An SVM-based system for predicting protein subnuclear localizations
© Lei and Dai; licensee BioMed Central Ltd. 2005
Received: 09 May 2005
Accepted: 07 December 2005
Published: 07 December 2005
The large gap between the number of protein sequences in databases and the number of functionally characterized proteins calls for the development of a fast computational tool for the prediction of subnuclear and subcellular localizations generally applicable to protein sequences. The information on localization may reveal the molecular function of novel proteins, in addition to providing insight on the biological pathways in which they function. The bulk of past work has been focused on protein subcellular localizations. Furthermore, no specific tool has been dedicated to prediction at the subnuclear level, despite its high importance. In order to design a suitable predictive system, the extraction of subtle sequence signals that can discriminate among proteins with different subnuclear localizations is the key.
New kernel functions used in a support vector machine (SVM) learning model are introduced for the measurement of sequence similarity. The k-peptide vectors are first mapped by a matrix of high-scored pairs of k-peptides which are measured by BLOSUM62 scores. The kernels, measuring the similarity for sequences, are then defined on the mapped vectors. By combining these new encoding methods, a multi-class classification system for the prediction of protein subnuclear localizations is established for the first time. The performance of the system is evaluated with a set of proteins collected in the Nuclear Protein Database (NPD). The overall accuracy of prediction for 6 localizations is about 50% (vs. random prediction 16.7%) for single localization proteins in the leave-one-out cross-validation; and 65% for an independent set of multi-localization proteins. This integrated system can be accessed at http://array.bioengr.uic.edu/subnuclear.htm.
The integrated system benefits from the combination of predictions from several SVMs based on selected encoding methods. Finally, the predictive power of the system is expected to improve as more proteins with known subnuclear localizations become available.
The cell nucleus is a highly complex organelle that organizes the comprehensive assembly of our genes and their corresponding regulatory factors. Accordingly, the cell nucleus reflects the intricate regulation of various biological activities. Although protein complexes disperse throughout the entire organelle, it is known that many nuclear proteins participating in related pathways tend to concentrate into specific areas [1, 2]. For example, the rDNA processing and ribosome biogenesis often occur within the nucleolus and the proteins responsible for pre-splicing appear to concentrate into multiple nuclear speckles, even while they are migrating in the nucleus. The confinement of biomolecules within specific compartments is crucial for the formation and function of the cell nucleus; in contrast, the mis-localization of proteins can lead to both human genetic disease and cancer .
Accordingly, information on protein subnuclear localization is essential for a full understanding of genomic regulation and function. Advances in experimental technology have enabled the large-scale identification of nuclear proteins. However, at the same time, the sequencing of both the human and mouse genomes has generated an enormous inventory of primary sequences with unknown functions. A faster and cheaper bioinformatics tool is required for the annotation of these exponentially accumulating sequences. A computational prediction of protein subnuclear compartments from primary protein sequences can provide important clues to the function of novel proteins.
A host of systems for the prediction of protein subcellular localizations has emerged over the last two decades [4–23]. This list includes several web-based predictors that have a broad coverage of subcellular localizations at the genomic level, such as PSORT , SubLoc , Proteome Analyst , CELLO , PSORTb v.2.0 , and LOCtree . The development led to the ability to predict the particular subcellular compartment, in which a given protein resides within a cell, with a steadily increasing accuracy. The predictions for eukaryotic organisms, however, have certain limitations. They can provide information on whether a protein localizes in the nuclear compartment, but they can not discriminate among the sub-compartments in which it functions.
The prediction of protein localization at the subnuclear level is challenging compared with that at the subcellular level. Three facts contribute to the difficulty: (1) proteins within the cell nucleus face no apparent physical barrier like a membrane ; (2) the nucleus is far more compact and complicated in comparison with other compartments in a cell ; and (3) protein complexes within the cell nucleus are not static [1, 24, 25]. Recent developments in live-cell imaging have revealed that nuclear processes may rely on a constant flow of molecules between dynamic compartments created by relatively immobile binding or assembly sites. As proteins diffuse through the nuclear space, they appear to alter their compartments during different phases of the cell cycle or accompanying differentiation . For instance, some nucleolar proteins are continually exchanging between the nucleoplasm and the nucleolus. Proteomic studies have also highlighted the dynamic nature of the nucleolar proteome .
