RNA N4-acetylcytidine modification site prediction method and system based on RNAErnie pre-training model

Abstract

The invention relates to an RNAN4-acetylcytidine modification site prediction method and an RNAN4-acetylcytidine modification site prediction system based on an RNAErnie pre-training model. The method comprises the following steps: collecting an RNA sequence data set, inputting the RNA sequence data set into an RNAErnie pre-training model, capturing a context dependency relationship, and extracting global features; performing feature coding through an RNAErnie pre-training model in combination with six traditional feature coding methods; and performing feature dimension reduction in the deep neural network model, inputting the feature dimension reduction result into a soft voting integration model, and integrating prediction results of different classifiers to obtain an RNAN4-acetylcytidine modification site prediction result. Multistage masking is carried out through an RNAErnie pre-training model, and details and physical and chemical attributes of the sequence can be captured in combination with six traditional feature coding modes; feature dimension reduction is automatically performed by using a deep neural network, so that the calculation complexity is reduced and key information is reserved; and the dimensionality-reduced features are input into a soft voting integrated model, and a final prediction result is obtained by integrating a plurality of classifiers, so that the prediction accuracy and robustness are remarkably improved.

Description

Technical Field

[0001] The present invention relates to the field of bioinformatics, and in particular to a method and system for predicting RNAN4-acetylcytidine modification sites based on an RNAErnie pre-training model. Background Art

[0002] To date, more than 170 modified nucleosides have been discovered in RNA. Post-transcriptional chemical modifications of RNA, collectively referred to as the “epitranscriptome,” have substantial effects on gene expression and cellular processes, and play an important role in molecular interactions and intermolecular relationships. N4-acetylcytidine (ac4C) is a common type catalyzed by the enzyme NAT10, which adds an acetyl group to the fourth nitrogen of the cytidine base. Initially discovered in tRNA and rRNA of eukaryotes and prokaryotes, current studies have also identified ac4C in human mRNA, where it can improve translation efficiency, enhance mRNA stability, and regulate gene expression. In addition, increasing evidence suggests that ac4C is associated with a variety of human diseases, including inflammation, metabolic disorders, autoimmune diseases, and cancer. In summary, ac4C modification, as a key post-transcriptional modification of RNA, plays an important role in cellular function and disease processes. Exploring the functions and mechanisms of RNA-ac4C modification sites is crucial to elucidate their biological significance and advance therapeutic strategies for related diseases.

[0003] Traditional RNA-ac4C modification site detection includes biological experimental methods, high-throughput sequencing technology, and computer-assisted analysis methods. Among them, the traditional biological experimental method is the traditional method for detecting ac4C modification in RNA, which mainly includes chemical analysis and immunoassay, which is widely used in laboratories, has high sensitivity and specificity, and is suitable for qualitative and quantitative analysis of specific modifications; high-throughput sequencing technology has been widely used in the whole genome level detection of ac4C modification in recent years, among which MeRIP-seq (mRNA immunoprecipitation sequencing) is the representative. This technology enriches the modification sites in RNA samples and then performs sequencing analysis. It can conduct large-scale exploration and analysis of ac4C modification in the whole genome; computer-assisted analysis methods are bioinformatics tools based on machine learning algorithms. By analyzing RNA sequence, structure, evolutionary conservation and other characteristics, a prediction model is constructed to help researchers quickly identify potential ac4C modification sites.

[0004] However, in traditional RNA-ac4C modification site detection, most biological experimental methods are expensive and time-consuming wet experiments, with high detection costs, complex operations, and low sensitivity and specificity; high-throughput sequencing technology often relies on antibody enrichment, has low resolution, and detection accuracy is limited by antibody quality and background noise; computer-assisted analysis methods rely heavily on traditional feature encoding technology, require complex feature engineering steps, and lack a comprehensive understanding of contextual semantic relationships. Therefore, traditional RNA-ac4C modification site detection methods often have high costs and insufficient information mining, resulting in low accuracy in RNA-ac4C modification site detection. Summary of the invention

[0005] Based on this, in order to solve the above technical problems, a method and system for predicting RNAN4-acetylcytidine modification sites based on the RNAErnie pre-training model is provided, which can be fast, low-cost, and improve the accuracy of the model's RNAN4-acetylcytidine modification site detection.

[0006] A method for predicting RNAN4-acetylcytidine modification sites based on an RNAErnie pre-training model, the method comprising:

[0007] Collecting an RNA sequence data set; the RNA sequence data set includes positive and negative samples;

[0008] Each RNA sequence in the RNA sequence data set is input into the RNAErnie pre-training model for multi-level masking to capture context dependencies and extract global features; and the RNAErnie pre-training model is combined with six traditional feature encoding methods to perform feature encoding on each RNA sequence to obtain encoded high-dimensional features;

[0009] Inputting the encoded high-dimensional features into a deep neural network model to perform feature dimensionality reduction to obtain features after dimensionality reduction;

[0010] The reduced-dimensional features are input into a soft voting integration model, and the prediction results of different classifiers are integrated through the soft voting integration model to obtain the RNAN4-acetylcytidine modification site prediction result;

[0011] The soft voting ensemble model is constructed by XGBoost, MLP, and CatBoost classifiers.

