Method and device for predicting siRNA silencing efficiency

Abstract

The embodiment of the invention provides a siRNA silencing efficiency prediction method and device, and relates to the technical field of data processing, the method comprises the following steps: obtaining tissue structure characteristics of mRNA, the tissue structure characteristics comprising tissue structures to which all basic groups in the mRNA belong, and the tissue structures comprising at least one of a convex ring, an inner ring, a multi-branch ring, a stem region, a hairpin ring and a free single chain; determining a matching region complementary with the siRNA base in the mRNA; based on the organization structure features, determining target organization structure features of the matching region; and predicting the silence efficiency of the siRNA to the mRNA based on the structural characteristics of the target tissue. By applying the siRNA silencing efficiency prediction method provided by the embodiment of the invention, a worker can conveniently analyze a prediction result, and then design of a subsequent actual experiment is carried out.

Description

Technical Field

[0001] The present application relates to the field of data processing technology, and in particular to a method and device for predicting siRNA silencing efficiency. Background Art

[0002] In the process of small nucleic acid drug design, the silencing efficiency of small nucleic acid siRNA (Small interfering Ribonucleic Acid) on receptor mRNA (Messenger Ribonucleic Acid) is affected by many factors. It is very difficult to manually consider many influencing factors and it is impossible to accurately quantify them. If siRNA and mRNA are used directly for actual experiments, the experimental costs are very high.

[0003] Therefore, if the silencing efficiency of siRNA on mRNA can be predicted before actual experiments, siRNAs with high predicted silencing efficiency can be screened in advance, and then actual experiments can be carried out on the screened siRNAs and mRNAs, thereby reducing the number of siRNAs required for actual experiments and effectively saving experimental costs. To this end, a solution for predicting the silencing efficiency of siRNA is needed. Summary of the Invention

[0004] The purpose of the present invention is to provide a method and device for predicting the silencing efficiency of siRNA, so as to predict the silencing efficiency of siRNA. The specific technical solution is as follows:

[0005] In a first aspect, the present invention provides a method for predicting siRNA silencing efficiency, the method comprising:

[0006] Obtaining an organizational structure characteristic of messenger ribonucleic acid (mRNA), wherein the organizational structure characteristic includes an organizational structure to which each base in the mRNA belongs, and the organizational structure includes at least one of a bulge loop, an internal loop, a multi-branched loop, a stem region, a hairpin loop, and a free single strand;

[0007] Determining a matching region in the mRNA that is complementary to the short interfering RNA (siRNA) base;

[0008] Determining target tissue structure features of the matching area based on the tissue structure features;

[0009] Based on the structural characteristics of the target tissue, the silencing efficiency of the siRNA on the mRNA is predicted.

[0010] In one embodiment of the present application, the obtaining of the organizational structure characteristics of messenger ribonucleic acid (mRNA) comprises:

[0011] Obtaining a dot-bracket secondary structure sequence of the mRNA, wherein each sequence position in the dot-bracket secondary structure sequence corresponds to a base in the mRNA, indicating that the base is located in a loop structure or a stem structure;

[0012] According to the dot-bracket secondary structure sequence, each base in the mRNA is divided into a basic organizational structure, wherein the basic organizational structure includes a loop structure and a stem structure;

[0013] For each basic tissue structure, all bases contained in the basic tissue structure are determined, and based on the determined bases, the tissue structure to which each base in the basic tissue structure belongs is determined to obtain a tissue structure feature.

[0014] In one embodiment of the present application, determining the organizational structure to which each base in the organizational structure belongs based on the determined base includes:

[0015] Determining that each base in a loop structure that is closed and contains two bases belonging to a stem structure belongs to a hairpin loop;

[0016] determining that each base in a loop structure comprising at least four non-adjacent bases belonging to a stem structure belongs to a multi-branched loop;

[0017] Each base in a loop structure comprising at least four adjacent bases belonging to the stem structure is determined to belong to a bulge loop.

[0018] In one embodiment of the present application, the method further includes:

[0019] Determine the target siRNA with a silencing efficiency higher than the preset efficiency among different siRNAs;

[0020] determining a target matching region in the mRNA that is complementary to the target siRNA base;

[0021] Counting the tissue structures in the target matching area whose occurrence frequency is higher than a preset frequency.

[0022] In one embodiment of the present application, the target tissue structure feature also includes at least one of the following information: the number of tissue structures contained in the matching area, the number of each type of tissue structure contained in the matching area, and the number of intersection nodes contained in the matching area, where the intersection nodes are bases that intersect between different types of tissue structures.

[0023] In one embodiment of the present application, the predicting the silencing efficiency of the siRNA on the mRNA based on the target tissue structural characteristics includes:

[0024] The silencing efficiency of the siRNA on the mRNA is predicted based on the target tissue structure characteristics and the basic characteristics of the matching region, wherein the basic characteristics include at least one of the following characteristics: basic base coding characteristics, thermodynamic characteristics, seed region characteristics, and expert rule characteristics.

[0025] In a second aspect, an embodiment of the present application provides a device for predicting siRNA silencing efficiency, the device comprising:

[0026] a feature acquisition module, configured to obtain an organizational structure feature of messenger ribonucleic acid (mRNA), wherein the organizational structure feature includes an organizational structure to which each base in the mRNA belongs, and the organizational structure includes at least one of a bulge loop, an inner loop, a multi-branched loop, a stem region, a hairpin loop, and a free single strand;

[0027] A region determination module is used to determine the matching region in the mRNA that is complementary to the short interfering RNA siRNA base;

[0028] a target feature determination module, configured to determine a target tissue structure feature of the matching area based on the tissue structure feature;

[0029] The silencing efficiency prediction module is used to predict the silencing efficiency of the siRNA on the mRNA based on the target tissue structure characteristics.