Employing the database Nuclear Protein Database (NPD) developed by Dellaire, Farrall and Bickmore , Bickmore and Sutherland  recently addressed the characteristics of the primary sequences of nuclear proteins, such as the molecular weight, isoelectric point, and amino acid composition for proteins in different subnuclear compartments. They also found that motifs and domains are often shared by proteins co-localized within the same subnuclear compartment. Furthermore, certain generally abundant motifs/domains are lacking from the proteins concentrated in some specific areas of the nucleus. Based on these findings, it should be possible to combine totality of this information in a manner that will enhance the prediction of compartmental-specific nuclear localizations of the protein constituents listed in genome databases.
Encouraged by our previous success in the design of a metric for the biological similarity of protein sequences [22, 23], a prediction system is developed based on support vector machines (SVMs), one of the most advanced machine learning methods [28, 29]. The principal feature of our mode of analysis is the introduction of new kernel functions which are effective in capturing the subtle difference between sequences originated from two distinct nuclear compartments.
Results and Discussion
Normally, conventional k-peptide encoding vectors (k = 1, 2, 3) are used for the description of a protein sequence. Successful applications include (1) the protein fold recognition [30, 31], and (2) the prediction of subcellular localization [5, 7, 16]. The basic concept of the new kernels proposed in our previous work [22, 23] is the measurement of biological similarity for k-peptides, having either none or a few shared residues, with the incorporation of evolutionary information. Our finding indicates that the mapping of conventional k-peptide encoding vectors by a matrix formed with high-scored pairs of k-peptides can facilitate the construction of a suitable metric. The score of a pair of k-peptides is calculated by the BLOSUM scores of residues and, therefore, the evolutionary information of the residues is embedded into the sequence description. A related concept that links two k-peptides with a small number of mutated residues has been presented by Leslie et al.  for protein homology detection.
This study presents the performance of conventional k-peptide encoding methods and the new proposed kernels for the prediction of protein subnuclear compartments. Furthermore, with the use of the jury voting scheme developed in , an integrated system was built by combining binary prediction outcomes obtained from different sequence encoding schemes. The results demonstrate that the integrated system enhances the overall performance of the system.
The dataset used in this study was extracted from the Nuclear Protein Database (NPD)  using a Perl script. The NPD is a curated database that stores information on more than 1000 vertebrate proteins, chiefly from human and mouse, which are reported in the literature to be localized in the cell nucleus. Since certain proteins associate with more than one compartment, a test dataset consisting of proteins with multiple localizations was first extracted out. These proteins have the same SwissProt ID or Entrez Protein ID though localized in different compartments. This preparative procedure resulted in 92 proteins that are localized within the six compartments described below. The majority is localized in 2 compartments and the remaining portion is localized in 3 or 4 compartments.
After excluding the multi-localization proteins, a non-redundant dataset was further constructed by PROSET  to ensure low sequence identity (<50%). In order to have sufficient number of proteins for training and testing, only six localizations were selected for evaluation. These are PML BODY (38), Nuclear Lamina (55), Nuclear Splicing Speckles (56), Chromatin (61), Nucleoplasm (75), and Nucleolus (219). Each of these proteins has a single localization and the total number is 504.
The summary of the nuclear proteins
Number of sequences
Nuclear Splicing Speckles
The evaluations of the predictive power of the methods were performed on the datasets. Since there are 6 localizations in the dataset, the one-versus-one multi-class classification system led to 6*(6-1)/2 = 15 SVM models for one single encoding method (see Methods for details). Three encoding techniques corresponding to the conventional k-peptide composition and three encoding methods based on the new kernels were used for k = 1,2,3. SVMLight  was used as the SVM solver.
The overall accuracy for the multi-class classification proposed by Rost and Sander  was used for the evaluation of our system. Suppose there are m = m1 + m2 + ... + m N test proteins, where m i is the number of proteins belonging to class i(i = 1,...,N). Suppose further that out of the proteins considered, p i proteins are correctly predicted to belong to class i. Then p = p1 + p2 + ... + p N is the total number of correctly predicted proteins. The accuracy for class i is
and the overall accuracy, denoted by Qacc, is defined as
Note that acc i and Q acc are respectively corresponding to the definitions of and Q total in Rost and Sander . Since the numbers of proteins for various localizations are unbalanced, the Matthew's correlation coefficient (MCC) was also employed for the optimization of parameters and evaluation of performance :
where p i is the number of correctly predicted proteins of the location i, s i is the number of correctly predicted proteins not in the location i, u i is the number of under-predicted proteins, and o i the number of over-predicted proteins.
