Prediction method and device of compound structure, model training method and device and electronic equipment

Abstract

The invention discloses a prediction method and device of a compound structure, a model training method and device and electronic equipment, and relates to the technical field of artificial intelligence, in particular to the technical fields of deep learning, biological calculation and the like. According to the specific implementation scheme, the method comprises the steps of obtaining an amino acid sequence of a receptor, sequence information of a to-be-bound ligand and a protein structure of the receptor, determining azimuth information of the ligand relative to the protein structure based on the protein structure of the receptor, and obtaining the to-be-bound ligand according to the azimuth information of the ligand relative to the protein structure, the amino acid sequence of the receptor and the sequence information of the ligand. And determining the structure of a target compound combined with the receptor and the ligand.

Description

Technical Field

[0001] The present application relates to the field of artificial intelligence technology, specifically to technical fields such as deep learning and biocomputing, and in particular to a method for predicting a complex structure, a model training method, a device and an electronic device. Background Art

[0002] As a macromolecular compound that supports the operation of almost all cells, proteins play an important role in different biological fields, such as enzyme reactions, cell signal transduction, metabolic regulation, and gene expression. Among them, the technology of predicting the three-dimensional structure (tertiary structure) of proteins in space based on the amino acid category (primary structure) of the protein chain has extremely high research value in the field of life sciences. For example, in the scenario of new drug discovery, R&D personnel need to find ligands (peptides, small molecules, etc.) for receptors. The binding mode / docking interface structure of receptors and ligands can provide useful auxiliary information for receptor-related drug research.

[0003] Therefore, it is very important to accurately predict the complex structure of receptor and ligand binding. Summary of the invention

[0004] The present application provides a method for predicting a complex structure, a model training method, a device and an electronic device.

[0005] According to one aspect of the present application, a method for predicting a complex structure is provided, comprising:

[0006] Obtaining the amino acid sequence of the receptor and the sequence information of the ligand to be bound, as well as the protein structure of the receptor;

[0007] Based on the protein structure of the receptor, determining the position information of the ligand relative to the protein structure;

[0008] The target complex structure of the receptor and the ligand is determined based on the position information of the ligand relative to the protein structure, the amino acid sequence of the receptor and the sequence information of the ligand.

[0009] According to another aspect of the present application, a model training method is provided, comprising:

[0010] Acquire a training sample, wherein the training sample includes the amino acid sequence of the receptor and the sequence information of the ligand to be bound, and the position information of the ligand relative to the protein structure of the receptor;

[0011] Inputting the training sample into a structure prediction model to obtain a predicted complex structure of the receptor and the ligand;

[0012] Determining a loss function of the structure prediction model according to a difference between the predicted complex structure and the target complex structure annotated by the training sample;

[0013] The structure prediction model is trained according to the loss function to obtain the trained structure prediction model.

[0014] According to one aspect of the present application, a device for predicting a complex structure is provided, comprising:

[0015] An acquisition module, used to acquire the amino acid sequence of the receptor and the sequence information of the ligand to be bound, as well as the protein structure of the receptor;

[0016] A determination module, used for determining the position information of the ligand relative to the protein structure based on the protein structure of the receptor;

[0017] The prediction module is used to determine the target complex structure of the receptor and the ligand based on the position information of the ligand relative to the protein structure, the amino acid sequence of the receptor and the sequence information of the ligand.

[0018] According to another aspect of the present application, a model training device is provided, comprising:

[0019] An acquisition module, used to acquire a training sample, wherein the training sample includes the amino acid sequence of the receptor and the sequence information of the ligand to be bound, and the position information of the ligand relative to the protein structure of the receptor;

[0020] A prediction module, used for inputting the training sample into a structure prediction model to obtain a predicted complex structure of the receptor and the ligand;

[0021] A determination module, configured to determine a loss function of the structure prediction model according to a difference between the predicted complex structure and the target complex structure annotated by the training sample;

[0022] A training module is used to train the structure prediction model according to the loss function to obtain the trained structure prediction model.

[0023] According to another aspect of the present application, there is provided an electronic device, including:

[0024] at least one processor; and

[0025] a memory communicatively connected to the at least one processor; wherein,

[0026] The memory stores instructions that can be executed by the at least one processor. The instructions are executed by the at least one processor so that the at least one processor can perform the method described in the above embodiment.

[0027] According to another aspect of the present application, a non-transitory computer-readable storage medium storing computer instructions is provided, wherein the computer instructions are used to enable the computer to execute the method according to the above embodiment.

[0028] According to another aspect of the present application, a computer program product is provided, including a computer program, wherein the computer program implements the steps of the method described in the above embodiment when executed by a processor.

[0029] It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present application, nor is it intended to limit the scope of the present application. Other features of the present application will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] The accompanying drawings are used to better understand the present solution and do not constitute a limitation of the present application.

[0031] Figure 1 A schematic diagram of a method for predicting a complex structure provided in an embodiment of the present application;

[0032] Figure 2 A schematic diagram of another method for predicting the structure of a complex provided in an embodiment of the present application;

[0033] Figure 3 A schematic diagram of another method for predicting the structure of a complex provided in an embodiment of the present application;

[0034] Figure 4 A schematic diagram of another method for predicting the structure of a complex provided in an embodiment of the present application;

[0035] Figure 5 A schematic diagram of determining the position of a ligand provided in an embodiment of the present application;

[0036] Figure 6 A schematic diagram of another method for predicting the structure of a complex provided in an embodiment of the present application;

[0037] Figure 7 A schematic diagram of a structure prediction model provided in an embodiment of the present application;

[0038] Figure 8 A flowchart of a model training method provided in an embodiment of the present application;

[0039] Fig. 9A schematic diagram of the structure of a composite structure prediction device provided in one embodiment of the present application;

[0040] Fig.10 A schematic diagram of a model training device provided in an embodiment of the present application

[0041] Fig.11 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0042] The following is a description of exemplary embodiments of the present application in conjunction with the accompanying drawings, including various details of the embodiments of the present application to facilitate understanding, which should be considered as merely exemplary. Therefore, it should be recognized by those of ordinary skill in the art that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of the present application. Similarly, for the sake of clarity and conciseness, the description of well-known functions and structures is omitted in the following description.

