Multilevel Contrastive Graph Masked Autoencoders for Unsupervised Graph-Structure Learning

Unsupervised graph-structure learning (GSL) which aims to learn an effective graph structure applied to arbitrary downstream tasks by data itself without any labels' guidance, has recently received increasing attention in various real applications. Although several existing unsupervised GSL has achieved superior performance in different graph analytical tasks, how to utilize the popular graph masked autoencoder to sufficiently acquire effective supervision information from the data itself for improving the effectiveness of learned graph structure has been not effectively explored so far. To tackle the above issue, we present a multilevel contrastive graph masked autoencoder (MCGMAE) for unsupervised GSL. Specifically, we first introduce a graph masked autoencoder with the dual feature masking strategy to reconstruct the same input graph-structured data under the original structure generated by the data itself and learned graph-structure scenarios, respectively. And then, the inter-and intra-class contrastive loss is introduced to maximize the mutual information in feature and graph-structure reconstruction levels simultaneously. More importantly, the above inter-and intra-class contrastive loss is also applied to the graph encoder module for further strengthening their agreement at the feature-encoder level. In comparison to the existing unsupervised GSL, our proposed MCGMAE can effectively improve the training robustness of the unsupervised GSL via different-level supervision information from the data itself. Extensive experiments on three graph analytical tasks and eight datasets validate the effectiveness of the proposed MCGMAE.

A novel two-way rebalancing strategy for identifying carbonylation sites

BACKGROUND

As an irreversible post-translational modification, protein carbonylation is closely related to many diseases and aging. Protein carbonylation prediction for related patients is significant, which can help clinicians make appropriate therapeutic schemes. Because carbonylation sites can be used to indicate change or loss of protein function, integrating these protein carbonylation site data has been a promising method in prediction. Based on these protein carbonylation site data, some protein carbonylation prediction methods have been proposed. However, most data is highly class imbalanced, and the number of un-carbonylation sites greatly exceeds that of carbonylation sites. Unfortunately, existing methods have not addressed this issue adequately.

RESULTS

In this work, we propose a novel two-way rebalancing strategy based on the attention technique and generative adversarial network (Carsite_AGan) for identifying protein carbonylation sites. Specifically, Carsite_AGan proposes a novel undersampling method based on attention technology that allows sites with high importance value to be selected from un-carbonylation sites. The attention technique can obtain the value of each sample's importance. In the meanwhile, Carsite_AGan designs a generative adversarial network-based oversampling method to generate high-feasibility carbonylation sites. The generative adversarial network can generate high-feasibility samples through its generator and discriminator. Finally, we use a classifier like a nonlinear support vector machine to identify protein carbonylation sites.

CONCLUSIONS

Experimental results demonstrate that our approach significantly outperforms other resampling methods. Using our approach to resampling carbonylation data can significantly improve the effect of identifying protein carbonylation sites.

Cancer survival prediction by learning comprehensive deep feature representation for multiple types of genetic data

BACKGROUND

Cancer is one of the leading death causes around the world. Accurate prediction of its survival time is significant, which can help clinicians make appropriate therapeutic schemes. Cancer data can be characterized by varied molecular features, clinical behaviors and morphological appearances. However, the cancer heterogeneity problem usually makes patient samples with different risks (i.e., short and long survival time) inseparable, thereby causing unsatisfactory prediction results. Clinical studies have shown that genetic data tends to contain more molecular biomarkers associated with cancer, and hence integrating multi-type genetic data may be a feasible way to deal with cancer heterogeneity. Although multi-type gene data have been used in the existing work, how to learn more effective features for cancer survival prediction has not been well studied.

RESULTS

To this end, we propose a deep learning approach to reduce the negative impact of cancer heterogeneity and improve the cancer survival prediction effect. It represents each type of genetic data as the shared and specific features, which can capture the consensus and complementary information among all types of data. We collect mRNA expression, DNA methylation and microRNA expression data for four cancers to conduct experiments.

CONCLUSIONS

Experimental results demonstrate that our approach substantially outperforms established integrative methods and is effective for cancer survival prediction.

AVAILABILITY AND IMPLEMENTATION

https://github.com/githyr/ComprehensiveSurvival .

Human Collective Intelligence Inspired Multi-View Representation Learning - Enabling View Communication by Simulating Human Communication Mechanism

In real-world applications, we often encounter multi-view learning tasks where we need to learn from multiple sources of data or use multiple sources of data to make decisions. Multi-view representation learning, which can learn a unified representation from multiple data sources, is a key pre-task of multi-view learning and plays a significant role in real-world applications. Accordingly, how to improve the performance of multi-view representation learning is an important issue. In this work, inspired by human collective intelligence shown in group decision making, we introduce the concept of view communication into multi-view representation learning. Furthermore, by simulating human communication mechanism, we propose a novel multi-view representation learning approach that can fulfill multi-round view communication. Thus, each view of our approach can exploit the complementary information from other views to help with modeling its own representation, and mutual help between views is achieved. Extensive experiment results on six datasets from three significant fields indicate that our approach substantially improves the average classification accuracy by 4.536% in medicine and bioinformatics fields as well as 4.115% in machine learning field.

