A prediction method, system and platform based on the effect of base mutation on mRNA splicing

Abstract

The present invention belongs to the technical field of base mutation splicing, and specifically relates to a prediction method, system and platform based on the effect of base mutation on mRNA splicing. Through a prediction method based on the effect of base mutation on mRNA splicing: obtaining base mutation data information, and converting and processing the base mutation data information in real time; constructing an AI model, using the AI ​​model to predict the splicing of sequences before and after the mutation, and generating splicing model prediction data in real time; analyzing and processing the predicted data in real time, and visually displaying the final data of the analysis and processing, as well as the corresponding system and platform, it is possible to predict the changes in transcript cutting caused by base mutations, predict the splicing position through the AI ​​model, and then analyze the possible splicing methods and transcription products, visualize the display, easy to operate, fast, and the results are simple and easy to understand. At the same time, it also provides researchers with a tool to explore the root causes of such mutations and other related research.

Description

Technical Field

[0001] The present invention belongs to the technical field of base mutation splicing, and specifically relates to a prediction method, system and platform based on the influence of base mutation on mRNA splicing. Background Art

[0002] Base mutations may lead to changes in a single amino acid, or may lead to changes in the splicing recognition sequence or other factors, thereby affecting the splicing of exons, and ultimately leading to more serious consequences. According to the statistical data analysis of human SNP pathogenicity on the Malacards website, ≥15% of the pathogenic mutation data occur in introns, and most of these pathogenic data are close to the boundaries of exons and introns. Moreover, the above data do not include pathogenic mutations that affect splicing on exons.

[0003] At present, the splicing prediction tools involved are mainly of the following types: 1. Predicting unknown transcripts by predicting splicing positions; 2. Predicting splicing positions contained in any sequence; 3. Predicting the increment and decrement of splicing donors and acceptors near the mutation position before and after mutation (by comparing the prediction results of the sequences before and after the mutation); 4. Predicting whether the mutation is pathogenic (including comprehensive analysis tools for various mutations); None of the above tools can explain how the mutation affects splicing and the specific impact on the transcription product after affecting splicing. At the same time, it is also convenient for people with a certain professional technical background in biology and AI technology to use and interpret the results. In other words, the existing processing methods are difficult to use and interpret the results.

[0004] In other words, traditional prediction operations cannot predict the changes in transcript cutting caused by base mutations, and there is no corresponding AI model to predict the cutting position and then analyze the possible cutting methods and transcription products; in addition, traditional operations cannot achieve visual display, and the operation is cumbersome and inefficient, and the generated prediction results are obscure and difficult to understand. In view of the above technical problems and defects, it is necessary to propose a prediction method, system and platform based on the influence of base mutations on mRNA splicing. Summary of the invention

[0005] In view of the above technical problems and defects, the present invention provides a prediction method, system and platform based on the effect of base mutation on mRNA splicing, that is to say:

[0006] The first object of the present invention is to provide a prediction method based on the effect of base mutation on mRNA splicing;

[0007] The second object of the present invention is to provide a prediction system based on the effect of base mutation on mRNA splicing;

[0008] The third object of the present invention is to provide a prediction platform based on the effect of base mutation on mRNA splicing;

[0009] The first object of the present invention is achieved in this way: the method specifically comprises the following steps:

[0010] Acquiring base mutation data information, and converting and processing the base mutation data information in real time;

[0011] Constructing an AI model, using the AI ​​model to predict the splicing of sequences before and after the mutation, and generating splicing model prediction data in real time;

[0012] The predicted data is analyzed and processed in real time, and the final data of the analysis and processing is displayed visually.

[0013] Furthermore, after the step of analyzing and processing the predicted data in real time and visually displaying the final data of the analysis and processing, the following steps are also included:

[0014] Obtain feedback data information, and iteratively train the AI ​​model in real time according to the feedback data information.

[0015] Furthermore, the step of obtaining base mutation data information and converting the base mutation data information in real time further includes the following steps:

[0016] Mapping the base mutation data information back to the gene sequence, and performing mutation conversion on the sequence in real time;

[0017] Adjust the annotation information corresponding to the sequence after mutation conversion, and build the base correspondence before and after mutation in real time, in order to confirm the protein product later.

[0018] Furthermore, the step of constructing an AI model, predicting the splicing of sequences before and after the mutation by using the AI ​​model, and generating splicing model prediction data in real time also includes the following steps:

[0019] Build a training dataset and generate sequence length in real time;

[0020] The sequence is encoded and processed, and an AI model is generated in real time.

[0021] Furthermore, the step of constructing an AI model, predicting the splicing of sequences before and after the mutation by using the AI ​​model, and generating splicing model prediction data in real time also includes the following steps:

[0022] Cut the sequence into short sequences with a span of 1 bp per generated sequence length, and perform real-time encoding processing on the short sequences;

[0023] Based on the constructed AI model, real-time data prediction is performed on the short sequences after encoding.