[0030] In one embodiment of the present application, the feature acquisition module includes:

[0031] A sequence acquisition submodule, for obtaining a dot-bracket secondary structure sequence of an mRNA, wherein each sequence position in the dot-bracket secondary structure sequence corresponds to a base in the mRNA, indicating that the base is located in a loop structure or a stem structure;

[0032] A structure division submodule, for dividing each base in the mRNA into a basic organizational structure according to the dot-bracket secondary structure sequence, wherein the basic organizational structure includes a loop structure and a stem structure;

[0033] The feature acquisition submodule is used to determine all bases contained in each basic tissue structure, and based on the determined bases, determine the tissue structure to which each base in the basic tissue structure belongs, so as to obtain tissue structure features.

[0034] In one embodiment of the present application, the feature acquisition submodule is specifically used to:

[0035] For each basic organizational structure, all bases included in the basic organizational structure are determined, and based on the determined bases, the organizational structure to which each base in the basic organizational structure belongs is determined based on the following method:

[0036] Determining that each base in a loop structure that is closed and contains two bases belonging to a stem structure belongs to a hairpin loop;

[0037] determining that each base in a loop structure comprising at least four non-adjacent bases belonging to a stem structure belongs to a multi-branched loop;

[0038] Each base in a loop structure comprising at least four adjacent bases belonging to the stem structure is determined to belong to a bulge loop.

[0039] In one embodiment of the present application, the device further comprises:

[0040] A target siRNA determination module, used to determine a target siRNA having a silencing efficiency higher than a preset efficiency among different siRNAs;

[0041] A target region determination module is used to determine a target matching region in the mRNA that is complementary to the target siRNA base;

[0042] The structure statistics module is used to count the organizational structures in the target matching area whose frequency of appearance is higher than a preset frequency.

[0043] In one embodiment of the present application, the target tissue structure feature also includes at least one of the following information: the number of tissue structures contained in the matching area, the number of each type of tissue structure contained in the matching area, and the number of intersection nodes contained in the matching area, where the intersection nodes are bases that intersect between different types of tissue structures.

[0044] In one embodiment of the present application, the silencing efficiency prediction module is specifically used to:

[0045] The silencing efficiency of the siRNA on the mRNA is predicted based on the target tissue structure characteristics and the basic characteristics of the matching region, wherein the basic characteristics include at least one of the following characteristics: basic base coding characteristics, thermodynamic characteristics, seed region characteristics, and expert rule characteristics.

[0046] In a third aspect, an embodiment of the present application provides an electronic device, including a processor, a communication interface, a memory, and a communication bus, wherein the processor, the communication interface, and the memory communicate with each other via the communication bus;

[0047] Memory for storing computer programs;

[0048] The processor is configured to implement any one of the method steps of the first aspect when executing a program stored in the memory.

[0049] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, any one of the method steps of the first aspect is implemented.

[0050] In a fifth aspect, an embodiment of the present application further provides a computer program product comprising instructions, which, when executed on a computer, enables the computer to execute any of the methods of the first aspect described above.

[0051] Beneficial effects of the embodiments of the present application:

[0052] The present application embodiment provides a kind of siRNA silencing efficiency prediction method, can predict the silencing efficiency of siRNA to mRNA according to the target tissue structure feature of the matching region complementary to the siRNA base in mRNA.The above-mentioned target tissue structure feature can represent the specific tissue structure to which each base in the matching region belongs, and therefore can represent the detailed specific structure of mRNA, therefore, for staff, the readability of the above-mentioned target tissue structure feature is stronger, and staff just can determine the specific structure of matching region by the above-mentioned target tissue structure feature.Therefore, after obtaining the prediction result of silencing efficiency, staff can be more convenient to analyze the prediction result based on the target tissue structure feature with stronger readability, and then carry out the design of subsequent actual experiment. BRIEF DESCRIPTION OF THE DRAWINGS

[0053] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other embodiments can also be obtained based on these drawings.

[0054] Figure 1 A schematic diagram of the process of the first siRNA silencing efficiency prediction method provided in the examples of the present application;

[0055] Figure 2 A schematic diagram of the mRNA organization structure provided in the examples of this application;

[0056] Figure 3 A schematic diagram of a matching area provided in an embodiment of the present application;

[0057] Figure 4 A schematic diagram of the process of the second siRNA silencing efficiency prediction method provided in the examples of the present application;

[0058] Figure 5 A flowchart of a method for obtaining target tissue structure characteristics provided in an embodiment of the present application;

[0059] Figure 6 A schematic diagram of the process of the third siRNA silencing efficiency prediction method provided in the examples of the present application;

[0060] Figure 7 A schematic diagram of the fourth siRNA silencing efficiency prediction method provided in the examples of the present application;

[0061] Figure 8 A schematic diagram of a process for analyzing silencing efficiency provided in an embodiment of the present application;

[0062] Figure 9 The present invention provides a siRNA silencing efficiency prediction device.

[0063] Figure 10 A structural diagram of an electronic device is provided for an embodiment of the present application. DETAILED DESCRIPTION

[0064] The following will be combined with the drawings in the embodiments of this application to clearly and completely describe the technical solutions in the embodiments of this application. Obviously, the embodiments described are only part of the embodiments of this application, not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field based on this application are within the scope of protection of this application.

[0065] In order to predict the silencing efficiency of siRNA against mRNA, the embodiments of the present application provide a method and device for predicting the silencing efficiency of siRNA.

[0066] See also Figure 1 , is a flow chart of the first siRNA silencing efficiency prediction method provided in an embodiment of the present application, comprising the following steps S101-S104.

[0067] S101: Obtain the organizational structure characteristics of mRNA.