Joint learning sample similarity and correlation representation for cancer survival prediction

BACKGROUND

As a highly aggressive disease, cancer has been becoming the leading death cause around the world. Accurate prediction of the survival expectancy for cancer patients is significant, which can help clinicians make appropriate therapeutic schemes. With the high-throughput sequencing technology becoming more and more cost-effective, integrating multi-type genome-wide data has been a promising method in cancer survival prediction. Based on these genomic data, some data-integration methods for cancer survival prediction have been proposed. However, existing methods fail to simultaneously utilize feature information and structure information of multi-type genome-wide data.

RESULTS

We propose a Multi-type Data Joint Learning (MDJL) approach based on multi-type genome-wide data, which comprehensively exploits feature information and structure information. Specifically, MDJL exploits correlation representations between any two data types by cross-correlation calculation for learning discriminant features. Moreover, based on the learned multiple correlation representations, MDJL constructs sample similarity matrices for capturing global and local structures across different data types. With the learned discriminant representation matrix and fused similarity matrix, MDJL constructs graph convolutional network with Cox loss for survival prediction.

CONCLUSIONS

Experimental results demonstrate that our approach substantially outperforms established integrative methods and is effective for cancer survival prediction.

[Prenatal genetic diagnosis of the fetuses with isolated corpus callosum abnormality]

Objective: To explore the application value of chromosome karyotype analysis, chromosomal microarray analysis (CMA) and whole exome sequencing (WES) in prenatal diagnosis of isolated corpus callosum abnormality (CCA) fetus. Methods: Fetuses diagnosed with isolated CCA by ultrasound and MRI and receiving invasive prenatal diagnosis in Guangzhou Women and Children's Medical Center and Qingyuan People's Hospital from January 2010 to April 2021 were selected. Karyotype analysis and/or CMA [or copy number variation sequencing (CNV-seq)] were performed on all fetal samples, and WES was performed on fetal samples and their parents whose karyotype analysis and/or CMA (or CNV-seq) results were not abnormal. Results: Among 65 fetuses with isolated CCA, 38 cases underwent karyotype analysis, and 3 cases were detected with abnormal karyotypes, with a detection rate of 8% (3/38). A total of 49 fetuses with isolated CCA underwent CMA (or CNV-seq) detection, and 6 cases of pathogenic CNV were detected, the detection rate was 12% (6/49). Among them, the karyotype analysis results were abnormal, and the detection rate of further CMA detection was 1/1. The karyotype results were normal, and the detection rate of further CMA (or CNV-seq) detection was 14% (3/21). The detection rate of CMA as the first-line detection technique was 7% (2/27). A total of 25 fetuses with isolated CCA with negative results of karyotyping and/or CMA were tested by WES, and 9 cases (36%, 9/25) were detected with pathogenic genes. The gradient genetic diagnosis of chromosomal karyotyping, CMA and WES resulted in a definite genetic diagnosis of 26% (17/65) of isolated CCA fetuses. Conclusions: Prenatal genetic diagnosis of isolated CCA fetuses is of great clinical significance. The detection rate of CMA is higher than that of traditional karyotyping. CMA detection could be used as a first-line detection technique for fetuses with isolated CCA. WES could increase the pathogenicity detection rate of fetuses with isolated CCA when karyotype analysis and/or CMA test results are negative.

Visual-Depth Matching Network: Deep RGB-D Domain Adaptation With Unequal Categories

Existing domain adaptation (DA) methods generally assume that different domains have identical label space, and the training data are only sampled from a single domain. This unrealistic assumption is quite restricted for real-world applications, since it neglects the more practical scenario, where the source domain can contain the categories that are not shared by the target domain, and the training data can be collected from multiple modalities. In this article, we address a more difficult but practical problem, which recognizes RGB images through training on RGB-D data under the label space inequality scenario. There are three challenges in this task: 1) source and target domains are affected by the domain mismatch issue, which results in that the trained models perform imperfectly on the test data; 2) depth images are absent in the target domain (e.g., target images are captured by smartphones), when the source domain contains both the RGB and depth data. It makes the ordinary visual recognition approaches hardly applied to this task; and 3) in the real world, the source and target domains always have different numbers of categories, which would result in a negative transfer bottleneck being more prominent. Toward tackling the above challenges, we formulate a deep model, called visual-depth matching network (VDMN), where two new modules and a matching component can be trained in an end-to-end fashion jointly to identify the common and outlier categories effectively. The significance of VDMN is that it can take advantage of depth information and handle the domain distribution mismatch under label inequality simultaneously. The experimental results reveal that VDMN exceeds the state-of-the-art performance on various DA datasets, especially under the label inequality scenario.

