Abstract: Methods, systems, and non-transitory computer readable media are disclosed for accurately and efficiently detect when bubbles impact nucleic-acid-sequencing runs based on data captured during (or derived from) base calls during sequencing runs. In particular, in one or more embodiments, the disclosed systems receive data identifying nucleobase calls and data identifying quality metrics for the nucleobase calls during sequencing cycles. Based on particular nucleobase calls and threshold markers for the quality metrics, the disclosed system utilizes a machine-learning-model to detect a presence of a bubble in a nucleotide-sample slide. Beyond simply detecting the presence of a bubble, the disclosed system can also classify different detected bubbles, such as air bubbles, oil bubbles, or ghost bubbles, or other outputs during sequencing.

Abstract: The technology disclosed attenuates spatial crosstalk from sequencing images for base calling. The technology disclosed accesses a section of an image output by a biosensor, where the section of the image includes a plurality of pixels depicting intensity emission values from a plurality of clusters within the biosensor and from locations within the biosensor that are adjacent to the plurality of clusters. The plurality of clusters includes a target cluster. The section of the image is convolved with a convolution kernel, to generate a feature map comprising a plurality of features having a corresponding plurality of feature values. A weighted feature value is assigned to the target cluster, where the weighted feature value is based on one or more features values of the plurality of feature values of the feature map. The weighted feature value assigned to the target cluster is processed, to base call the target cluster.

Abstract: A system for base calling includes memory storing a topology of a neural network, a plurality of weights sets, and sensor data for a series of sensing cycles. Sequencing events span temporal progression of the base calling operation through subseries of sensing cycles, and spatial progression of the base calling operation through locations on a biosensor. A configurable processor is configured to load the topology on the configurable processor, select a weight set in dependence upon a subject subseries of sensing cycles and/or a subject location on the biosensor, load subject sensor data for the subject subseries of sensing cycles and the subject location on the processing elements, configure the topology using the selected weight set, and cause the neural network to process the subject sensor data to produce base call classification data for the subject subseries and the subject location.

Abstract: The technology disclosed corrects inter-cluster intensity profile variation for improved base calling on a cluster-by-cluster basis. The technology disclosed accesses current intensity data and historic intensity data of a target cluster, where the current intensity data is for a current sequencing cycle and the historic intensity data is for one or more preceding sequencing cycles. A first accumulated intensity correction parameter is determined by accumulating distribution intensities measured for the target cluster at the current and preceding sequencing cycles. A second accumulated intensity correction parameter is determined by accumulating intensity errors measured for the target cluster at the current and preceding sequencing cycles. Based on the first and second accumulated intensity correction parameters, next intensity data for a next sequencing cycle is corrected to generate corrected next intensity data, which is used to base call the target cluster at the next sequencing cycle.

Abstract: A method of quantizing parameters of a neural network includes grouping a plurality of parameters of a neural network in a plurality of groups. Each group of the plurality of groups includes corresponding two or more parameters of the plurality of parameters. In an example, for each group, a corresponding quantization format is selected from a plurality of available quantization formats, such that a first quantization format selected for at least a first group is different from a second quantization format selected for at least a second group. For each group, individual parameters within the corresponding group are quantized using the quantization format selected for the corresponding group. The quantized parameters of the plurality of groups are stored in a memory.

Abstract: The technology disclosed generates variation correction coefficients on a cluster-by-cluster basis to correct inter-cluster intensity profile variation for improved base calling. An amplification coefficient corrects scale variation. Channel-specific offset coefficients correct shift variation along respective intensity channels. The variation correction coefficients for a target cluster are generated based on combining analysis of historic intensity data generated for the target cluster at preceding sequencing cycles of a sequencing run with analysis of current intensity data generated for the target cluster at a current sequencing cycle of the sequencing run. The variation correction coefficients are then used to correct next intensity data generated for the target cluster at a next sequencing cycle of the sequencing run. The corrected next intensity data is then used to base call the target cluster at the next sequencing cycle.

Abstract: The technology disclosed generates variation correction coefficients on a cluster-by-cluster basis to correct inter-cluster intensity profile variation for improved base calling. An amplification coefficient corrects scale variation. Channel-specific offset coefficients correct shift variation along respective intensity channels. The variation correction coefficients for a target cluster are generated based on combining analysis of historic intensity data generated for the target cluster at preceding sequencing cycles of a sequencing run with analysis of current intensity data generated for the target cluster at a current sequencing cycle of the sequencing run. The variation correction coefficients are then used to correct next intensity data generated for the target cluster at a next sequencing cycle of the sequencing run. The corrected next intensity data is then used to base call the target cluster at the next sequencing cycle.

Abstract: The technology disclosed relates to identifying unreliable clusters to improve accuracy and efficiency of base calling. The technology disclosed includes accessing per-cycle cluster data for a plurality of clusters and for a first subset of sequencing cycles of a sequencing run, and base calling each cluster in the plurality of clusters at each sequencing cycle in the first subset of sequencing cycles, including generating per-cycle probability quadruple for each cluster and for each sequencing cycle. The technology disclosed includes determining a filter value for each per-cluster, per-cycle probability quadruple based on the probabilities it identifies, identifying those clusters in the plurality of clusters as unreliable clusters whose sequences of filter values contain at least “N” number of filter values below a threshold “M”, and bypassing base calling the unreliable clusters at a remainder of sequencing cycles of the sequencing run.

