A system and method for optimizing the latent space in generative machine learning models, and applications of the optimizations for use in the de novo generation of molecules for both ligand-based and pocket-based generation. The ligand-based optimizations comprise a tunable reward system based on a multi-property model and further define new measurable metrics: molecular novelty and uniqueness. The pocket-based optimizations comprise an initial multi-property optimization followed up by either a seed-based optimization or a relaxed-based optimization.

An electronic device generates, according to a connection graph structure corresponding to a reference drug molecule, an atomic latent vector corresponding to the reference drug molecule. The device performs atom masking processing on the atomic latent vector to obtain a scaffold latent vector and a sidechain latent vector included in the atomic latent vector. The device generates a target scaffold latent vector with a target transition degree between the scaffold latent vector and the target scaffold latent vector according to a spatial distribution of the scaffold latent vector. The device generates a transitioned drug molecule according to the target scaffold latent vector and the sidechain latent vector.

An electronic device generates, according to a connection graph structure corresponding to a reference drug molecule, an atomic latent vector corresponding to the reference drug molecule. The device performs atom masking processing on the atomic latent vector to obtain a scaffold latent vector and a sidechain latent vector included in the atomic latent vector. The device generates a target scaffold latent vector with a target transition degree between the scaffold latent vector and the target scaffold latent vector according to a spatial distribution of the scaffold latent vector. The device generates a transitioned drug molecule according to the target scaffold latent vector and the sidechain latent vector.

A concrete formulation system for repairing a cultural relic building and a use method thereof. The method includes obtaining a first index value, a second index value, and a third index value of a cultural relic building concrete sample and comparing the index values in a database of the concrete formulation system to obtain raw material components and contents of an original preparation formula of cultural relic concrete. The method further includes preparing a repairing concrete sample, measuring the index values, of the repairing concrete sample and comparing the index values of the cultural relic building concrete sample, and if the result is that the difference between the first index values is not greater than 20%, the difference between the second index values is not greater than 60%, and the difference between the third index values is not greater than 60%, using the repairing concrete sample for cultural relic repair.

A concrete formulation system for repairing a cultural relic building and a use method thereof. The method includes obtaining a first index value, a second index value, and a third index value of a cultural relic building concrete sample and comparing the index values in a database of the concrete formulation system to obtain raw material components and contents of an original preparation formula of cultural relic concrete. The method further includes preparing a repairing concrete sample, measuring the index values, of the repairing concrete sample and comparing the index values of the cultural relic building concrete sample, and if the result is that the difference between the first index values is not greater than 20%, the difference between the second index values is not greater than 60%, and the difference between the third index values is not greater than 60%, using the repairing concrete sample for cultural relic repair.

In a method of molecular scaffold hopping an interface of a scheduler computer sends instructions, prepared by the scheduler computer, to a job runner computer to perform a plurality of separate computational tasks. Each of the separate computational tasks includes calculating one or more chemical properties for a query molecule or molecules in a library of molecules. One or more of the plurality of separate computational tasks performed on the job runner computer are preemptible computing instances. Status indicators sent from the job runner computer are received by the interface for each of the plurality of separate computational tasks. The indicators are one of: incomplete, completed, or failed computing instances. The interface resends the instructions to the job runner computer that correspond to the separate computational tasks having the failed computing instance indicator to increase fault-tolerance against the separate computational tasks not attaining the completed computing instance indicator.

A computer implemented method for determining performance properties of an oil-containing product for cosmetics, the oil-containing product for cosmetics comprising different oils forming a mixture, the method comprising the steps of: providing to a processing device via an input channel o performance properties for each of the different oils o a measure for the ratio of the different oils in the mixture, o a data driven model and/or a rigorous model determining with a processing device determined performance properties of the oil-containing product for cosmetics comprising the mixture, based on o the data driven model o the performance properties for each of the different oils o the measure for the ratio of the different oils in the mixture, providing via an output channel o the determined performance properties of the oil-containing product for personal care and/or o the measure for the ratio of the different oils in the mixture and/or o a formulation of the mixture, and or o a formulation of the oil-containing product for personal care.

A computer implemented method for determining performance properties of an oil-containing product for cosmetics, the oil-containing product for cosmetics comprising different oils forming a mixture, the method comprising the steps of: providing to a processing device via an input channel o performance properties for each of the different oils o a measure for the ratio of the different oils in the mixture, o a data driven model and/or a rigorous model determining with a processing device determined performance properties of the oil-containing product for cosmetics comprising the mixture, based on o the data driven model o the performance properties for each of the different oils o the measure for the ratio of the different oils in the mixture, providing via an output channel o the determined performance properties of the oil-containing product for personal care and/or o the measure for the ratio of the different oils in the mixture and/or o a formulation of the mixture, and or o a formulation of the oil-containing product for personal care.

A structure model includes a first encoder that converts a compound structure representation to a real number vector and a first decoder that estimates the compound structure representation from the real number vector resulting from the conversion by the first encoder. A structure-property relationship model includes a second encoder that converts, to a real number vector, an extended vector including, as components, the real number vector generated by the first encoder and a target value vector including target values of one or more physical property values and a second decoder that estimates the extended vector from the real number vector generated by the second encoder.

A structure model includes a first encoder that converts a compound structure representation to a real number vector and a first decoder that estimates the compound structure representation from the real number vector resulting from the conversion by the first encoder. A structure-property relationship model includes a second encoder that converts, to a real number vector, an extended vector including, as components, the real number vector generated by the first encoder and a target value vector including target values of one or more physical property values and a second decoder that estimates the extended vector from the real number vector generated by the second encoder.