[0043] In related technologies, protein structure prediction methods based on artificial intelligence (AI) models, such as the AI ​​program AlphaFold, are gradually approaching experimental observations. Starting from the sequence information of receptors and ligands, the model directly predicts the structure of the complex of receptor and ligand binding, which is also called the binding conformation. However, protein complexes with the same sequence in nature can have different structures. For example, Figure 1 As shown in the middle left figure, chain A of protein 7eid can bind to two ligands, C or D. The two ligands are peptide chains, and the amino acid sequences of peptide chain C and peptide chain D are exactly the same, both of which are: KGGKGLGKGG. The left figure shows the real complex structure of chain A binding to peptide chain C and peptide chain D, that is, the real binding conformation of ACD. If the model input only considers sequence information, it is difficult for the model to distinguish the binding mode of chain AC and chain AD of 7eid sample. For example, the model input is the sequence information of chain A and chain C. Figure 1 As shown in the middle right figure, the predicted AC-bound complex structure is quite different from the actual result in the left figure, resulting in poor prediction accuracy.

[0044] In response to the above problems, the present application proposes a composite structure prediction method, a model training method, a device and an electronic device.

[0045] The following describes the composite structure prediction method, model training method, device and electronic device of the embodiments of the present application with reference to the accompanying drawings.

[0046] It should be noted that in the technical solution of this application, the collection, storage, use, processing, transmission, provision and disclosure of user personal information involved are all carried out with the user's consent, and are in compliance with relevant laws and regulations and do not violate public order and good morals.

[0047] Figure 2 A schematic diagram of a process for predicting a complex structure provided in an embodiment of the present application.

[0048] The method for predicting the structure of a composite material according to an embodiment of the present application may be performed by a device for predicting the structure of a composite material according to an embodiment of the present application. The device may be configured in an electronic device to achieve prediction of the structure of the composite material.

[0049] Among them, the electronic device can be any device with computing capabilities, such as a personal computer, a mobile terminal, a server, etc. The mobile terminal can be, for example, a vehicle-mounted device, a mobile phone, a tablet computer, a personal digital assistant, a wearable device, and other hardware devices with various operating systems, touch screens and / or display screens.

[0050] like Figure 2 As shown, the method comprises the following steps:

[0051] Step 201, obtaining the amino acid sequence of the receptor and the sequence information of the ligand to be bound, as well as the protein structure of the receptor.

[0052] Among them, the receptor is a macromolecular compound, usually a protein. Receptors include small molecules and polypeptides. The amino acid sequence of the receptor is usually a long chain composed of multiple amino acids, which is the primary structure. The protein structure of the receptor is the tertiary structure. Among them, the ligand to be bound can bind to the receptor to obtain a composite three-dimensional structure of the receptor and the ligand, also known as the binding conformation.

[0053] Among them, the amino acid sequence can be obtained from an existing test set, or the amino acid sequence can also be collected online, for example, by using web crawler technology, or the amino acid sequence can also be provided by the user, which is not limited in the embodiments of the present application.

[0054] The sequence information of the ligand includes the small molecule information when the ligand is a small molecule, and the small molecule information includes a series of sequence data describing the structure, properties and functions of the small molecule. When the ligand is a peptide chain, the sequence information of the ligand includes the amino acid sequence of the peptide chain.

[0055] Among them, as an implementation method, the protein structure of the receptor can be predicted using the artificial intelligence program AlphaFold in the related art, wherein AlphaFold has a high accuracy in predicting the three-dimensional structure of a single substance, so the amino acid sequence of the receptor is input into the trained AlphaFold model, and the predicted protein structure of the receptor is input. As another implementation method, if the true protein structure of the receptor is a known structure, it can be directly obtained from the stored database.

[0056] Step 202, based on the protein structure of the receptor, determine the position information of the ligand relative to the protein structure.

[0057] In one implementation of an embodiment of the present application, prediction based on sequence data has poor accuracy, and thus, on the protein structure of the receptor, the orientation information of the ligand relative to the protein structure when the ligand binds to the receptor is determined, wherein the orientation information includes the position region of the ligand and the direction information of the position region, which can indicate the spatial position and direction of the ligand when the ligand binds to the protein of the receptor, thereby realizing the positioning of the ligand.

[0058] Step 203, determining the target complex structure of the receptor and the ligand based on the position information of the ligand relative to the protein structure, the amino acid sequence of the receptor and the sequence information of the ligand.

[0059] In the embodiments of the present application, the amino acid sequence of the receptor and the sequence information of the ligand provide the sequence information of the receptor and the ligand. Based on the sequence information, the possible binding position and binding structure information when the receptor and the ligand bind can be determined. However, since the same sequence corresponds to different structures, in order to improve the accuracy, the present application provides the orientation information of the ligand when the ligand and receptor bind, and provides the initial spatial position and structural information of the ligand and receptor binding, and then continuously performs structural corrections based on the above sequence information and orientation information to obtain the final predicted target complex structure, thereby improving the accuracy of the prediction.

