A comprehensive method for RNA sequence structure analysis and its local environment influence weighting

Abstract

The application relates to a comprehensive RNA sequence structure analysis and a local environment influence weighting method, which comprises the following steps: obtaining an RNA sequence to be processed and inputting an RNA sequence structure analysis model; based on a preset distance constraint condition, screening a to-be-processed base pair from the RNA sequence; wherein the to-be-processed base pair comprises a standard base pair and / or a non-standard base pair; performing initialization processing on a base pairing parameter; based on the displacement parameter, configuring two adjacent bases corresponding to a first base i and a second base j in the to-be-processed base pair, and when the two adjacent bases are determined to be paired, updating the pairing probability according to the weight parameter of the adjacent base pair corresponding to the two adjacent bases; and constructing a pairing weight matrix according to the updated pairing probability corresponding to each to-be-processed base pair. The method considers the influence of the non-standard base pair, improves the accuracy of the pairing weight matrix, and obtains more accurate results when the method is applied to an RNA secondary structure prediction task.

Description

Technical Field

[0001] This invention relates to the field of RNA structure analysis technology, specifically to a comprehensive RNA sequence structure analysis and its weighted method for local environmental influence. Background Technology

[0002] In related technologies, RNA secondary structure mainly consists of stem regions formed by adjacent base pairings and loop structures formed by unpaired bases; hence, it can also be called a stem-loop structure. For stem regions, base pairs near the center (center) are relatively stable, while base pairs at the ends (edges) are relatively unstable. This is mainly because edge bases are more easily influenced by other regions during secondary structure formation. Based on this theory, the CDPFold model considers the influence of whether the bases on either side of the current two bases pair in a standard configuration. If the bases on either side pair, it proves that the region can form a stem region, and therefore the weight of the current standard base pair is increased using a Gaussian function. It is important to note that this algorithm assumes that the two bases form a Watson-Crick pair (AU, CG) or a non-Watson-Crick pair (UG), i.e., a standard base pair. This also leads to its relatively low accuracy in predicting RNA secondary structure.

[0003] It should be noted that the information disclosed in the background section above is only used to enhance the understanding of the background of the present invention, and therefore may include information that does not constitute prior art known to those skilled in the art. Summary of the Invention

[0004] This invention provides a comprehensive RNA sequence structure analysis and its local environmental influence weighting method, a storage medium, a computer program product, and an electronic device, which can obtain a more accurate paired weight matrix, thereby effectively improving the accuracy of RNA secondary structure prediction and overcoming the defects of the prior art to a certain extent.

[0005] Other features and advantages of the invention will become apparent from the following detailed description, or may be learned in part by practice of the invention.

[0006] According to a first aspect of the present invention, a comprehensive RNA sequence structure analysis and its weighted method for local environmental influences are provided, the method comprising:

[0007] Obtain the RNA sequence to be processed and input the RNA sequence into the RNA sequence structure analysis model;

[0008] Based on preset distance constraints, the RNA sequence is screened for base pairs to be processed; wherein, the base pairs to be processed include: standard base pairs and / or non-standard base pairs;

[0009] The base pairing parameters are initialized; the base pairing parameters include: the pairing probability W between the first base i and the second base j in the base pair to be processed, which is used to configure the displacement parameters of adjacent base pairs;

[0010] Based on the displacement parameters, configure the two neighboring bases corresponding to the first base i and the second base j in the base pair to be processed, and when determining the pairing of the two neighboring bases, update the pairing probability according to the weight parameters of the neighboring base pairs corresponding to the two neighboring bases.

[0011] Construct a pairing weight matrix based on the updated pairing probabilities corresponding to each base to be processed.

[0012] In some exemplary embodiments, after inputting the RNA sequence into an RNA sequence structure analysis model, the method further includes:

[0013] Based on the RNA sequence length L, a pairing weight matrix of size L*L is constructed for the RNA sequence, and the initial value of the pairing weight matrix is ​​configured to be 0.

