Protein side chain structure prediction method and device based on coherent Isin machine

Abstract

The invention provides a method and a device for predicting a protein side chain structure based on a coherent Isin machine, and the method comprises the steps: firstly, obtaining a protein file; then, according to the protein file, generating a side chain conformation relation network diagram which comprises a plurality of side chain conformation nodes and connecting edges which are established among the side chain conformation nodes and meet preset conditions; searching a solution space represented by the side chain conformation relation graph by using a coherent Isin machine system, and solving a ground state of the Hamiltonian H; and finally, generating a target side chain structure of the protein according to the ground state of the Hamiltonian H. According to the protein side chain structure prediction method provided by the invention, all possible side chain conformation combinations can be systematically searched, it is ensured that the found solution is globally optimal, and the solution precision is higher. In addition, a coherent Isin machine system is utilized, and the calculation efficiency is higher when a large-scale problem is processed.

Description

Technical Field

[0001] The present invention relates to the field of computational biology, and in particular to a method and device for predicting protein side chain structure based on a coherent Ising machine. Background Art

[0002] The Protein Side-chain Packing Problem (PSPP) is a key challenge in computational biology and structure prediction. The PSPP problem involves predicting the optimal arrangement of the side chains of amino acid residues in three-dimensional space based on the known protein backbone structure to achieve the stability and functionality of the entire protein structure. This problem is considered NP-hard due to its complex combinatorial nature and huge search space, meaning that there is no known polynomial time algorithm that can accurately solve all instances.

[0003] Existing solutions to the PSPP problem include: 1. Dead-end Elimination (DEE):

[0004] DEE is a deterministic algorithm that reduces the search space by iteratively eliminating side chain conformations that cannot possibly belong to the global lowest energy conformation. The method is based on a simple criterion: if a side chain conformation cannot exist in any possible global lowest energy conformation, it can be removed from the search space. The DEE method is guaranteed to find the global optimal solution, but it may encounter convergence problems when dealing with large proteins and requires huge computing resources, limiting its application to large-scale problems.

[0005] 2. Genetic Algorithms (GA): Genetic algorithm is a heuristic algorithm that imitates the process of natural selection. In the PSPP problem, the genetic algorithm initializes a population of side chain conformations and then iteratively improves these conformations through operations such as selection, crossover and mutation. Eventually, the algorithm converges to one or more sets of low-energy side chain conformations. The advantage of genetic algorithms lies in their parallel processing capabilities, but they may not guarantee to find the global optimal solution, and their performance is highly dependent on parameter settings, and the computational efficiency may not be high.

[0006] 3. Monte Carlo Methods: The Monte Carlo method is a computational method based on random sampling, which is used to solve complex optimization problems. In the PSPP problem, the Monte Carlo method randomly selects side chain conformations and calculates their energies, and then accepts or rejects new conformations based on the energy evaluation. This method is suitable for dealing with large-scale problems, but its random sampling-based nature makes it impossible to guarantee the global optimal solution, and it may require a large number of samples, which is computationally expensive and slow to converge.

[0007] It can be seen that in the PSPP problem, although these algorithms can provide approximate solutions to a certain extent, they face limitations in computational efficiency, accuracy of solutions, and scalability. In addition, these methods often require huge computing resources when dealing with large-scale problems, which limits their feasibility in practical applications. Summary of the invention

[0008] In order to solve the above problems, the present invention provides a method and device for predicting protein side chain structure based on coherent Ising machine.

[0009] According to a first aspect, a method for predicting a protein side chain structure is provided, comprising the following steps: S1. Obtain a protein file, which includes the spatial coordinates of multiple atoms in the protein, wherein the multiple atoms form multiple amino acid residues.

[0010] S2. Generate a side chain conformation relationship network diagram according to the protein file, which includes a plurality of side chain conformation nodes and connection edges between the side chain conformation nodes that meet predetermined conditions.

[0011] The determination of the plurality of side chain conformation nodes comprises: for each of the plurality of amino acid residues, generating a specific number of side chain conformations by sampling the side chain search space, and screening out side chain conformations that do not overlap spatially with the main chain of the protein as nodes.