[0024] Furthermore, the step of analyzing and processing the predicted data in real time and visually displaying the final data of the analysis and processing further includes the following steps:

[0025] Determine whether the original cleavage position (i.e., the original cleavage position near the mutation) changes the cleavage type classification;

[0026] Obtain the splice donor position and the splice acceptor position, and generate the predicted value peak position.

[0027] Furthermore, the step of analyzing and processing the predicted data in real time and visually displaying the final data of the analysis and processing further includes the following steps:

[0028] The type of mutation occurring near the splicing donor or acceptor is determined, final splicing mode data information is generated, and the final splicing mode data information is analyzed and processed.

[0029] The second object of the present invention is achieved in this way: the system specifically comprises:

[0030] An acquisition unit, used to acquire base mutation data information and convert and process the base mutation data information in real time;

[0031] Constructing a generation unit, which is used to construct an AI model, and using the AI ​​model to predict the splicing of sequences before and after the mutation, and to generate splicing model prediction data in real time;

[0032] The analysis and processing visualization unit is used to analyze and process the predicted data in real time and visualize the final analysis and processing data.

[0033] Furthermore, the system is also provided with:

[0034] An iterative acquisition unit, used to acquire feedback data information, and iteratively train the AI ​​model in real time according to the feedback data information;

[0035] The acquisition unit is also provided with:

[0036] A mapping conversion module, used to map the base mutation data information back to the gene sequence and perform mutation conversion on the sequence in real time;

[0037] The adjustment construction module is used to adjust the annotation information corresponding to the sequence after mutation conversion and to construct the corresponding relationship between the bases before and after mutation in real time;

[0038] The construction generation unit is also provided with:

[0039] The first generation module is used to construct a training data set and generate sequence length in real time;

[0040] A second generation module is used to encode the sequence and construct a generation AI model in real time;

[0041] The third generation module is used to cut the sequence into short sequences with a span of 1 bp per generated sequence length, and perform real-time encoding processing on the short sequences;

[0042] The data prediction module is used to perform real-time data prediction on the encoded short sequence based on the constructed AI model;

[0043] The analysis and processing visualization unit is also provided with:

[0044] The first determination module is used to determine whether the original cutting position has changed the cutting type classification.

[0045] A fourth generation module is used to obtain the splicing donor position and the splicing acceptor position, and generate the predicted value peak position;

[0046] The second determination module is used to determine the type of mutation occurring near the splicing donor or acceptor, generate final splicing mode data information, and parse and process the final splicing mode data information.

[0047] The third object of the present invention is achieved as follows: the platform specifically includes: a processor, a memory, and a prediction platform control program based on the effect of base mutation on mRNA splicing;

[0048] Wherein the processor executes the prediction platform control program based on the effect of base mutation on mRNA splicing, the prediction platform control program based on the effect of base mutation on mRNA splicing is stored in the memory, and the prediction platform control program based on the effect of base mutation on mRNA splicing implements the steps of the prediction method based on the effect of base mutation on mRNA splicing.

[0049] Compared with the prior art, the present invention has the following beneficial effects:

[0050] The present invention adopts a prediction method based on the effect of base mutation on mRNA splicing: base mutation data information is obtained, and the base mutation data information is converted and processed in real time; an AI model is constructed, and the splicing prediction of the sequences before and after the mutation is performed through the AI ​​model, and splicing model prediction data is generated in real time; the predicted data is analyzed and processed in real time, and the final data of the analysis and processing is visualized, as well as the corresponding system and platform, which can predict the change of transcript cutting caused by base mutation, predict the splicing position through the AI ​​model, and then analyze the possible splicing mode and transcription product, and visualize the display, which is convenient to operate, fast, and the result is simple and easy to understand. At the same time, a tool is provided for researchers to study the impact of such mutations. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0052] Figure 1 A schematic diagram of a method for predicting the effect of base mutation on mRNA splicing according to the present invention;

[0053] Figure 2 A schematic diagram of a process of predicting the effect of base mutation on mRNA splicing according to the present invention;

[0054] Figure 3 This is a schematic diagram of the second process of a prediction method based on the effect of base mutation on mRNA splicing according to the present invention;

[0055] Figure 4 The third process diagram of the prediction method based on the influence of base mutation on mRNA splicing of the present invention is shown;

[0056] Figure 5 It is a schematic diagram of four processes of a prediction method based on the effect of base mutation on mRNA splicing of the present invention;

[0057] Figure 6 The fifth flow chart of the prediction method based on the effect of base mutation on mRNA splicing of the present invention is shown;

[0058] Figure 7 The sixth flow chart of the prediction method based on the effect of base mutation on mRNA splicing of the present invention is shown;

[0059] Figure 8 This is a flow chart of Embodiment 1 of a method for predicting the effect of base mutation on mRNA splicing according to the present invention;