[0012] In one embodiment, the method further comprises:

[0013] Determine an evaluation index, and perform a performance evaluation on the soft voting ensemble model using a ten-fold cross validation method according to the evaluation index to obtain an evaluation result;

[0014] Among them, the evaluation indicators include sensitivity, specificity, accuracy, Matthews correlation coefficient, and area under the curve.

[0015] In one embodiment, the method further comprises:

[0016] Displaying a user interaction interface, and obtaining the RNA sequence to be predicted through the user interaction interface;

[0017] Inputting the RNA sequence to be predicted into the soft voting integrated model, and outputting the RNAN4-acetylcytidine modification site prediction result corresponding to the RNA sequence to be predicted;

[0018] The prediction result of RNAN4-acetylcytidine modification site corresponding to the RNA sequence to be predicted is displayed in the user interaction interface.

[0019] In one embodiment, after collecting the RNA sequence data set, the method further comprises:

[0020] Determine the ratio of data set division;

[0021] Based on the data set division ratio, the RNA sequence data set is subjected to stratified sampling processing to obtain a divided training data set and a test data set.

[0022] In one embodiment, the RNAErnie pre-trained model is based on a knowledge integration enhanced representation framework and combines Transformer layers and a multi-head self-attention mechanism; wherein:

[0023] Input each RNA sequence in the RNA sequence data set into the RNAErnie pre-training model respectively, and calculate the attention score corresponding to each RNA sequence through each attention head based on the multi-head self-attention mechanism;

[0024] The obtained attention scores are connected, and each RNA sequence is mapped to a query, key and value matrix through a linear transformation matrix.

[0025] In one embodiment, each RNA sequence in the RNA sequence data set is input into the RNAErnie pre-training model for multi-level masking, including:

[0026] The RNAErnie pre-training model adopts motif-level masking, subsequence-level masking, and motif-level random masking strategies, combined with coarse-grained types of RNA as vocabulary markers;

[0027] The RNAErnie pre-trained model appends the vocabulary token to the last segment of each RNA sequence to enhance the RNA sequence representation.

[0028] In one embodiment, the high-dimensional features are input into a deep neural network model to perform feature dimensionality reduction to obtain the reduced-dimensional features, including:

[0029] The encoded high-dimensional features are input into a deep neural network model, and through the multi-layer nonlinear mapping of the deep neural network model, the high-dimensional features are mapped from the high-dimensional space to the low-dimensional space to obtain the reduced-dimensional features.

[0030] In one embodiment, the prediction results of different classifiers are integrated by the soft voting integration model to obtain the RNAN4-acetylcytidine modification site prediction results, including:

[0031] Determining the prediction probabilities of all classifiers through the soft voting ensemble model;

[0032] Performing weighted average calculation on each of the predicted probabilities to obtain the maximum value of the weighted average probability;

[0033] The maximum value is used as the RNAN4-acetylcytidine modification site prediction result.

[0034] A RNAN4-acetylcytidine modification site prediction system based on the RNAErnie pre-training model, the system comprising:

[0035] A data set collection module is used to collect RNA sequence data sets; the RNA sequence data sets include positive and negative samples;

[0036] A feature encoding module is used to input each RNA sequence in the RNA sequence data set into the RNAErnie pre-training model for multi-level masking, capture context dependencies and extract global features; and combine the RNAErnie pre-training model with six traditional feature encoding methods to perform feature encoding on each RNA sequence to obtain encoded high-dimensional features;

[0037] A feature dimension reduction module is used to input the encoded high-dimensional features into a deep neural network model to perform feature dimension reduction and obtain features after dimension reduction;

[0038] A result prediction module is used to input the reduced-dimensional features into a soft voting integrated model, and integrate the prediction results of different classifiers through the soft voting integrated model to obtain the RNAN4-acetylcytidine modification site prediction result;

[0039] The soft voting ensemble model is constructed by XGBoost, MLP, and CatBoost classifiers.

[0040] The above-mentioned RNAN4-acetylcytidine modification site prediction method and system based on the RNAErnie pre-training model can accurately capture context dependencies and extract global features through multi-level masking of the RNAErnie pre-training model, capture more comprehensive RNA sequence information, and combine six traditional feature encoding methods to capture the details and physical and chemical properties of the sequence; use deep neural networks to automatically reduce the dimension of features, and reduce the computational complexity and retain key information by automatically learning and screening the most relevant features; input the reduced-dimensional features into the soft voting integration model, and obtain the final prediction results by integrating multiple classifiers, which significantly improves the accuracy and robustness of the prediction, and can quickly and cost-effectively improve the model's RNAN4-acetylcytidine modification site detection accuracy. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] Figure 1 This is an application environment diagram of a method for predicting RNAN4-acetylcytidine modification sites based on an RNAErnie pre-training model in one embodiment;

[0042] Figure 2 A schematic diagram of a process for predicting RNAN4-acetylcytidine modification sites based on the RNAErnie pre-training model in one embodiment;

[0043] Figure 3 A schematic diagram of a model framework of Voting-ac4C in one embodiment;

[0044] Figure 4 Schematic diagram of parameters used to verify the reliability of hybrid feature encoding in ablation experiments;

[0045] Figure 5 Schematic diagram of the parameters used to verify the reliability of the selected machine learning classifier for ablation experiments;

[0046] Figure 6 Schematic diagram of parameters used to verify the reliability of the soft voting method for ablation experiments;