[0068] Among them, the above-mentioned organizational structure characteristics represent the organizational structure to which each base in the above-mentioned mRNA belongs, and the above-mentioned organizational structure includes at least one of a bulge loop, an inner loop, a multi-branched loop, a stem region, a hairpin loop, and a free single chain.

[0069] See also Figure 2 , is a schematic diagram of the mRNA organizational structure provided in an embodiment of the present application, in which circles are bases, where A is adenine, G is guanine, C is cytosine, and U is uracil, and the numbers in the figure represent the base numbers.

[0070] The solid-line frame in the figure represents the organizational structure contained in the mRNA, where a1 is a free single strand, a2 is a bulge loop, a3 is an inner loop, a4 is a multi-branched loop, a5 is a stem region, and a6 is a hairpin loop.

[0071] In one embodiment of the present application, each base in the mRNA can be numbered sequentially, and the correspondence between the base number and the type of organizational structure to which the base belongs can be recorded separately. The type of the organizational structure can be represented by type information in the form of characters, symbols, numbers, etc., and the correspondence between the base number and type information can be recorded in the form of a list. Alternatively, only the type information corresponding to each base can be recorded continuously, and the order of the type information is the same as the number of the corresponding base.

[0072] It should be noted that for cross nodes, that is, bases that intersect between different types of organizational structures, the embodiments of the present application consider that the base belongs to two organizational structures, that is, when recording the above correspondence, the base corresponds to the types of two organizational structures.

[0073] In addition, dot-bracket secondary structure sequences are often used in related technologies to represent the structure of mRNA. The above-mentioned dot-bracket secondary structure sequences can indicate whether each base is a base that has been paired with other bases or a free base that has not been paired with other bases, wherein the paired bases are represented by a left bracket "(" or a right bracket ")", and the free bases are represented by a dot symbol ".". Among them, a group of bases between corresponding left brackets and right brackets belong to a stem structure, and consecutive dot symbols belong to a loop structure. That is, compared with the organizational structure features used in the embodiments of the present application, the dot-bracket secondary structure sequence represents the stem structure and the loop structure, but cannot represent the specific type of organizational structure, and has poor readability. In the dot-bracket secondary structure sequence, it only indicates that the cross node belongs to one of the loop structure and the stem structure. Therefore, compared with the dot-bracket secondary structure sequence, the organizational structure features used in the embodiments of the present application are more readable for the staff, and the use of organizational structure features is more conducive to the staff to analyze the prediction results.

[0074] In another embodiment of the present application, the target organizational structure feature further includes at least one of the following information: the number of organizational structures contained in the matching area, the number of each type of organizational structure contained in the matching area, and the number of cross nodes contained in the matching area.

[0075] The number of organizational structures included in the matching area is the total number of all organizational structures. For the same type of organizational structure, it can be counted only once or multiple times according to the actual number of each organizational structure.

[0076] S102: Determine the matching region in the mRNA that is complementary to the siRNA base.

[0077] Specifically, according to the base matching principle, bases A and T are complementary, and G and C are complementary.

[0078] The above-mentioned siRNA is the siRNA for which silencing efficiency prediction is to be performed. In one embodiment of the present application, each base of the siRNA can be traversed to determine the base sequence that is complementary to the siRNA base, and then the region containing the base sequence in the mRNA can be searched as the matching region.

[0079] In another embodiment of the present application, the starting base of the mRNA can be used as a reference base, and the starting base of the siRNA can be overlapped with the reference base to determine whether there is a match. If there is a match, a matching region is obtained. If there is no match, the next base of the reference base is used as a new reference base to continue matching. The above process is repeated until a matching region is determined, or no matching region is found in the mRNA.

[0080] It should be noted that in the embodiments of the present application, it is not necessary to actually prepare siRNA. Researchers only need to design the bases contained in the siRNA and the order of arrangement of the bases to determine the matching region and subsequently calculate the silencing efficiency, thereby saving the labor and industrial costs required for preparing siRNA.

[0081] S103: Based on the tissue structure characteristics, determine the target tissue structure characteristics of the matching area.

[0082] Specifically, since the above tissue structure features can represent the tissue structures to which all bases in the mRNA belong, after determining the matching region, the tissue structures to which the bases contained in the matching region belong can be extracted from the above tissue structure features, thereby obtaining the target tissue structure features.

[0083] See also Figure 3 , is a schematic diagram of a matching area provided in an embodiment of the present application.

[0084] A, C, G, and T in the figure represent bases, and the shaded area in the figure is the matching area.

[0085] S104: Based on the target tissue structure characteristics, predict the silencing efficiency of the siRNA on the mRNA.

[0086] In one embodiment of the present application, the target tissue structure features can be input into a pre-trained silencing efficiency prediction model to obtain the silencing efficiency of siRNA on mRNA. The silencing efficiency prediction model can be trained and verified based on the information of the sample siRNA and mRNA used in the real experiment and the sample silencing efficiency obtained in the real experiment. The data used in the training process are the sample tissue structure features of the sample area in the mRNA matching the sample siRNA, and the sample silencing efficiency obtained by experimenting with the sample siRNA.

[0087] The sample tissue structure characteristics are input into the silencing efficiency model to obtain the output result, which is compared with the sample silencing efficiency, and the model loss is calculated. Then, the model parameters of the silencing efficiency model are adjusted based on the model loss until the preset training termination condition is reached, and a trained silencing efficiency prediction model is obtained.

[0088] The data for the above real experiments can come from open source data or be obtained by staff through experiments conducted by themselves.

[0089] In another embodiment of the present application, the target tissue structural features of the siRNA to be predicted and the sample tissue structural features corresponding to the sample siRNA can be compared to obtain the similarity between the two. The sample silencing efficiency corresponding to the sample siRNA with the highest similarity to the siRNA to be predicted is used as the silencing efficiency of the siRNA to be predicted.

