• 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.

• Proceedings of the Korea Contents Association Conference
• /
• 2007.11a
• /
• pp.12-16
• /
• 2007

The function of a protein is closely co-related with its subcellular location(s). Given a protein sequence, therefore, how to determine its subcellular location is a vitally important problem. We have developed a new prediction method for protein subcellular location(s), which is based on n-gram feature extraction and k-nearest neighbor (kNN) classification algorithm. It classifies a protein sequence to one or more subcellular compartments based on the locations of top k sequences which show the highest similarity weights against the input sequence. The similarity weight is a kind of similarity measure which is determined by comparing n-gram features between two sequences. Currently our method extract penta-grams as features of protein sequences, computes scores of the potential localization site(s) using kNN algorithm, and finally presents the locations and their associated scores. We constructed a large-scale data set of protein sequences with known subcellular locations from the SWISS-PROT database. This data set contains 51,885 entries with one or more known subcellular locations. Our method show very high prediction precision of about 93% for this data set, and compared with other method, it also showed comparable prediction improvement for a test collection used in a previous work.

• 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.

• YAKHAK HOEJI
• /
• v.38 no.1
• /
• pp.12-19
• /
• 1994

Capsaicin(8-methyl-N-vanillyl-6-nonenamide) is the principal pungent component of Capsicum fruits. This work is directed to the capsaicin-hydrolyzing enzyme playing a key role in the rate limiting and critical step of capsaicin metabolism. In order to get precise information on the enzyme's subcellular location, rat liver homogenate was divided into six subcellular fractions by differential centrifugation technique: crude nuclear pellet, PNS(post nuclear supernatant) fraction, lysosomal pellet, cytosol, Tris wash fraction, micrisomes. Capsaicin-hydrolysing enzyme activity was analysed by high performance liquid chromatography(HPLC). This enzyme was found at the highest specific activity in the microsomal fraction and co-distributed with marker enzymes of the endoplasmic reticulum, NADPH-cytochrome c reductase and nucleoside diphosphatase. This is compatible with the result of ninhydrin color reaction of vanillylamine, primary metabolite of capsaicin hydrolysis, on thin layer chromatography(TLC). This enzyme is most active at pH $8.0{\sim}9.0$. Definite subcellular location of this enzyme will make it easy to proceed with further study.

• 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.

• Biomaterials Research
• /
• v.22 no.4
• /
• pp.221-234
• /
• 2018

Background: Interest in subcellular organelle-targeting theranostics is substantially increasing due to the significance of subcellular organelle-targeting drug delivery for maximizing therapeutic effects and minimizing side effects, as well as the significance of theranostics for delivering therapeutics at the correct locations and doses for diseases throughout diagnosis. Among organelles, mitochondria have received substantial attention due to their significant controlling functions in cells. Main body: With the necessity of subcellular organelle-targeting drug delivery and theranostics, examples of mitochondria-targeting moieties and types of mitochondria-targeting theranostics were introduced. In addition, the current studies of mitochondria-targeting theranostic chemicals, chemical conjugates, and nanosystems were summarized. Conclusion: With the current issues of mitochondria-targeting theranostic chemicals, chemical conjugates, and nanosystems, their potentials and alternatives are discussed.

• 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.

• The KIPS Transactions:PartB
• /
• v.15B no.4
• /
• pp.375-382
• /
• 2008

A protein's subcellular localization is considered an essential part of the description of its associated biomolecular phenomena. As the volume of biomolecular reports has increased, there has been a great deal of research on text mining to detect protein subcellular localization information in documents. It has been argued that linguistic information, especially syntactic information, is useful for identifying the subcellular localizations of proteins of interest. However, previous systems for detecting protein subcellular localization information used only shallow syntactic parsers, and showed poor performance. Thus, there remains a need to use a full syntactic parser and to apply deep linguistic knowledge to the analysis of text for protein subcellular localization information. In addition, we have attempted to use semantic information from the WordNet thesaurus. To improve performance in detecting protein subcellular localization information, this paper proposes a three-step method based on a full syntactic dependency parser and WordNet thesaurus. In the first step, we constructed syntactic dependency paths from each protein to its location candidate, and then converted the syntactic dependency paths into dependency trees. In the second step, we retrieved root information of the syntactic dependency trees. In the final step, we extracted syn-semantic patterns of protein subtrees and location subtrees. From the root and subtree nodes, we extracted syntactic category and syntactic direction as syntactic information, and synset offset of the WordNet thesaurus as semantic information. According to the root information and syn-semantic patterns of subtrees from the training data, we extracted (protein, localization) pairs from the test sentences. Even with no biomolecular knowledge, our method showed reasonable performance in experimental results using Medline abstract data. Our proposed method gave an F-measure of 74.53% for training data and 58.90% for test data, significantly outperforming previous methods, by 12-25%.