[0060] In the method for predicting the structure of the complex of the embodiment of the present application, the amino acid sequence of the receptor and the sequence information of the ligand to be bound, as well as the protein structure of the receptor are obtained, and based on the protein structure of the receptor, the position information of the ligand relative to the protein structure is determined, and the target complex structure of the receptor and the ligand is determined according to the position information of the ligand relative to the protein structure, the amino acid sequence of the receptor and the sequence information of the ligand. By providing the position information of the ligand relative to the receptor when the ligand and the receptor are bound, the different structures of the complexes with the same sequence in nature can be better distinguished, thereby improving the effect of predicting the structure of the complex.

[0061] Based on the above embodiments, Figure 3 A schematic diagram of another method for predicting the structure of a complex provided in an embodiment of the present application is shown in FIG. Figure 3 As shown, the method comprises the following steps:

[0062] Step 301, obtaining the amino acid sequence of the receptor and the sequence information of the ligand to be bound, as well as the protein structure of the receptor.

[0063] Step 302, based on the protein structure of the receptor, determine the position information of the ligand relative to the protein structure.

[0064] Among them, step 301 and step 302 can refer to the explanation in the above-mentioned embodiment, and the principles are the same, so they will not be repeated here.

[0065] Step 303, determining the initial complex structure of the receptor and ligand based on the position information of the ligand relative to the protein structure.

[0066] In an embodiment of the present application, the positional information of the ligand includes the spatial relative position relationship between the ligand and the receptor when they are bound. By determining the protein structure of the receptor and the positional information of the ligand when the ligand and the receptor are bound, the initial complex structure of the receptor and the complex can be determined, which indicates the initial conformation of the ligand and receptor binding.

[0067] Step 304, determining the target complex structure of the receptor and the ligand based on the initial complex structure, the amino acid sequence of the receptor and the sequence information of the ligand.

[0068] In the embodiments of the present application, the initial complex structure of ligand and receptor binding is provided in the present application, and the initial spatial position and structural information of the ligand and receptor binding are provided, and then continuous structural corrections are performed based on the above-mentioned sequence information and initial structural information to obtain the final predicted target complex structure, so as to achieve the distinction of complex structures with the same sequence but different structures in nature based on the initial complex structure, thereby improving the accuracy of complex prediction.

[0069] In the method for predicting the structure of the complex of the embodiment of the present application, the amino acid sequence of the receptor and the sequence information of the ligand to be bound, as well as the protein structure of the receptor are obtained, and the orientation information of the ligand relative to the protein structure is determined based on the protein structure of the receptor, and the target complex structure of the receptor and the ligand binding is determined according to the orientation information of the ligand relative to the protein structure, the amino acid sequence of the receptor and the sequence information of the ligand. By providing the orientation information of the ligand relative to the receptor when the ligand and the receptor bind, the initial spatial position relationship of the ligand and the receptor binding is indicated, and prediction based on the orientation information and sequence information can better distinguish ligands with the same sequence but different structures in nature, as well as complex structures with the same sequence but different structures, thereby improving the accuracy of the target complex structure finally predicted.

[0070] Based on the above embodiments, Figure 4 A schematic diagram of another method for predicting the structure of a complex provided in an embodiment of the present application is shown in FIG. Figure 4 As shown, the method comprises the following steps:

[0071] Step 401, obtaining the amino acid sequence of the receptor and the sequence information of the ligand to be bound, as well as the protein structure of the receptor.

[0072] Among them, step 401 can refer to the explanation in the above-mentioned embodiment, and the principle is the same, which will not be repeated here.

[0073] Step 402: display the protein structure on an interactive interface of an electronic device.

[0074] In an embodiment of the present application, a protein structure is displayed on an interactive interface of an electronic device to interactively determine the position information of a ligand associated with the protein structure set.

[0075] Step 403, determining the binding position on the protein structure according to the detected first instruction.

[0076] Among them, the first instruction can be generated during the interaction between the interactive device and the electronic device, for example, the interactive device is a mouse or a touch screen, or the first instruction is implemented through an operation in the interactive interface of the electronic device, such as a click operation. The first instruction is used to determine the binding position of the ligand and the receptor protein when they bind, also known as the binding site.

[0077] Step 404: Determine the position region of the ligand in space and the direction information of the position region according to the detected second instruction and the binding position.

[0078] Similarly, the second instruction can refer to the description of the first instruction, which will not be repeated in this embodiment. The second instruction is used to draw with the binding position as the starting point to determine the position area of ​​the ligand and the direction information of the position area in the space around the protein structure.

[0079] Through interaction, prior knowledge can be obtained, such as the expert experience of drug developers, to determine the approximate position information of the ligand based on the protein structure. By providing the relative position information of the receptor and the ligand, it is possible to provide information such as the position and direction of the ligand when predicting the composite structure based on the sequence information, thereby improving the accuracy of the prediction.

[0080] As an example, Figure 5 A schematic diagram of determining the position of a ligand provided in an embodiment of the present application is shown in FIG. Figure 5 As shown, the receptor is chain A of protein 7eid, and the ligand can be peptide chain C or peptide chain D, wherein the amino acid sequences of peptide chain C and peptide chain D are completely identical. Figure 5 As shown, the binding site determined on chain A for binding to peptide chain C, as well as the position region and direction information of the position region of peptide chain C, and the binding site determined on chain A for binding to peptide chain D, as well as the position region and direction information of the position region of peptide chain D are shown. Figure 5It can be seen that although the amino acid sequences of peptide chain C and peptide chain D are consistent, the binding orientation information, that is, the relative position information, is not the same, that is, the position and direction of the ligand are different, so as to realize the identification of different ligands or sequence information of complexes in nature according to the orientation information of the added ligand, so as to improve the accuracy of model prediction.