[0047] Figure 7 It is a structural block diagram of an RNAN4-acetylcytidine modification site prediction system based on the RNAErnie pre-training model in one embodiment;

[0048] Figure 8 It is a structural block diagram of an RNAN4-acetylcytidine modification site prediction system based on the RNAErnie pre-training model in another embodiment;

[0049] Fig. 9 FIG. 4 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0050] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0051] The RNAN4-acetylcytidine modification site prediction method based on the RNAErnie pre-training model provided in the embodiments of the present application can be applied to Figure 1 In the application environment shown. Figure 1 As shown, the application environment includes a computer device 110. The computer device 110 can collect RNA sequence data sets; the RNA sequence data sets contain positive and negative samples; the computer device 110 can input each RNA sequence in the RNA sequence data set into the RNAErnie pre-training model for multi-level masking, thereby capturing context dependencies and extracting global features; and the RNAErnie pre-training model is combined with six traditional feature encoding methods to encode the features of each RNA sequence to obtain the encoded high-dimensional features; the computer device 110 can input the encoded high-dimensional features into the deep neural network model for feature dimension reduction to obtain the reduced-dimensional features; the computer device 110 can input the reduced-dimensional features into the soft voting integration model, and integrate the prediction results of different classifiers through the soft voting integration model to obtain the RNAN4-acetylcytidine modification site prediction results; wherein the soft voting integration model is constructed by XGBoost, MLP, and CatBoost classifiers. Among them, the computer device 110 can be, but not limited to, various personal computers, laptops, smart phones, robots, unmanned aerial vehicles, tablet computers and other devices.

[0052] In one embodiment, Figure 2 As shown, a method for predicting RNAN4-acetylcytidine modification sites based on the RNAErnie pre-training model is provided, comprising the following steps:

[0053] Step 202, collecting an RNA sequence data set; the RNA sequence data set includes positive and negative samples.

[0054] Establishing a reliable benchmark data set is the basis for developing a powerful potential mechanism for predicting ac4C modification sites. In this embodiment, a pre-designed and provided RNA sequence data set can be used, which can specifically include 2758 balanced positive and negative samples. The data set is divided into a training set (2206 samples) and a test set (552 samples). Positive and negative samples are equally distributed in the training and test data sets to ensure the stability and generalization ability of the model.

[0055] In one embodiment, a method for predicting RNAN4-acetylcytidine modification sites based on an RNAErnie pre-training model is provided, which may also include a process of dividing a data set ratio, and the specific process includes: determining a data set division ratio; based on the data set division ratio, performing stratified sampling processing on the RNA sequence data set to obtain a divided training data set and a test data set.

[0056] Specifically, in this embodiment, all samples are divided into training and test data sets by stratified sampling at a ratio of 4:1, and the training data set includes 2206 positive and negative samples. In contrast, the independent test data set consists of 552 samples from each category, including positive and negative.

[0057] Step 204, each RNA sequence in the RNA sequence data set is input into the RNAErnie pre-training model for multi-level masking to capture context dependencies and extract global features; and the RNAErnie pre-training model is combined with six traditional feature encoding methods to perform feature encoding on each RNA sequence to obtain encoded high-dimensional features.

[0058] For each RNA sequence in the RNA sequence dataset, the global context features are obtained through the RNAErnie pre-trained model. Among them, the RNAErnie pre-trained model is used to encode the features of RNA sequences. RNAErnie is a pre-trained model based on the Transformer architecture designed specifically for RNA sequences. It is built on the Enhanced Representation through Knowledge Integration (ERNIE) framework and combines multiple Transformer layers and multi-head self-attention mechanisms. The hidden state dimension of each Transformer block is 768. These design choices enable the RNAErnie pre-trained model to capture complex patterns and deep biological information in RNA sequences.

[0059] In one embodiment, the RNAErnie pre-training model is established on the basis of a representation framework enhanced by knowledge integration, and is combined with a Transformer layer and a multi-head self-attention mechanism; a method for predicting RNAN4-acetylcytidine modification sites based on the RNAErnie pre-training model is provided, which can also include a process of feature processing using the RNAErnie pre-training model, and the specific process includes: inputting each RNA sequence in the RNA sequence data set into the RNAErnie pre-training model respectively, and based on the multi-head self-attention mechanism, calculating the attention score corresponding to each RNA sequence through each attention head; connecting the obtained attention scores, and mapping each RNA sequence to a query, key and value matrix through a linear transformation matrix.

[0060] In this embodiment, the RNAErnie pre-training model is based on the Transformer architecture, one of the core components of which is the multi-head attention mechanism, which captures different aspects of the input sequence by computing multiple attention heads in parallel, thereby enhancing the ability to understand RNA sequences. For each attention head, W represents a set of linear transformation matrices. Specifically, W Q , W K and W V are the linear transformation matrices used to map the input sequence X to the query (Q), key (K), and value (V) matrices. The calculation formula involved in this process is: Q = XW Q ; K = XW K ; V = XW V ; Each head calculates an attention score through a self-attention mechanism to evaluate the relationship between elements of the input sequence. The calculation formula is: Among them, the dimension of the key vector is d k The dot product of the query matrix Q and the key matrix K is used to scale to prevent gradient problems; this scaled dot product generates the original attention score, which is then converted into a probability distribution through the softmax function; this distribution is used to weight the vectors in the value matrix V to produce a contextual representation of the sequence. The outputs of multiple attention heads are connected and then linearly transformed to obtain the final result. The calculation formula involved in this process is: MultiHead(Q,K,V)=Concat(head1,head2,…,headh)W O , where the concatenation operator Concat merges the various head outputs, and W O is a trainable transformation matrix that maps the combined features to the desired output space.