[0060] Fig. 9 This is a schematic diagram of the process of Embodiment 1 of the second embodiment of a method for predicting the effect of base mutation on mRNA splicing according to the present invention;

[0061] Fig.10 This is a schematic diagram of the process of Embodiment 1 of the third embodiment of a method for predicting the effect of base mutation on mRNA splicing according to the present invention;

[0062] Fig.11 This is a schematic diagram of the process of Embodiment 1 of the fourth embodiment of a method for predicting the effect of base mutation on mRNA splicing according to the present invention;

[0063] Fig.12 This is a flow chart of Embodiment 2 of a method for predicting the effect of base mutation on mRNA splicing according to the present invention;

[0064] Fig.13 This is a flow chart of Embodiment 2 of the second method for predicting the effect of base mutation on mRNA splicing according to the present invention;

[0065] Fig.14 A schematic diagram of the architecture of a prediction system based on the effect of base mutation on mRNA splicing according to the present invention;

[0066] Fig.15 A schematic diagram of the architecture of a prediction platform based on the effect of base mutation on mRNA splicing according to the present invention;

[0067] Fig.16 A schematic diagram of a computer-readable storage medium architecture in an embodiment of the present invention;

[0068] The purpose, features and advantages of the present invention will be further described with reference to the accompanying drawings in conjunction with the embodiments. DETAILED DESCRIPTION

[0069] In order to better understand the purpose, technical solutions and advantages of the present invention, the present invention is further described below in conjunction with the accompanying drawings and specific implementation methods. Those skilled in the art can easily understand other advantages and effects of the present invention from the contents disclosed in this specification.

[0070] The present invention may also be implemented or applied through other different specific examples, and the details in this specification may also be modified and changed in various ways based on different viewpoints and applications without departing from the spirit of the present invention.

[0071] It should be noted that if the embodiments of the present invention involve directional indications (such as up, down, left, right, front, back, etc.), the directional indications are only used to explain the relative position relationship, movement status, etc. between the components under a certain specific posture (as shown in the accompanying drawings). If the specific posture changes, the directional indication will also change accordingly.

[0072] In addition, if there are descriptions involving "first", "second", etc. in the embodiments of the present invention, the descriptions of "first", "second", etc. are only used for descriptive purposes and cannot be understood as indicating or suggesting their relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" and "second" may explicitly or implicitly include at least one of the features. Secondly, the technical solutions between the various embodiments can be combined with each other, but they must be based on the ability of ordinary technicians in the field to implement them. When the combination of technical solutions is contradictory or cannot be implemented, it should be deemed that such a combination of technical solutions does not exist and is not within the scope of protection required by the present invention.

[0073] Preferably, the prediction method based on the effect of base mutation on mRNA splicing of the present invention is applied in one or more terminals or servers. The terminal is a device that can automatically perform numerical calculations and / or information processing according to pre-set or stored instructions, and its hardware includes but is not limited to microprocessors, application specific integrated circuits (ASIC), programmable gate arrays (FPGA), digital signal processors (DSP), embedded devices, etc.

[0074] The terminal can be a computing device such as a desktop computer, a notebook, a PDA, a cloud server, etc. The terminal can interact with the client through a keyboard, a mouse, a remote control, a touch pad, or a voice control device.

[0075] like Figure 1-16 As shown, the present invention realizes a prediction method, system and platform based on the influence of base mutation on mRNA splicing.

[0076] like Figure 1-7 , which is a flow chart of a method for predicting the effect of base mutations on mRNA splicing provided by an embodiment of the present invention.

[0077] In this embodiment, the method for predicting the effect of base mutation on mRNA splicing can be applied to a terminal or a fixed terminal with a display function, and the terminal is not limited to a personal computer, a smart phone, a tablet computer, a desktop computer or an all-in-one computer equipped with a camera, etc.

[0078] The method for predicting the effect of base mutation on mRNA splicing can also be applied to a hardware environment consisting of a terminal and a server connected to the terminal via a network. The network includes but is not limited to: a wide area network, a metropolitan area network or a local area network. The method for predicting the effect of base mutation on mRNA splicing according to the embodiment of the present invention can be executed by a server, by a terminal, or by both a server and a terminal.

[0079] For example, for a terminal that needs to perform a prediction based on the effect of base mutation on mRNA splicing, the function of predicting the effect of base mutation on mRNA splicing provided by the method of the present invention can be directly integrated on the terminal, or a client for implementing the method of the present invention can be installed. For another example, the method provided by the present invention can also be run on a server or other device in the form of a software development kit (SDK), and an interface for the function of predicting the effect of base mutation on mRNA splicing is provided in the form of SDK, and the terminal or other device can implement the function of predicting the effect of base mutation on mRNA splicing through the provided interface.

[0080] The present invention will be further described below in conjunction with the accompanying drawings.

