A system and method that receive a distance matrix for multiple patients and a patient of interest, assign a radial distance value between the patient of interest and the other patients based on the distance matrix value for each of the multiple patients, generate an angular distance value between the multiple patients based at least in part on a measure of similarity between each patient, and minimize a cost function based at least in part on the angular distance value between each patient and each other patient. Minimizing the cost function may include calculating a patient contribution to the cost function for a plurality of angular distance values and selecting the angular distance value with the smallest patient contribution. The processor also may be configured to generate and display a radar plot based on the assigned radial distance value and generated angular distance value of each patient.

Disclosed are methods, systems, and articles of manufacture for performing a process on biological samples. An analysis of biological samples in multiple regions of interest in a microfluidic device and a timeline correlated with the analysis may be identified. One or more region-of-interest types for the multiple regions of interest may be determined; and multiple characteristics may be determined for the biological samples based at least in part upon the one or more region-of-interest types. Associated data that respectively correspond to the multiple regions of interest in a user interface for at least a portion of the biological samples in the user interface based at least in part upon the multiple identifiers and the timeline. A count of the biological samples in a region of interest may be determined based at least in part upon a class or type of data using a convolutional neural network (CNN).

Disclosed are methods, systems, and articles of manufacture for performing a process on biological samples. An analysis of biological samples in multiple regions of interest in a microfluidic device and a timeline correlated with the analysis may be identified. One or more region-of-interest types for the multiple regions of interest may be determined; and multiple characteristics may be determined for the biological samples based at least in part upon the one or more region-of-interest types. Associated data that respectively correspond to the multiple regions of interest in a user interface for at least a portion of the biological samples in the user interface based at least in part upon the multiple identifiers and the timeline. A count of the biological samples in a region of interest may be determined based at least in part upon a class or type of data using a convolutional neural network (CNN).

Methods, apparatus, and storage medium for determining a condition of a biostructure by a neural network based on quantitative imaging data (QID) corresponding to an image of the biostructure. The method includes obtaining specific quantitative imaging data (QID) corresponding to an image of a biostructure; determining a context spectrum selection from context spectrum including a range of selectable values by: applying the specific QID to an input layer of a context-spectrum neural network, wherein the context-spectrum neural network is trained, according to a combination of focal loss and dice loss, based on previous QID and constructed context spectrum data associated with the previous QID; mapping the context spectrum selection to the image to generate a context spectrum mask for the image; and determining a condition of the biostructure based on the context spectrum mask.

Methods, apparatus, and storage medium for determining a condition of a biostructure by a neural network based on quantitative imaging data (QID) corresponding to an image of the biostructure. The method includes obtaining specific quantitative imaging data (QID) corresponding to an image of a biostructure; determining a context spectrum selection from context spectrum including a range of selectable values by: applying the specific QID to an input layer of a context-spectrum neural network, wherein the context-spectrum neural network is trained, according to a combination of focal loss and dice loss, based on previous QID and constructed context spectrum data associated with the previous QID; mapping the context spectrum selection to the image to generate a context spectrum mask for the image; and determining a condition of the biostructure based on the context spectrum mask.

A method to select a protein target for therapeutic application includes accessing genomic information and protein-protein interaction (PPI) data, computing a thermodynamic measure for each protein node within the network of protein nodes, generating an energy landscape data corresponding to the network of protein nodes and the thermodynamic measure, generating a PPI subnetwork by applying a topological filtration to the energy landscape data of the PPI data, computing a first Betti number for the PPI subnetwork, sequentially removing a protein node(s) from the PPI subnetwork while replacing the previously removed node(s), computing a new Betti number for the PPI subnetwork with the protein node(s) removed, computing a change between the Betti numbers, and determining, based on the change between the Beti numbers, a most significant protein target within the PPI subnetwork.

A method to select a protein target for therapeutic application includes accessing genomic information and protein-protein interaction (PPI) data, computing a thermodynamic measure for each protein node within the network of protein nodes, generating an energy landscape data corresponding to the network of protein nodes and the thermodynamic measure, generating a PPI subnetwork by applying a topological filtration to the energy landscape data of the PPI data, computing a first Betti number for the PPI subnetwork, sequentially removing a protein node(s) from the PPI subnetwork while replacing the previously removed node(s), computing a new Betti number for the PPI subnetwork with the protein node(s) removed, computing a change between the Betti numbers, and determining, based on the change between the Beti numbers, a most significant protein target within the PPI subnetwork.

The invention relates to an in silico screening method to identify candidate excipients for reducing aggregation of a protein in a formulation. The method combines computational molecular modeling and molecular dynamics simulations to identify sites on a protein where non-specific self-interaction and interaction of different test excipients may occur, determine the relative binding energies of such interactions, and select one or more test excipients that meet specified interaction criteria for use as candidate excipients in empirical screening studies.

The invention relates to an in silico screening method to identify candidate excipients for reducing aggregation of a protein in a formulation. The method combines computational molecular modeling and molecular dynamics simulations to identify sites on a protein where non-specific self-interaction and interaction of different test excipients may occur, determine the relative binding energies of such interactions, and select one or more test excipients that meet specified interaction criteria for use as candidate excipients in empirical screening studies.

A method includes generating, by a processor system, a graph. The graph is based at least in part on a plurality of instances in which operational taxonomic units are identified as being represented within an environment. The method can also include determining, using the processor system, that at least one instance of the plurality of instances corresponds to a false-positive identification of an operational taxonomic unit. The determining is based on the properties of the graph. The method can also include reporting the determination.