broadens the light-absorption range from ultraviolet to visible-light, and the dual sites in the mesopores can easily adsorb CO2 , so that the intermediate product of CO* can be spontaneously changed into *CHO. The formation of a highly stable NbCHO* intermediate at the dual sites is proposed to be the key feature determining selectivity. The preliminary results show that without using sacrificial agents and photosensitizers, the nanofiber catalyst achieves 64.8% selectivity for CH4 production with a high evolution rate of 19.5 µmol g-1 h-1 under visible-light. Furthermore, the flexible catalyst film can be directly used in devices, showing appealing and broadly commercial applications.

Multiple Protein Subcellular Locations Prediction Based on Deep Convolutional Neural Networks with Self-Attention Mechanism.

As an important research field in bioinformatics, protein subcellular location prediction is critical to reveal the protein functions and provide insightful information for disease diagnosis and drug development. Predicting protein subcellular locations remains a challenging task due to the difficulty of finding representative features and robust classifiers. Many feature fusion methods have been widely applied to tackle the above issues. However, they still suffer from accuracy loss due to feature redundancy. Furthermore, multiple protein subcellular locations prediction is more complicated since it is fundamentally a multi-label classification problem. The traditional binary classifiers or even multi-class classifiers cannot achieve satisfactory results. This paper proposes a novel method for protein subcellular location prediction with both single and multiple sites based on deep convolutional neural networks. Specifically, we first obtain the integrated features by simultaneously considering the pseudo amino acid, amino acid index distribution, and physicochemical property. We then adopt deep convolutional neural networks to extract high-dimensional features from the fused feature, removing the redundant preliminary features and gaining better representations of the raw sequences. Moreover, we use the self-attention mechanism and a customized loss function to ensure that the model is more inclined to positive data. In addition, we use random k-label sets to reduce the number of prediction labels. Meanwhile, we employ a hybrid strategy of over-sampling and under-sampling to tackle the data imbalance problem. We compare our model with three representative classification alternatives. The experiment results show that our model achieves the best performance in terms of accuracy, demonstrating the efficacy of the proposed model.

A Cascade Flexible Neural Forest Model for Cancer Subtypes Classification on Gene Expression Data.

The correct classification of cancer subtypes is of great significance for the in-depth study of cancer pathogenesis and the realization of accurate treatment for cancer patients. In recent years, the classification of cancer subtypes using deep neural networks and gene expression data has become a hot topic. However, most classifiers may face the challenges of overfitting and low classification accuracy when dealing with small sample size and high-dimensional biological data. In this paper, the Cascade Flexible Neural Forest (CFNForest) Model was proposed to accomplish cancer subtype classification. CFNForest extended the traditional flexible neural tree structure to FNT Group Forest exploiting a bagging ensemble strategy and could automatically generate the model's structure and parameters. In order to deepen the FNT Group Forest without introducing new hyperparameters, the multilayer cascade framework was exploited to design the FNT Group Forest model, which transformed features between levels and improved the performance of the model. The proposed CFNForest model also improved the operational efficiency and the robustness of the model by sample selection mechanism between layers and setting different weights for the output of each layer. To accomplish cancer subtype classification, FNT Group Forest with different feature sets was used to enrich the structural diversity of the model, which make it more suitable for processing small sample size datasets. The experiments on RNA-seq gene expression data showed that CFNForest effectively improves the accuracy of cancer subtype classification. The classification results have good robustness.

Privacy protection of medical data in social network.

BACKGROUND: Protection of privacy data published in the health care field is an important research field. The Health Insurance Portability and Accountability Act (HIPAA) in the USA is the current legislation for privacy protection. However, the Institute of Medicine Committee on Health Research and the Privacy of Health Information recently concluded that HIPAA cannot adequately safeguard the privacy, while at the same time researchers cannot use the medical data for effective researches. Therefore, more effective privacy protection methods are urgently needed to ensure the security of released medical data. METHODS: Privacy protection methods based on clustering are the methods and algorithms to ensure that the published data remains useful and protected. In this paper, we first analyzed the importance of the key attributes of medical data in the social network. According to the attribute function and the main objective of privacy protection, the attribute information was divided into three categories. We then proposed an algorithm based on greedy clustering to group the data points according to the attributes and the connective information of the nodes in the published social network. Finally, we analyzed the loss of information during the procedure of clustering, and evaluated the proposed approach with respect to classification accuracy and information loss rates on a medical dataset. RESULTS: The associated social network of a medical dataset was analyzed for privacy preservation. We evaluated the values of generalization loss and structure loss for different values of k and a, i.e. [Formula: see text] = {3, 6, 9, 12, 15, 18, 21, 24, 27, 30}, a = {0, 0.2, 0.4, 0.6, 0.8, 1}. The experimental results in our proposed approach showed that the generalization loss approached optimal when a = 1 and k = 21, and structure loss approached optimal when a = 0.4 and k = 3. CONCLUSION: We showed the importance of the attributes and the structure of the released health data in privacy preservation. Our method achieved better results of privacy preservation in social network by optimizing generalization loss and structure loss. The proposed method to evaluate loss obtained a balance between the data availability and the risk of privacy leakage.