Menthol Flavor in E-Cigarette Vapor Modulates Social Behavior Correlated With Central and Peripheral Changes of Immunometabolic Signalings

The use of electronic cigarette (e-cigarette) has been increasing dramatically worldwide. More than 8,000 flavors of e-cigarettes are currently marketed and menthol is one of the most popular flavor additives in the electronic nicotine delivery systems (ENDS). There is a controversy over the roles of e-cigarettes in social behavior, and little is known about the potential impacts of flavorings in the ENDS. In our study, we aimed to investigate the effects of menthol flavor in ENDS on the social behavior of long-term vapor-exposed mice with a daily intake limit, and the underlying immunometabolic changes in the central and peripheral systems. We found that the addition of menthol flavor in nicotine vapor enhanced the social activity compared with the nicotine alone. The dramatically reduced activation of cellular energy measured by adenosine 5′ monophosphate-activated protein kinase (AMPK) signaling in the hippocampus were observed after the chronic exposure of menthol-flavored ENDS. Multiple sera cytokines including C5, TIMP-1, and CXCL13 were decreased accordingly as per their peripheral immunometabolic responses to menthol flavor in the nicotine vapor. The serum level of C5 was positively correlated with the alteration activity of the AMPK-ERK signaling in the hippocampus. Our current findings provide evidence for the enhancement of menthol flavor in ENDS on social functioning, which is correlated with the central and peripheral immunometabolic disruptions; this raises the vigilance of the cautious addition of various flavorings in e-cigarettes and the urgency of further investigations on the complex interplay and health effects of flavoring additives with nicotine in e-cigarettes.

[Prenatal diagnosis and clinical outcomes of 297 fetuses with conotruncal defects]

Objective: To analyze the prenatal diagnosis results and pregnancy outcomes of conotruncal defects (CTD) fetuses, and to explore the correlation between the CTD and chromosome diseases. Methods: A total of 297 cases of invasive prenatal diagnosis and chromosome analysis were collected at the Prenatal Diagnosis Center of Guangzhou Women and Children's Medical Center due to CTD from January 1st, 2011 to December 31th, 2019. According to ultrasonic diagnosis, CTD fetuses were divided into 6 subtypes: tetralogy of Fallot (109 cases), pulmonary atresia (30 cases), transposition of the great arteries (77 cases), double outlet right ventricle (53 cases), truncus arteriosus (14 cases) and interrupted aortic arch (14 cases). According to whether they were combined with intracardiac or extracardiac abnormalities, they were divided into simple group (134 cases), combined with other intracardiac abnormalities group (86 cases), combined with extracardiac abnormalities group (20 cases), combined with intracardiac and extracardiac abnormalities group (37 cases) and only combined with ultrasound soft marker group (20 cases), the last 4 groups were referred as non-simple types. The chromosome test results and pregnancy outcomes of each type and group were analyzed retrospectively. Results: Among the 297 CTD fetuses, the chromosome abnormality rate was 17.5% (52/297). There were 21 cases of abnormal chromosome number, 28 cases of pathogenetic copy number variantions and 3 cases of mosaics. All the 19 cases of micropathogenic fragments smaller than 5 Mb were detected by chromosomal microarray analysis (CMA). Among all the subtypes of CTD, the chromosomal abnormality rate of truncus arteriosus was the highest, at 7/14; while the rate of transposition of the great arteries was the lowest, at 5.2% (4/77). There were significant differences in the rate of chromosomal abnormalities between simple and non-simple types [10.4% (14/134) vs 23.3% (38/163); χ²=8.428, P=0.004]. In each group, the chromosomal abnormality rate was the highest in the combined with intracardiac and extracardiac abnormalities group, at 37.8% (14/37), and the lowest in the simple group, at 10.4% (14/134). There was no significant difference in the rate of chromosomal abnormalities in all subtypes of simple group (all P>0.05). Among 112 cases of live birth, 1 case was 22q11.2 microdeletion syndrome, 5 cases of postnatal clinical diagnosis and prenatal ultrasound diagnosis were not completely consistent, 5 cases died after birth. Conclusions: The incidence of chromosomal abnormalities is high in fetuses with CTD. CTD fetuses with concurrent extrapardiac malformations are more likely to incorporate chromosomal abnormalities. CMA technology could be used as a first-line genetic detection method for CTD. After excluding chromosomal abnormalities, most of the children with CTD have good prognosis.

[Analysis of families with fetal congenital abnormalities but negative prenatal diagnosis by whole exome sequencing]

Objective: To evaluate the value of whole exome sequencing (WES) in prenatal clinical application. Methods: A total of 1 152 cases of congenital abnormal [including structural malformation, nuchal translucency (NT) thickening and intrauterine growth restriction] with traditional prenatal diagnosis [including G-band karyotype analysis and chromosome microarray analysis (CMA)] negative were analyzed. The congenital abnormal fetuses were divided into retrospective group and prospective group according to the time of WES detection, that is whether the pregnancy termination or not. According to the specific location of fetal malformation and their family history, the cohort was divided into subgroups. The clinical prognosis of all fetuses were followed up, and the effect of WES test results on pregnancy decision-making and clinical intervention were analyzed. According to the follow-up results, the data of fetuses with new phenotypes in the third trimester or after birth were re-analyzed. Results: Among 1 152 families who received WES, 5 families were excluded because of nonbiological parents. Among the remaining 1 147 families, 152 fetuses obtained positive diagnosis (13.3%,152/1 147), including 74 fetuses in the retrospective group (16.1%,74/460) and 78 fetuses in the prospective group (11.4%,78/687). In fetuses with negative CMA and G-band karyotype analysis results but new phenotypes in the third trimester or after birth, the positive rate by WES data re-analysis was 4.9% (8/163). A total of 34 (21.3%, 34/160) fetuses were directly affected by the corresponding positive molecular diagnosis. Among 68 cases of live births with diagnostic variation grade 4, 29 cases (42.7%, 29/68) received appropriate medical intervention through rapid review of WES results. Conclusions: WES could increase the detection rate of abnormal fetuses with negative G-banding karyotype analysis and CMA by 13.3%. Prenatal WES could guide pregnancy decision-making and early clinical intervention. It might be an effective strategy to pay attention to the special follow-up of the third trimester and postnatal fetus and to re-analyze the WES data.

