• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.18 no.10
• /
• pp.2562-2570
• /
• 2014

One of the important hints for inferring the function of unknown proteins is the knowledge about protein subcellular localization. Recently, there are considerable researches on the prediction of subcellular localization of proteins which simultaneously exist at multiple subcellular localization. In this paper, label power-set classification is improved for the accurate prediction of multiple subcellular localization. The predicted multi-labels from the label power-set classifier are combined with their prediction probability to give the final result. To find the accurate probability estimates of multi-classes, this paper employs pair-wise comparison and error-correcting output codes frameworks. Prediction experiments on protein subcellular localization show significant performance improvement.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.18 no.7
• /
• pp.1749-1756
• /
• 2014

Knowledge about protein subcellular localization provides important information about protein function. This paper improves a label power-set multi-label classification for the accurate prediction of subcellular localization of proteins which simultaneously exist at multiple subcellular locations. Among multi-label classification methods, label power-set method can effectively model the correlation between subcellular locations of proteins performing certain biological function. With constrained optimization, this paper calculates combination weights which are used in the linear combination representation of a multi-label by other multi-labels. Using these weights, the prediction probabilities of multi-labels are combined to give final prediction results. Experimental results on human protein dataset show that the proposed method achieves higher performance than other prediction methods for protein subcellular localization. This shows that the proposed method can successfully enrich the prediction probability of multi-labels by exploiting the overlapping information between multi-labels.

• Proceedings of the Korean Society for Bioinformatics Conference
• /
• 2004.11a
• /
• pp.101-106
• /
• 2004

Subcellular localization is a key functional char acteristic of proteins. With the number of sequences entering databanks rapidly increasing, the importance of developing a powerful tool to identify protein subcellular location has become self-evident. In this paper, we introduce a novel method for predic ting protein subcellular locations from protein sequences. The main idea was motivated from the observation that amino acid pair composition data is redundant. By classifying from multiple feature subsets and using many kinds of amino acid pair composition s, we forced the classifiers to make uncorrelated errors. Therefore when we combined the predictors using a voting scheme, the prediction accuracy c ould be improved. Experiment was conducted on several data sets and significant improvement has been achieve d in a jackknife test.

• Molecules and Cells
• /
• v.40 no.11
• /
• pp.828-836
• /
• 2017

Eukaryotic cells consist of a complex network of thousands of proteins present in different organelles where organelle-specific cellular processes occur. Identification of the subcellular localization of a protein is important for understanding its potential biochemical functions. In the post-genomic era, localization of unknown proteins is achieved using multiple tools including a fluorescent-tagged protein approach. Several fluorescent-tagged protein organelle markers have been introduced into dicot plants, but its use is still limited in monocot plants. Here, we generated a set of multicolored organelle markers (fluorescent-tagged proteins) based on well-established targeting sequences. We used a series of pGWBs binary vectors to ameliorate localization and co-localization experiments using monocot plants. We constructed different fluorescent-tagged markers to visualize rice cell organelles, i.e., nucleus, plastids, mitochondria, peroxisomes, golgi body, endoplasmic reticulum, plasma membrane, and tonoplast, with four different fluorescent proteins (FPs) (G3GFP, mRFP, YFP, and CFP). Visualization of FP-tagged markers in their respective compartments has been reported for dicot and monocot plants. The comparative localization of the nucleus marker with a nucleus localizing sequence, and the similar, characteristic morphology of mCherry-tagged Arabidopsis organelle markers and our generated organelle markers in onion cells, provide further evidence for the correct subcellular localization of the Oryza sativa (rice) organelle marker. The set of eight different rice organelle markers with four different FPs provides a valuable resource for determining the subcellular localization of newly identified proteins, conducting co-localization assays, and generating stable transgenic localization in monocot plants.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.18 no.4
• /
• pp.992-999
• /
• 2014

This paper presents an extensive experimental comparison of a variety of multi-label learning methods for the accurate prediction of subcellular localization of proteins which simultaneously exist at multiple subcellular locations. We compared several methods from three categories of multi-label classification algorithms: algorithm adaptation, problem transformation, and meta learning. Experimental results are analyzed using 12 multi-label evaluation measures to assess the behavior of the methods from a variety of view-points. We also use a new summarization measure to find the best performing method. Experimental results show that the best performing methods are power-set method pruning a infrequently occurring subsets of labels and classifier chains modeling relevant labels with an additional feature. futhermore, ensembles of many classifiers of these methods enhance the performance further. The recommendation from this study is that the correlation of subcellular locations is an effective clue for classification, this is because the subcellular locations of proteins performing certain biological function are not independent but correlated.