[0090] As can be seen from the above, the siRNA silencing efficiency prediction method provided by the embodiment of the present application can predict the silencing efficiency of siRNA to mRNA based on the target tissue structure characteristics of the matching area complementary to the siRNA base in mRNA. The above-mentioned target tissue structure characteristics can represent the specific tissue structure to which each base in the matching area belongs, and therefore the detailed specific structure of mRNA can be represented. Therefore, the readability of the above-mentioned target tissue structure characteristics is stronger for the staff, and the staff can determine the specific structure of the matching area by the above-mentioned target tissue structure characteristics. Therefore, after obtaining the predicted result of silencing efficiency, the staff can be more convenient to analyze the predicted result based on the target tissue structure characteristics with stronger readability, and then carry out the design of subsequent actual experiments.

[0091] See also Figure 4 , is a flow chart of the second siRNA silencing efficiency prediction method provided in the embodiment of the present application, which is similar to the aforementioned Figure 1 Compared with the embodiment shown, the above step S101 can be implemented by the following steps S101A-S101C.

[0092] S101A: Obtain the dot-bracket secondary structure sequence of mRNA.

[0093] Each sequence position in the dotted bracket secondary structure sequence corresponds to a base in the mRNA, indicating that the base is located in a loop structure or a stem structure.

[0094] Specifically, the above-mentioned dot bracket secondary structure sequence is a method used in the related art to represent the structure of mRNA. The method for obtaining the dot bracket secondary structure sequence and the specific expression form belong to the related art, and the embodiments of this application will not be repeated here. For example, referring to Example a, the above-mentioned dot bracket secondary structure sequence can be "(((..((((…)))).)))", wherein the leftmost left bracket and the rightmost right bracket are a set of corresponding brackets, with a stem structure between the two, and the three consecutive dot symbols in the middle and the left bracket and right bracket on both sides thereof together form a ring structure.

[0095] S101B: Based on the dot-bracket secondary structure sequence above, the individual bases in the mRNA are divided into basic organizational structures.

[0096] Among them, the above-mentioned basic tissue structure includes a ring structure and a stem structure.

[0097] Specifically, a set of bases between corresponding left and right brackets belong to a stem structure, and consecutive dot symbols belong to a loop structure. For details, please refer to Example a above.

[0098] It should be noted that, for the intersection nodes between the ring structure and the stem structure, in this embodiment, the intersection nodes are classified into both the ring structure and the stem structure.

[0099] S101C: For each basic tissue structure, determine all bases contained in the basic tissue structure, and based on the determined bases, determine the tissue structure to which each base in the basic tissue structure belongs, to obtain a tissue structure feature.

[0100] In one embodiment of the present application, the organizational structure to which all bases in each basic organizational structure belong can be determined by following steps AC.

[0101] Step A: Determine whether each base in a loop structure that is closed and contains two bases belonging to the stem structure belongs to the hairpin loop.

[0102] Specifically, for each loop structure, the bases contained in the loop structure that belong to the stem structure are determined. If there are two such bases, the loop structure is determined to be a hairpin loop, and all bases contained in the hairpin loop belong to the hairpin loop.

[0103] Step B: Determine whether each base in a loop structure comprising at least four non-adjacent bases belonging to a stem structure belongs to a multi-branched loop.

[0104] Specifically, for each ring structure, the bases contained in the ring structure that belong to the stem structure are determined. If the number of such bases is greater than or equal to 4, and such bases are not adjacent to each other, then the ring structure is determined to be a multi-branch ring, and all bases contained in the multi-branch ring belong to the multi-branch ring.

[0105] Step C: Determine whether each base in a loop structure comprising at least four adjacent bases belonging to a stem structure belongs to a bulge loop.

[0106] Specifically, for each loop structure, the bases contained in the loop structure that belong to the stem structure are determined. If the number of such bases is greater than or equal to 4 and such bases are adjacent to each other, the loop structure is determined to be a convex loop, and all bases contained in the convex loop belong to the convex loop.

[0107] In addition, the method for determining the stem region is the same as the method for determining the stem structure from the dot-bracket secondary structure sequence shown above, and will not be repeated here.

[0108] Furthermore, the bases corresponding to the points in the dot-bracket secondary structure sequence that are continuous and do not have brackets at both ends are determined as free single strands.

[0109] From the above, it can be seen that in the embodiment of the present application, the organizational structure characteristics of the mRNA required for this application can be automatically generated based on the dot-bracket secondary organizational sequence in the relevant technology, so that the above organizational structure characteristics can be efficiently generated, and then the silencing efficiency of the above siRNA can be predicted efficiently.

[0110] Based on the above method of obtaining the organizational structure characteristics, the target organizational structure characteristics of the matching area can be obtained. Figure 5 , which is a flow chart of a method for obtaining target tissue structure characteristics provided in an embodiment of the present application.

[0111] The process is divided into two main processes: process 1, process 2, and process 3. Process 1 calculates the tissue structure corresponding to each base of the targeted mRNA, that is, obtains the tissue structure characteristics of the mRNA; process 2 processes the siRNA; and process 3 processes the tissue structure characteristics, that is, generates the target tissue structure characteristics.

[0112] Specifically, process 1 includes steps 1.1 to 1.5.

[0113] Step 1.1: Generate the dot-bracket secondary structure sequence of the mRNA.

[0114] Step 1.2: Number the bases at each sequence position and perform pairing processing to determine the basic organizational structure to which each base belongs.

[0115] Step 1.3: Traverse all bases contained in each basic tissue structure.

