Good Model Design Research Articles

Computational Modulation of the V3 Region of Glycoprotein gp125 of HIV-2.

HIV-2 infection is frequently neglected in HIV/AIDS campaigns. However, a special emphasis must be given to HIV-2 as an untreated infection that also leads to AIDS and death, and for which the efficacy of most available drugs is limited against HIV-2. HIV envelope glycoproteins mediate binding to the receptor CD4 and co-receptors at the surface of the target cell, enabling fusion with the cell membrane and viral entry. Here, we developed and optimized a computer-assisted drug design approach of an important HIV-2 glycoprotein that allows us to explore and gain further insights at the molecular level into protein structures and interactions crucial for the inhibition of HIV-2 cell entry. The 3D structure of a key HIV-2ROD gp125 region was generated by a homology modeling campaign. To disclose the importance of the main structural features and compare them with experimental results, 3D-models of six mutants were also generated. These mutations revealed the selective impact on the behavior of the protein. Furthermore, molecular dynamics simulations were performed to optimize the models, and the dynamic behavior was tackled to account for structure flexibility and interactions network formation. Structurally, the mutations studied lead to a loss of aromatic features, which is very important for the establishment of π-π interactions and could induce a structural preference by a specific coreceptor. These new insights into the structure-function relationship of HIV-2 gp125 V3 and surrounding regions will help in the design of better models and the design of new small molecules capable to inhibit the attachment and binding of HIV with host cells.

Motion Blur Removal With Quality Assessment Guidance

Non-uniform blind motion deblurring is a challenging yet fundamental task in the computer vision field, which aims to restore the latent sharp image from the blurry input. Recently, deep-learning-based methods have made significant improvement and progress, on the metric of PSNR. They achieve good results mainly because they adopt Mean Squared Error (MSE) as the optimization objective, in addition to their good model design. However, simple adoption of the PSNR metric and the MSE loss, has non-ignorable disadvantages. PSNR cannot always succeed in assessing the deblurred quality in accordance with the human visual system (HVS), and MSE guides the network to generate over-smoothed images. To address these problems, we are the first to propose the deep-learning-based multi-scale non-reference quality assessment network (Deep DEBLUR-IQA) for assessing the quality of deblurred results. Moreover, a deblurring network of high efficiency is presented. It is more than 50 times faster than other SOTA multi-scale Convolution Neural Network (CNN) methods, with the newly propose Residual Dilated Block (RDB) and Light ResBlock (LRB). The deblurring network's performance can be further boosted with Multiple Dilation Block (MDB), with an acceptable speed decrease. Finally, and most importantly, we are the first to let Deep DEBLUR-IQA guide the deblurring network's optimization. This IQA-guided enhancement paradigm can significantly improve the deblurring results’ subjective quality while achieving excellent PSNR. Experimental results demonstrate that the proposed method performs favorably against state-of-the-art methods quantitatively and qualitatively.

ITP-Pred: an interpretable method for predicting, therapeutic peptides with fused features low-dimension representation.

The peptide therapeutics market is providing new opportunities for the biotechnology and pharmaceutical industries. Therefore, identifying therapeutic peptides and exploring their properties are important. Although several studies have proposed different machine learning methods to predict peptides as being therapeutic peptides, most do not explain the decision factors of model in detail. In this work, an Interpretable Therapeutic Peptide Prediction (ITP-Pred) model based on efficient feature fusion was developed. First, we proposed three kinds of feature descriptors based on sequence and physicochemical property encoded, namely amino acid composition (AAC), group AAC and coding autocorrelation, and concatenated them to obtain the feature representation of therapeutic peptide. Then, we input it into the CNN-Bi-directional Long Short-Term Memory (BiLSTM) model to automatically learn recognition of therapeutic peptides. The cross-validation and independent verification experiments results indicated that ITP-Pred has a higher prediction performance on the benchmark dataset than other comparison methods. Finally, we analyzed the output of the model from two aspects: sequence order and physical and chemical properties, mining important features as guidance for the design of better models that can complement existing methods.

Structural elucidation and molecular dynamics study targeting the viral surface glycoproteins against HIV-2 infection

Introduction: The acquired immunodeficiency syndrome (AIDS) is the culmination of the infection by the human immunodeficiency viruses upon destruction of CD4+ lymphocytes of the host [1]. The efficacy of the available antiretroviral drugs is very limited against HIV-2 and, most importantly, none of the current drugs effectively prevents entry into the cells. HIV envelope glycoproteins mediate binding to the receptor CD4 and co-receptors at the surface of the target cell, enabling fusion with the cell membrane and viral entry [2,3]. The discovery of multiple new hit compounds that can be used as useful starting points towards drug candidates for HIV-1 and HIV-2 therapy is the main goal of this work. The glycoproteins gp120 and gp125 are critical to the receptors recognition and internalization of viral material into the cell. The study aimed to assess if the modulation of the glycoproteins activity can lead to the disturbance of the entry viral mechanism. Materials and methods: Until now, it has been marked by the use of computational techniques to study the viral surface glycoproteins as potential drug targets against HIV-1 and HIV-2 infections. A 3D structure of HIV-2ROD gp125 was generated by homology modelling, using MOE2016 and MODELLER 9v19. Additionally, to disclose the importance of the main structural features and compare with experimental results, 3D-models of six V3 mutants were also generated using the C2V3C3 domain. Additionally, molecular dynamics is being performed, using Gromacs 2006.3, in order to better characterize this protein and disclose its the biological dynamic behaviour. The structures to use in molecular dynamic simulations were prepared using MOE 2016.0802 software and further exported as PDB files. Results: It is primordial to understand the structural behavior of these domains inserted in the main structure. These mutations revealed selectively impact in the behaviour of the protein. Structurally, the mutations studied leads to a loss of aromatic features, very important for the establishment of π-π interactions, which could induce a structural preference by a specific coreceptor. Discussion and conclusions: In the absence of a crystallographic structure of HIV-2 envelope gp125 comprising variable domains, computer aided modulation is crucial to identify structural features in the variable regions that correlate with HIV-2 tropism and susceptibility to neutralization, highly associated with the mutated residues. These new insights into the structure-function relationship will help in the design of better models and into the following of the design of new small molecules capable of use under the proposal presented inhibit the attachment and binding of HIV with host cells mediated by the envelope surface glycoproteins.

Concepts in Cancer Modeling: A Brief History.

Modeling, an experimental approach to investigate complex biological systems, has significantly contributed to our understanding of cancer. Although extensive cancer research has been conducted utilizing animal models for elucidating mechanisms and developing therapeutics, the concepts in a good model design and its application have not been well elaborated. In this review, we discuss the theory underlying biological modeling and the process of producing a valuable and relevant animal model. Several renowned examples in the history of cancer research will be used to illustrate how modeling can be translatable to clinical applications. Finally, we will also discuss how the advances in cancer genomics and cancer modeling will influence each other going forward. Cancer Res; 76(20); 5921-5. ©2016 AACR.