Semi-Supervised Multi-View Deep Discriminant Representation Learning

Learning an expressive representation from multi-view data is a key step in various real-world applications. In this paper, we propose a semi-supervised multi-view deep discriminant representation learning (SMDDRL) approach. Unlike existing joint or alignment multi-view representation learning methods that cannot simultaneously utilize the consensus and complementary properties of multi-view data to learn inter-view shared and intra-view specific representations, SMDDRL comprehensively exploits the consensus and complementary properties as well as learns both shared and specific representations by employing the shared and specific representation learning network. Unlike existing shared and specific multi-view representation learning methods that ignore the redundancy problem in representation learning, SMDDRL incorporates the orthogonality and adversarial similarity constraints to reduce the redundancy of learned representations. Moreover, to exploit the information contained in unlabeled data, we design a semi-supervised learning framework by combining deep metric learning and density clustering. Experimental results on three typical multi-view learning tasks, i.e., webpage classification, image classification, and document classification demonstrate the effectiveness of the proposed approach.

mGlu2/3 receptor in the prelimbic cortex is implicated in stress resilience and vulnerability in mice

Resilience, referring to "achieving a positive outcome in the face of adversity", is a common phenomenon in daily life. Elucidating the mechanisms of stress resilience is instrumental to developing more effective treatments for stress-related psychiatric disorders such as depression. Metabotropic glutamate receptors (mGlu2/3 and mGlu5) within the medial prefrontal cortex (mPFC) have been recently recognized as promising therapeutic targets for rapid-acting antidepressant treatment. In this study, we assessed the functional roles of the mGlu2/3 and mGlu5 within different subregions of the mPFC in modulating stress resilience and vulnerability by using chronic social defeat stress (CSDS) paradigms in mice. Our results showed that approximately 51.6% of the subjects exhibited depression- or anxiety-like behaviors after exposure to CSDS. When a susceptible mouse was confronted with an attacker, c-Fos expression in the prelimbic cortex (PrL) subregion of the mPFC substantially increased. Compared with the resilient and control groups, the expression of mGlu2/3 was elevated in the PrL of the susceptible group. The expression of mGlu5 showed no significant difference among the three groups in the whole mPFC. Finally, we found that the social avoidance symptoms of the susceptible mice were rapidly relieved by intra-PrL administration of LY341495-an mGluR2/3 antagonists. The above results indicate that mGluR2/3 within the PrL may play an important regulatory role in stress-related psychiatric disorders. Our results are meaningful, as they expand our understanding of stress resilience and vulnerability which may open an avenue to develop novel, personalized approaches to mitigate depression and promote stress resilience.

The GABA(B1) receptor within the infralimbic cortex is implicated in stress resilience and vulnerability in mice

Resilience is the capacity to maintain normal psychological and physical functions in the face of stress and adversity. Understanding how one can develop and enhance resilience is of great relevance to not only promoting coping mechanisms but also mitigating maladaptive stress responses in psychiatric illnesses such as depression. Preclinical studies suggest that GABA(B) receptors (GABA(B1) and GABA(B2)) are potential targets for the treatment of major depression. In this study, we assessed the functional role of GABA(B) receptors in stress resilience and vulnerability by using a chronic unpredictable stress (CUS) model in mice. As the medial prefrontal cortex (mPFC) plays a key role in the top-down modulation of stress responses, we focused our study on this brain structure. Our results showed that only approximately 41.9% of subjects exhibited anxiety- or despair-like behaviors after exposure to CUS. The vulnerable mice showed higher c-Fos expression in the infralimbic cortex (IL) subregion of the mPFC when exposed to a social stressor. Moreover, the expression of GABA(B1) but not GABA(B2) receptors was significantly downregulated in IL subregion of susceptible mice. Finally, we found that intra-IL administration of baclofen, a GABA(B) receptor agonist, rapidly relieved the social avoidance symptoms of the "stress-susceptible" mice. Taken together, our results show that the GABA(B1) receptor within the IL may play an important role in stress resilience and vulnerability, and thus open an avenue to develop novel, personalized approaches to promote stress resilience and treat stress-related psychiatric disorders.

