12 results about "Base calling" patented technology

This disclosure describes methods, non-transitory computer readable media, and systems that can utilize a machine learning model to recalibrate nucleotide-base calls (e.g., variant calls) of a call-generation model. For instance, the disclosed systems can train and utilize a call-recalibration-machine-learning model to generate a set of predicted variant-call classifications based on sequencing metrics associated with a sample nucleotide sequence. Leveraging the set of variant-call classifications, the disclosed systems can further update or modify nucleotide-base calls (e.g., variant calls) corresponding to genomic coordinates. Indeed, the disclosed systems can generate an initial nucleotide-base call based on sequencing metrics for nucleotide reads of a sample sequence utilizing a call-generation model and further utilize a call-recalibration-machine-learning model to generate classification predictions for updating or recalibrating the initial nucleotide-base call from a subset of the same sequencing metrics or other sequencing metrics.

The application discloses a nanopore base recognition method based on Libtorch and C++, which comprises the following steps: obtaining nanopore sequencing data of a target sample and preprocessing the data, wherein the preprocessing comprises normalization and overlapping segmentation; delivering the preprocessed data to a model inference module based on a convolutional neural network and a bidirectional long short-term memory network in an asynchronous mode, performing GPU inference on each time step, and outputting base sequence weights of each time step; decoding the base sequence weights of each time step output by the model inference module through a CTC decoding module based on a greedy search and a prefix beam search; reassembling the decoded result; and outputting the result. The model inference module is optimized, efficient data loading and multi-GPU inference are realized, the inference time is significantly shortened, the memory occupation is effectively reduced, the memory consumption is reduced while the high accuracy is maintained, and the running speed and throughput of base recognition are accelerated.

The present disclosure provides methods for reducing sequencing errors comprising one or any combination of: (i) removing deaminated bases in any nucleic acid molecule throughout a library preparation workflow which includes immobilised splints which bind to the library, the use of a compaction oligonucleotide, optionally with an intervening sequence, formation of closed circular nucleic acids, creating gaps using glycosylase and lyase activities at positions with deaminated bases. The library may be sequenced using pairwise sequencing, e.g. with dark sequencing and / or sequencing using a multivalent labelled probe for the formation of an avidity molecule and soluble primer and polymerase. Method for sequencing concatemers in which the concatermers are contacted with polymerases, soluble primers and a multivalent labelled molecule which forms a complex with the polymerase. Detecting polymerase position and nucleobase bound to the polymerase in the complex. These methods generate higher quality base calls during downstream sequencing workflows.

The application provides a method for determining a quality score Q value of base detection, a sequencing method and a device. The method comprises: receiving input image data for determining a quality score Q value of base detection in an Nth sequencing reaction, wherein the input image data comprises an image of a template to be detected in an Mth sequencing reaction and an image of the template to be detected in the Nth sequencing reaction, M and N are natural numbers and M is less than N; determining a predetermined prediction feature based on the input image data; determining a prediction probability value of correctly identifying a base incorporated into the template to be detected in the Nth sequencing reaction based on the predetermined prediction feature and using a trained machine learning model; and determining the quality score Q value of base detection in the Nth sequencing reaction based on the prediction probability value. The method can improve the efficiency and / or accuracy of determining the quality score Q value of base detection.

The present application provides a base calling method, a base calling model training method, and a related device. The base calling method comprises: acquiring, during a sequencing cycle of gene sequencing, a plurality of fluorescence images of a plurality of nucleic acid sequence clusters to be sequenced; by means of an embedding module of a preset base calling model, performing feature mapping on fluorescence intensity sequences corresponding to the plurality of fluorescence images to obtain a feature tensor; by means of a multi-head attention mechanism-based encoding module in the base calling model, encoding the feature tensor to obtain an encoded tensor; and by means of a classification module of the base calling model, classifying the plurality of said nucleic acid sequence clusters on the basis of the encoded tensor to obtain base categories corresponding to the plurality of said nucleic acid sequence clusters in the sequencing cycle. Use of the described method can improve the accuracy of identifying a base category corresponding to a nucleic acid sequence cluster to be sequenced.

A computer-implemented method comprises: determining coefficients corresponding to a section of a flow cell; accessing an image depicting the section of the flow cell and intensity emissions from a target cluster of concatemers; and generating a base call for the target cluster of concatemers by applying the coefficients to the intensity emissions for the target cluster of concatemers.

This disclosure describes methods, non-transitory computer readable media, and systems that can utilize a machine learning model to recalibrate nucleotide base calls (e.g., variant calls) of a call generation model. For instance, the disclosed systems can train and utilize a call recalibration machine learning model to generate a set of predicted variant call classifications based on sequencing metrics associated with a sample nucleotide sequence. Leveraging the set of variant call classifications, the disclosed systems can further update or modify nucleotide base calls (e.g., variant calls) corresponding to genomic coordinates, such as multiallelic genomic coordinates, haploid genomic coordinates, and genomic coordinates indicated (by the call generation model) to exhibit homozygous reference genotypes.

Provided in the present application are a base calling method, a base calling model training method, and a related device. The base calling method comprises: acquiring a plurality of fluorescence images of a plurality of nucleic acid sequence clusters under test in a sequencing cycle process of gene sequencing; on the basis of an embedded module of a preset base calling model, performing feature mapping on fluorescence intensity sequences corresponding to the plurality of fluorescence images to obtain a fluorescence feature sequence; inputting the fluorescent feature sequence into a timing neural network module of the base calling model to obtain a target feature sequence output by the timing neural network module; and, by means of a classification module of the base calling model, classifying the plurality of nucleic acid sequence clusters under test on the basis of the target feature sequence to obtain base categories corresponding to the plurality of nucleic acid sequence clusters under test in the sequencing cycle. Using the method can improve the accuracy of calling base categories corresponding to nucleic acid sequence clusters under test.

The application relates to a base recognition method and related equipment. The method is applied to a first node and at least one second node. The first node receives image data, distributes the image data according to the at least one second node to obtain first image sub-data, and sends the first image sub-data to the at least one second node. The at least one second node calculates the first image sub-data to obtain first base recognition information. The application realizes base recognition of image data through multiple distributed computing nodes (such as the second node), can reduce the cost of computing resources, and as the number of computing nodes increases, the overall computing performance also increases; since the computing nodes process distributed image data, the amount of data processed by the computing nodes is small, and subsequent data transmission and data read-write operations between the second node and other external equipment (such as a bioinformatics server) are facilitated.