Limits...
A machine learning approach to explore the spectra intensity pattern of peptides using tandem mass spectrometry data.

Zhou C, Bowler LD, Feng J - BMC Bioinformatics (2008)

Bottom Line: The predictions include not only the mean values of spectra intensity but also the variances that can be used to tolerate noises and system biases within experimental MS/MS spectra.The features with significant influence can be used in turn to predict spectra intensities.Such information can help develop more reliable algorithms for peptide and protein identification.

View Article: PubMed Central - HTML - PubMed

Affiliation: Department of Computer Science and Mathematics, University of Warwick, Coventry CV4 7AL, UK. joecong2@yahoo.co.uk

ABSTRACT

Background: A better understanding of the mechanisms involved in gas-phase fragmentation of peptides is essential for the development of more reliable algorithms for high-throughput protein identification using mass spectrometry (MS). Current methodologies depend predominantly on the use of derived m/z values of fragment ions, and, the knowledge provided by the intensity information present in MS/MS spectra has not been fully exploited. Indeed spectrum intensity information is very rarely utilized in the algorithms currently in use for high-throughput protein identification.

Results: In this work, a Bayesian neural network approach is employed to analyze ion intensity information present in 13878 different MS/MS spectra. The influence of a library of 35 features on peptide fragmentation is examined under different proton mobility conditions. Useful rules involved in peptide fragmentation are found and subsets of features which have significant influence on fragmentation pathway of peptides are characterised. An intensity model is built based on the selected features and the model can make an accurate prediction of the intensity patterns for given MS/MS spectra. The predictions include not only the mean values of spectra intensity but also the variances that can be used to tolerate noises and system biases within experimental MS/MS spectra.

Conclusion: The intensity patterns of fragmentation spectra are informative and can be used to analyze the influence of various characteristics of fragmented peptides on their fragmentation pathway. The features with significant influence can be used in turn to predict spectra intensities. Such information can help develop more reliable algorithms for peptide and protein identification.

Show MeSH

Related in: MedlinePlus

Structure of the Bayesian neural network used to explore the mechanism of gas-phase fragmentation of peptides. The network is fully connected and feed-forward with three layers including one hidden layer. 73 nodes are used in the input layer representing 35 features. 40 nodes in binary are used to represent the presence of 20 different residues at N and C terminus to the target peptide bond. Every node in the input layer has an independent coefficient to reveal its "relevance" to the network output. The hidden layer has 40 nodes and the activation function of the hidden layer is sigmoidal.
© Copyright Policy - open-access
Related In: Results  -  Collection

License
getmorefigures.php?uid=PMC2529326&req=5

Figure 1: Structure of the Bayesian neural network used to explore the mechanism of gas-phase fragmentation of peptides. The network is fully connected and feed-forward with three layers including one hidden layer. 73 nodes are used in the input layer representing 35 features. 40 nodes in binary are used to represent the presence of 20 different residues at N and C terminus to the target peptide bond. Every node in the input layer has an independent coefficient to reveal its "relevance" to the network output. The hidden layer has 40 nodes and the activation function of the hidden layer is sigmoidal.

Mentions: In this part of the study, MS/MS spectra data as described in [23] were acquired from Wysocki VH. The intensity information contained within the spectra was then used to verify a library of features that are supposed to influence peptide fragmentation (Table 1). The values of relevant amino acid properties that were used for calculating these features can be found in Table 2. This feature set is a modified version of what was used by Elias, et al. [19]. We aimed to determine a group of features that genuinely influence the intensity patterns of MS/MS spectra. For this purpose, a Bayesian neural network model was developed. The structure of the network model is illustrated in Figure 1 and more details can be found in the method section of the paper.


A machine learning approach to explore the spectra intensity pattern of peptides using tandem mass spectrometry data.

Zhou C, Bowler LD, Feng J - BMC Bioinformatics (2008)

Structure of the Bayesian neural network used to explore the mechanism of gas-phase fragmentation of peptides. The network is fully connected and feed-forward with three layers including one hidden layer. 73 nodes are used in the input layer representing 35 features. 40 nodes in binary are used to represent the presence of 20 different residues at N and C terminus to the target peptide bond. Every node in the input layer has an independent coefficient to reveal its "relevance" to the network output. The hidden layer has 40 nodes and the activation function of the hidden layer is sigmoidal.
© Copyright Policy - open-access
Related In: Results  -  Collection

License
Show All Figures
getmorefigures.php?uid=PMC2529326&req=5

Figure 1: Structure of the Bayesian neural network used to explore the mechanism of gas-phase fragmentation of peptides. The network is fully connected and feed-forward with three layers including one hidden layer. 73 nodes are used in the input layer representing 35 features. 40 nodes in binary are used to represent the presence of 20 different residues at N and C terminus to the target peptide bond. Every node in the input layer has an independent coefficient to reveal its "relevance" to the network output. The hidden layer has 40 nodes and the activation function of the hidden layer is sigmoidal.
Mentions: In this part of the study, MS/MS spectra data as described in [23] were acquired from Wysocki VH. The intensity information contained within the spectra was then used to verify a library of features that are supposed to influence peptide fragmentation (Table 1). The values of relevant amino acid properties that were used for calculating these features can be found in Table 2. This feature set is a modified version of what was used by Elias, et al. [19]. We aimed to determine a group of features that genuinely influence the intensity patterns of MS/MS spectra. For this purpose, a Bayesian neural network model was developed. The structure of the network model is illustrated in Figure 1 and more details can be found in the method section of the paper.

Bottom Line: The predictions include not only the mean values of spectra intensity but also the variances that can be used to tolerate noises and system biases within experimental MS/MS spectra.The features with significant influence can be used in turn to predict spectra intensities.Such information can help develop more reliable algorithms for peptide and protein identification.

View Article: PubMed Central - HTML - PubMed

Affiliation: Department of Computer Science and Mathematics, University of Warwick, Coventry CV4 7AL, UK. joecong2@yahoo.co.uk

ABSTRACT

Background: A better understanding of the mechanisms involved in gas-phase fragmentation of peptides is essential for the development of more reliable algorithms for high-throughput protein identification using mass spectrometry (MS). Current methodologies depend predominantly on the use of derived m/z values of fragment ions, and, the knowledge provided by the intensity information present in MS/MS spectra has not been fully exploited. Indeed spectrum intensity information is very rarely utilized in the algorithms currently in use for high-throughput protein identification.

Results: In this work, a Bayesian neural network approach is employed to analyze ion intensity information present in 13878 different MS/MS spectra. The influence of a library of 35 features on peptide fragmentation is examined under different proton mobility conditions. Useful rules involved in peptide fragmentation are found and subsets of features which have significant influence on fragmentation pathway of peptides are characterised. An intensity model is built based on the selected features and the model can make an accurate prediction of the intensity patterns for given MS/MS spectra. The predictions include not only the mean values of spectra intensity but also the variances that can be used to tolerate noises and system biases within experimental MS/MS spectra.

Conclusion: The intensity patterns of fragmentation spectra are informative and can be used to analyze the influence of various characteristics of fragmented peptides on their fragmentation pathway. The features with significant influence can be used in turn to predict spectra intensities. Such information can help develop more reliable algorithms for peptide and protein identification.

Show MeSH
Related in: MedlinePlus