Modal-Regression-Based Structured Low-Rank Matrix Recovery for Multiview Learning

Low-rank Multiview Subspace Learning (LMvSL) has shown great potential in cross-view classification in recent years. Despite their empirical success, existing LMvSL-based methods are incapable of handling well view discrepancy and discriminancy simultaneously, which, thus, leads to performance degradation when there is a large discrepancy among multiview data. To circumvent this drawback, motivated by the block-diagonal representation learning, we propose structured low-rank matrix recovery (SLMR), a unique method of effectively removing view discrepancy and improving discriminancy through the recovery of the structured low-rank matrix. Furthermore, recent low-rank modeling provides a satisfactory solution to address the data contaminated by the predefined assumptions of noise distribution, such as Gaussian or Laplacian distribution. However, these models are not practical, since complicated noise in practice may violate those assumptions and the distribution is generally unknown in advance. To alleviate such a limitation, modal regression is elegantly incorporated into the framework of SLMR (termed MR-SLMR). Different from previous LMvSL-based methods, our MR-SLMR can handle any zero-mode noise variable that contains a wide range of noise, such as Gaussian noise, random noise, and outliers. The alternating direction method of multipliers (ADMM) framework and half-quadratic theory are used to optimize efficiently MR-SLMR. Experimental results on four public databases demonstrate the superiority of MR-SLMR and its robustness to complicated noise.

Multiset Feature Learning for Highly Imbalanced Data Classification

With the expansion of data, increasing imbalanced data has emerged. When the imbalance ratio (IR) of data is high, most existing imbalanced learning methods decline seriously in classification performance. In this paper, we systematically investigate the highly imbalanced data classification problem, and propose an uncorrelated cost-sensitive multiset learning (UCML) approach for it. Specifically, UCML first constructs multiple balanced subsets through random partition, and then employs the multiset feature learning (MFL) to learn discriminant features from the constructed multiset. To enhance the usability of each subset and deal with the non-linearity issue existed in each subset, we further propose a deep metric based UCML (DM-UCML) approach. DM-UCML introduces the generative adversarial network technique into the multiset constructing process, such that each subset can own similar distribution with the original dataset. To cope with the non-linearity issue, DM-UCML integrates deep metric learning with MFL, such that more favorable performance can be achieved. In addition, DM-UCML designs a new discriminant term to enhance the discriminability of learned metrics. Experiments on eight traditional highly class-imbalanced datasets and two large-scale datasets indicate that: the proposed approaches outperform state-of-the-art highly imbalanced learning methods and are more robust to high IR.

Multiview Hybrid Embedding: A Divide-and-Conquer Approach

We present a novel cross-view classification algorithm where the gallery and probe data come from different views. A popular approach to tackle this problem is the multiview subspace learning (MvSL) that aims to learn a latent subspace shared by multiview data. Despite promising results obtained on some applications, the performance of existing methods deteriorates dramatically when the multiview data is sampled from nonlinear manifolds or suffers from heavy outliers. To circumvent this drawback, motivated by the Divide-and-Conquer strategy, we propose multiview hybrid embedding (MvHE), a unique method of dividing the problem of cross-view classification into three subproblems and building one model for each subproblem. Specifically, the first model is designed to remove view discrepancy, whereas the second and third models attempt to discover the intrinsic nonlinear structure and to increase the discriminability in intraview and interview samples, respectively. The kernel extension is conducted to further boost the representation power of MvHE. Extensive experiments are conducted on four benchmark datasets. Our methods demonstrate the overwhelming advantages against the state-of-the-art MvSL-based cross-view classification approaches in terms of classification accuracy and robustness.

[Whole exome sequencing and analysis of a Chinese family with familial pulmonary sarcoidosis]

Objective: To analyze the clinical features and the results of the whole exome sequencing (WES) of a Chinese family containing both pulmonary sarcoidosis patients and healthy members, and to find potent genes and variants that may be involved in the pathogenesis of sarcoidosis. Methods: Three patients with pulmonary sarcoidosis and 1 healthy member was included from a Chinese Han family in the north of China diagnosed in November 2016, which characterized as 2 consecutive generations including 2 males and 1 female, aged from 23 to 69 years old. The proband is Ⅱ-6. Pulmonary sarcoidosis was diagnosed by clinical features, imaging and pathological findings, and clinical data such as family history were collected. Whole blood samples were taken and WES (Illumina NovaSeq S2) was performed. The pathogenicity analysis and gene annotation analysis were performed by ExAC, SIFT, Polyphenv2, Metascape databases. Results: It was found that 27 genes were highly pathogenic in the database filtering result. After gene annotation analysis, we found that ZC3H12A gene can negatively regulate the differentiation of Th17 cells, which may be involved in the onset of pulmonary sarcoidosis. Sanger sequencing confirmed the c.1361 A>G variant in 3 sarcoidosis patients but normal in healthy member. Conclusions: In patients with familial pulmonary sarcoidosis, the genetic background could regulate immune response which is one of the pathogenic mechanisms of sarcoidosis. The whole exome test and gene ontology analysis showed that Ⅱ-2, Ⅱ-6 and Ⅲ-1 pulmonary sarcoidosis patients in this family were all shared the same variant on ZC3H12A gene, which played a pivotal role in differentiation of Th17 cells and is a potent pathogenesis gene in this Chinese pulmonary sarcoidosis family.

Adaptive Weighted Sparse Principal Component Analysis for Robust Unsupervised Feature Selection

Current unsupervised feature selection methods cannot well select the effective features from the corrupted data. To this end, we propose a robust unsupervised feature selection method under the robust principal component analysis (PCA) reconstruction criterion, which is named the adaptive weighted sparse PCA (AW-SPCA). In the proposed method, both the regularization term and the reconstruction error term are constrained by the l_2,1 -norm: the l_2,1 -norm regularization term plays a role in the feature selection, while the l_2,1 -norm reconstruction error term plays a role in the robust reconstruction. The proposed method is in a convex formulation, and the selected features by it can be used for robust reconstruction and clustering. Experimental results demonstrate that the proposed method can obtain better reconstruction and clustering performance, especially for the corrupted data.