[0061] In one embodiment, a method for predicting RNAN4-acetylcytidine modification sites based on an RNAErnie pre-training model is provided, which may also include a multi-level masking process, the specific process including: the RNAErnie pre-training model adopts motif-level masking, subsequence-level masking, and motif-level random masking strategies, combined with coarse-grained RNA as vocabulary tags; the RNAErnie pre-training model attaches vocabulary tags to the last segment of each RNA sequence to enhance the RNA sequence representation.

[0062] Among them, the RNAErnie pre-training model adopts three masking strategies to enhance the RNA sequence representation: motif-level masking refers to masking single nucleotides to capture local features; subsequence-level masking targets continuous fragments of RNA sequences, aiming to capture long dependencies and global features; motif-level random masking introduces randomness by masking nucleotides without considering their position or continuity, thereby improving the robustness and generalization ability of the model.

[0063] In addition, the RNAErnie pre-training model incorporates coarse-grained types of RNA (e.g., mRNA, miRNA, lncRNA) as special vocabulary tags, appending these type tags to the last segment of each RNA sequence during pre-training. This strategy enables the model to identify and utilize RNA type-specific features when processing various downstream tasks, thereby enhancing the domain adaptability of the model and its ability to generalize across multiple tasks.

[0064] Among them, six traditional feature encoding methods are combined for feature encoding, namely: One-hot, ENAC, C2, ND, TPCP, Ksnpf feature encoding methods. Specifically, the One-hot encoding method: used in bioinformatics to represent nucleotide sequences, representing the four RNA bases in RNA molecules, adenine (A), cytosine (C), guanine (G) and uracil (U), as a binary vector composed of 0 and 1. Specifically, this means that the nucleotides A, C, G and U are represented by four vectors (1, 0, 0, 0), (0, 1, 0, 0), (0, 0, 1, 0) and (0, 0, 0, 1), respectively; the ENAC encoding method: using a sliding window method, the nucleic acid composition is calculated within a window of fixed length, and a feature vector for each window is generated, which can capture the local structural information in the sequence and provide useful feature representation for subsequent analysis and modeling; the C2 encoding method: converts the elements of the biological sequence into specific values ​​from the perspective of the global sequence, and converts the RNA bases in the nucleotide sequence of the RNA molecule into 2-bit binary For example, adenine (A) is encoded as (0, 0), cytosine (C) is encoded as (1, 1), guanine (G) is encoded as (1, 0), and uracil (U) is encoded as (0, 1); ND encoding method: the main principle is to regard one or more bases in the RNA sequence as a single element and calculate their frequency in the sequence; TPCP encoding method: 11 physicochemical properties are used. For each sequence window containing TPCP, a 1375-dimensional vector (i.e., 125 trinucleotide combinations × 11 physicochemical properties) is generated, and any trinucleotide containing nucleotide N is set to zero; Ksnpf encoding method: the occurrence of 16 nucleotide pairs separated by k arbitrary nucleotides in the sequence is quantified. By setting k to values ​​of 0, 1, 2, 3, and 4, the sequence is converted into various feature representations reflecting the frequency of these nucleotide pairs at different intervals.

[0065] In this embodiment, for each RNA sequence, a multi-dimensional feature encoding method is adopted, and the global context features are obtained through the RNAErnie pre-training model. The six traditional encoding methods of One-hot, ENAC, C2, ND, TPCP and Ksnpf are combined to extract rich features of RNA sequences from multiple angles such as physicochemical properties and position specificity. The hybrid feature representation of these multiple encoding methods can comprehensively reflect the local and global information of the sequence, and effectively enhance the feature expression ability of the model.

[0066] Step 206: Input the encoded high-dimensional features into a deep neural network model to perform feature dimensionality reduction to obtain features after dimensionality reduction.

[0067] The generated high-dimensional features are input into the deep neural network model for feature dimensionality reduction. The deep neural network automatically learns and filters features, retains the most predictive features, reduces redundant information, and reduces computational complexity.

[0068] In one embodiment, a method for predicting RNAN4-acetylcytidine modification sites based on the RNAErnie pre-training model provided can also include a process of feature dimensionality reduction, and the specific process includes: inputting the encoded high-dimensional features into a deep neural network model, and mapping the high-dimensional features from the high-dimensional space to the low-dimensional space through the multi-layer nonlinear mapping of the deep neural network model to obtain the reduced-dimensional features.

[0069] In the model construction process of this embodiment, the hybrid features that integrate the RNAErnie pre-training model and six traditional feature encoding methods are input into the deep neural network (DNN) for feature dimensionality reduction. Through the multi-layer nonlinear mapping of DNN, the features are mapped from high-dimensional space to low-dimensional space, which effectively reduces the computational complexity and storage requirements, and retains the main features that are critical to prediction. In addition, DNN can capture the complex interactive relationships between different features and achieve a higher level of feature expression. This feature dimensionality reduction method not only avoids the interference of redundant information, but also improves the model's understanding of the importance of features, thereby significantly improving the accuracy of prediction.

