Abstract: Disclosed systems and methods obtain a graph of a polymer comprising nodes and edges, the nodes representing polymer atoms, the edges encoding distances and relative orientations between corresponding pairs of nodes and whether pairs of nodes are covalently bound. Each subgraph in a plurality of first partial-context subgraphs of the graph is sequentially inputted into a first model to calculate first side chain dihedral angles for polymer residues. This updates the graph through first side chain dihedral angles. Each second subgraph in a plurality of second partial-context subgraphs of the updated graph is inputted into a second model, thereby obtaining calculated second side chain dihedral angles for polymer residues that serve to update the graph through second side chain dihedral angles. The graph is again updated with updated side chain dihedral angle values obtained by sequentially inputting full-context subgraphs, each such subgraph representing a different residue, into a full-context model.

Abstract: Systems and methods for polymer sequence prediction are provided. Atomic coordinates for at least the main chain atoms of a polypeptide comprising a plurality of residues is obtained and used to encode the residues into residue feature sets. Each residue feature set comprises, for the respective residue and for each neighboring residue within a nearest neighbor cutoff, an indication of secondary structure, a relative solvent accessible surface area of backbone atoms, and cosine and sine values of backbone dihedrals; a C? to C? distance of each neighboring residue; and an orientation and position of each neighboring residue backbone relative to the backbone residue segment of the respective residue. A residue in the plurality of residues is identified, and the corresponding residue feature set is inputted into a neural network comprising at least 500 parameters, thus obtaining a plurality of probabilities, including a probability for each naturally occurring amino acid.

Abstract: Systems and methods for evaluating thermodynamics of atomic changes in a polymer include using a first portion of a refined derived set of three-dimensional coordinates for a derivation of the polymer, which incorporates the atomic change under study, to compute a first effective atomistic Hessian. A second effective atomistic Hessian is computed using a second portion of a refined native set of three-dimensional coordinates for the native polymer. Atoms in the first and second portions are identical. A thermodynamic property of the first portion is determined using the refined derived set of three-dimensional coordinates and the first effective atomistic Hessian. A thermodynamic property of the second portion of the native polymer is determined using the refined native set of three-dimensional coordinates and the second effective atomistic Hessian. The effect of the atomic changes is quantified by taking the difference between the calculated thermodynamic properties of the first and second portions.

Abstract: Systems and methods for evaluating thermodynamics of atomic changes in a polymer include using a first portion of a refined derived set of three-dimensional coordinates for a derivation of the polymer, which incorporates the atomic change under study, to compute a first effective atomistic Hessian. A second effective atomistic Hessian is computed using a second portion of a refined native set of three-dimensional coordinates for the native polymer. Atoms in the first and second portions are identical. A thermodynamic property of the first portion is determined using the refined derived set of three-dimensional coordinates and the first effective atomistic Hessian. A thermodynamic property of the second portion of the native polymer is determined using the refined native set of three-dimensional coordinates and the second effective atomistic Hessian. The effect of the atomic changes is quantified by taking the difference between the calculated thermodynamic properties of the first and second portions.