US 12,461,077 B2
Computer-implemented method for identifying at least one peak in a mass spectrometry response curve
Christoph Guetter, Alameda, CA (US); Kirill Tarasov, Tutzing (DE); Andreas Reichert, Peissenberg (DE); Raghavan Venugopal, Fremont, CA (US); and Daniel Russakoff, San Francisco, CA (US)
Assigned to Roche Diagnostics Operations, Inc., Indianapolis, IN (US); and Ventana Medical Systems, Inc., Tucson, AZ (US)
Filed by Ventana Medical Systems, Inc., Tucson, AZ (US); and Roche Diagnostics Operations, Inc., Indianapolis, IN (US)
Filed on Sep. 13, 2022, as Appl. No. 17/931,691.
Application 17/931,691 is a continuation of application No. PCT/EP2021/057935, filed on Mar. 26, 2021.
Claims priority of application No. 20166187 (EP), filed on Mar. 27, 2020.
Prior Publication US 2023/0003697 A1, Jan. 5, 2023
Int. Cl. G01N 30/86 (2006.01); G06N 3/048 (2023.01); G06N 3/063 (2023.01)
CPC G01N 30/8631 (2013.01) [G01N 30/8644 (2013.01); G01N 30/8693 (2013.01); G06N 3/048 (2023.01); G06N 3/063 (2013.01)] 11 Claims
OG exemplary drawing
 
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.