Computer-implemented method for identifying at least one peak in a mass spectrometry response curve
A computer implemented method for identifying at least one peak in a mass spectrometry response curve is provided comprising: a) providing at least one mass spectrometry response curve by using at least one mass spectrometry device; b) evaluating the mass spectrometry response curve by using at least one trained model thereby identifying a start point and an end point of at least one peak of the mass spectrometry response curve, wherein the model was trained using a deep learning regression architecture.
1 . A computer implemented method for identifying at least one peak in a mass spectrometry response curve and monitoring at least one analyte in a sample, the method comprising the following steps:
a) providing at least one mass spectrometry response curve by using at least one mass spectrometry device that includes a detector, a quadrupole mass analyzer, and an ionization source;
b) evaluating the mass spectrometry response curve by using at least one trained model thereby identifying a start point and an end point of at least one peak of the mass spectrometry response curve, wherein the model is trained using a deep learning regression architecture, including i) providing at least one training dataset comprising a plurality of input mass spectrometry response curves and corresponding ground truth, and ii) determining the at least one model by using the deep learning regression architecture on the training dataset, wherein the determination of the model comprises determining a model architecture and at least one parameter of the model; and
c) identifying, by an evaluation device, the analyte in the sample based on the evaluation of the mass spectrometry response curve, including performing correlation of defined masses to identified masses or identification of a characteristic fragmentation pattern.
2 . The method according to claim 1 , wherein the deep learning regression architecture comprises a convolutional neural network.
3 . The method according to claim 2 , wherein the convolutional neural network is a multilayer convolutional neural network.
4 . The method according to claim 3 , wherein the convolutional neural network comprises a plurality of convolutional layers, wherein the convolutional layers are one dimensional layers.
5 . The method according to claim 2 , wherein the convolutional neural network comprises as a final layer a regression layer, wherein the regression layer has a linear or sigmoid activation.
6 . The method according to claim 1 , wherein the training dataset is provided as a five channel vector comprising an aggregated time vector, two analyte mass spectrometry response curves and two internal standard mass spectrometry response curves.
7 . The method according to claim 1 , wherein the training of the model comprises at least one normalization step and/or at least one augmentation step.
8 . The method according to claim 1 , wherein the training step further comprises at least one testing step using at least one test dataset, wherein the testing step comprises determining a start point and an end point of at least one peak of the mass spectrometry response curve of the test dataset using the determined model, wherein performance of the determined model is determined based on the determined start point and an end point and a ground truth of the mass spectrometry response curve of the test dataset.
9 . The method according to claim 1 , wherein the method comprises determining a peak area of the peak of the mass spectrometry response curve by using the identified start point and end point.
10 . A device for monitoring at least one analyte in a sample comprising:
at least one mass spectrometry device that includes a detector, a quadrupole mass analyzer, and an ionization source, wherein the mass spectrometry device is configured for providing at least one mass spectrometry response curve;
at least one evaluation device configured for evaluating the mass spectrometry response curve by using at least one trained model thereby identifying a start point and an end point of at least one peak of the mass spectrometry response curve, wherein the model is trained using a deep learning regression architecture, including i) providing at least one training dataset comprising a plurality of input mass spectrometry response curves and corresponding ground truth, and ii) determining the at least one model by using the deep learning regression architecture on the training dataset, wherein the determination of the model comprises determining a model architecture and at least one parameter of the model, wherein the at least one evaluation device is further configured to identify the analyte in the sample based on the evaluation of the mass spectrometry response curve, including correlation of defined masses to identified masses or identification of a characteristic fragmentation pattern.
11 . A non-transitory machine-readable storage media comprising instructions that, when executed, cause a computer to:
a) provide at least one mass spectrometry response curve by using at least one mass spectrometry device that includes a detector, a quadrupole mass analyzer, and an ionization source;
b) evaluate the mass spectrometry response curve by using at least one trained model thereby identifying a start point and an end point of at least one peak of the mass spectrometry response curve, wherein the model is trained using a deep learning regression architecture including i) providing at least one training dataset comprising a plurality of input mass spectrometry response curves and corresponding ground truth, and ii) determining the at least one model by using the deep learning regression architecture on the training dataset, wherein the determination of the model comprises determining a model architecture and at least one parameter of the model; and
c) identify the analyte in the sample based on the evaluation of the mass spectrometry response curve, including correlation of defined masses to identified masses or identification of a characteristic fragmentation pattern.