Using Deep Neural Networks to Improve the Performance of Protein–Protein Interactions Prediction

2020 ◽  
Vol 34 (13) ◽  
pp. 2052012 ◽  
Author(s):  
Yuan-Miao Gui ◽  
Ru-Jing Wang ◽  
Xue Wang ◽  
Yuan-Yuan Wei
Keyword(s):  
Neural Networks ◽  
Protein Interactions ◽  
Deep Neural Networks ◽  
Molecular Mechanisms ◽  
Extraction Methods ◽  
Amino Acid Sequences ◽  
Prediction Methods ◽  
Protein Protein Interactions ◽  
Local Descriptor ◽  
Auto Covariance

Protein–protein interactions (PPIs) help to elucidate the molecular mechanisms of life activities and have a certain role in promoting disease treatment and new drug development. With the advent of the proteomics era, some PPIs prediction methods have emerged. However, the performances of these PPIs prediction methods still need to be optimized and improved. In order to optimize the performance of the PPIs prediction methods, we used the dropout method to reduce over-fitting by deep neural networks (DNNs), and combined with three types of feature extraction methods, conjoint triad (CT), auto covariance (AC) and local descriptor (LD), to build DNN models based on amino acid sequences. The results showed that the accuracy of the CT, AC and LD increased from 97.11% to 98.12%, 96.84% to 98.17%, and 95.30% to 95.60%, respectively. The loss values of the CT, AC and LD decreased from 27.47% to 14.96%, 65.91% to 17.82% and 36.23% to 15.34%, respectively. Experimental results show that dropout can optimize the performances of the DNN models. The results can provide a resource for scholars in future studies involving the prediction of PPIs. The experimental code is available at https://github.com/smalltalkman/hppi-tensorflow .

scholarly journals An Efficient Feature Extraction Technique Based on Local Coding PSSM and Multifeatures Fusion for Predicting Protein-Protein Interactions

2019 ◽  
Vol 15 ◽  
pp. 117693431987992 ◽  
Author(s):  
Ji-Yong An ◽  
Yong Zhou ◽  
Yu-Jun Zhao ◽  
Zi-Ji Yan
Keyword(s):  
Feature Extraction ◽  
Protein Interactions ◽  
Functional Organization ◽  
Extraction Methods ◽  
Amino Acid Sequences ◽  
Evolutionary Information ◽  
Support Vector ◽  
Svm Classifier ◽  
Protein Protein Interactions ◽  
Local Coding

Background: Increasing evidence has indicated that protein-protein interactions (PPIs) play important roles in various aspects of the structural and functional organization of a cell. Thus, continuing to uncover potential PPIs is an important topic in the biomedical domain. Although various feature extraction methods with machine learning approaches have enhanced the prediction of PPIs. There remains room for improvement by developing novel and effective feature extraction methods and classifier approaches to identify PPIs. Method: In this study, we proposed a sequence-based feature extraction method called LCPSSMMF, which combined local coding position-specific scoring matrix (PSSM) with multifeatures fusion. First, we used a novel local coding method based on PSSM to build a new PSSM (CPSSM); the advantage of this method is that it incorporated global and local feature extraction, which can account for the interactions between residues in both continuous and discontinuous regions of amino acid sequences. Second, we adopted 2 different feature extraction methods (Local Average Group [LAG] and Bigram Probability [BP]) to capture multiple key feature information by employing the evolutionary information embedded in the CPSSM matrix. Finally, feature vectors were acquired by using multifeatures fusion method. Result: To evaluate the performance of the proposed feature extraction approach, we employed support vector machine (SVM) as a prediction classifier and applied this method to yeast and human PPI datasets. The prediction accuracies of LCPSSMMF were 93.43% and 90.41% on the yeast and human datasets, respectively. Moreover, we also compared the proposed method with the previous sequence-based approaches on the yeast datasets by using the same SVM classifier. The experimental results indicated that the performance of LCPSSMMF significantly exceeded that of several other state-of-the-art methods. It is proven that the LCPSSMMF approach can capture more local and global discriminatory information than almost all previous methods and can function remarkably well in identifying PPIs. To facilitate extensive research in future proteomics studies, we developed a LCPSSMMFSVM server, which is freely available for academic use at http://219.219.62.123:8888/LCPSSMMFSVM .

