Methods and systems for determining a plurality of sequences of nucleic acid (e.g., DNA) molecules in a sequencing-by-synthesis process are provided. In one embodiment, the method comprises obtaining images of fluorescent signals obtained in a plurality of synthesis cycles. The images of fluorescent signals are associated with a plurality of different fluorescence channels. The method further comprises preprocessing the images of fluorescent signals to obtain processed images. Based on a set of the processed images, the method further comprises detecting center positions of clusters of the fluorescent signals using a trained convolutional neural network (CNN) and extracting, based on the center positions of the clusters of fluorescent signals, features from the set of the processed images to generate feature embedding vectors. The method further comprises determining, in parallel, the plurality of sequences of DNA molecules using the extracted features based on a trained attention-based neural network.

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.

A computer-implemented method for determining an output signal characterizing a first classification of an input image into a class from a plurality of classes. The output signal further characterizes a second classification of a robustness of the first classification against an attack with an adversarial patch.

A method for quantifying labels on a substrate is performed by an electronic device with one or more processors and memory. The method includes obtaining digital data corresponding to a multi-dimensional measurement over the substrate; identifying a first set of sub-portions of the digital data; and, for a respective sub-portion of the first set of sub-portions of the digital data: increasing a quantity of labels, and subtracting a reference signal distribution from the respective sub-portion to obtain subtracted sub-portion data. The method also includes obtaining subtracted digital data. The subtracted digital data includes the subtracted sub-portion data for the respective sub-portion. The method further includes identifying a second set of one or more sub-portions of the subtracted digital data; and, for a respective sub-portion of the second set of one or more sub-portions of the subtracted digital data, increasing a quantity of labels.

A method of generating a codebook includes obtaining a plurality of gene-identifying code words for the codebook. Each gene-identifying code word is represented by a sequence of N bits that correspond to a best match to a pixel data value identifying a gene. A plurality of negative control code words is generated, and each negative control code word is represented by a sequence of N bits. The negative control code words have an equal number of on-values. On-values of the plurality of negative control code words are evenly distributed across the N bits such that each ordinal position in the sequence of N bits has a same total number of on-bits from the plurality of negative control code words, and a Hamming distance between each negative control code word and each gene-identify code word is at least a distance threshold.

An image processing method including identifying, using a machine learning system, an area of interest of a target image by analyzing microscopic features extracted from multiple image regions in the target image, the machine learning system being generated by processing a plurality of training images each comprising an image of human tissue and a diagnostic label characterizing at least one of a slide morphology, a diagnostic value, a pathologist review outcome, and an analytic difficulty; determining, using the machine learning system, a probability of a target feature being present in the area of interest of the target image based on an average probability; and determining, using the machine learning system, a prioritization value, of a plurality of prioritization values, of the target image based on the probability of the target feature being present in the target image.

An image processing method including receiving a target image of a slide corresponding to a target specimen comprising a tissue sample of a patient; generating a machine learning system by processing a plurality of training images, each training image comprising an image of human tissue and a label characterizing at least one of a slide morphology, a diagnostic value, a pathologist review outcome, and an analytic difficulty; automatically identifying, using the machine learning system, an area of interest of the target image by analyzing microscopic features extracted from multiple image regions in the target image; determining, using the machine learning system, a probability of a target feature being present in the area of interest of the target image based on an average probability; and determining, using the machine learning system, a prioritization value, of a plurality of prioritization values.

Methods and systems for image analysis are provided, and in particular for identifying a set of base-calling locations in a flow cell for DNA sequencing. These include capturing flow cell images after each sequencing step performed on the flow cell, and identifying candidate cluster centers in at least one of the flow cell images. Intensities are determined for each candidate cluster center in a set of flow cell images. Purities are determined for each candidate cluster center based on the intensities. Each candidate cluster center with a purity greater than the purity of the surrounding candidate cluster centers within a distance threshold is added to a template set of base-calling locations.

A system and method for improving the efficiency of information flow of and during clinical trials and also using edge-based and cloud-based machine learning for analyzing clinical trial data from inception to completion subsequently protecting investments, assets, and human life. The system comprises a pharmaceutical research system that receives, pushes, and facilitates data packets containing clinical trial information across multiple sites and across multiple trial personnel while also using machine learning for a variety of tasks. A mobile application on edge devices uses edge-based machine learning to identify biomarkers and provides sponsors and clinicians with an expedient and secure communication means. The edge devices and the cloud-based machine learning communicate full-duplex and share information and machine learning models leading to an improvement in early adverse effects detection. Biomarkers predicting severe adverse effects trigger the system to send alerts, reports, and potential victims to medical personnel for immediate intervention.

A particle detection method detects presence and location of particles on a target using measured signals from a plurality of structured illumination patterns. The particle detection method uses measured signals obtained by illuminating the target with structured illumination patterns to detect particles. Specifically, the degree of variation in these measured signals in raw images is calculated to determine whether a particle is present on the target at a particular area of interest.