AlgPred: PREDICTION OF ALLERGENIC PROTEINS AND MAPPING OF IgE EPITOPES

Sudipto Saha and G. P. S. Raghava*

Institute of Microbial Technology, Okhla Phase 3, New Delhi, India

Running Tite: Allergens prediction

Address correspondence to: Dr. G. P. S. Raghava, Professor, Department of Computational Biology Institute of Microbial Technology  Okhla Phase 3, New Delhi, INDIA, Phone: +91-11-26907444; Fax: +91-172-26907444 E-mail: raghava@iiitd.ac.in

Available at :  http://webs.iiitd.edu.in/raghava/algpred

 

Algorithm used in developing AlgPred server

 

Data set partitioning

One of the challenges in developing any prediction method is to minimize the similarity between proteins used for training and protein used for testing. Though removing redundancy is not a problem but it reduces the number of proteins used for training, which is not good for any learning method. In this study we a different approach have been used to minimize similarity between proteins used for training and testing without reducing total number of proteins.   First proteins are clustered based on similarity using BLAST E-value 8E-4 (26% identity for one sequence pair). These clusters were divided into five sets in such a way that each set have nearly equal number of sequences, where all proteins of a given cluster are kept in one set. As sequences in one cluster do not have similarity (e-value of 8E-4) with sequences of other clusters so sequences in one set will not have similarity with sequences of other sets. 

 

 

Presence of IgE epitopes

In this approach, a protein is predicted allergen if protein have one or more than one IgE epitopes.  Thus in this study, similarity based approach has been used, where a protein is assigned allergen if it have a region/peptide identical to known IgE epitopes.  First all 183 IgE epitopes scanned against all proteins in dataset and found 61 hits in allergens and 16 hits in non-allergens, when stringent condition of 100% identity was used. Ideally, IgE epitope should not be present in non-allergens, thus epitopes present in non-allergens has been analyzed. It has been observed that most of the epitopes founds in non-allergen were short in length (3 or 4 residues); for example epitopes HWR, IRRA and YHVP have 7, 6 and 1 hits respectively in non-allergens. Due to their short length they were unable to provide specificity. Thus for further study, only those epitopes (178 epitopes) have been used which have five or more than five residues. As shown in Table 1, for PID 100 we got 56 hits in allergen (or 9.69 % of allergens were correctly assigned as allergens) and 2 hits in non-allergens (or 0.28% of non-allergens assigned wrongly as allergens). In order to increase the sensitivity or percent coverage of allergens we relaxed the criteria. Though the sensitivity increased but the percent of false assignment of non-allergen to allergen also increased when we relaxed the criteria.  Thus, we set PID cut-off based on length of epitope rather than uniform cut-off. This way we were able to achieve better sensitivity without loosing significant specificity. The best results were obtained using PID865 where PID cut-off is 80, 60 and 50 for epitopes having residues less than 10, between 10 to 15 and more than 15, respectively.

 

Table 1: Searching of 178 IgE epitopes in protein dataset consists of 578 allergens and 700 non-allergens. Different percent identity (PID) cut-off was used to search epitopes in proteins, cut-off was also set based on amino acids (A.A.) in IgE epitopes.

 

 

Approach

PID (Cut-off)

 

Total Hits

Allergens

Non-allergens

PID100

100

56 (9.69%)

2 (0.28%)

PID81

>80

77 (13.32%)

8 (1.11%)

PID80

³80

102 (17.65%)

74 (10.57 %)

PID876

>80 (epitopes have  £ 9 A.A.)

³70 (epitopes have > 9 & £ 15 A.A.) >60 (epitopes have > 15 A.A.)

91 (15.74%)

11 (1.57%)

PID865

>80 (epitopes have  £ 9 A.A.)

³60 (epitopes have > 9 & £ 15 A.A.) >50 (epitopes have > 15 A.A.)

101 (17.47%)

13 (1.85%)

 

 

 

Allergen Representative Peptides collection and Prediction using ARPs

The dataset of ARPs consists of 2890 ARPs (24 amino acid peptides) obtained from Bjorklund et al., 2005 . They collected high-quality repositories of amino acid sequences of proteinaceous allergens (allergen database) and non-allergens (consumed commodities, such as rice, apple, tomato etc.) and generated all possible overlapping 24mer peptides for both types of proteins (allergen and non-allergens). Based on the global similarity scores of each allergen peptide, a set containing 2890 ARPs were created which has high similarity in allergenic proteins but not in non-allergenic proteins.