[0116] Step 1.4: Determine the type of specific tissue structure based on all bases contained in the basic tissue structure.

[0117] For the specific determination method, please refer to the embodiment of step S101C above.

[0118] Step 1.5: Reverse mapping, mapping the type information of the tissue structure to all bases contained in the tissue structure.

[0119] In addition, process 2 includes the following steps 2.

[0120] Step 2: Calculate the matching region in the mRNA that is complementary to the siRNA based on the principle of base complementary pairing.

[0121] Furthermore, process 3 includes the following steps 3.

[0122] Step 3: Extract the target tissue structure features corresponding to the matching area from the tissue structure features.

[0123] The specific process of determining the target organizational structure characteristics can be found in the previous description and will not be repeated here.

[0124] See also Figure 6 , is a schematic diagram of the process of the third siRNA silencing efficiency prediction method provided in the embodiment of the present application, which is similar to the aforementioned Figure 1 Compared with the embodiment shown, the process further includes the following steps S105-S107.

[0125] S105: Determine a target siRNA among different siRNAs whose silencing efficiency is higher than a preset efficiency.

[0126] Specifically, for different siRNAs, the present application can use the embodiments shown above to predict the silencing efficiency of the siRNA, compare the silencing efficiency of different siRNAs with the preset efficiency, and obtain siRNAs with higher silencing efficiency, that is, siRNAs with more obvious inhibitory effects on the targeted mRNA.

[0127] S106: Determine the target matching region in the mRNA that is complementary to the target siRNA base.

[0128] Specifically, the method of determining the target matching area is similar to the aforementioned step S102 and will not be repeated here.

[0129] S107: Counting the organizational structures in the target matching area whose occurrence frequency is higher than a preset frequency.

[0130] In one embodiment of the present application, the number of various types of tissue structures contained in the target matching region corresponding to each target siRNA can be determined respectively.

[0131] For each type of organizational structure, the sum of the number of organizational structures of this type in each target matching area is counted to obtain the occurrence frequency of this type of organizational structure.

[0132] The tissue structures with a statistically significant frequency of occurrence are those that appear more frequently in the target matching region inhibited by siRNA, which has a more pronounced inhibitory effect on the targeted mRNA. Therefore, it can be inferred that if this type of tissue structure is inhibited, a better inhibitory effect may be achieved, that is, a higher silencing efficiency may be obtained.

[0133] Therefore, after obtaining statistically significant tissue structures with a frequency higher than a preset frequency, the staff can conduct subsequent siRNA research and development based on this, and develop siRNA drugs targeting such tissue structures.

[0134] From the above, it can be seen that since the tissue structure characteristics used in the embodiments of the present application can represent the specific structure in the mRNA, after completing the prediction of the silencing efficiency, the specific tissue structure in the suppressed target matching area can be analyzed, so as to analyze which type of tissue structure can achieve a higher silencing efficiency, which can facilitate the staff's subsequent further research and development of siRNA.

[0135] See also Figure 7 , is a flow chart of the fourth siRNA silencing efficiency prediction method provided in the embodiment of the present application, which is similar to the aforementioned Figure 1 Compared with the embodiment shown, the above step S104 can be implemented by the following step S104A.

[0136] S104A: Based on the target tissue structural characteristics and the basic characteristics of the matching region, predict the silencing efficiency of the siRNA on the mRNA.

[0137] Among them, the above-mentioned basic features include at least one of the following features: basic base coding features, thermodynamic features, seed region features, and expert rule features.

[0138] Specifically, the basic base coding features represent the order and base types of the bases in the matching region, including A, T, C, G, and U. The seed region refers to a fragment of mRNA containing 2-8 bases, located within the matching region. Thermodynamic features include the binding energy of each pair of bases in the matching region, as well as the difference in binding energy between the first and last bases. Expert features are the preference for A, T, C, or G bases at each position in the matching region, based on historical research literature and experimental data.

[0139] As can be seen from the above, in addition to using the target tissue structure features, the embodiments of the present application also use the basic features of the matching area to jointly determine the silencing efficiency of siRNA. Using more features can comprehensively refer to various information of the matching area and improve the accuracy of the determined siRNA silencing efficiency.

[0140] See also Figure 8 , is a flow chart of a silencing efficiency analysis provided in an embodiment of the present application, including the following steps S801-S805.

[0141] S801: Obtain experimental data.

[0142] The experimental data includes the siRNA sequence used in the experiment, the mRNA to be targeted, and the experimental results.

[0143] S802: Process the experimental data to obtain features.

[0144] The features include basic base coding features, thermodynamic features, seed region features, expert rule features, and combination structure features.

[0145] S803: Training a silence efficiency model based on the processed features.

[0146] S804: Use the test set to test the silence efficiency model.

[0147] S805: Interpret experimental data based on tissue structural characteristics.

[0148] The specific implementation of the above steps S801-S804 can be found in the above description, and the method of interpreting the experimental data can be found in the embodiment shown in the above steps S105-S107, which will not be repeated here.

[0149] In addition, in order to verify the feasibility of the solution provided in the examples of this application, for the same siRNA and mRNA, this application uses two different prediction methods to predict the silencing efficiency, and then compares the results of the two to obtain verification results.

[0150] The two prediction methods are: using dot-bracket secondary structure sequences to represent mRNA structure, and using the tissue structural features described in the examples of this application to represent mRNA structure. Furthermore, for each prediction method, this application uses two different datasets for verification: an open source dataset and a hybrid dataset obtained by combining data obtained through in-house experiments with open source data.

[0151] See Table 1, which is a verification result table provided in an embodiment of the present application.