[0012] The predetermined conditions that need to be met to establish a connection edge include: the two side chain conformation nodes do not belong to the same amino acid residue and have no overlap in space.

[0013] S3. Using a coherent Ising machine system, searching the solution space represented by the side chain conformation relationship diagram to solve the ground state of the Hamiltonian H, the Hamiltonian H is:

[0014] in, Representative The amino acid residue Whether the node corresponding to the side chain conformation is selected, for The weight of Representative The amino acid residue The side chain conformation and The amino acid residue Is there a connecting edge between the nodes corresponding to the side chain conformations? K1 is The coefficient of .

[0015] S4. Generate a target side chain structure of the protein according to the ground state of the Hamiltonian H.

[0016] In some embodiments, side chain conformations that do not spatially overlap with the main chain of the protein are screened out, specifically comprising: for each side chain conformation, measuring its minimum distance from the main chain, and if the distance is greater than a first threshold, selecting the side chain conformation of the amino acid residue as a node.

[0017] In some embodiments, to meet the predetermined condition, the establishment of the connecting edge specifically includes: for each pair of side chain conformations that do not belong to the same amino acid residue, measuring the minimum atomic distance between them, and if the distance is greater than a second threshold, establishing a connecting edge between their corresponding vertices.

[0018] In some embodiments, the use of a coherent Ising machine system to search the solution space represented by the side chain conformation relationship diagram to solve the ground state of the Hamiltonian H specifically includes: Initializing the coherent Ising machine according to the Hamiltonian H, and starting the coherent Ising machine system evolution process; During the evolution of the coherent Ising machine system, the phase and intensity of the light field in the coherent Ising machine system are measured multiple times, and the coherent Ising machine system parameters are adjusted in real time according to the measurement results, and finally a collective oscillation mode far above the threshold is obtained. The quantum spin state in this mode corresponds to the ground state of the Hamiltonian H.

[0019] In some embodiments, the coherent Ising machine system comprises: A network of optical parametric oscillators to simulate spin interactions in the Ising model; Phase-sensitive amplifier, used to amplify signals with a specific phase; A field programmable gate array for controlling an optical parametric oscillator network; A phase / intensity meter, used to measure the phase and intensity of the light field in the cavity; Optical modulators, which are used to vary the phase difference between the light beams, thereby simulating the strength of the interaction between different spin states; A beam splitter is used to produce interference effects and simulate the connection between spins in the Ising model; Optical fiber, used as a transmission medium for optical signals.

[0020] According to a second aspect, a protein side chain structure prediction device based on a coherent Ising machine is provided, comprising: The acquisition module is used to acquire a protein file, which includes the spatial coordinates of multiple atoms in the protein, and the multiple atoms form multiple amino acid residues.

[0021] A graph generation module is used to generate a side chain conformation relationship network graph according to the protein file, which includes a plurality of side chain conformation nodes and connecting edges between the side chain conformation nodes that meet predetermined conditions. The determination of the plurality of side chain conformation nodes includes: for each of the plurality of amino acid residues, a specific number of side chain conformations are generated by side chain search space sampling, and side chain conformations that do not overlap with the main chain of the protein in space are screened out as nodes; the predetermined conditions include: two side chain conformation nodes do not belong to the same amino acid residue and do not overlap in space.

[0022] A solution module is used to search the solution space represented by the side chain conformation relationship diagram using a coherent Ising machine system to solve the ground state of the Hamiltonian H, where the Hamiltonian H is:

[0023] in, Representative The amino acid residue Whether the node corresponding to the side chain conformation is selected, for The weight of Representative The amino acid residue The side chain conformation and The amino acid residue Is there a connecting edge between the nodes corresponding to the side chain conformations? K1 is The coefficient of .

[0024] An output module outputs the target side chain structure of the protein according to the ground state of the Hamiltonian H.

