An optimization apparatus includes a memory; and a processor coupled to the memory and the processor configured to: compute a local solution for a combinatorial optimization problem based on a first evaluation function representing the combinatorial optimization problem, select a state variable group targeted by partial problems from the plurality of state variables based on a first state variable whose value at the local solution is a predetermined value among the plurality of state variables included in the first evaluation function, a weight coefficient representing a magnitude of an interaction between the plurality of state variables held in a storage unit, and input selection region information, search a ground state for a second evaluation function representing the partial problems for the selected state variable group, and generate a whole solution by updating the local solution based on the partial solutions acquired by the ground state search.

The technology disclosed relates to determining pathogenicity of nucleotide variants. In particular, the technology disclosed relates to specifying a particular amino acid at a particular position in a protein as a gap amino acid, and specifying remaining amino acids at remaining positions in the protein as non-gap amino acids. The technology disclosed further relates to generating a gapped spatial representation of the protein that includes spatial configurations of the non-gap amino acids, and excludes a spatial configuration of the gap amino acid, and determining a pathogenicity of a nucleotide variant based at least in part on the gapped spatial representation, and a representation of an alternate amino acid created by the nucleotide variant at the particular position.

An artificial intelligence-enabled health ecosystem that leverages physiological data (captured, for example, by wearable health monitoring devices), medical history data (e.g., including biofluid data captured by biofluid analyzers), contextual information relevant to health outcomes, and genetic data (captured, for example, by genetic analyzers) to identify correlations in disparate health data, so that inferences can be drawn, health outcomes can be better anticipated and managed, and targeted drugs can be developed.

An attention-based graph architecture that exploits MSA Transformer embeddings to directly produce models of three-dimensional folded structures from protein sequences includes a method and system for augmenting the protein sequence to obtain multiple sequence alignments, producing enriched individual and pairwise embeddings from the multiple sequence alignments using an MSA-Transformer, extracting relevant features and structure latent states from the enriched individual and pairwise embeddings for use by a downstream graph transformer, assigning individual and pairwise embeddings to nodes and edges, respectively, using the downstream graph transformer to operate on node representations through an attention-based mechanism that considers pairwise edge attributes to obtain final node encodings, and projecting the final node encodings to form the computer-modeled folded protein structure. An induced distogram of the computer-modeled folded protein structure may be computed.

An attention-based graph architecture that exploits MSA Transformer embeddings to directly produce models of three-dimensional folded structures from protein sequences includes a method and system for augmenting the protein sequence to obtain multiple sequence alignments, producing enriched individual and pairwise embeddings from the multiple sequence alignments using an MSA-Transformer, extracting relevant features and structure latent states from the enriched individual and pairwise embeddings for use by a downstream graph transformer, assigning individual and pairwise embeddings to nodes and edges, respectively, using the downstream graph transformer to operate on node representations through an attention-based mechanism that considers pairwise edge attributes to obtain final node encodings, and projecting the final node encodings to form the computer-modeled folded protein structure. An induced distogram of the computer-modeled folded protein structure may be computed.

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.

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.

Embodiments of the invention include systems and methods that enable the identification of candidate proteins that have desired features of a target protein. An example method comprises receiving first and second input proteins. The method further comprises applying a first machine learning model to the first and second input proteins to generate corresponding fragments. The method further comprises applying a second machine learning model to the fragments, wherein applying the second machine learning model comprises generating an encoded representation in a multidimensional space for each of the fragments. The method also comprises generating a similarity score between the fragments from the first input and the second input. The method then comprises generating a hierarchical scale of similarity between the first and second inputs according to the similarity score and selecting candidate proteins based on the hierarchical scale.

Embodiments of the invention include systems and methods that enable the identification of candidate proteins that have desired features of a target protein. An example method comprises receiving first and second input proteins. The method further comprises applying a first machine learning model to the first and second input proteins to generate corresponding fragments. The method further comprises applying a second machine learning model to the fragments, wherein applying the second machine learning model comprises generating an encoded representation in a multidimensional space for each of the fragments. The method also comprises generating a similarity score between the fragments from the first input and the second input. The method then comprises generating a hierarchical scale of similarity between the first and second inputs according to the similarity score and selecting candidate proteins based on the hierarchical scale.

A method and system for generating a protein sequence is implemented using a computer-implemented neural network. An empty or partially filed sequence of node elements, representing amino acid positions of the protein sequence, and an edge index, having edge elements defining physical interaction between amino acid positions, are received. The computer-implemented neural network operates to determine enhanced edge attribute values for edge elements of the edge index and enhanced amino acid values for node elements of the sequence. Amino acid values are generated for elements of the partially filed sequence having missing values.