Abstract: In some embodiments, tissue microarray (TMA) core images are used to train a deep learning network that can then be deployed to computer inferences regarding whole tissue section (WTS) images (WSIs). Preprocessing aligns paired serial core images from differently stained core sections with their associated metadata and H-scores (or other label data obtained from evaluating one of the paired core sections). In some embodiment, a self-supervised learning (SSL) pre-trained encoder is used to generate patch-level embeddings from TMA core images associated with corresponding labels that are then used to train an attention-based deep learning network to generate inferences. These and other aspects of the present disclosure are more fully detailed herein.

Abstract: A computer-implemented method of estimating a risk associated with patient safety is disclosed. One or more computers execute processing comprising receiving a training data set comprising drug-associated patient safety data and human omics data. One or more probabilistic features from the training data set are identified, where the one or more probabilistic features comprise human omics features associated with a drug therapeutic. A ground truth label associated with the drug therapeutic and comprising a positive or a negative patient safety outcome corresponding to the one or more probabilistic features is derived. The method trains one or more machine learning models in accordance with the ground truth label and applies the trained machine learning models to a patient dataset of human omics data to generate a calculated indication of a positive or a negative patient safety outcome. The method takes one or more actions in response to the calculated indication.

Abstract: Computerized systems and methods for digital histopathology analysis are disclosed. In one embodiment, a series of deep learning networks are used that train, in succession, on datasets of successively increasing relevance. In some examples, learned parameters from at least a portion of one deep learning network are transferred to a next deep learning network in a succession of deep learning networks. In some examples, at least one of the deep learning networks includes a self-supervised learning network. In some examples, at least one of the deep learning networks includes an attention-based learning network. These and other examples and details are disclosed herein in various contexts including, for example evaluating genotypes of cancer tissue (e.g., bladder, prostate, or lung cancer) using histopathology images. In some examples, the context is to assist in predicting presence or absence of certain cancer genotypes and/or predicting patient responses to a new treatment.

Abstract: Disclosed herein are methods for training and deploying a predictive model for generating a prediction, e.g., patient eligibility for a CAR-T therapy. Datasets, such as open healthcare claims datasets, may be missing data. Missing data may hamper the ability to generate sufficient information needed for training a predictive model. Methods include leveraging comprehensive datasets, such as closed claims datasets, to create training examples for input into a machine learning algorithm. In various embodiments, the comprehensive dataset is modified to simulate the data missingness in the target dataset; then, the modified dataset is paired with the ground truth label derived from the comprehensive dataset to create training examples. In various embodiments, a comprehensive dataset is paired with a target dataset to create training examples. After training a predictive model on such examples, the model can be deployed to make predictions in the target dataset even in light of missing data.

Abstract: Disclosed herein are methods for training and deploying a predictive model for generating a prediction, e.g., patient eligibility for a CAR-T therapy. Datasets, such as open healthcare claims datasets, may be missing data. Missing data may hamper the ability to generate sufficient information needed for training a predictive model. Methods include leveraging comprehensive datasets, such as closed claims datasets, to create training examples for input into a machine learning algorithm. In various embodiments, the comprehensive dataset is modified to simulate the data missingness in the target dataset; then, the modified dataset is paired with the ground truth label derived from the comprehensive dataset to create training examples. In various embodiments, a comprehensive dataset is paired with a target dataset to create training examples. After training a predictive model on such examples, the model can be deployed to make predictions in the target dataset even in light of missing data.

Abstract: The present disclosure relates to a process for manufacturing an oral pharmaceutical dosage form including: mixing an active pharmaceutical ingredient (API) and surfactant into a blend; feeding the blend into a processor that applies heat and shear forces at a temperature within a range of approximately equal to the melting point of the surfactant to 3° C. below the melting point of the surfactant so as to form API granulates; and formulating the API granulates into a dosage form. The disclosed technology provides a surprisingly effective and economical means for producing high dose solid dosage forms containing poorly soluble APIs with minimal excipient burden.

Abstract: A deep learning pipeline can be configured to use medical image data to generate predictions of therapeutic responses to a new treatment in members of a cohort of interest of treatment candidates. A plurality of respective deep learning networks may be trained using respective medical image datasets having respective degrees of relevance to the cohort of interest. Learned parameters of one deep learning network may be transferred in succession to another deep learning network after training the one deep learning network with a one of the respective medical image datasets and before training the other deep learning network with another medical image dataset of the respective medical image datasets.

Abstract: Disclosed herein are methods for training and deploying a predictive model for generating a prediction, e.g., patient eligibility for a CAR-T therapy. Datasets, such as open healthcare claims datasets, may be missing data. Missing data may hamper the ability to generate sufficient information needed for training a predictive model. Methods include leveraging comprehensive datasets, such as closed claims datasets, to create training examples for input into a machine learning algorithm. In various embodiments, the comprehensive dataset is modified to simulate the data missingness in the target dataset; then, the modified dataset is paired with the ground truth label derived from the comprehensive dataset to create training examples. In various embodiments, a comprehensive dataset is paired with a target dataset to create training examples. After training a predictive model on such examples, the model can be deployed to make predictions in the target dataset even in light of missing data.

Abstract: A method for identifying a compound which modulates the activity of acyl-coA: diacylglycerol acyltransferase comprises the steps of contacting a stable isotope labeled fatty acid with cells in either presence or absence of the compound, extracting the cells with isopropyl alcohol, and determining the level of a stable isotope labeled triglyceride in the presence or absence of the compound; wherein a change in the level of the stable isotope labeled triglyceride indicates that the compound modulates the DGAT activity.

Abstract: A method of screening a compound which modulates dipeptidyl peptidase I (DPPI) activities comprises the steps of adding a peptide substrate of DPPI to a reaction mixture which comprises DPPI and a compound, wherein the peptide substrate of DPPI has at least 3 amino acids and binds to a binding site of DPPI in addition to the S1-S2 site; and measuring the molecular weight of the substrate, wherein a change in the molecular weight of the substrate is indicative of the presence of DPPI activity.