[0025] In some embodiments, the side chain conformations that do not overlap spatially with the main chain of the protein are screened, specifically comprising: For each side chain conformation, measure its minimum distance from the main chain. If the distance is greater than a first threshold, select the side chain conformation of the amino acid residue as a node. In some embodiments, the establishing of the connection edge includes: For each pair of side chain conformations that do not belong to the same amino acid residue, the minimum atomic distance between them is measured, and if the distance is greater than a second threshold, a connecting edge is established between their corresponding vertices.

[0026] In some embodiments, the use of a coherent Ising machine system to search the solution space represented by the side chain conformation relationship diagram to solve the ground state of the Hamiltonian H specifically includes: Initializing the coherent Ising machine according to the Hamiltonian H, and starting the coherent Ising machine system evolution process; During the evolution of the coherent Ising machine system, the phase and intensity of the light field in the coherent Ising machine system are measured multiple times, and the coherent Ising machine system parameters are adjusted in real time according to the measurement results, and finally a collective oscillation mode far above the threshold is obtained. The quantum spin state in this mode corresponds to the ground state of the Hamiltonian H.

[0027] The protein side chain structure prediction method provided by the present invention can systematically search all possible side chain conformation combinations to ensure that the solution found is the global optimal one with higher solution accuracy. In addition, the present invention utilizes a coherent Ising machine system, which has higher computational efficiency when dealing with large-scale problems. The present invention utilizes a coherent Ising machine to predict protein side chain folding, improves the traditional solution complexity, and makes the algorithm complexity have the advantages of polynomial improved scaling or constant prefactor, which makes the advantages of the present method more and more obvious as the system scale increases. BRIEF DESCRIPTION OF THE DRAWINGS

[0028] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0029] Figure 1 A flow chart of a protein side chain structure prediction method provided by the present invention; Figure 2 A schematic diagram of the structure of a coherent Ising machine system provided in an embodiment of the present invention; Figure 3 A schematic diagram of a protein side chain structure prediction device provided by the present invention. DETAILED DESCRIPTION

[0030] In order to make the purpose, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be described below in conjunction with the accompanying drawings.

[0031] The Coherent Ising Machine (CIM) is a computing platform based on quantum optics simulation of the Ising model. Its advantages lie in its fast computing speed and strong scalability. It is suitable for processing a variety of large-scale combinatorial optimization problems, especially for processing large-scale quantum bits and NP-hard problems. When processing these problems, CIM can ensure that the solution found is the global optimal while maintaining the efficiency of the calculation and the accuracy of the solution.

[0032] CIM, with its unique parallel processing capability and high-speed computing performance, provides a new solution to the PSPP problem. Based on this, the present invention first converts the PSPP problem into an Ising model optimization problem by designing the Hamiltonian of the coherent Ising machine, so that it can be efficiently calculated; and then uses the coherent Ising machine to solve the PSPP problem, ensuring that the solution found is the global optimal one.

[0033] The following is a description of the protein side chain structure prediction method provided by the present invention in conjunction with the accompanying drawings. The flowchart of the method is as follows: Figure 1 As shown, the following steps are included:

[0034] S1. Obtain a protein file, which includes the spatial coordinates of multiple atoms in the protein, wherein the multiple atoms form multiple amino acid residues.

[0035] It can be understood that proteins are molecular chains formed by multiple amino acid residues connected by peptide bonds, and each amino acid residue contains a main chain and a side chain. The main chain is composed of a repeating sequence of atoms (including nitrogen atoms, alpha carbon atoms, and carbonyl carbon atoms), forming the backbone structure of the protein. The side chain is a unique chemical group connected to the alpha carbon atom of the main chain, composed of different types of atoms, which determines the characteristics and functions of the amino acid. All these structures are ultimately formed by the arrangement and bonding of atoms, and atoms are the most basic units that make up proteins.

[0036] S2. Generate a side chain conformation relationship network diagram according to the protein file, which includes a plurality of side chain conformation nodes and connection edges between the side chain conformation nodes that meet predetermined conditions.