[0081] Step 405: determining the initial three-dimensional position of each atom of the ligand in the position region according to the position region and the direction information of the position region.

[0082] Step 406, obtaining an initial complex structure according to the protein structure of the receptor and the initial three-dimensional positions of each atom of the ligand.

[0083] In an embodiment of the present application, based on the position region and the directional information of the position region, the three-dimensional coordinate interval range of the position region corresponding to the binding of the ligand and the receptor can be determined, and then, the initial three-dimensional positions of the atoms included in the ligand are initialized in the position region where the ligand is located according to a random algorithm, so as to further determine the positions of the atoms of the ligand from the region, so as to accurately obtain the initial complex structure of the ligand and the receptor assembly, so as to provide accurate spatial structure information.

[0084] Step 407: Perform a local transformation on the initial composite structure to obtain a first composite structure.

[0085] In the embodiment of the present application, the first composite structure is obtained by locally transforming the initial composite structure, thereby realizing local noise addition to the composite structure. Local loading enables the first composite structure to carry more original structural information, thereby improving the accuracy of subsequent model predictions. This can be achieved in the following ways:

[0086] In one implementation of the embodiment of the present application, the target atom in the initial complex structure is randomly determined, and the target atom can be a target atom in the atoms of the ligand, that is, the target atom is a part of all the atoms of the ligand; or a target atom including atoms in the ligand and the receptor, that is, the target atom refers to a part of all the atoms included in the ligand and the receptor. Then, the target atom is shifted in position, thereby achieving a change in the initial complex structure to obtain a first complex structure.

[0087] In another implementation of the embodiment of the present application, the initial composite structure is twisted, thereby achieving a change in the initial composite structure to obtain a first composite structure.

[0088] In another implementation of the embodiment of the present application, the initial composite structure is rotated, thereby changing the initial composite structure to obtain a first composite structure.

[0089] Step 408: Using a structure prediction model, the target complex structure of the receptor and the ligand is determined based on the structure of the first complex, the amino acid sequence of the receptor, and the sequence information of the ligand.

[0090] Among them, the structure prediction model, such as the various models of the artificial intelligence program AlphaFold, is not limited in this embodiment.

[0091] In the embodiments of the present application, a structure prediction model is used to predict and continuously correct the three-dimensional position of each atom in the complex structure based on the first complex structure, the amino acid sequence of the receptor and the sequence information of the ligand to determine the target complex structure of the receptor and the ligand, thereby improving accuracy.

[0092] The method for predicting the structure of the complex of the embodiment of the present application can determine the three-dimensional coordinate interval range of the position area corresponding to the binding of the ligand and the receptor according to the position area of ​​the ligand and the direction information of the position area determined based on prior experience, and then, initialize the initial three-dimensional position of each atom included in the ligand in the position area where the ligand is located according to the random algorithm, and further determine the position of the atoms of the ligand from the area to accurately obtain the initial complex structure of the ligand and receptor set, so as to provide accurate spatial structure information. Furthermore, by locally transforming the initial complex structure to obtain the first complex structure, the local noise addition of the complex structure is realized, and the local loading makes the first complex structure carry more original structure information, which can improve the accuracy of subsequent model prediction.

[0093] Based on the above embodiments, Figure 6 A schematic diagram of another method for predicting the structure of a complex provided in an embodiment of the present application is shown in FIG. Figure 6 As shown, the method comprises the following steps:

[0094] Step 601, obtaining the amino acid sequence of the receptor and the sequence information of the ligand to be bound, as well as the protein structure of the receptor.

[0095] Step 602, based on the protein structure of the receptor, determine the position information of the ligand relative to the protein structure.

[0096] Step 603, determining the initial complex structure of the receptor and ligand based on the position information of the ligand relative to the protein structure.

[0097] Step 604: perform local transformation on the initial composite structure to obtain a first composite structure.

[0098] Among them, steps 601 to 604 can refer to the relevant explanations in the aforementioned embodiments, and the principles are the same, so they will not be repeated here.

[0099] Step 605, using the encoding network in the structure prediction model, encodes the amino acid sequence of the receptor and the sequence information of the ligand to be bound to obtain a fusion encoding feature.

[0100] Here, the encoding network refers to a network that can encode the sequence information of amino acid sequences and ligands, such as the encoding network of AlphaFold.

[0101] As an example, Figure 7 As shown in the figure, the ligand is a small molecule. In order to increase the amount of input information, the input data includes the amino acid sequence of the receptor and the sequence information of the small molecule, and can also include covalent information. First, the amino acid sequence (Genetic search) and structural template (Template search) of the receptor protein are searched in the gene database and the structure database, and the reference conformation information Conformer generation is obtained according to the small molecule ligand search. Then, the amino acid sequence, structural template, reference conformation, covalent information, etc. are input into the input embedder Input embedder, template module Template module, multiple sequence alignment (Multiple Sequence Alignment, MSA) module and other modules in the encoding network in a sequence manner, and finally the fused encoding features are obtained through the 48-layer pairwise relationship processing Pairforme module.

[0102] Among them, the fused coding features include original sequence features, first coding features and second coding features, wherein the first coding features carry distance information, relative position coding information, etc. between atoms, and the second coding features are obtained by splicing and encoding multiple input sequences, and carry topological features, geometric features, interaction features, binding features, functional features, etc. between atoms.

[0103] Step 606, using the decoding network in the structure prediction model, performing a set number of iterations according to the first complex structure and the fused encoding features to update the complex structure of the receptor and ligand binding.