In order to evaluate the performance of the system for multi-localization proteins, the criterion proposed in Gardy et al. was used . More specifically, for a protein with multi-localization, if the system validly predicts one of the locations, then the entire prediction is considered correct. It should be noted that this criterion overestimates the performance. Since our method can only predict one localization for a given protein, other evaluation methods for multi-localization proteins such as the one proposed by Chou and Cai [14, 18] can not be applied.
Results for each individual encoding method
Accuracy % [MCC]
Nuclear Splicing Speckles
Single-localization Overall Accuracy and MCC
Multi-localization Overall Accuracy and MCC
Results using combined methods
Combination of AA, DI, TRI
Combination of D1X1, D2X2, and D3X3
Accuracy % [MCC]
Nuclear Splicing Speckles
Single-localization Overall Accuracy and MCC
Multi-localization Overall Accuracy and MCC
The final models for the prediction system are the combination of the new encoding methods D1X1, D2X2, and D3X3, since adding any conventional k-peptide encoding method does not improve the performance of the system. The predictions for all the 92 multi-localization testing proteins are detailed in Table S1 in the supplementary file [see Additional file 1].
An SVM-based multi-class classification system has been developed for the prediction of protein subnuclear localizations. This is the first system designed specifically for this task. This system, which integrates predictions from three new encoding methods, achieves encouraging levels of accuracy for six specific subnuclear localizations. However, compared to the prediction of protein localizations at the subcellular level, the corresponding prediction at the subnuclear level is far more challenging. This difficulty arises mainly from the biological fact that each compartment within the cell nucleus contains no apparent physical barrier like a membrane. Furthermore, the nucleus is a considerably more compact and complex organelle in comparison to other organelles in the cell. Finally, the dynamic nature of the nucleolar proteome adds an additional level of complexity to the task of prediction.
Kernels based on high-scored pairs of k-peptides
Recently, Lei and Dai proposed new kernels based on high-scored pairs of k-peptides for protein sequence encoding [22, 23] for the SVMs. Superior performance of the SVMs with these new kernels was demonstrated through application to the prediction of protein subcellular localization. The kernels proposed in [22, 23] can be described as follows.
A matrix D k of high scored k-peptide pairs is defined with a prescribed threshold. Each entry is associated with the BLOSUM score of some pair of k-peptides. The matrix is of dimension 21 k × 21 k , where 21 is the number of amino acid symbols (normal 20 amino acids plus the special symbol ''X''). The thresholds are set to zeroes for k = 1, 2. Therefore, matrix D1 is the same as the BLOSUM matrix, except that the entries with negative values are replaced by zeroes; the entries of matrix D2 are the BLOSUM pair scores of two di-peptides with all negative values being replaced by zeroes. Since the size of D3 is very large and the majority of all possible pairs is associated with lower scores, the elimination of those pairs can reduce noise that may confuse the prediction. Therefore, a careful thresholding is necessary to ensure the sparsity of the matrix D3. In this work, the threshold is set to 8 for k = 3. For example, the score is 12 for an AAA-AAA pair, 11 for an AAY-ACY pair, and 0 for a TVW-TVR pair since TVW-TVR BLOSUM62 pair-score is 6, which is smaller than the threshold value 8. Given the dimensional scaling, when k > 3, such a coding scheme is less attractive from a computational point of view.
For a pair of k-peptide composition vectors x ki , x kj , the new kernels are defined as
K (x ki , x kj ) = exp(-γ || D k x ki - D k x kj ||2), k = 1, 2, 3, ....
It can be considered as a Gaussian kernel for a pair of vectors D k x ki and D k x kj . These kernels define the sequence similarity for the mapped vectors D k x ki and D k x kj , not directly for the k-peptide composition vectors x ki and x kj . In this study, the kernel type used for the conventional k-peptide composition encoding methods is the radial basis kernel: exp(-γ || x ki - x kj ||2)
In the following, the concept described above is illustrated and the comparison with the conventional k-peptide encoding method is provided. Consider two short amino acid sequences AAACY and AACCY. Using the input format of the SVMLight , the conventional tri-peptide encoding method generates two coding vectors:
x31: 1:0.33 2:0.33 42:0.33
x32: 2:0.33 23:0.33 483:0.33
where the numbers appearing in the vectors are in the format of "index: score". It is obvious that the two sequences share the tri-peptide "AAC", and the corresponding vector index is 2. On the other hand, using BLOSUM62, the transformed vectors D3x31 for x31 and D3x32 for x32 are calculated as follows:
Example of encoding AAACY to D3x31:
D3x31: 1:6.67 2:8.33 6:2.67 16: 3.00 17:2.67 18:2.67 21: 3.67 22:6.33 23:8.00 24:3.33 25:3.67 26:5.33 27:3.33 28:5.00 29:4.00 30:3.67 ...