[0081] like Figure 1 As shown, the present invention provides a prediction method based on the effect of base mutation on mRNA splicing, and the method specifically comprises the following steps:

[0082] S1. Acquire base mutation data information, and convert and process the base mutation data information in real time;

[0083] S2. Building an AI model, using the AI ​​model to predict the splicing of sequences before and after the mutation, and generating splicing model prediction data in real time;

[0084] S3. Analyze and process the predicted data in real time, and visualize the final data of the analysis and processing.

[0085] After the step of analyzing and processing the predicted data in real time and visually displaying the final data of the analysis and processing, the following steps are also included:

[0086] S4. Obtain feedback data information, and iteratively train the AI ​​model in real time according to the feedback data information.

[0087] The step of obtaining base mutation data information and converting the base mutation data information in real time also includes the following steps:

[0088] S11, mapping the base mutation data information back to the gene sequence, and performing mutation conversion on the sequence in real time;

[0089] S12. Adjust the annotation information corresponding to the sequence after mutation conversion, and construct the base correspondence before and after mutation in real time, in order to confirm the protein product later.

[0090] The step of constructing an AI model, predicting the splicing of sequences before and after the mutation by using the AI ​​model, and generating splicing model prediction data in real time also includes the following steps:

[0091] S21, construct a training data set and generate sequence length in real time;

[0092] S22, encoding the sequence and generating an AI model in real time.

[0093] The step of constructing an AI model, predicting the splicing of sequences before and after the mutation by using the AI ​​model, and generating splicing model prediction data in real time also includes the following steps:

[0094] S23, cutting the sequence into short sequences with a span of 1 bp per generated sequence length, and encoding the short sequences in real time;

[0095] S24. Based on the constructed AI model, real-time data prediction is performed on the short sequence after encoding.

[0096] The step of analyzing and processing the predicted data in real time and visually displaying the final data of the analysis and processing also includes the following steps:

[0097] S31, determining whether the original cleavage position (the original cleavage position near the mutation) has changed the cleavage type classification; that is, determining whether the original cleavage position has been changed due to the mutation;

[0098] S32, obtaining the splicing donor position and the splicing acceptor position, and generating the predicted value peak position, analyzing the most likely cutting mode according to the predicted corresponding data of the sequence before and after the mutation, and obtaining the corresponding predicted correlation coefficient.

[0099] The step of analyzing and processing the predicted data in real time and visually displaying the final data of the analysis and processing also includes the following steps:

[0100] S33, determining the type of mutation occurring near the splicing donor or acceptor, generating final splicing mode data information, and parsing the final splicing mode data information; that is, determining the position of the splicing donor or splicing acceptor near the mutation and the mutation type of the product.

[0101] Specifically, in the scheme of the present invention, Figure 2As shown in the figure, the main processing flow of the prediction method system is: input the mutation base information to be predicted, convert it into data for AI model prediction through code, and then further logically analyze the prediction results. The present invention utilizes the existing gene annotation information, and mainly analyzes the impact of mutations on the original splicing pattern, and finally visualizes the results on the web page.

[0102] That is to say, the prediction system of the base mutation affecting shearing of the present invention specifically comprises the following steps:

[0103] Step 1: Input base mutation information, allowing short insertion, deletion and mutation of base fragments.

[0104] Step 2: Perform information conversion processing on the mutation information, mainly locating the genome, intercepting the sequence of a certain area before and after the mutation, and processing the mRNA coding information before and after the mutation.

[0105] Step 3: Use the trained AI model to predict the splicing of sequences before and after mutation.

[0106] The AI ​​model is a deep learning model that is trained through three-classification of existing gene splicing data. It is trained only on the intercepted gene base fragments, and the data is annotated according to the existing actual gene annotation information. The labels are divided into three categories: splicing donors, splicing acceptors, and non-splicing sites.

[0107] Step 4: Analyze the prediction results of the splicing model.

[0108] Step 5: Visualize the final analysis results of the editing.

[0109] Step 6: Collect user feedback information and iteratively train the AI ​​model.

[0110] According to step 2, the data conversion of the present invention includes the conversion of sequences and the conversion of gene annotation information.

[0111] like Figure 3 As shown, the information conversion process for mutation information specifically includes the following steps:

[0112] S011. Map the input mutation information back to the gene sequence.

[0113] S012. Perform mutation conversion on the sequence, including base mutation, insertion and deletion.

[0114] S013. Adjust the annotation information of the mutant sequence accordingly, and record the corresponding relationship between the bases before and after the mutation, so as to compare the splicing positions before and after the mutation in the later stage.

[0115] According to step three, the AI ​​prediction of the present invention includes two parts: the training of the AI ​​model and the use of the AI ​​model.

[0116] like Figure 4 As shown, the AI ​​model predicts the sequence cutting position training specifically includes the following steps:

[0117] S021. Create a training data set with a sequence length of l (l is preferably greater than 20).

