Limits...
Generating quantitative models describing the sequence specificity of biological processes with the stabilized matrix method.

Peters B, Sette A - BMC Bioinformatics (2005)

Bottom Line: First, they can provide a summary of experimental results, allowing for a deeper understanding of the mechanisms involved in sequence recognition.This method has been successfully applied to predicting peptide binding to MHC molecules, peptide transport by the transporter associated with antigen presentation (TAP) and proteasomal cleavage of protein sequences.Making the SMM method publicly available enables bioinformaticians and experimental biologists to easily access it, to compare its performance to other prediction methods, and to extend it to other applications.

View Article: PubMed Central - HTML - PubMed

Affiliation: La Jolla Institute for Allergy and Immunology, 3030 Bunker Hill Street, Suite 326, San Diego, CA 92109, USA. bjoern_peters@gmx.net

ABSTRACT

Background: Many processes in molecular biology involve the recognition of short sequences of nucleic-or amino acids, such as the binding of immunogenic peptides to major histocompatibility complex (MHC) molecules. From experimental data, a model of the sequence specificity of these processes can be constructed, such as a sequence motif, a scoring matrix or an artificial neural network. The purpose of these models is two-fold. First, they can provide a summary of experimental results, allowing for a deeper understanding of the mechanisms involved in sequence recognition. Second, such models can be used to predict the experimental outcome for yet untested sequences. In the past we reported the development of a method to generate such models called the Stabilized Matrix Method (SMM). This method has been successfully applied to predicting peptide binding to MHC molecules, peptide transport by the transporter associated with antigen presentation (TAP) and proteasomal cleavage of protein sequences.

Results: Herein we report the implementation of the SMM algorithm as a publicly available software package. Specific features determining the type of problems the method is most appropriate for are discussed. Advantageous features of the package are: (1) the output generated is easy to interpret, (2) input and output are both quantitative, (3) specific computational strategies to handle experimental noise are built in, (4) the algorithm is designed to effectively handle bounded experimental data, (5) experimental data from randomized peptide libraries and conventional peptides can easily be combined, and (6) it is possible to incorporate pair interactions between positions of a sequence.

Conclusion: Making the SMM method publicly available enables bioinformaticians and experimental biologists to easily access it, to compare its performance to other prediction methods, and to extend it to other applications.

Show MeSH
Visualization of prediction quality. Scatter plot of predicted vs. measured affinity for peptide binding to TAP. The depicted prediction corresponds to the data point in figure 5 with the lowest cross-validated distance, in which 350 peptides and the peptide library were used for training.
© Copyright Policy
Related In: Results  -  Collection


getmorefigures.php?uid=PMC1173087&req=5

Figure 6: Visualization of prediction quality. Scatter plot of predicted vs. measured affinity for peptide binding to TAP. The depicted prediction corresponds to the data point in figure 5 with the lowest cross-validated distance, in which 350 peptides and the peptide library were used for training.

Mentions: A novel feature of the SMM method is that it can combine data from these two sources. When the SMM algorithm is given experimental data from individual peptides and from a randomized library summarized in a scoring matrix matlib, it simply subtracts the values predicted by matlib from each individual peptide measurement. These y'meas = ymeas - ypred,lib values are then used to generate a second scoring matrix mat'. The final SMM scoring matrix is simply the sum of the two: matcombined = mat' + matlib. Figure 5 compares the performance of this combined approach to that of a prediction based on peptide or library experiments alone. If enough peptide data is present (roughly the same number as matrix parameters), the combined prediction is better than that of the library matrix alone. At all data points, the combined prediction is better than that using the peptides alone. Importantly, this simple strategy of subtracting library predictions can be used in combination with any prediction method, and is likely to generate similar results, as it effectively increases the training set size. To visualize the prediction quality associated with the distances reported in Figure 5, Figure 6 depicts a scatter plot of the predicted and measured binding affinity for individual peptides corresponding to the data point with the lowest distance in Figure 5.


