Abstract: Methods, systems, and apparatus are provided for determining whether a nucleic acid sequence imbalance exists within a biological sample. One or more cutoff values for determining an imbalance of, for example, the ratio of the two sequences (or sets of sequences) are chosen. The cutoff value may be determined based at least in part on the percentage of fetal DNA in a sample, such as maternal plasma, containing a background of maternal nucleic acid sequences. The percentage of fetal DNA can be calculated from the same or different data used to determine the cutoff value, and can use a locus where the mother is homozygous and the fetus is heterozygous. The cutoff value may be determined using many different types of methods, such as sequential probability ratio testing (SPRT).

Abstract: The invention relates to methods for indirectly determining clinical laboratory reference intervals. In one aspect, a reference interval is determined using all measurements for a given analyte stored in a large existing database. In other aspects, a characteristic of a subject is used to select a reference population for inclusion in reference interval calculations. In other aspects, the invention provides methods for changing treatment plan, diagnosis, or prognosis for an individual subject based on differences between the new reference interval and a previously utilized reference interval. In other aspects, the invention provides systems and computer readable media for indirectly determining reference intervals.

Abstract: The invention relates to a novel administration regime useful in the treatment of diseases or conditions where administration of insulin will be of benefit. In particular, the invention relates to a long-acting or ultra-long acting insulin for use in treating a disease or condition where administration of insulin will be of benefit, wherein the administration of said insulin includes or consists of one or more of the following steps: (a) obtaining a first data set of the subject, (b) obtaining a second data set of the subject, (c) obtaining a first data structure of the subject, and (d) obtaining a second data structure of the subject. When a determination is made that the at least first data structure, second data structure, first data set, and second data set collectively do contain the set of evaluation information, the device further includes providing the long-acting or ultra-long-acting insulin dose guidance recommendation.

Abstract: An electronic processing system agent accesses population health literacy data from at least 100 individuals pertaining to assessed health literacy of members of the population, and demographic data from the population corresponding to age, race, and education level. The agent collects skills data from the patient corresponding to a set of questions relating to skills needed for understanding therapeutic instructions, and personal data relating to the patient's age, race, and education level. The agent carries out a polytomous logistic regression using the collected population health literacy data, demographic data, skills data, and personal data to assign a health literacy level to the patient corresponding to one of a plurality of groups, and communicates a strategy for the patient corresponding to the patient's assigned health literacy level, in real time, to enable the patient to have a communication of therapeutic instructions when the patient has responded to the set of questions.

Abstract: A method for determining the genetic relationship of a conceptus with sperm and oocyte providers is provided, comprising receiving conceptus, sperm provider, and oocyte provider sequence data; aligning the received sequence data to a reference genome; identifying single nucleotide polymorphisms (SNPs) in the sperm provider, oocyte provider, and conceptus sequence data; imputing missing gaps in the sperm provider sequence data and the oocyte provider sequence data using an imputation reference; calculating a paternal consistency score between the sperm provider and the conceptus; calculating a maternal consistency score between the oocyte provider and conceptus; and classifying the sperm provider and/or the oocyte provider as related to the conceptus if the paternal consistency score and/or the maternal consistency score exceeds the predetermined threshold.

Abstract: A system and method for diagnosing, determining treatment, and determining prognosis of health, performance, fitness, training regimen, and breeding condition of an animal subject using expert systems, data integration, imaging and 3D scanning technology are disclosed. The system and method uses data integration, imaging and 3D scanning technology and other methods to collect data in a very precise and repeatable process. The system and method uses an AI expert system with deep learning analysis to analyze health history of an animal, performance of the animal, and breeding potential of the animal. This approach provides a highly accurate, repeatable and unbiased method to evaluate an animal and to recommend diagnosis and treatment.

Abstract: Automated methods for detecting cancer and related hyperplasias in biological samples.

Abstract: Conventionally, deep learning-based methods have shown some success in ligand-based drug design. However, these methods face data scarcity problems while designing drugs against novel targets. Embodiments of the present disclosure provide systems and methods that leverage the potential of deep learning and molecular modeling approaches to develop a drug design pipeline, which can be useful for cases where there is limited or no availability of target-specific ligand datasets. Inhibitors of other proteins, structurally similar to the target protein are screened at the active site of the target protein to create an initial target-specific dataset. Transfer learning is implemented to learn features of target-specific dataset and design new chemical entities/molecules using a deep generative model. A deep predictive model is used predict docking scores of newly designed/identified molecules.

Abstract: A computer-based specimen analyzer (10) is configured to detect a level of expression of genes in a cell sample by detecting dots that represent differently stained genes and chromosomes in a cell. The color of the stained genes and the chromosomes is enhanced and filtered to produce a dot mask that defines areas in the image that are genes, chromosomes, or non-genetic material. Metrics are determined for the dots and/or pixels in the image of the cell in areas corresponding to the dots. The metrics are fed to a classifier that separates genes from chromosomes. The results of the classifier are counted to estimate the expression level of genes in the tissue samples.