[0118] X: intergenic sequence, N: exon sequence, n: intron sequence

[0119] Non-cleavage positions: intergenic, exon, and intron;

[0120] Splice donor: spanning exons and introns, 1 / 2 length on exons, 1 / 2 length on introns;

[0121] Splice acceptor: spans introns and exons, 1 / 2 length is on introns, 1 / 2 length is on exons.

[0122] S022. One-hot encode the sequence.

[0123] S023. Training AI Models

[0124] The trained AI model parameters are archived and used later for predicting splicing positions.

[0125] like Figure 5 As shown in the figure (where X, N, and n in the sequence of length L are all any ATCG bases; and the l in the final (L-l+1) is the length set by the AI ​​model prediction box), using the AI ​​model to predict the sequence cutting position specifically includes the following steps:

[0126] S031. Cut the WT and MT sequences into short sequences of several lengths with a span of 1 bp.

[0127] S032. One-hot encode the sequence.

[0128] S033. Use the trained AI model to predict the data obtained in the previous step.

[0129] Finally, we can get a prediction of whether each short sequence is a cutting position, among which the possible results are non-cutting position, splice donor and splice acceptor. At the same time, the specific prediction value of each type will be recorded as the basis for the credibility of subsequent prediction results.

[0130] like Figure 6 As shown, the information conversion based on the prediction results of the AI ​​model specifically includes the following steps:

[0131] S041. Determine whether the original cutting position is affected by the cutting recognition due to the mutation, thereby changing the cutting prediction classification.

[0132] S042. Compare WT and MT to obtain newly added splice donor and splice acceptor positions, and select the position with the highest prediction value.

[0133] S043. Analyze the final shearing method.

[0134] like Figure 7 As shown, the logic of parsing the cutting mode specifically includes the following steps:

[0135] S051, mutations occurred near the splice donor (acceptor);

[0136] The original cutting position is destroyed.

[0137] In the absence of any splicing donor (acceptor), exon jumping is likely to occur during mRNA transcription.

[0138] There is a new donor (acceptor) position, and mRNA will most likely be cut at the new position during transcription, resulting in base insertion or deletion, which may also cause frameshift or premature termination of transcription.

[0139] There are alternative donor (acceptor) sites (new cutting sites not produced by mutations), and mRNA may be cut at the alternative sites during transcription, or exon jumping may occur.

[0140] The original cutting position still exists;

[0141] In the absence of a splice donor (acceptor), mRNA transcription is not affected.

[0142] There are new donor (acceptor) sites, and there may be three situations: mixed splicing, the coexistence of original splicing + new splicing; new splicing; original splicing.

[0143] There are alternative donor (acceptor) positions, and there may be three situations: alternative position shearing; original position shearing; mixed shearing, where the original splicing position is affected by mutation.

[0144] The original splice position prediction was wrong;

[0145] This indicates that the original splicing position was not correctly identified;

[0146] S042, parsing information of the final editing method;

[0147] exon skipping;

[0148] Whether sequence insertion or deletion leads to frameshift or premature termination of transcription;

[0149] No impact;

[0150] S043. Further training the model based on the data information submitted by the user interaction;

[0151] If the prediction result is wrong, the user will feedback the experimental results to the system, and the model will be continuously retrained and optimized or the logical rules will be optimized to adapt to more mutation situations based on the information submitted by the user.

[0152] The present invention can predict the changes in transcript cutting caused by base mutations, predict the cutting position through AI model, and then analyze the possible cutting mode and transcription products, and display them visually. It is easy to operate, fast, and the results are simple and easy to understand. At the same time, it provides researchers with a tool to study the impact of such mutations.

[0153] Example 1

[0154] like Figure 8-11 As shown, gene: VPS13 synonym: COH1 gene number: 157680 transcript: NM_017890.4 mutation information: c.8697-9A>G

[0155] Wild:---caatttcctag|AGAAGA---

[0156] Predicted shearing:

[0157] Mut:---cag|tttcctagAGAAGA---Insert 8bp frameshift

[0158] The blue column represents the original position in the WT sequence prediction result cutting position, and the red column represents the newly generated cutting position in the MT sequence. The color of the column represents the probability of being predicted as the cutting position. A mutation occurred at the 9 bases on the left side of the exon, and this result shows two cutting methods. The first method: the original position is still predicted as the cutting position, but the probability is much lower than the newly generated cutting position, and it is highly likely that no cutting will be performed here; the second method: the cutting method of the new cutting position will insert a 10bp intron sequence, because the sequence length change is not a multiple of 3, and cutting in this way will eventually cause the protein product encoded by the CDS to produce a frameshift.

[0159] Literature data: Literature: https: / / www.ncbi.nlm.nih.gov / pubmed / 22855652

[0160] The sequencing results in the literature showed that the gene had a mutation from base A to G, and finally formed a hybrid mutation. There are two sequences in the mRNA sequencing analysis data, one is the normal cleavage data of WT, and the other is because the mutation caused the cleavage site to change and a new cleavage position was generated. The cleavage position is located 8 bases upstream of the original cleavage position, and the final protein translation is frameshifted.

