Abstract: The present invention provides a computer-implemented, machine learning method for generating safe text. A first portion of a trainable prompt is generated using negative influential features and positive influential features of a predicted condition. A second portion of the trainable prompt is trained to steer a pre-trained large language model (PLLM) to generate the safe text using at least the first portion of the trainable prompt. The method has applications including, but not limited to, use cases in medicine (e.g., digital medicine, personalized healthcare, AI-assisted drug or vaccine development, diagnosis or treatment, disease prediction, etc.), and cyber security.

Abstract: A computer-implemented, machine learning method for cross-cohort predictions from medical data. Patients of one or more source cohorts are mapped to a feature space of a target cohort based on constraints. Patient distributions of the one or more source cohorts and the target cohort are learned. The patient distributions of the one or more source cohorts are corrected for the target cohort. The method has applications including, but not limited to medical AI, drug development, medical diagnostics/applications and in healthcare, for example, to optimize predictions or support decision making.

Abstract: A computer-implemented, machine learning method for incorporating a new entity in a knowledge graph for optimizing or improving a target property includes detecting counterfactual causes in a causality graph that are to be modified to achieve the target property. The causality graph is connected to the knowledge graph by links representing semantic relations. The new entity is generated in the knowledge graph by embedding the new entity in a latent space of the knowledge graph relative to existing entities. A change of causes in the causality graph resulting from generating the new entity in the knowledge graph is simulated. The method can be applied, for example, to use cases in medical/healthcare, smart cities or smart agriculture, for example, to support decision making using Artificial Intelligence (AI).

Abstract: The present disclosure relates to RNAi agents, e.g., double stranded RNAi agents, able to inhibit patatin-like phospholipase domain-containing protein 3 (PNPLA3) gene expression. Also disclosed are pharmaceutical compositions that include PNPLA3 RNAi agents and methods of use thereof. The PNPLA3 RNAi agents disclosed herein may be conjugated to targeting ligands to facilitate the delivery to cells, including to hepatocytes. Delivery of the PNPLA3 RNAi agents in vivo provides for inhibition of PNPLA3 gene expression. The RNAi agents can be used in methods of treatment of PNPLA3-related diseases and disorders, including non-alcoholic fatty liver disease (NAFLD), non-alcoholic steatohepatitis (NASH), hepatic fibrosis, and alcoholic or non-alcoholic liver diseases, including cirrhosis.

Abstract: An allocation system includes a memory storing instructions, and a processor. The processor is configured to access the memory and execute the instructions to: obtain data that includes profiles of doctors and clinical initial information of a patient that arrives at a hospital; preprocess the obtained data, wherein preprocessing includes a text preprocessing pipeline and word embedding; allocate a doctor to the patient that arrives at the hospital by using a neural network, wherein the neural network is machine-learned by using graph data of clinical narratives composed by doctors about patients, historical profiles of the patients and the profiles of doctors; and output information indicating the allocated doctor.

Abstract: A machine-learning method to optimize resource allocation extracts human-interpretable (e.g., doctor-interpretable) entity profiles from a text-labeled data graph of a system having a plurality of entities. The data graph is associated with a smart hospital and includes nodes representing the entities and edges between the nodes representing links between the entities. The method includes: obtaining the data graph and extracting the human-interpretable entity profiles from a tensor that has been learned, using a neural network, to capture patterns among text associated with the edges between respective pairs of the nodes. The neural network layers of the neural network are constructed such that the edges are modeled as a function of the associated text and cluster representations of the respective pairs of the nodes.

Abstract: Described are RNAi agents, e.g., double stranded RNAi agents, for inhibiting patatin-like phospholipase domain-containing protein 3 (PNPLA3) gene expression. Also disclosed are pharmaceutical compositions that include PNPLA3 RNAi agents and methods of use thereof. The PNPLA3 RNAi agents disclosed herein may be conjugated to targeting ligands to facilitate the delivery to cells, including to hepatocytes. Delivery of the PNPLA3 RNAi agents in vivo provides for inhibition of PNPLA3 gene expression. The RNAi agents can be used in methods of treatment of PNPLA3-related diseases and disorders, including non-alcoholic fatty liver disease (NAFLD), nonalcoholic steatohepatitis (NASH), hepatic fibrosis, and alcoholic or non-alcoholic liver diseases, including cirrhosis.

