Abstract: Provided herein are immunogenic compositions comprising tumor-specific neoantigen long peptides, tumor-specific neoantigen short peptides, and adjuvant, optionally a helper peptide, and optionally a tumor-specific peptide. The disclosure also provides methods of using these immunogenic compositions for treating cancer.

Abstract: Disclosed herein is a method, comprising administering to a subject in need thereof an initial immunogenic composition comprising a plurality of tumor-specific neoantigens, each corresponding to a member of a first set of tumor-associated mutations in a subject, and none corresponding to a member of a second set of tumor-associated mutations in the subject; and quantifying each member of the first set of tumor-associated mutations and each member of the second set of tumor-associated mutations in circulating material comprising tumor-associated mutations isolated from the subject at each of multiple time points.

Abstract: Disclosed herein are methods for evaluating the efficacy of an immunogenic composition by monitoring circulating tumor DNA. The disclosure also relates to methods for treating a subject having cancer.

Abstract: Techniques are described and relate to anisotropic pooling for contextual embedding of a protein sequence. In an example, a system receives a first biological sequence and determines a sequence arrangement that comprises a component of the first biological sequence and a second biological sequence of components. By using an artificial intelligence (AI) model, the system determines a third sequence that comprises a contextual embedding vector corresponding to the component of the first biological sequence. The AI model generates the third sequence based at least in part on the sequence arrangement and by at least using a convolution and anisotropic pooling.

Abstract: Techniques for automated alignment of image capture of physical ailments are described. A method of automated alignment of image capture of physical ailments includes determining an alignment class of a first image of an object using an alignment classifier executing on a user device, providing alignment instructions based on the alignment class and a reference image associated with the object using at least one machine learning model executing on the user device, obtaining an aligned image of the object after the user device has been repositioned relative to the object based on the alignment instructions, and sending the aligned image to an agent device via a telemedicine service of a provider network.

Abstract: Disclosed herein are methods for selecting tumor-specific neoantigens from a tumor of a subject that are suitable for subject-specific immunogenic compositions.

Abstract: Techniques for predicting a pair of an enzyme primary sequence and a substrate, and interaction probability for the pair are described. An exemplary method includes receiving a request to predict a pair of an enzyme primary sequence and a substrate, and interaction probability for the pair; combining an enzyme vector, a substrate vector, and an interaction indication for the enzyme and substrate to form a machine learning model input; applying a machine learning model to the machine learning model input to predict the pair of an enzyme primary sequence and a substrate, and interaction probability for the pair; and outputting a result of the application of the machine learning model including the predicted pair of an enzyme primary sequence and a substrate, and interaction probability for the pair.

Abstract: Techniques for predicting a protein sequence are described. An exemplary method includes receiving a request to predict a missing area of a protein's primary sequence and a corresponding three-dimensional position of the missing area; applying a machine learning model to backbone Cartesian coordinates of the protein's primary sequence and a protein vector of a representation of the protein's primary sequence including the missing area to predict a missing area of the protein primary sequence and a corresponding three-dimensional position for the missing area, wherein the machine learning model is selected from the group consisting of: an attention-based machine learning model, a bidirectional long short term memory-based model, and a convolutional neural network-based model; and outputting a result of the machine learning model.

Abstract: Provided herein are immunogenic compositions comprising tumor-specific neoantigen long peptides, tumor-specific neoantigen short peptides, and adjuvant, optionally a helper peptide, and optionally a tumor-specific peptide. The disclosure also provides methods of using these immunogenic compositions for treating cancer.

Abstract: Disclosed herein are methods for ranking tumor-specific neoantigens from a tumor of a subject that are suitable for subject-specific immunogenic compositions. Suitable tumor-specific neoantigens are tumor-specific neoantigens that are likely presented on the cell surface of the tumor, are likely to be immunogenic, are predicted to be expressed in sufficient amounts to elicit an immune response in the subject, optionally represent sufficient diversity across the tumor, and have relatively high manufacture feasibility. The present methods take a set of neoantigens (peptide vaccine candidates) and ranks the neoantigens in a way such that a group of top-ranked neoantigens simultaneously promotes cell-surface presentation of important neoantigens for Class I and Class II MHC molecules. The top-ranked neoantigens can then be further narrowed according manufacturability and/or other criteria.

Abstract: A thermoplastic polyurethane resin composition comprising: a thermoplastic polyurethane resin; an ultraviolet absorber package comprising a benzotriazole compound (UVA1), and a triazine compound (UVA2) wherein the mass ratio of UVA1 to UVA2 is from 1:1 to 3:1; optionally, a hindered amine light stabilizer and/or an antioxidant compound; and wherein the thermoplastic polyurethane resin composition has a maximum ultraviolet transmittance of ?3% in the wavelengths between 280 nm and 365 nm and an ultraviolet transmittance of ?6% in the wavelengths between 365 nm and 370 nm when the thermoplastic polyurethane resin is formed into a film having a thickness of 6 mils and wherein the cumulative weight % of UVA1 and UVA2 in the polyurethane resin composition ranges from 0.5 wt % to 0.85 wt % based on the total weight of the polyurethane resin composition.

Abstract: Techniques for automated alignment of image capture of physical ailments are described. A method of automated alignment of image capture of physical ailments includes determining an alignment class of a first image of an object using an alignment classifier executing on a user device, providing alignment instructions based on the alignment class and a reference image associated with the object using at least one machine learning model executing on the user device, obtaining an aligned image of the object after the user device has been repositioned relative to the object based on the alignment instructions, and sending the aligned image to an agent device via a telemedicine service of a provider network.

Abstract: Techniques are described and relate to assigning peptides to peptide groups for vaccine development. In an example, a peptide property of a peptide is determined, where this peptide is from different peptides that are to be assigned to different groups of vaccine. A determination is also made that the peptide is to be assigned to a first group from the different groups based at least in part on the peptide property. The first group has a first group property that is based at least in part on peptide properties of first peptides to be assigned to the first group. The first group property is within a similarity range relative to a second group property of a second group from the different groups. Information is generated and indicates that the peptide is assigned to the first group.

Abstract: Devices, systems, and methods are provided for audio and video capture and presentation. A method may include receiving, by a first device, images of a user, identifying, in a first image of the images, a first expression of the user, and identifying, in a second image of the images, a second expression of the user. The method may include determining that the first expression is associated with a first phoneme and that the second expression is associated with a second phoneme. The method may include generating audio including the first phoneme and the second phoneme, and sending the audio to a second device for presentation.