[0161] Example 2

[0162] like Figure 12-13 As shown, gene: DNAJB13 gene number: 374407 transcript: NM_153614.3 mutation information: c.68+1G>C

[0163] Wild:---GCCCAGATCAAGCAGGC|gtaagttggggtgggagccag---

[0164] Predicted shearing:

[0165] Mut:---CAAGCAGGCctaagttg ~90bp omitted ~ag|gtaaacctt---100bp frameshift inserted;

[0166] A mutation occurs at the position of one base to the right of exon 1. This result shows that there is only one possible cut, and the color column is blue. Therefore, the original cut position is destroyed after the mutation. The sequence is analyzed by the most likely downstream cut position and finally cut at one of the alternative cut positions. The cutting method causes the sequence to insert 100 bases of the intron. Because the change in sequence length is not a multiple of 3, it will eventually cause the protein product encoded by the CDS to produce a frameshift.

[0167] Reference: https: / / pubmed.ncbi.nlm.nih.gov / 27486783 /

[0168] The sequencing results in the literature also showed that after the base mutation, the sequence was cut 100 bases downstream, and the cds sequence introduced a 100bp intron sequence, resulting in the premature generation of a stop codon and premature termination of the coding.

[0169] To achieve the above objectives, the present invention also provides a prediction system based on the effect of base mutation on mRNA splicing, such as Fig.14 As shown, the system specifically includes:

[0170] An acquisition unit, used to acquire base mutation data information and convert and process the base mutation data information in real time;

[0171] Constructing a generation unit, which is used to construct an AI model, and using the AI ​​model to predict the splicing of sequences before and after the mutation, and to generate splicing model prediction data in real time;

[0172] The analysis and processing visualization unit is used to analyze and process the predicted data in real time and visualize the final analysis and processing data.

[0173] Furthermore, the system is also provided with:

[0174] An iterative acquisition unit, used to acquire feedback data information, and iteratively train the AI ​​model in real time according to the feedback data information;

[0175] The acquisition unit is also provided with:

[0176] A mapping conversion module, used to map the base mutation data information back to the gene sequence and perform mutation conversion on the sequence in real time;

[0177] The adjustment construction module is used to adjust the annotation information corresponding to the sequence after mutation conversion and to construct the corresponding relationship between the bases before and after mutation in real time;

[0178] The construction generation unit is also provided with:

[0179] The first generation module is used to construct a training data set and generate sequence length in real time;

[0180] A second generation module is used to encode the sequence and construct a generation AI model in real time;

[0181] The third generation module is used to cut the sequence into short sequences with a span of 1 bp per generated sequence length, and perform real-time encoding processing on the short sequences;

[0182] The data prediction module is used to perform real-time data prediction on the encoded short sequence based on the constructed AI model;

[0183] The analysis and processing visualization unit is also provided with:

[0184] The first determination module is used to determine whether the original cutting position has changed the cutting type classification.

[0185] A fourth generation module is used to obtain the splicing donor position and the splicing acceptor position, and generate the predicted value peak position;

[0186] The second determination module is used to determine the type of mutation near the splicing donor or acceptor, generate the final splicing mode data information, and parse and process the final splicing mode data information

[0187] Specifically, the details of the method steps corresponding to the system can be found in the above-mentioned system, which will not be repeated here.

[0188] To achieve the above objectives, the present invention also provides a platform based on the prediction of the effect of base mutations on mRNA splicing, such as Fig.15 As shown, it includes: a processor, a memory, and a platform control program based on the prediction of the effect of base mutation on mRNA splicing;

[0189] The processor executes the platform control program based on the prediction of the effect of base mutation on mRNA splicing, the platform control program based on the prediction of the effect of base mutation on mRNA splicing is stored in the memory, and the platform control program based on the prediction of the effect of base mutation on mRNA splicing implements the method steps of predicting the effect of base mutation on mRNA splicing, for example:

[0190] S1. Acquire base mutation data information, and convert and process the base mutation data information in real time;

[0191] S2. Building an AI model, using the AI ​​model to predict the splicing of sequences before and after the mutation, and generating splicing model prediction data in real time;

[0192] S3. Analyze and process the predicted data in real time, and visualize the final data of the analysis and processing.

[0193] After the step of analyzing and processing the predicted data in real time and visually displaying the final data of the analysis and processing, the following steps are also included:

[0194] S4. Obtain feedback data information, and iteratively train the AI ​​model in real time according to the feedback data information.

[0195] The specific details of the steps have been explained above and will not be repeated here.

