CN115910234A - Complex ligand binding position evaluation method, complex ligand binding position evaluation device and computer equipment - Google Patents
Complex ligand binding position evaluation method, complex ligand binding position evaluation device and computer equipment Download PDFInfo
- Publication number
- CN115910234A CN115910234A CN202210092867.9A CN202210092867A CN115910234A CN 115910234 A CN115910234 A CN 115910234A CN 202210092867 A CN202210092867 A CN 202210092867A CN 115910234 A CN115910234 A CN 115910234A
- Authority
- CN
- China
- Prior art keywords
- target
- ligand
- complex
- conformation
- binding strength
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Abstract
The application discloses a method and a device for evaluating a ligand binding position of a complex and computer equipment. The method comprises the steps of respectively binding a target ligand to a plurality of candidate binding positions in a target protein to obtain a candidate complex conformation corresponding to each candidate binding position; obtaining distance information between each atom of the target protein and each atom of the target ligand in each candidate complex conformation; determining binding strength information of the target protein and the target ligand in each candidate complex conformation according to the distance information; target binding sites are determined based on the binding strength information. The method can improve the accuracy of the evaluation of the ligand binding position in the complex.
Description
Technical Field
The application relates to the field of biotechnology, in particular to a method and a device for evaluating a ligand binding position of a complex and computer equipment.
Background
With the continuous development and popularization of computer technology, the assistance of computer simulation to research and development of drugs is an effective means in the process of research and development of drugs, and the time and money can be greatly saved by the aid of technology to research and development of drugs.
During drug development, it is often necessary to assess the docking position of the ligand to the protein in the complex in order to screen out high quality complexes. At present, when the suitable docking position of the ligand in the protein is evaluated, the traditional scoring function is often adopted to score the complex obtained after the ligand is docked to different positions, and then the suitable docking position of the ligand in the protein is determined according to the scoring result obtained by the scoring function.
Due to the fact that the accuracy of the traditional scoring function is not high, the assessment on the ligand docking position in the complex is not accurate enough.
Disclosure of Invention
The embodiment of the application provides a method, a device and a computer device for evaluating a ligand binding position of a complex, and the method can effectively improve the evaluation accuracy of the ligand binding position evaluation of the complex.
In a first aspect, the present application provides a method for evaluating a ligand binding site of a complex, the method comprising:
respectively binding a target ligand to a plurality of candidate binding positions in a target protein to obtain a candidate complex conformation corresponding to each candidate binding position;
obtaining distance information between each atom of the target protein and each atom of the target ligand in each candidate complex conformation;
determining binding strength information for the target protein and the target ligand in each candidate complex conformation from the distance information;
determining a target binding location based on the binding strength information.
Accordingly, a second aspect of the present application provides a device for evaluating a ligand binding site of a complex, the device comprising:
the binding unit is used for respectively binding the target ligand to a plurality of candidate binding positions in the target protein to obtain a candidate complex conformation corresponding to each candidate binding position;
an obtaining unit for obtaining information on a distance between each atom of the target protein and each atom of the target ligand in each candidate complex conformation;
a first determining unit for determining binding strength information of the target protein and the target ligand in each candidate complex conformation based on the distance information;
a second determination unit for determining a target binding location based on the binding strength information.
The third aspect of the present application also provides a computer readable storage medium storing a plurality of instructions adapted to be loaded by a processor to perform the steps of the method for assessing a ligand binding site of a complex provided in the first aspect of the present application.
A fourth aspect of the present application provides a computer device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, the processor implementing the steps of the method for assessing a ligand binding site of a complex provided in the first aspect of the present application when executing the computer program.
A fifth aspect of the present application provides a computer program product comprising computer program/instructions which, when executed by a processor, implement the steps in the method for assessing the ligand binding site of a complex provided in the first aspect.
According to the method for evaluating the ligand binding position of the complex, the target ligand is respectively bound to a plurality of candidate binding positions in the target protein, so that a candidate complex conformation corresponding to each candidate binding position is obtained; obtaining distance information between each atom of the target protein and each atom of the target ligand in each candidate complex conformation; determining binding strength information of the target protein and the target ligand in each candidate complex conformation according to the distance information; the target binding location is determined based on the binding strength information.
Therefore, the method for evaluating the ligand binding position of the complex provided by the application can calculate the binding strength of the protein and the ligand in the complex according to the distance information between the protein atom and the ligand atom in the complex, and then determine the optimal binding position of the ligand according to the different binding strengths corresponding to the different positions where the ligand is docked. Namely, the method can accurately calculate the binding strength corresponding to different complex conformations obtained after the ligand is bound to different binding positions of the protein, and then determine the optimal set position according to the binding strength, thereby improving the accuracy of the evaluation of the ligand binding position in the complex.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed to be used in the description of the embodiments are briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present application, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.
FIG. 1 is a schematic diagram of one scenario for ligand binding site assessment of a complex in the present application;
FIG. 2 is a schematic flow diagram of a method for assessing the ligand binding site of a complex provided herein;
FIG. 3 is a graph of the results of a ligand binding strength assessment method of the present application in a specific database;
FIG. 4 is a graph of the results of a test of the conformational optimization method provided herein in a particular database;
FIG. 5 is a graph of the results of another test of the conformational optimization methods provided herein in a particular database;
FIG. 6 is a schematic diagram of the structure of a ligand binding site evaluation device for a complex provided herein;
fig. 7 is a schematic structural diagram of a computer device provided in the present application.
Detailed Description
The technical solution in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. It is to be understood that the described embodiments are merely exemplary of the invention, and not restrictive of the full scope of the invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The embodiment of the invention provides a method and a device for evaluating a ligand binding position of a complex and computer equipment. The method for evaluating the ligand binding site of the complex can be used in a device for evaluating the ligand binding site of a complex. The ligand binding site evaluation means of the complex may be integrated in a computer device, which may be a terminal or a server. The terminal can be a mobile phone, a tablet Computer, a notebook Computer, a smart television, a wearable smart device, a Personal Computer (PC), a vehicle-mounted terminal, and the like. The server may be an independent physical server, a server cluster or a distributed system formed by a plurality of physical servers, or a cloud server providing basic cloud computing services such as cloud service, a cloud database, cloud computing, a cloud function, cloud storage, network service, cloud communication, middleware service, domain name service, security service, network acceleration service (CDN), big data and an artificial intelligence platform. Wherein a server may be a node in a blockchain.
