단백질의 세포내 위치 예측을 위한 다중레이블 분류 방법의 성능 비교 = A Performance Comparison of Multi-Label Classification Methods for Protein Subcellular Localization Prediction

국문 초록 (Abstract)

단백질이 존재하는 세포내의 다중 위치를 정확하게 예측하기 위하여 다중레이블 학습 방법을 광범위하게 비교한다. 이를 위하여 다중레이블 분류의 접근 방법인 알고리즘 적응, 문제 변환, 메타 학습의 여러 방법을 비교 평가한다. 다양한 관점에서 다중레이블 분류 방법의 특성을 평가하기 위하여 12가지 평가 척도를 사용하였고, 최적의 성능을 보이는 방법을 찾기 위하여 새로운 요약 척도를 사용하였다. 비교 실험 결과, 흔하지 않은 다중레이블 집합을 가지치기 하는 멱집합 방법과, 관련 레이블들을 추가된 특징으로 나타내는 분류기-체인 방법의 성능이 높았다. 또한, 이들 방법들로 구성된 여러 개의 분류기를 조합하면 더욱 성능이 향상되었다. 즉, 세포내 위치간의 연관관계를 사용하는 것이 예측에 효과적인데, 특정 생물학적 기능을 수행하는 단백질의 세포내 위치들의 관계는 독립적이지 않고 서로 관련되어 있기 때문이라 판단된다.

다국어 초록 (Multilingual Abstract)

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.

참고문헌 (Reference)

1 S. Wan, "mGOASVM : multilabel protein subcellular localization based on gene ontology and support vector machines" 13 : 290-, 2012

2 W.-Z. Lin, "iLoc-Animal : a multi-label learning classifier for predicting subcellular localization of animal proteins" 9 (9): 634-644, 2013

3 S.-M. Chi, "WegoLoc : accurate prediction of protein subcellular localization using weighted gene ontology terms" 28 (28): 1028-1030, 2012

4 M. Hall, "The WEKA Data Mining Software : An Update" 11 (11): 10-18, 2009

5 G. Tsoumakas, "Random k-Labelsets for Multi-Label Classification" 23 (23): 1079-1089, 2011

6 S. -M. Chi, "Prediction of protein subcellular localization by weighted gene ontology terms" 399 (399): 402-405, 2010

7 X. Wang, "Multilabel learning via random label selection for protein subcellular multilocations prediction" 10 (10): 436-446, 2013

8 G.-Z. Li, "Multilabel learning for protein subcellular location prediction" 11 (11): 237-243, 2012

9 J. Furnkranz, "Multilabel classification via calibrated label ranking" 73 (73): 133-153, 2008

10 M.-L. Zhang, "Multi-label neural networks with applications to functional genomics and text cate gorization" 18 (18): 1338-1351, 2006

11 S. Mei, "Multi-label multi-kernel transfer learning for human protein subcellular localization" 7 (7): e37716-, 2012

12 J. Read, "Multi-Label Classification using Ensembles of Pruned Sets" 995-1000, 2008

13 M.-L. Zhang, "Ml-knn: A lazy learning approach to multi-label learning" 40 (40): 2038-2048, 2007

14 J. He, "Imbalanced multi-modal multilabel learning for subcellular localization prediction of human proteins with both single and multiple sites" 7 (7): e37155-, 2012

15 G. Tsoumakas, "Effective and Efficient Multilabel Classification in Domains with Large Number of Labels" 30-44, 2008

16 G. Tsoumakas, "Data Mining and Knowledge Discovery Handbook" Springer 667-685, 2010

17 G. Tsoumakas, "Correlation-Based Pruning of Stacked Binary Relevance Models for Multi-Label Learning" 101-116, 2009

18 W. Cheng, "Combining instance-based learning and logistic regression for multilabel classification" 76 (76): 211-225, 2009

19 G. Nasierding, "Clustering Based Multi-Label Classification for Image Annotation and Retrieval" 4514-4519, 2009

20 J. Read, "Classifier Chains for Multi-label Classification" 85 (85): 335-359, 2011

21 R. E. Schapire, "BoosTexter: A boostingbased system for text categorization" 39 (39): 135-168, 2000

22 G. Madjarov, "An extensive experimental comparison of methods for multi-label learning" 45 (45): 3084-3104, 2012

23 E. Spyromitros, "An Empirical Study of Lazy Multilabel Classification Algorithms" 401-406, 2008

24 H.-B. Shen, "A top-down approach to enhance the power of predicting human protein subcellular localization: Hum-mPLoc 2.0" 394 (394): 269-274, 2009

25 M.-L. Zhang, "A review on multi-label learning algorithms" IEEE transactions on knowledge and data engineering