PROTAC target molecule generation method, a computer system, and a storage medium

1 . A proteolysis-targeting chimera (PROTAC) target molecule generation method, characterized by comprising the following steps:

obtaining a first parameter, a second parameter and a third parameter;

extracting a target protein ligand structure corresponding to the first parameter in a target protein ligand database to form a first subset;

extracting a degradation agent fragment structure corresponding to the second parameter in a degradation agent fragment database to form a second subset;

extracting a linker fragment structure corresponding to the third parameter in a linker fragment database to form a third subset,

wherein extracting the linker fragment structure includes performing a length search in the linker fragment database to output a linker fragment structure conforming to a preset length to form the third subset; and

permuting and combining the fragment structures in the first subset, the second subset, and the third subset to generate one or more PROTAC target molecules,

wherein the length search comprises:

obtaining a first PROTAC molecule;

identifying special node markers in the first PROTAC molecule;

removing an active fragment structure and the degradation agent fragment structure in the first PROTAC molecule based on the special node markers to obtain an intermediate molecule to obtain an intermediate molecule; and

converting the intermediate molecule into a graph structure and calculating a length between two vertices in the graph structure, wherein the graph structure comprises atoms and line segments binding adjacent atoms.

2 . The PROTAC target molecule generation method according to claim 1 , wherein

extracting the target protein ligand structure corresponding to the first parameter in the target protein ligand database to form the first subset includes:

obtaining a ligand characteristic structure in a target protein ligand structure input by a user;

comparing a similarity between each target protein ligand structure in the target protein ligand database and the ligand characteristic structure; and

outputting the target protein ligand structure corresponding to the first parameter with the highest similarity degree to form the first subset; and wherein

extracting a degradation agent fragment structure corresponding to the second parameter in the degradation agent fragment database to form a second subset includes:

obtaining a degradation agent characteristic structure of the degradation agent fragment structure input by the user,

comparing a similarity between each degradation agent fragment in the degradation agent fragment database with the degradation agent characteristic structure, and

outputting the degradation agent fragment structure corresponding to the second parameter with the highest similarity degree to form the second subset.

3 . The PROTAC target molecule generation method according to claim 1 , wherein

extracting the target protein ligand structure corresponding to the first parameter in the target protein ligand database to form the first subset includes:

arranging the target protein ligand structures in the target protein ligand database in descending order according to a first activity order; and

outputting the target protein ligand structure corresponding to the first parameter to form the first subset, and wherein

extracting the degradation agent fragment structure corresponding to the second parameter in tire degradation agent fragment database to form the second subset includes:

arranging the degradation agent fragment structures in the degradation agent fragment database in descending order according to a second activity order; and

outputting the degradation agent fragment structure corresponding to the second parameter to form the second subset.

4 . The PROTAC target molecule generation method according to claim 1 , wherein the preset length is an integer.

5 . The PROTAC target molecule generation method according to claim 1 , characterized in that before obtaining the first parameter, the second parameter, and the third parameter, the method for generating the PROTAC target molecule further comprises:

obtaining a second PROTAC molecule input by the user, wherein the second PROTAC molecule is expressed by a simplified molecular-input line-entry system (SMILES) molecular structure or a Protein Data Bank (PDB) protein structure.

6 . The PROTAC target molecule generation method according to claim 1 , wherein after generating the PROTAC target molecule, the method for generating the PROTAC target molecule further comprises:

scoring the PROTAC target molecule according to a preset scoring model; and

deriving the PROTAC target molecule with a score greater than or equal to a first threshold.

7 . The PROTAC target molecule generation method according to claim 6 , characterized in that the preset scoring model comprises a binary classification model using a random forest method.

8 . The PROTAC target molecule generation method according to claim 1 , wherein

the fragment structure in at least one element of a set comprising the target protein ligand database, the degradation agent fragment database, and the linker fragment database is from an open source database; and wherein

the open source database includes, but is not limited to, at least one element of a set comprising PROTAC-DB, PROTACpedia, Chembl, and BindmgDB.

9 . A computer system comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that when the processor executes the computer program, realizes the steps of a proteolysis-targeting chimera (PROTAC) target molecule generation method according to claim 1 .

10 . A computer-readable storage medium, on which a computer program is stored, characterized in that when the computer program is executed by a processor, realize the steps of a proteolysis-targeting chimera (PROTAC) target molecule generation method according to claim 1 .