[0152] Table 1

[0153]

[0154] As can be seen from Table 1, for the same prediction method, regardless of whether an open source dataset or a mixed dataset is used, the PCC and ROC-AUC values ​​of the prediction results are similar; for the same dataset, different prediction methods are used for prediction, and the PCC and ROC-AUC values ​​of the prediction results are also similar. In other words, using the organizational structure features provided in the embodiment of the present application to predict the silencing efficiency will not have a significant impact on the prediction effect of the silencing efficiency, but the organizational structure features provided in the present application can provide stronger interpretability and readability, which is convenient for staff to conduct subsequent research based on the predicted silencing efficiency.

[0155] Corresponding to the aforementioned siRNA silencing efficiency prediction method, the embodiment of the present application further provides a siRNA silencing efficiency prediction device.

[0156] See also Figure 9 , an embodiment of the present application provides a siRNA silencing efficiency prediction device, the device comprising:

[0157] A feature acquisition module 901 is configured to obtain a structural feature of messenger RNA (mRNA), wherein the structural feature includes a structural feature of each base in the mRNA, wherein the structural feature includes at least one of a bulge loop, an inner loop, a multi-branched loop, a stem region, a hairpin loop, and a free single strand;

[0158] The region determination module 902 is used to determine the matching region in the mRNA that is complementary to the short interfering RNA siRNA base;

[0159] A target feature determination module 903 is configured to determine a target tissue structure feature of the matching area based on the tissue structure feature;

[0160] The silencing efficiency prediction module 904 is used to predict the silencing efficiency of the siRNA on the mRNA based on the target tissue structure characteristics.

[0161] As can be seen from the above, the siRNA silencing efficiency prediction method provided by the embodiment of the present application can predict the silencing efficiency of siRNA to mRNA based on the target tissue structure characteristics of the matching area complementary to the siRNA base in mRNA. The above-mentioned target tissue structure characteristics can represent the specific tissue structure to which each base in the matching area belongs, and therefore the detailed specific structure of mRNA can be represented. Therefore, the readability of the above-mentioned target tissue structure characteristics is stronger for the staff, and the staff can determine the specific structure of the matching area by the above-mentioned target tissue structure characteristics. Therefore, after obtaining the predicted result of silencing efficiency, the staff can be more convenient to analyze the predicted result based on the target tissue structure characteristics with stronger readability, and then carry out the design of subsequent actual experiments.

[0162] In one embodiment of the present application, the feature acquisition module 901 includes:

[0163] A sequence acquisition submodule, for obtaining a dot-bracket secondary structure sequence of an mRNA, wherein each sequence position in the dot-bracket secondary structure sequence corresponds to a base in the mRNA, indicating that the base is located in a loop structure or a stem structure;

[0164] A structure division submodule, for dividing each base in the mRNA into a basic organizational structure according to the dot-bracket secondary structure sequence, wherein the basic organizational structure includes a loop structure and a stem structure;

[0165] The feature acquisition submodule is used to determine all bases contained in each basic tissue structure, and based on the determined bases, determine the tissue structure to which each base in the basic tissue structure belongs, so as to obtain tissue structure features.

[0166] From the above, it can be seen that in the embodiment of the present application, the organizational structure characteristics of the mRNA required for this application can be automatically generated based on the dot-bracket secondary organizational sequence in the relevant technology, so that the above organizational structure characteristics can be efficiently generated, and then the silencing efficiency of the above siRNA can be predicted efficiently.

[0167] In one embodiment of the present application, the feature acquisition submodule is specifically used to:

[0168] For each basic organizational structure, all bases included in the basic organizational structure are determined, and based on the determined bases, the organizational structure to which each base in the basic organizational structure belongs is determined based on the following method:

[0169] Determining that each base in a loop structure that is closed and contains two bases belonging to a stem structure belongs to a hairpin loop;

[0170] determining that each base in a loop structure comprising at least four non-adjacent bases belonging to a stem structure belongs to a multi-branched loop;

[0171] Each base in a loop structure comprising at least four adjacent bases belonging to the stem structure is determined to belong to a bulge loop.

[0172] In one embodiment of the present application, the device further comprises:

[0173] A target siRNA determination module, used to determine a target siRNA having a silencing efficiency higher than a preset efficiency among different siRNAs;

[0174] A target region determination module is used to determine a target matching region in the mRNA that is complementary to the target siRNA base;

[0175] The structure statistics module is used to count the organizational structures in the target matching area whose frequency of appearance is higher than a preset frequency.

[0176] From the above, it can be seen that since the tissue structure characteristics used in the embodiments of the present application can represent the specific structure in the mRNA, after completing the prediction of the silencing efficiency, the specific tissue structure in the suppressed target matching area can be analyzed, so as to analyze which type of tissue structure can achieve a higher silencing efficiency, which can facilitate the staff's subsequent further research and development of siRNA.

[0177] In one embodiment of the present application, the target tissue structure feature also includes at least one of the following information: the number of tissue structures contained in the matching area, the number of each type of tissue structure contained in the matching area, and the number of intersection nodes contained in the matching area, where the intersection nodes are bases that intersect between different types of tissue structures.

[0178] In one embodiment of the present application, the silencing efficiency prediction module 904 is specifically configured to:

[0179] The silencing efficiency of the siRNA on the mRNA is predicted based on the target tissue structure characteristics and the basic characteristics of the matching region, wherein the basic characteristics include at least one of the following characteristics: basic base coding characteristics, thermodynamic characteristics, seed region characteristics, and expert rule characteristics.

[0180] As can be seen from the above, in addition to using the target tissue structure features, the embodiments of the present application also use the basic features of the matching area to jointly determine the silencing efficiency of siRNA. Using more features can comprehensively refer to various information of the matching area and improve the accuracy of the determined siRNA silencing efficiency.