[0070] Step 208, input the reduced dimension features into the soft voting integration model, integrate the prediction results of different classifiers through the soft voting integration model, and obtain the RNAN4-acetylcytidine modification site prediction result.

[0071] Among them, the soft voting ensemble model is constructed by XGBoost, MLP, and CatBoost classifiers. The features after dimension reduction are passed into the soft voting ensemble model constructed by XGBoost, MLP, and CatBoost classifiers. By integrating the prediction results of different classifiers, the prediction performance and stability of the model are improved.

[0072] In one embodiment, a method for predicting RNAN4-acetylcytidine modification sites based on an RNAErnie pre-training model is provided, and further includes a process of prediction through a soft voting integration model, the specific process including: determining the prediction probability of all classifiers through a soft voting integration model; performing a weighted average calculation on each prediction probability to obtain the maximum value of the weighted average probability; and using the maximum value as the RNAN4-acetylcytidine modification site prediction result.

[0073] Soft voting is an ensemble learning method that calculates the final prediction probability by taking a weighted average of the prediction probabilities of all classifiers. The core formula of the soft voting model is: In the formula, represents the final prediction, c represents the category, n is the number of base models, and w i is the weight of the ith model, and P i (y=c|x) is the probability that the sample predicted by the i-th model belongs to category c. The final category prediction is based on the maximum value of the weighted average probability, that is, the class with the highest predicted probability is selected as the final prediction result.

[0074] In one embodiment, a method for predicting RNAN4-acetylcytidine modification sites based on an RNAErnie pre-training model is provided, and further includes a process for evaluating the performance of a soft voting ensemble model. The specific process includes: determining an evaluation index, and performing a performance evaluation on the soft voting ensemble model using a ten-fold cross validation method according to the evaluation index to obtain an evaluation result; wherein the evaluation index includes sensitivity, specificity, accuracy, Matthews correlation coefficient, and area under the curve.

[0075] Among them, ten-fold cross validation and independent test sets were used to comprehensively evaluate the performance of the model. The evaluation indicators included sensitivity (SN), specificity (SP), accuracy (ACC), Matthews correlation coefficient (MCC) and area under the curve (AUC). The evaluation method ensured that the model had good generalization performance and robust predictive ability.

[0076] In order to evaluate the performance of the model, five commonly used evaluation indicators are used in this embodiment, including sensitivity (SN), specificity (SP), accuracy (ACC), Matthews correlation coefficient (MCC) and area under the curve (AUC), and the formulas of these indicators are respectively expressed as follows: Among them, TP, TN, FN, and FP represent the number of true positives, true negatives, false negatives, and false positives, respectively; SN represents the proportion of correctly identified positive samples; SP represents the proportion of correctly identified negative samples; ACC represents the proportion of all correctly classified samples; MCC measures the correlation between the true value and the predicted value, ranging from [-1,1]. In addition, in order to comprehensively compare the performance of different models, it is necessary to calculate the evaluation index based on the area under the receiver operating characteristic (ROC) curve, which shows the ratio of true positives to false positives; AUC values ​​range from 0 to 1, and the higher the AUC value, the better the predictive performance of the underlying model. The higher the values ​​of these five indicators, the better the model performance.

[0077] In one embodiment, a method for predicting RNAN4-acetylcytidine modification sites based on the RNAErnie pre-training model provided may also include a process of establishing a website for user interaction, the specific process including: displaying a user interaction interface, and obtaining an RNA sequence to be predicted through the user interaction interface; inputting the RNA sequence to be predicted into the soft voting integrated model, and outputting an RNAN4-acetylcytidine modification site prediction result corresponding to the RNA sequence to be predicted; and displaying the RNA N4-acetylcytidine modification site prediction result corresponding to the RNA sequence to be predicted in the user interaction interface.

[0078] A user-friendly online platform can be established on a computer device to provide an intuitive interface, where users can easily input RNA sequences and quickly obtain prediction results for ac4C modification sites. The design of the platform makes the application of the RNAN4-acetylcytidine modification site prediction method based on the RNAErnie pre-training model provided in this application more convenient and popular.

[0079] In one embodiment, Figure 3 As shown, an application model framework of an RNAN4-acetylcytidine modification site prediction method based on the RNAErnie pre-training model is provided, which mainly includes five parts: A. data collection; B. feature encoding; C. feature dimensionality reduction; D. model evaluation; and E. website service.

[0080] Specifically, Figure 3 As shown, first, an RNA sequence data set is collected, specifically, a data set of each RNA sequence is collected from a database, and then divided into a training set and a test set; then, the RNAErnie pre-training model and six traditional feature encoding methods are used to encode the RNA sequence to obtain high-dimensional features; the high-dimensional features are input into a deep neural network model for feature dimensionality reduction; the reduced features are input into a soft voting integration model; the prediction results of different classifiers are integrated through the soft voting integration model to obtain the RNA N4-acetylcytidine modification site prediction results.