[0104] In the embodiment of the present application, the decoding network is also called a diffusion module. During the iterative process of setting the number of rounds, the inputs of different rounds of iteration may be different, as described below:

[0105] In the embodiment of the present application, for the first round of iteration in the set number of iterations, the iteration process includes:

[0106] The first complex structure and the fused coding features are input into the decoding network for decoding to obtain the complex structure of the receptor and the ligand bound by the first round of iterative update. Specifically, the first complex structure and the fused coding features are input into the decoding network for decoding, and the decoding network predicts the predicted positions of each atom included in the first complex structure based on the input features, that is, the first complex structure is denoised by the atomic position prediction to correct the first complex structure and obtain an updated complex result.

[0107] Any iteration process after the first iteration is a non-first iteration process, including:

[0108] The complex structure of the receptor and ligand binding updated in the previous iteration of this iteration is obtained. According to the complex structure of the receptor and ligand binding updated in the previous iteration of this iteration and the fusion coding features, it is input into the decoding network for decoding to obtain the complex structure of the receptor and ligand binding updated in this iteration. Through non-first iterations, further noise removal is performed to correct the first complex structure and obtain the updated complex result, so that the prediction result is closer to the real result.

[0109] The number of rounds may be determined based on demand and is not limited in this embodiment.

[0110] It should be noted that Figure 7 The confidence module in is used to score the multiple complex structures predicted in each round to determine the complex structure with the highest score as the prediction result of each round.

[0111] Step 607: The complex structure of the receptor and ligand bound obtained in the last round of iterative updating is used as the target complex structure of the receptor and ligand bound.

[0112] In the embodiments of the present application, multiple rounds of iterations are performed on the structure prediction model to achieve gradual noise reduction, so as to continuously correct the structure of the complex and complete the final prediction of the structure of the complex. The initial complex structure of the complex is determined by the orientation information of the provided ligand, which not only carries the binding position information of the ligand, but also carries more detailed information such as the shape, extension direction and area of ​​the ligand, so that an accurate complex structure can be predicted during the prediction process.

[0113] The method for predicting the complex structure of the embodiment of the present application performs multiple rounds of iterations of the structure prediction model to achieve gradual noise reduction, so as to continuously correct the complex structure and complete the final prediction of the complex structure. The initial complex structure of the complex is determined by the orientation information of the provided ligand, which not only carries the binding position information of the ligand, but also carries more detailed information such as the shape, extension direction and area of ​​the ligand, so that an accurate complex structure can be predicted during the prediction process.

[0114] Based on the above embodiments, Figure 8 A flow chart of a model training method provided in an embodiment of the present application is shown in FIG. Figure 8 As shown, the method comprises the following steps:

[0115] Step 801: Acquire a training sample, wherein the training sample includes the amino acid sequence of the receptor and the sequence information of the ligand to be bound, and the position information of the ligand relative to the protein structure of the receptor.

[0116] As an implementation method, the position information of the ligand relative to the protein structure of the receptor can be added based on interaction. For details, please refer to the relevant explanations in the above embodiments. The principles are the same and will not be repeated here.

[0117] As another implementation, the position information of the ligand relative to the protein structure of the receptor in the training sample can also be obtained by locally transforming the structure of the ligand in the existing complex structure of the ligand and receptor, for example, by determining through position shift.

[0118] During the training process of the present application, multiple samples may be used for training, and the training samples may include the above-mentioned two samples to increase the form of samples and improve the efficiency of sample generation.

[0119] Step 802: input the training sample into the structure prediction model to obtain the predicted complex structure of the receptor and the ligand.

[0120] Among them, the model structure and the principle of prediction can refer to the relevant explanations in the aforementioned embodiments. The principles are the same and will not be repeated here.

[0121] Step 803: Determine the loss function of the structure prediction model according to the difference between the predicted complex structure and the target complex structure annotated by the training sample.

[0122] In one implementation of the embodiment of the present application, the difference between the predicted complex structure and the target complex structure can be determined by determining the loss function based on the difference between the predicted position of each atom in the predicted complex structure and the actual position of each atom in the target complex structure.

[0123] Step 804: train the structure prediction model according to the loss function to obtain a trained structure prediction model.

[0124] In the embodiment of the present application, the parameters of the structure prediction model are adjusted according to the loss function to obtain the trained structure prediction model.

[0125] It should be noted that the aforementioned steps 801 to 804 need to be repeated multiple times, and different training samples can be used each time, so that the training is stopped when the loss function is less than the threshold, or the training is stopped when the number of repeated executions is greater than the threshold. The structure prediction model obtained after the last model parameter adjustment is used as the trained structure prediction model.

[0126] In the model training method of the embodiment of the present application, compared with the method of only considering sequence information in the related art, the present application can better distinguish different structures of the same sequence complexes in nature by providing the orientation information of the ligand relative to the receptor when the ligand and the receptor bind. Through model training, the trained model can distinguish substances with the same sequence in nature, thereby improving the prediction effect and accuracy of the complex structure.

[0127] In order to implement the above embodiment, the present application also provides a device for predicting the structure of a composite material. Fig. 9 A schematic diagram of the structure of a complex structure prediction device provided in one embodiment of the present application.

[0128] like Fig. 9 As shown, the device comprises:

[0129] The acquisition module 91 is used to acquire the amino acid sequence of the receptor and the sequence information of the ligand to be bound, as well as the protein structure of the receptor.

[0130] The determination module 92 is used to determine the position information of the ligand relative to the protein structure based on the protein structure of the receptor.

[0131] The prediction module 93 is used to determine the target complex structure of the receptor and the ligand based on the position information of the ligand relative to the protein structure, the amino acid sequence of the receptor and the sequence information of the ligand.