[0181] The present application also provides an electronic device, such as Figure 10 As shown, it includes a processor 1001, a communication interface 1002, a memory 1003 and a communication bus 1004, wherein the processor 1001, the communication interface 1002, and the memory 1003 communicate with each other through the communication bus 1004.

[0182] Memory 1003, used for storing computer programs;

[0183] The processor 1001 is configured to implement any of the steps of the aforementioned siRNA silencing efficiency prediction method when executing the program stored in the memory 1003 .

[0184] When the electronic device provided by the embodiment of the present application is used to predict siRNA silencing efficiency, the siRNA silencing efficiency prediction method provided by the embodiment of the present application can predict the silencing efficiency of siRNA to mRNA based on the target tissue structure characteristics of the matching area complementary to the siRNA base in mRNA. The above-mentioned target tissue structure characteristics can represent the specific tissue structure to which each base in the matching area belongs, and therefore the detailed specific structure of mRNA can be represented. Therefore, the readability of the above-mentioned target tissue structure characteristics is stronger for the staff, and the staff can determine the specific structure of the matching area by the above-mentioned target tissue structure characteristics. Therefore, after obtaining the predicted result of silencing efficiency, the staff can be more convenient to analyze the predicted result based on the target tissue structure characteristics with stronger readability, and then carry out the design of subsequent actual experiments.

[0185] The communication bus mentioned in the electronic device mentioned above may be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus. This communication bus can be divided into an address bus, a data bus, a control bus, etc. For ease of illustration, only one thick line is used in the figure, but this does not mean that there is only one bus or only one type of bus.

[0186] The communication interface is used for communication between the above electronic device and other devices.

[0187] The memory may include random access memory (RAM) or non-volatile memory (NVM), such as at least one disk storage. Alternatively, the memory may be at least one storage device located away from the processor.

[0188] The above-mentioned processor can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, and discrete hardware components.

[0189] In another embodiment provided in the present application, a computer-readable storage medium is provided, wherein a computer program is stored in the computer-readable storage medium. When the computer program is executed by a processor, the steps of any of the above-mentioned siRNA silencing efficiency prediction methods are implemented.

[0190] When the computer-readable storage medium provided by the embodiment of the present application is used to predict siRNA silencing efficiency, the siRNA silencing efficiency prediction method provided by the embodiment of the present application can predict the silencing efficiency of siRNA to mRNA based on the target tissue structure characteristics of the matching region complementary to the siRNA base in mRNA. The above-mentioned target tissue structure characteristics can represent the specific tissue structure to which each base in the matching region belongs, and therefore the detailed specific structure of mRNA can be represented. Therefore, the readability of the above-mentioned target tissue structure characteristics is stronger for the staff, and the staff can determine the specific structure of the matching region by the above-mentioned target tissue structure characteristics. Therefore, after obtaining the predicted result of silencing efficiency, the staff can be more convenient to analyze the predicted result based on the target tissue structure characteristics with stronger readability, and then carry out the design of subsequent actual experiments.

[0191] In another embodiment provided by the present application, a computer program product comprising instructions is also provided, which, when executed on a computer, enables the computer to execute any of the siRNA silencing efficiency prediction methods in the above embodiments.

[0192] When the computer program product provided by the embodiment of the present application is used to predict siRNA silencing efficiency, the siRNA silencing efficiency prediction method provided by the embodiment of the present application can predict the silencing efficiency of siRNA to mRNA based on the target tissue structure characteristics of the matching region complementary to the siRNA base in mRNA. The above-mentioned target tissue structure characteristics can represent the specific tissue structure to which each base in the matching region belongs, and therefore the detailed specific structure of mRNA can be represented. Therefore, the readability of the above-mentioned target tissue structure characteristics is stronger for the staff, and the staff can determine the specific structure of the matching region by the above-mentioned target tissue structure characteristics. Therefore, after obtaining the predicted result of silencing efficiency, the staff can be more convenient to analyze the predicted result based on the target tissue structure characteristics with stronger readability, and then carry out the design of subsequent actual experiments.

[0193] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware or any combination thereof. When software is used for implementation, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from a website, computer, server or data center to another website, computer, server or data center via a wired (e.g., coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) method. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that includes one or more available media integrations. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium (e.g., a solid-state drive (SSD)).

[0194] It should be noted that, in this document, relational terms such as first and second, etc., are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply the existence of any such actual relationship or order between these entities or operations. Moreover, the terms "comprises," "comprising," or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article, or device comprising a series of elements includes not only those elements, but also other elements not explicitly listed, or elements inherent to such process, method, article, or device. In the absence of further limitations, an element defined by the phrase "comprising a ..." does not exclude the presence of other identical elements in the process, method, article, or device comprising the element.

[0195] Each embodiment in this specification is described in a related manner. Similar portions between embodiments can be referenced to each other. Each embodiment focuses on the differences between other embodiments. In particular, since the apparatus, electronic device, computer-readable storage medium, and computer program product embodiments are generally similar to the method embodiments, their descriptions are relatively simplified. For related portions, reference can be made to the descriptions of the method embodiments.

[0196] The above description is only a preferred embodiment of the present application and is not intended to limit the scope of protection of the present application. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present application are included in the scope of protection of the present application.

Claims

1. A method for predicting siRNA silencing efficiency, characterized in that: The method comprises: Obtaining an organizational structure characteristic of messenger ribonucleic acid (mRNA), wherein the organizational structure characteristic includes an organizational structure to which each base in the mRNA belongs, and the organizational structure includes at least one of a bulge loop, an internal loop, a multi-branched loop, a stem region, a hairpin loop, and a free single strand; Determining a matching region in the mRNA that is complementary to the short interfering RNA (siRNA) base; Determining target tissue structure features of the matching area based on the tissue structure features; Based on the structural characteristics of the target tissue, the silencing efficiency of the siRNA on the mRNA is predicted.