Abstract: A molding method of a support rod that first passing a plurality of long fibers through a resin bath for impregnating with resin, then passing the plurality of long fibers impregnated with resin through a bundling hole of a position-constrained vertical plate on a machine to preliminarily form a bundle end; providing a coating layer on the machine, one end of the coating layer obliquely passes through a guiding portion on the position-constrained vertical plate to downwardly contact the bundle end; then placing the one end of the coating layer and the bundle end into a mold cavity of a mold at the same time to form a long rod body; and then cutting the long rod body into multi-segment support rods through a cutting process.

Abstract: A method for generating a self-explaining decision in an artificial intelligence (AI) system includes receiving or defining a graph for a task in the AI system, the graph including a plurality of nodes connected by edges. Message passing is performed among the nodes of the graph, wherein a discrete attention mechanism is implemented during the message passing, whereby features of each node are transformed into a discrete representation, which varies depending on which neighboring node a message is passed to. The self-explaining decision is generated for one of the nodes based on the message passing.

Abstract: A method for determining causes of network slice performance degradation in an open radio access network (O-RAN), the O-RAN being under Central Unit-Distributed Unit (CU-DU) functional split. In a setup phase, telemetries that contain multivariate observations of DUs are obtained, telemetry data is aggregated, high order features from correlations between multivariate observations across the DUs is extracted for a specific time slot, and a k-time slots ahead performance model is learned. In a detection phase, the performance model forecasts the network slice performance upon receiving new telemetries. If a performance degradation is forecasted, a set of performance models is sampled and impact scores based on gradients of telemetries are computed. The high order features using the sampled performance prediction models are extracted.

Abstract: Provided are a display panel, a method for driving a display panel, and a display device. The display panel includes first pixels. The first pixel includes first and second light-emitting elements, and first and second pixel circuits respectively electrically connected to first electrodes of the first and second light-emitting elements. First electrodes of the first and second light-emitting element are independent from each other. Second electrodes of the first and second light-emitting elements are electrically connected to each other. Light-emitting material layers of the first and second light-emitting elements are formed into one piece. When the display panel displays at least one frame of an image, data voltages received by the first pixel circuit and the second pixel circuit in a same first pixel are different from each other. Thus, an influence of hysteresis effect on brightness of the first pixel is reduced to improve the display effect.

Abstract: Described are RNAi agents, compositions that include RNAi agents, and methods for inhibition of a double homeobox 4 (DUX4) gene. The DUX4 RNAi agents and RNAi agent conjugates disclosed herein inhibit the expression of a DUX4 gene. Pharmaceutical compositions that include one or more DUX4 RNAi agents, optionally with one or more additional therapeutics, are also described. Delivery of the described DUX4 RNAi agents to skeletal muscle cells in vivo, provides for inhibition of DUX4 gene expression and a reduction in DUX4 levels, which can provide a therapeutic benefit to subjects, including human subjects, suffering from certain skeletal muscle-related diseases or disorders including Facioscapulohumeral Muscular Dystrophy (FSID).

Abstract: Described are RNAi agents, compositions that include RNAi agents, and methods for inhibition of a double homeobox 4 (DUX4) gene. The DUX4 RNAi agents and RNAi agent conjugates disclosed herein inhibit the expression of a DUX4 gene. Pharmaceutical compositions that include one or more DUX4 RNAi agents, optionally with one or more additional therapeutics, are also described. Delivery of the described DUX4 RNAi agents to skeletal muscle cells in vivo, provides for inhibition of DUX4 gene expression and a reduction in DUX4 levels, which can provide a therapeutic benefit to subjects, including human subjects, suffering from certain skeletal muscle-related diseases or disorders including Facioscapulohumeral Muscular Dystrophy (FSHD).