Abstract: A combination of markers (TMEM, MenaCalc, and MenalNV) for hematogenous metastatic cancer and their use for diagnosis, prognosis and predictive performance are disclosed.

Abstract: The present invention relates to an artificial-intelligence-based cancer diagnosis and cancer type prediction method, and, more particularly, to an artificial-intelligence-based cancer diagnosis and cancer type prediction method, which extracts nucleic acids from a biological sample to acquire sequence information, and thus generate vectorized data on the basis of aligned nucleic acid fragments, and then inputs same into a trained artificial intelligence model to analyze a calculated value. Compared with a conventional method, which uses a step of determining the number of chromosomes on the basis of a read count and utilizes each related value as a normalized value, the artificial-intelligence-based cancer diagnosis and cancer type prediction method according to the present invention generates vectorized data to perform an analysis using an AI algorithm, and thus is useful in that similar effects can be exhibited even when read coverage is low.

Abstract: A method for identifying a key module and a key node of a biomolecular complex network by fusing multiple methods on the basis of a topological structure of the biomolecular complex network which may be such as a protein-protein interaction network, a gene expression regulation network, a biological metabolism network, an epigenetic network, a phenotypic network or a signaling network, comprising the following main steps: according to the biomolecular network and a module division for the network, comprehensively and quantitatively identifying the key module and key node on the basis of the topological structure by various measuring methods from multi-angle.

Abstract: An analysis method of analyzing a nucleic acid sequence of a patient sample with a computer, may include: obtaining first nucleic acid sequence data derived from a tumor cell collected from a patient, and second nucleic acid sequence data derived from a non-tumor cell collected from the patient; detecting a somatic mutation based on the first nucleic acid sequence data; detecting a germline mutation based on the second nucleic acid sequence data; selecting a presentation form for information on the germline mutation among candidate forms; and creating an analysis report in the selected form.

Abstract: Disclosed herein is a method for predicting a patient response to a sodium ion channel blocker such as mexiletine when the patient has LQT syndrome or an arrhythmia. The method generally comprises determining a plurality of parameters associated with sodium ion channels; generating a model for patient response by using a partial least squared (PLS) regression analysis on said plurality of parameters; and using the model to predict the patient response if the patient is administered a sodium ion channel blocker such as mexiletine.

Abstract: Provided is a deep learning algorithm that analyzes fragments of biological sequences. The input for the deep learning algorithm is a biological sequence fragment of unknown origin and the output is the closest known biological genome that could share phenotypic properties with the biological species of unknown origin. The workflow thus has application for genomic classification, identification of mutations within known genomes, and the identification of the closest class for unknown species.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for determining a predicted structure of a protein that is specified by an amino acid sequence. In one aspect, a method comprises: obtaining a multiple sequence alignment for the protein; determining, from the multiple sequence alignment and for each pair of amino acids in the amino acid sequence of the protein, a respective initial embedding of the pair of amino acids; processing the initial embeddings of the pairs of amino acids using a pair embedding neural network comprising a plurality of self-attention neural network layers to generate a final embedding of each pair of amino acids; and determining the predicted structure of the protein based on the final embedding of each pair of amino acids.

Abstract: An approach is disclosed for activating cell-mediated herd immunity (CMHI) in a group of people. A scalable infrastructure is provided with one or more compliance protocol targets to facilitate activation of at least one of the four types of individual cell-mediated immunity (CMI): absolute humidity CMI, vitamin D CMI, gut microbiome CMI, and antiviral priming CMI, in the group of people. The activation is for at least one of: absolute humidity CMHI, vitamin D CMHI, gut microbiome CMHI, and antiviral priming CMHI in the group of people. The CMHI is achieved in the group of people when the compliance protocol targets are achieved.

Abstract: Processes to reveal biological attributes from nucleic acids are provided. In some instances, nucleic acids are used to develop frequency sequence signal maps, construct V-plots, and/or to train computational models. In some instances, trained computational models are used to predict features that reveal biological attributes.

Abstract: Methods and systems are provided herein to track an original biological deposit that is withdrawn from a public repository. In some aspects, the public repository may include the ATCC or any other public repository in which biological materials are deposited for access by the general public. These techniques may be used to identify a product or biological deposit from a third party that is derived from the original biological deposit.

Abstract: Embodiments of the present invention may provide automated techniques for signal analysis that may continuously provide up-to-date results that link EEG and behaviors that are important for daily activities. Such techniques may provide automation, objectivity, real-time monitoring and portability. In an embodiment of the present invention, a computer-implemented method for monitoring neural activity may comprise receiving data representing at least one signal representing neural activity of a test subject, pre-processing the received data by performing at least one of band-pass filtering, artifact removal, identifying common spatial patterns, and temporally segmentation, processing the pre-processed data by performing at least one of time domain processing, frequency domain processing, and time-frequency domain processing, generating a machine learning model using the processed data as a training dataset, and outputting a characterization of the neural activity based on the machine learning model.