Granted Patent B2

US 12,306,203 · App. 17/296,480 · Granted May 20, 2025

Inventor: Michael Keller (Bauma/ZH, CH)

Assignee: TECAN TRADING AG

G01N35/1016

Abstract

Claims (38)

1. A method for classifying liquid handling procedures with a control device of a laboratory automation system, the method comprising:

receiving measurement data encoding a measurement curve of measurements over time during a liquid handling procedure;

inputting the measurement data into a neural network;

inputting liquid handling data into the neural network, wherein the liquid handling data encode a configuration and/or setting of a laboratory automation system performing the liquid handling procedure;

calculating at least one quality value for the liquid handling procedure with the neural network; and

controlling the laboratory automation system with the at least one quality value by marking a liquid handling procedure as erroneous when the quality value is indicative of a failed liquid handling procedure,

wherein the neural network comprises at least one measurement data branch composed of at least one layer and a liquid handling data branch composed of at least one layer,

wherein the neural network comprises a dense layer branch into which an output of the measurement data branch and an output of the liquid handling data branch is input, and

wherein the measurement data is input into an input layer of the measurement data branch and the liquid handling data is input into an input layer of the liquid handling data branch.

2. The method of claim 1 ,

wherein the measurement data comprise a vector of timely ordered measurement values.

3. The method of claim 1 ,

wherein the measurement data branch comprises at least two convolutional layers.

4. The method of claim 1 ,

wherein the dense layer branch comprises at least two dense layers.

5. The method of claim 1 ,

wherein the neural network outputs a classification value, classifying the liquid handling procedure.

6. The method of claim 5 , wherein the classification value indicates at least one of: correct procedure, clot, air aspiration, short sample, bubbles, foam, blocked tip, leakage.

7. The method of claim 1 ,

wherein the neural network outputs an estimation value, estimating a physical quantity of the liquid handling procedure.

8. The method of claim 7 ,

wherein the estimation value estimates at least one of: a dispensed volume, an aspirated volume.

9. The method of claim 1 ,

wherein the liquid handling procedure comprises at least one of:

aspirating the liquid into a pipette by lowering a pressure in the pipette; and

dispensing a liquid in the pipette ( 14 ) and/or a dispense cannula by raising a pressure in the pipette and/or the dispense cannula.

10. A computer program for classifying liquid handling procedures, which, when being executed by a processor, is adapted to carry out the steps of the method of claim 1 .

11. A computer-readable medium, in which a computer program according to claim 10 is stored.

12. A laboratory automation system, the system comprising:

a liquid handling arm for carrying a pipette and/or a dispense cannula;

a pump for changing a pressure in a volume connected to the pipette for aspiring and dispensing a liquid in the pipette;

a sensor device for performing measurements in the volume connected to the pipette; and

a control device for controlling the pump and for receiving measurement data from the sensor device;

wherein the control device is adapted for performing the method of one of claim 1 .

13. The method of claim 1 , further comprising:

discarding a result of the liquid handling procedure when the quality value is indicative of a failed liquid handling procedure.

14. The method of claim 1 , further comprising:

repeating an assay and/or sample processing with the liquid handling procedure when the quality value is indicative of a failed liquid handling procedure.

Assignments (1)

Priority Claims (1)

Continuity (1)

References Cited (28)