Generating quantitative models describing the sequence specificity of biological processes with the stabilized matrix method.

Peters B, Sette A - BMC Bioinformatics (2005)

Visualization of prediction quality. Scatter plot of predicted vs. measured affinity for peptide binding to TAP. The depicted prediction corresponds to the data point in figure 5 with the lowest cross-validated distance, in which 350 peptides and the peptide library were used for training.
© Copyright Policy
Related In: Results  -  Collection

Show All Figures
getmorefigures.php?uid=PMC1173087&req=5

Figure 6: Visualization of prediction quality. Scatter plot of predicted vs. measured affinity for peptide binding to TAP. The depicted prediction corresponds to the data point in figure 5 with the lowest cross-validated distance, in which 350 peptides and the peptide library were used for training.
Mentions: A novel feature of the SMM method is that it can combine data from these two sources. When the SMM algorithm is given experimental data from individual peptides and from a randomized library summarized in a scoring matrix matlib, it simply subtracts the values predicted by matlib from each individual peptide measurement. These y'meas = ymeas - ypred,lib values are then used to generate a second scoring matrix mat'. The final SMM scoring matrix is simply the sum of the two: matcombined = mat' + matlib. Figure 5 compares the performance of this combined approach to that of a prediction based on peptide or library experiments alone. If enough peptide data is present (roughly the same number as matrix parameters), the combined prediction is better than that of the library matrix alone. At all data points, the combined prediction is better than that using the peptides alone. Importantly, this simple strategy of subtracting library predictions can be used in combination with any prediction method, and is likely to generate similar results, as it effectively increases the training set size. To visualize the prediction quality associated with the distances reported in Figure 5, Figure 6 depicts a scatter plot of the predicted and measured binding affinity for individual peptides corresponding to the data point with the lowest distance in Figure 5.

Bottom Line: First, they can provide a summary of experimental results, allowing for a deeper understanding of the mechanisms involved in sequence recognition.This method has been successfully applied to predicting peptide binding to MHC molecules, peptide transport by the transporter associated with antigen presentation (TAP) and proteasomal cleavage of protein sequences.Making the SMM method publicly available enables bioinformaticians and experimental biologists to easily access it, to compare its performance to other prediction methods, and to extend it to other applications.

View Article: PubMed Central - HTML - PubMed

Affiliation: La Jolla Institute for Allergy and Immunology, 3030 Bunker Hill Street, Suite 326, San Diego, CA 92109, USA. bjoern_peters@gmx.net

ABSTRACT

Background: Many processes in molecular biology involve the recognition of short sequences of nucleic-or amino acids, such as the binding of immunogenic peptides to major histocompatibility complex (MHC) molecules. From experimental data, a model of the sequence specificity of these processes can be constructed, such as a sequence motif, a scoring matrix or an artificial neural network. The purpose of these models is two-fold. First, they can provide a summary of experimental results, allowing for a deeper understanding of the mechanisms involved in sequence recognition. Second, such models can be used to predict the experimental outcome for yet untested sequences. In the past we reported the development of a method to generate such models called the Stabilized Matrix Method (SMM). This method has been successfully applied to predicting peptide binding to MHC molecules, peptide transport by the transporter associated with antigen presentation (TAP) and proteasomal cleavage of protein sequences.

Results: Herein we report the implementation of the SMM algorithm as a publicly available software package. Specific features determining the type of problems the method is most appropriate for are discussed. Advantageous features of the package are: (1) the output generated is easy to interpret, (2) input and output are both quantitative, (3) specific computational strategies to handle experimental noise are built in, (4) the algorithm is designed to effectively handle bounded experimental data, (5) experimental data from randomized peptide libraries and conventional peptides can easily be combined, and (6) it is possible to incorporate pair interactions between positions of a sequence.

Conclusion: Making the SMM method publicly available enables bioinformaticians and experimental biologists to easily access it, to compare its performance to other prediction methods, and to extend it to other applications.

Show MeSH