In multi-view multi-label classification task, each sample is described by features from multiple views and contains multiple semantic information. Previous methods established a separate classifier for each view and combined the prediction results and contribution weights of all classifiers to make the final prediction. However, these methods tended to overlook possible interactions among multiple views and did not consider the shared information among multiple views. Therefore, we propose Multi-view Multi-label Learning based on Improved Fusion Strategy (MMIFS). Firstly, we learn a shared subspace and utilize it as a supplementary view. Then we construct a separate classifier for each view and learn the corresponding contribution weights. We introduce digital labels instead of logical labels and maintain label co-occurrence dependency based on the smoothing assumption. Finally, we improve the performance of MMIFS by converting linear model to non-linear model. Based on extensive experiments with five datasets, MMIFS exhibits favorable performance and effectiveness.

Global scale concerns regarding rise in microplastics pollution in the environment have recently aroused. Ingestion of microplastics by biota, including freshwater zooplankton has been well studied, however, despite keystone species in freshwater food webs, the molecular response (e.g. oxidative defense) of zooplankton in response to microplastics is still in its infancy. The thioredoxin (TRx) system has a vital function in cellular antioxidative defense via eliminating the excessive generation of reactive oxygen species (ROS). Therefore, it is necessary to investigate the effects of thioredoxin reductase (TRxR), due to its triggering the TRx catalysis cascade. The present study identified TRxR in Daphnia magna (Dm-TRxR) for the first time, and found that the full-length cDNA was 1862 bp long, containing an 1821-bp open reading frame. Homologous alignments showed the presence of conserved catalytic domain CVNVGC and the seleocysteine (SeCys) residue (U) located in the N- and C- terminal portions. Subsequently, the expression of Dm-TRxR, together with permease, arginine kinase (AK), was investigated by approach of quantitative real-time PCR after exposure to four (1.25-mu m) polystyrene (PS) microbeads concentrations: 0 (control), 2, 4 and 8 mg L-1 for 10 days. Dm-TRxR, permease and AK mRNA were significantly upregulated after exposure to 2, 4 mg L-1 of PS, but then declined in the presence of 8 mg L-1 PS. The gene expression results suggested that oxidative defense, energy production and substance extra cellular transportation were significantly regulated by microplastic exposure. Collectively, the present study will advance our knowledge regarding the biological effects of microplastic pollution on zooplankton, and builds a foundation for freshwater environmental studies on mechanistic and biochemical responses to microplastics.

Group independent component analysis (GICA) has been successfully applied to study multi-subject functional magnetic resonance imaging (fMRI) data, and the group independent component (GIC) represents the commonality of all subjects in the group. However, some studies show that the performance of GICA can be improved by incorporating a priori information, which is not always considered when looking for GICs in existing GICA methods. In this paper, we propose an improved multi-objective optimization-based constrained independent component analysis (CICA) method to take advantage of the temporal a priori information extracted from all subjects in the group by incorporating it into the computational process of GICA for group fMRI data analysis. The experimental results of simulated and real data show that the activated regions and the time course detected by the improved CICA method are more accurate in some sense. Moreover, the GIC computed by the improved CICA method has a higher correlation with the corresponding independent component of each subject in the group, which means that the improved CICA method with the temporal a priori information extracted from the group can better reflect the commonality of the subjects. These results demonstrate that the improved CICA method has its own advantages in fMRI data analysis.

To solve the interferential problem of illumination in face recognition,this paper proposes a method called two dimensional discriminative projection based on nearest orthogonal matrix (2DDP-NOM).It obtains nearest orthogonal matrix representation of face image matrix by singular value decomposition firstly;then constructs the intra-class scatter based on nearest orthogonal matrix and the inter-class scatter based on nearest orthogonal matrix by nearest orthogonal matrix;lastly,obtains two dimensional discriminative projection by maximizing the inter-class scatter and minimizing the intra-class scatter simultaneously and gets the low dimensional features by this projection.Experiments are performed on Yale,CMU-PIE and AR databases and the experimental results demonstrate the effectiveness of 2DDP-NOM.

Lung cancer, characterized by uncontrolled cell growth in the lung tissue, is the leading cause of global cancer deaths. Until now, effective treatment of this disease is limited. Many synthetic compounds have emerged with the advancement of combinatorial chemistry. Identification of effective lung cancer candidate drug compounds among them is a great challenge. Thus, it is necessary to build effective computational methods that can assist us in selecting for potential lung cancer drug compounds. In this study, a computational method was proposed to tackle this problem. The chemical–chemical interactions and chemical–protein interactions were utilized to select candidate drug compounds that have close associations with approved lung cancer drugs and lung cancer-related genes. A permutation test and K-means clustering algorithm were employed to exclude candidate drugs with low possibilities to treat lung cancer. The final analysis suggests that the remaining drug compounds have potential anti-lung cancer activities and most of them have structural dissimilarity with approved drugs for lung cancer.

Hepatitis C virus (HCV) is an infectious virus that can cause serious illnesses. Only a few drugs have been reported to effectively treat hepatitis C. To have greater diversity in drug choice and better treatment options, it is necessary to develop more drugs to treat the infection. However, it is time-consuming and expensive to discover candidate drugs using experimental methods, and computational methods may complement experimental approaches as a preliminary filtering process. This type of approach was proposed by using known chemical-chemical interactions to extract interactive compounds with three known drug compounds of HCV, and the probabilities of these drug compounds being able to treat hepatitis C were calculated using chemical-protein interactions between the interactive compounds and HCV target genes. Moreover, the randomization test and expectation-maximization (EM) algorithm were both employed to exclude false discoveries. Analysis of the selected compounds, including acyclovir and ganciclovir, indicated that some of these compounds had potential to treat the HCV. Hopefully, this proposed method could provide new insights into the discovery of candidate drugs for the treatment of HCV and other diseases.

To overcome the negative effect of factors such as illumination and expression on face recognition,an adaptive feature and weight selection method was proposed.The method was based on Gabor image for face recognition.Firstly,40 independent feature matrices which were reconstructed with the same scale and the same direction transform results of the different face images were obtained by regarding every Gabor wavelet transformed output image as an independent sample.In order to enhance the robustness to facial expression and illumination variations,the contribution of each new feature matrix could be adaptively computed by the proposed adaptive weight method.Secondly,after applying discrete cosine transform to each feature matrix,the coefficients which had more power to discriminate different classes than others were selected by discrimination power analysis to construct feature vectors.And,linear discriminant analysis features were extracted to fulfill recognition task.Experiments on the face databases demonstrate the effectiveness of the proposed method.

Recently, linear preserving projections (LPP) is proposed to manifold learning and pattern classification. LPP can not be used to solve illumination and facial expressions problem in face recognition. However, in the real world face images are always affected by variations in illumination conditions and different facial expressions. So, the fuzzy linear preserving projections (FLPP) algorithm is proposed, in which the fuzzy k-nearest neighbor (FKNN) is implemented to achieve the local distribution information of original samples from a high dimensional data into a low dimensional space. Experimental results on the ORL and AR face databases show the effectiveness of the proposed method. Copyright © 2010 Binary Information Press May, 2010.