Abstract: Some techniques relate to projecting aptamer representations into an embedding space and clustering the representations. A cluster-specific binding metric can be defined for each cluster based on aptamer-specific binding metrics of aptamers associated with the cluster. A subset of the clusters can be selected based on the cluster-specific binding metrics. Identifications of aptamers assigned to the subset of clusters can then be output.

Abstract: A multi-dimensional latent space (defined by an Encoder model) corresponds to projections of sequences of aptamers. An architecture of the Encoder model, a hyperparameter of the Encoder model, or a characteristic of a training data set used to train the Encoder model was selected using an assessment of an encoding-efficiency of the Encoder model that is based on: a predicted extents to which representations in an embedding space are indicative of specific aptamer sequences to which a probability distribution of the embedding space differs from a probability distribution of a source space that represents individual base-pairs; generating projections in the latent space using representations of aptamers and the Encoder model; identifying one or more candidate aptamers for the particular target using the projections and the Decoder model; and outputting an identification of the one or more candidate aptamers.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for processing fundus images using fundus image processing machine learning models. One of the methods includes obtaining a model input comprising one or more fundus images, each fundus image being an image of a fundus of an eye of a patient; processing the model input using a fundus image processing machine learning model, wherein the fundus image processing machine learning model is configured to process the model input comprising the one or more fundus image to generate a model output; and processing the model output to generate health analysis data.

Abstract: A virtual camera captures first images of a three-dimensional (3D) digital representation of a visual asset from different perspectives and under different lighting conditions. The first images are training images that are stored in a memory. One or more processors implement a generative adversarial network (GAN) that includes a generator and a discriminator, which are implemented as different neural networks. The generator generates second images that represent variations of the visual asset concurrently with the discriminator attempting to distinguish between the first and second images. The one or more processors update a first model in the discriminator and/or a second model in the generator based on whether the discriminator successfully distinguished between the first and second images. Once trained, the generator generates images of the visual asset based on the first model, e.g., based on a label or an outline of the visual asset.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for processing fundus images using fundus image processing machine learning models. One of the methods includes obtaining a model input comprising one or more fundus images, each fundus image being an image of a fundus of an eye of a patient; processing the model input using a fundus image processing machine learning model, wherein the fundus image processing machine learning model is configured to process the model input comprising the one or more fundus image to generate a model output; and processing the model output to generate health analysis data.

Abstract: The present disclosure relates to in vitro experiments and in silico computation and machine-learning based techniques to iteratively improve a process for identifying binders that can bind a target. Particularly, aspects of the present disclosure are directed to obtaining initial sequence data, identifying, by a first machine-learning model having model parameters learned from the initial sequence data, a first set of aptamer sequences, obtaining, using an in vitro binding selection process, subsequent sequence data including sequences from the first set of aptamer sequences, identifying, by a second machine-learning model having model parameters learned from the subsequent sequence data, a second set of aptamer sequences, determining, using one or more in vitro assays, analytical data for aptamers synthesized from the second set of aptamer sequences, and identifying a final set of aptamer sequences from the second set of aptamer sequences based on the analytical data associated with each aptamer.

Abstract: A latent space is defined to represent sequences using training data and a machine-learning model. The training data identifies sequences of molecules and binding-approximation metrics that characterizes whether the molecules bind to a particular target and/or that approximate an extent to which the molecule is more likely to bind to the particular target than some other molecules. Supplemental training data is accessed that identifies other sequences of other molecules and binding affinity scores quantifying binding strengths between the molecules and the particular target. Projections of representations of the other sequences in the supplemental training data are projected in the latent space using the binding affinity scores. An area or position of interest within the latent space is identified based on the projections. A particular sequence represented within or at the area or position of interest or at the position of interest is identified for downstream processing.

Abstract: The present disclosure relates to in vitro experiments and in silico computation and machine-learning based techniques to iteratively improve a process for identifying binders that can bind any given molecular target. Particularly, aspects of the present disclosure are directed to obtaining initial sequence data for aptamers that bind to a target, measuring a first signal to noise ratio within the initial sequence data, provisioning, based on the first signal to noise ratio, a first machine-learning system, generating, by the first machine-learning system, a first set of aptamer sequences, obtaining subsequent sequence data for aptamers that bind to the target, measuring a second signal to noise ratio within the subsequent sequence data, provisioning, based on the second signal to noise ratio, a second machine-learning system, generating, by the second machine-learning system, a second set of aptamer sequences, and outputting the second set of aptamer sequences.

Abstract: The present disclosure relates to in vitro experiments and in silico computation and machine-learning based techniques to iteratively improve a process for identifying binders that can bind any given molecular target. Particularly, aspects of the present disclosure are directed to obtaining sequence data for aptamers that bind to a target, where the sequence data has a first signal to noise ratio, generating, by a search process, a first set of aptamer sequences derived from the sequence data, obtaining subsequent sequence data for subsequent aptamers that bind to the target, where the subsequent aptamers includes aptamers synthesized from the first set of aptamer sequences, and the subsequent sequence data has a second signal to noise ratio greater than the first signal to noise ratio, generating, by a linear machine-learning model, a second set of aptamer sequences derived from the subsequent sequence data, and outputting the second set of aptamer sequences.