[0081] In one embodiment, in order to verify the superiority of the soft voting integrated model provided in the present application to predict ac4C, namely the Voting-ac4C model, the experimental results are compared with the existing ten-fold cross validation as follows:

[0082] The Voting-ac4C model was deeply compared with several typical existing models, including PACES, XG-ac4C, iRNA-ac4C, Auto-ac4C and ac4C-AFL. The comparison results are shown in the table:

[0083]

[0084] From the 10-fold cross-validation results in the table, Voting-ac4C outperforms all existing models in multiple key performance indicators such as sensitivity (SN), specificity (SP), accuracy (ACC), Matthews correlation coefficient (MCC) and area under the curve (AUC). This shows that Voting-ac4C not only significantly improves accuracy, but also balances the prediction capabilities of different categories while maintaining high sensitivity and specificity. In addition, Voting-ac4C combines a pre-trained large language model with a variety of traditional feature encoding methods to capture more comprehensive RNA sequence information, enabling it to achieve a breakthrough in performance and further verifying its effectiveness and reliability as a tool for predicting ac4C modification sites.

[0085] Next, the experimental results of the Voting-ac4C model and the existing model on independent dataset tests are compared as follows:

[0086] The test results on independent data sets show that the Voting-ac4C model performs well in all performance indicators. The comparison results are shown in the following table:

[0087]

[0088]

[0089] As can be seen from the table, the sensitivity (SN), specificity (SP), accuracy (ACC), Matthews correlation coefficient (MCC) and area under the curve (AUC) of the Voting-ac4C model reached 85.14%, 81.15%, 83.15%, 66.35% and 88.73%, respectively. These results show that the Voting-ac4C model not only has high accuracy in the task of predicting ac4C modification sites, but also has strong sensitivity and specificity, and can effectively distinguish positive and negative samples. Compared with existing models, the overall performance of Voting-ac4C is significantly superior, especially in terms of accuracy and MCC, which reflects its ability to predict balanced performance between different categories. This further verifies the robustness and practicality of the Voting-ac4C model in its wide application in the prediction of ac4C modification sites.

[0090] Next, the performance comparison of the RNAErnie pre-trained model combined with other encoding methods is as follows:

[0091] First, we evaluated the model performance of RNAErnie combined with each traditional feature encoding method separately. The results are shown in the following table:

[0092]

[0093] It can be seen that the performance of single encoding methods reveals their respective advantages and disadvantages, among which Ksnpf and ENAC have superior performance, reaching 78.07% and 75.54% accuracy (ACC) respectively, but they still do not achieve high prediction performance.

[0094] After evaluating a single method, this example explored the impact of feature encoding combinations on model performance. After gradually combining different encoding methods, it was found that the model performance was significantly improved, as shown in the following table:

[0095]

[0096]

[0097] As shown in the table above, after combining Ksnpf and ENAC encoding, the accuracy (ACC) increased to 80.34%, which is a significant improvement over the results of using these two encodings alone (78.07% and 75.54%). Further adding C2 encoding, ACC increased to 80.71%, indicating that the introduction of diverse features helps capture more sequence information. When One-hot, ND and TPCP encodings were added, the accuracy of the final combination reached 83.15%, which is significantly higher than using RNAErnie alone and any traditional encoding method (the best result is 78.07%). In addition, the Matthews correlation coefficient (MCC) increased from a maximum of 56.16% to 66.35%, and the AUC increased from 86.47% to 88.73%. These results show the significant advantages of feature combination, proving that by fusing different encoding methods, the model can better utilize the multidimensional information of RNA sequences, thereby improving prediction performance and achieving the effect of "1+1>2".

[0098] In this embodiment, if Figure 4 As shown, Figure 4 It was demonstrated that the performance of the model after the combination of multiple features was significantly better than that of a single encoding method. The results verified that the RNAErnie pre-training model proposed in this application combined with a hybrid strategy of six traditional feature encodings can more comprehensively characterize the characteristics of RNA sequences, thereby improving the accuracy and stability of predictions, demonstrating the innovation and advantages of this application.

[0099] Next, the comparison between the soft voting ensemble model in this application and other machine learning classifiers is as follows:

[0100] When constructing the RNA-ac4C modification site prediction model, XGBoost, CatBoost and MLP were selected as the base classifiers of the soft voting ensemble learning model. In order to further verify the effectiveness of these classifiers, the performance of six different machine learning classifiers was compared, such as Figure 5 As shown in the figure, XGBoost, CatBoost and MLP performed well in multiple indicators such as sensitivity (SN), specificity (SP), accuracy (ACC), Matthews correlation coefficient (MCC) and area under the curve (AUC), significantly outperforming other classifiers. Therefore, these three classifiers have become ideal choices for building soft voting ensemble learning models, effectively improving the comprehensive performance of the prediction model.

[0101] The comparison between the soft voting ensemble model and other ensemble learning methods is as follows:

[0102] In order to further verify the stability and reliability of the model, several common ensemble learning methods were compared, including blending, stacking, bagging, hard voting, and soft voting. Figure 6 As shown in the figure, Soft Voting performs better than other methods in all evaluation indicators, proving that it has significant advantages in improving model prediction performance.

[0103] It should be understood that, although the various steps in the above-mentioned flow chart are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps is not strictly limited in order, and these steps can be executed in other orders. Moreover, at least a part of the steps in the above-mentioned flow chart may include a plurality of sub-steps or a plurality of stages, and these sub-steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these sub-steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the sub-steps or stages of other steps.

