Abstract: The proposed model is a Variational Autoencoder having a learnable prior that is parametrized with a Tensor Train (VAE-TTLP). The VAE-TTLP can be used to generate new objects, such as molecules, that have specific properties and that can have specific biological activity (when a molecule). The VAE-TTLP can be trained in a way with the Tensor Train so that the provided data may omit one or more properties of the object, and still result in an object with a desired property.

Abstract: A method is provided for generating new objects having given properties, such as a specific bioactivity (e.g., binding with a specific protein). In some aspects, the method can include: (a) receiving objects (e.g., physical structures) and their properties (e.g., chemical properties, bioactivity properties, etc.) from a dataset; (b) providing the objects and their properties to a machine learning platform, wherein the machine learning platform outputs a trained model; and (c) the machine learning platform takes the trained model and a set of properties and outputs new objects with desired properties. The new objects are different from the received objects. In some aspects, the objects are molecular structures, such as potential active agents, such as small molecule drugs, biological agents, nucleic acids, proteins, antibodies, or other active agents with a desired or defined bioactivity (e.g., binding a specific protein, preferentially over other proteins).

Abstract: The proposed model is a Variational Autoencoder having a learnable prior that is parametrized with a Tensor Train (VAE-TTLP). The VAE-TTLP can be used to generate new objects, such as molecules, that have specific properties and that can have specific biological activity (when a molecule). The VAE-TTLP can be trained in a way with the Tensor Train so that the provided data may omit one or more properties of the object, and still result in an object with a desired property.

Abstract: A method is provided for generating new objects having given properties, such as a specific bioactivity (e.g., binding with a specific protein). In some aspects, the method can include: (a) receiving objects (e.g., physical structures) and their properties (e.g., chemical properties, bioactivity properties, etc.) from a dataset; (b) providing the objects and their properties to a machine learning platform, wherein the machine learning platform outputs a trained model; and (c) the machine learning platform takes the trained model and a set of properties and outputs new objects with desired properties. The new objects are different from the received objects. In some aspects, the objects are molecular structures, such as potential active agents, such as small molecule drugs, biological agents, nucleic acids, proteins, antibodies, or other active agents with a desired or defined bioactivity (e.g., binding a specific protein, preferentially over other proteins).

Abstract: The proposed model is a Variational Autoencoder having a learnable prior that is parametrized with a Tensor Train (VAE-TTLP). The VAE-TTLP can be used to generate new objects, such as molecules, that have specific properties and that can have specific biological activity (when a molecule). The VAE-TTLP can be trained in a way with the Tensor Train so that the provided data may omit one or more properties of the object, and still result in an object with a desired property.

Abstract: A computer-implemented method for a generative adversarial approach for conformational space modeling of molecules is provided. The method can include obtaining molecule graph data for a molecule and inputting the molecule graph data into a machine learning platform. The machine learning platform can include architecture of a molecular graph generator, conformation discriminator, stochastic encoder, and latent variables discriminator. The method can include generating a plurality of conformations for the molecule with the machine learning platform. The plurality of conformations are specific to the molecule. Each conformation can have internal coordinates defining positions of atoms of the molecule. At least one conformation for the molecule can be selected based on at least one parameter related to molecular conformations. A report can be prepared that includes the selected at least one conformation for the molecule.

Abstract: A method for generating an object includes: providing a dataset having object data and condition data; processing the object data to obtain latent object data and latent object-condition data; processing the condition data to obtain latent condition data and latent condition-object data; processing the latent object data and the latent object-condition data to obtain generated object data; processing the latent condition data and latent condition-object data to obtain generated condition data; comparing the latent object-condition data to the latent condition-object data to determine a difference; processing the latent object data and latent condition data and one of the latent object-condition data or latent condition-object data to obtain a discriminator value; and selecting a selected object based on the generated object data.

Abstract: Creating synthetic biological data for a subject can include: (a) receiving a real biological data signature derived from a biological sample of the subject; (b) creating input vectors based on the real biological data signature; (c) inputting the input vectors into a machine learning platform; (d) generating a predicted biological data signature of the subject based on the input vectors, wherein the predicted biological data signature includes synthetic biological data specific to the subject; and (e) preparing a report that includes the synthetic biological data of the subject. Biological pathway activation signatures can be genomics, transcriptomics, proteomics, metabolomics, lipidomics, glycomics, methylomics, or secretomics. Conditioning latent codes of the input vectors in a latent space of the machine learning platform with at least one constraint of an attribute of the subject is performed so the predicted biological data signature is based on the at least one constraint.

Abstract: A DDR1 inhibitor compound can have a structure of Formula A, derivative thereof, prodrug thereof, salt thereof, stereoisomer thereof, tautomer thereof, polymorph thereof, or solvate thereof, or having any chirality at any chiral center, ring A is a ring structure; ring B is a ring structure; the X1, X2, X3, X4, and X5 are each independently a carbon or a hetero atom with or without a substituent; the Y is a linker; and each R1, R2, R3, R5, and R6 is independently a substituent; and each n is an integer, such as from 0 to the maximum number of allowed substituents on the linker or ring, wherein R5 and/or R6 is optionally nothing.