Abstract: A method for detecting false positive variant calls in a next generation sequencing analysis pipeline involves obtaining a plurality of read pileup windows associated with a first sample genome. The method also involves obtaining, for each reference nucleotide position represented in the plurality of read pileup windows, a label indicating that the reference nucleotide position is either (i) a known variant or (ii) a non-variant. The method further involves training a neural network based on data indicative of the plurality of read pileup windows and the labels. Additionally, the method involves receiving a read pileup window associated with a second sample genome. Further, the method involves determining, using the trained neural network, a likelihood that the read pileup window associated with the second sample genome represents a variant.

Abstract: The present disclosure is directed to systems and method to perform improved detection of out-of-distribution (OOD) inputs. In particular, current deep generative model-based approaches for OOD detection are significantly negatively affected by and struggle to distinguish population level background statistics from semantic content relevant to the in-distribution examples. In fact, such approaches have even been experimentally observed to assign higher likelihood to OOD inputs, which is opposite to the desired behavior. To resolve this problem, the present disclosure proposes a likelihood ratio method for deep generative models which effectively corrects for these confounding background statistics.

Abstract: Systems and methods are provided for receiving at least one image and a reference image, and performing a plurality of downscaling operations having separable convolutions on the received at least one image. A plurality of residual blocks may be formed, with each residual block containing two separable convolutions of the kernel and two instance normalizations. A plurality of upscaling operations may be performed on the plurality of residual blocks, and a stylized image may be displayed based on at least the performed plurality of upscaling operations and the reference image.

Abstract: A method for detecting false positive variant calls in a next generation sequencing analysis pipeline involves obtaining a plurality of read pileup windows associated with a first sample genome. The method also involves obtaining, for each reference nucleotide position represented in the plurality of read pileup windows, a label indicating that the reference nucleotide position is either (i) a known variant or (ii) a non-variant. The method further involves training a neural network based on data indicative of the plurality of read pileup windows and the labels. Additionally, the method involves receiving a read pileup window associated with a second sample genome. Further, the method involves determining, using the trained neural network, a likelihood that the read pileup window associated with the second sample genome represents a variant.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for processing fundus images using fundus image processing machine learning models. One of the methods includes obtaining a model input comprising one or more fundus images, each fundus image being an image of a fundus of an eye of a patient; processing the model input using a fundus image processing machine learning model, wherein the fundus image processing machine learning model is configured to process the model input comprising the one or more fundus image to generate a model output; and processing the model output to generate health analysis data.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for processing fundus images using fundus image processing machine learning models. One of the methods includes obtaining a model input comprising one or more fundus images, each fundus image being an image of a fundus of an eye of a patient; processing the model input using a fundus image processing machine learning model, wherein the fundus image processing machine learning model is configured to process the model input comprising the one or more fundus image to generate a model output; and processing the model output to generate health analysis data.

Abstract: The present invention relates to systems and methods for determining the identity of alleles from genomic sequencing data via pseudoalignments. Particularly, aspects of the present invention are directed to a computer implemented method that includes obtaining a paired-end fragment from a genomic sample, determining a first nucleotide substring from a first end of the paired-end fragment matches a nucleotide substring within an index of nucleotide substrings and alleles, determining a second nucleotide substring from a second end of the paired-end fragment matches another nucleotide substring within the index, determining an intersection between the nucleotide substring and the another nucleotide substring exists, when an allele that contains the nucleotide substring is the same allele that contains the another nucleotide substring; and determining a probability that the paired end fragment is an observation of the allele based on the existence of the intersection.

Abstract: A method for variant calling in a next generation sequencing analysis pipeline involves obtaining a plurality of sequence reads that each include a nucleotide aligned at a nucleotide position within a sample genome. The method also involves obtaining a plurality of alleles associated with the nucleotide position. The method further involves determining that a particular allele of the plurality of alleles matches one or more sequence reads of the plurality of sequence reads, wherein the particular allele is located at the nucleotide position. Additionally, the method involves generating an image based on information associated with the plurality of sequence reads. Further, the method involves determining, by providing the generated image to a trained neural network, a likelihood that the sample genome contains the particular allele. The method may also involves providing an output signal indicative of the determined likelihood.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for processing fundus images using fundus image processing machine learning models. One of the methods includes obtaining a model input comprising one or more fundus images, each fundus image being an image of a fundus of an eye of a patient; processing the model input using a fundus image processing machine learning model, wherein the fundus image processing machine learning model is configured to process the model input comprising the one or more fundus image to generate a model output; and processing the model output to generate health analysis data.