[0104] In one embodiment, Figure 7 As shown, a RNA N4-acetylcytidine modification site prediction system based on the RNAErnie pre-training model is provided, including: a data set acquisition module 710, a feature encoding module 720, a feature dimension reduction module 730 and a result prediction module 740, wherein:

[0105] The data set collection module 710 is used to collect RNA sequence data sets; the RNA sequence data sets include positive and negative samples;

[0106] The feature encoding module 720 is used to input each RNA sequence in the RNA sequence data set into the RNAErnie pre-training model for multi-level masking, capture context dependencies and extract global features; and combine the RNAErnie pre-training model with six traditional feature encoding methods to perform feature encoding on each RNA sequence to obtain encoded high-dimensional features;

[0107] A feature dimension reduction module 730 is used to input the encoded high-dimensional features into a deep neural network model to perform feature dimension reduction to obtain features after dimension reduction;

[0108] The result prediction module 740 is used to input the reduced-dimensional features into the soft voting integration model, integrate the prediction results of different classifiers through the soft voting integration model, and obtain the RNAN4-acetylcytidine modification site prediction results; wherein the soft voting integration model is constructed by XGBoost, MLP, and CatBoost classifiers.

[0109] like Figure 8 As shown, in one embodiment, a RNA N4-acetylcytidine modification site prediction system based on the RNAErnie pre-training model is provided, which also includes a model evaluation module 750 for determining an evaluation index, and performing a performance evaluation on the soft voting ensemble model using a ten-fold cross validation method according to the evaluation index to obtain an evaluation result; wherein the evaluation index includes sensitivity, specificity, accuracy, Matthews correlation coefficient, area under the curve

[0110] like Figure 8 As shown, in one embodiment, a RNA N4-acetylcytidine modification site prediction system based on the RNAErnie pre-training model is provided, which also includes a user interaction module 760, which is used to display a user interaction interface, and obtain a RNA sequence to be predicted through the user interaction interface; input the RNA sequence to be predicted into the soft voting integrated model, and output the RNAN4-acetylcytidine modification site prediction result corresponding to the RNA sequence to be predicted; and display the RNAN4-acetylcytidine modification site prediction result corresponding to the RNA sequence to be predicted in the user interaction interface.

[0111] In one embodiment, the data set acquisition module 710 is further used to determine the data set division ratio; based on the data set division ratio, the RNA sequence data set is subjected to stratified sampling processing to obtain a divided training data set and a test data set.

[0112] In one embodiment, the RNAErnie pre-training model is based on a knowledge integration enhanced representation framework, and is combined with a Transformer layer and a multi-head self-attention mechanism; the feature encoding module 730 is also used to input each RNA sequence in the RNA sequence data set into the RNAErnie pre-training model, and based on the multi-head self-attention mechanism, the attention score corresponding to each RNA sequence is calculated by each attention head; the obtained attention scores are connected, and each RNA sequence is mapped to a query, key, and value matrix through a linear transformation matrix.

[0113] In one embodiment, the feature encoding module 720 is also used in the RNAErnie pre-training model to adopt motif-level masking, subsequence-level masking, and motif-level random masking strategies, combined with coarse-grained RNA as vocabulary tags; the RNAErnie pre-training model attaches vocabulary tags to the last segment of each RNA sequence to enhance the RNA sequence representation.

[0114] In one embodiment, the feature dimensionality reduction module 730 is also used to input the encoded high-dimensional features into a deep neural network model, and map the high-dimensional features from a high-dimensional space to a low-dimensional space through the multi-layer nonlinear mapping of the deep neural network model to obtain the reduced-dimensional features.

[0115] In one embodiment, the result prediction module 740 is also used to determine the prediction probability of all classifiers through a soft voting integration model; perform weighted average calculation on each prediction probability to obtain the maximum value of the weighted average probability; and use the maximum value as the RNAN4-acetylcytidine modification site prediction result.

[0116] In one embodiment, a computer device is provided. The computer device may be a terminal, and its internal structure diagram may be as follows: Fig. 9 As shown. The computer device includes a processor, a memory, a network interface, a display screen and an input device connected by a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The network interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a method for predicting RNAN4-acetylcytidine modification sites based on the RNAErnie pre-training model is implemented. The display screen of the computer device can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device can be a touch layer covered on the display screen, or a button, trackball or touchpad set on the computer device housing, or an external keyboard, touchpad or mouse, etc.

[0117] Those skilled in the art will understand that Fig. 9 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0118] In one embodiment, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and when the processor executes the computer program, the steps of a method for predicting RNAN4-acetylcytidine modification sites based on an RNAErnie pre-training model are implemented.

[0119] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps of a method for predicting RNAN4-acetylcytidine modification sites based on an RNAErnie pre-training model are implemented.

[0120] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0121] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0122] The above-mentioned embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the invention patent. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the patent of the present application shall be subject to the attached claims.