Please refer to fig. 1, which is a schematic view of a scenario of a method for estimating a ligand binding site of a complex provided in the present application. As shown in the figure, the server a receives an evaluation request sent by the terminal B, where the evaluation request includes a target protein and a target ligand included in a complex to be evaluated, and an evaluation instruction for evaluating a ligand binding site in the complex. Then the server A respectively combines the target ligand with a plurality of candidate combination positions in the target protein to obtain a candidate complex conformation corresponding to each candidate combination position; obtaining distance information between each atom of the target protein and each atom of the target ligand in each candidate complex conformation; determining binding strength information of the target protein and the target ligand in each candidate complex conformation according to the distance information; target binding sites are determined based on the binding strength information. The target binding position is then returned to terminal B as an evaluation result.
It should be noted that the schematic diagram of the ligand binding site evaluation scenario of the complex shown in fig. 1 is only an example, and the ligand binding site evaluation scenario of the complex described in the embodiment of the present application is for more clearly illustrating the technical solution of the present application, and does not constitute a limitation to the technical solution provided in the present application. It can be known to those skilled in the art that, with the evolution of the complex ligand binding site evaluation scenario and the emergence of new business scenario, the technical solution provided in the present application is also applicable to similar technical problems.
Based on the above-described implementation scenarios, detailed descriptions will be given below.
In the related art, when the ligand binding site in the complex is evaluated, the conformation of the complex obtained by binding the ligand to the different binding sites is generally scored using a scoring function. The traditional scoring function is mostly based on experience, the accuracy is not high, and the generalization capability is limited. In this regard, the present application provides a method for evaluating a ligand binding site of a complex, which can improve the accuracy of the evaluation of the ligand binding site of the complex to some extent.
The embodiments of the present application will be described from the perspective of a ligand binding site evaluation device of a complex, which may be integrated in a computer device. The computer device may be a terminal or a server. The terminal can be a mobile phone, a tablet Computer, a notebook Computer, a smart television, a wearable smart device, a Personal Computer (PC), a vehicle-mounted terminal, and the like. The server may be an independent physical server, a server cluster or a distributed system formed by a plurality of physical servers, or a cloud server providing basic cloud computing services such as cloud service, a cloud database, cloud computing, a cloud function, cloud storage, network service, cloud communication, middleware service, domain name service, security service, network acceleration service (CDN), big data and an artificial intelligence platform. As shown in fig. 2, a schematic flow chart of a method for evaluating a ligand binding site of a complex provided herein includes:
Where the target ligand and target protein are the ligand and protein that are identified to be bound in a complex, binding of the ligand to the protein may also be referred to herein as docking the ligand into the protein. Specifically, the target protein and the target ligand may be proteins and ligands included in the binding site evaluation instruction transmitted from the other terminal.
In virtual drug screening, it is often necessary to target ligands to proteins to determine the efficacy of drugs against viruses. Wherein, the method for judging whether the ligand (small molecule or short peptide) drug can be effectively combined with the pathogenic protein is to calculate the combination strength between the protein and the ligand, and the larger the combination strength is, the more compact the combination of the protein and the ligand is. However, the magnitude of the binding strength is greatly influenced by the binding site of the ligand, and the same ligand pair can obtain different binding strengths at different binding sites, so that the evaluation and optimization of the binding site is of great importance in drug design.
Docking of ligands into protein active pockets is essentially a two-step procedure: firstly, the method comprises the following steps: sampling, and searching for multiple positions of ligand binding at the active pocket of the protein. Secondly, the method comprises the following steps: and (4) scoring, and predicting the binding energy size of the ligand between the proteins at different binding positions through a scoring function. Binding energy here refers to the binding potential between the protein and the ligand, i.e.the binding strength. Most of the current molecular docking software uses traditional scoring functions, however, the precision of the traditional scoring functions is not enough, so that the evaluation accuracy of ligand binding positions generated in the docking process is poor, and the false positive rate of the molecular docking process is high. Conventional scoring functions are generally classified into three categories: a physical-based scoring function, an empirical-based scoring function, and a knowledge-based scoring function. The conventional method has low accuracy in predicting the protein-ligand interaction and has limited generalization ability. In recent years, the trend of predicting protein-ligand interaction by using a machine learning method is particularly along with the introduction of deep learning, and the efficiency and the accuracy of predicting the protein-ligand interaction can be greatly improved by adopting algorithms such as a convolutional neural network and a graph neural network. The embodiment of the application provides a method for evaluating the ligand binding position of a complex based on a deep learning method, and the method is used for improving the accuracy of the evaluation of the ligand binding position in the complex.
When the target protein and the target ligand to be docked are determined, a plurality of possible binding sites in the target protein need to be determined first, and specifically, a plurality of possible binding sites of the ligand in an active pocket of the protein can be determined first using molecular docking software, and these binding sites can be referred to herein as candidate binding sites. The molecular docking software can be AutoDock Vina, wherein AutoDock Vina is an open source molecular simulation software and is mainly applied to performing ligand-protein docking.
After determining a plurality of possible candidate binding sites for a ligand in the active pocket of the protein, the target ligand may be docked into these candidate binding sites one by one, resulting in a candidate complex conformation corresponding to each candidate binding site. Wherein, the docking of the target ligand to these candidate set positions may be a simulated docking using a computer to obtain a candidate complex conformation corresponding to each candidate binding position.
At step 102, distance information between each atom of the target protein and each atom of the target ligand in each candidate complex conformation is obtained.
Wherein, after the candidate complex conformation corresponding to each candidate binding position is determined by simulation, the distance information between the atom of the target protein and the atom of the target ligand in each candidate complex conformation can be further calculated.
Wherein, the protein contains amino acid and heavy atom, wherein the heavy atom is non-hydrogen atom. Specifically, the amino acid types include twenty basic amino acids and one additional group. Among them, the twenty basic amino acids include: glycine, alanine, valine, leucine, isoleucine, methionine (methionine), proline, tryptophan, serine, tyrosine, cysteine, phenylalanine, asparagine, glutamine, threonine, aspartic acid, glutamic acid, lysine, arginine, and histidine. An additional group of amino acids can be defined as other amino acids (other, OTH). Amino acids contain several atoms, carbon, nitrogen, hydrogen and oxygen. Heavy atom types in proteins include carbon (C), nitrogen (N), oxygen (O), sulfur (S), and extra atom types (DU).
The atoms in the target ligand can be classified into carbon, nitrogen, oxygen, sulfur, phosphorus, halogen and other 7 kinds of them according to the element type, and the halogen can be any one of fluorine, chlorine, bromine and iodine.
Calculating distance information between atoms of the target protein and atoms of the target ligand in each candidate complex conformation can be calculating distance information between each atom of the target protein and each atom of the target ligand, and can also be calculating distance information between atoms of amino acid and heavy atom combination type in the protein and ligand atoms.
