As a crime of employing technical means to steal sensitive information of users, phishing is currently a critical threat facing the Internet, and losses due to phishing are growing steadily. Feature engineering is important in phishing website detection solutions, but the accuracy of detection critically depends on prior knowledge of features. Moreover, although features extracted from different dimensions are more comprehensive, a drawback is that extracting these features requires a large amount of time. To address these limitations, we propose a multidimensional feature phishing detection approach based on a fast detection method by using deep learning. In the first step, character sequence features of the given URL are extracted and used for quick classification by deep learning, and this step does not require thirdparty assistance or any prior knowledge about phishing. In the second step, we combine URL statistical features, webpage code features, webpage text features, and the quick classification result of deep learning into multidimensional features. The approach can reduce the detection time for setting a threshold. Testing on a dataset containing millions of phishing URLs and legitimate URLs, the accuracy reaches 98.99%, and the false positive rate is only 0.59%. By reasonably adjusting the threshold, the experimental results show that the detection efficiency can be improved. INDEX TERMS Phishing website detection, convolutional neural network, long short-term memory network, semantic feature, machine learning.

CD44, the primary receptor for hyaluronic acid, plays an important role in tumor growth and metastasis. CD44-hyaluronic acid interactions can be exploited for targeted delivery of anti-cancer agents specifically to cancer cells. Although various splicing variants of CD44 are expressed on the plasma membrane of cancer cells, the hyaluronic acid binding domain (HABD) is highly conserved among the CD44 splicing variants. Using a novel two-step process, we have identified monothiophosphate-modified aptamers (thioaptamers) that specifically bind to the CD44’s HABD with high affinities. Binding affinities of the selected thioaptamers for the HABD were in the range of 180–295 nM, significantly higher affinity than that of hyaluronic acid (Kd > μM range). The selected thioaptamers bound to CD44 positive human ovarian cancer cell lines (SKOV3, IGROV, and A2780), but failed to bind CD44 negative NIH3T3 cell line. Our results indicated that thio substitution at specific positions of the DNA phosphate backbone result in specific and high affinity binding of thioaptamers to CD44. The selected thioaptamers will be of great interest for further development as a targeting or imaging agent to deliver therapeutic payloads for cancer tissues.

Alzheimer's disease (AD) is an irreversible progressive neurodegenerative disorder. Mild cognitive impairment (MCI) is the prodromal state of AD, which is further classified into a progressive state (i.e., pMCI) and a stable state (i.e., sMCI). With the development of deep learning, the convolutional neural networks (CNNs) have made great progress in image recognition using magnetic resonance imaging (MRI) and positron emission tomography (PET) for AD diagnosis. However, due to the limited availability of these imaging data, it is still challenging to effectively use CNNs for AD diagnosis. Toward this end, we design a novel deep learning framework. Specifically, the virtues of 3D-CNN and fully stacked bidirectional long short-term memory (FSBi-LSTM) are exploited in our framework. First, we design a 3D-CNN architecture to derive deep feature representation from both MRI and PET. Then, we apply FSBi-LSTM on the hidden spatial information from deep feature maps to further improve its performance. Finally, we validate our method on the AD neuroimaging initiative (ADNI) dataset. Our method achieves average accuracies of 94.82%, 86.36%, and 65.35% for differentiating AD from normal control (NC), pMCI from NC, and sMCI from NC, respectively, and outperforms the related algorithms in the literature.

No abstract

Accurate identification and understanding informative feature is important for early Alzheimer's disease (AD) prognosis and diagnosis. In this paper, we propose a novel discriminative sparse learning method with relational regularization to jointly predict the clinical score and classify AD disease stages using multimodal features. Specifically, we apply a discriminative learning technique to expand the class-specific difference and include geometric information for effective feature selection. In addition, two kind of relational information are incorporated to explore the intrinsic relationships among features and training subjects in terms of similarity learning. We map the original feature into the target space to identify the informative and predictive features by sparse learning technique. A unique loss function is designed to include both discriminative learning and relational regularization methods. Experimental results based on a total of 805 subjects [including 226 AD patients, 393 mild cognitive impairment (MCI) subjects, and 186 normal controls (NCs)] from AD neuroimaging initiative database show that the proposed method can obtain a classification accuracy of 94.68% for AD versus NC, 80.32% for MCI versus NC, and 74.58% for progressive MCI versus stable MCI, respectively. In addition, we achieve remarkable performance for the clinical scores prediction and classification label identification, which has efficacy for AD disease diagnosis and prognosis. The algorithm comparison demonstrates the effectiveness of the introduced learning techniques and superiority over the state-of-the-arts methods.

No abstract

No abstract

Phosphorylated peptides and proteins play an important role in normal cellular activities, e.g., gene expression, mitosis, differentiation, proliferation, and apoptosis, as well as tumor initiation, progression and metastasis. However, technical hurdles hinder the use of common fractionation methods to capture phosphopeptides from complex biological fluids such as human sera. Herein, we present the development of a dual strategy material that offers enhanced capture of low molecular weight phosphoproteins: mesoporous silica thin films with precisely engineered pore sizes that sterically select for molecular size combined with chemically selective surface modifications (i.e. Ga3+, Ti4+ and Zr4+) that target phosphoroproteins. These materials provide high reproducibility (CV = 18%) and increase the stability of the captured proteins by excluding degrading enzymes, such as trypsin. The chemical and physical properties of the composite mesoporous thin films were characterized by X-ray diffraction, transmission electron microscopy, X-ray photoelectron spectroscopy, energy dispersive X-ray spectroscopy and ellipsometry. Using mass spectroscopy and biostatistics analysis, the enrichment efficiency of different metal ions immobilized on mesoporous silica chips was investigated. The novel technology reported provides a platform capable of efficiently profiling the serum proteome for biomarker discovery, forensic sampling, and routine diagnostic applications.