Abstract: Systems, methods, and apparatus are described herein for identifying callable regions and performing variant calling while operating within allocated memory. A sequencing subsystem may comprise a variant caller or variant caller subsystem. The variant caller may include a calling subsystem configured to identify callable regions and may send the callable regions to a downstream genotyping subsystem of the variant caller. The calling subsystem of the variant caller may be configured to detect a callable region of the sequencing data when a depth of the plurality of reads is above a callable region depth threshold. The calling subsystem of the variant caller may monitor memory used by the callable region and, when the memory used exceeds a memory threshold of a total amount of memory allocated, the calling subsystem may split or spill at least a portion of the callable region to operate within the total amount of allocated memory.

Abstract: Defocus is introduced during sequencing by synthesis by tilt of a flow cell and by variations in flatness of the flow cell. Effects of the defocus are reduced, and base calling quality is improved using techniques relating to dependence of base calling on flow cell tilt. For example, the flow cell surface height is measured throughout the flow cell. A focal height of an imager having a sensor for the sequencing is set, optionally adaptively, one or more times during the sequencing. Each image captured by the sensor is partitioned, e.g., based on differences between focal height and the measured flow cell surface height across areas of the sensor. Filters, e.g., related to defocus correction, are selected based at least in part on the difference between the focal height and the measured flow cell surface height at a particular area of the image being corrected for defocus.

Abstract: Systems, methods, and apparatus are described herein for training machine learning models to predict probe intensity values using sample-specific image data and/or applying the predicted probe intensity values. As described herein, sample-specific image may include a signal associated with a sample for a process probe in a microarray relating to a single individual. The machine learning model may be trained, using the sample-specific image data, to predict a probe intensity value. The probe intensity value may be a raw probe intensity value or a normalized probe intensity value. After being trained, the machine learning model may receive as input a probe sequence or probe features. The machine learning model may be used to predict a total probe intensity value based on the probe sequence or the one or more probe features.

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.

Abstract: Artificial intelligence driven signal enhancement of sequencing images enables enhanced sequencing by synthesis that determines a sequence of bases in genetic material with any one or more of: improved performance, improved accuracy, and/or reduced cost. A training set of images taken at unreduced and reduced power levels used to excite fluorescence during sequencing by synthesis is used to train a neural network to enable the neural network to recover enhanced images, as if taken at the unreduced power level, from unenhanced images taken at the reduced power level.

Abstract: Artificial intelligence driven enhancement of motion blurred sequencing images enables enhanced sequencing that determines a sequence of bases in genetic material with any one or more of: improved performance, improved accuracy, and/or reduced cost. A training set of images taken after unreduced and reduced movement settling times during sequencing is used to train a neural network to enable the neural network to recover enhanced images, as if taken after the unreduced movement settling time, from unenhanced images taken after the reduced movement settling time.

Abstract: An iterative process may be implemented for incrementally aggregating available batches of sample data with previously available batches to perform sequencing analysis. Genomic variant call files associated with one or more samples may be received in batches from sequencing devices and aggregated for performing sequencing analysis. The aggregated genomic variant call files may be used to generate cohort files and census files that comprise summary information related to the genomic variant call files in each batch. The census data in census files may be aggregated into a global census file that includes summary genome variant data. Multi-sample variant call files may be generated based on the global census file, cohort files, and census files. The genomic variant call files may be processed using parallel processing at multiple compute nodes. The files may be further compressed and overlapping data may be efficiently stored in buffer positions.

Abstract: The technology disclosed includes a system. The system includes a spatial convolutional neural network configured to process sequencing images of clusters, and produce spatially convolved features, a filtering logic configured to select, from the spatially convolved features, a subset of spatially convolved features that contain centers of the clusters, a compression logic configured to compress the subset of spatially convolved features into a set of compressed features, a contextualization logic configured to access state information for compressed features in the set of compressed features, a temporal convolutional neural network configured to process the set of stateful compressed features, and produce temporally convolved stateful features, and a base calling logic configured to generate base calls for the clusters based on the temporally convolved stateful features.

Abstract: A method of base calling using at least two base callers is disclosed. The method includes executing at least a first base caller and a second base caller on sensor data generated for sensing cycles in a series of sensing cycles; generating, by the first base caller, first classification information associated with the sensor data, based on executing the first base caller on the sensor data; and generating, by the second base caller, second classification information associated with the sensor data, based on executing the second base caller on the sensor data. In an example, based on the first classification information and the second classification information, a final classification information is generated, where the final classification information includes one or more base calls for the sensor data.

Abstract: A method of generating base calls by a base caller is disclosed. The method includes receiving a plurality of sensor data from a flow cell, wherein the plurality of sensor data is within a first range and identifying a second range, such that at least a threshold percentage of the plurality of sensor data are within the second range. At least a subset of the plurality of sensor data, that are within the second range, are mapped to a third range, thereby generating a plurality of normalized sensor data. The plurality of normalized sensor data is processed in a base caller, to call, for the plurality of normalized sensor data, one or more corresponding bases.

Abstract: We disclose a system. The system comprises a memory and a runtime logic. The memory stores a plurality of specialist signal profilers. Each specialist signal profiler in the plurality of specialist signal profilers is trained to maximize signal-to-noise ratio of sequenced signals in a particular signal profile detected for analytes in a particular analyte class and characterized in a particular training data set. The runtime logic, having access to the memory, is configured to execute a base calling operation by applying respective specialist signal profilers in the plurality of specialist signal profilers to sequenced signals in respective signal profiles detected for analytes in respective analyte classes during the base calling operation.

Abstract: The technology disclosed extracts intensities from sequencing images for base calling target clusters and attenuates spatial crosstalk from neighboring clusters. The technology disclosed accesses a particular section from a plurality of sections of an image output by a sensor, the particular section of the image including at least one pixel depicting intensity emission values from a target cluster and neighboring clusters located across the sensor, and convolves the particular section of the image with a corresponding convolution kernel in a plurality of convolution kernels, to generate a feature map comprising a plurality of feature values. The technology disclosed further assigns a corresponding feature value to the target cluster based on feature values in the plurality of feature values adjoining a center of the target cluster, and processes the corresponding feature value assigned to the target cluster, to base call the target cluster.

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 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: 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.