• Journal of Information Processing Systems
• /
• v.8 no.3
• /
• pp.459-470
• /
• 2012

Recently, high-throughput technologies such as the two-hybrid system, protein chip, Mass Spectrometry, and the phage display have furnished a lot of data on protein-protein interactions (PPIs), but the data has not been accurate so far and the quantity has also been limited. In this respect, computational techniques for the prediction and validation of PPIs have been developed. However, existing computational methods do not take into account the fact that a PPI is actually originated from the interactions of domains that each protein contains. So, in this work, the information on domain modules of individual proteins has been employed in order to find out the protein interaction relationship. The system developed here, WASPI (Web-based Assistant System for Protein-protein interaction Inference), has been implemented to provide many functional insights into the protein interactions and their domains. To achieve those objectives, several preprocessing steps have been taken. First, the domain module information of interacting proteins was extracted by taking advantage of the InterPro database, which includes protein families, domains, and functional sites. The InterProScan program was used in this preprocess. Second, the homology comparison with the GO (Gene Ontology) and COG (Clusters of Orthologous Groups) with an E-value of $10^{-5}$, $10^{-3}$ respectively, was employed to obtain the information on the function and annotation of each interacting protein of a secondary PPI database in the WASPI. The BLAST program was utilized for the homology comparison.

• Mass Spectrometry Letters
• /
• v.9 no.2
• /
• pp.51-55
• /
• 2018

Capture of non-glycoproteins during lectin affinity chromatography is frequently observed, although it would seem to be anomalous. In actuality, lectin affinity chromatography works at post-translational modification (PTM) sites on a glycoprotein which is not involved in protein-protein interactions (PPIs). In this study, serial affinity column set (SACS) using lectins followed by proteomics methods was used to identify PPI mechanisms of captured proteins in human plasma. MetaCore, STRING, Ingenuity Pathway Analysis (IPA), and IntAct were individually used to elucidate the interactions of the identified abundant proteins and to obtain the corresponding interaction maps. The abundant non-glycoproteins were captured with the binding to the selected glycoproteins. Therefore, depletion process in sample pretreatment for abundant protein removal should be considered with more caution because it may lose precious disease-related low abundant proteins through PPIs of the removed abundant proteins in human plasma during the depletion process in biomarker discovery. Glycoproteins bearing specific glycans are frequently associated with cancer and can be specifically isolated by lectin affinity chromatography. Therefore, SACS using Lycopersicon esculentum lectin (LEL) can also be used to study disease interactomes.

• BMB Reports
• /
• v.51 no.10
• /
• pp.526-531
• /
• 2018

Protein-Protein Interactions (PPIs) play essential roles in diverse biological processes and their misregulations are associated with a wide range of diseases. Especially, the growing attention to PPIs as a new class of therapeutic target is increasing the need for an efficient method of cell-based PPI analysis. Thus, we newly developed a robust PPI assay (SeePPI) based on the co-translocation of interacting proteins to the discrete subcellular compartment 'processing body' (p-body) inside living cells, enabling a facile analysis of PPI by the enriched fluorescent signal. The feasibility and strength of SeePPI (${\underline{S}}ignal$ ${\underline{e}}nhancement$ ${\underline{e}}xclusively$ on ${\underline{P}}-body$ for ${\underline{P}}rotein-protein$ ${\underline{I}}nteraction$) assay was firmly demonstrated with FKBP12/FRB interaction induced by rapamycin within seconds in real-time analysis of living cells, indicating its recapitulation of physiological PPI dynamics. In addition, we applied p53/MDM2 interaction and its dissociation by Nutlin-3 to SeePPI assay and further confirmed that SeePPI was quantitative and well reflected the endogenous PPI. Our SeePPI assay will provide another useful tool to achieve an efficient analysis of PPIs and their modulators in cells.

• International Journal of Computer Science & Network Security
• /
• v.21 no.3
• /
• pp.41-47
• /
• 2021

Detection of protein-protein interactions (PPIs) remains essential for the development of therapies against diseases. Experimental studies to detect PPI are longer and more expensive. Today, with the availability of PPI data, several computer models for predicting PPIs have been proposed. One of the big challenges in this task is feature extraction. The relevance of the information extracted by some extraction techniques remains limited. In this work, we first propose an extraction method based on correlation relationships between the physicochemical properties of amino acids. The proposed method uses a correlation matrix obtained from the hydrophobicity and hydrophilicity properties that it then integrates in the calculation of the bigram. Then, we use the SVM algorithm to detect the presence of an interaction between 2 given proteins. Experimental results show that the proposed method obtains better performances compared to the approaches in the literature. It obtains performances of 94.75% in accuracy, 95.12% in precision and 96% in sensitivity on human HPRD protein data.

• KIISE Transactions on Computing Practices
• /
• v.23 no.3
• /
• pp.194-198
• /
• 2017

In this paper, we propose a revised Deep Convolutional Neural Network (DCNN) model to extract Protein-Protein Interaction (PPIs) from the scientific literature. The proposed method has the merit of improving performance by applying various global features in addition to the simple lexical features used in conventional relation extraction approaches. In the experiments using AIMed, which is the most famous collection used for PPI extraction, the proposed model shows state-of-the art scores (78.0 F-score) revealing the best performance so far in this domain. Also, the paper shows that, without conducting feature engineering using complicated language processing, convolutional neural networks with embedding can achieve superior PPIE performance.

• Asian Pacific Journal of Cancer Prevention
• /
• v.17 no.3
• /
• pp.1003-1008
• /
• 2016

Breast cancer is now the leading cause of cancer death in women worldwide. Cancer progression is driven not only by cancer cell intrinsic alterations and interactions with tumor microenvironment, but also by systemic effects. Integration of multiple profiling data may provide insights into the underlying molecular mechanisms of complex systemic processes. We performed a bioinformatic analysis of two public available microarray datasets for breast tumor stroma and peripheral blood mononuclear cells, featuring integrated transcriptomics data, protein-protein interactions (PPIs) and protein subcellular localization, to identify genes and biological pathways that contribute to dialogue between tumor stroma and the peripheral circulation. Genes of the integrin family as well as CXCR4 proved to be hub nodes of the crosstalk network and may play an important role in response to stroma-derived chemoattractants. This study pointed to potential for development of therapeutic strategies that target systemic signals travelling through the circulation and interdict tumor cell recruitment.

• Journal of the Korean Society for Library and Information Science
• /
• v.45 no.2
• /
• pp.251-275
• /
• 2011

In this paper, we propose a novel kernel called a semantic parse tree kernel that extends the parse tree kernel previously studied to extract protein-protein interactions(PPIs) and shown prominent results. Among the drawbacks of the existing parse tree kernel is that it could degenerate the overall performance of PPI extraction because the kernel function may produce lower kernel values of two sentences than the actual analogy between them due to the simple comparison mechanisms handling only the superficial aspects of the constituting words. The new kernel can compute the lexical semantic similarity as well as the syntactic analogy between two parse trees of target sentences. In order to calculate the lexical semantic similarity, it incorporates context-based word sense disambiguation producing synsets in WordNet as its outputs, which, in turn, can be transformed into more general ones. In experiments, we introduced two new parameters: tree kernel decay factors, and degrees of abstracting lexical concepts which can accelerate the optimization of PPI extraction performance in addition to the conventional SVM's regularization factor. Through these multi-strategic experiments, we confirmed the pivotal role of the newly applied parameters. Additionally, the experimental results showed that semantic parse tree kernel is superior to the conventional kernels especially in the PPI classification tasks.