DeepPPI: Boosting Prediction of Protein–Protein Interactions with Deep Neural Networks

2017 ◽  
Vol 57 (6) ◽  
pp. 1499-1510 ◽  
Author(s):  
Xiuquan Du ◽  
Shiwei Sun ◽  
Changlin Hu ◽  
Yu Yao ◽  
Yuanting Yan ◽  
...  
Keyword(s):  
Neural Networks ◽  
Protein Interactions ◽  
Deep Neural Networks ◽  
Protein Protein Interactions

Structure, Function, Involvement in Diseases and Targeting of 14-3-3 Proteins: An Update

2018 ◽  
Vol 25 (1) ◽  
pp. 5-21 ◽  
Author(s):  
Ylenia Cau ◽  
Daniela Valensin ◽  
Mattia Mori ◽  
Sara Draghi ◽  
Maurizio Botta
Keyword(s):  
Protein Interactions ◽  
Molecular Mechanisms ◽  
Physiological Role ◽  
Specific Protein ◽  
Protein Protein Interactions ◽  
Cellular Processes ◽  
Protein Partners ◽  
High Sequence Homology ◽  
Small Molecule Modulators

14-3-3 is a class of proteins able to interact with a multitude of targets by establishing protein-protein interactions (PPIs). They are usually found in all eukaryotes with a conserved secondary structure and high sequence homology among species. 14-3-3 proteins are involved in many physiological and pathological cellular processes either by triggering or interfering with the activity of specific protein partners. In the last years, the scientific community has collected many evidences on the role played by seven human 14-3-3 isoforms in cancer or neurodegenerative diseases. Indeed, these proteins regulate the molecular mechanisms associated to these diseases by interacting with (i) oncogenic and (ii) pro-apoptotic proteins and (iii) with proteins involved in Parkinson and Alzheimer diseases. The discovery of small molecule modulators of 14-3-3 PPIs could facilitate complete understanding of the physiological role of these proteins, and might offer valuable therapeutic approaches for these critical pathological states.

Quantitative analysis of the interactions between HIV-1 integrase and retroviral reverse transcriptases

2008 ◽  
Vol 412 (1) ◽  
pp. 163-170 ◽  
Author(s):  
Alon Herschhorn ◽  
Iris Oz-Gleenberg ◽  
Amnon Hizi
Keyword(s):  
Conformational Changes ◽  
Protein Interactions ◽  
Molecular Mechanisms ◽  
Reaction Model ◽  
Protein Protein Interactions ◽  
Common Site ◽  
Leukaemia Virus ◽  
Reverse Transcriptases ◽  
Interaction Kinetics ◽  
Hiv 1

The RT (reverse transcriptase) of HIV-1 interacts with HIV-1 IN (integrase) and inhibits its enzymatic activities. However, the molecular mechanisms underling these interactions are not well understood. In order to study these mechanisms, we have analysed the interactions of HIV-1 IN with HIV-1 RT and with two other related RTs: those of HIV-2 and MLV (murine-leukaemia virus). All three RTs inhibited HIV-1 IN, albeit to a different extent, suggesting a common site of binding that could be slightly modified for each one of the studied RTs. Using surface plasmon resonance technology, which monitors direct protein–protein interactions, we performed kinetic analyses of the binding of HIV-1 IN to these three RTs and observed interesting binding patterns. The interaction of HIV-1 RT with HIV-1 IN was unique and followed a two-state reaction model. According to this model, the initial IN–RT complex formation was followed by a conformational change in the complex that led to an elevation of the total affinity between these two proteins. In contrast, HIV-2 and MLV RTs interacted with IN in a simple bi-molecular manner, without any apparent secondary conformational changes. Interestingly, HIV-1 and HIV-2 RTs were the most efficient inhibitors of HIV-1 IN activity, whereas HIV-1 and MLV RTs showed the highest affinity towards HIV-1 IN. These modes of direct protein interactions, along with the apparent rate constants calculated and the correlations of the interaction kinetics with the capacity of the RTs to inhibit IN activities, are all discussed.

