Abstract: The technology disclosed relates to splice site prediction and aberrant splicing detection. In particular, it relates to a splice site predictor that includes a convolutional neural network trained on training examples of donor splice sites, acceptor splice sites, and non-splicing sites. An input stage of the convolutional neural network feeds an input sequence of nucleotides for evaluation of target nucleotides in the input sequence. An output stage of the convolutional neural network translates analysis by the convolutional neural network into classification scores for likelihoods that each of the target nucleotides is a donor splice site, an acceptor splice site, and a non-splicing site.

Abstract: The technology disclosed relates to splice site prediction and aberrant splicing detection. In particular, it relates to a splice site predictor that includes a convolutional neural network trained on training examples of donor splice sites, acceptor splice sites, and non-splicing sites. An input stage of the convolutional neural network feeds an input sequence of nucleotides for evaluation of target nucleotides in the input sequence. An output stage of the convolutional neural network translates analysis by the convolutional neural network into classification scores for likelihoods that each of the target nucleotides is a donor splice site, an acceptor splice site, and a non-splicing site.

Abstract: We disclose computational models that alleviate the effects of human ascertainment biases in curated pathogenic non-coding variant databases by generating pathogenicity scores for variants occurring in the promoter regions (referred to herein as promoter single nucleotide variants (pSNVs)). We train deep learning networks (referred to herein as pathogenicity classifiers) using a semi-supervised approach to discriminate between a set of labeled benign variants and an unlabeled set of variants that were matched to remove biases.

Abstract: The technology disclosed relates to constructing a convolutional neural network-based classifier for variant classification. In particular, it relates to training a convolutional neural network-based classifier on training data using a backpropagation-based gradient update technique that progressively match outputs of the convolutional neural network-based classifier with corresponding ground truth labels. The convolutional neural network-based classifier comprises groups of residual blocks, each group of residual blocks is parameterized by a number of convolution filters in the residual blocks, a convolution window size of the residual blocks, and an atrous convolution rate of the residual blocks, the size of convolution window varies between groups of residual blocks, the atrous convolution rate varies between groups of residual blocks. The training data includes benign training examples and pathogenic training examples of translated sequence pairs generated from benign variants and pathogenic variants.

Abstract: The technology disclosed relates to constructing a convolutional neural network-based classifier for variant classification. In particular, it relates to training a convolutional neural network-based classifier on training data using a backpropagation-based gradient update technique that progressively match outputs of the convolutional network network-based classifier with corresponding ground truth labels. The convolutional neural network-based classifier comprises groups of residual blocks, each group of residual blocks is parameterized by a number of convolution filters in the residual blocks, a convolution window size of the residual blocks, and an atrous convolution rate of the residual blocks, the size of convolution window varies between groups of residual blocks, the atrous convolution rate varies between groups of residual blocks. The training data includes benign training examples and pathogenic training examples of translated sequence pairs generated from benign variants and pathogenic variants.

Abstract: An artificial intelligence-based system comprises an input preparation module that accesses a sequence database and generates an input base sequence. The input base sequence comprises a target base sequence with target bases, wherein the target base sequence is flanked by a right base sequence with downstream context bases, and a left base sequence with upstream context bases. A sequence-to-sequence model processes the input base sequence and generates an alternative representation of the input base sequence. An output module processes the alternative representation of the input base sequence and produces at least one per-base output for each of the target bases in the target base sequence. The per-base output specifies, for a corresponding target base, signal levels of a plurality of epigenetic tracks.

Abstract: The technology disclosed relates to constructing a convolutional neural network-based classifier for variant classification. In particular, it relates to training a convolutional neural network-based classifier on training data using a backpropagation-based gradient update technique that progressively match outputs of the convolutional neural network-based classifier with corresponding ground truth labels. The convolutional neural network-based classifier comprises groups of residual blocks, each group of residual blocks is parameterized by a number of convolution filters in the residual blocks, a convolution window size of the residual blocks, and an atrous convolution rate of the residual blocks, the size of convolution window varies between groups of residual blocks, the atrous convolution rate varies between groups of residual blocks. The training data includes benign training examples and pathogenic training examples of translated sequence pairs generated from benign variants and pathogenic variants.