D3x32: 1:2.67 2:10.00 22:4.33 23:11.67 24:3.33 25:3.00 26:7.67 27:3.33 28:7.00 ...
From the list it is seen that the transformed vectors share more common indices, such as 1, 2, 22–28 etc. Therefore, the similarity between the two sequences is more likely to be captured by the new methods even they do not share explicitly those tri-peptides. The mismatch string kernels proposed in Leslie et al.  also consider the similarity between mismatch k-peptides. For example, compared with the conventional tri-peptide encoding, the two sequences share several more common tri-peptides, such as AAA and AAC, AAC and ACC, ACY and CCY, if one mismatch is allowed in two peptides. Therefore, our method is related to the mismatch string kernel but it is different.
Multi-class classification system
The efficient extension of SVMs to the handling of multiple classes has been achieved for applications to protein fold prediction  and the prediction of subcellular localization [7, 16]. The one-versus-one  framework was used here for the assembly of the multi-class classifier from binary classifiers. For a classification problem of N class, it trains every pair-wise binary classifier. This gives a total of 1/2 * N (N - 1) classifiers. The prediction of the label of a testing protein follows the jury voting; specifically, sum the predictions for each classifier and take the label with the highest votes. When ties arise, the class label is assigned to the class with the maximum value of the sum of the function margins. This jury voting scheme is very flexible for the assembly of the predictions obtained from various SVM models. It can integrate not only the outcome from binary predictors with one encoding scheme, but also those obtained from alternative encoding methods. Accordingly, the class label of the testing protein is assigned to the class with the maximum votes.
Cross-validation and final prediction system
C: the trade-off between the training error and class separation;
γ: the parameter in the radial basis functions exp(-γ || x i - x j ||2) or exp(-γ || D k x ki - D k x kj ||2);
J: the biased penalty for errors from positive and negative training points.
C: 2-2, 2-1, 1, ..., 29, 210;
γ: 2-15, 2-14, 2-13, ..., 214, 215;
J: 1, 2, 3, ..., 8, 9.
The labels of the training sets were arranged in a way that the size of the negative set is always larger than that of the positive set in our experiment. Here, the penalty term in the SVM is split into two terms: . The heavier weight CJ imposed on the errors originating from the negative points enforces a low false positive rate for unbalanced training sets .
The final prediction system was constructed as follows. The entire set of proteins with single-localization was used as a training set; and the optimal value for each parameter of the SVMs for the training set was taken as the average value of the optimal parameters obtained from the LOOCV procedure. Using these optimized parameters, final binary classifies were learned from the training set. The evaluation for the set of multi-localization proteins was based on this final prediction system. The framework for the overall training and testing procedures is illustrated in Figure S1 in the supplementary file [see Additional file 2].
Availability and requirements
Project name: Subnuclear Compartments Prediction System (Version 1.0)
Project home page: http://array.bioengr.uic.edu/subnuclear.htm
Operating system(s): Linux
Programming language: Perl
Any restrictions to use by non-academics: None
This research was supported in part by National Science Foundation (EIA-022-0301) and Naval Research Laboratory (N00173-03-1-G016). The authors are grateful to Deepa Vijayraghaven for her assistance with the computing environment. We thank anonymous referees for their valuable suggestions.