The approach was tested on 664 allergens and 700 non-allergens . As shown in Table 2, the number of correctly assigned allergens (or sensitivity) increased from 52.71% to 94.28% when e-value BLAST increased from 10-9  to 1.0. Though the sensitivity increased with increase in e-value, the number of non-allergen falsely predicted allergens also increased from 2 to 338.  It is found that e-value of 0.001 provides reasonably high sensitivity 83.58% with only 15 false positive (non-allergens predicted as allergens). Thus e-value 0.001 used as default cut-off for further study.

 

Table 2 : The search results of 1364 proteins (664 allergens & 700 non-allergens), which  searched against ARPs database using BLAST.

 

E-value

Total Hits

Allergen

Non-allergen

1

626 (94.28%)

338 (48.25%)

10-1

586 (88.22%)

48 (6.86%)

10-2

562 (84.64%)

23 (3.29%)

10-3

555 (83.58%)

15 (2.14%)

10-4

527 (79.37%)

8  (1.14%)

10-6

465 (70.03%)

5  (0.71%)

10-9

350 (52.71%)

2 (0.28%)

 

 

MEME/MAST

MEME/MAST: version 3.0.4, obtained from http://meme.sdsc.edu/meme/ website. MEME (Multiple Em for Motif Elicitation) is a tool for discovering motifs in a group of related protein sequences. A motif is a sequence pattern that occurs repeatedly in a group of related protein sequences. MEME represents motifs as position-dependent letter-probability matrices, which describe the probability of each possible letter at each position in the pattern. MEME takes as input a group of protein sequences (the training set) and output as many motif as requested. MEME uses statistical modeling techniques to automatically choose the best width, number of occurrences, and description for each motif. MAST (Motif Alignment and Search Tool) is a tool for searching biological sequence databases for sequences that contain one or more of a group of known motifs. MAST takes as input a file containing the descriptions of one or more motifs and searches sequence databases that have been created that match the motifs. First, five MEME matrices have been created corresponding to five sets, one matrix for one set.  Then each matrix was used in as input file for searching motifs in remaining four sets using program MAST. Finally we compute the performance of this approach and achieved the sensitivity in the range of 7% (at 0.001 e-value) to 94% (at 100 e-value) (Table 3). Though the sensitivity increased with increase in e-value but the percent of wrong assignment of non-allergens to allergens also increased from 2.85% to 66.86%. This demonstrate that motif based approach developed in this study have low specificity.

 

Table 3:  MEME/MAST results of allergen and non-allergen motifs. It shows allergen hits out of total 578 allergens and non-allergen hits out of total 700 non-allergens.

 

E-value

Total Hits

Allergen

Non-allergen

10-3

38 (6.57%)

20 (2.86%)

10-1

86 (14.88%)

62 (8.86%)

1

142 (24.57%)

113 (16.14%)

10

246 42.56%)

240 (34.29%)

20

309 (53.46%)

288 (41.14%)

50

427 (73.88%)

389 (55.57%)

100

543 (93.94%)

468 (66.86%)

 

 

Support vector machine

 

The support vector machines (SVM) are universal approximator based on statistical and optimising theory. The SVM is particularly attractive to biological analysis due to its ability to handle noise, large dataset and large input spaces. The SVM has been shown to perform better in protein secondary structure, MHC and TAP binder prediction and analysis of microarray data. The basic idea of SVM can be described as follows; first the inputs are formulated as feature vectors. Secondly these feature vectors are mapped into a feature space by using the kernel function. Thirdly, a division is computed in the feature space to optimally separate to classes of training vectors. The SVM always seeks global hyperplane to separate the both classes of examples in training set and avoid overfitting. The hyperplane found by SVM is one that maximise the separating margins between both binary classes This property of SVM is made is more superiors in comparison to other classifiers based on artificial intelligence.

 

In this study, we have used SVM_light to predict the allergenic proteins. The software is freely downloadable from http://www.cs.cornell.edu/People/tj/svm_light/ . The software enable the users to define a number of parameters and allow to select a choice of inbuilt kernel function including linear, RBF, Polynomial (given degree) or user defined kernel.