[0196] In the embodiment of the present invention, the built-in processor of the platform for predicting the effect of base mutation on mRNA splicing can be composed of an integrated circuit, for example, a single packaged integrated circuit, or a plurality of integrated circuits with the same or different functions, including one or more central processing units (CPU), microprocessors, digital processing chips, graphics processors, and combinations of various control chips. The processor uses various interfaces and lines to connect various components, and executes or executes programs or units stored in the memory, and calls data stored in the memory, so as to perform various functions and process data based on the prediction of the effect of base mutation on mRNA splicing;

[0197] The memory is used to store program codes and various data, is installed in a platform based on the prediction of the effect of base mutations on mRNA splicing, and realizes high-speed and automatic access to programs or data during operation.

[0198] The memory includes read-only memory (ROM), random access memory (RAM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), one-time programmable read-only memory (OTPROM), electronically erasable programmable read-only memory (EEPROM), compact disc read-only memory (CD-ROM) or other optical disc storage, magnetic disk storage, magnetic tape storage, or any other computer-readable medium that can be used to carry or store data.

[0199] To achieve the above object, the present invention also provides a computer readable storage medium, such as Fig.16 As shown, the computer-readable storage medium stores a platform control program based on the prediction of the effect of base mutation on mRNA splicing, and the platform control program based on the prediction of the effect of base mutation on mRNA splicing implements the method steps based on the prediction of the effect of base mutation on mRNA splicing, for example:

[0200] S1. Acquire base mutation data information, and convert and process the base mutation data information in real time;

[0201] S2. Building an AI model, using the AI ​​model to predict the splicing of sequences before and after the mutation, and generating splicing model prediction data in real time;

[0202] S3. Analyze and process the predicted data in real time, and visualize the final data of the analysis and processing.

[0203] After the step of analyzing and processing the predicted data in real time and visually displaying the final data of the analysis and processing, the following steps are also included:

[0204] S4. Obtain feedback data information, and iteratively train the AI ​​model in real time according to the feedback data information.

[0205] The specific details of the steps have been explained above and will not be repeated here.

[0206] In the description of the embodiments of the present invention, it should be noted that any process or method description in the flowchart or otherwise described herein may be understood as representing a module, fragment or portion of a code comprising one or more executable instructions for implementing steps of a specific logical function or process, and the scope of the preferred embodiments of the present invention includes alternative implementations, in which functions may not be performed in the order shown or discussed, including performing functions in a substantially simultaneous manner or in reverse order depending on the functions involved, which should be understood by technicians in the technical field to which the embodiments of the present invention belong.

[0207] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processing module, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in combination with these instruction execution systems, devices or apparatuses. For the purposes of this specification, a "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in combination with these instruction execution systems, devices or apparatuses. More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection with one or more wires (electronic devices), a portable computer disk box (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), a fiber optic device, and a portable compact disk read-only memory (CDROM).

[0208] In addition, the computer-readable medium may even be paper or other suitable medium on which the program is printed, since the program can be obtained electronically, for example, by optically scanning the paper or other medium and then editing, interpreting or processing in other suitable ways if necessary, and then stored in a computer memory.

[0209] In an embodiment of the present invention, in order to achieve the above-mentioned purpose, the present invention further provides a chip system, wherein the chip system comprises at least one processor, and when the program instructions are executed in the at least one processor, the chip system performs the method steps of predicting the effect of base mutation on mRNA splicing, for example:

[0210] S1. Acquire base mutation data information, and convert and process the base mutation data information in real time;

[0211] S2. Building an AI model, using the AI ​​model to predict the splicing of sequences before and after the mutation, and generating splicing model prediction data in real time;

[0212] S3. Analyze and process the predicted data in real time, and visualize the final data of the analysis and processing.

[0213] After the step of analyzing and processing the predicted data in real time and visually displaying the final data of the analysis and processing, the following steps are also included:

[0214] S4. Obtain feedback data information, and iteratively train the AI ​​model in real time according to the feedback data information.

[0215] The specific details of the steps have been explained above and will not be repeated here.

[0216] The present invention adopts a prediction method based on the effect of base mutation on mRNA splicing: base mutation data information is obtained, and the base mutation data information is converted and processed in real time; an AI model is constructed, and the splicing prediction of the sequences before and after the mutation is performed through the AI ​​model, and splicing model prediction data is generated in real time; the predicted data is analyzed and processed in real time, and the final data of the analysis and processing is visualized, as well as the corresponding system and platform, which can predict the change of transcript cutting caused by base mutation, predict the splicing position through the AI ​​model, and then analyze the possible splicing mode and transcription product, and visualize the display, which is convenient to operate, fast, and the result is simple and easy to understand. At the same time, a tool is provided for researchers to study the impact of such mutations.

[0217] The above-mentioned embodiments only express several implementation methods of the present invention, and the description thereof is relatively specific and detailed, but it cannot be understood as limiting the scope of the patent of the present invention. It should be pointed out that, for ordinary technicians in this field, several variations and improvements can be made without departing from the concept of the present invention, which all belong to the protection scope of the present invention. Therefore, the protection scope of the patent of the present invention shall be subject to the attached claims.