Claims

1. A method for predicting RNAN4-acetylcytidine modification sites based on the RNAErnie pre-training model, characterized in that: The method comprises: Collecting an RNA sequence data set; the RNA sequence data set includes positive and negative samples; Each RNA sequence in the RNA sequence data set is input into the RNAErnie pre-training model for multi-level masking to capture context dependencies and extract global features; and the RNAErnie pre-training model is combined with six traditional feature encoding methods to perform feature encoding on each RNA sequence to obtain encoded high-dimensional features; Inputting the encoded high-dimensional features into a deep neural network model to perform feature dimensionality reduction to obtain features after dimensionality reduction; The reduced-dimensional features are input into a soft voting integration model, and the prediction results of different classifiers are integrated through the soft voting integration model to obtain the RNAN4-acetylcytidine modification site prediction result; The soft voting ensemble model is constructed by XGBoost, MLP, and CatBoost classifiers.

2. The RNAN4-acetylcytidine modification site prediction method based on the RNAErnie pre-training model according to claim 1, characterized in that: The method further comprises: Determine an evaluation index, and perform a performance evaluation on the soft voting ensemble model using a ten-fold cross validation method according to the evaluation index to obtain an evaluation result; Among them, the evaluation indicators include sensitivity, specificity, accuracy, Matthews correlation coefficient, and area under the curve.

3. The RNAN4-acetylcytidine modification site prediction method based on the RNAErnie pre-training model according to claim 1, characterized in that: The method further comprises: Displaying a user interaction interface, and obtaining the RNA sequence to be predicted through the user interaction interface; Inputting the RNA sequence to be predicted into the soft voting integrated model, and outputting the RNAN4-acetylcytidine modification site prediction result corresponding to the RNA sequence to be predicted; The prediction result of RNAN4-acetylcytidine modification site corresponding to the RNA sequence to be predicted is displayed in the user interaction interface.

4. The RNAN4-acetylcytidine modification site prediction method based on the RNAErnie pre-training model according to claim 1, characterized in that: After collecting the RNA sequence data set, the method further comprises: Determine the ratio of data set division; Based on the data set division ratio, the RNA sequence data set is subjected to stratified sampling processing to obtain a divided training data set and a test data set.

5. The RNAN4-acetylcytidine modification site prediction method based on the RNAErnie pre-training model according to claim 1, characterized in that: The RNAErnie pre-trained model is based on the framework of enhanced representation through knowledge integration, and combines the Transformer layer and multi-head self-attention mechanism; where: Input each RNA sequence in the RNA sequence data set into the RNAErnie pre-training model respectively, and calculate the attention score corresponding to each RNA sequence through each attention head based on the multi-head self-attention mechanism; The obtained attention scores are connected, and each RNA sequence is mapped to a query, key and value matrix through a linear transformation matrix.

6. The RNAN4-acetylcytidine modification site prediction method based on the RNAErnie pre-training model according to claim 1, characterized in that: Each RNA sequence in the RNA sequence data set is input into the RNAErnie pre-training model for multi-level masking, including: The RNAErnie pre-training model adopts motif-level masking, subsequence-level masking, and motif-level random masking strategies, combined with coarse-grained types of RNA as vocabulary markers; The RNAErnie pre-trained model appends the vocabulary token to the last segment of each RNA sequence to enhance the RNA sequence representation.

7. The RNAN4-acetylcytidine modification site prediction method based on the RNAErnie pre-training model according to claim 1, characterized in that: The encoded high-dimensional features are input into a deep neural network model to perform feature dimensionality reduction, and the reduced-dimensional features are obtained, including: The encoded high-dimensional features are input into a deep neural network model, and through the multi-layer nonlinear mapping of the deep neural network model, the high-dimensional features are mapped from the high-dimensional space to the low-dimensional space to obtain the reduced-dimensional features.

8. The RNAN4-acetylcytidine modification site prediction method based on the RNAErnie pre-training model according to claim 1, characterized in that: The prediction results of different classifiers are integrated through the soft voting integration model to obtain the RNAN4-acetylcytidine modification site prediction results, including: Determining the prediction probabilities of all classifiers through the soft voting ensemble model; Performing weighted average calculation on each of the predicted probabilities to obtain the maximum value of the weighted average probability; The maximum value is used as the RNAN4-acetylcytidine modification site prediction result.

9. A RNAN4-acetylcytidine modification site prediction system based on the RNAErnie pre-training model, characterized in that: The system comprises: A data set collection module is used to collect RNA sequence data sets; the RNA sequence data sets include positive and negative samples; A feature encoding module is used to input each RNA sequence in the RNA sequence data set into the RNAErnie pre-training model for multi-level masking, capture context dependencies and extract global features; and combine the RNAErnie pre-training model with six traditional feature encoding methods to perform feature encoding on each RNA sequence to obtain encoded high-dimensional features; A feature dimension reduction module is used to perform feature dimension reduction from the high-dimensional features input into a deep neural network model to obtain features after dimension reduction; A result prediction module is used to input the reduced-dimensional features into a soft voting integrated model, and integrate the prediction results of different classifiers through the soft voting integrated model to obtain the RNAN4-acetylcytidine modification site prediction result; The soft voting ensemble model is constructed by XGBoost, MLP, and CatBoost classifiers.

10. The RNAN4-acetylcytidine modification site prediction system based on the RNAErnie pre-training model according to claim 9, characterized in that: The system also includes a model evaluation module, which is used to determine evaluation indicators, and perform performance evaluation on the soft voting integration model using a ten-fold cross validation method according to the evaluation indicators to obtain evaluation results; wherein the evaluation indicators include sensitivity, specificity, accuracy, Matthews correlation coefficient, and area under the curve.

Images