The distance information between atoms is calculated, and each candidate complex conformation can be arranged in a preset three-dimensional coordinate system, and then the coordinate information of each atom is acquired. And then calculates distance information between atoms based on the coordinate information.
After calculating the distance information between each atom of the target protein and each atom of the target ligand in each candidate complex conformation, the binding strength information between the target protein and the target ligand in each candidate complex conformation can be evaluated according to the distance information.
In some embodiments, determining binding strength information for the target protein and the target ligand in each candidate complex conformation from the distance information comprises:
1. generating a ligand binding strength evaluation characteristic corresponding to each candidate complex conformation according to the distance information;
2. and inputting the ligand binding strength evaluation characteristics corresponding to each candidate compound conformation into a preset neural network model to obtain the output binding strength information of the target protein and the target ligand in each candidate compound conformation.
In the embodiment of the present application, a deep learning method may be used to achieve the evaluation of the binding strength between the target protein and the target ligand in each candidate complex conformation through a neural network model. The neural network model can be a preset neural network model and is used for outputting corresponding ligand binding strength information according to the input ligand binding strength evaluation characteristics.
Specifically, the ligand binding strength characteristic corresponding to each candidate complex may be generated according to the distance information between the protein atom and the ligand atom in each candidate complex. And then inputting the ligand binding strength characteristic corresponding to each candidate compound into the trained preset neural network model for ligand binding strength evaluation to obtain the ligand binding strength information corresponding to each candidate compound.
In some embodiments, generating a ligand binding strength assessment feature corresponding to each candidate complex conformation from the distance information comprises:
1.1, determining a first number of first target atoms in the target protein based on combinations of different amino acids and heavy atoms;
1.2, determining a second number of second target atoms in the target ligand;
1.3, determining target distance information between each first target atom and each second target atom in the distance information;
and 1.4, generating a ligand binding strength evaluation characteristic corresponding to each candidate complex conformation according to the target distance information.
In the embodiment of the present application, the ligand binding strength characteristic corresponding to each candidate complex can be determined based on the distance information between the protein heavy atoms and the ligand atoms in the different classes. Specifically, as mentioned above, if there are 21 amino acid types and 5 heavy atoms in the protein, the atomic species in the protein can be determined by the combination of different amino acids and heavy atoms, so that 21 × 5=105 protein atoms can be obtained, which may be referred to as the first target atom herein. Where the same heavy atom is bound to different amino acids, it can be identified as a different protein atom. Also, as previously mentioned, there are 7 of the aforementioned ligand atom types, where the ligand atom may be referred to as the second target atom. Then there may be 105 x 7=735 atom pairs bound between the protein and the ligand. For each atom binding mode, the distance between the atom pair corresponding to the binding mode can be determined according to the calculated distance information between all atoms of the protein and all atoms of the ligand, and then a characteristic value is calculated according to the distance between the atom pair, and the characteristic values form a characteristic vector of 735D, and the characteristic vector can be used as the ligand binding strength evaluation characteristic in the application.
In some embodiments, generating a ligand binding strength assessment feature corresponding to each candidate complex conformation from the target distance information comprises:
1.4.1, calculating a first characteristic dimension of the target distance information to obtain a first sub-ligand binding strength evaluation characteristic corresponding to each candidate compound conformation;
1.4.2, calculating a second characteristic dimension of the target distance information to obtain a second sub-ligand binding strength evaluation characteristic corresponding to each candidate compound conformation;
and 1.4.3, splicing the first sub ligand binding strength evaluation characteristic and the second sub ligand binding strength evaluation characteristic corresponding to each candidate complex conformation to obtain the ligand binding strength evaluation characteristic corresponding to each candidate complex conformation.
In the embodiment of the present application, the eigenvalue corresponding to each type of atom pair is calculated, and specifically, the interaction force between two atoms in the atom pair may be calculated. The interaction forces between atoms in an atom pair may include van der waals interactions and electrostatic interactions, among others. In embodiments of the present application, the interactions between pairs of atoms may be characterized using the negative exponential power between the atomic distances. Because the negative exponential order indexes of the distances corresponding to the van der waals interaction and the electrostatic interaction are different, the van der waals interaction potential energy and the electrostatic interaction potential energy between each type of atom pairs can be calculated according to the distance information between the atoms, and the van der waals interaction potential energy and the electrostatic interaction potential energy can be respectively referred to as a first sub-ligand set strength evaluation characteristic and a second sub-ligand binding strength evaluation characteristic. The two potential values corresponding to each atom pair are used as the parameters of the feature, so that the feature vector of 735 × 2=1470 dimension corresponding to each candidate complex conformation can be obtained. The feature vector is then characterized for the strength of ligand binding corresponding to the candidate complex conformation.
The method for calculating the corresponding characteristic value according to the distance information between the atom pairs in the application can adopt the following formula (1) to calculate:
wherein RA represents an atom type in a protein, i.e., one of the aforementioned 105 protein atom types; l represents the atom type of the ligand, i.e. one of the atom types of the ligand in 7 mentioned above. i is an exponential power, and specifically may be 1 or 6.d is the distance between atoms in an atom pair.
Thus, for each candidate complex conformation, 1470 such E-values can be calculated, and the ligand binding strength assessment feature corresponding to that candidate complex conformation can be constructed based on the 1470 values.
In some embodiments, since when the distance between atoms in an atom pair is too small, it may cause explosion of a characteristic value, for this reason, in the embodiments of the present application, certain judgment and limitation may be performed on the distance between atoms in an atom pair. The distance d between atoms in a limiting atom pair satisfies the following inequality:
0.3nm≤d≤2.0nm
where nm represents a length unit of nanometers, and d is set to 0.3 nanometers when the distance between atoms in an atom pair is less than 0.3 nanometers; when the distance between atoms in an atom pair is greater than 2 nanometers, then its corresponding characteristic value E is set to 0.
In some embodiments, before inputting the ligand binding strength evaluation feature corresponding to each candidate complex conformation into the preset neural network model and obtaining the output binding strength information of the target protein and the target ligand in each candidate complex conformation, the method further comprises:
A. obtaining a training sample, wherein the training sample comprises ligand binding strength evaluation characteristics corresponding to a plurality of sample complex conformations and binding strength information corresponding to each sample complex conformation;
B. and (3) taking the ligand binding strength evaluation characteristics corresponding to the conformations of the plurality of sample complexes as input, and taking the binding strength information corresponding to the conformation of each sample complex as output to train a preset neural network model.