scholarly journals Significance of thiol-disulfide balance in SARS-CoV-2 infection

2021 ◽  
Vol 72 (3) ◽  
pp. 30-36
Author(s):  
Tatjana Simić
Keyword(s):  
Cell Surface ◽  
Host Cell ◽  
Protein Interactions ◽  
Viral Entry ◽  
Molecular Mechanisms ◽  
Alkylating Agents ◽  
Protein S ◽  
Protein Protein Interactions ◽  
Virus Surface ◽  
Host Cell Surface

Studies of the molecular mechanisms regarding interaction of different viruses with receptors on the host cell surface have shown that the viral entry depends on the specific relationship between free thiol (SH) groups and disulfides on the virus surface, as well as the thiol disulfide balance on the host cell surface. The presence of oxidizing compounds or alkylating agents, which disturb the thiol-disulfide balance on the surface of the virus, can also affect its infectious potential. Disturbed thiol-disulfide balance may also influence protein-protein interactions between SARS-CoV-2 protein S and ACE2 receptors of the host cell. This review presents the basic mechanisms of maintaining intracellular and extracellular thiol disulfide balance and previous experimental and clinical evidence in favor of impaired balance in SARS-CoV-2 infection. Besides, the results of the clinical application or experimental analysis of compounds that induce changes in the thiol disulfide balance towards reduction of disulfide bridges in proteins of interest in COVID-19 infection are presented.

scholarly journals Search for New Candidate Genes Involved in the Comorbidity of Asthma and Hypertension Based on Automatic Analysis of Scientific Literature

2018 ◽  
Vol 15 (4) ◽  
Author(s):  
Olga V. Saik ◽  
Pavel S. Demenkov ◽  
Timofey V. Ivanisenko ◽  
Elena Yu. Bragina ◽  
Maxim B. Freidin ◽  
...  
Keyword(s):  
Protein Interactions ◽  
Gene Networks ◽  
Molecular Mechanisms ◽  
Molecular Genetic ◽  
Genetic Networks ◽  
Positive Sign ◽  
Phenotypic Traits ◽  
Protein Protein Interactions ◽  
Scientific Publications ◽  
Associative Gene Networks

AbstractComorbid states of diseases significantly complicate diagnosis and treatment. Molecular mechanisms of comorbid states of asthma and hypertension are still poorly understood. Prioritization is a way for identifying genes involved in complex phenotypic traits. Existing methods of prioritization consider genetic, expression and evolutionary data, molecular-genetic networks and other. In the case of molecular-genetic networks, as a rule, protein-protein interactions and KEGG networks are used. ANDSystem allows reconstructing associative gene networks, which include more than 20 types of interactions, including protein-protein interactions, expression regulation, transport, catalysis, etc. In this work, a set of genes has been prioritized to find genes potentially involved in asthma and hypertension comorbidity. The prioritization was carried out using well-known methods (ToppGene and Endeavor) and a cross-talk centrality criterion, calculated by analysis of associative gene networks from ANDSystem. The identified genes, including IL1A, CD40LG, STAT3, IL15, FAS, APP, TLR2, C3, IL13 and CXCL10, may be involved in the molecular mechanisms of comorbid asthma/hypertension. An analysis of the dynamics of the frequency of mentioning the most priority genes in scientific publications revealed that the top 100 priority genes are significantly enriched with genes with increased positive dynamics, which may be a positive sign for further studies of these genes.

Sign in / Sign up

Export Citation Format

Share Document