Dependence of base calling on flow cell tilt

A method of selectively performing equalizer-based base calling on in-focus and defocus elements of an image collected during sequencing, the method comprising:

• capturing an image of a portion of a flow cell using a sensor having a depth of field (DoF);
• categorizing, based at least in part on one or more tilt measurements of the flow cell portion, respective elements of the image as either in-focus or defocus in spatial relation the DoF;
• selecting, based at least in part on a scalar tilt measurement, one or more respective equalizer-based base callers for each of the in-focus and defocus categories;
• and
• performing base calling of the image using the one or more selected equalizer-based base callers, wherein performing base calling comprises:
• applying a set of coefficients in a respective LUT to intensity values of a corresponding set of image pixels of a target base,
• determining, based on application of the set of coefficients, a weighted sum of intensity values of the image pixels, and
• outputting the weighted sum as a base call prediction.

A method of training an equalizer to perform equalizer-based base calling on in-focus and defocus elements of an image collected during sequencing, the method comprising:

• obtaining a training dataset of images of respective portions of one or more flow cells, wherein each image comprises known areas of defocus based on tilt measurements of a respective flow cell portion;
• inputting the training dataset into the equalizer;
• causing the equalizer to perform base calling on known areas of defocus in the training dataset, wherein performing base calling comprises:
• applying a set of coefficients in a respective LUT of the equalizer to intensity values of a corresponding set of image pixels of a target base,
• determining, based on application of the set of coefficients, a weighted sum of intensity values of the image pixels,
• calculating an error for the weighted sum based on an intensity target determined for the target base,
• updating, using a derivative of the error, the set of coefficients with values that reduce the error, and
• repeatedly causing the equalizer to perform base calling on known areas of defocus until an updated set of coefficients no longer reduce the error.

A system for selectively performing base calling on in-focus and defocus elements of an image collected during sequencing, the method comprising:

• at least one processor;
• and
• at least one memory system having computer-executable instructions stored thereon that, when executed by the processor, cause the processor to:
• receive an image of a portion of a flow cell captured using a sensor having a depth of field (DoF);
• determine, based at least in part on one or more tilt measurements of the flow cell portion, categories of respective elements of the image as either in-focus or defocus in spatial relation the DoF;
• select, based at least in part on a scalar tilt measurement, one or more respective base callers for each of the in-focus and defocus categories;
• and
• cause each of the one or more selected base callers to selectively perform base calling on respective in-focus and defocus elements of the image.