 

Preliminary tests showed that the radial basis function (RBF) kernel gives results better than other kernels. Therefore, in this work we used the RBF kernel for all the experiments. The input vectors used were amino acid composition (20 vectors) and dipeptide composition (400 vectors) of each protein sequence.

 

Protein features 

 Amino acid  composition. Amino acid composition is the fraction of each amino acid in a protein. The fraction of all 20 natural amino acids was calculated using the following equations:

Fraction of amino acid i =

 

 

 

 


where i can be any amino acid.

 

Dipeptide composition. Dipeptide composition was used to encapsulate the global information about each protein sequence, which gives a fixed pattern length of 400 (20 ´ 20). This representation encompassed the information about amino acid composition along local order of amino acid. The fraction of each dipeptide was calculated using following equation:

fraction of dipep (i) = 

               

 

where dipep(i) is one out of 400 dipeptides.

 

Five fold cross-validation:

The performance of all methods developed in this study is evaluated using five-fold cross validation. In five-fold cross validation dataset has been divided into five sets, where each set have nearly equal number of allergens and non-allergens. The training and testing of every method has been carried out five times, each time using one distinct set for testing and remaining four sets for training.  The overall performance of a method is average performance over five sets.

Performance measures

The standard parameters have been used to evaluate the performance of various methods developed in this study. Following is brief description of the parameters; i) Sensitivity is the percent of epitopes that are correctly predicted as epitopes also referred as recall; ii) Specificity is the percent of correctly predicted as non-epitopes; iii) Accuracy is the proportion of correctly predicted peptides; iv) PPV (positive prediction value) is the probability of correctly positive prediction also referred as precision  v) NPV(negative prediction value) is the probability of correctly negative prediction and vi) Matthew’s correlation coefficient (MCC). The parameters may be calculated by the following equations.

 

                                         

                                                  

                                         

 

                                         

 

                                         

                                          MCC=

 

 

Where TP and FN refer to true positive and false negatives, TN and FP refer to true negatives and false positives.

 

The performance of SVM module based on amino acid and dipeptide composition

The following Table 4 and Table 5 demonstrate the performance of SVM based method using amino acid and dipeptide composition respectively. The RBF kernel was used and SVM module based on amino acid composition parameters used are g=50; c=1; and j=1;

Whereas SVM module based on dipeptide composition parameters used are g=100; c=1; and j=1.

 

Table 4: Performance of SVM based method using amino acid composition

 

Threshold

Sensitivity

Specificity

Accuracy

PPV

NPV

MCC

1.0

 0.3374

 0.9829

 0.6918

 0.9417

0.6442

 0.4336

0.8

 0.4243

 0.9700

 0.7239

 0.9208

0.6729

 0.4843

0.6

 0.5200

 0.9586

 0.7608

 0.9116

0.7093

 0.5456

0.4

 0.5878

 0.9386

 0.7804

 0.8871

0.7357

 0.5732

0.2

 0.6539

 0.9243

 0.8024

 0.8765

0.7657

 0.6099

0.0

 0.7357

 0.8929

 0.8220

 0.8494

0.8054

 0.6422

-0.2

 0.8383

 0.8543

 0.8471

 0.8253

0.8667

 0.6930

-0.4

 0.8887

 0.8186

 0.8502

 0.8009

0.9009

 0.7053

-0.6

 0.9061

 0.7614

 0.8267

 0.7573

0.9096

 0.6680

-0.8

 0.9391

 0.6957

 0.8055

 0.7171

0.9347

 0.6441

-1.0

 0.9583

 0.6100

 0.7671

 0.6687

0.9489

 0.5933

 

 

Table 5: Performance of SVM based method using dipeptide composition

 

Threshold

Sensitivity

Specificity

Accuracy

PPV

NPV

MCC

1.0

 0.0957

 1.0000

 0.5922

 1.0000

0.5742

 0.2346

0.8

 0.1791

 1.0000

 0.6298

 1.0000

0.5978

 0.3275

0.6

 0.2696

 0.9886

 0.6643

 0.9509

0.6229

 0.3852

0.4

 0.3913

 0.9686

 0.7082

 0.9109

0.6602

 0.4538

0.2

 0.5461

 0.9429

 0.7639

 0.8870

0.7174

 0.5441

0.0

 0.7043

 0.9100

 0.8173

 0.8654

0.7903

 0.6353

-0.2

 0.8278

 0.8500

 0.8400

 0.8193

0.8586

 0.6786

-0.4

 0.8922

 0.7743

 0.8275

 0.7645

0.8988

 0.6657

-0.6

 0.9374

 0.6771

 0.7945

 0.7046

0.9312

 0.6259

-0.8

 0.9600

 0.5657

 0.7435

 0.6449

0.9474

 0.5589

-1.0

 0.9757

 0.4471

 0.6855

 0.5918

0.9601

 0.4840

 