- Heidi GES, Gail KM, Kathryn N, Lisa VF, Rachel F, Graham D, Javier FC, Wendy AB: Large-scale identification of mammalian proteins localized to nuclear sub-compartments. Human Molecular Genetics 2001, 10: 1995–2011. 10.1093/hmg/10.18.1995View ArticleGoogle Scholar
- Joanna MB, Wendy AB: Putting the genome on the map. Trends Genet 1998, 14: 403–409. 10.1016/S0168-9525(98)01572-8View ArticleGoogle Scholar
- Phair RD, Misteli T: High mobility of proteins in the mammalian cell nucleus. Nature 2000, 404: 604–609. 10.1038/35007077View ArticlePubMedGoogle Scholar
- Nakai K, Horton P: PSORT: a program for detecting sorting signals in proteins and predicting their subcellular localization. Trends in Biochem Sci 1999, 24: 34–35. 10.1016/S0968-0004(98)01336-XView ArticleGoogle Scholar
- Chou K-C, Elrod DW: Protein subcellular location prediction. Protein Eng 1999, 12: 107–118. 10.1093/protein/12.2.107View ArticlePubMedGoogle Scholar
- Emanuelsson O, Nielsen H, Brunak S, von Heijne G: Predicting subcellular localization of proteins based on their N-terminal amino acid sequence. Journal of Molecular Biology 2000, 300: 1005. 10.1006/jmbi.2000.3903View ArticlePubMedGoogle Scholar
- Hua S, Sun Z: Support vector machine approach for protein subcellular localization prediction. Bioinformatics 2001, 17: 721–728. 10.1093/bioinformatics/17.8.721View ArticlePubMedGoogle Scholar
- Chou KC: Prediction of protein cellular attributes using pseudo amino acid composition. PROTEINS: Structure, Function, and Genetics 2001, 43: 246–255. 10.1002/prot.1035View ArticleGoogle Scholar
- Chou KC, Cai YD: Using functional domain composition and support vector machines for prediction of protein subcellular location. Journal of Biological Chemistry 2002, 277: 45765–45769. 10.1074/jbc.M204161200View ArticlePubMedGoogle Scholar
- Nair R, Rost B: Better prediction of sub-cellular localization by combining evolutionary and structural information. Proteins: Structure, Function, and Genetics 2003, 53: 917–930. 10.1002/prot.10507View ArticleGoogle Scholar
- Pan YX, Zhang ZZ, Guo ZM, Feng GY, Huang ZD, He L: Application of pseudo amino acid composition for predicting protein subcellular location: stochastic signal processing approach. Journal of Protein Chemistry 2003, 22: 395–402. 10.1023/A:1025350409648View ArticlePubMedGoogle Scholar
- Zhou GP, Doctor K: Subcellular location prediction of apoptosis proteins. PROTEINS: Structure, Function, and Genetics 2003, 50: 44–48. 10.1002/prot.10251View ArticleGoogle Scholar
- Chou CK, Cai YD: A new hybrid approach to predict subcellular localization of proteins by incorporating gene ontology. Biochem Biophys Res Comm 2003, 311: 743–747. 10.1016/j.bbrc.2003.10.062View ArticlePubMedGoogle Scholar
- Cai YD, Chou CK: Predicting 22 protein localizations in budding yeast. Biochem Biophys Res Comm 2004, 323: 425–428. 10.1016/j.bbrc.2004.08.113View ArticlePubMedGoogle Scholar
- Szafron D, Lu P, Greiner R, Wishart DS, Poulin B, Eisner R, Lu Z, Anvik J, Macdonell C, Fyshe A, et al.: Proteome Analyst: custom predictions with explanations in a web-based tool for high-throughput proteome annotations. Nucleic Acids Res 2004, 32(Web Server):W365–371.PubMed CentralView ArticlePubMedGoogle Scholar
- Yu CS, Lin CJ, Hwang JK: Predicting subcellular localization of proteins for Gram-negative bacteria by support vector machines based on n-peptide compositions. Protein Sci 2004, 13: 1402–1406. 10.1110/ps.03479604PubMed CentralView ArticlePubMedGoogle Scholar
- Gardy JL, Laird MR, Chen F, Rey S, Walsh CJ, Ester M, Brinkman FS: PSORTb v.2.0: expanded prediction of bacterial protein subcellular localization and insights gained from comparative proteome analysis. Bioinformatics 2005, 21: 617–623. 10.1093/bioinformatics/bti057View ArticlePubMedGoogle Scholar
- Chou KC, Cai YD: Predicting protein localization in budding yeast. Bioinformatics 2005, 21: 944–950. 10.1093/bioinformatics/bti104View ArticlePubMedGoogle Scholar
- Xiao X, Shao S, Ding Y, Huang Z, Huang Y, Chou KC: Using complexity measure factor to predict protein subcellular location. Amino Acids 2005, 28: 57–61. 10.1007/s00726-004-0148-7View ArticlePubMedGoogle Scholar
