System and method for predicting protein structure based on RNA sequence of quantum computing

Abstract

The invention discloses an RNA sequence prediction protein structure system and method based on quantum computing and electronic equipment, and the system comprises a user interaction terminal layer which is used for obtaining a target RNA sequence input by a user; the classical computing layer is connected with the user interaction terminal layer and the quantum computing cloud platform layer, and is used for processing and analyzing the target RNA sequence, distributing a computing task according to an analysis result, and generating a predicted protein structure according to an obtained computing result; the quantum computing cloud platform layer is used for computing the quantum computing tasks allocated by the classic computing layer; the calculation result comprises a classical calculation result and / or a quantum calculation result. The system disclosed by the invention can more effectively pass through an energy barrier in a complex energy landscape and find a globally optimal solution with a higher probability. Therefore, the problem that a prediction structure is inaccurate due to the fact that a traditional classical algorithm often falls into a local minimum value when searching for the lowest energy conformation of the protein is solved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of computer, in particular to a RNA sequence predicting protein structure system based on quantum computing, a RNA sequence predicting protein structure method based on quantum computing and an electronic device. BACKGROUND

[0002] The three-dimensional spatial structure of a protein directly determines its biochemical function. The structure analysis methods in the related art mainly rely on X-ray crystal diffraction, Cryo-Electron Microscopy (Cryo-EM) and Nuclear Magnetic Resonance (NMR). Although the results are accurate, these methods are extremely costly, long in cycle and difficult to handle unstable structures such as membrane proteins.

[0003] In recent years, the deep learning-based computational biology method represented by AlphaFold predicts unknown structures by learning a large amount of known protein structure database and using multiple sequence alignment and evolutionary constraints. However, this method has the following defects: 1. The deep learning model is highly dependent on evolutionary information. For completely new artificial proteins, orphan genes and other proteins expressed by them that do not exist in nature, or sequences with rare mutations, the prediction accuracy will drop sharply due to the lack of homologous sequence data. 2. The ab initio prediction method based on physical principles (such as molecular dynamics simulation) does not rely on the database, and determines the structure by finding the state with the lowest energy. However, the protein folding problem is a NP-hard combinatorial optimization problem in mathematics. As the length of the amino acid chain increases, the conformational space explodes exponentially, and the classical computer cannot traverse all conformations in polynomial time to find the global optimal solution, often falling into a local minimum. 3. Although quantum computing has a huge theoretical advantage in solving combinatorial optimization problems, the current noisy intermediate-scale quantum computer has a limited number of quantum bits (usually less than 100), and the entanglement fidelity decreases with the increase of circuit depth. A medium-sized protein may require thousands of logical quantum bits to simulate, and it is not realistic to directly put the full-length sequence into the existing quantum computer for operation. SUMMARY

[0004] The present application is proposed to solve at least one of the above problems. According to a first aspect of the present application, a RNA sequence predicting protein structure system based on quantum computing is provided, comprising: a user interaction terminal layer, a classical computing layer and a quantum computing cloud platform layer.

[0005] The user interaction terminal layer is configured to obtain a target RNA sequence input by a user.

[0006] The classical computing layer is connected with the user interaction terminal layer and the quantum computing cloud platform layer, and is used for processing and analyzing the target RNA sequence, distributing a computing task according to an analysis result, and generating a predicted protein structure according to a computing result.

[0007] The quantum computing cloud platform layer is used for computing a quantum computing task distributed by the classical computing layer.

[0008] The computing result includes a classical computing result and / or a quantum computing result.

[0009] In an embodiment of the present application, the classical computing layer includes a sequence preprocessing module, a quantum mapping bridging module, a hybrid computing power scheduling module and a structure reconstruction module.

[0010] The sequence preprocessing module is connected with the user interaction terminal layer, and is used for translating, segmenting and marking the target RNA sequence.

[0011] The quantum mapping bridging module is connected with the sequence preprocessing module, and is used for generating a lattice polypeptide and a corresponding control instruction according to an amino acid polypeptide sequence obtained after processing of the sequence preprocessing module.

[0012] The hybrid computing power scheduling module is connected with the quantum mapping bridging module and the quantum computing cloud platform layer, and is connected to a classical computing power module, and is used for analyzing a computing task difficulty according to the lattice polypeptide, sending the control instruction to the classical computing power module and / or the quantum computing cloud platform layer based on a difficulty analysis result, and obtaining a three-dimensional coordinate of an amino acid in a lattice according to a classical computing result and / or a quantum computing result fed back by the classical computing power module and / or the quantum computing cloud platform layer.

[0013] The structure reconstruction module is connected with the hybrid computing power scheduling module, and is used for generating a predicted protein structure according to the three-dimensional coordinate in the lattice.

[0014] In an embodiment of the present application, the sequence preprocessing module includes a translation unit and an intelligent segmentation and marking unit.

[0015] The translation unit is connected with the user interaction terminal layer, and is used for translating the target RNA sequence into an amino acid polypeptide chain.