[0037] Wherein, the determination of the plurality of side chain conformation nodes includes: for each of the plurality of amino acid residues, generating a specific number of side chain conformations by sampling the side chain search space, that is, sampling a specific number of side chain conformations from the side chain search space of the amino acid residue, and screening out the side chain conformations that do not overlap with the main chain of the protein in space as nodes. It can be understood that the side chain conformation refers to the spatial arrangement or geometric shape of the amino acid side chains in the protein.

[0038] In some embodiments, the side chain conformations that do not overlap with the main chain of the protein in space are screened, specifically comprising: for each side chain conformation, measuring its minimum distance from the main chain, and if the distance is greater than a first threshold, selecting the amino acid residue side chain conformation as a node. It should be understood that the "first" in the "first threshold" and the "second" and other similar terms in the text are to distinguish similar things and do not have other limiting functions such as sorting.

[0039] The predetermined conditions that need to be met to establish a connection edge include: the two side chain conformation nodes do not belong to the same amino acid residue and have no overlap in space.

[0040] In some embodiments, to meet the predetermined condition, the establishment of the connecting edge specifically includes: for each pair of side chain conformations that do not belong to the same amino acid residue, measuring the minimum atomic distance between them, and if the distance is greater than a second threshold, establishing a connecting edge between their corresponding vertices.

[0041] Through the above steps, all possible side chain conformations of amino acid residues and their relationships are converted into a side chain conformation relationship network graph G=(V, E), where V is the node set and E is the edge set. V contains nodes that do not collide with the main chain. (i.e. No. conformations), E contains { , } (i.e. No. The conformation and The residue The conformations do not overlap in space). In this way, the protein side chain folding problem is transformed into a graph theory problem. Next, the optimal arrangement of all amino acid residue side chains is found by finding the largest group in the graph G. This can be achieved by constructing the Hamiltonian H of the graph G and using CIM to solve the ground state of the Hamiltonian H. The specific steps are as follows:

[0042] S3. Using a coherent Ising machine system, searching the solution space represented by the side chain conformation relationship diagram to solve the ground state of the Hamiltonian H, the Hamiltonian H is:

[0043] (1)

[0044] The meaning and possible values ​​of each parameter are as follows:

[0045] Representative The amino acid residue Whether the node corresponding to the side chain conformation is selected or not, and whether the node is selected corresponds to the node spin state in the coherent Ising machine. For example, it can be set to when the spin is +1, it means that this conformation is selected.

[0046] for The weight can be 1.

[0047] Representative The amino acid residue The side chain conformation and The amino acid residue Whether there is a connection edge between the nodes corresponding to the side chain conformations. For example, it takes 1 when there is a connection edge and takes 0 when there is no connection edge.

[0048] K1 is The coefficient can be set to any positive number, such as 1.

[0049] In this step, the coherent Ising machine system can be used to find the ground state of the Hamiltonian H shown in equation (1), that is, the largest cluster of the graph G.

[0050] In some embodiments, the use of a coherent Ising machine system to search the solution space represented by the side chain conformation relationship diagram to solve the ground state of the Hamiltonian H specifically includes:

[0051] S31. Initialize a coherent Ising machine according to the Hamiltonian H.

[0052] S32, starting the coherent Ising machine system evolution process, increasing the pump amplitude from 0, and finally obtaining a collective oscillation mode far above the threshold, in which the quantum spin state corresponds to the ground state of the Hamiltonian H.

[0053] It should be understood that during the evolution of the coherent Ising machine system, the phase and intensity of the light field in the coherent Ising machine system can be measured multiple times, and the coherent Ising machine system parameters can be adjusted in real time according to the measurement results.

[0054] From the above, the ground state of Hamiltonian H can be obtained using the coherent Ising machine system.

[0055] S4. Generate a target side chain structure of the protein according to the ground state of the Hamiltonian H.

[0056] Specifically, the ground state of the Hamiltonian H, or the nodes in the largest cluster, are inversely encoded into the side chain conformations of protein residues as the final prediction results.

[0057] For example, the output form of the final prediction result can be a protein three-dimensional structure diagram or protein atomic spatial coordinates.