Intraspectrum Discrimination and Interspectrum Correlation Analysis Deep Network for Multispectral Face Recognition

Multispectral images contain rich recognition information since the multispectral camera can reveal information that is not visible to the human eye or to the conventional RGB camera. Due to this characteristic of multispectral images, multispectral face recognition has attracted lots of research interest. Although some multispectral face recognition methods have been presented in the last decade, how to fully and effectively explore the intraspectrum discriminant information and the useful interspectrum correlation information in multispectral face images for recognition has not been well studied. To boost the performance of multispectral face recognition, we propose an intraspectrum discrimination and interspectrum correlation analysis deep network (IDICN) approach. Multiple spectra are divided into several spectrum-sets, with each containing a group of spectra within a small spectral range. The IDICN network contains a set of spectrum-set-specific deep convolutional neural networks attempting to extract spectrum-set-specific features, followed by a spectrum pooling layer, whose target is to select a group of spectra with favorable discriminative abilities adaptively. IDICN jointly learns the nonlinear representations of the selected spectra, such that the intraspectrum Fisher loss and the interspectrum discriminant correlation are minimized. Experiments on the well-known Hong Kong Polytechnic University, Carnegie Mellon University, and the University of Western Australia multispectral face datasets demonstrate the superior performance of the proposed approach over several state-of-the-art methods.

Involvement of oxytocin and GABA in consolation behavior elicited by socially defeated individuals in mandarin voles

Consolation, which entails comforting contact directed toward a distressed party, is a common empathetic response in humans and other species with advanced cognition. Here, using the social defeat paradigm, we provide empirical evidence that highly social and monogamous mandarin voles (Microtus mandarinus) increased grooming toward a socially defeated partner but not toward a partner who underwent only separation. This selective behavioral response existed in both males and females. Accompanied with these behavioral changes, c-Fos expression was elevated in many of the brain regions relevant for emotional processing, such as the anterior cingulate cortex (ACC), bed nucleus of the stria terminalis, paraventricular nucleus (PVN), basal/basolateral and central nucleus of the amygdala, and lateral habenular nucleus in both sexes; in the medial preoptic area, the increase in c-Fos expression was found only in females, whereas in the medial nucleus of the amygdala, this increase was found only in males. In particular, the GAD67/c-Fos and oxytocin (OT)/c-Fos colocalization rates were elevated in the ACC and PVN, indicating selective activation of GABA and OT neurons in these regions. The "stressed" pairs matched their anxiety-like behaviors in the open-field test, and their plasma corticosterone levels correlated well with each other, suggesting an empathy-based mechanism. This partner-directed grooming was blocked by pretreatment with an OT receptor antagonist or a GABA_A receptor antagonist in the ACC but not by a V1a subtype vasopressin receptor antagonist. We conclude that consolation behavior can be elicited by the social defeat paradigm in mandarin voles, and this behavior may be involved in a coordinated network of emotion-related brain structures, which differs slightly between the sexes. We also found that the endogenous OT and the GABA systems within the ACC are essential for consolation behavior in mandarin voles.

Single Sample Face Recognition under Varying Illumination via QRCP Decomposition

In this paper, we present a novel high-frequency facial feature and a high-frequency based sparse representation classification to tackle single sample face recognition (SSFR) under varying illumination. Firstly, we propose the assumption that QRCP bases can represent intrinsic face surface features with different frequencies, and their corresponding energy coefficients describe illumination intensities. Based on this assumption, we take QRCP bases with corresponding weighting coefficients (i.e. the major components of energy coefficients) to develop the high-frequency facial feature of the face image, which is named as QRCP-face. The normalized QRCP-face (NQRCPface) is constructed to further constraint illumination effects by normalizing the weighting coefficients of QRCP-face. Moreover, we propose the adaptive QRCP-face (AQRCP-face) that assigns a special parameter to NQRCP-face via the illumination level estimated by the weighting coefficients. Secondly, we consider that the differences of pixel images cannot model the intraclass variations of generic faces with illumination variations, and the specific identification information of the generic face is redundant for the current SSFR with generic learning. To tackle above two issues, we develop a general high-frequency based sparse representation (GHSP) model. Two practical approaches separated high-frequency based sparse representation (SHSP) and unified high-frequency based sparse representation (UHSP) are developed. Finally, the performances of the proposed methods are verified on the Extended Yale B, CMU PIE, AR, LFW and our self-built Driver face databases. The experimental results indicate that the proposed methods outperform previous approaches for SSFR under varying illumination.

