State-based base calling

Patent metadata

Field	Value
Publication number	US-12412387-B2
Application number	US-202217944809-A
Country	US
Kind code	B2
Filing date	Sep 14, 2022
Priority date	Sep 22, 2021
Publication date	Sep 9, 2025
Grant date	Sep 9, 2025

Abstract

The technology disclosed relates to state-based base calling. In particular, the technology disclosed relates to incorporating state information about data from previous sequencing cycles into the analysis of data from a current sequencing cycle when generating a base call for the current sequencing cycle. For example, when generating a base call for an Nth sequencing cycle, the technology disclosed can incorporate into the base calling logic state information about data from sequencing cycles 1 to N−1.

First claim

What we claim is:

1. A system, comprising:
memory storing, for a current sequencing cycle of a sequencing run, respective current intensity values for respective pixels in a plurality of pixels;
the memory storing, for one or more previous sequencing cycles of the sequencing run that precede the current sequencing cycle, sequences of respective previous intensity values for the respective pixels;
a state generator, having access to the memory, configured to generate respective current state values for the respective pixels in dependence upon
(i) the respective current intensity values, and
(ii) respective previous intensity values in the sequences of respective previous intensity values, and to store the respective current state values in the memory; and

a base caller, having access to the memory, configured to generate base calls for the current sequencing cycle in response to processing
(i) the respective current intensity values, and
(ii) the respective current state values.

2. The system of claim 1 , wherein respective intensity values for the respective pixels are each characterized by channel-specific intensity values for a plurality of channels.

3. The system of claim 2 , wherein respective state values for the respective pixels are each characterized by channel-specific state values for the plurality of channels.

4. The system of claim 3 , wherein the respective current state values are pixel-wise encoded with the respective current intensity values.

5. The system of claim 3 , wherein channel-specific state values for a subset of channels in the plurality of channels are pixel-wise encoded with the respective current intensity values.

6. The system of claim 3 , wherein the channel-specific state values are averaged across channels in the plurality of channels to generate respective pan-channel current state values, wherein the respective pan-channel current state values are pixel-wise encoded with the respective current intensity values.

7. The system of claim 4 , wherein the pixel-wise encoding includes pixel-wise concatenation.

8. The system of claim 4 , wherein the pixel-wise encoding includes pixel-wise summing.

9. The system of claim 1 , wherein the respective current state values are respective current average intensities determined for the respective pixels at the current sequencing cycle from
(i) the respective previous intensity values, and
(ii) the respective current intensity values.

10. The system of claim 9 , wherein the respective current average intensities are each characterized by channel-specific current average intensities.

11. The system of claim 10 , wherein the respective current state values are respective current maximum intensities determined for the respective pixels at the current sequencing cycle from
(i) the respective previous intensity values, and
(ii) the respective current intensity values.

12. The system of claim 11 , wherein the respective current maximum intensities are each characterized by channel-specific current maximum intensities.

13. The system of claim 12 , wherein the respective current state values are respective current minimum intensities determined for the respective pixels at the current sequencing cycle from
(i) the respective previous intensity values, and
(ii) the respective current intensity values.

14. The system of claim 13 , wherein the respective current minimum intensities are each characterized by channel-specific current minimum intensities.

15. The system of claim 14 , wherein the respective current state values are respective current exponentially weighted average intensities determined for the respective pixels at the current sequencing cycle from
(i) the respective previous intensity values, and
(ii) the respective current intensity values.

16. The system of claim 15 , wherein the respective current exponentially weighted average intensities are determined based on weighting recent sequencing cycles more than earlier sequencing cycles.

17. The system of claim 16 , wherein the respective current exponentially weighted average intensities are each characterized by channel-specific current exponentially weighted average intensities.

18. The system of claim 17 , wherein the respective current state values are respective current moving average intensities determined for the respective pixels at the current sequencing cycle from
(i) the respective current intensity values, and
(ii) a rolling subset of the respective previous intensity values.

19. The system of claim 18 , wherein the respective current moving average intensities are each characterized by channel-specific current moving average intensities.

20. The system of claim 19 , wherein each of the respective current intensity values is attributed to an active state bucket or an inactive state bucket based on comparison of the respective current intensity values to respective current active state intensities and respective current inactive state intensities.

21. The system of claim 20 , wherein the respective current active state intensities are respective current global maximum intensities determined for the respective pixels at the current sequencing cycle from
(i) the respective previous intensity values.

22. The system of claim 21 , wherein the respective current global maximum intensities are each characterized by channel-specific current global maximum intensities.

23. The system of claim 22 , wherein the respective current inactive state intensities are respective current global minimum intensities determined for the respective pixels at the current sequencing cycle from
(i) the respective previous intensity values.

24. The system of claim 23 , wherein the respective current global minimum intensities are each characterized by channel-specific current global minimum intensities.

25. The system of claim 24 , wherein the respective current state values further include respective current active state values and respective current inactive state values generated for the respective pixels at the current sequencing cycle.

26. The system of claim 25 , wherein the respective current active state values are each characterized by channel-specific current active state values.

27. The system of claim 26 , wherein the respective current inactive state values are each characterized by channel-specific current inactive state values.

28. The system of claim 27 , wherein a current active state value for a pixel in a subject channel is determined at the current sequencing cycle from
(i) a current intensity value for the pixel in the subject channel that is detected and attributed to the active state bucket at the current sequencing cycle, and
(ii) previous intensity values for the pixel in the subject channel that were detected at the one or more previous sequencing cycles.

29. A computer-implemented method, including:
accessing current window sequenced signal data for a first plurality of sequencing cycles in a current sliding window of sequencing cycles;
accessing previous sequenced signal data for a second plurality of sequencing cycles that precede sequencing cycles in the first plurality of sequencing cycles;
generating state signal data based on the current window sequenced signal data and the previous sequenced signal data; and
base calling at least one sequencing cycle in the firs

Assignees

• Illumina Inc

Inventors

• Parnaby Gavin Derek
• Ojard Eric Jon
• Kashefhaghighi Dorna

Classifications

• G16B30/00 Primary

  ICT specially adapted for sequence analysis involving nucleotides or amino acids · CPC title

• G06N3/0464

  Convolutional networks [CNN, ConvNet] · CPC title

• G16B40/20

  Supervised data analysis · CPC title

• G06N3/084

  Backpropagation, e.g. using gradient descent · CPC title

• G06V20/698

  Matching; Classification · CPC title