[0014] In some exemplary embodiments, the step of screening base pairs to be processed based on preset distance constraints includes:

[0015] Configure base pairs in the RNA sequence that are at a distance greater than or equal to a preset distance threshold as base pairs to be processed; and

[0016] Base pairs whose distance is less than a preset distance threshold are ignored.

[0017] In some exemplary embodiments, the displacement parameters for configuring adjacent base pairs include: a first displacement parameter α, or a first displacement parameter α and a second displacement parameter β; wherein the initial values ​​of the first displacement parameter α and the second displacement parameter β are 1.

[0018] In some exemplary embodiments, configuring the two neighboring bases corresponding to the first base i and the second base j in the base pair to be processed based on the displacement parameter, and updating the pairing probability according to the weight parameter of the neighboring base pair corresponding to the two neighboring bases when determining the pairing of the two neighboring bases, includes:

[0019] Based on the first displacement parameter α, determine the first neighboring base i-α and the second neighboring base j+α corresponding to the first base i and the second base j;

[0020] When it is determined that the first neighboring base i-α and the second neighboring base j+α have successfully paired, the first matching weight of the corresponding first neighboring base pair is calculated, and the pairing probability W is updated according to the first matching weight.

[0021] Update the first displacement parameter α to α+1, and repeat the above steps based on the updated first displacement parameter α+1.

[0022] In some exemplary embodiments, the method further includes:

[0023] Determine the third adjacent base i+β and the fourth adjacent base j-α corresponding to the first base i and the second base j based on the first displacement parameter α and the second displacement parameter β;

[0024] When the third neighboring base i+β and the fourth neighboring base j-α are successfully paired, the second matching weight of the corresponding second neighboring base pair is calculated, and the pairing probability W is updated according to the second matching weight.

[0025] Update the second displacement parameter β to β+1, and repeat the above steps based on the updated second displacement parameter β+1.

[0026] In some exemplary embodiments, the method further includes:

[0027] Pre-configure the weight parameters for standard base pairs and non-standard base pairs.

[0028] According to a second aspect of the present invention, a storage medium is provided having a computer program stored thereon, which, when executed by a processor, implements the above-described comprehensive RNA sequence structure analysis and its local environmental influence weighting method.

[0029] According to a third aspect of the present invention, a computer program product is provided, on which a computer program is stored, wherein when the computer program is executed by a processor, the above-described comprehensive RNA sequence structure analysis and its local environmental influence weighting method are implemented.

[0030] According to a fourth aspect of the present invention, an electronic device is provided, comprising:

[0031] Processor; and

[0032] Memory for storing the executable instructions of the processor;

[0033] The processor is configured to implement the above-described comprehensive RNA sequence structure analysis and its local environmental influence weighting method when executing the executable instructions.

[0034] The comprehensive RNA sequence structure analysis and its local environmental influence weighting method provided in the embodiments of the present invention, by using preset distance constraints to screen base pairs to be processed, can incorporate the influence of non-standard base pairs when judging base pairing, thereby improving the accuracy of the pairing weight matrix. When applied to RNA secondary structure prediction tasks, it can obtain more accurate RNA secondary structure prediction results.

[0035] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and are not intended to limit the invention. Attached Figure Description

[0036] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the invention and, together with the description, serve to explain the principles of the invention. It is obvious that the drawings described below are merely some embodiments of the invention, and those skilled in the art can obtain other drawings based on these drawings without any inventive effort.

[0037] Figure 1 This diagram illustrates an exemplary embodiment of the present invention: a comprehensive RNA sequence structure analysis and its weighted method for local environmental influences.

[0038] Figure 2 This diagram illustrates a method flow for a pcRNASA model according to an exemplary embodiment of the present invention.