[0058] The above is the protein side chain structure prediction method based on the coherent Ising machine provided by the present invention. The coherent Ising machine system used in the method is briefly introduced below.

[0059] The coherent Ising machine system uses a Doubly Resonant Optical Parametric Oscillator (DOPO) to achieve artificial spins, and a phase sensitive amplifier (PSA) is placed in the optical cavity to enhance the optical signal at a specific phase. PSA is an optical amplifier based on optical parametric amplification, which can effectively amplify the 0 and π phase components relative to the pump phase. Therefore, DOPO only adopts 0 or π phases above the oscillation threshold; therefore, discrete phase states can be used to represent Ising spin states. The interaction between DOPO pulses is achieved using measurement feedback technology. By repeating the measurement feedback modulation process in the cavity many times while increasing the pump amplitude from 0, the "strongest" collective oscillation mode far above the threshold will eventually be obtained, which corresponds to the optimal solution to the given Ising problem.

[0060] The schematic diagram of the coherent Ising machine system is shown in Figure 2 As shown, including:

[0061] (1) A network of optical parametric oscillators to simulate spin interactions in the Ising model.

[0062] (2) Phase-sensitive amplifier: used to amplify signals of a specific phase.

[0063] (3) Field-Programmable Gate Array (FPGA), used to control the optical parametric oscillator network.

[0064] FPGA can be programmed to configure its internal circuits and can be used to adjust the coherent Ising machine system parameters in real time according to measurement results during the evolution of the coherent Ising machine system.

[0065] (4) Phase / intensity meter, used to measure the phase and intensity of the light field in the cavity.

[0066] (5) An optical modulator, which is used to change the phase difference between the light beams, thereby simulating the interaction strength between different spin states.

[0067] (6) Beam splitter, used to produce interference effect and simulate the connection between spins in the Ising model.

[0068] (7) Optical fiber, used as a transmission medium for optical signals.

[0069] It can be seen from the above that compared with the prior art, the protein side chain structure prediction method provided by the present invention has the following beneficial effects:

[0070] 1. Guarantee of global optimal solution: This method can systematically search all possible side chain conformation combinations to ensure that the solution found is the global optimal one. This is particularly important in the NP-hard PSPP problem, because many heuristic algorithms can quickly find approximate solutions, but cannot guarantee the optimality of the solution.

[0071] 2. High-precision prediction capability: Compared with traditional heuristic or approximate algorithms, this method has higher solution accuracy and can provide more accurate results, satisfying the exact solution obtained by the enumeration algorithm.

[0072] 3. Acceleration potential: This method is based on a coherent Ising machine system implementation, which provides higher approximate solution accuracy than classical computers, and its advantages become more and more obvious as the size of the problem increases. The acceleration advantage of the Ising machine goes beyond the field of complexity theory and provides a scaling or constant pre-factor advantage of polynomial improvements, which has a great impact on the running time of large problems, that is, as the size of the system increases, the advantages of this method become more and more obvious.

[0073] 4. Ability to directly obtain three-dimensional conformation: This method can directly obtain the three-dimensional conformation of protein side chain folding, providing a more convenient and rapid solution for the biopharmaceutical field.

[0074] The present invention also provides a protein side chain structure prediction device 300 based on a coherent Ising machine, the schematic diagram of which is shown in FIG. Figure 3 As shown, including:

[0075] The acquisition module 301 is used to acquire a protein file, which includes the spatial coordinates of multiple atoms in the protein, and the multiple atoms form multiple amino acid residues.

[0076] The graph generation module 302 is used to generate a side chain conformation relationship network graph according to the protein file, which includes a plurality of side chain conformation nodes and connecting edges between the side chain conformation nodes that meet predetermined conditions. The determination of the plurality of side chain conformation nodes includes: for each of the plurality of amino acid residues, a specific number of side chain conformations are generated by side chain search space sampling, and side chain conformations that do not overlap with the main chain of the protein in space are screened out as nodes; the predetermined conditions include: two side chain conformation nodes do not belong to the same amino acid residue and do not overlap in space.

