Abstract: A method for training a model to estimate synthetic accessibility may be provided. A retrosynthesis-related synthetic accessibility model may be provided. A molecular structures database may be accessed. At least one molecular structure may be obtained from the molecular structures database with the model. The at least one molecular structure may be virtually sliced into synthon-like fragments with the model. A frequency of the synthon-like fragments in natural molecules may be determined with the model. Molecular descriptors for the synthon-like fragments may be calculated with the model. An aggregated synthetic accessibility score for the synthon-like fragments may be determined with the model. The aggregated synthetic accessibility score for the synthon-like fragments may be stored in a database for the model.

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 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: Provided herein are compounds of Formulas (I), (II), (III), and (IV) and subformulas thereof, wherein the variables are defined herein. Also provided herein are pharmaceutical compositions comprising a compound of Formula (I), (II), (III), or (IV) and methods of using the compounds, e.g., in the treatment of immune disorders, inflammatory disorders, and cancer.

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: 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: 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: 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 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: Provided herein are compounds of Formulas (I), (II), (III), and (IV) and subformulas thereof, wherein the variables are defined herein. Also provided herein are pharmaceutical compositions comprising a compound of Formula (I), (II), (III), or (IV) and methods of using the compounds, e.g., in the treatment of immune disorders, inflammatory disorders, and cancer.

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.