In the embodiment of the present application, when the predetermined neural network model is used to process the ligand binding strength evaluation feature corresponding to each candidate complex conformation to obtain the ligand binding strength feature corresponding to each candidate complex conformation, the predetermined neural network model needs to be a trained neural network model. Therefore, before the preset neural network model is used for ligand binding strength evaluation, the preset neural network model needs to be trained. The preset neural network model may be a convolutional neural network model or other neural network models, and is not limited herein.
Specifically, the method of supervised training can be adopted to train the preset neural network model. Therefore, a training sample for training the preset neural network model needs to be obtained first, and the training sample includes a plurality of input features and a label value corresponding to each input feature. The input feature can be a ligand binding strength evaluation feature corresponding to the conformation of the sample complex, and the corresponding tag value can be binding strength information corresponding to the conformation of the sample complex.
Therefore, when the preset neural network model is trained by adopting the training sample, the ligand bonding strength evaluation characteristic corresponding to the sample compound is input into the preset neural network model to obtain the output bonding strength information, and then the model parameter of the preset neural network model is adjusted based on the difference between the output bonding strength information and the label value until the preset neural network model converges to obtain the trained preset neural network model.
In some embodiments, obtaining a training sample comprising ligand binding strength assessment features corresponding to a plurality of sample complex conformations and binding strength information corresponding to each sample complex conformation comprises:
a1, obtaining a first number of sample compounds;
a2, carrying out re-docking on the ligands in each sample complex to obtain a second number of sample complex conformations;
a3, calculating the binding strength information corresponding to the complex conformation of each sample;
a4, obtaining sample distance information between protein atoms and ligand atoms in the complex conformation of each sample;
and A5, generating a ligand binding strength evaluation characteristic corresponding to each sample complex conformation according to the sample distance information, wherein the ligand binding strength evaluation characteristic corresponding to each sample complex conformation and the binding strength information corresponding to each sample complex conformation form a training sample.
In the embodiment of the present application, the training samples may be obtained by performing re-docking and calculation using the standard conformation of the complex. Specifically, a first number of sample complexes may be downloaded from the database, wherein the conformation of the complexes corresponding to the sample complexes is the standard conformation, i.e., the conformation in which the binding strength between the protein and the ligand is maximal.
Then, the molecular docking software is adopted to re-dock each sample complex, and a plurality of sample complex conformations corresponding to each sample complex are obtained. At this time, root Mean square Error (RMSD) between the multiple sample complex conformations and the standard conformations of the sample complexes can be calculated, and the RMSD corresponding to each sample complex conformation can be used as its corresponding label value, i.e. its corresponding binding strength information. It is understood that a smaller RMSD value indicates a smaller difference between the complex conformation of the complex sample and the standard conformation, and that the binding strength of the ligand to the protein in the complex conformation is larger, and the state is more stable. Then, each sample complex conformation can be traversed, and the corresponding RMSD value can be calculated as the tag value of the sample complex conformation.
Then, for the multiple sample complex conformations resulting from the re-docking, their corresponding binding strength assessment features may be further generated. The method for generating the binding strength evaluation features of the sample complex conformation may be the same as the method for generating the binding strength evaluation features of the candidate complex conformation, and will not be described in detail.
After the binding strength assessment feature corresponding to each sample complex conformation and the RMSD corresponding to each sample complex conformation are generated, the binding strength assessment feature corresponding to each sample complex conformation and the corresponding RMSD can be used as training samples to train the predetermined neural network model.
As mentioned above, the input parameter for training the predetermined neural network model is the binding strength evaluation characteristic of each sample complex conformation, and the label value is the RMSD corresponding to each sample complex conformation. Then, after inputting the binding strength characteristics of each candidate complex conformation into the trained neural network model, the RMSD value corresponding to each candidate complex conformation is outputted.
It is understood that a smaller RMSD value indicates a smaller difference between the candidate complex conformation and the standard conformation, and thus indicates a greater binding strength between the protein and the ligand in the candidate complex conformation. After determining the corresponding RMSD value for each candidate complex conformation, the optimal binding site in the protein can be determined accordingly.
Wherein determining a target binding location based on the binding strength information comprises:
1. determining a target complex conformation among the candidate complex conformations according to the binding strength information;
2. and determining the binding position corresponding to the target complex conformation as the target binding position.
In the present embodiment, after determining the binding strength information corresponding to each candidate complex conformation, i.e., determining the RMSD value corresponding to each candidate complex conformation, the candidate complex conformation with the smallest RMSD value can be determined as the most stable complex conformation and determined as the target complex conformation.
Further, docking of the target ligand to the target binding site in the target protein, which is the optimal binding site, can be determined from the target complex conformation.
In some embodiments, the method for assessing a ligand binding site of a complex provided herein may further comprise:
A. obtaining spatial features of the target ligand in the conformation of the target complex, the spatial features including variable parameters characterizing the spatial position of each atom in the target ligand;
B. adjusting the spatial characteristics based on the binding strength information of the protein and the ligand in the conformation of the target compound to obtain target spatial characteristics;
C. the spatial position of each atom of the target ligand in the conformation of the target complex is determined based on the spatial features of the target.
Wherein, in the complex, the RMSD value influencing the conformation of the complex not only comprises the binding position of the ligand on the protein, but also comprises the spatial position information of atoms in the ligand. Since the spatial position information of the atoms in the ligand has a small influence on the RMSD value with respect to the influence of the position of the ligand at which the ligand is bound on the protein, the influence of the change in the spatial position of the atoms in the ligand is not considered when the ligand-bound position of the complex is evaluated, and the spatial position of the atoms in the ligand is fixed by default.
However, having determined the optimal binding position of the ligand in the protein, one can further determine the optimal spatial position of the atoms in the ligand, which can lead to smaller RMSD values and thus more stable complex conformations. That is, the present application also provides a conformation optimization method, which can be further used to further optimize the conformation of the complex after the ligand binding site is determined.
Thus, after determining the optimal binding site for binding the target ligand to the target protein, the spatial characteristics of the target ligand in the conformation of the target complex can be further obtained. Wherein the spatial signature comprises a variable parameter characterizing the spatial position of each atom in the target ligand. Specifically, the bonding relationships between atoms of the target ligand in the conformation of the target complex can be extracted, and the control features of the target ligand can be characterized by a vector of 6+k dimensions. Where 6 refers to the three-dimensional coordinates of the first atom of the target ligand to the target protein and the rotation angle around X, Y and the Z axis. Wherein the three-dimensional coordinates are (x, y, z) and the rotation angle is (alpha, beta, gamma). k is the twist angle (θ) of k rotatable bonds within the target ligand 1 ,θ 2 ,θ 3 ,…,θ k )。
Wherein, 6+k dimensional eigenvalues in the spatial characteristics of the target ligand are all variables, corresponding to different complex conformations for different eigenvalues. At this time, the three-dimensional coordinates of each atom in the target ligand can be calculated from these characteristic value variables of 6+k dimensions, where the three-dimensional coordinates are the three-dimensional coordinates expressed by the aforementioned characteristic value variables. Further, the ligand binding strength characteristic corresponding to the target complex conformation can be calculated according to the three-dimensional coordinates of the atoms of the target ligand and the three-dimensional coordinates of the target protein, and the ligand binding strength characteristic is further processed by adopting a preset neural network to obtain the RMSD value corresponding to the target conformation. Wherein it is understood that the RMSD value is associated with a variable parameter in the spatial signature of the target ligand.
