• 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.

• 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.

• 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%.

• Proceedings of the Korean Society for Bioinformatics Conference
• /
• 2005.09a
• /
• pp.237-242
• /
• 2005

Predicting the cellular location of an unknown protein gives a valuable information for inferring the possible function of the protein. For more accurate prediction system, we need a good feature extraction method that transforms the raw sequence data into the numerical feature vector, minimizing information loss. In this paper, we propose new methods of extracting underlying features only from the sequence data by computing pairwise sequence alignment scores. In addition, we use composition based features to improve prediction accuracy. To construct an SVM ensemble from separately trained SVM classifiers, we propose specificity based weighted majority voting. The overall prediction accuracy evaluated by the 5-fold cross-validation reached 88.53% for the eukaryotic animal data set. By comparing the prediction accuracy of various feature extraction methods, we could get the biological insight on the location of targeting information. Our numerical experiments confirm that our new feature extraction methods are very useful for predicting subcellular localization of proteins.

• Journal of Korean Society of Forest Science
• /
• v.80 no.1
• /
• pp.97-102
• /
• 1991

Subcellular location of five isozymes in Populus species was studied by isozyme analysis with plant and mitochondria. Isozymes analyzed were ADH, 6-PGD, MDH, PGI, and Diaptrorase. ADH seems to be cytosolic isozyme encoded with nuclear genes at one locus, while 6-PGD seems to be mitochondrial one. MDH showed three hands in cytosol and four other bands in mitochondria. Three cytosolic hands were showed for PGI. Diaphorase showed one mitochodrial band and two cytosofic bands which seemed to the encoded by nuclear genes at one locus.

• Biomedical Science Letters
• /
• v.18 no.2
• /
• pp.160-164
• /
• 2012

The baculovirus/insect cell expression system is of great value for the large-scale production of normal and mutant mammalian passive glucose-transport proteins heterologously for structural and functional studies. In most mammalian cells that express HepG2, this transporter isoform is predominantly located at the cell surface. However, it had been reported that heterologous expression of other membrane proteins using the baculovirus system induced highly vacuolated cytoplasmic membranes. Therefore, how a cell responds to the synthesis of large amounts of a glycoprotein could be an interesting area for investigation. In order to examine the subcellular location of the human HepG2 transport proteins when expressed in insect cells, immunofluorescence studies were carried out. Insect cells were infected with the recombinant baculovirus AcNPVHIS-GT or with wild-type virus at a MOI of 5, or were not exposed to viral infection. A high level of fluorescence displayed in cells infected with the recombinant virus indicated that transporters are expressed abundantly and present on the surface of infected Sf21 cells. The evidence for the specificity of the immunostaining was strengthened by the negative results shown in the negative controls. Distribution of the transporter protein expressed in insect cells was further revealed by making a series of optical sections through an AcNPVHIS-GT-infected cell using a confocal microscope, which permits optical sectioning of cell sample. These sections displayed intense cytoplasmic immunofluorecence surrounding the region occupied by the enlarged nucleus, indicating that the expressed protein was present not only at the cell surface but also throughout the cytoplasmic membranous structures.

• Proceedings of the Korean Information Science Society Conference
• /
• 2005.07b
• /
• pp.226-228
• /
• 2005

Predicting the cellular location of an unknown protein gives valuable information for inferring the possible function of the protein. For more accurate Prediction system, we need a good feature extraction method that transforms the raw sequence data into the numerical feature vector, minimizing information loss. In this paper we propose new methods of extracting underlying features only from the sequence data by computing pairwise sequence alignment scores. In addition, we use composition based features to improve prediction accuracy. To construct an SVM ensemble from separately trained SVM classifiers, we propose specificity based weighted majority voting . The overall prediction accuracy evaluated by the 5-fold cross-validation reached $88.53\%$ for the eukaryotic animal data set. By comparing the prediction accuracy of various feature extraction methods, we could get the biological insight on the location of targeting information. Our numerical experiments confirm that our new feature extraction methods are very useful forpredicting subcellular localization of proteins.

• Molecules and Cells
• /
• v.22 no.1
• /
• pp.97-103
• /
• 2006

Phosphoinositides are critical regulators of ion channel and transporter activity. There are multiple isomers of biologically active phosphoinositides in the plasma membrane and the different lipid species are non-randomly distributed. However, the mechanism by which cells impose selectivity and directionality on lipid movements and so generate a non-random lipid distribution remains unclear. In the present study we investigated which structural elements of phosphoinositides are responsible for their subcellular location and movement. We incubated phosphatidylinositol (PI), phosphatidylinositol 4-monophosphate (PI(4)P) and phosphatidylinositol 4,5-bisphosphate ($PI(4,5)P_2$) with short or long acyl chains in CHO and HEK cells. We show that phosphate number and acyl chain length determine cellular location and translocation movement. In CHO cells, $PI(4,5)P_2$ with a long acyl chain was released into the cytosol easily because of a low partition coefficient whereas long chain PI was released more slowly because of a high partition coefficient. In HEK cells, the cellular location and translocation movement of PI were similar to those of PI in CHO cells, whereas those of $PI(4,5)P_2$ were different; some mechanism restricted the translocation movement of $PI(4,5)P_2$, and this is in good agreement with the extremely low lateral diffusion of $PI(4,5)P_2$. In contrast to the dependence on the number of phosphates of the phospholipid head group of long acyl chain analogs, short acyl chain phospholipids easily undergo translocation movement regardless of cell type and number of phosphates in the lipid headgroup.

• Journal of KIISE:Software and Applications
• /
• v.37 no.11
• /
• pp.803-811
• /
• 2010

Since protein subcellular location and biological function are highly correlated, the prediction of protein subcellular localization can provide information about the function of a protein. In order to enhance the prediction performance, external information other than amino acids sequence information is actively exploited in many researches. This paper compares the prediction capabilities resided in amino acid sequence similarity, protein profile, gene ontology, motif, and textual information. In the experiments using PLOC dataset which has proteins less than 80% sequence similarity, sequence similarity information and gene ontology are effective information, achieving a classification accuracy of 94.8%. In the experiments using BaCelLo IDS dataset with low sequence similarity less than 30%, using gene ontology gives the best prediction accuracies, 93.2% for animals and 86.6% for fungi.