公开(公告)号：US20230003697A1

公开(公告)日：2023-01-05

申请号：US17931691

申请日：2022-09-13

Applicant: Ventana Medical Systems, Inc. ,  Roche Diagnostics Operations, Inc.

Inventor： Christoph Guetter ,  Kirill Tarasov ,  Andreas Reichert ,  Raghavan Venugopal ,  Daniel Russakoff

IPC: G01N30/86 ,  G06N3/04 ,  G06N3/063

Abstract: 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.

公开(公告)号：US20220155269A1

公开(公告)日：2022-05-19

申请号：US17649801

申请日：2022-02-03

Applicant: Roche Diagnostics Operations, Inc.

Inventor： Galina Babitzki ,  Ruediger Laubender ,  Julian Michely ,  Andreas Reichert ,  Kirill Tarasov

IPC: G01N30/86 ,  G01N30/72

Abstract: A computer implemented method for automatic peak integration of at least one chromatogram of at least one sample. The method comprises retrieving at least one chromatogram of the chemical related substance and at least one chromatogram of the analyte; evaluating the chromatogram of the chemical related substance, wherein the evaluating comprises determining at least one initial value for analyte retention time by determining retention time of the chemical related substance and adding the retention time of the chemical related substance with a pre-determined or pre-defined constant offset and/or multiplying the retention time of the chemical related substance with a pre-determined or pre-defined constant factor; evaluating the chromatogram of the analyte, wherein the evaluating comprises at least one position determining step; and at least one peak integration step, wherein analyte peak area and analyte peak shape are determined by applying at least one fitting analysis to the chromatogram of the analyte.

公开(公告)号：US20240385154A1

公开(公告)日：2024-11-21

申请号：US18689808

申请日：2022-09-05

Applicant: Roche Diagnostics Operations, Inc.

Inventor： Kirill Tarasov ,  Andreas Reichert ,  Manuela Hummel ,  Robert Lang ,  Marius Wagner

IPC: G01N30/86 ,  G01N30/02 ,  G01N30/72

Abstract: A computer implemented method for automated quality check of chromatographic and/or mass spectral data is disclosed. The method comprises the following steps: a) (110) providing processed chromatographic and/or mass spectral data obtained by at least one mass spectrometry device (112); b) (114) classifying quality of the chromatographic and/or mass spectral data by applying at least one trained machine learning model on the chromatographic and/or mass spectral data, wherein the trained machine learning model uses at least one regression model (116), wherein the trained machine learning model is trained on at least one training dataset comprising historical and/or semi-synthetic chromatographic and/or mass spectral data, wherein the trained machine learning model is an analyte-specific trained machine learning model.

公开(公告)号：US20230251233A1

公开(公告)日：2023-08-10

申请号：US18124837

申请日：2023-03-22

Applicant: Roche Diagnostics Operations, Inc.

Inventor： Julian Michely ,  Andreas Reichert

IPC: G01N30/86 ,  G01N30/72

CPC classification number: G01N30/8631 ,  G01N30/7233 ,  G01N30/8693 ,  G01N2030/027

Abstract: A computer-implemented method for detecting at least one interference and/or at least one artefact in at least one chromatogram determined by at least one mass spectrometry device (110) is proposed. The chromatogram comprises a plurality of raw data points. The method comprises the following steps:

a) retrieving the at least one chromatogram by at least one processing device (126);
b) applying at least one peak fit modelling to the chromatogram by using the processing device (126);
c) determining information about residuals of the raw data points by using the processing device (126);
d) detecting the at least one interference and/or the at least one artefact by using the processing device (126) by comparing the determined information about the residuals with at least one pre-determined threshold, wherein, if the determined information about the residuals exceed the pre-determined threshold, the at least one interference and/or the at least one artefact is detected.