- Gao Y, Shao S, Xiao X, Ding Y, Huang Y, Huang Z, Chou CK: Using pseudo amino acid composition to predict protein subcellular location: approached with Lyapunov index, Bessel function, and Chebyshev filter. Amino Acids 2005, 28: 373–376. 10.1007/s00726-005-0206-9View ArticlePubMedGoogle Scholar
- Nair R, Rost B: Mimicking Cellular Sorting Improves Prediction of Subcellular Localization. Journal of Molecular Biology 2005, 348: 85–100. 10.1016/j.jmb.2005.02.025View ArticlePubMedGoogle Scholar
- Lei Z, Dai Y: A new kernel based on high-scored pairs of tri-peptides and its application in prediction of protein subcellular localization. In Proceedings of International Workshop on Bioinformatics Research and Applications. Volume 3515. Lecture Notes in Computer Science (LNCS), Springer-Verlag, Berlin; 2005:903–910.Google Scholar
- Lei Z, Dai Y: A class of new kernels based on high-scored pairs of k-peptides and its application in prediction of protein subcellular localization. LNCS Transactions on Computational Systems Biology 2005, in press.Google Scholar
- Carmo-Fonseca M: The contribution of nuclear compartmentalization to gene regulation. Cell 2002, 108: 513–521. 10.1016/S0092-8674(02)00650-5View ArticlePubMedGoogle Scholar
- Hancock R: Internal organisation of the nucleus: assembly of compartments by macromolecular crowding and the nuclear matrix model. Biology of the Cell 2004, 96: 595–601. 10.1016/j.biolcel.2004.05.003View ArticlePubMedGoogle Scholar
- Dellaire G, Farrall R, Bickmore WA: The Nuclear Protein Database (NPD): subnuclear localisation and functional annotation of the nuclear proteome. Nucl Acids Res 2003, 31: 328–330. 10.1093/nar/gkg018PubMed CentralView ArticlePubMedGoogle Scholar
- Bickmore WA, Sutherland HGE: NEW EMBO MEMBER'S REVIEW: Addressing protein localization within the nucleus. EMBO J 2002, 21: 1248–1254. 10.1093/emboj/21.6.1248PubMed CentralView ArticlePubMedGoogle Scholar
- Vapnik VN: Statistical learning theory. Wiley, New York; 1998.Google Scholar
- Cristianini N, Shawe-Taylor J: An Introduction to Support Vector Machines. Cambridge University Press; 2000.Google Scholar
- Ding CHQ, Dubchak I: Multi-class protein fold recognition using support vector machines and neural networks. Bioinformatics 2001, 17: 349–358. 10.1093/bioinformatics/17.4.349View ArticlePubMedGoogle Scholar
- Yu CS, Wang JY, Yang JM, Lyu PC, Lin CJ, Hwang JK: Fine-grained protein fold assignment by support vector machines using generalized n-peptide coding schemes and jury voting from multiple-parameters sets. PROTEINS: Structure, Function, and Genetics 2003, 50: 531–536. 10.1002/prot.10313View ArticleGoogle Scholar
- Leslie CS, Eskin E, Cohen A, Weston J, Noble WS: Mismatch string kernels for discriminative protein classification. Bioinformatics 2004, 20: 467–476. 10.1093/bioinformatics/btg431View ArticlePubMedGoogle Scholar
- Brendel V: PROSET – a fast procedure to create non-redundant sets of protein sequences. Mathl Comput Modelling 1992, 16: 37–43. 10.1016/0895-7177(92)90150-JView ArticleGoogle Scholar
- Rost B, Sander C: Prediction of protein secondary structure at better than 70% accuracy. Journal of Molecular Biology 1993, 232: 584–599. 10.1006/jmbi.1993.1413View ArticlePubMedGoogle Scholar
- Matthews BW: Comparison of the predicted and observed secondary structure of T4 phage lysozyme. Biochim Biophys Acta 1975, 405: 442–451.View ArticlePubMedGoogle Scholar
- Platt JC, Cristianini N, Shawe-Taylor J: Large margin DAGs for multiclass classification. In Advances in Neural Information Processing Systems. Volume 12. MIT Press; 2000:547–553.Google Scholar
- Chou KC, Zhang CT: Review: Prediction of protein structural classes. Critical Reviews in Biochemistry and Molecular Biology 1995, 30: 275–349.View ArticlePubMedGoogle Scholar
- Morik K, Brockhausen P, Joachims T: Combining statistical learning with a knowledge-based approach – A case study in intensive care monitoring. Proceedings of the Sixteenth International Conference on Machine Learning 1999, 268–277.Google Scholar
This article is published under license to BioMed Central Ltd. This is an Open Access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/2.0), which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.