公开(公告)号：US20220336042A1

公开(公告)日：2022-10-20

申请号：US17640771

申请日：2020-09-29

Applicant: Cytiva Sweden AB

Inventor： Tobias Soderman ,  Olof Karlsson ,  Magnus Raberg ,  Andreas Borgstrom

IPC: G16B15/00 ,  G16B40/20 ,  G01N21/552 ,  G01N21/27 ,  G06N3/08

Abstract: Disclosed is a method for classifying monitoring results from an analytical sensor system (20) arranged to monitor molecular interactions at a sensing surface, wherein detection curves representing progress of the molecular interactions with time are produced. The method comprises steps of: acquiring (100) a set of detection curves, fitting (101) a first mathemati- cal model to the set of detection curves; calculating (102) a set of features from the set of detection curves and fitted mathematical model; based on the calculated set of features, classifying (103) each detection curve into qual- ity classification group; and based on the classification determining which detection curves to use in kinetic analysis of the monitored molecular inter- actions.

公开(公告)号：US20220259532A1

公开(公告)日：2022-08-18

申请号：US17618352

申请日：2020-06-23

Applicant: Cytiva Sweden AB

Inventor： Magnus Raberg ,  Tobias Soderman ,  Andreas Borgstrom ,  Helena Ohrvik

IPC: C12M1/36 ,  G05B17/02

Abstract: The present invention relates to a computer implemented method performed by a controller (C) configured to control a bioprocess comprised in a bioreactor (BR), the method comprising obtaining (410) measurement results by performing spectroscopy of a bioprocessing fluid (FL) comprised in the bioreactor (BR), generating bioprocessing parameters using the measurement results, one or more bioprocessing target parameters and one or more trained models, and, controlling the bioprocess using the generated bioprocessing parameters. The method wherein the one or more trained models are neural networks, wherein the measurement results comprise a spectrum, wherein the spectrum is split to a number N parts used to calculate N average values, wherein the N average values and the corresponding values of bioprocessing parameters are used § as features in the neural network.

公开(公告)号：US11093583B2

公开(公告)日：2021-08-17

申请号：US15761570

申请日：2016-09-29

Applicant: CYTIVA SWEDEN AB

Inventor： Tobias Soderman ,  Viveca Lindahl

IPC: G06F17/18

Abstract: Methods and biosensor systems for improved evaluation of an interaction between an analyte in a fluid sample and a ligand immobilized on a sensor surface of a biosensor are provided. In one example, a method is provided which includes allowing a plurality of fluid samples to flow across a first sensor surface and a second sensor surface having a ligand immobilized thereon, where the fluid samples include a solvent (for example, an organic solvent with bulk effects such as DMSO) at known concentrations. The method further includes creating a data set for each fluid sample and forming a clean data set with outliers removed. Software for performing steps of methods disclosed and a computer readable medium for storing the software are also provided.

公开(公告)号：US20230228676A1

公开(公告)日：2023-07-20

申请号：US17998236

申请日：2021-06-22

Applicant: CYTIVA SWEDEN AB

Inventor： Tobias Soderman ,  Olof Karlsson ,  Paul E. Belcher

IPC: G01N21/27 ,  G16C20/70 ,  G16C20/50

CPC classification number: G01N21/272 ,  G16C20/70 ,  G16C20/50

Abstract: Disclosed is a method for classifying monitoring results from an analytical sensor system (20), by allowing (100) a first set of analyte sample solutions to interact with a ligand (3) and acquiring (101) a set of response data, extracting (102) at least one interaction parameter from the response data, and for each analyte sample solution providing (103) a trained machine learning algorithm with the interaction parameter(s). The trained machine learning algorithm classifies (104) each analyte sample solution based on the interaction parameter(s) into at least one quality classification group indicative of the interaction of the analyte sample solution with the ligand (3). The machine learning algorithm is trained (200) using a set of interaction parameters extracted from response data obtained from interactions between a second set of analyte sample solutions with at least one ligand (3), and at least one quality classification group indicative of the interaction of the analyte sample solution with the ligand (3).