Video-based Person Re-identification by Simultaneously Learning Intra-video and Inter-video Distance Metrics

Video-based person re-identification (re-id) is an important application in practice. Since large variations exist between different pedestrian videos, as well as within each video, it's challenging to conduct re-identification between pedestrian videos. In this paper, we propose a simultaneous intra-video and inter-video distance learning (SI2DL) approach for video-based person re-id. Specifically, SI2DL simultaneously learns an intravideo distance metric and an inter-video distance metric from the training videos. The intra-video distance metric is used to make each video more compact, and the inter-video one is used to ensure that the distance between truly matching videos is smaller than that between wrong matching videos. Considering that the goal of distance learning is to make truly matching video pairs from different persons be well separated with each other, we also propose a pair separation based SI2DL (P-SI2DL). P-SI2DL aims to learn a pair of distance metrics, under which any two truly matching video pairs can be well separated. Experiments on four public pedestrian image sequence datasets show that our approaches achieve the state-of-the-art performance.

A joint space-angle regularization approach for single 4D diffusion image super-resolution

PURPOSE

Low signal-to-noise-ratio and limited scan time of diffusion magnetic resonance imaging (dMRI) in current clinical settings impede obtaining images with high spatial and angular resolution (HSAR) for a reliable fiber reconstruction with fine anatomical details. To overcome this problem, we propose a joint space-angle regularization approach to reconstruct HSAR diffusion signals from a single 4D low resolution (LR) dMRI, which is down-sampled in both 3D-space and q-space.

METHODS

Different from the existing works which combine multiple 4D LR diffusion images acquired using specific acquisition protocols, the proposed method reconstructs HSAR dMRI from only a single 4D dMRI by exploring and integrating two key priors, that is, the nonlocal self-similarity in the spatial domain as a prior to increase spatial resolution and ridgelet approximations in the diffusion domain as another prior to increase the angular resolution of dMRI. To more effectively capture nonlocal self-similarity in the spatial domain, a novel 3D block-based nonlocal means filter is imposed as the 3D image space regularization term which is accurate in measuring the similarity and fast for 3D reconstruction. To reduce computational complexity, we use the L₂ -norm instead of sparsity constraint on the representation coefficients.

RESULTS

Experimental results demonstrate that the proposed method can obtain the HSAR dMRI efficiently with approximately 2% per-voxel root-mean-square error between the actual and reconstructed HSAR dMRI.

CONCLUSION

The proposed approach can effectively increase the spatial and angular resolution of the dMRI which is independent of the acquisition protocol, thus overcomes the inherent resolution limitation of imaging systems.

Chronic Co-species Housing Mice and Rats Increased the Competitiveness of Male Mice

Rats are predators of mice in nature. Nevertheless, it is a common practice to house mice and rats in a same room in some laboratories. In this study, we investigated the behavioral and physiological responsively of mice in long-term co-species housing conditions. Twenty-four male mice were randomly assigned to their original raising room (control) or a rat room (co-species-housed) for more than 6 weeks. In the open-field and light-dark box tests, the behaviors of the co-species-housed mice and controls were not different. In a 2-choice test of paired urine odors [rabbit urine (as a novel odor) vs. rat urine, cat urine (as a natural predator-scent) vs. rabbit urine, and cat urine vs. rat urine], the co-species-housed mice were more ready to investigate the rat urine odor compared with the controls and may have adapted to it. In an encounter test, the rat-room-exposed mice exhibited increased aggression levels, and their urines were more attractive to females. Correspondingly, the levels of major urinary proteins were increased in the co-species-housed mouse urine, along with some volatile pheromones. The serum testosterone levels were also enhanced in the co-species-housed mice, whereas the corticosterone levels were not different. The norepinephrine, dopamine, and 5-HT levels in the right hippocampus and striatum were not different between the 2. Our findings indicate that chronic co-species housing results in adaptation in male mice; furthermore, it appears that long-term rat-odor stimuli enhance the competitiveness of mice, which suggests that appropriate predator-odor stimuli may be important to the fitness of prey animals.

Structure-Based Low-Rank Model With Graph Nuclear Norm Regularization for Noise Removal

Nonlocal image representation methods, including group-based sparse coding and block-matching 3-D filtering, have shown their great performance in application to low-level tasks. The nonlocal prior is extracted from each group consisting of patches with similar intensities. Grouping patches based on intensity similarity, however, gives rise to disturbance and inaccuracy in estimation of the true images. To address this problem, we propose a structure-based low-rank model with graph nuclear norm regularization. We exploit the local manifold structure inside a patch and group the patches by the distance metric of manifold structure. With the manifold structure information, a graph nuclear norm regularization is established and incorporated into a low-rank approximation model. We then prove that the graph-based regularization is equivalent to a weighted nuclear norm and the proposed model can be solved by a weighted singular-value thresholding algorithm. Extensive experiments on additive white Gaussian noise removal and mixed noise removal demonstrate that the proposed method achieves a better performance than several state-of-the-art algorithms.