[0132] Furthermore, in one implementation of the embodiment of the present application, the prediction module 93 is further configured to:

[0133] Determining the initial complex structure of the receptor and the ligand based on the position information of the ligand relative to the protein structure;

[0134] The target complex structure of the receptor and the ligand is determined based on the initial complex structure, the amino acid sequence of the receptor and the sequence information of the ligand.

[0135] In one implementation of the embodiment of the present application, the determination module 92 is further configured to:

[0136] Displaying the protein structure on an interactive interface of an electronic device;

[0137] Determining a binding position on the protein structure based on the detected first instruction;

[0138] According to the detected second instruction and the binding position, the position region of the ligand in space and the direction information of the position region are determined.

[0139] In one implementation of the embodiment of the present application, the prediction module 93 is further configured to:

[0140] Determining the initial three-dimensional position of each atom of the ligand in the position region according to the position region and the direction information of the position region;

[0141] The initial complex structure is obtained based on the protein structure of the receptor and the initial three-dimensional positions of each atom of the ligand.

[0142] In one implementation of the embodiment of the present application, the prediction module 93 is further configured to:

[0143] Performing a local transformation on the initial complex structure to obtain a first complex structure;

[0144] A structure prediction model is used to determine the target complex structure of the receptor and the ligand based on the first complex structure, the amino acid sequence of the receptor and the sequence information of the ligand.

[0145] In one implementation of the embodiment of the present application, the prediction module 93 is further configured to:

[0146] Using the encoding network in the structure prediction model, the amino acid sequence of the receptor and the sequence information of the ligand to be bound are encoded to obtain a fusion encoding feature;

[0147] Using a decoding network in the structure prediction model, a set number of iterations are performed according to the first composite structure and the fusion coding feature to update the structure of the complex bound by the receptor and the ligand;

[0148] The complex structure of the receptor and the ligand obtained in the last round of iterative updating is used as the target complex structure of the receptor and the ligand.

[0149] In one implementation of the embodiment of the present application, the first round of iterations in the set number of iterations includes:

[0150] The first complex structure and the fusion coding feature are input into the decoding network for decoding to obtain the complex structure of the receptor and the ligand obtained by the first round of iterative update.

[0151] In one implementation of the embodiment of the present application, the non-first round of iterations in the set number of iterations includes:

[0152] Obtaining a complex structure of the receptor and the ligand that is updated in a previous iteration of this iteration;

[0153] According to the complex structure of the receptor and the ligand combined that was updated in the previous round of iteration and the fusion coding feature, the complex structure of the receptor and the ligand combined that was updated in the current round of iteration is input into the decoding network for decoding to obtain the complex structure of the receptor and the ligand combined that was updated in the current round of iteration.

[0154] It should be noted that the explanation of the aforementioned method embodiment is also applicable to the device of this embodiment, so it will not be repeated here.

[0155] In the prediction device of the complex structure of the embodiment of the present application, the amino acid sequence of the receptor and the sequence information of the ligand to be bound, as well as the protein structure of the receptor are obtained, and the orientation information of the ligand relative to the protein structure is determined based on the protein structure of the receptor. According to the orientation information of the ligand relative to the protein structure, the amino acid sequence of the receptor and the sequence information of the ligand, the target complex structure of the receptor and the ligand binding is determined. By providing the orientation information of the ligand relative to the receptor when the ligand and the receptor bind, the initial spatial position relationship of the ligand and the receptor binding is indicated. Prediction based on the orientation information and sequence information can better distinguish substances with the same sequence but different structures in nature, and improve the accuracy of the target complex structure finally predicted. .

[0156] In order to implement the above embodiment, the embodiment of the present application also proposes a model training device.

[0157] Fig.10 A schematic diagram of the structure of a model training device provided in an embodiment of the present application.

[0158] like Fig.10 As shown, the device comprises:

[0159] The acquisition module 11 is used to acquire training samples, wherein the training samples include the amino acid sequence of the receptor and the sequence information of the ligand to be bound, and the position information of the ligand relative to the protein structure of the receptor.

[0160] The prediction module 12 is used to input the training sample into the structure prediction model to obtain the predicted complex structure of the receptor and the ligand.

[0161] The determination module 13 is used to determine the loss function of the structure prediction model according to the difference between the predicted complex structure and the target complex structure annotated by the training sample.

[0162] The training module 14 is used to train the structure prediction model according to the loss function to obtain the trained structure prediction model.

[0163] It should be noted that the explanation of the aforementioned method embodiment is also applicable to the device of this embodiment, so it will not be repeated here.

[0164] In the model training device of the embodiment of the present application, by providing the position information of the ligand relative to the receptor when the ligand and the receptor bind, it is possible to better distinguish the different structures of the same sequence complexes in nature. Through model training, the trained model can distinguish substances with the same sequence in nature, thereby improving the prediction effect and accuracy of the complex structure.

[0165] According to an embodiment of the present application, the present application also provides an electronic device, a readable storage medium and a computer program product.

[0166] Fig.11 A schematic diagram of the structure of an electronic device provided for an embodiment of the present application. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workbenches, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present application described and / or required herein.

[0167] like Fig.11As shown, the device 700 includes a computing unit 701, which can perform various appropriate actions and processes according to a computer program stored in a ROM (Read-Only Memory) 702 or a computer program loaded from a storage unit 708 to a RAM (Random Access Memory) 703. In the RAM 703, various programs and data required for the operation of the device 700 can also be stored. The computing unit 701, the ROM 702, and the RAM 703 are connected to each other via a bus 704. An I / O (Input / Output) interface 705 is also connected to the bus 704.

