• 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.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 Korean Information Science Society Conference
• /
• 2005.07b
• /
• pp.283-285
• /
• 2005

단백질들이 어느 세포내 소기관에 위치하는지에 대한 지식은 그들의 기능을 예측하는데 있어서 중요한 정보를 제공한다. 하지만 실험적으로 세포내 소기관 위치를 분석하는 작업은 않은 비용과 시간을 요구한다. 따라서 지금까지 단백질의 세포내 소기관 위치 예측을 위한 다양한 계산적 방법들이 개발되었으나, 효율적인 학습 데이터의 생성에 있어서 문제점을 가지고 있다. 본 논문은 기계학습 기법을 이용하여 주요 서열 구성을 선택함으로써 예측의 성능을 최대화 하는 방법을 제안하고자 한다. 실험은 효모의 단백질의 세포 내 소기관 위치 예측에 있어서 주요 아미노산 서열들을 선택함으로써 예측의 성능을 향상시키는 결과를 보이고 있다.

• 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.

• 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.

• 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
• /
• 2004.11a
• /
• pp.64-73
• /
• 2004

세포 내에서 일어나는 신호 전달 과정은 단백질간의 상호작용을 통해 수행되고 조절된다. 단백질 상호작용 데이터를 활용하여 수행된 연구로는 단백질의 기능을 유추하거나 전체 네트워크 중 다른 지역보다 더 조밀한 상호작용을 추출하여 complex 혹은 pathway를 발견하고 진화 과정을 이해하는 바탕이 되고 있다. 본 연구에서는 신호 전달 경로에 대한 사전 정보 없이 yeast 상호작용 정보와 녹색형광단백질(GFP)을 이용하여 밝혀진 4000여 개의 yeast 단백질 위치 분포 data를 이용하여 신호전달경로를 찾는 방법을 시도했다. 기존 연구에 의해 밝혀진 yeast 내의 단백질 위치 분포 결과를 보면 21개의 category에 대해 각 단백질 상호작용 분포가 다양하게 나타나고, 특정 위치에서 상호작용 빈도수가 현저히 크다는 것을 알 수 있다. 특히 두 단백질이 같은 장소에 있을 경우 상호작용 확률이 높으며, 세포 내 소기관 사이에도 상호작용의 정도가 다양함이 알려져 있다. 따라서 이러한 분포상의 특성을 고려하여 상호작용을 기반으로 하여 세포막 단백질을 출발점으로, 핵에 있는 단백질을 도착점으로 잡고, 그 사이에 존재하는 다양한 가능 경로 중에서 단백질의 위치 정보를 가중치로 사용하여 그 중 최대 가능 경로를 찾도록 구현하였다. 이와 같은 pathway 모델링은 기존에 밝혀진 pathway와의 비교를 통해 알려지지 않은 새로운 경로를 발견하고, 이전에 경로에 참여하지 않은 단백질들을 발견할 수 있고, 이미 알려진 단백질들의 새로운 기능들에 대해서도 추론할 수 있을 것이라 기대한다.

• 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.

• Journal of KIISE:Software and Applications
• /
• v.37 no.1
• /
• pp.74-79
• /
• 2010

The amino acid composition of a protein provides basic information for solving many problems in bioinformatics. We propose a new method that uses biologically relevant similarity between amino acids to determine the amino acid composition, where the BOLOSUM matrix is exploited to define a similarity measure between amino acids. Futhermore, to extract more information from a protein sequence than conventional methods for determining amino acid composition, we exploit the concepts of spectral analysis of signals such as radar and speech signals-the concepts of time-dependent analysis, time resolution, and frequency resolution. The proposed method was applied to predict subcellular localization of proteins, and showed significantly improved performance over previous methods for amino acid composition estimation.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2009.01a
• /
• pp.77-84
• /
• 2009

Intracellular signal transduction is achieved by protein-protein interaction. In this paper, we suggest performance algorithm based on Yeast protein-protein interaction and protein location information. We compare if pathways predicted with high valued weights indicate similar tendency with pathways provided in KEGG.