Abstract: The technology disclosed relates to equalizer-based intensity correction for base calling. In particular, the technology disclosed relates to accessing an image whose pixels depict intensity emissions from a target cluster and intensity emissions from additional adjacent clusters, selecting a lookup table that contains pixel coefficients that are configured to increase a signal-to-noise ratio, applying the pixel coefficients to intensity values of the pixels in the image to produce an output, and base calling the target cluster based on the output.

Abstract: The technology disclosed attenuates spatial crosstalk from sequencing images for base calling. In particular, the technology disclosed accesses an image whose pixels depict intensity emissions from a target cluster and intensity emissions from additional adjacent clusters. The pixels include a center pixel that contains a center of the target cluster. Each pixel in the pixels is divisible into a plurality of subpixels. Depending upon a particular subpixel, in a plurality of subpixels of the center pixel, which contains the center of the target cluster, the technology disclosed selects, from a bank of subpixel lookup tables, a subpixel lookup table that corresponds to the particular subpixel. The selected subpixel lookup table contains pixel coefficients that are configured to maximizes a signal-to-noise ratio. The technology disclosed element-wise multiplies the pixel coefficients with the pixels and determines a weighted sum.

Abstract: The technology disclosed attenuates spatial crosstalk from sequencing images for base calling. In particular, the technology disclosed accesses an image whose pixels depict intensity emissions from a target cluster and intensity emissions from additional adjacent clusters. The pixels include a center pixel that contains a center of the target cluster. Each pixel in the pixels is divisible into a plurality of subpixels. Depending upon a particular subpixel, in a plurality of subpixels of the center pixel, which contains the center of the target cluster, the technology disclosed selects, from a bank of subpixel lookup tables, a subpixel lookup table that corresponds to the particular subpixel. The selected subpixel lookup table contains pixel coefficients that are configured to maximizes a signal-to-noise ratio. The technology disclosed element-wise multiplies the pixel coefficients with the pixels and determines a weighted sum.

Abstract: The technology disclosed relates to an artificial intelligence-based method of base calling. In particular, it relates to processing, through a spatial network of a neural network-based base caller, a first window of per-cycle analyte channel sets in for a first window of sequencing cycles of a sequencing run, and generating respective sequences of spatial output sets for respective sequencing cycles in the first window of sequencing cycles, processing, through a compression network of the neural network-based base caller, respective final spatial output sets in the respective sequences of spatial output sets, and generating respective compressed spatial output sets for the respective sequencing cycles in the first window of sequencing cycles, and generating, based on the respective compressed spatial output sets, base call predictions for one or more sequencing cycles in the first window of sequencing cycles.

Abstract: A system for analysis of base call sensor output has memory accessible by the runtime program storing tile data including sensor data for a tile from sensing cycles of a base calling operation. A neural network processor having access to the memory is configured to execute runs of a neural network using trained parameters to produce classification data for sensing cycles. A run of the neural network operates on a sequence of N arrays of tile data from respective sensing cycles of N sensing cycles, including a subject cycle, to produce the classification data for the subject cycle. Data flow logic moves tile data and the trained parameters from the memory to the neural network processor for runs of the neural network using input units including data for spatially aligned patches of the N arrays from respective sensing cycles of N sensing cycles.

Abstract: The technology disclosed relates to a system that comprises a spatial convolution network and a bus network. The spatial convolution network is configured to process a window of per-cycle sequencing image sets on a cycle-by-cycle basis by separately processing respective per-cycle sequencing image sets through respective spatial processing pipelines to generate respective per-cycle spatial feature map sets for respective sequencing cycles. The bus network is configured to form buses between spatial convolution layers within the respective spatial processing pipelines. The buses are configured to cause respective per-cycle spatial feature map sets generated by two or more spatial convolution layers in a particular sequence of spatial convolution layer for a particular sequencing cycle to combine into a combined per-cycle spatial feature map set, and provide the combined per-cycle spatial feature map set as input to another spatial convolution layer in the particular sequence of spatial convolution layer.

Abstract: The technology disclosed relates to a system that comprises a spatial convolution network and a temporal convolution network. The spatial convolution network is configured to process a window of per-cycle sequencing image sets and generate respective per-cycle spatial feature map sets. Trained coefficients of spatial convolution filters in spatial convolution filter banks of respective sequences of spatial convolution filter banks vary between sequences of spatial convolution layers in respective sequences of spatial convolution layers. The temporal convolution network is configured to process the per-cycle spatial feature map sets on a groupwise basis and generate respective per-group temporal feature map sets. Trained coefficients of temporal convolution filters in respective temporal convolution filter banks vary between temporal convolution filter banks in respective temporal convolution filter banks.