[0168] A number of components in the device 700 are connected to the I / O interface 705, including: an input unit 706, such as a keyboard, a mouse, etc.; an output unit 707, such as various types of displays, speakers, etc.; a storage unit 708, such as a disk, an optical disk, etc.; and a communication unit 709, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 709 allows the device 700 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0169] The computing unit 701 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the computing unit 701 include, but are not limited to, a CPU (Central Processing Unit), a GPU (Graphic Processing Units), various dedicated AI (Artificial Intelligence) computing chips, various computing units running machine learning model algorithms, a DSP (Digital Signal Processor), and any appropriate processor, controller, microcontroller, etc. The computing unit 701 performs the various methods and processes described above. For example, in some embodiments, the above methods may be implemented as a computer software program, which is tangibly contained in a machine-readable medium, such as a storage unit 708. In some embodiments, part or all of the computer program may be loaded and / or installed on the device 700 via the ROM 702 and / or the communication unit 709. When the computer program is loaded into the RAM 703 and executed by the computing unit 701, one or more steps of the method described above may be performed. Alternatively, in other embodiments, the computing unit 701 may be configured to execute the above method in any other appropriate manner (for example, by means of firmware).

[0170] Various embodiments of the systems and techniques described above herein may be implemented in digital electronic circuit systems, integrated circuit systems, FPGAs (Field Programmable Gate Arrays), ASICs (Application-Specific Integrated Circuits), ASSPs (Application Specific Standard Products), SOCs (System On Chips), CPLDs (Complex Programmable Logic Devices), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include: being implemented in one or more computer programs that may be executed and / or interpreted on a programmable system including at least one programmable processor that may be a dedicated or general-purpose programmable processor that may receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0171] The program code for implementing the method of the present application can be written in any combination of one or more programming languages. These program codes can be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that the program code, when executed by the processor or controller, implements the functions / operations specified in the flow chart and / or block diagram. The program code can be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0172] In the context of the present application, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or equipment. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or device, or any suitable combination of the foregoing. More specific examples of machine-readable storage media may include electrical connections based on one or more lines, portable computer disks, hard disks, RAM, ROM, EPROM (Electrically Programmable Read-Only-Memory) or flash memory, optical fiber, CD-ROM (Compact Disc Read-Only Memory), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0173] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device (e.g., a CRT (Cathode-Ray Tube) or LCD (Liquid Crystal Display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the computer. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0174] The systems and techniques described herein may be implemented in a computing system that includes backend components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes frontend components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such backend components, middleware components, or frontend components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: LAN (Local Area Network), WAN (Wide Area Network), the Internet, and blockchain networks.

[0175] A computer system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The relationship between the client and the server is generated by computer programs running on the corresponding computers and having a client-server relationship with each other. The server may be a cloud server, also known as a cloud computing server or a cloud host, which is a host product in the cloud computing service system to solve the defects of difficult management and weak business scalability in traditional physical hosts and VPS services (Virtual Private Server). The server may also be a server of a distributed system, or a server combined with a blockchain.

[0176] According to an embodiment of the present application, the present application also provides a computer program product, which, when an instruction processor in the computer program product executes, executes the method proposed in the above embodiment of the present application.

[0177] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps recorded in this application can be executed in parallel, sequentially or in different orders, as long as the expected results of the technical solution disclosed in this application can be achieved, and this document is not limited here.

[0178] The above specific implementations do not constitute a limitation on the protection scope of this application. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principles of this application should be included in the protection scope of this application.

Claims

1. A method for predicting a complex structure, characterized in that: include: Obtaining the amino acid sequence of the receptor and the sequence information of the ligand to be bound, as well as the protein structure of the receptor; Based on the protein structure of the receptor, determining the position information of the ligand relative to the protein structure; The target complex structure of the receptor and the ligand is determined based on the position information of the ligand relative to the protein structure, the amino acid sequence of the receptor and the sequence information of the ligand.

2. The method according to claim 1, characterized in that The step of determining the target complex structure of the receptor and the ligand based on the position information of the ligand relative to the protein structure, the amino acid sequence of the receptor and the sequence information of the ligand comprises: Determining the initial complex structure of the receptor and the ligand based on the position information of the ligand relative to the protein structure; The target complex structure of the receptor and the ligand is determined based on the initial complex structure, the amino acid sequence of the receptor and the sequence information of the ligand.

3. The method according to claim 2, characterized in that The determining, based on the protein structure of the receptor, the position information of the ligand relative to the protein structure comprises: Displaying the protein structure on an interactive interface of an electronic device; Determining a binding position on the protein structure based on the detected first instruction; According to the detected second instruction and the binding position, the position region of the ligand in space and the direction information of the position region are determined.

4. The method according to claim 3, characterized in that Determining the initial complex structure of the receptor and the ligand based on the position information of the ligand relative to the protein structure includes: Determining the initial three-dimensional position of each atom of the ligand in the position region according to the position region and the direction information of the position region; The initial complex structure is obtained based on the protein structure of the receptor and the initial three-dimensional positions of each atom of the ligand.

5. The method according to claim 3, characterized in that Determining the target complex structure of the receptor and the ligand according to the initial complex structure, the amino acid sequence of the receptor and the sequence information of the ligand to be bound comprises: Performing a local transformation on the initial complex structure to obtain a first complex structure; A structure prediction model is used to determine the target complex structure of the receptor and the ligand based on the first complex structure, the amino acid sequence of the receptor and the sequence information of the ligand.