• The Korean Journal of Physiology
• /
• v.24 no.2
• /
• pp.331-344
• /
• 1990

What makes glucose transport function sensitive to insulin in one cell type such as adipocyte, and insensitive in another such as liver cells is unresolved question at this time. Recently it is known that insulin stimulates glucose transport in adipocytes largely by redistributing transporter from the storage pool that is included in a low density microsomal fraction to plasma membrane. Therefore, insulin sensitivity may depend upon the relative distribution of gluscose transporters between the plasma membrane and in an intracellular storage compartment. In hepatocytes, the subcellular distribution of glucose transporter is less well documented. It is thus possible that the apparent insensitivity of the hepatocyte system could be either due to lack of the constitutively maintained, intracellular storage pool of glucose transporter or lack of insulin-mediated transporter translocation mechanism in this cell. In this study, I examined if any intracellular glucose transporter pool exists in hepatocytes and this pool is affected by insulin. The results obtained summarized as followings: 1) Distribution of subcellular fractions of hepatocyte showed that there are $24.9{\pm}1.3%$ of plasma membrane, $36.9{\pm}1.7%$ of nucleus-mitochondria enriched fraction, $23.5{\pm}1.2%$ of lysosomal fraction, $9.6{\pm}1.0%$ of high density microsomal fraction and $4.9{\pm}0.5%$ of low density microsomal fraction. 2) In adipocyte, there were $29.9{\pm}2.6%$ of plasma membrane, $19.4{\pm}1.9%$ of nucleus-mitochondria enriched fraction, $26.7{\pm}1.8%$ of high density microsomal fraction and $23.9{\pm}2.1%$ of low density microsomal fraction. 3) Surface labelling of sodium borohydride revealed that plasma membrane contaminated to lysosomal fraction by $26.8{\pm}2.8%$, high density microsomal fraction by $8.3{\pm}1.3%$ and low density microsomal fraction by $1.7{\pm}0.4%$ respectively. 4) Cytochalasin B bound to all of subcellular fractions with a Kd of $1.0{\times}10^{-6}M$. 5) Photolabelling of cytochalasin B to subcellular fractions occurred on 45 K dalton protein band, a putative glucose transporter and D-glucose inhibited the photolabelling. 6) Insulin didn't affect on the distribution of subcellular fractions and translocation of intracellular glucose transporters of hepatocytes. 7) HEGT reconstituted into hepatocytes was largely associated with plasma membrane and very little was found in low density microsomal fraction which equals to the native glucose transporter distribution. Insulin didn't affect on the distribution of exogeneous glucose transporter in hepatocytes. From the above results it is concluded that insulin insensitivity of hepatocyte may due to lack of intracellular storage pool of glucose transporter and thus intracellular storage pool of glucose transporter is an essential feature of the insulin action.

• Molecules and Cells
• /
• v.27 no.5
• /
• pp.539-546
• /
• 2009

In Saccharomyces cerevisiae, ribosomal protein L7, one of the ~46 ribosomal proteins of the 60S subunit, is encoded by paralogous RPL7A and RPL7B genes. The amino acid sequence identity between RPl7a and RPl7b is 97 percent; they differ by only 5 amino acid residues. Interestingly, despite the high sequence homology, Rpl7b is detected in both the cytoplasm and the nucleolus, whereas Rpl7a is detected exclusively in the cytoplasm. A site-directed mutagenesis experiment revealed that the change in the amino acid sequence of Rpl7b does not influence its subcellular localization. In addition, introns of RPL7A and RPL7B did not affect the subcellular localization of Rpl7a and Rpl7b. Remarkably, Rpl7b was detected exclusively in the cytoplasm in rpl7a knockout mutant, and overexpression of Rpl7a resulted in its accumulation in the nucleolus, indicating that the subcellular localization of Rpl7a and Rpl7b is influenced by the intracellular level of Rpl7a. Rpl7b showed a wide range of localization patterns, from exclusively cytoplasmic to exclusively nucleolar, in knockout mutants for some rRNA-processing factors, nuclear pore proteins, and large ribosomal subunit assembly factors. Rpl7a, however, was detected exclusively in the cytoplasm in these mutants. Taken together, these results suggest that although Rpl7a and Rpl7b are paralogous and functionally replaceable with each other, their precise physiological roles may not be identical.