Abstract: A method for generating an object includes: providing a dataset having object data and condition data; processing the object data to obtain latent object data and latent object-condition data; processing the condition data to obtain latent condition data and latent condition-object data; processing the latent object data and the latent object-condition data to obtain generated object data; processing the latent condition data and latent condition-object data to obtain generated condition data; comparing the latent object-condition data to the latent condition-object data to determine a difference; processing the latent object data and latent condition data and one of the latent object-condition data or latent condition-object data to obtain a discriminator value; and selecting a selected object based on the generated object data.

Abstract: A computing method for normalizing molecule graph data for hierarchical molecular generation can include: providing molecule graph data of a molecule having a node; recursively splitting the node into two nodes; iteratively recursively spilling other nodes into two nodes; generating generated molecular graph data of a generated molecule from node splitting; and providing a report with the generated molecular graph. A computing method can include: providing molecule graph data into a latent code generator having multiple levels with a forward and inverse; and generating latent codes by processing molecule graph data through multiple levels of operations, wherein each level of operations has a sequence of sublevels of operations in forward path and inverse path, wherein the sublevels of operations include node merging operation and node splitting operation; generating at least one molecular structure from latent codes; and outputting generate molecule graph data having the at least one molecular structure.

Abstract: A model of a deterministic decoder VAE (DD-VAE) is provided. The DD-VAE has evidence lower bound derived, and a convenient approximation can be proposed with proven convergence to optimal parameters of a non-relaxed objective. The invention introduces bounded support distributions as a solution thereto. Experiments on multiple datasets (synthetic, MNIST, MOSES, ZINC) are performed to show that DD-VAE yields both a proper generative distribution and useful latent codes.

Abstract: A scaffold-oriented line notation can include: a scaffold sequence of atom identifiers of a scaffold, the scaffold sequence includes at least one decoration marker or any number of decoration markers, each decoration marker being adjacent to an atom identifier of a linking atom of the scaffold; a decoration separator following a last atom identifier or a last decoration marker of the scaffold sequence; at least one decoration having at least one atom identifier in a line notation that defines a chemical structure of the chemical moiety of the decoration that is attached to the linking atom of the scaffold of the molecule; in the scaffold sequence, an order of the at least one decoration marker defines an order of the at least one decoration; in the at least one decoration, the first decoration follows the first decoration separator.

Abstract: A computer-implemented method can include: receiving input of a biological target; receiving a generative model (e.g., tensorial reinforcement learning (GENTRL) model or other model) trained with reference compounds, wherein the reference compounds include: general compounds, compounds that modulate the biological target, and compounds that modulate biomolecules other than the biological target; generating structures of generated compounds with the generative model; prioritizing structures of generated compounds based on at least one criteria; processing prioritized chemical structures of the generated compounds through a Sammon mapping protocol to obtain hit structures; and providing chemical structures of the hit structures.

Abstract: A DDR1 inhibitor compound can have a structure of Formula A, derivative thereof, prodrug thereof, salt thereof, stereoisomer thereof, tautomer thereof, polymorph thereof, or solvate thereof, or having any chirality at any chiral center, ring A is a ring structure; ring B is a ring structure; the X1, X2, X3, X4, and X5 are each independently a carbon or a hetero atom with or without a substituent; the Y is a linker; and each R1, R2, R3, R5, and R6 is independently a substituent; and each n is an integer, such as from 0 to the maximum number of allowed substituents on the linker or ring, wherein R5 and/or R6 is optionally nothing.

Abstract: The proposed model is a Variational Autoencoder having a learnable prior that is parametrized with a Tensor Train (VAE-TTLP). The VAE-TTLP can be used to generate new objects, such as molecules, that have specific properties and that can have specific biological activity (when a molecule). The VAE-TTLP can be trained in a way with the Tensor Train so that the provided data may omit one or more properties of the object, and still result in an object with a desired property.

Abstract: A method is provided for generating new objects having given properties, such as a specific bioactivity (e.g., binding with a specific protein). In some aspects, the method can include: (a) receiving objects (e.g., physical structures) and their properties (e.g., chemical properties, bioactivity properties, etc.) from a dataset; (b) providing the objects and their properties to a machine learning platform, wherein the machine learning platform outputs a trained model; and (c) the machine learning platform takes the trained model and a set of properties and outputs new objects with desired properties. The new objects are different from the received objects. In some aspects, the objects are molecular structures, such as potential active agents, such as small molecule drugs, biological agents, nucleic acids, proteins, antibodies, or other active agents with a desired or defined bioactivity (e.g., binding a specific protein, preferentially over other proteins).

Abstract: A method for generating an object includes: providing a dataset having object data and condition data; processing the object data to obtain latent object data and latent object-condition data; processing the condition data to obtain latent condition data and latent condition-object data; processing the latent object data and the latent object-condition data to obtain generated object data; processing the latent condition data and latent condition-object data to obtain generated condition data; comparing the latent object-condition data to the latent condition-object data to determine a difference; processing the latent object data and latent condition data and one of the latent object-condition data or latent condition-object data to obtain a discriminator value; and selecting a selected object based on the generated object data.