Method for predicting peptide detection in mass spectrometry
A method of predicting whether a peptide present in a biological sample will be detected by analysis with a mass spectrometer. The method uses at least one mass spectrometer to perform repeated analysis of a sample containing peptides from proteins with known amino acids. The method then generates a data set of peptides identified as contained within the sample by the repeated analysis. The method then calculates the probability that a specific peptide in the data set was detected in the repeated analysis. The method then creates a plurality of vectors, where each vector has a plurality of dimensions, and each dimension represents a property of one or more of the amino acids present in each peptide and adjacent peptides in the data set. Using these vectors, the method then generates an algorithm from the plurality of vectors and the calculated probabilities that specific peptides in the data set were detected in the repeated analysis. The algorithm is thus capable of calculating the probability that a hypothetical peptide represented as a vector will be detected by a mass spectrometry based proteomic platform, given that the peptide is present in a sample introduced into a mass spectrometer.
1. A method for predicting that a peptide will be detected in a mass spectrometry based proteomic platform comprising the steps of:
a. using at least one mass spectrometer, performing repeated analysis of a sample containing peptides from proteins with a known amino acid sequence,
b. generating a data set of peptides identified as contained within the sample by the repeated analysis,
c. calculating the probability that a specific peptide in the data set was detected in the repeated analysis,
d. creating a plurality of vectors, each vector having a plurality of dimensions, each dimension representing a property of one or more of the amino acids present in each peptide in the data set,
e. generating an algorithm from the plurality of vectors and the calculated probabilities that specific peptides in the data set were detected in the repeated analysis, said algorithm capable of calculating the probability that a hypothetical peptide represented as a vector will be detected by a mass spectrometry based proteomic platform, given that the corresponding peptide is present in a sample introduced into a mass spectrometer.
2. The method of claim 1 wherein the step of generating an algorithm from the data set is by a data driven model.
3. The method of claim 2 wherein the data driven model is selected from the group: multivariate regression, neural network, support vector machine, and combinations thereof.
4. An apparatus for predicting that a peptide will be detected in a mass spectrometry based proteomic platform comprising:
a computer configured to:
i. accept data from repeated mass spectrometric analysis of a sample containing peptides from proteins with a known amino acid sequence,
ii. accept a data set of peptides identified as contained within the sample by the repeated analysis,
iii. calculate the probability that a specific peptide in the data set was detected in the repeated analysis,
iv. create a plurality of vectors, each vector having a plurality of dimensions, each dimension representing a property of one or more of the amino acids present in each peptide in the data set,
v. generate an algorithm from the plurality of vectors and the calculated probabilities that specific peptides in the data set were detected in the repeated analysis, said algorithm capable of calculating the probability that a hypothetical peptide represented as a vector will be detected by a mass spectrometry based proteomic platform given that the corresponding peptide is present in a sample introduced into a mass spectrometer.
5. The apparatus of claim 4 wherein the algorithm generated from the data set is generated by a data driven model.
6. The apparatus of claim 5 wherein the data driven model is selected from the group: multivariate regression, neural network, support vector machine, and combinations thereof.