[0077] The solution module 303 is used to search the solution space represented by the side chain conformation relationship diagram using a coherent Ising machine system to solve the ground state of the Hamiltonian H, where the Hamiltonian H is:

[0078]

[0079] in, Representative The amino acid residue Whether the node corresponding to the side chain conformation is selected, for The weight of Representative The amino acid residue The side chain conformation and The amino acid residue Is there a connecting edge between the nodes corresponding to the side chain conformations? K1 is The coefficient of .

[0080] The output module 304 outputs the target side chain structure of the protein according to the ground state of the Hamiltonian H.

[0081] It should be noted that the above-mentioned device can execute the above-mentioned protein side chain structure prediction method. The functions of each module can also refer to the above-mentioned introduction to the method and will not be described in detail.

[0082] In the description of the embodiments of the present application, words such as "exemplary", "for example" or "for example" are used to indicate examples, illustrations or descriptions. Any embodiment or design described as "exemplary", "for example" or "for example" in the embodiments of the present application should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of words such as "exemplary", "for example" or "for example" is intended to present related concepts in a concrete way.

[0083] In the description of the embodiments of the present application, the term "and / or" is merely a description of the association relationship of associated objects, indicating that three relationships may exist. For example, A and / or B may represent: A exists alone, B exists alone, and A and B exist at the same time. In addition, unless otherwise specified, the term "plurality" means two or more.

[0084] In addition, the terms "includes," "comprising," "having" and variations thereof mean "including but not limited to," unless specifically emphasized otherwise.

[0085] The specific implementation methods described above further illustrate the objectives, technical solutions and beneficial effects of the present invention in detail. It should be understood that the above description is only a specific implementation method of the present invention and is not intended to limit the scope of protection of the present invention. Any modifications, equivalent substitutions, improvements, etc. made on the basis of the technical solution of the present invention should be included in the scope of protection of the present invention.

Claims

1. A method for predicting protein side chain structure, characterized in that: The following steps are involved: Obtaining a protein file, which includes spatial coordinates of a plurality of atoms in the protein, wherein the plurality of atoms form a plurality of amino acid residues; Generating a side chain conformation relationship network diagram according to the protein file, which includes a plurality of side chain conformation nodes and connection edges between the side chain conformation nodes that meet predetermined conditions; The determination of the plurality of side chain conformation nodes comprises: for each of the plurality of amino acid residues, generating a specific number of side chain conformations by side chain search space sampling, and selecting side chain conformations that do not overlap with the main chain of the protein in space as nodes; the predetermined conditions include: two side chain conformation nodes do not belong to the same amino acid residue and do not overlap in space; The coherent Ising machine system is used to search the solution space represented by the side chain conformation relationship diagram to solve the ground state of the Hamiltonian H, which is: in, Representative The amino acid residue Whether the node corresponding to the side chain conformation is selected, for The weight of Representative The amino acid residue The side chain conformation and The amino acid residue Is there a connecting edge between the nodes corresponding to the side chain conformations? K1 is The coefficient of The target side chain structure of the protein is generated according to the ground state of the Hamiltonian H.

2. The method according to claim 1, characterized in that Screen out side chain conformations that do not overlap spatially with the main chain of the protein, specifically including: For each side chain conformation, the minimum distance between it and the main chain is measured. If the distance is greater than a first threshold, the side chain conformation of the amino acid residue is selected as a node.

3. The method according to claim 1, characterized in that The establishment of the connection edge includes: For each pair of side chain conformations that do not belong to the same amino acid residue, the minimum atomic distance between them is measured, and if the distance is greater than a second threshold, a connecting edge is established between their corresponding vertices.