Abstract: A machine-learning method to optimize resource allocation extracts human-interpretable (e.g., doctor-interpretable) entity profiles from a text-labeled data graph of a system having a plurality of entities. The data graph is associated with a smart hospital and includes nodes representing the entities and edges between the nodes representing links between the entities. The method includes: obtaining the data graph and extracting the human-interpretable entity profiles from a tensor that has been learned, using a neural network, to capture patterns among text associated with the edges between respective pairs of the nodes. The neural network layers of the neural network are constructed such that the edges are modeled as a function of the associated text and cluster representations of the respective pairs of the nodes.

Abstract: Described are RNAi agents, compositions that include RNAi agents, and methods for inhibition of a double homeobox 4 (DUX4) gene. The DUX4 RNAi agents and RNAi agent conjugates disclosed herein inhibit the expression of a DUX4 gene. Pharmaceutical compositions that include one or more DUX4 RNAi agents, optionally with one or more additional therapeutics, are also described. Delivery of the described DUX4 RNAi agents to skeletal muscle cells in vivo, provides for inhibition of DUX4 gene expression and a reduction in DUX4 levels, which can provide a therapeutic benefit to subjects, including human subjects, suffering from certain skeletal muscle-related diseases or disorders including Facioscapulohumeral Muscular Dystrophy (FSHD).

Abstract: A method extracts human-interpretable entity profiles from a text-labeled data graph of a system having a plurality of entities. The data graph includes nodes representing the entities and edges between the nodes representing links between the entities. A plurality of text is respectively associated with the corresponding edges. The method includes: constructing neural network layers configured such that each of the edges between a pair of the nodes is modeled as a function of the associated text and cluster representations of the pair of the nodes; for each one of the pair of nodes, performing machine learning to learn a tensor to capture patterns among the associated text and the pair of nodes, and extracting the entity profiles from the tensor.

Abstract: A method provides a trustworthy artificial intelligence graph-based solution for configuring a plurality of systems in a network. The method includes generating a graph in which each node in the graph represents one of the plurality of systems, wherein links are created between the nodes in the graph, and passing messages along the links. Each node passes a message and a level of uncertainty in the message to neighboring nodes of each node, and receives subsequent messages and subsequent levels of uncertainty in the subsequent messages from the neighboring nodes. The method also includes updating, by each node based on the subsequent messages and the subsequent levels of uncertainty in the subsequent messages received from the neighboring nodes, the respective message and the respective level of uncertainty in the respective message, and predicting configuration values for the systems based on the updated messages and the updated levels of uncertainty.

Abstract: An image processing method includes analyzing multiple images data based on Illumination-invariant Feature Network (IF-NET) with an image processing device to generate corresponding sets of eigenvector, in which image data includes a first image data related to at least one first feature of the sets of eigenvector, and a second image data related to at least one second feature of the sets of eigenvector; choosing a corresponding first training set of tiles and second training set of tiles from the first image data and second image data with an image processing device based on IF-NET, and computing on both training set of tiles to generate a least one loss value; and adjusting IF-NET based on a least one loss value. An image processing system is also disclosed herein.

Abstract: Provided are a chimeric antigen receptor, a construction method therefor and an application thereof. The chimeric antigen receptor consists of an antigen binding domain, an extracellular hinge region, a transmembrane domain, a co-stimulatory domain and a CD3z signaling domain. Further provided is a CAR-T cell which comprises two chimeric antigen receptors containing different antigen binding domains, and which is bispecific and exhibits increased cell killing efficiency and a better tumor inhibitory effect in vivo.

Abstract: The present disclosure relates to RNAi agents, e.g., double stranded RNAi agents, able to inhibit xanthine dehydrogenase (XDH) gene expression. Also disclosed are pharmaceutical compositions that include XDH RNAi agents and methods of use thereof. The XDH RNAi agents disclosed herein may be conjugated to targeting ligands to facilitate the delivery to cells, including to hepatocytes. Delivery of the XDH RNAi agents in vivo provides for inhibition of XDH gene expression. The RNAi agents can be used in methods of treatment of diseases, disorders, or symptoms mediated in part by XDH gene expression, such as gout and hyperuricemia.