In this way, the variable parameters can be adjusted to minimize the RMSD, so as to obtain the corresponding target control feature when the RMSD value is minimum.
After the spatial signature of interest is determined, the spatial position of each atom in the ligand of interest can be calculated based on the specific values of the variable parameters in the spatial signature of interest, resulting in a complex conformation with minimal RMSD.
In some embodiments, the spatial signature is adjusted based on information on the binding strength of the protein to the ligand in the conformation of the target complex to obtain a target spatial signature, comprising:
b1, recalculating the binding strength information of the protein and the ligand in the target complex conformation based on the spatial characteristics to obtain a binding strength representation function containing variable parameters;
b2, processing the bonding strength expression function by adopting a gradient descent method to obtain a numerical value of each variable parameter;
and B3, determining the target space characteristics according to the numerical value of each variable parameter.
In the embodiment of the present application, the spatial characteristics are adjusted based on the binding strength information of the protein and the ligand in the target complex conformation, and specifically, the binding strength information characterized by variable parameters in the spatial characteristics may be obtained by calculation, that is, the RMSD characterized by the variable parameters in the spatial characteristics is obtained. Specifically, the method can be used for calculating a characterization function of the RMSD expressed by variable parameters in the spatial features.
Because the characterization function is completely derivable, the characterization function can be iteratively solved by adopting a gradient descent method, namely, the spatial characteristics of the target ligand are repeatedly optimized. And when the iterative optimization times reach the preset times or the descending amplitude of the RMSD value is smaller than the preset amplitude, determining the convergence of the characterization function to obtain the final value of each variable parameter. The final values of the variable parameters determine the target spatial characteristics of the target ligand.
The accuracy of the ligand binding strength evaluation method included in the ligand binding site evaluation method of the complex provided herein is illustrated below with some specific examples. FIG. 3 is a graph showing the results of the ligand binding strength evaluation method of the present application in a specific database. As shown, fig. 3 is a graph of the results of the ligand binding strength assessment method (also referred to as scoring function) in the present application in CASF-2016, where CASF-2016 provides criteria for evaluating the scoring function, and there are 285 native protein-ligand complexes in CASF-2016, where each protein-ligand, upon re-docking by molecular docking software, generates about 100 complex conformations for testing the docking performance of the scoring function provided herein. As shown in fig. 3, the scoring function provided by the present application exhibits stronger prediction performance as the RMSD interval increases. The spearman correlation approaches 0.7 when the RMSD is between 0-5 angstroms.
As shown in fig. 4, a test result diagram of the conformation optimization method provided in the present application in a specific database is shown. As shown, the probability distribution of successful conformation optimization of each protein-ligand in the above-mentioned CASF-2016 test set is shown, and the success rate of the conformation optimization method provided by the present application on most protein-ligand conformation optimization is above 50%.
As shown in fig. 5, another test result in a specific database for the conformational optimization method provided herein. As shown in the figure, the graph shows the probability of successful conformation optimization in different RMSD intervals, and the success rate of conformation optimization provided by the present application is close to 70% in the RMSD interval of 1 to 3.
According to the above description, the method for evaluating the ligand binding site of the complex provided in the embodiments of the present application obtains a candidate complex conformation corresponding to each candidate binding site by binding the target ligand to a plurality of candidate binding sites in the target protein, respectively; obtaining distance information between each atom of the target protein and each atom of the target ligand in each candidate complex conformation; determining binding strength information of the target protein and the target ligand in each candidate complex conformation according to the distance information; target binding sites are determined based on the binding strength information.
Therefore, the method for evaluating the ligand binding position of the complex provided by the application can calculate the binding strength of the protein and the ligand in the complex according to the distance information between the protein atom and the ligand atom in the complex, and then determine the optimal binding position of the ligand according to the different binding strengths corresponding to the different positions where the ligand is docked. Namely, the method can accurately calculate the binding strength corresponding to different complex conformations obtained after the ligand is bound to different binding positions of the protein, and then determine the optimal set position according to the binding strength, thereby improving the accuracy of the evaluation of the ligand binding position in the complex.
In order to better implement the above method, the embodiments of the present application further provide a complex ligand binding site evaluation device, which may be integrated in a terminal or a server.
For example, as shown in fig. 6, a schematic structural diagram of a device for evaluating a ligand binding site of a complex provided in an embodiment of the present application may include a binding unit 301, an obtaining unit 302, a first determining unit 303, and a second determining unit 304, as follows:
a binding unit 301, configured to bind a target ligand to multiple candidate binding positions in a target protein, respectively, to obtain a candidate complex conformation corresponding to each candidate binding position;
an obtaining unit 302 for obtaining information on a distance between each atom of the target protein and each atom of the target ligand in each candidate complex conformation;
a first determining unit 303, configured to determine, according to the distance information, binding strength information of the target protein and the target ligand in each candidate complex conformation;
a second determination unit 304 for determining a target binding location based on the binding strength information.
In some embodiments, the first determining unit includes:
a generating subunit, configured to generate, according to the distance information, a ligand binding strength evaluation feature corresponding to each candidate complex conformation;
and the evaluation subunit is used for inputting the ligand binding strength evaluation characteristics corresponding to each candidate complex conformation into a preset neural network model to obtain the output binding strength information of the target protein and the target ligand in each candidate complex conformation.
In some embodiments, the generating subunit includes:
a first determination module for determining a first number of first target atoms in the target protein based on combinations of different amino acids and heavy atoms;
a second determination module for determining a second number of second target atoms in the target ligand;
a third determining module, configured to determine, in the distance information, target distance information between each first target atom and each second target atom;
and the first generation module is used for generating a ligand binding strength evaluation characteristic corresponding to each candidate complex conformation according to the target distance information.