[0039] Figure 3 The diagram illustrates the composition of an electronic device according to an exemplary embodiment of the present invention. Detailed Implementation

[0040] Exemplary embodiments will now be described more fully with reference to the accompanying drawings. However, these exemplary embodiments can be implemented in many forms and should not be construed as limited to the examples set forth herein; rather, they are provided so that the invention will be more comprehensive and complete, and will fully convey the concept of the exemplary embodiments to those skilled in the art. The described features, structures, or characteristics may be combined in any suitable manner in one or more embodiments.

[0041] Furthermore, the accompanying drawings are merely illustrative of the invention and are not necessarily drawn to scale. The same reference numerals in the drawings denote the same or similar parts, and therefore repeated descriptions of them will be omitted. Some block diagrams shown in the drawings are functional entities and do not necessarily correspond to physically or logically independent entities. These functional entities can be implemented in software, in one or more hardware modules or integrated circuits, or in different network and / or processor devices and / or microcontroller devices.

[0042] In related technologies, the CDPFold model considers the impact of whether the bases on either side of the two bases form a standard pair. If the bases on either side form a pair, it proves that the region can form a stem region, and therefore the weight of the current standard base pair is increased according to a Gaussian function. It is important to note that this algorithm is based on the premise that the two bases form a Watson-Crick pair (AU, CG) or a non-Watson-Crick pair (UG), i.e., a standard base pair.

[0043] To address the shortcomings and deficiencies of existing technologies, this exemplary embodiment provides a comprehensive method for RNA sequence structure analysis and weighted analysis of its local environmental influences. (Reference) Figure 1 As shown, the method may specifically include the following steps:

[0044] Step S11: Obtain the RNA sequence to be processed and input the RNA sequence into the RNA sequence structure analysis model;

[0045] Step S12: Based on preset distance constraints, screen the RNA sequence for base pairs to be processed; wherein, the base pairs to be processed include: standard base pairs and / or non-standard base pairs;

[0046] Step S13: Initialize the base pairing parameters; wherein, the base pairing parameters include: the pairing probability W between the first base i and the second base j in the base pair to be processed, which is used to configure the displacement parameters of adjacent base pairs;

[0047] Step S14: Configure the two neighboring bases corresponding to the first base i and the second base j in the base pair to be processed based on the displacement parameters, and update the pairing probability according to the weight parameters of the neighboring base pairs corresponding to the two neighboring bases when determining the pairing of the two neighboring bases.

[0048] Step S15: Construct a pairing weight matrix based on the updated pairing probabilities corresponding to each base to be processed.

[0049] The following will describe in more detail each step of the comprehensive RNA sequence structure analysis and its local environmental influence weighting method in this exemplary embodiment, with reference to the accompanying drawings and embodiments.

[0050] In step S11, the RNA sequence to be processed is obtained and input into the RNA sequence structure analysis model.

[0051] For example, a user can initiate an analysis task for one or more RNA sequences on a terminal device. The terminal device can send the analysis task to a server, which analyzes the RNA sequences, generates corresponding analysis results, and then sends the results back to the terminal device for display. This allows the terminal device and server to collaboratively perform a comprehensive RNA sequence structure analysis and a weighted method for the influence of local environmental factors. Alternatively, the analysis task can be executed locally on the terminal device, using an RNA sequence structure analysis model (pcRNASA model) to perform data analysis and output the results.

[0052] For example, after inputting the RNA sequence into the RNA sequence structure analysis model, the method further includes: constructing a pairing weight matrix of size L*L for the RNA sequence based on the RNA sequence length L, and configuring the initial value of the pairing weight matrix to 0.

[0053] Specifically, for the current input RNA sequence of length L, where the RNA sequence can be composed of four bases: A, U, G, and C, an L*L square matrix with a value of 0 can be initialized first.

[0054] For example, the method includes: pre-configuring weight parameters corresponding to standard base pairs and non-standard base pairs.

