The technical solution relates to the field of artificial intelligence technologies, such as machine learning technologies, natural language processing technologies, or the like. A plurality of training samples are collected, each of the plurality of training samples includes information of a known training target protein, information of two training drugs, and a real difference between affinities of the two training drugs for the known training target. The ranking learning model is trained with the plurality of training samples, such that the ranking learning model learns a capability of predicting a magnitude relationship between the affinities of the two training drugs for the known training target protein in each of the plurality of training samples.

Methods for identifying compounds that are inhibitors or are likely to be inhibitors of amyloid protein aggregation, as well as three-dimensional, non-crystallographic models (i.e. “pseudo-crystal structures”) of amyloid aggregation utilized in the methods, are described. Means for creating the three-dimensional, non-crystallographic models (i.e. “pseudo-crystal structures”) of amyloid aggregation are also described.

Methods for identifying compounds that are inhibitors or are likely to be inhibitors of amyloid protein aggregation, as well as three-dimensional, non-crystallographic models (i.e. “pseudo-crystal structures”) of amyloid aggregation utilized in the methods, are described. Means for creating the three-dimensional, non-crystallographic models (i.e. “pseudo-crystal structures”) of amyloid aggregation are also described.

Disclosed herein are methods and systems for identifying a drug capable of changing a cell's state, function, and/or predicted age, which is useful in, at least, drug discovery. Further disclosed herein are methods and systems for identifying an in vitro cell's state, function, and/or predicted age.

Disclosed herein are methods and systems for identifying a drug capable of changing a cell's state, function, and/or predicted age, which is useful in, at least, drug discovery. Further disclosed herein are methods and systems for identifying an in vitro cell's state, function, and/or predicted age.

A system, device, and method for predicting an active set of compounds that bind to a biomolecular target is disclosed. The system and device contain modules allowing for the prediction of an active set of compounds. A core identification module can identify the core of an initial lead compound. A core hopping module is used to identify potential lead compounds having different cores compared to the core of an initial lead compound. A scoring module can use computational techniques to calculate the relative binding free energy of each identified potential lead compound. An activity prediction module can use the relative binding free energy calculations to predict an active set of compounds that bind to the biomolecular target. Empirical analysis can be used to inform the accuracy and completeness of the predicted active set of compounds.

Aspects of the present disclosure relate to computing systems and computational methods for docking a library of compounds against a massive amount of conformations of a protein of interest.

Aspects of the present disclosure relate to computing systems and computational methods for docking a library of compounds against a massive amount of conformations of a protein of interest.

The present disclosure relates to a method for generating variants of a protein based on a native protein regulated by allosteric pathway, the method comprising: i) providing 3D structures of the native protein; ii) identifying at least one pair of coupled allosteric sites within the amino acid sequence of the native protein named microswitch; iii) generating in silico mutations of said identified microswitch to generate a pool of variants; iv) computing at least one score reflecting the variation in allosteric coupling; and/or the variation in the relative stability v) predicting the activity of each variant compared to the native protein based on the computed score. The disclosure also concern a computer implemented program to carry out said method, and a variant of a protein or an active fragment thereof, a polynucleotide.

The present disclosure relates to a method for generating variants of a protein based on a native protein regulated by allosteric pathway, the method comprising: i) providing 3D structures of the native protein; ii) identifying at least one pair of coupled allosteric sites within the amino acid sequence of the native protein named microswitch; iii) generating in silico mutations of said identified microswitch to generate a pool of variants; iv) computing at least one score reflecting the variation in allosteric coupling; and/or the variation in the relative stability v) predicting the activity of each variant compared to the native protein based on the computed score. The disclosure also concern a computer implemented program to carry out said method, and a variant of a protein or an active fragment thereof, a polynucleotide.