 

Hybrid Approach

The objective of this approach is to improve the sensitivity as well as the specificity of allergen prediction method. Each approach has its own limitations, as some provides high sensitivity but low specificity and vice verse. In order to get high sensitivity without loosing much specificity or high specificity with reasonable percent coverage, we combined two or more than two approaches. First, SVM and IgE epitope based approaches have been combined, where a protein is assigned as allergen if predicted allergen by IgE method (PID865) and also have SVM score ³ -0.5. A protein is assigned allegen or non allergen using SVM approach, if protein have no similarity with known IgE epitopes. As shown in Table 6, the sensitivity increased around 11% (33.74 to 44.52), where as the specificity decreased marginally by 0.15%. Similar trend observed when SVM based method using dipeptide composition has been combined with IgE epitope based method. No improvement has been observed when motif based and SVM based approaches have been combined. 

 

Table 6: The performance of hybrid approach, which combines SVM based approach using amino acid composition and IgE epitope based approach (PID865).

 

Threshold

Sensitivity

Specificity

Accuracy

PPV

NPV

MCC

1.0

 0.4452

 0.9814

 0.7396

 0.9517

0.6836

 0.5211

0.8

 0.4922

 0.9700

 0.7545

 0.9309

0.7000

 0.5405

0.6

 0.5652

 0.9586

 0.7812

 0.9181

0.7293

 0.5829

0.4

 0.6191

 0.9386

 0.7945

 0.8922

0.7509

 0.5995

0.2

 0.6713

 0.9243

 0.8102

 0.8793

0.7749

 0.6248

0.0

 0.7443

 0.8929

 0.8259

 0.8509

0.8106

 0.6499

-0.2

 0.8417

 0.8543

 0.8486

 0.8259

0.8692

 0.6963

-0.4

 0.8887

 0.8186

 0.8502

 0.8009

0.9009

 0.7053

-0.6

 0.9061

 0.7614

 0.8267

 0.7573

0.9096

 0.6680

-0.8

 0.9391

 0.6957

 0.8055

 0.7171

0.9347

 0.6441

-1.0

 0.9583

 0.6100

 0.7671

 0.6687

0.9489

 0.5933

 

 

Evaluation on Independent Dataset and on Swiss-Prot protein sequences

It has been shown in number of studies that there is biasness in performance of the method if it is trained and tested on same dataset despite n-fold cross-validation (37,38). Thus it’s advisable to test any newly developed method on an independent dataset not used in training or testing of the method. In order to avoid any biasness we used default parameters for each approach (cut-off etc.). As shown in Table 7, the accuracy of prediction based on SVM based approaches were around 85%, followed by ARPs BLAST of 67%. The performance on Swiss-Prot proteins shows the SVM based method using amino acid and dipeptide composition, falsely predicted 46.74% and 39.30% non-allergens as allergens respectively. Though specificity of these SVM based method is poor but same time coverage or sensitivity is higher than other method. In reverse IgE epitope and MEME methods predicts low rate of false positive but have poor sensitivity. 

 

Table 7: Performance of different methods on 101725 non-allergens obtained from Swiss-Prot and on 323 allergens (independent dataset not used in training or testing of methods).

 

Prediction Methods

101725 Non-allergens obtained from Swiss-Prot

 

Independent dataset of 323 allergens

Falsely predicted allergens

Specificity (Predicted non-allergens)

Allergens correctly predicted allergens (Sensitivity)

SVMc

44684 

56.07%

272 (84.21%)

SVMd

39590 

61.09%

274 (84.83%)

MAST (ev100)

13545 

86.68%

58 (17.95%)

MAST (ev 0.1)

3480 

96.58%

40 (12.38%)

BLAST (ARP)

2060 

97.97%

215 (66.56%)

IgE Epitope

1777 

98.25%

35 (10.84%)

Available at :  http://webs.iiitd.edu.in/raghava/algpred