[0055] Specifically, based on biological knowledge, base C and base G pairing is the most stable, therefore their initial pairing weight is set to 3; base A and base U pairing is relatively stable, therefore their initial pairing weight is set to 2; base U and base G pairing is relatively unstable, therefore their initial pairing weight is set to 1; non-standard base pairings are very unstable, therefore their initial weight is considered to be 0. The formula can include:

[0056]

[0057] In step S12, the RNA sequence is screened for base pairs to be processed based on a preset distance constraint; wherein the base pairs to be processed include: standard base pairs and / or non-standard base pairs.

[0058] For example, the step of screening base pairs to be processed based on preset distance constraints includes:

[0059] Configure base pairs in the RNA sequence that are at a distance greater than or equal to a preset distance threshold as base pairs to be processed; and

[0060] Base pairs whose distance is less than a preset distance threshold are ignored.

[0061] Specifically, distance constraints can be pre-configured, for example, the distance threshold between two bases can be configured to 3 or 4.

[0062] For example, considering pairing distance constraints, pairing is only considered when the distance between two base pairs is greater than 3. If the distance between base pairs is less than 4, no action is taken, and pairing is not considered.

[0063] This constraint can be expressed as:

[0064] W ij =0, if |ij|<4

[0065] In step S13, the base pairing parameters are initialized; wherein, the base pairing parameters include: the pairing probability W between the first base i and the second base j in the base pair to be processed, which is used to configure the displacement parameters of adjacent base pairs.

[0066] For example, the displacement parameters for configuring adjacent base pairs include: a first displacement parameter α, or a first displacement parameter α and a second displacement parameter β; wherein the initial values ​​of the first displacement parameter α and the second displacement parameter β are 1.

[0067] For example, we can initialize the pairing probability W between base i and base j, and initialize the values ​​of α and β to 1.

[0068] In step S14, the two neighboring bases corresponding to the first base i and the second base j in the base pair to be processed are configured based on the displacement parameter, and when the pairing of the two neighboring bases is determined, the pairing probability is updated according to the weight parameter of the neighboring base pair corresponding to the two neighboring bases.

[0069] For example, step S14 may include:

[0070] Step 141: Determine the first neighboring base i-α and the second neighboring base j+α corresponding to the first base i and the second base j based on the first displacement parameter α;

[0071] Step 142: When it is determined that the first adjacent base i-α and the second adjacent base j+α have successfully paired, calculate the first matching weight of the corresponding first adjacent base pair, and update the pairing probability W according to the first matching weight.

[0072] Step 143: Update the first displacement parameter α to α+1, and repeat the above steps based on the updated first displacement parameter α+1.

[0073] Specifically, it could involve determining whether adjacent bases form a base pair. For example, consider whether base i-α and base j+α are paired; if they are paired, calculate the weight and accumulate it to W, update α to α+1, and continue this step; if they are not paired, the process ends.

[0074] Furthermore, step S14 above may also include:

[0075] Step S144: Determine the third adjacent base i+β and the fourth adjacent base j-α corresponding to the first base i and the second base j based on the first displacement parameter α and the second displacement parameter β;

[0076] Step S145: When it is determined that the third neighboring base i+β and the fourth neighboring base j-α have successfully paired, calculate the second matching weight of the corresponding second neighboring base pair, and update the pairing probability W according to the second matching weight.

[0077] Step S146: Update the second displacement parameter β to β+1, and repeat the above steps based on the updated second displacement parameter β+1.

[0078] Specifically, we can further consider whether adjacent bases in other directions form base pairs to make a judgment. For example, we consider whether base i+β and base j-α are paired. If they are paired, we calculate the weight and accumulate it to W, update β to β+1 and continue this step; if they are not paired, we end the process.

[0079] Specifically, in addition to individual base pairs, this method also considers the influence of the local environment within the RNA secondary structure on pairing tendencies. For example, the pairing tendency of a base is theoretically influenced by the pairing state of adjacent bases, suggesting that pre-paired neighbors may facilitate further pairing by advantageously altering the spatial structure of the RNA. To quantify this, this method improves the calculation of the pairing probability between base i and base j by incorporating the influence of adjacent pairing. This improvement can be expressed by the formula:

[0080] W (i,j) =P left +P (i,j) +P right

[0081] Among them, P left and P right Let represent the pairing probabilities of base i and base j being adjacent. Since base pairs closer to the center are more stable in the stem region, a Gaussian function is chosen as the weight, meaning the closer to the center, the greater the Gaussian weight.