6. The method according to claim 5, characterized in that The method of using a structure prediction model to determine the target complex structure of the receptor and the ligand according to the first complex structure, the amino acid sequence of the receptor and the sequence information of the ligand comprises: Using the encoding network in the structure prediction model, the amino acid sequence of the receptor and the sequence information of the ligand to be bound are encoded to obtain a fusion encoding feature; Using a decoding network in the structure prediction model, a set number of iterations are performed according to the first composite structure and the fusion coding feature to update the structure of the complex bound by the receptor and the ligand; The complex structure of the receptor and the ligand obtained in the last round of iterative updating is used as the target complex structure of the receptor and the ligand.

7. The method according to claim 6, characterized in that The first round of iterations in the set number of iterations includes: The first complex structure and the fusion coding feature are input into the decoding network for decoding to obtain the complex structure of the receptor and the ligand obtained by the first round of iterative update.

8. The method according to claim 6, characterized in that The non-first round of iterations in the set number of iterations includes: Obtaining a complex structure of the receptor and the ligand that is updated in a previous iteration of this iteration; According to the complex structure of the receptor and the ligand combined that was updated in the previous round of iteration and the fusion coding feature, the complex structure of the receptor and the ligand combined that was updated in the current round of iteration is input into the decoding network for decoding to obtain the complex structure of the receptor and the ligand combined that was updated in the current round of iteration.

9. A model training method, characterized in that: include: Acquiring a training sample, wherein the training sample includes the amino acid sequence of the receptor and the sequence information of the ligand to be bound, and the position information of the ligand relative to the protein structure of the receptor; Inputting the training sample into a structure prediction model to obtain a predicted complex structure of the receptor and the ligand; Determining a loss function of the structure prediction model according to a difference between the predicted complex structure and the target complex structure annotated by the training sample; The structure prediction model is trained according to the loss function to obtain the trained structure prediction model.

10. A device for predicting a complex structure, characterized in that: include: An acquisition module, used to acquire the amino acid sequence of the receptor and the sequence information of the ligand to be bound, as well as the protein structure of the receptor; A determination module, used for determining the position information of the ligand relative to the protein structure based on the protein structure of the receptor; The prediction module is used to determine the target complex structure of the receptor and the ligand based on the position information of the ligand relative to the protein structure, the amino acid sequence of the receptor and the sequence information of the ligand.

11. The device according to claim 10, characterized in that The prediction module is further used for: Determining the initial complex structure of the receptor and the ligand based on the position information of the ligand relative to the protein structure; The target complex structure of the receptor and the ligand is determined based on the initial complex structure, the amino acid sequence of the receptor and the sequence information of the ligand.

12. The device according to claim 11, characterized in that The determining module is further used for: Displaying the protein structure on an interactive interface of an electronic device; Determining a binding position on the protein structure based on the detected first instruction; According to the detected second instruction and the binding position, the position region of the ligand in space and the direction information of the position region are determined.

13. The device according to claim 12, characterized in that The prediction module is further used for: Determining the initial three-dimensional position of each atom of the ligand in the position region according to the position region and the direction information of the position region; The initial complex structure is obtained based on the protein structure of the receptor and the initial three-dimensional positions of each atom of the ligand.

14. The device according to claim 12, characterized in that The prediction module is further used for: Performing a local transformation on the initial complex structure to obtain a first complex structure; A structure prediction model is used to determine the target complex structure of the receptor and the ligand based on the first complex structure, the amino acid sequence of the receptor and the sequence information of the ligand.

15. The device according to claim 14, characterized in that The prediction module is further used for: Using the encoding network in the structure prediction model, the amino acid sequence of the receptor and the sequence information of the ligand to be bound are encoded to obtain a fusion encoding feature; Using a decoding network in the structure prediction model, a set number of iterations are performed according to the first composite structure and the fusion coding feature to update the structure of the complex bound by the receptor and the ligand; The complex structure of the receptor and the ligand obtained in the last round of iterative updating is used as the target complex structure of the receptor and the ligand.

16. The device according to claim 15, characterized in that The first round of iterations in the set number of iterations includes: The first complex structure and the fusion coding feature are input into the decoding network for decoding to obtain the complex structure of the receptor and the ligand obtained by the first round of iterative update.

17. The device according to claim 15, characterized in that The non-first round of iterations in the set number of iterations includes: Obtaining a complex structure of the receptor and the ligand that is updated in a previous iteration of this iteration; According to the complex structure of the receptor and the ligand combined that was updated in the previous round of iteration and the fusion coding feature, the complex structure of the receptor and the ligand combined that was updated in the current round of iteration is input into the decoding network for decoding to obtain the complex structure of the receptor and the ligand combined that was updated in the current round of iteration.

18. A model training device, characterized in that: include: An acquisition module, used to acquire a training sample, wherein the training sample includes the amino acid sequence of the receptor and the sequence information of the ligand to be bound, and the position information of the ligand relative to the protein structure of the receptor; A prediction module, used for inputting the training sample into a structure prediction model to obtain a predicted complex structure of the receptor and the ligand; A determination module, configured to determine a loss function of the structure prediction model according to a difference between the predicted complex structure and the target complex structure annotated by the training sample; A training module is used to train the structure prediction model according to the loss function to obtain the trained structure prediction model.

19. An electronic device comprising: at least one processor; as well as a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to execute the method of any one of claims 1 to 8, or execute the method of claim 9.

20. A non-transitory computer-readable storage medium storing computer instructions, wherein: The computer instructions are used to enable the computer to execute the method according to any one of claims 1 to 8, or to execute the method according to claim 9.

21. A computer program product, comprising a computer program, wherein when the computer program is executed by a processor, the computer program implements the steps of the method according to any one of claims 1 to 8, or implements the steps of the method according to claim 9.

Images