Systems and techniques are described to generate amino acid sequences of target proteins based on amino acid sequences of template proteins using machine learning techniques. The amino acid sequences of the target proteins can be generated based on data that constrains the modifications that can be made to the amino acid sequences of the template proteins. In illustrative examples, the template proteins can include antibodies produced by a non-human mammal that bind to an antigen and the target proteins can correspond to human antibodies with a region having at least a threshold amount of identity with the binding region of the template antibody. Generative adversarial networks can be used to produce the amino acid sequences of the target proteins.

The present invention provides compositions and methods that can be used to identify an antigen or epitope region of an antigen specific for a disease or other condition. Such methods incorporate k-mer binding statistics to serum antibody from condition and control cohort samples to predict the suitability of antigen sequences identified as relevant to the disease or condition as antigen markers. Also disclosed herein are systems for performing the same.

The present invention provides compositions and methods that can be used to identify an antigen or epitope region of an antigen specific for a disease or other condition. Such methods incorporate k-mer binding statistics to serum antibody from condition and control cohort samples to predict the suitability of antigen sequences identified as relevant to the disease or condition as antigen markers. Also disclosed herein are systems for performing the same.

Disclosed are a method and a device for constructing an antibody complementarity determining region (CDR) library. Also disclosed are a method, a device and a computer program product for determining the occurrence frequency of member sequences of an antibody CDR library, by means of which an antibody CDR library with a specific amino acid distribution at one or more positions can be obtained.

Disclosed are a method and a device for constructing an antibody complementarity determining region (CDR) library. Also disclosed are a method, a device and a computer program product for determining the occurrence frequency of member sequences of an antibody CDR library, by means of which an antibody CDR library with a specific amino acid distribution at one or more positions can be obtained.

The present invention relates to a method of characterizing the binding characteristics between a peptide of interest and MHC molecules of a given cell type, the method comprising the steps of: (i) Providing two or more cells characterized by displaying, on their surface, MHC molecules, (ii) dispensing the two or more cells in two or more vessels, so that each vessel comprises one or more cells, (iii) adding, to the different vessels, different variants of a peptide of interest, wherein the variants of said peptide are labeled and have the same amino acid sequence, yet differ from one another in the type of labeling and their concentration, and exposing the cells thereto so as to form, in the different vessels, peptide-MHC complexes on the surface of the cells, (iv) isolating the thus formed peptide-MHC complexes and (v) determining the concentration of the different peptide-MHC complexes formed (FIG. 1).

The present invention relates to a method of characterizing the binding characteristics between a peptide of interest and MHC molecules of a given cell type, the method comprising the steps of: (i) Providing two or more cells characterized by displaying, on their surface, MHC molecules, (ii) dispensing the two or more cells in two or more vessels, so that each vessel comprises one or more cells, (iii) adding, to the different vessels, different variants of a peptide of interest, wherein the variants of said peptide are labeled and have the same amino acid sequence, yet differ from one another in the type of labeling and their concentration, and exposing the cells thereto so as to form, in the different vessels, peptide-MHC complexes on the surface of the cells, (iv) isolating the thus formed peptide-MHC complexes and (v) determining the concentration of the different peptide-MHC complexes formed (FIG. 1).

Aspects of the present disclosure relate to computing systems and computational methods for docking a library of compounds against a massive amount of conformations of a protein of interest.

Aspects of the present disclosure relate to computing systems and computational methods for docking a library of compounds against a massive amount of conformations of a protein of interest.

The present disclosure provides compositions and methods for the generation of an antibody or immunogenic composition, such as a vaccine, through epitope focusing by variable effective antigen surface concentration. Generally, the composition and methods of the disclosure comprise three steps: a “design process” comprising one or more in silico bioinformatics steps to select and generate a library of potential antigens for use in the immunogenic composition; a “formulation process”, comprising in vitro testing of potential antigens, using various biochemical assays, and further combining two or more antigens to generate one or more immunogenic compositions; and an “administering” step, whereby the immunogenic composition is administered to a host animal, immune cell, subject or patient. Further steps may also be included, such as the isolation and production of antibodies raised by host immune response to the immunogenic composition.