Using large-scale reinforcement learning to train a policy model that can be utilized by a robot in performing a robotic task in which the robot interacts with one or more environmental objects. In various implementations, off-policy deep reinforcement learning is used to train the policy model, and the off-policy deep reinforcement learning is based on self-supervised data collection. The policy model can be a neural network model. Implementations of the reinforcement learning utilized in training the neural network model utilize a continuous-action variant of Q-learning. Through techniques disclosed herein, implementations can learn policies that generalize effectively to previously unseen objects, previously unseen environments, etc.

Processes are provided for detecting loss of heterozygosity of Human Leukocyte Antigen (HLA) in a subject using analysis of next generation sequencing (NGS) data. The processes include aligning NGS data and identifying unmapped and mapped reads, updating reference data, and feeding one or more sequence reads to an HLA typing process for identifying candidate HLA alleles and feeding HLA type data to a loss of heterozygosity (LOH) modeling process for determining a LOH status for each HLA allele. A report may be generated of the LOH statuses for each of HLA allele.

A system, method and apparatus for executing a bioinformatics analysis on genetic sequence data includes an integrated circuit formed of a set of hardwired digital logic circuits that are interconnected by physical electrical interconnects. One of the physical electrical interconnects forms an input to the integrated circuit that may be connected with an electronic data source for receiving reads of genomic data. The hardwired digital logic circuits may be arranged as a set of processing engines, each processing engine being formed of a subset of the hardwired digital logic circuits to perform one or more steps in the bioinformatics analysis on the reads of genomic data. Each subset of the hardwired digital logic circuits may be formed in a wired configuration to perform the one or more steps in the bioinformatics analysis.

Embodiments discussed herein facilitate determination of risk of relapse of AML post-transplant. One example embodiment is a method, comprising: accessing a digital whole slide image (WSI) comprising a post-transplant bone marrow aspirate from a patient that has acute myeloid leukemia (AML); segmenting one or more myeloblasts on the digital WSI; extracting one or more features from the segmented one or more myeloblasts; providing the one or more features extracted from the segmented one or more myeloblasts to a trained machine learning model; and receiving, from the trained machine learning model, an indication of a risk of relapse of the AML.

A system and a method for measuring a road surface input load for a vehicle, may include a plurality of strain gauges mounted on a surface of a hub bearing in the vehicle; a storage connected to the plurality of strain gauges and configured to store a deep learning artificial neural network model which learns road surface input load data of the vehicle according to the pieces of output data of the plurality of strain gauges; and a processor connected to the storage and the plurality of strain gauges and configured to perform calculation which is performed in each layer of the deep learning artificial neural network model stored in the storage and derive the road surface input load data of the vehicle according to the pieces of output data of the plurality of strain gauges.

Partial differential equations used to simulate physical systems can be solved, in one embodiment, by a solver that has been trained with a set of generative neural networks that operated at different resolutions in a solution space of a domain that defines the physical space of the physical system. The solver can operate in a latent vector space which encodes solutions to the PDE in latent vectors in the latent vector space. The variables of the PDE can be partially decoupled in the latent vector space while the solver operates. The domain can be divided into subdomains that are classified based on their positions in the domain.

Disclosed are a system for predicting optical properties of molecules based on machine learning and a method thereof. More particularly, the system for predicting optical properties according to an embodiment includes a preprocessor that receives molecular information of a target molecule and surrounding molecules, and vectorizes the molecular information of a target molecule and surrounding molecules; a feature extractor that receives the vectorized information of the target molecule and surrounding molecules and extracts the features of the target molecule and surrounding molecules; an integrated feature extractor that receives both features of the target molecule and surrounding molecules and extract the integrated features of the target molecule and surrounding molecules by using an algorithm; and an optical property predictor that receives the integrated features of the target molecule and surrounding molecules and predicts optical properties of the target molecule affected by surrounding molecules.

The present invention relates to an electronic synaptic device and a method of manufacturing the same, and more specifically, to a human-friendly electronic synaptic device based on nanocomposites including a protein, and a method of manufacturing the same.

The invention provides, inter alia, recombinase-based systems that provide for integrated logic and memory in living cells such as mammalian cells. The nucleic acid cassettes, switches, and systems described herein allow for control of gene expression or gene regulation. The invention also provides nucleic acid-based switches for adopted T-cell therapy.

Provided are nucleic acid translators capable of carrying out logic operations with improved efficiency, maximized output and reduced off-target effects, in particular in a biological system. Methods of using these translators to transduce signal are also provided.