[0082] The formula for calculating the influence weight of neighboring bases using the Gaussian function can be expressed as follows:

[0083] W (i,j) =W (i,j) +P (i,j) +Caussian(α)

[0084] Here, α represents the distance from bases i and j.

[0085] In step S15, a pairing weight matrix is ​​constructed based on the updated pairing probabilities corresponding to each base to be processed.

[0086] Specifically, after determining whether adjacent bases of each base pair to be processed in the RNA sequence are paired, a corresponding pairing weight matrix can be generated based on the obtained configuration probabilities. After repeated calculations, the final weight matrix L*L corresponding to an RNA sequence of length L is determined. This weight matrix can be applied to predict the secondary structure of RNA.

[0087] For example, refer to Figure 2 As shown, the specific workflow of the pcRNASA model may include:

[0088] S1, input an RNA sequence of length L, wherein the RNA sequence is composed of four bases: A, U, G, and C;

[0089] S2, initialize an L*L square matrix with a value of 0;

[0090] S3, First consider the distance constraint: If the distance between base pairs is less than 4, then do nothing and jump to step S7;

[0091] S4, initialize the pairing probability W of base i and base j, and initialize the values ​​of α and β to 1.

[0092] S5, consider whether base i-α and base j+α are paired. If they are paired, calculate the weight and accumulate it to W, update α to α+1 and continue this step; if they are not paired, end the process.

[0093] S6, consider whether base i+β and base j-α are paired. If they are paired, calculate the weight and accumulate it to W, update β to β+1 and continue this step; if they are not paired, end the process.

[0094] S6, obtain the pairing weights of base i and base j and end the calculation;

[0095] S7. Repeat steps S3 to S7 for all base pairs to obtain the pairing weight matrix corresponding to the RNA sequence.

[0096] Specifically, this method does not consider pairing weights based on whether a base pair is a standard base pair. Instead, it comprehensively considers the influence of non-standard base pairs and judges adjacent bases based on preset distance constraints. This is very important for determining the true secondary structure of RNA sequences.

[0097] For example, to further verify the technical effect of the method of the present invention, we applied the pcRNASA model to the RNA secondary structure prediction task to verify whether the performance of RNA secondary structure prediction could be improved after adding a weight matrix. Precision, recall, and F1 score are recognized performance evaluation indicators in RNA secondary structure prediction tasks. The results further show that the present invention can improve the accuracy of RNA secondary structure prediction. Specific steps include:

[0098] 1) Select the benchmark datasets RNAStralign and TR0 from the RNA secondary structure prediction task as the training set, and ArchiveII and TS0 as the test set;

[0099] 2) An RNA sequence characterization model was selected to work with pcRNASA to complete the downstream RNA secondary structure prediction task. Considering the limitations of the characterization model, the training set and the test set were divided into 128 groups and 512 groups according to length, respectively, and sequences longer than 512 were filtered out;

[0100] 3) The performance of pcRNASA was validated using an RNA secondary structure prediction model based on the U-Net architecture. The U-Net architecture mainly consists of an encoder and a decoder. The encoder extracts high-level features from the input data, while the decoder maps the features to prediction results of the same size as the input data. Each encoder submodule consists of three layers: 2D convolution, Dropout, and normalization. The 2D convolution compresses the feature map, Dropout helps alleviate overfitting, and normalization accelerates convergence. Each decoder submodule consists of three layers: 2D transposed convolution, Dropout, and normalization. The 2D transposed convolution restores the size of the feature map, and the Dropout and normalization layers function the same as their counterparts in the encoder.