Super-Resolution Person Re-Identification With Semi-Coupled Low-Rank Discriminant Dictionary Learning

Person re-identification has been widely studied due to its importance in surveillance and forensics applications. In practice, gallery images are high resolution (HR), while probe images are usually low resolution (LR) in the identification scenarios with large variation of illumination, weather, or quality of cameras. Person re-identification in this kind of scenarios, which we call super-resolution (SR) person re-identification, has not been well studied. In this paper, we propose a semi-coupled low-rank discriminant dictionary learning (SLD²L) approach for SR person re-identification task. With the HR and LR dictionary pair and mapping matrices learned from the features of HR and LR training images, SLD²L can convert the features of the LR probe images into HR features. To ensure that the converted features have favorable discriminative capability and the learned dictionaries can well characterize intrinsic feature spaces of the HR and LR images, we design a discriminant term and a low-rank regularization term for SLD²L. Moreover, considering that low resolution results in different degrees of loss for different types of visual appearance features, we propose a multi-view SLD²L (MVSLD²L) approach, which can learn the type-specific dictionary pair and mappings for each type of feature. Experimental results on multiple publicly available data sets demonstrate the effectiveness of our proposed approaches for the SR person re-identification task.

[Application of chromosomal microarray analysis for fetuses with talipes equinovarus]

OBJECTIVE

To investigate the application of fetuses with talipes equinovarus(TE)using chromosomal microarray analysis(CMA)technology.

METHODS

From May 2012 to June 2015, 54 fetuses were found with TE and with or without other structural anomalies by prenatal ultrasound. Karyotyping was taking for them all, and the fetuses with normal karyotypes took another CMA test. The data were analyzed with CHAS software. Finally all the cases were followed up to know about their pregnancy outcomes.

RESULTS

One of the 54 cases was detected with abnormal karyotype which was trisomy 18(2%, 1/54). CMA was undertaken to the remaining fetuses, they were divided into 2 groups, including isolated TE group(n= 38)and complex TE group(n=15). The detection rate of clinical significant copy number variations(CNV)by CMA was 11%(6/53), while isolated and complex TE group were 5%(2/38)and 4/15, respectively(P= 0.047). Of the 53 cases, 51 cases were successfully followed up. Eleven cases were found without TE after birth, and the false positive rate(FPR)of TE was 22%(11/51).

CONCLUSIONS

Whole-genome high-resolution CMA increased the detection rate by 11% in fetuses with TE. With the FPR and the detection rate of the clinical significant CNV of 2 groups, whole-genome CMA could be recommended to the fetuses with complex TE group but normal karyotypes. A series of ultrasonic tests should be suggested to the isolate TE group, while with the abnormal ultrasound, fetuses would be suggested to have CMA test for decreasing the rates of invasive prenatal diagnosis and FPR.

Palmprint and face multi-modal biometric recognition based on SDA-GSVD and its kernelization

When extracting discriminative features from multimodal data, current methods rarely concern themselves with the data distribution. In this paper, we present an assumption that is consistent with the viewpoint of discrimination, that is, a person's overall biometric data should be regarded as one class in the input space, and his different biometric data can form different Gaussians distributions, i.e., different subclasses. Hence, we propose a novel multimodal feature extraction and recognition approach based on subclass discriminant analysis (SDA). Specifically, one person's different bio-data are treated as different subclasses of one class, and a transformed space is calculated, where the difference among subclasses belonging to different persons is maximized, and the difference within each subclass is minimized. Then, the obtained multimodal features are used for classification. Two solutions are presented to overcome the singularity problem encountered in calculation, which are using PCA preprocessing, and employing the generalized singular value decomposition (GSVD) technique, respectively. Further, we provide nonlinear extensions of SDA based multimodal feature extraction, that is, the feature fusion based on KPCA-SDA and KSDA-GSVD. In KPCA-SDA, we first apply Kernel PCA on each single modal before performing SDA. While in KSDA-GSVD, we directly perform Kernel SDA to fuse multimodal data by applying GSVD to avoid the singular problem. For simplicity two typical types of biometric data are considered in this paper, i.e., palmprint data and face data. Compared with several representative multimodal biometrics recognition methods, experimental results show that our approaches outperform related multimodal recognition methods and KSDA-GSVD achieves the best recognition performance.

Effect of mutations in a simian virus 40 PolyA signal enhancer on green fluorescent protein reporter gene expression

Our previous studies have shown that tandem Alu repeats inhibit green fluorescent protein (GFP) gene expression when inserted downstream of the GFP gene in the pEGFP-C1 vector. We found that the 22R sequence (5'-GTGAAAAAAATGCTTTATTTGT-3') from the antisense PolyA (240 bp polyadenylation signal) of simian virus 40, eliminated repression of GFP gene expression when inserted between the GFP gene and the Alu repeats. The 22R sequence contains an imperfect palindrome; based on RNA structure software prediction, it forms an unstable stem-loop structure, including a loop, a first stem, a bulge, and a second stem. Analysis of mutations of the loop length of the 22R sequence showed that the three-nucleotide loop (wild-type, 22R) induced much stronger GFP expression than did other loop lengths. Two mutations, 4TMI (A7→T, A17→T) and 5AMI (A6→T, T18→A), which caused the base type changes in the bulge and in the second stem in the 22R sequence, induced stronger GFP gene expression than 22R itself. Mutation of the bulge base (A17→T), leading to complete complementation of the stem, caused weaker GFP gene expression. Sequences without a palindrome (7pieA, 5'-GTGAAAAAAATG CAAAAAAAGT-3', 7pieT, 5'-GTGTTTTTTTTGCTTTTTTTGT-3') did not activate GFP gene expression. We conclude that an imperfect palindrome affects and can increase GFP gene expression.