Machine learning-based genotyping process outcome prediction using aggregate metrics

A system including one or more processors coupled to memory, the memory loaded with computer instructions to avoid post-processing of an image from extension of probes on beads during a sample evaluation run, the instructions, when executed on the one or more processors, cause the one or more processors to:

• receive an image of beads in an array of tiles on a beadchip,
• calculate averages, over each tile in at least one image channel, of focus quality values of images of the beads,
• predict from the average focus quality values of the tiles, using a trained classifier, a likelihood of failure score due to a failure selected from a group comprising blur, reagent flow failure, misalignment failure, spacer shift failure, hybridization failure, or surface abrasion failure for the sample evaluation run, wherein the trained classifier is trained to predict likelihood of failure scores from average focus quality values of images of beads in arrays of tiles on beadchips, and
• report the likelihood of failure score for the sample evaluation run to an operator of the sample evaluation run, wherein the likelihood of failure score indicates the likelihood of failure in post-processing of samples in the images of the beads due to process-related or sample-related errors, and wherein the likelihood of failure score is reported to the operator to avoid the post-processing of the samples imaged from the beads during the sample evaluation run.

A non-transitory computer readable storage medium impressed with computer program instructions to avoid post-processing of an image from extension of probes on beads during a sample evaluation run, the instructions, when executed on at least one processor, cause the at least one processor to:

• receive an image of beads in an array of tiles on a beadchip,
• calculate averages, over each tile in at last one image channel, of focus quality values of images of the beads,
• predict from the average focus quality values of the tiles, using a trained classifier, a likelihood of failure score due to a failure selected from a group comprising blur, reagent flow failure, misalignment failure, spacer shift failure, hybridization failure, or surface abrasion failure for the sample evaluation run, wherein the trained classifier is trained to predict likelihood of failure scores from average focus quality values of images of beads in arrays of tiles on beadchips, and
• report the likelihood of failure score for the sample evaluation run to an operator of the sample evaluation run, wherein the likelihood of failure score indicates the likelihood of failure in post-processing of samples in the images of the beads due to process-related or sample-related errors, and wherein the likelihood of failure score is reported to the operator to avoid the post-processing of the samples imaged from the beads during the sample evaluation run.