Abstract: Provided herein are methods for making, and epitope-targeted, conditionally-activated, pro-drug, antibody, comprising: complementarity determining regions (CDRs) from an antibody identified from an in vivo, in vitro, or in silico antibody library; one or more engineered epitope masks connected to a linker, wherein the linker comprises a peptide, a polymer, or a chemical-linker that is cleaveable in vivo at a target site by an enzyme or cleaved chemically, and wherein the one or more engineered epitope masks binds the epitope-specific antibody at the CDRs of the epitope-specific antibody; and wherein the one or more engineered epitope masks linked to the antibody via the linker, wherein the masks are conditionally bound to the CDRs of the epitope-specific antibody, and wherein cleavage of the linker releases the one or more engineered epitope masks from the antigen binding site.

Abstract: Provided herein are anti-Trop 2 antibodies or binding fragments thereof that bind Trop 2, e.g., human Trop 2. The anti-Trop 2 antibodies of the disclosure are useful for the treatment of proliferative disorders or cells that express Trop 2 or mutant Trop 2. Also provided herein are methods of use for the anti-Trop 2 antibodies or binding fragments thereof, as well as bi-valent or multi-valent anti-Trop 2 antibodies or binding fragments thereof that may form complexes that attract immune effectors or binding to other cells, such as, a second antibody, antigen-binding of the second antibody or fragment thereof; a target-binding protein, a cytokine; a lectin; or a toxin.

Abstract: Systems and methods for using machine learning to improve disease diagnostics are provided. A method can include obtaining, using a peptide array, peptide sequence data and peptide binding values from one or more samples, wherein the peptide sequence data and the peptide binding values correspond to a plurality of conditions; for each of the one or more samples, normalizing the peptide binding values according to a median binding value of peptides associated with the peptide array; and training a regressor using dense compact representations of the peptide sequence data and peptide binding values. The method can further include providing an output of the regressor to a classifier, wherein the classifier is configured to determine whether the patient has one of the plurality of conditions based on the output of the regressor.

Abstract: Provided herein are methods for design of engineered polypeptides that recapitulate molecular structure features of a predetermined portion of several reference protein structures, e.g., related antibody epitopes or protein binding sites. A Machine Learning (ML) model may be used to generate engineered polypeptides. After substituting target residues for corresponding residues in other reference structures in the same scaffold, the scaffolds with each set of target residues may be filtered by structural comparison to identify generalized scaffolds. Generalized scaffolds may be improved by screening libraries of polypeptides.

Abstract: Provided herein are methods for design of engineered polypeptides that recapitulate molecular structure features of a predetermined portion of a reference protein structure, e.g., an antibody epitope or a protein binding site. A Machine Learning (ML) model is trained by labeling blueprint records generated from a reference target structure with scores calculated based on computational protein modeling of polypeptide structures generated by the blueprint records. The method may include training an ML model based on a first set of blueprint records, or representations thereof, and a first set of scores, each blueprint record from the first set of blueprint records associated with each score from the first set of scores. After the training, the machine learning model may be executed to generate a second set of blueprint records. A set of engineered polypeptides are then generated based on the second set of blueprint records.

Abstract: Provided herein are methods for design of engineered polypeptides that recapitulate molecular structure features of a predetermined portion of a reference protein structure, e.g., an antibody epitope or a protein binding site. A Machine Learning (ML) model is trained by labeling blueprint records generated from a reference target structure with scores calculated based on computational protein modeling of polypeptide structures generated by the blueprint records. The method may include training an ML model based on a first set of blueprint records, or representations thereof, and a first set of scores, each blueprint record from the first set of blueprint records associated with each score from the first set of scores. After the training, the machine learning model may be executed to generate a second set of blueprint records. A set of engineered polypeptides are then generated based on the second set of blueprint records.

Abstract: Mechanisms for molecule design using machine learning include: forming a first training set for a neural network using, for each of a first plurality of known molecules, a plurality of input values that represent the structure of the known molecule and a plurality of functional property values for the known molecule; training the neural network using the first training set; proposing a first plurality of proposed molecules, and predicting first predicted functional property values of the first plurality of proposed molecules that have the desired function property values; causing the first plurality of proposed molecules to be synthesized to form a first plurality of synthesized molecules; receiving first measured functional property values of the first plurality of synthesized molecules; and adding data regarding the first plurality of synthesized molecules to the first training set to form a second training set and retrain the neural network using the second training set.

Abstract: Provided herein are methods for design of engineered polypeptides that recapitulate molecular structure features of a predetermined portion of a reference protein structure, e.g., an antibody epitope or a protein binding site. A Machine Learning (ML) model is trained by labeling blueprint records generated from a reference target structure with scores calculated based on computational protein modeling of polypeptide structures generated by the blueprint records. The method may include training an ML model based on a first set of blueprint records, or representations thereof, and a first set of scores, each blueprint record from the first set of blueprint records associated with each score from the first set of scores. After the training, the machine learning model may be executed to generate a second set of blueprint records. A set of engineered polypeptides are then generated based on the second set of blueprint records.

Abstract: Methods and systems for predicting functions of molecular sequences, comprising: generating an array that represents a sequence of molecules; determining a projection of the sequence of molecules, wherein the determining comprises multiplying a representation of the array that represents the sequence of the molecules by a first hidden layer matrix that represents a number of possible sequence dependent functions, wherein the first hidden layer matrix is determined during training of a neural network; and determining a function of the sequence of molecules by applying a plurality of weights to a representation of the projection of the sequence of molecules, wherein the plurality of weights is determined during the training of the neural network.