In some embodiments, the first generating module comprises:
the first calculation submodule is used for calculating a first characteristic dimension of the target distance information to obtain a first sub-ligand binding strength evaluation characteristic corresponding to each candidate compound conformation;
the second calculation sub-module is used for calculating a second characteristic dimension of the target distance information to obtain a second sub-ligand binding strength evaluation characteristic corresponding to each candidate compound conformation;
and the splicing submodule is used for splicing the first sub-ligand binding strength evaluation characteristic and the second sub-ligand binding strength evaluation characteristic corresponding to each candidate compound conformation to obtain the ligand binding strength evaluation characteristic corresponding to each candidate compound conformation.
In some embodiments, the complex provided herein further comprises:
a first obtaining subunit, configured to obtain a training sample, where the training sample includes ligand binding strength evaluation features corresponding to multiple sample complex conformations and binding strength information corresponding to each sample complex conformation;
and the training subunit is used for taking the ligand binding strength evaluation characteristics corresponding to the sample complex conformations as input and taking the binding strength information corresponding to each sample complex conformation as output to train a preset neural network model.
In some embodiments, the first obtaining subunit includes:
a first obtaining module for obtaining a first number of sample complexes;
a docking module for re-docking the ligands in each sample complex to obtain a second number of sample complex conformations;
the calculation module is used for calculating the corresponding binding strength information of each sample complex conformation;
the second acquisition module is used for acquiring sample distance information between the protein atoms and the ligand atoms in the conformation of each sample complex;
and the second generation module is used for generating a ligand binding strength evaluation characteristic corresponding to each sample complex conformation according to the sample distance information, and the ligand binding strength evaluation characteristic corresponding to each sample complex conformation and the binding strength information corresponding to each sample complex conformation form a training sample.
In some embodiments, the second determining unit includes:
a first determining subunit for determining a target complex conformation among the candidate complex conformations based on the binding strength information;
and the second determining subunit is used for determining the binding position corresponding to the target complex conformation as the target binding position.
In some embodiments, the ligand binding site evaluation device of the complex provided herein further comprises:
a second acquiring subunit for acquiring a spatial signature of a target ligand in the conformation of the target complex, the spatial signature comprising a variable parameter characterizing the spatial position of each atom in the target ligand;
the adjusting subunit is used for adjusting the spatial characteristics based on the information of the binding strength of the protein and the ligand in the target complex conformation to obtain target spatial characteristics;
a third determining subunit for determining the spatial position of each atom of the target ligand in the conformation of the target complex based on the spatial features of the target.
In some embodiments, the conditioning subunit comprises:
a calculation module for recalculating the binding strength information of the protein and the ligand in the conformation of the target complex based on the spatial features to obtain a binding strength representation function containing the variable parameter;
the processing module is used for processing the bonding strength representation function by adopting a gradient descent method to obtain a numerical value of each variable parameter;
and determining the target space characteristics according to the numerical value of each variable parameter.
In a specific implementation, the above units may be implemented as independent entities, or may be combined arbitrarily to be implemented as the same or several entities, and the specific implementation of the above units may refer to the foregoing method embodiments, which are not described herein again.
According to the above description, the apparatus for evaluating a ligand binding site of a complex provided in the embodiments of the present application binds a target ligand to a plurality of candidate binding sites in a target protein through the binding unit 301, respectively, to obtain a candidate complex conformation corresponding to each candidate binding site; the obtaining unit 302 obtains information on a distance between each atom of the target protein and each atom of the target ligand in each candidate complex conformation; the first determining unit 303 determines binding strength information of the target protein and the target ligand in each candidate complex conformation based on the distance information; the second determination unit 304 determines the target binding site based on the binding strength information.
Therefore, the method for evaluating the ligand binding position of the complex provided by the application can calculate the binding strength of the protein and the ligand in the complex according to the distance information between the protein atom and the ligand atom in the complex, and then determine the optimal binding position of the ligand according to the different binding strengths corresponding to the different positions where the ligand is docked. Namely, the method can accurately calculate the binding strength corresponding to different complex conformations obtained after the ligand is bound to different binding positions of the protein, and then determine the optimal set position according to the binding strength, thereby improving the accuracy of the evaluation of the ligand binding positions in the complex.
Further, the present application provides a conformation optimization method, which can optimize the spatial position information of atoms in the ligand to obtain a more stable complex conformation. The efficiency and accuracy of conformation optimization are improved.
An embodiment of the present application further provides a computer device, where the computer device may be a terminal or a server, and as shown in fig. 7, is a schematic structural diagram of the computer device provided in the present application. Specifically, the method comprises the following steps:
the computer device may include components such as a processing unit 401 of one or more processing cores, a storage unit 402 of one or more storage media, a power module 403, and an input module 404. Those skilled in the art will appreciate that the computer device configuration illustrated in FIG. 7 does not constitute a limitation of computer devices, and may include more or fewer components than those illustrated, or some components may be combined, or a different arrangement of components. Wherein:
the processing unit 401 is a control center of the computer device, connects respective parts of the entire computer device with various interfaces and lines, and executes various functions of the computer device and processes data by running or executing software programs and/or modules stored in the storage unit 402 and calling data stored in the storage unit 402. Optionally, the processing unit 401 may include one or more processing cores; preferably, the processing unit 401 may integrate an application processor and a modem processor, wherein the application processor mainly handles operating systems, user interfaces, application programs, and the like, and the modem processor mainly handles wireless communications. It is to be understood that the above-described modem processor may not be integrated into the processing unit 401.
The storage unit 402 may be used to store software programs and modules, and the processing unit 401 executes various functional applications and data processing by operating the software programs and modules stored in the storage unit 402. The storage unit 402 may mainly include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program required by at least one function (such as a sound playing function, an image playing function, web page access, and the like), and the like; the storage data area may store data created according to use of the computer device, and the like. Further, the storage unit 402 may include high-speed random access memory, and may also include non-volatile memory, such as at least one magnetic disk storage device, flash memory device, or other volatile solid-state storage device. Accordingly, the memory unit 402 may also include a memory controller to provide the processing unit 401 access to the memory unit 402.
The computer device further comprises a power module 403 for supplying power to each component, and preferably, the power module 403 is logically connected to the processing unit 401 through a power management system, so as to implement functions of managing charging, discharging, and power consumption through the power management system. The power module 403 may also include any component of one or more dc or ac power sources, recharging systems, power failure detection circuitry, power converters or inverters, power status indicators, and the like.
The computer device may also include an input module 404, the input module 404 being operable to receive input numeric or character information and to generate keyboard, mouse, joystick, optical or trackball signal inputs related to user settings and function control.