Claims

1. A prediction method based on the effect of base mutation on mRNA splicing, characterized in that The method specifically comprises the following steps: Acquiring base mutation data information, and converting and processing the base mutation data information in real time; Constructing an AI model, using the AI ​​model to predict the splicing of sequences before and after the mutation, and generating splicing model prediction data in real time, including: constructing a training data set, and generating sequence length in real time; encoding the sequence, and constructing an AI model in real time; cutting the sequence into short sequences with a span of 1 bp per generated sequence length, and encoding the short sequences in real time; and performing data prediction on the encoded short sequences in real time according to the constructed AI model; Among them, the AI ​​model predicts the sequence cutting position training specifically includes the following steps: S021. Create a training data set with a sequence length of l; X: intergenic sequence, N: exon sequence, n: intron sequence Non-cleavage positions: intergenic, exon, and intron; Splice donor: spanning exons and introns, 1 / 2 length on exons, 1 / 2 length on introns; Splice acceptor: spans introns and exons, 1 / 2 length is on introns, 1 / 2 length is on exons; S022, one-hot encode the sequence; S023. Train AI models; The predicted data is analyzed and processed in real time, and the final data of the analysis and processing is displayed visually, including: determining whether the original cutting position has changed the cutting type classification; obtaining the splicing donor position and the splicing acceptor position, and generating the predicted value peak position; determining the type of mutation near the splicing donor or acceptor, generating the final splicing mode data information, and analyzing and processing the final splicing mode data information.

2. A prediction method based on the effect of base mutation on mRNA splicing according to claim 1, characterized in that After the step of analyzing and processing the predicted data in real time and visually displaying the final data of the analysis and processing, the following steps are also included: Obtain feedback data information, and iteratively train the AI ​​model in real time according to the feedback data information.

3. A prediction method based on the effect of base mutation on mRNA splicing according to claim 1, characterized in that The step of obtaining base mutation data information and converting the base mutation data information in real time also includes the following steps: Mapping the base mutation data information back to the gene sequence, and performing mutation conversion on the sequence in real time; Adjust the annotation information corresponding to the sequence after mutation conversion, and build the corresponding relationship between the bases before and after mutation in real time.

4. A prediction system based on the effect of base mutation on mRNA splicing, characterized in that The system specifically comprises: An acquisition unit, used to acquire base mutation data information and convert and process the base mutation data information in real time; Constructing a generation unit, which is used to construct an AI model, and using the AI ​​model to predict the splicing of sequences before and after the mutation, and to generate splicing model prediction data in real time; The construction generation unit is also provided with: The first generation module is used to construct a training data set and generate sequence length in real time; A second generation module is used to encode the sequence and construct a generation AI model in real time; The third generation module is used to cut the sequence into short sequences with a span of 1 bp per generated sequence length, and perform real-time encoding processing on the short sequences; The data prediction module is used to perform real-time data prediction on the encoded short sequence based on the constructed AI model; Among them, the AI ​​model predicts the sequence cutting position training specifically includes the following steps: S021. Create a training data set with a sequence length of l; X: intergenic sequence, N: exon sequence, n: intron sequence Non-cleavage positions: intergenic, exon, and intron; Splice donor: spanning exons and introns, 1 / 2 length on exons, 1 / 2 length on introns; Splice acceptor: spans introns and exons, 1 / 2 length is on introns, 1 / 2 length is on exons; S022, one-hot encode the sequence; S023. Train AI models; An analysis and processing visualization unit is used to analyze and process the predicted data in real time and visualize the final analysis and processing data; The analysis and processing visualization unit is also provided with: The first determination module is used to determine whether the original cutting position has changed the cutting type classification. A fourth generation module is used to obtain the splicing donor position and the splicing acceptor position, and generate the predicted value peak position; The second determination module is used to determine the type of mutation occurring near the splicing donor or acceptor, generate final splicing mode data information, and parse and process the final splicing mode data information.

5. A prediction system based on the effect of base mutation on mRNA splicing according to claim 4, characterized in that The system is also provided with: An iterative acquisition unit, used to acquire feedback data information, and iteratively train the AI ​​model in real time according to the feedback data information; The acquisition unit is also provided with: A mapping conversion module, used to map the base mutation data information back to the gene sequence and perform mutation conversion on the sequence in real time; The adjustment construction module is used to adjust the annotation information corresponding to the sequence after mutation conversion and to construct the corresponding relationship between the bases before and after the mutation in real time.

6. A prediction platform based on the effect of base mutation on mRNA splicing, characterized in that: include: A processor, a memory, and a control program for a prediction platform based on the effect of base mutations on mRNA splicing; Wherein the processor executes the prediction platform control program based on the effect of base mutation on mRNA splicing, the prediction platform control program based on the effect of base mutation on mRNA splicing is stored in the memory, and the prediction platform control program based on the effect of base mutation on mRNA splicing implements the steps of a prediction method based on the effect of base mutation on mRNA splicing as described in any one of claims 1 to 3.

Images