2. The method according to claim 1, characterized in that The method of obtaining the organizational structure characteristics of messenger ribonucleic acid (mRNA) comprises: Obtaining a dot-bracket secondary structure sequence of the mRNA, wherein each sequence position in the dot-bracket secondary structure sequence corresponds to a base in the mRNA, indicating that the base is located in a loop structure or a stem structure; According to the dot-bracket secondary structure sequence, each base in the mRNA is divided into a basic organizational structure, wherein the basic organizational structure includes a loop structure and a stem structure; For each basic tissue structure, all bases contained in the basic tissue structure are determined, and based on the determined bases, the tissue structure to which each base in the basic tissue structure belongs is determined to obtain a tissue structure feature.

3. The method according to claim 2, characterized in that Determining the organizational structure to which each base in the organizational structure belongs based on the determined bases includes: Determining that each base in a loop structure that is closed and contains two bases belonging to a stem structure belongs to a hairpin loop; determining that each base in a loop structure comprising at least four non-adjacent bases belonging to a stem structure belongs to a multi-branched loop; Each base in a loop structure comprising at least four adjacent bases belonging to the stem structure is determined to belong to a bulge loop.

4. The method according to claim 1, wherein The method further comprises: Determine the target siRNA with a silencing efficiency higher than the preset efficiency among different siRNAs; determining a target matching region in the mRNA that is complementary to the target siRNA base; Counting the tissue structures in the target matching area whose occurrence frequency is higher than a preset frequency.

5. The method according to any one of claims 1 to 4, characterized in that The target tissue structure feature also includes at least one of the following information: the number of tissue structures contained in the matching area, the number of each type of tissue structure contained in the matching area, and the number of intersection nodes contained in the matching area, where the intersection nodes are bases that intersect between different types of tissue structures.

6. The method according to any one of claims 1 to 4, characterized in that The step of predicting the silencing efficiency of the siRNA on the mRNA based on the target tissue structural characteristics comprises: The silencing efficiency of the siRNA on the mRNA is predicted based on the target tissue structure characteristics and the basic characteristics of the matching region, wherein the basic characteristics include at least one of the following characteristics: basic base coding characteristics, thermodynamic characteristics, seed region characteristics, and expert rule characteristics.

7. A siRNA silencing efficiency prediction device, characterized in that: The device comprises: a feature acquisition module, configured to obtain an organizational structure feature of messenger ribonucleic acid (mRNA), wherein the organizational structure feature includes an organizational structure to which each base in the mRNA belongs, and the organizational structure includes at least one of a bulge loop, an inner loop, a multi-branched loop, a stem region, a hairpin loop, and a free single strand; A region determination module is used to determine the matching region in the mRNA that is complementary to the short interfering RNA siRNA base; a target feature determination module, configured to determine a target tissue structure feature of the matching area based on the tissue structure feature; The silencing efficiency prediction module is used to predict the silencing efficiency of the siRNA on the mRNA based on the target tissue structure characteristics.

8. The device according to claim 7, characterized in that The feature acquisition module includes: A sequence acquisition submodule, for obtaining a dot-bracket secondary structure sequence of an mRNA, wherein each sequence position in the dot-bracket secondary structure sequence corresponds to a base in the mRNA, indicating that the base is located in a loop structure or a stem structure; A structure division submodule, for dividing each base in the mRNA into a basic organizational structure according to the dot-bracket secondary structure sequence, wherein the basic organizational structure includes a loop structure and a stem structure; The feature acquisition submodule is used to determine all bases contained in each basic tissue structure, and based on the determined bases, determine the tissue structure to which each base in the basic tissue structure belongs, so as to obtain tissue structure features.

9. The device according to claim 8, characterized in that The feature acquisition submodule is specifically used to: For each basic organizational structure, all bases included in the basic organizational structure are determined, and based on the determined bases, the organizational structure to which each base in the basic organizational structure belongs is determined based on the following method: Determining that each base in a loop structure that is closed and contains two bases belonging to a stem structure belongs to a hairpin loop; determining that each base in a loop structure comprising at least four non-adjacent bases belonging to a stem structure belongs to a multi-branched loop; Each base in a loop structure comprising at least four adjacent bases belonging to the stem structure is determined to belong to a bulge loop.

10. The device according to claim 7, characterized in that The device further comprises: A target siRNA determination module, used to determine a target siRNA having a silencing efficiency higher than a preset efficiency among different siRNAs; A target region determination module is used to determine a target matching region in the mRNA that is complementary to the target siRNA base; The structure statistics module is used to count the organizational structures in the target matching area whose frequency of appearance is higher than a preset frequency.

11. The device according to any one of claims 7 to 10, characterized in that The target tissue structure feature also includes at least one of the following information: the number of tissue structures contained in the matching area, the number of each type of tissue structure contained in the matching area, and the number of intersection nodes contained in the matching area, where the intersection nodes are bases that intersect between different types of tissue structures.

12. The device according to any one of claims 7 to 10, characterized in that The silencing efficiency prediction module is specifically used to: The silencing efficiency of the siRNA on the mRNA is predicted based on the target tissue structure characteristics and the basic characteristics of the matching region, wherein the basic characteristics include at least one of the following characteristics: basic base coding characteristics, thermodynamic characteristics, seed region characteristics, and expert rule characteristics.

13. An electronic device, characterized in that: It includes a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory communicate with each other via the communication bus; Memory for storing computer programs; A processor is configured to implement any one of the method steps of claims 1-6 when executing a program stored in a memory.

14. A computer-readable storage medium, characterized in that The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method steps of any one of claims 1 to 6 are implemented.

Images