Although not shown, the computer device may further include a display unit and the like, which are not described in detail herein. Specifically, in this embodiment, the processing unit 401 in the computer device loads the executable file corresponding to the process of one or more application programs into the storage unit 402 according to the following instructions, and the processing unit 401 runs the application programs stored in the storage unit 402, so as to implement various functions as follows:
respectively binding a target ligand to a plurality of candidate binding positions in a target protein to obtain a candidate complex conformation corresponding to each candidate binding position; obtaining distance information between each atom of the target protein and each atom of the target ligand in each candidate complex conformation; determining binding strength information of the target protein and the target ligand in each candidate complex conformation according to the distance information; the target binding location is determined based on the binding strength information.
It should be noted that the computer device provided in the embodiment of the present application and the method in the foregoing embodiment belong to the same concept, and specific implementation of the above operations may refer to the foregoing embodiment, which is not described herein again.
It will be understood by those skilled in the art that all or part of the steps of the methods of the above embodiments may be performed by instructions or by associated hardware controlled by the instructions, which may be stored in a computer readable storage medium and loaded and executed by a processor.
To this end, the embodiment of the present invention provides a computer-readable storage medium, in which a plurality of instructions are stored, and the instructions can be loaded by a processor to execute the steps in any one of the methods provided by the embodiments of the present invention. For example, the instructions may perform the steps of:
respectively binding a target ligand to a plurality of candidate binding positions in a target protein to obtain a candidate complex conformation corresponding to each candidate binding position; obtaining distance information between each atom of the target protein and each atom of the target ligand in each candidate complex conformation; determining binding strength information of the target protein and the target ligand in each candidate complex conformation according to the distance information; target binding sites are determined based on the binding strength information.
The above operations can be implemented in the foregoing embodiments, and are not described in detail herein.
Wherein the computer-readable storage medium may include: read Only Memory (ROM), random Access Memory (RAM), magnetic or optical disks, and the like.
Since the instructions stored in the computer-readable storage medium can execute the steps in any method provided by the embodiment of the present invention, the beneficial effects that can be achieved by any method provided by the embodiment of the present invention can be achieved, which are detailed in the foregoing embodiments and will not be described herein again.
According to an aspect of the application, there is provided, among other things, a computer program product or computer program comprising computer instructions stored in a storage medium. A processor of a computer device reads the computer instructions from the storage medium, and the processor executes the computer instructions to cause the computer device to perform the methods provided in the various alternative implementations of the method for ligand binding site assessment of a complex described above.
The method, the apparatus and the computer device for evaluating the ligand binding site of the complex provided by the embodiments of the present invention are described in detail above, and the principles and embodiments of the present invention are explained herein by applying specific examples, and the above description of the embodiments is only used to help understanding the method and the core concept of the present invention; meanwhile, for those skilled in the art, according to the idea of the present invention, there may be variations in the specific embodiments and the application scope, and in summary, the content of the present specification should not be construed as a limitation to the present invention.
Claims (15)
1. A method for assessing the ligand binding site of a complex, the method comprising:
respectively binding a target ligand to a plurality of candidate binding positions in a target protein to obtain a candidate complex conformation corresponding to each candidate binding position;
obtaining distance information between each atom of the target protein and each atom of the target ligand in each candidate complex conformation;
determining binding strength information for the target protein and the target ligand in each candidate complex conformation from the distance information;
determining a target binding location based on the binding strength information.
2. The method of claim 1, wherein said determining binding strength information for said target protein and said target ligand in each candidate complex conformation from said distance information comprises:
generating a ligand binding strength evaluation characteristic corresponding to each candidate complex conformation according to the distance information;
and inputting the ligand binding strength evaluation characteristics corresponding to each candidate compound conformation into a preset neural network model to obtain the output binding strength information of the target protein and the target ligand in each candidate compound conformation.
3. The method of claim 2, wherein generating the ligand binding strength assessment feature for each candidate complex conformation based on the distance information comprises:
determining a first number of first target atoms in the target protein based on combinations of different amino acids and heavy atoms;
determining a second number of second target atoms in the target ligand;
determining target distance information between each first target atom and each second target atom in the distance information;
and generating a ligand binding strength evaluation characteristic corresponding to each candidate complex conformation according to the target distance information.
4. The method of claim 3, wherein generating the ligand binding strength assessment feature corresponding to each candidate complex conformation from the target distance information comprises:
calculating a first characteristic dimension of the target distance information to obtain a first sub-ligand binding strength evaluation characteristic corresponding to each candidate compound conformation;
calculating a second characteristic dimension of the target distance information to obtain a second sub-ligand binding strength evaluation characteristic corresponding to each candidate complex conformation;
and splicing the first sub-ligand binding strength evaluation characteristic and the second sub-ligand binding strength evaluation characteristic corresponding to each candidate complex conformation to obtain the ligand binding strength evaluation characteristic corresponding to each candidate complex conformation.
5. The method of claim 2, wherein before inputting the ligand binding strength assessment feature corresponding to each candidate complex conformation into a preset neural network model and obtaining the output binding strength information of the target protein and the target ligand in each candidate complex conformation, the method further comprises:
obtaining a training sample, wherein the training sample comprises ligand binding strength evaluation characteristics corresponding to a plurality of sample complex conformations and binding strength information corresponding to each sample complex conformation;
and training a preset neural network model by taking the ligand binding strength evaluation characteristics corresponding to the sample complex conformations as input and taking the binding strength information corresponding to each sample complex conformation as output.
6. The method of claim 5, wherein obtaining a training sample comprising ligand binding strength assessment features corresponding to a plurality of sample complex conformations and binding strength information corresponding to each sample complex conformation comprises:
obtaining a first number of sample complexes;
re-docking the ligands in each sample complex to obtain a second number of sample complex conformations;
calculating the binding strength information corresponding to the conformation of each sample complex;
obtaining sample distance information between protein atoms and ligand atoms in the conformation of each sample complex;
and generating a ligand binding strength evaluation characteristic corresponding to each sample complex conformation according to the sample distance information, wherein the ligand binding strength evaluation characteristic corresponding to each sample complex conformation and the binding strength information corresponding to each sample complex conformation form a training sample.
7. The method of claim 1, wherein said determining a target binding location based on said binding strength information comprises:
determining a target complex conformation among the candidate complex conformations according to the binding strength information;
and determining the binding position corresponding to the target complex conformation as the target binding position.
8. The method of claim 7, further comprising:
obtaining a spatial signature of a target ligand in the conformation of the target complex, the spatial signature comprising a variable parameter characterizing the spatial position of each atom in the target ligand;
adjusting the spatial characteristics based on the binding strength information of the protein and the ligand in the target complex conformation to obtain target spatial characteristics;
determining the spatial position of each atom of the target ligand in the conformation of the target complex from the spatial features of interest.