• Animal cells and systems
• /
• v.5 no.3
• /
• pp.225-229
• /
• 2001

Nek2 is a mammalian protein kinase that is structurally homologous to NIMA, a mitotic regulator in Aspergillus nidulans. To understand cellular processes in which Nek2 participates during mammalian development, we investigated the expression and subcellular localization of Nek2 in vivo. The Nek2 protein was detected in spermatocytes and in a fraction of actively dividing ovarian follicle cells and of embryonic tissues. We also observed that Nek2 was localized in both the nucleus and centrosome in embryonic cells. Such localization pattern supports the proposal that Nek2 is a mitotic regulator that is involved in multiple cell cycle events during mammalian development.

• Asian Pacific Journal of Cancer Prevention
• /
• v.15 no.16
• /
• pp.6899-6904
• /
• 2014

NGAL (neutrophil gelatinase-associated lipocalin) is a novel cancer-related protein involves multiple functions in many cancers and other diseases. We previously overexpressed NGAL to analyze its role in esophageal squamous cell carcinoma (ESCC). In this study, a protein-protein interaction (PPI) was constructed and the shortest paths from NGAL to transcription factors in the network were analyzed. We found 28 shortest paths from NGAL to RELA, most of them obeying the principle of extracellular to cytoplasm, then nucleus. These shortest paths were also prioritized according to their normalized intensity from the microarray by the order of interaction cascades. A systems approach was developed in this study by linking differentially expressed genes with publicly available PPI data, Gene Ontology and subcellular localizaton for the integrated analyses. These shortest paths from NGAL to DEG transcription factors or other transcription factors in the PPI network provide important clues for future experimental identification of new pathways.

• Biomedical Science Letters
• /
• v.7 no.2
• /
• pp.59-64
• /
• 2001

Nebulin is an unusually large actin-binding protein specific to the skeletal muscle of vertebrates. The correlation of nebulin size with thin filament length have led to the suggestion that nebulin acts as a molecular ruler for the length of thin filaments. An SH3 domain occupies the C terminus of nebulin, in the sarcomeric Z-disk and is preceded by a 120-residue stretch containing multiple putative phosphorylation sites. SH3 domain mediates protein-protein interaction involved in the subcellular localization of proteins, cytoskeletal organization and signal transduction. However the binding partner and physiological role of nebulin SH3 domains remains unknown. Using the yeast two-hybrid system, we identified supervillin, an actin-binding protein, as a nebulin SH3 domain-interacting protein. The SH3 domain of nebulin binds to the sequence encoding amino acids 977 to 1335 of supervillin. But the sequence encoding amino acids 977 to 1335 displays weaker binding than the sequence encoding amino acids 977 to 1788.

• 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 Applied Biological Chemistry
• /
• v.53 no.4
• /
• pp.189-194
• /
• 2010

We confirmed the hypo-osmotic shock strengths and duration, different type of vectors, and subcelluar localization to identify the optimum analysis condition of plant aquaporin activity in Xenopus ooctye using Arabidopsis thaliana AtPIP2-1 gene. Six minutes and 1/5ND buffer hypoosmotic shock treatment was the best condition to show the maximum swelling of Xenopus oocytes where AtPIP2-1 was expressed using pcDNA3.1 vector. AtPIP2-1 protein was expressed more efficiently in pGEMHE vector which has 5' and 3' UTR (untranslation region) of Xenopus ${\beta}$-GLOBIN gene in multiple cloning site than in pcDNA3.1 vector. Also green fluorescence of GFP fused to AtPIP2-1 was detected onto oocyte plasmamembrane where is the proper subcellular localization target of AtPIP2-1.