Abstract: The technology disclosed relates to constructing a convolutional neural network-based classifier for variant classification. In particular, it relates to training a convolutional neural network-based classifier on training data using a backpropagation-based gradient update technique that progressively match outputs of the convolutional network network-based classifier with corresponding ground truth labels. The convolutional neural network-based classifier comprises groups of residual blocks, each group of residual blocks is parameterized by a number of convolution filters in the residual blocks, a convolution window size of the residual blocks, and an atrous convolution rate of the residual blocks, the size of convolution window varies between groups of residual blocks, the atrous convolution rate varies between groups of residual blocks. The training data includes benign training examples and pathogenic training examples of translated sequence pairs generated from benign variants and pathogenic variants.

Abstract: Systems and methods for determining structural variation and phasing using variant call data obtained from nucleic acid of a biological sample are provided. Sequence reads are obtained, each comprising a portion corresponding to a subset of the test nucleic acid and a portion encoding a barcode independent of the sequencing data. Bin information is obtained. Each bin represents a different portion of the sample nucleic acid. Each bin corresponds to a set of sequence reads in a plurality of sets of sequence reads formed from the sequence reads such that each sequence read in a respective set of sequence reads corresponds to a subset of the nucleic acid represented by the bin corresponding to the respective set. Binomial tests identify bin pairs having more sequence reads with the same barcode in common than expected by chance. Probabilistic models determine structural variation likelihood from the sequence reads of these bin pairs.

Abstract: Systems and methods for analyzing first and second strings against a ground truth string are provided. A construct representing a plurality of components is obtained, each component for a different portion of the truth string. The construct comprises a plurality of measurement string sampling pools each having an identifier and a corresponding plurality of measurement samplings corresponding to one or two of the components. Each sampling has the identifier and a portion of the first or second string. Samplings are assigned to first, second or third classes when coding a portion of the first string, second string, or both the first and second string. First and second positions are tested for sequence events by calculating a plurality of sequence event models using assumptions on the components having samplings encompassing the first and second positions and class assignments. These assumptions are updated using the calculated models and the models are recalculated.

Abstract: Systems and methods for determining structural variation and phasing using variant call data obtained from nucleic acid of a biological sample are provided. Sequence reads are obtained, each comprising a portion corresponding to a subset of the test nucleic acid and a portion encoding a barcode independent of the sequencing data. Bin information is obtained. Each bin represents a different portion of the sample nucleic acid. Each bin corresponds to a set of sequence reads in a plurality of sets of sequence reads formed from the sequence reads such that each sequence read in a respective set of sequence reads corresponds to a subset of the nucleic acid represented by the bin corresponding to the respective set. Binomial tests identify bin pairs having more sequence reads with the same barcode in common than expected by chance. Probabilistic models determine structural variation likelihood from the sequence reads of these bin pairs.

Abstract: Systems and methods for analyzing first and second strings against a ground truth string are provided. A construct representing a plurality of components is obtained, each component for a different portion of the truth string. The construct comprises a plurality of measurement string sampling pools each having an identifier and a corresponding plurality of measurement samplings corresponding to one or two of the components. Each sampling has the identifier and a portion of the first or second string. Samplings are assigned to first, second or third classes when coding a portion of the first string, second string, or both the first and second string. First and second positions are tested for sequence events by calculating a plurality of sequence event models using assumptions on the components having samplings encompassing the first and second positions and class assignments. These assumptions are updated using the calculated models and the models are recalculated.

Abstract: We disclose computational models that alleviate the effects of human ascertainment biases in curated pathogenic non-coding variant databases by generating pathogenicity scores for variants occurring in the promoter regions (referred to herein as promoter single nucleotide variants (pSNVs)). We train deep learning networks (referred to herein as pathogenicity classifiers) using a semi-supervised approach to discriminate between a set of labeled benign variants and an unlabeled set of variants that were matched to remove biases.

Abstract: Systems and methods for analyzing first and second strings against a ground truth string are provided. A construct representing a plurality of components is obtained, each component for a different portion of the truth string. The construct comprises a plurality of measurement string sampling pools each having an identifier and a corresponding plurality of measurement samplings corresponding to one or two of the components. Each sampling has the identifier and a portion of the first or second string. Samplings are assigned to first, second or third classes when coding a portion of the first string, second string, or both the first and second string. First and second positions are tested for events by calculating a plurality of event models using assumptions on the components having samplings encompassing the first and second positions and class assignments. These assumptions are updated using the calculated models and the models are recalculated.