4. The method according to claim 1, characterized in that: The method of using a coherent Ising machine system to search the solution space represented by the side chain conformation relationship diagram to solve the ground state of the Hamiltonian H specifically includes: Initializing the coherent Ising machine according to the Hamiltonian H, and starting the coherent Ising machine system evolution process; During the evolution of the coherent Ising machine system, the phase and intensity of the light field in the coherent Ising machine system are measured multiple times, and the coherent Ising machine system parameters are adjusted in real time according to the measurement results, and finally a collective oscillation mode far above the threshold is obtained. The quantum spin state in this mode corresponds to the ground state of the Hamiltonian H.

5. The method according to claim 1, characterized in that: The coherent Ising machine system comprises: A network of optical parametric oscillators to simulate spin interactions in the Ising model; Phase-sensitive amplifier, used to amplify signals with specific phases; A field programmable gate array for controlling an optical parametric oscillator network; A phase / intensity meter, used to measure the phase and intensity of the light field in the cavity; Optical modulators, which are used to vary the phase difference between the light beams, thereby simulating the strength of the interaction between different spin states; A beam splitter is used to produce interference effects and simulate the connection between spins in the Ising model; Optical fiber, used as a transmission medium for optical signals.

6. A protein side chain structure prediction device based on a coherent Ising machine, characterized in that: include: An acquisition module, used for acquiring a protein file, which includes spatial coordinates of a plurality of atoms in the protein, wherein the plurality of atoms form a plurality of amino acid residues; A graph generation module, used to generate a side chain conformation relationship network graph according to the protein file, which includes a plurality of side chain conformation nodes and connection edges between the side chain conformation nodes that meet predetermined conditions; The determination of the plurality of side chain conformation nodes comprises: for each of the plurality of amino acid residues, generating a specific number of side chain conformations by side chain search space sampling, and selecting side chain conformations that do not overlap with the main chain of the protein in space as nodes; the predetermined conditions include: two side chain conformation nodes do not belong to the same amino acid residue and do not overlap in space; A solution module is used to search the solution space represented by the side chain conformation relationship diagram using a coherent Ising machine system to solve the ground state of the Hamiltonian H, where the Hamiltonian H is: in, Representative The amino acid residue Whether the node corresponding to the side chain conformation is selected, for The weight of Representative The amino acid residue The side chain conformation and The amino acid residue Is there a connecting edge between the nodes corresponding to the side chain conformations? K1 is The coefficient of An output module outputs the target side chain structure of the protein according to the ground state of the Hamiltonian H.

7. The device according to claim 6, characterized in that Screen out side chain conformations that do not overlap spatially with the main chain of the protein, specifically including: For each side chain conformation, the minimum distance between it and the main chain is measured. If the distance is greater than a first threshold, the side chain conformation of the amino acid residue is selected as a node.

8. The device according to claim 6, characterized in that The establishment of the connection edge includes: For each pair of side chain conformations that do not belong to the same amino acid residue, the minimum atomic distance between them is measured, and if the distance is greater than a second threshold, a connecting edge is established between their corresponding vertices.

9. The device according to claim 6, characterized in that The method of using a coherent Ising machine system to search the solution space represented by the side chain conformation relationship diagram to solve the ground state of the Hamiltonian H specifically includes: Initializing the coherent Ising machine according to the Hamiltonian H, and starting the coherent Ising machine system evolution process; During the evolution of the coherent Ising machine system, the phase and intensity of the light field in the coherent Ising machine system are measured multiple times, and the coherent Ising machine system parameters are adjusted in real time according to the measurement results, and finally a collective oscillation mode far above the threshold is obtained. The quantum spin state in this mode corresponds to the ground state of the Hamiltonian H.

10. The device according to claim 6, characterized in that The coherent Ising machine system comprises: A network of optical parametric oscillators to simulate spin interactions in the Ising model; Phase-sensitive amplifier, used to amplify signals with specific phases; A field programmable gate array for controlling an optical parametric oscillator network; A phase / intensity meter, used to measure the phase and intensity of the light field in the cavity; Optical modulators, which are used to vary the phase difference between the light beams, thereby simulating the strength of the interaction between different spin states; A beam splitter is used to produce interference effects and simulate the connection between spins in the Ising model; Optical fiber, used as a transmission medium for optical signals.

Images