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).