Abstract: The technology disclosed relates to constructing a convolutional neural network-based classifier for variant classification. In particular, it relates to training a convolutional neural network-based classifier on training data using a backpropagation-based gradient update technique that progressively match outputs of the convolutional network network-based classifier with corresponding ground truth labels. The convolutional neural network-based classifier comprises groups of residual blocks, each group of residual blocks is parameterized by a number of convolution filters in the residual blocks, a convolution window size of the residual blocks, and an atrous convolution rate of the residual blocks, the size of convolution window varies between groups of residual blocks, the atrous convolution rate varies between groups of residual blocks. The training data includes benign training examples and pathogenic training examples of translated sequence pairs generated from benign variants and pathogenic variants.

Abstract: The technology disclosed relates to constructing a convolutional neural network-based classifier for variant classification. In particular, it relates to training a convolutional neural network-based classifier on training data using a backpropagation-based gradient update technique that progressively match outputs of the convolutional network network-based classifier with corresponding ground truth labels. The convolutional neural network-based classifier comprises groups of residual blocks, each group of residual blocks is parameterized by a number of convolution filters in the residual blocks, a convolution window size of the residual blocks, and an atrous convolution rate of the residual blocks, the size of convolution window varies between groups of residual blocks, the atrous convolution rate varies between groups of residual blocks. The training data includes benign training examples and pathogenic training examples of translated sequence pairs generated from benign variants and pathogenic variants.

Abstract: The technology disclosed relates to constructing a convolutional neural network-based classifier for variant classification. In particular, it relates to training a convolutional neural network-based classifier on training data using a backpropagation-based gradient update technique that progressively match outputs of the convolutional network network-based classifier with corresponding ground truth labels. The convolutional neural network-based classifier comprises groups of residual blocks, each group of residual blocks is parameterized by a number of convolution filters in the residual blocks, a convolution window size of the residual blocks, and an atrous convolution rate of the residual blocks, the size of convolution window varies between groups of residual blocks, the atrous convolution rate varies between groups of residual blocks. The training data includes benign training examples and pathogenic training examples of translated sequence pairs generated from benign variants and pathogenic variants.

Abstract: Systems and methods for analyzing first and second strings against a ground truth string are provided. A construct representing a plurality of components is obtained, each component for a different portion of the truth string. The construct comprises a plurality of measurement string sampling pools each having an identifier and a corresponding plurality of measurement samplings corresponding to one or two of the components. Each sampling has the identifier and a portion of the first or second string. Samplings are assigned to first, second or third classes when coding a portion of the first string, second string, or both the first and second string. First and second positions are tested for sequence events by calculating a plurality of sequence event models using assumptions on the components having samplings encompassing the first and second positions and class assignments. These assumptions are updated using the calculated models and the models are recalculated.

Abstract: Systems and methods for analyzing first and second strings against a ground truth string are provided. A construct representing a plurality of components is obtained, each component for a different portion of the truth string. The construct comprises a plurality of measurement string sampling pools each having an identifier and a corresponding plurality of measurement samplings corresponding to one or two of the components. Each sampling has the identifier and a portion of the first or second string. Samplings are assigned to first, second or third classes when coding a portion of the first string, second string, or both the first and second string. First and second positions are tested for events by calculating a plurality of event models using assumptions on the components having samplings encompassing the first and second positions and class assignments. These assumptions are updated using the calculated models and the models are recalculated.

Abstract: Systems and methods for determining structural variation and phasing using variant call data obtained from nucleic acid of a biological sample are provided. Sequence reads are obtained, each comprising a portion corresponding to a subset of the test nucleic acid and a portion encoding a barcode independent of the sequencing data. Bin information is obtained. Each bin represents a different portion of the sample nucleic acid. Each bin corresponds to a set of sequence reads in a plurality of sets of sequence reads formed from the sequence reads such that each sequence read in a respective set of sequence reads corresponds to a subset of the nucleic acid represented by the bin corresponding to the respective set. Binomial tests identify bin pairs having more sequence reads with the same barcode in common than expected by chance. Probabilistic models determine structural variation likelihood from the sequence reads of these bin pairs.