[0016] The intelligent segmentation and labeling unit is connected with the translation unit and the quantum computing cloud platform layer, and is configured to obtain a quantum bit threshold in the quantum computing cloud platform layer, determine whether the length of the amino acid polypeptide chain exceeds the quantum bit threshold, if yes, cut the amino acid polypeptide chain into a plurality of subdomain fragments with overlapping parts, and label a topological label on the cut overlapping area, and if no, keep the amino acid polypeptide chain as a single domain.

[0017] In an embodiment of the present application, the quantum mapping bridging module comprises a lattice modeling unit and a parameter encoding unit.

[0018] The lattice modeling unit is connected with the intelligent segmentation and labeling unit, and is configured to map each of the subdomain fragments or the amino acid polypeptide chain kept as a single domain to a three-dimensional space lattice to obtain a corresponding lattice polypeptide.

[0019] The parameter encoding unit is connected with the lattice modeling unit, and is configured to convert a general interaction parameter between amino acid residues in each of the lattice polypeptides into a corresponding control instruction.

[0020] The general interaction parameter comprises an interaction force.

[0021] In an embodiment of the present application, the mixed computing power scheduling module comprises a computing power routing unit and a result decoding unit.

[0022] The computing power routing unit is connected with the quantum mapping bridging module and the quantum computing cloud platform layer, and is connected to a classical computing power module, and is configured to determine the difficulty of a computing task according to the lattice polypeptide, if the lattice polypeptide belongs to a regular structure short fragment, send the control instruction corresponding to the lattice polypeptide to the classical computing power module, and if the lattice polypeptide does not belong to a regular structure short fragment, send the control instruction corresponding to the lattice polypeptide to the quantum computing cloud platform layer.

[0023] The result decoding unit is connected with the quantum computing cloud platform layer, and is connected to the classical computing power module, and is configured to restore the classical computing result and / or the quantum computing result to three-dimensional coordinates of amino acids in a lattice.

[0024] The classical computing power module completes classical computing according to the control instruction to obtain the classical computing result.

[0025] In an embodiment of the present application, the structure reconstruction module comprises a topological splicing unit and a global refinement unit.

[0026] The topology splicing unit is connected with the result decoding unit, and is configured to assemble multiple local optimal structures into a complete full-length chain by using a rigid body rotation and translation algorithm based on three-dimensional coordinates in a lattice and the topology label.

[0027] The global refinement unit is connected with the topology splicing unit, and is configured to perform molecular dynamics relaxation on the spliced full-length chain to eliminate atomic conflicts at the splicing position, and obtain the predicted protein structure.

[0028] In an embodiment of the present application, the user interaction terminal layer comprises an RNA sequence input interface module and a 3D structure visualization display module.

[0029] The RNA sequence input interface module is configured to receive the target RNA sequence.

[0030] The 3D structure visualization display module is connected with the classical calculation layer, and is configured to perform 3D visualization display on the predicted protein structure.

[0031] In an embodiment of the present application, the quantum computing cloud platform layer comprises a cloud API interface module and a quantum processing module.

[0032] The cloud API interface module is connected with the classical calculation layer, and is configured to receive the control instruction.

[0033] The quantum processing module is connected with the cloud API interface module, and is configured to complete quantum calculation according to the control instruction, and obtain the quantum calculation result.

[0034] According to the second aspect of the present application, an RNA sequence predicted protein structure method based on quantum calculation is provided, comprising:

[0035] Obtaining a target RNA sequence input by a user.

[0036] Processing and analyzing the target RNA sequence, and assigning a calculation task according to an analysis result.

[0037] If the calculation task comprises a classical calculation task, performing classical calculation based on the classical calculation task to obtain a classical calculation result.

[0038] If the calculation task comprises a quantum calculation task, performing quantum calculation based on the quantum calculation task to obtain a quantum calculation result.

[0039] Generating a predicted protein structure according to the obtained classical calculation result and / or quantum calculation result.

[0040] According to a third aspect of the present application, an electronic device is provided, comprising a memory, a processor, and a computer program stored in the memory, which, when executed by the processor, implements the above-mentioned method for predicting protein structure from RNA sequence based on quantum computing.

[0041] The RNA sequence-based protein structure prediction system based on quantum computing provided in the present application can more effectively cross energy barriers in a complex energy landscape to find a global optimal solution with a higher probability through the quantum tunneling effect and superposition state characteristics unique to quantum computing. Thus, the problem of inaccurate predicted structure caused by the traditional classical algorithm often falling into a local minimum when searching for the lowest energy conformation of a protein is solved. At the same time, the hybrid architecture of classical computing and quantum computing strips the simple conformation search to classical computing power, avoiding the waste of resources of full quantum simulation, and achieving the optimal balance between computing power cost and prediction accuracy. BRIEF DESCRIPTION OF DRAWINGS

[0042] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed in the embodiment description will be briefly introduced. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor.

[0043] Figure 1 A structure schematic diagram of the RNA sequence-based protein structure prediction system based on quantum computing provided in an embodiment of the present application is shown in the figure.

[0044] Figure 2 A structure schematic diagram of the RNA sequence-based protein structure prediction system based on quantum computing provided in another embodiment of the present application is shown in the figure.

[0045] Figure 3 A structure schematic diagram of the classical computing layer in an embodiment of the present application is shown in the figure.

[0046] Figure 4 A flowchart of the RNA sequence-based protein structure prediction method based on quantum computing provided in an embodiment of the present application is shown in the figure.

[0047] Figure 5 A structure schematic diagram of the electronic device provided in an embodiment of the present application is shown in the figure. DETAILED DESCRIPTION

[0048] To make the objectives, technical solutions, and advantages of the present invention more apparent, exemplary embodiments according to the present invention will be described in detail below with reference to the accompanying drawings. Obviously, the described embodiments are merely a part of the embodiments of the present invention, and not all of the embodiments of the present invention. It should be understood that the present invention is not limited to the exemplary embodiments described herein. Based on the embodiments of the present invention described herein, all other embodiments obtained by those skilled in the art without inventive effort should fall within the protection scope of the present invention.

[0049] In the following description, numerous specific details are set forth in order to provide a more thorough understanding of the invention. However, it will be apparent to those skilled in the art that the invention can be practiced without one or more of these details. In other instances, certain technical features well-known in the art have not been described in order to avoid obscuring the invention.

[0050] It should be understood that the invention can be embodied in various forms and should not be construed as being limited to the embodiments set forth herein. Rather, providing these embodiments will make the disclosure thorough and complete, and will fully convey the scope of the invention to those skilled in the art.

[0051] To fully understand this invention, a detailed structure will be presented in the following description to illustrate the technical solution proposed by this invention. Optional embodiments of the invention are described in detail below; however, in addition to these detailed descriptions, the invention may have other embodiments.

[0052] The following detailed description of some embodiments of the present invention is provided in conjunction with the accompanying drawings. Unless otherwise specified, the following embodiments and features can be combined with each other.

[0053] To improve the accuracy, efficiency, and computational resource utilization of protein structure prediction results, the first aspect of this invention provides a quantum computing-based RNA sequence prediction protein structure system, such as... Figure 1 As shown, the quantum computing-based RNA sequence prediction protein structure system includes: a user interaction terminal layer 10, a classical computing layer 20, and a quantum computing cloud platform layer 30.

[0054] User interaction terminal layer 10 is used to obtain the target RNA sequence input by the user.

[0055] As an example, the user interaction terminal layer 10 can also visualize the predicted protein structure generated by the classical computing layer 20.

[0056] The classical computing layer 20 is connected with the user interaction terminal layer 10 and the quantum computing cloud platform layer 30, and is used for processing and analyzing the target RNA sequence, distributing the computing task according to the analysis result, and generating the predicted protein structure according to the obtained computing result.

[0057] The computing result includes a classical computing result and / or a quantum computing result.

[0058] The quantum computing cloud platform layer 30 is used for computing the quantum computing task distributed by the classical computing layer 20.

[0059] It should be noted that the quantum computing cloud platform layer 30 can solve the problems of high-dimensional optimization, many-body quantum effect calculation, global conformation sampling and the like that cannot be efficiently processed by classical computing through the dedicated quantum hardware and the protein structure prediction exclusive quantum algorithm, and break through the upper limit of performance and precision of the classical algorithm.

[0060] The RNA sequence protein structure prediction system based on quantum computing in the embodiment of the application can more effectively cross the energy barrier in the complex energy landscape through the quantum tunneling effect and the superposition state characteristics of quantum computing, and find the global optimal solution with a higher probability. Thus, the problem that the traditional classical algorithm often falls into a local minimum value when searching for the lowest energy conformation of the protein, resulting in inaccurate predicted structure, is solved. At the same time, the mixed architecture of classical computing and quantum computing strips the simple conformation search to the classical computing power, avoids the resource waste of full quantum simulation, and realizes the optimal balance between the computing power cost and the prediction accuracy.

[0061] In some embodiments, as shown in Figure 2 The classical computing layer 20 includes a sequence preprocessing module 201, a quantum mapping bridge module 202, a hybrid computing power scheduling module 203 and a structure reconstruction module 204.

[0062] The sequence preprocessing module 201 is connected with the user interaction terminal layer 10, and is used for translating, segmenting and labeling the target RNA sequence.

[0063] Specifically, the sequence preprocessing module 201 is connected with the RNA sequence input interface module 101.

[0064] As an example, the sequence preprocessing module 201 first translates the target RNA sequence into an amino acid polypeptide chain through the built-in standard genetic code table. Then, the amino acid polypeptide chain is segmented according to the maximum available quantum bit number of the quantum computing cloud platform layer 30, and one or more amino acid fragments are obtained. Finally, topological labels are marked in the overlapping regions after segmentation, and the relative positional relationship between the fragments is recorded, so as to facilitate the splicing between the fragments.

[0065] The quantum mapping bridge module 202 is connected with the sequence preprocessing module 201, and is configured to generate a lattice polypeptide and a corresponding control instruction according to an amino acid polypeptide sequence obtained after processing by the sequence preprocessing module 201.

[0066] As an example, the quantum mapping bridge module 202 maps the amino acid fragments into a three-dimensional space lattice, each amino acid fragment is placed on a node of the lattice, converts a continuous protein conformation space into a discrete lattice model, and can generate a corresponding control instruction according to interaction force information between the amino acid fragments.

[0067] The hybrid computing power scheduling module 203 is connected with the quantum mapping bridge module 202 and the quantum computing cloud platform layer 30, and is connected to a classical computing power module, and is configured to analyze a computing task difficulty according to the lattice polypeptide, send the control instruction to the classical computing power module and / or the quantum computing cloud platform layer 30 based on a difficulty analysis result, and obtain a three-dimensional coordinate of the amino acid in the lattice according to a classical computing result and / or a quantum computing result fed back by the classical computing power module and / or the quantum computing cloud platform layer 30.

[0068] The hybrid computing power scheduling module 203 is connected with the cloud API interface module 301 in the quantum computing cloud platform layer 30.

[0069] It should be noted that the amino acid fragments can be divided into different computing task difficulties according to the length and structure of the amino acid fragments. Specifically, if it is a short chain fragment (such as < 50 amino acids), a regular secondary structure (such as a simple a-helix, β-fold), it is determined as a low complexity task; if it is a long chain fragment or contains a hydrophobic core region with random coil, it is determined as a high complexity task.

[0070] As an example, for a low complexity task, the control instruction is sent to the classical computing power module, and a classical algorithm such as molecular dynamics simulation is used for calculation, which is efficient and low in cost. For a high complexity task, the control instruction is sent to the quantum computing cloud platform layer 30, and a quantum superposition state and tunneling effect are used to find a global optimal conformation.

[0071] The structure reconstruction module 204 is connected with the hybrid computing power scheduling module 203, and is configured to generate a predicted protein structure according to the three-dimensional coordinate in the lattice.

[0072] As an example, the structure reconstruction module 204 reads the topological label left by the sequence preprocessing module 201, takes the coordinate coincidence degree of the overlapping region as an “alignment anchor point”, and assembles the three-dimensional structures of multiple subfragments into a complete full-length amino acid chain.

[0073] In this embodiment, by combining the advantages of classical and quantum computing power, the computing power difficulty of long-chain protein prediction is solved, and the structure prediction accuracy and efficiency of various complex scenarios are improved.

[0074] In some embodiments, as shown in FIG. 2A, the sequence preprocessing module 201 comprises a translation unit 2011 and an intelligent segmentation and labeling unit 2012. Figure 3

[0075] The translation unit 2011 is connected with the user interaction terminal layer 10, and is configured to translate the target RNA sequence into an amino acid polypeptide chain.

[0076] The intelligent segmentation and labeling unit 2012 is connected with the translation unit 2011 and the quantum computing cloud platform layer 30, and is configured to obtain a quantum bit threshold in the quantum computing cloud platform layer 30, determine whether the length of the amino acid polypeptide chain exceeds the quantum bit threshold, if yes, cut the amino acid polypeptide chain into a plurality of subdomain fragments with overlapping parts, and label a topological label on the cut overlapping area, and if no, keep the amino acid polypeptide chain as a single domain.

[0077] As an example, the long-chain polypeptide can be cut into a plurality of overlapping subdomain fragments by using a sliding window algorithm, and a topological label is marked on the cut overlapping area as an "alignment anchor point" for subsequent splicing.

[0078] Preferably, each amino acid needs 3-5 quantum bits, so that, for example, 50 bits can carry about 10-15 fragments of amino acids.

[0079] In this embodiment, the sequence preprocessing module 201 not only realizes the accurate biological conversion from RNA to amino acid chain, but also breaks through the limitation of the number of quantum bits by intelligent segmentation and topological labeling adapting to the threshold of quantum hardware, supports quantum-assisted calculation of long-chain proteins, and provides a core basis for subsequent accurate splicing of structures, thereby improving the calculation feasibility and result accuracy.

[0080] In some embodiments, as shown in FIG. 2B, the quantum mapping bridge module 202 comprises a lattice modeling unit 2021 and a parameter encoding unit 2022. Figure 3

[0081] The lattice modeling unit 2021 is connected with the intelligent segmentation and labeling unit 2012, and is configured to map each subdomain fragment or the amino acid polypeptide chain kept as a single domain to a three-dimensional space lattice to obtain a corresponding lattice polypeptide.

[0082] The parameter encoding unit 2022 is connected with the lattice modeling unit 2021, and is configured to convert the general interaction parameters between the amino acid residues in each lattice polypeptide into corresponding control instructions.

[0083] The general interaction parameters include interaction forces.

[0084] ​​It should be noted that the interaction force includes van der Waals force, hydrogen bond, hydrophobic interaction, electrostatic interaction, etc.

[0085] As an example, the extracted various types of interaction forces can be converted into Hamiltonian parameters describing the total energy of the system in quantum mechanics, and the standardized quantum control instruction set is generated based on the Hamiltonian parameters to adapt to the hardware characteristics of the quantum computing cloud platform layer 30; and the classical computing power control instruction set is also generated to adapt to the classical computing power module according to the extracted various types of interaction forces.

[0086] In this embodiment, the quantum mapping bridge module 202 realizes the discretization conversion of the biological polypeptide structure vector to the quantum computing adaptation by the lattice modeling, and then converts the biophysical interaction between the amino acid residues into a standardized quantum control instruction through parameter encoding, thereby providing a unified and executable computing input basis for the hybrid computing power scheduling.

[0087] In some embodiments, as shown in Figure 3 The hybrid computing power scheduling module 203 includes a computing power routing unit 2031 and a result decoding unit 2032.

[0088] The computing power routing unit 2031 is connected with the quantum mapping bridge module 202 and the quantum computing cloud platform layer 30, and is connected to the classical computing power module, for judging the difficulty of the computing task according to the lattice polypeptide, if the lattice polypeptide belongs to a regular structure short segment, the control instruction corresponding to the lattice polypeptide is sent to the classical computing power module, if the lattice polypeptide does not belong to a regular structure short segment, the control instruction corresponding to the lattice polypeptide is sent to the quantum computing cloud platform layer 30.

[0089] Specifically, the computing power routing unit 2031 is connected with the parameter encoding unit 2022 in the quantum mapping bridge module 202.

[0090] It should be noted that the regular structure short segment refers to a lattice polypeptide with a length not exceeding the quantum bit threshold and a structure with a clear regularity (such as a simple alpha-helix, beta-fold, etc. secondary structure segment), which has low conformation search difficulty and small amount of calculation; the irregular structure short segment includes a complex subdomain after long chain cutting, a hydrophobic core segment containing random coil, etc., which has a complex conformation space and belongs to a high-difficulty task that cannot be efficiently processed by a classical algorithm.

[0091] As an example, the concurrent manager can be used to simultaneously send computing requests of multiple segments to the quantum computing cloud platform layer 30 to realize parallel acceleration.

[0092] The result decoding unit 2032 is connected with the quantum computing cloud platform layer 30 and connected to the classical computing power module, for restoring the classical computing result and / or the quantum computing result to the three-dimensional coordinates of the amino acid in the lattice.

[0093] The classical computing module completes classical computing according to the control instruction to obtain a classical computing result.

[0094] As an example, the result decoding unit 2032 restores the measurement result (0 / 1 bit stream) returned by the quantum computing cloud platform layer 30 into the three-dimensional coordinates of the amino acid in the lattice.

[0095] In this embodiment, the hybrid computing power scheduling module 203 realizes intelligent and accurate shunting of classical and quantum computing power through the computing power routing unit 2031, so that low-difficulty computing tasks are efficiently completed by classical computing power, high-difficulty tasks are processed by quantum computing power, and different types of computing results are uniformly restored to standardized lattice three-dimensional coordinates through the result decoding unit 2032, thereby realizing optimal allocation of computing power resources.

[0096] In some embodiments, as shown in FIG. 2B, the structure reconstruction module 204 includes a topology splicing unit 2041 and a global refinement unit 2042. Figure 3

[0097] The topology splicing unit 2041 is connected with the result decoding unit 2032, and is configured to assemble multiple local optimal structures into a complete full-length chain based on the three-dimensional coordinates in the lattice and by using a rigid body rotation and translation algorithm and a topology label.

[0098] The global refinement unit 2042 is connected with the topology splicing unit 2041, and is configured to perform molecular dynamics relaxation on the full-length chain after splicing to eliminate atomic conflicts at the splicing position, and obtain a predicted protein structure.

[0099] Specifically, the molecular dynamics relaxation algorithm is adopted to perform global refinement on the full-length chain structure based on a classical biophysical force field, simulate the molecular motion of the amino acid in the natural state, let the structure spontaneously adjust the atomic position, bond length, bond angle and spatial conformation under the action of physical force, gradually eliminate the atomic conflicts at the splicing position, and make the entire structure tend to a thermodynamic stable state. After the relaxation optimization is completed, the structure with the lowest energy and the most stable conformation is selected as the final predicted protein structure, and complete atomic coordinates, domain distribution, chemical bond information and other data of the structure are generated to meet the needs of subsequent visualization display and biological function analysis.

[0100] In this embodiment, the structure reconstruction module 204 relies on the overlapping region coordinates and the rigid body algorithm through the topology splicing unit 2041 to accurately and seamlessly assemble the local optimal structures obtained by segment computing into a complete full-length chain, and then eliminates the splicing defects and optimizes the structure thermodynamic stability through the molecular dynamics relaxation of the global refinement unit 2042, so as to finally generate a complete, high-precision and biophysical rule-compliant predicted protein structure, thereby guaranteeing the spatial continuity and biological reliability of the prediction result.

[0101] ​In some embodiments, as shown in Figure 2 The user interaction terminal layer 10 includes an RNA sequence input interface module 101 and a 3D structure visualization display module 102.

[0102] The RNA sequence input interface module 101 is configured to receive a target RNA sequence.

[0103] The 3D structure visualization display module 102 is connected to the classical computing layer 20 and configured to perform 3D visualization display on the predicted protein structure.

[0104] Specifically, the 3D structure visualization display module 102 is connected to the structure reconstruction module 204.

[0105] In this embodiment, the user interaction terminal layer 10 provides a low-threshold, standardized sequence input and task initiation channel for users through the RNA sequence input interface module, and converts abstract protein structure data into an intuitive and interactive 3D model through the 3D structure visualization display module.

[0106] In some embodiments, as shown in Figure 2 The quantum computing cloud platform layer 30 includes a cloud API interface module 301 and a quantum processing module 302.

[0107] The cloud API interface module 301 is connected to the classical computing layer 20 and configured to receive control instructions.

[0108] It should be noted that the quantum control instructions issued by the classical computing layer 20 can be received through a general cloud API communication protocol.

[0109] Specifically, the cloud API interface module 301 also sends the quantum computing results back to the hybrid computing power scheduling module 203 in the classical computing layer.

[0110] The quantum processing module 302 is connected to the cloud API interface module 301 and configured to complete quantum computing according to the control instructions to obtain quantum computing results.

[0111] It should be noted that the quantum processing module 302 can be adapted to different physical implementations of quantum hardware such as superconducting, ion trap, and optical quantum. By running quantum optimization algorithms, the quantum superposition state (simultaneously exploring multiple conformations) and the quantum tunneling effect (crossing local minimum energy barriers) are used to efficiently find the “global optimal conformation” (i.e., the natural stable structure) of the protein with the lowest energy.

[0112] In addition, the present application also provides an RNA sequence prediction protein structure method based on quantum computing, as shown in Figure 4 The RNA sequence prediction protein structure method based on quantum computing includes:

[0113] S1, Obtain the target RNA sequence input by the user.

[0114] S2 processes and analyzes the target RNA sequence and assigns computational tasks based on the analysis results.

[0115] S3. If the computation task includes a classical computation task, then perform classical computation based on the classical computation task to obtain the classical computation result.

[0116] S4. If the computation task includes a quantum computation task, then perform quantum computation based on the quantum computation task to obtain the quantum computation result.

[0117] S5 generates a predicted protein structure based on the obtained classical and / or quantum computation results.

[0118] Other specific embodiments of the quantum computing-based RNA sequence prediction protein structure method of the present invention can be found in the specific embodiments of the quantum computing-based RNA sequence prediction protein structure system of the above embodiments of the present invention.

[0119] In addition, the present invention also provides an electronic device, such as Figure 5 As shown, the controller 500 includes a processor 501 and a memory 503. The processor 501 and the memory 503 are connected, for example, via a bus 502.

[0120] Optionally, the controller 500 may also include a transceiver 504. It should be noted that in practical applications, the transceiver 504 is not limited to one, and the structure of the controller 500 does not constitute a limitation on the embodiments of the present invention.

[0121] Processor 501 may be a CPU (Central Processing Unit), a general-purpose processor, a DSP (Digital Signal Processor), an ASIC (Application Specific Integrated Circuit), an FPGA (Field Programmable Gate Array), or other programmable logic devices, transistor logic devices, hardware components, or any combination thereof. It can implement or execute the various exemplary logic blocks, modules, and circuits described in conjunction with the disclosure of this invention. Processor 501 may also be a combination that implements computational functions, such as including one or more microprocessor combinations, a combination of a DSP and a microprocessor, etc.

[0122] The bus 502 can include a path for transmitting information between the above-mentioned components. The bus 502 can be a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus, etc. The bus 502 can be divided into an address bus, a data bus, a control bus, etc. For convenience of representation, Figure 5 Only one thick line is used to represent the bus in the middle, but it does not mean that there is only one bus or only one type of bus.

[0123] The memory 503 is configured to store a computer program corresponding to the method for predicting protein structure of RNA sequence based on quantum computing in the above-mentioned embodiments of the application, and the computer program is controlled and executed by the processor 501. The processor 501 is configured to execute the computer program stored in the memory 503, so as to realize the content shown in the above-mentioned method embodiments.

[0124] The controller 500 includes, but is not limited to, a mobile terminal such as a notebook computer, a PDA (Personal Digital Assistant), a PAD (Tablet Personal Computer), etc., and a fixed terminal such as a desktop computer, etc. Figure 5 The controller 500 shown is only an example, and should not bring any limitation to the function and use range of the embodiments of the application.

[0125] Although the example embodiments have been described herein with reference to the accompanying drawings, it should be understood that the above-mentioned example embodiments are only exemplary, and are not intended to limit the scope of the application. Those of ordinary skill in the art can make various changes and modifications without departing from the scope and spirit of the application. All these changes and modifications are intended to be included within the scope of the application as claimed in the appended claims.

[0126] Those of ordinary skill in the art can realize that the units and algorithm steps of each example described in combination with the embodiments disclosed herein can be realized in electronic hardware, or in a combination of computer software and electronic hardware. Whether the functions are realized in hardware or software depends on the specific application and design constraints of the technical solution. Those of ordinary skill in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of the application.

[0127] In several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the above-described device embodiments are merely illustrative, and the division of the units is merely a logical function division. In actual implementation, another division manner can be used, for example, a plurality of units or components can be combined or integrated into another device, or some features can be omitted or not executed.

[0128] In the specification provided herein, a large number of specific details are described. However, it can be understood that the embodiments of the present application can be practiced without these specific details. In some examples, well-known methods, structures and techniques are not described in detail in order not to obscure the understanding of the present specification.

[0129] Similarly, it should be understood that, in order to simplify the present application and help understand one or more of the various inventive aspects, in the description of the exemplary embodiments of the present application, various features of the present application are sometimes grouped together in a single embodiment, figure, or description of it. However, the method of the present application should not be interpreted as reflecting an intention that the claimed present application requires more features than the features explicitly recited in each claim. Rather, as reflected by the corresponding claims, the inventive point is that the corresponding technical problem can be solved with fewer features than all the features of a certain disclosed single embodiment. Therefore, the claims following the specific embodiments are hereby expressly incorporated into the specific embodiments, in which each claim itself is a separate embodiment of the present application.

[0130] Those skilled in the art can understand that, except for the mutual exclusion between features, all the features disclosed in the specification (including the accompanying claims, abstract and drawings) and all the processes or units of any method or device disclosed in this way can be combined in any combination. Unless explicitly stated otherwise, each feature disclosed in the specification (including the accompanying claims, abstract and drawings) can be replaced by an alternative feature that provides the same, equivalent or similar purpose.

[0131] In addition, those skilled in the art can understand that, although some embodiments described herein include certain features rather than others included in other embodiments, the combination of features of different embodiments means that it is within the scope of the present application and forms different embodiments. For example, in the claims, any one of the claimed embodiments can be used in any combination.

[0132] Various component embodiments of the present application can be implemented in hardware, or as software modules running in one or more processors, or in combinations thereof. As will be appreciated by one skilled in the art, a microprocessor or digital signal processor (DSP) can be used in practice to implement some or all of the functionality of some of the modules according to embodiments of the present application. The present application can also be implemented as an apparatus program (e.g., computer program and computer program product) for performing part or all of the methods described herein. A program implementing the present application can be stored on a computer readable medium, or can have one or more signals. Such signals can be downloaded from an Internet website, or provided on a carrier medium, or in any other form.

[0133] It should be noted that the above-mentioned embodiments illustrate rather than limit the application, and that one skilled in the art will be able to design many alternative embodiments without departing from the scope of the appended claims. In the claims, any reference signs placed between parentheses shall not be construed as limiting the claim. The word 'comprising' does not exclude the presence of elements or steps other than those listed in a claim. The word 'a' or 'an' preceding an element does not exclude the presence of a plurality of such elements. The application can be implemented by means of both hardware and software, and any combination thereof. In a unit claim, several devices can be listed with a conjunction like 'or', but it is to be understood that a combination of these devices can be used in the application. The use of the word 'at least' followed by a list of one or more items does not preclude the presence of only one of the items. The use of the words 'first','second' and 'third', etc. does not limit the scope of the application, but merely identifies a name of a claim. The indefinite articles 'a' and 'an' preceding the name of an element do not exclude the presence of a plurality of such elements.

[0134] The above description is only specific embodiments of the present application or specific explanations of specific embodiments, and the protection scope of the present application is not limited thereto. Any person skilled in the art can easily think of changes or replacements within the technical scope disclosed in the present application, and all such changes or replacements should be covered within the protection scope of the present application. The protection scope of the present application should be subject to the protection scope of the claims.

Claims

1. A quantum computing-based system for predicting protein structure from RNA sequences, characterized in that, The system includes: The user interaction terminal layer is used to obtain the target RNA sequence input by the user. The classical computing layer, connected to the user interaction terminal layer and the quantum computing cloud platform layer, is used to process and analyze the target RNA sequence, allocate computing tasks based on the analysis results, and generate predicted protein structures based on the obtained computing results. The quantum computing cloud platform layer is used to perform quantum computing tasks assigned by the classical computing layer; The calculation results include classical calculation results and / or quantum calculation results.

2. The RNA sequence prediction protein structure system based on quantum computing according to claim 1, characterized in that, The classical computing layer includes: A sequence preprocessing module, connected to the user interaction terminal layer, is used to translate, segment, and label the target RNA sequence; A quantum mapping bridging module, connected to the sequence preprocessing module, is used to generate a lattice-shaped polypeptide and its corresponding control instructions based on the amino acid polypeptide sequence obtained after processing by the sequence preprocessing module. A hybrid computing power scheduling module is connected to the quantum mapping bridging module and the quantum computing cloud platform layer, and also connected to the classical computing power module. It is used to analyze the computational task difficulty based on the lattice-shaped polypeptide, send the control command to the classical computing power module and / or the quantum computing cloud platform layer based on the difficulty analysis result, and obtain the three-dimensional coordinates of the amino acid in the lattice based on the classical computation result and / or the quantum computation result fed back by the classical computing power module and / or the quantum computing cloud platform layer. The structure reconstruction module, connected to the hybrid computing scheduling module, is used to generate predicted protein structures based on the three-dimensional coordinates in the lattice.

3. The RNA sequence prediction protein structure system based on quantum computing according to claim 2, characterized in that, The sequence preprocessing module includes: A translation unit, connected to the user interaction terminal layer, is used to translate the target RNA sequence into an amino acid polypeptide chain. The intelligent segmentation and labeling unit, connected to the translation unit and the quantum computing cloud platform layer, is used to obtain the qubit threshold in the quantum computing cloud platform layer, determine whether the length of the amino acid polypeptide chain exceeds the qubit threshold, and if it does, the amino acid polypeptide chain is segmented into multiple subdomain segments with overlapping regions, and topological tags are marked on the segmented overlapping regions; if it does not exceed the threshold, the amino acid polypeptide chain is kept as a single domain.

4. The RNA sequence prediction protein structure system based on quantum computing according to claim 3, characterized in that, The quantum mapping bridging module includes: A lattice modeling unit, connected to the intelligent segmentation and labeling unit, is used to map each of the subdomain fragments or amino acid polypeptide chains that remain as a single domain onto a three-dimensional spatial lattice to obtain the corresponding lattice-based polypeptide. The parameter encoding unit, connected to the lattice modeling unit, is used to convert the general interaction parameters between amino acid residues in each of the lattice-based polypeptides into corresponding control commands. The general interaction parameters include interaction forces.

5. The RNA sequence prediction protein structure system based on quantum computing according to claim 3, characterized in that, The hybrid computing power scheduling module includes: The computing power routing unit is connected to the quantum mapping bridging module and the quantum computing cloud platform layer, and is also connected to the classical computing power module. It is used to determine the difficulty of the computing task based on the lattice-shaped peptide. If the lattice-shaped peptide is a short fragment with a regular structure, the control command corresponding to the lattice-shaped peptide is sent to the classical computing power module. If the lattice-shaped peptide is not a short fragment with a regular structure, the control command corresponding to the lattice-shaped peptide is sent to the quantum computing cloud platform layer. The result decoding unit is connected to the quantum computing cloud platform layer and the classical computing module, and is used to restore the classical computing results and / or the quantum computing results to the three-dimensional coordinates of amino acids in the crystal lattice. The classical computing module performs classical calculations according to the control instructions and obtains the classical calculation results.

6. The RNA sequence prediction protein structure system based on quantum computing according to claim 5, characterized in that, The structural reconstruction module includes: The topology splicing unit, connected to the result decoding unit, is used to assemble multiple locally optimal structures into a complete full-length chain based on the three-dimensional coordinates in the lattice and using the topology tags through a rigid body rotation and translation algorithm. The global refinement unit, connected to the topology splicing unit, is used to perform molecular dynamics relaxation on the spliced ​​full-length chain, eliminate atomic conflicts generated at the splicing points, and obtain the predicted protein structure.

7. The RNA sequence prediction protein structure system based on quantum computing according to claim 1, characterized in that, The user interaction terminal layer includes: An RNA sequence input interface module is used to receive the target RNA sequence; The 3D structure visualization module is connected to the classical computing layer and is used to perform 3D visualization of the predicted protein structure.

8. The RNA sequence prediction protein structure system based on quantum computing according to claim 2, characterized in that, The quantum computing cloud platform layer includes: The cloud API interface module is connected to the classic computing layer and is used to receive the control commands; The quantum processing module is connected to the cloud API interface module and is used to perform quantum calculations according to the control instructions to obtain the quantum calculation results.

9. A method for predicting protein structure from RNA sequences based on quantum computing, characterized in that, The method includes: Obtain the target RNA sequence input by the user; The target RNA sequence is processed and analyzed, and computational tasks are assigned based on the analysis results; If the computation task includes a classical computation task, then classical computation is performed based on the classical computation task to obtain the classical computation result; If the computational task includes a quantum computation task, then quantum computation is performed based on the quantum computation task to obtain the quantum computation result; Based on the obtained classical calculation results and / or quantum calculation results, a predicted protein structure is generated.

10. An electronic device, characterized in that, It includes a memory, a processor, and a computer program stored in the memory, which, when executed by the processor, implements the quantum computing-based method for predicting protein structure from RNA sequences as described in claim 9.

Images