[0101] In the RNA secondary structure prediction task, U-Net's input is three-dimensional image-like data. In this validation process, the image-like data consists of two parts: L*L*D data obtained by fully stitching together the results of the representation model, and an L*L*1 base pairing weight matrix obtained from the pcRNASA model, where D is the feature dimension of the representation model. When the pairing weight matrix from the pcRNASA model is not included, the input to the U-Net module is L*L*D; when the pairing weight matrix from the pcRNASA model is included, the input to the U-Net module is L*L*(D+1).

[0102] Two contrastive models are trained separately, while other modules remain consistent. The output of U-Net is an L*L*1 single-channel matrix, where each pixel represents the base pairing probability in the RNA sequence. The pairing probabilities are then post-processed to obtain the predicted secondary structure.

[0103] 4) Calculate the precision, recall, and F1 score for the test set using the comparison model obtained in step 3. After obtaining the precision, recall, and F1 score for 128 and 512 groups of the same dataset, calculate their weighted average as the final evaluation result;

[0104] 5) The reliability of the invention is verified by comparing the precision, recall, and F1 score of the two comparative models.

[0105] Table 1 compares the experimental results of the U-Net-based RNA secondary structure prediction model using this invention and without it on the benchmark datasets ArchiveII (training set RNAStralign) and TS0 (training set TR0). The results show that adding the weight matrix of this invention improves the F1 score on both datasets. Specifically, it improves by 3.75% on ArchiveII and by 25% on TS0.

[0106] The above results indicate that the comprehensive RNA sequence structure analysis and local environmental influence weighting method constructed by the present invention can effectively serve the RNA secondary structure prediction task and improve the performance of the RNA secondary structure prediction model.

[0107] Table 1

[0108]

[0109]

[0110] The pcRNASA model provided by the method in this embodiment of the invention considers the influence and importance of non-standard base pairs in the formation of RNA secondary structure. Instead of eliminating non-standard base pairs, it uses distance constraints to select adjacent base pairs and constructs the final weight matrix. This allows it to better perform its function in RNA secondary structure prediction tasks, thereby obtaining more realistic secondary structures and serving practical applications such as RNA vaccine design.

[0111] It should be noted that the above figures are merely illustrative of the processes included in the method according to exemplary embodiments of the present invention, and are not intended to be limiting. It is readily understood that the processes shown in the above figures do not indicate or limit the temporal order of these processes. Furthermore, it is readily understood that these processes may, for example, be executed synchronously or asynchronously in multiple modules.

[0112] It should be noted that although several modules or units of the device for performing actions have been mentioned in the detailed description above, this division is not mandatory. In fact, according to embodiments of the present invention, the features and functions of two or more modules or units described above can be embodied in one module or unit. Conversely, the features and functions of one module or unit described above can be further divided and embodied by multiple modules or units.

[0113] Figure 3 A schematic diagram of an electronic device suitable for implementing embodiments of the present invention is shown.

[0114] It should be noted that, Figure 3 The electronic device 1000 shown is merely an example and should not be construed as limiting the functionality and scope of use of the embodiments of the present invention.

[0115] like Figure 3 As shown, the electronic device 1000 includes a Central Processing Unit (CPU) 1001, which can perform various appropriate actions and processes based on programs stored in Read-Only Memory (ROM) 1002 or programs loaded from Storage Unit 1008 into Random Access Memory (RAM) 1003. The RAM 1003 also stores various programs and data required for system operation. The CPU 1001, ROM 1002, and RAM 1003 are interconnected via a bus 1004. An Input / Output (I / O) interface 1005 is also connected to the bus 1004.

[0116] The following components are connected to I / O interface 1005: an input section 1006 including a keyboard, mouse, etc.; an output section 1007 including a cathode ray tube (CRT), liquid crystal display (LCD), etc., and speakers, etc.; a storage section 1008 including a hard disk, etc.; and a communication section 1009 including a network interface card such as a LAN (Local Area Network) card, modem, etc. The communication section 1009 performs communication processing via a network such as the Internet. A drive 1010 is also connected to I / O interface 1005 as needed. Removable media 1011, such as a disk, optical disk, magneto-optical disk, semiconductor memory, etc., are installed on drive 1010 as needed so that computer programs read from them can be installed into storage section 1008 as needed.

[0117] In particular, according to embodiments of the present invention, the processes described below with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of the present invention include a computer program product comprising a computer program carried on a storage medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via communication section 1009, and / or installed from removable medium 1011. When the computer program is executed by central processing unit (CPU) 1001, it performs various functions defined in the system of this application.

[0118] It should be noted that the storage medium shown in the embodiments of the present invention can be a computer-readable signal medium or a computer-readable storage medium, or any combination thereof. A computer-readable storage medium can be, for example,—but not limited to—an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of a computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM), flash memory, optical fiber, portable compact disc read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In the present invention, a computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. In the present invention, a computer-readable signal medium can include a data signal propagated in baseband or as part of a carrier wave, wherein computer-readable program code is carried. Such transmitted data signals can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. The computer-readable signal medium can also be any storage medium other than a computer-readable storage medium, which can send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device. The program code contained on the storage medium can be transmitted using any suitable medium, including but not limited to wireless, wired, etc., or any suitable combination thereof.

[0119] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of the present invention. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in a block diagram or flowchart, and combinations of blocks in a block diagram or flowchart, may be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0120] The units described in the embodiments of the present invention can be implemented in software or hardware, and the described units can also be located in a processor. The names of these units do not necessarily limit the specific unit itself.

[0121] It should be noted that, as another aspect, this application also provides a storage medium, which may be included in an electronic device or may exist independently without being assembled into the electronic device. The aforementioned storage medium carries one or more programs, which, when executed by an electronic device, cause the electronic device to perform the methods described in the following embodiments. For example, the electronic device may perform... Figure 1 The steps of the method shown.

[0122] In one embodiment, this application provides a computer program product including a computer program that, when executed by a processor, implements the steps in the above-described method embodiments.

[0123] Furthermore, the above figures are merely illustrative of the processes included in the method according to exemplary embodiments of the present invention, and are not intended to be limiting. It is readily understood that the processes shown in the above figures do not indicate or limit the temporal order of these processes. Additionally, it is readily understood that these processes may be executed synchronously or asynchronously, for example, in multiple modules.

[0124] Other embodiments of the invention will readily occur to those skilled in the art upon consideration of the specification and practice of the invention herein. This application is intended to cover any variations, uses, or adaptations of the invention that follow the general principles of the invention and include common knowledge or customary techniques in the art not disclosed herein. The specification and embodiments are to be considered exemplary only, and the true scope and spirit of the invention are indicated by the claims.

[0125] It should be understood that the present invention is not limited to the precise structure described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of the invention is limited only by the appended claims.

Claims

1. A comprehensive RNA sequence structure analysis and weighted method for the influence of its local environment, characterized in that, The method includes: Based on the stability of base pairs, the weight parameters corresponding to standard base pairs and non-standard base pairs are pre-configured, including: the initial pairing weight of base C and base G is set to 3; the initial pairing weight of base A and base U is set to 2; the initial pairing weight of base U and base G is set to 1; and the initial weight of non-standard base pairs is 0. Obtain the RNA sequence to be processed and input the RNA sequence into the RNA sequence structure analysis model; Based on a preset distance constraint, the RNA sequence is screened for base pairs to be processed, including: configuring base pairs in the RNA sequence with a distance greater than or equal to a preset distance threshold as base pairs to be processed; and ignoring base pairs with a distance less than the preset distance threshold; wherein, the base pairs to be processed include: standard base pairs and non-standard base pairs; the constraint is expressed as: W ij =0, if |ij|<4; The base pairing parameters are initialized; wherein, the base pairing parameters include: the pairing probability W between the first base i and the second base j in the base pair to be processed, which is used to configure the displacement parameters of adjacent base pairs; the displacement parameters used to configure adjacent base pairs include: a first displacement parameter α and a second displacement parameter β; wherein, the initial values ​​of the first displacement parameter α and the second displacement parameter β are 1; Based on the displacement parameter, configure the two neighboring bases corresponding to the first base i and the second base j in the base pair to be processed. When determining that the two neighboring bases are paired, update the pairing probability according to the weight parameter of the neighboring base pair corresponding to the two neighboring bases, including: determining the first neighboring base i-α and the second neighboring base j+α corresponding to the first base i and the second base j based on the first displacement parameter α; wherein, consider whether the base i-α and the base j+α are paired, and if they are not paired, the process ends; when it is determined that the first neighboring base i-α and the second neighboring base j+α are successfully paired, calculate the first matching weight of the corresponding first neighboring base pair, and adjust the pairing probability W according to the first matching weight. The process involves updating the first displacement parameter α to α+1 and repeating the above steps based on the updated first displacement parameter α+1. It also involves determining the third adjacent base i+β and the fourth adjacent base j-β corresponding to the first base i and the second base j based on the second displacement parameter β. This process considers whether base i+β and base j-β are paired; if they are not paired, the process ends. When it is determined that the third adjacent base i+β and the fourth adjacent base j-β are successfully paired, the second matching weight of the corresponding second adjacent base pair is calculated, and the pairing probability W is updated based on the second matching weight. The second displacement parameter β is updated to β+1, and the above steps are repeated based on the updated second displacement parameter β+1. A pairing weight matrix is ​​constructed based on the updated pairing probabilities corresponding to each base to be processed; the pairing weight matrix is ​​used to predict the secondary structure of RNA.

2. The method according to claim 1, characterized in that, After inputting the RNA sequence into the RNA sequence structure analysis model, the method further includes: Based on the RNA sequence length L, a pairing weight matrix of size L * L is constructed for the RNA sequence, and the initial value of the pairing weight matrix is ​​configured to be 0.

3. The method according to claim 1, characterized in that, The process of screening base pairs to be processed based on preset distance constraints includes: Configure base pairs in the RNA sequence that are at a distance greater than or equal to a preset distance threshold as base pairs to be processed; and Base pairs whose distance is less than a preset distance threshold are ignored.

4. The method according to claim 1, characterized in that, The method further includes: Three-dimensional image-like data is input into an RNA secondary structure prediction model based on the U-Net architecture; wherein, the three-dimensional image-like data includes L * L * D data obtained by fully stitching the results of the representation model, and a paired weight matrix of size L * L * 1; where D is the feature dimension of the representation model. The RNA secondary structure prediction model based on the U-Net architecture consists of an encoder and a decoder. The encoder extracts high-level features from the input data, and each encoder submodule comprises three layers: a 2D convolutional layer, a Dropout layer, and a normalization layer. The 2D convolutional layer compresses the feature map, the Dropout layer alleviates overfitting, and the normalization layer accelerates convergence. The decoder maps the features to prediction results of the same size as the input data; each decoder submodule comprises three layers: a 2D transposed convolutional layer, a Dropout layer, and a normalization layer. The model output is an L * L * 1 single-channel matrix, where each pixel represents the base pairing probability in the RNA sequence. The pairing probabilities are post-processed to obtain the predicted secondary structure.

5. A storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the comprehensive RNA sequence structure analysis and its local environmental influence weighting method as described in any one of claims 1 to 4.

6. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by the processor, it implements the basic comprehensive RNA sequence structure analysis and the weighted method for local environmental influences as described in any one of claims 1 to 4.

7. An electronic device, characterized in that, include: processor; as well as Memory for storing the executable instructions of the processor; The processor is configured to perform the comprehensive RNA sequence structure analysis and its local environmental influence weighting method as described in any one of claims 1 to 4 by executing the executable instructions.

Images