9. The method of claim 8, wherein the adjusting the spatial signature based on information on the binding strength of the protein to the ligand in the conformation of the target complex to obtain the target spatial signature comprises:
recalculating the binding strength information of the protein and the ligand in the target complex conformation based on the spatial characteristics to obtain a binding strength representation function containing the variable parameters;
processing the bonding strength representation function by adopting a gradient descent method to obtain a numerical value of each variable parameter;
and determining the target space characteristics according to the numerical value of each variable parameter.
10. A complex ligand binding site evaluation device, comprising:
the binding unit is used for respectively binding the target ligand to a plurality of candidate binding positions in the target protein to obtain a candidate complex conformation corresponding to each candidate binding position;
an obtaining unit for obtaining information on a distance between each atom of the target protein and each atom of the target ligand in each candidate complex conformation;
a first determining unit for determining binding strength information of the target protein and the target ligand in each candidate complex conformation based on the distance information;
a second determination unit for determining a target binding location based on the binding strength information.
11. The apparatus of claim 10, wherein the first determining unit comprises:
a generating subunit, configured to generate, according to the distance information, a ligand binding strength evaluation feature corresponding to each candidate complex conformation;
and the evaluation subunit is used for inputting the ligand binding strength evaluation characteristics corresponding to each candidate complex conformation into a preset neural network model to obtain the output binding strength information of the target protein and the target ligand in each candidate complex conformation.
12. The apparatus of claim 11, wherein the generating subunit comprises:
a first determination module for determining a first number of first target atoms in the target protein based on combinations of different amino acids and heavy atoms;
a second determination module for determining a second number of second target atoms in the target ligand;
a third determining module, configured to determine, in the distance information, target distance information between each first target atom and each second target atom;
and the generating module is used for generating a ligand binding strength evaluation characteristic corresponding to each candidate complex conformation according to the target distance information.
13. The apparatus of claim 12, wherein the generating module comprises:
the first calculation submodule is used for calculating a first characteristic dimension of the target distance information to obtain a first sub-ligand binding strength evaluation characteristic corresponding to each candidate compound conformation;
the second calculation submodule is used for calculating a second characteristic dimension of the target distance information to obtain a second sub-ligand binding strength evaluation characteristic corresponding to each candidate compound conformation;
and the splicing submodule is used for splicing the first sub-ligand binding strength evaluation characteristic and the second sub-ligand binding strength evaluation characteristic corresponding to each candidate compound conformation to obtain the ligand binding strength evaluation characteristic corresponding to each candidate compound conformation.
14. A computer readable storage medium storing a plurality of instructions adapted to be loaded by a processor to perform the steps of the method for assessing a ligand binding site of a complex according to any one of claims 1 to 9.
15. A computer device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, the processor implementing the steps in the method for assessing the ligand binding site of a complex according to any one of claims 1 to 9 when executing the computer program.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210092867.9A CN115910234A (en) | 2022-01-26 | 2022-01-26 | Complex ligand binding position evaluation method, complex ligand binding position evaluation device and computer equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210092867.9A CN115910234A (en) | 2022-01-26 | 2022-01-26 | Complex ligand binding position evaluation method, complex ligand binding position evaluation device and computer equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115910234A true CN115910234A (en) | 2023-04-04 |
Family
ID=86482924
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210092867.9A Pending CN115910234A (en) | 2022-01-26 | 2022-01-26 | Complex ligand binding position evaluation method, complex ligand binding position evaluation device and computer equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115910234A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116453587A (en) * | 2023-06-15 | 2023-07-18 | 之江实验室 | Task execution method and device, storage medium and electronic equipment |
-
2022
- 2022-01-26 CN CN202210092867.9A patent/CN115910234A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116453587A (en) * | 2023-06-15 | 2023-07-18 | 之江实验室 | Task execution method and device, storage medium and electronic equipment |
| CN116453587B (en) * | 2023-06-15 | 2023-08-29 | 之江实验室 | Task execution method for predicting ligand affinity based on molecular dynamics model |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Agrawal et al. | Benchmarking of different molecular docking methods for protein-peptide docking | |
| Coleman et al. | Analysis of dawnbench, a time-to-accuracy machine learning performance benchmark | |
| Wang et al. | Protein docking model evaluation by 3D deep convolutional neural networks | |
| Stepniewska-Dziubinska et al. | Improving detection of protein-ligand binding sites with 3D segmentation | |
| Havranek et al. | Tanford–Kirkwood electrostatics for protein modeling | |
| WO2021082753A1 (en) | Method, device and apparatus for predicting protein structure information, and storage medium | |
| Chen et al. | LigandRFs: random forest ensemble to identify ligand-binding residues from sequence information alone | |
| Li et al. | DelPhiForce, a tool for electrostatic force calculations: Applications to macromolecular binding | |
| CN111298445A (en) | Target account detection method and device, electronic equipment and storage medium | |
| JP2019507398A (en) | Collaborative filtering method, apparatus, server, and storage medium for fusing time factors | |
| Wang et al. | A fully differentiable ligand pose optimization framework guided by deep learning and a traditional scoring function | |
| Zhang et al. | A fast mathematical programming procedure for simultaneous fitting of assembly components into cryoEM density maps | |
| WO2019190625A1 (en) | Relative density-based clustering and anomaly detection system | |
| Chen et al. | Prediction of midbody, centrosome and kinetochore proteins based on gene ontology information | |
| Clark et al. | Predicting binding sites from unbound versus bound protein structures | |
| CN115910234A (en) | Complex ligand binding position evaluation method, complex ligand binding position evaluation device and computer equipment | |
| Hanke et al. | Prediction of protein retention times in hydrophobic interaction chromatography by robust statistical characterization of their atomic‐level surface properties | |
| CN110207643B (en) | Folding angle detection method and device, terminal and storage medium | |
| CN115527607A (en) | Method for predicting and processing combination posture of drug molecule and protein target | |
| US20210064982A1 (en) | Cross-domain homophily quanitifcation for transfer learning | |
| Köfinger et al. | Inferring structural ensembles of flexible and dynamic macromolecules using Bayesian, maximum entropy, and minimal-ensemble refinement methods | |
| US11797769B1 (en) | Artificial intelligence system using hybrid technique for task-oriented dialog management | |
| CN116825236A (en) | Method, device, equipment and medium for generating drug molecules of protein targets | |
| Pagès et al. | DeepSymmetry: using 3D convolutional networks for identification of tandem repeats and internal symmetries in protein structures | |
| WO2023131206A1 (en) | Method and apparatus for evaluating bonding strength of complex, and computer device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |