Rice m6A methylation site prediction method and system based on feature extraction and fusion

Abstract

The invention provides a rice m6A methylation site prediction method and system based on feature extraction and fusion, and the method comprises the steps: obtaining a to-be-predicted rice m6A data set, constructing a maximum-length filling sequence through employing a tag coding and filling strategy, and obtaining the initial features of a variable-length m6A sequence, and inputting the initial features of the variable-length m6A sequence into the trained rice m6A methylation site prediction model to obtain a rice m6A methylation site prediction result. The rice m6A methylation site prediction method solves the technical problems that according to an existing rice m6A methylation site prediction method, sparse and invalid features are caused by adopting a filling mode for a variable-length sequence, and different source features are directly stacked, so that the prediction accuracy of rice m6A methylation sites is low, and the prediction effect is poor.

Description

Technical Field

[0001] The present invention relates to the technical field of bioinformatics, and in particular to rice m 6 A methylation site prediction method and system. Background Art

[0002] Epigenetics was first proposed by geneticist Conrad Hal Waddington. It refers to the stable and heritable change mechanism in the case of non-(deoxy) nucleic acid sequence changes, such as chemical modifications. This mechanism mainly includes DNA methylation, RNA methylation, demethylation, chromatin remodeling and histone modification. Recently, epigenetic changes have been shown to play an important role in inducing phenotypic diversity, and they play an indispensable role in the development and biological processes of multicellular organisms.

[0003] There are more than 200 post-transcriptional epigenetic modifications in eukaryotic RNAs, such as 6 -methyladenosine (m 6 A), N 1 -methyladenosine (m 1 A), 5-methylcytidine (m 5 C), 1-methylguanosine (m 1 G), pseudouridine (ψ), etc. The most common epigenetic modification is m 6 A, which is widely present in messenger RNAs, microRNAs, long non-coding RNAs, transfer RNAs and ribosomal RNAs. Methyltransferase complexes (Writers), demethylases (Erasers) and m 6 A binding protein (Readers) is m 6 A is the main component of the modification system. Writers and Erasers add and delete methyl groups (-CH3) on the 6th amino group (-NH2) of adenosine in RNAs, respectively. Readers recognize m 6 A site and plays a specific regulatory role. In rice, m 6 A is involved in growth, development, and responses to biotic and abiotic stresses. 6 A regulates the early degeneration of microspores in the vacuolar pollen stage of rice. 6 A is dynamically regulated during rice-plant virus interactions. Cheng et al. found that rice m 6 A may be related to the abnormal root development induced by cadmium stress.

[0004] In plants, methyl RNA immunoprecipitation and sequencing (MeRIP-seq, also known as m 6 A-seq) can detect m 6However, the MeRIP-seq method can only detect mA sites with a resolution of 100 to 200 nucleotides. 6 A transcript, cannot satisfy m 6 A base resolution requirement for editing. In order to achieve m 6 To detect the single-base resolution of the A site, the researchers made some improvements to the MeRIP-seq technology, including photocrosslinking-assisted m 6 A sequencing strategy (PA-m 6 A-seq), m 6 A single nucleotide resolution cross-linking and immunoprecipitation (miCLIP), m 6 A Cross-linking immunoprecipitation sequencing (m 6 A-CLIP-seq) etc. However, m 6 The A sites are mainly concentrated in organs and tissues with high RNA metabolism, and the sample size of these tissues is often small. Therefore, the above technology cannot be biologically replicated, so it is impossible to accurately detect m in tissues or cells. 6 The deamination adjacent RNA modification target sequencing (DART-seq) method only requires 10 ng of total RNAs, which is about 50 times less than that required by the MeRIP-seq method. The third-generation sequencing technology has rapidly developed to detect m 6 A site method, including single-molecule real-time sequencing and single-molecule nanopore sequencing. In 2020, Parker et al. successfully used nanopore direct RNA sequencing technology to map the Arabidopsis m 6 A. This technique is well suited for studying small samples and has the potential to accelerate the development of m 6 A research, and will have a great impact on future m 6 A single-base resolution modification and editing provides great help.

[0005] Although biological experiments 6 A site detection technology is constantly improving and perfecting, but it still requires a lot of manpower, material and financial resources, so the development of m 6 Computational methods related to A site identification are necessary.

[0006] At present, researchers have proposed some m 6 For example, the existing invention patent application document with publication number CN111161793A, “N-terminal site prediction method in RNA based on stacking integration” 6-Methyladenosine modification site prediction method" proposed the StackRAM method. This method includes: extracting RNA sequence features of three species, Saccharomyces cerevisiae, humans and Arabidopsis thaliana (sequence lengths are 101, 41 and 21, respectively, and trained respectively) through 6 feature extraction methods, namely binary coding, chemical properties, nucleotide frequency, k-mer nucleotide frequency, pseudo-dinucleotide composition and position-specific trinucleotide tendency, and obtaining the initial feature space of the original data set through feature fusion; using elastic network to reduce the dimension, eliminate redundant and noise features, retain important features related to model classification, and obtain the best feature set; input the optimal feature subset and the corresponding category label into the stacking ensemble for model training, and evaluate the prediction performance of the model in combination with evaluation indicators to obtain a prediction model; input the RNA sequence to be predicted in the test set into the prediction model to predict m 6 A site and output. Existing public literature: m based on sequence features and graph embedding information 6 A site identification method, which also targets Saccharomyces cerevisiae, Arabidopsis thaliana and human species, using m 6 Seven sequence feature encoding methods are commonly used in the computational method of A modification site identification: nucleotide composition conversion distribution characteristics, k-spaced nucleotide pair frequency characteristics, nucleotide physicochemical property density characteristics, nucleotide pair position specificity characteristics, bispectral Bayesian characteristics, electron-ion pseudo potential energy characteristics and pseudo k-member nucleotide composition characteristics. Then, a fast neighborhood similarity calculation method was introduced, and a sample similarity network was constructed based on sequence features. The graph embedding features of each sample in the network were learned through three graph node embedding algorithms, SocDim, node2vec and GraRep. Finally, the sequence features and graph embedding features were concatenated into an input vector, and the computational model was trained based on the CatBoost classifier. This computational model was named m6AGE. This method was first used in m 6 The computational method for identifying A modification sites combines the traditional sequence feature encoding method and the graph node embedding algorithm, and uses three graph node embedding algorithms in the sample similarity network to fully learn the graph embedding features of each sample in an unsupervised manner. The existing public document "Research on m6A(m) methylation site prediction based on integrated deep learning" is based on high-confidence data (sequence length 41) in multiple tissues of mammals, namely humans, mice and rats, and combines the one-hot feature encoding method, nucleotide chemical properties and nucleotide density (also known as cumulative nucleotide frequency, ANF) into a new feature, which is used as the input of the model. A new computational method, im6APred, was constructed using integrated deep learning to accurately identify m 6A site. This model, im6APred, is based on a comprehensive evaluation of multiple classification methods, including four traditional classification algorithms, three deep learning algorithms, and their integration. The best classifier combination was selected through five cross-validation tests to achieve an effective superposition model.

[0007] However, the prediction of rice m 6 There were few methods for calculating the A site. Until 2021, after collecting and processing the first rice m 6 A dataset, Wang and colleagues proposed the first rice m 6 A computational method for site prediction is called SMEP. 6 A sequence is a variable length sequence. SMEP first uses padding operation and label encoding to obtain the maximum length padded sequence. After the embedding layer, SMEP uses multiple concatenated convolutional layers to extract high-order features. Finally, after the flattening layer, SMEP uses a multi-layer perceptron for the final m 6 As an effective computational method, SMEP is a 6 Recently, Song et al. proposed an ensemble learning framework based on the gradient boosting decision tree algorithm, called PEA-m, by stacking multi-source features generated by statistics and deep learning to enhance feature representation. 6 A, for rice 6 Improvements in A-site prediction have achieved good performance.

[0008] Through the above method, it can be found that other species m 6 A data length is a fixed length short sequence. For other species m 6 The coding features used by the prediction methods StackRAM, m6AGE, and im6APred for A sites can be divided into two categories: feature coding methods based on nucleotide composition and feature coding methods based on nucleotide frequency. Feature coding methods based on nucleotide composition type include binary coding, chemical properties, pseudo-dinucleotide composition, and position-specific trinucleotide tendency. These feature coding methods are applied to m6AGE of fixed-length short sequences of these other species. 6 A is simple and convenient in terms of data, but cannot be directly applied to rice 6 A, because this will result in unequal feature dimensions and cannot be input into the model. Feature encoding methods based on nucleotide frequency types, such as nucleotide frequency and k-mer nucleotide frequency, can compress variable-length sequence encoding into fixed-length feature dimensions, but will result in a large amount of sequence information missing. Therefore, feature encoding methods based on nucleotide composition and nucleotide frequency cannot be well applied to rice m 6A site prediction. SMEP uses the padding operation to obtain the maximum length of the padding sequence to deal with rice m 6 A variable length sequence. However, although the padding operation can retain the complete sequence information, it will also make the sequence features sparse and invalid, thus affecting feature extraction and reducing prediction accuracy. 6 A enhances rice m by stacking multi-source features generated by statistics and deep learning 6 A site features, but simply stacking these features from different sources has limitations for feature enhancement. At the same time, the traditional machine learning methods used in the above methods, such as stacking ensemble and CatBoost classifier, are not end-to-end models and have weak ability to solve unstructured data.

[0009] In summary, the existing rice m 6 A methylation site prediction method adopts a filling method for variable-length sequences, resulting in sparse and invalid features, and directly stacking features from different sources, which leads to rice m 6 A technical problem of low prediction accuracy and poor prediction effect of methylation sites. Summary of the invention

[0010] The technical problem to be solved by the present invention is: how to solve the existing rice m 6 A methylation site prediction method adopts a filling method for variable-length sequences, resulting in sparse and invalid features, and directly stacking features from different sources, which leads to rice m 6 A technical problem of low prediction accuracy and poor prediction effect of methylation sites.

[0011] The present invention adopts the following technical solutions to solve the above technical problems: rice m 6 A methylation site prediction methods include:

[0012] S1, from m 6 In A-seq sequence data, obtain rice m 6 A dataset;

[0013] S2, perform input representation operation, and change the rice m 6 In the A dataset, all variable-length sequences are padded to the preset maximum length to obtain the maximum-length padded sequence. The maximum-length padded sequence is label-encoded to obtain the input representation result F. input ;

[0014] S3, based on the input representation result F input , extract multi-core features;

[0015] S4. In the model training operation, perform a global-local feature fusion operation on the multi-core features to obtain a global-local fusion feature; use the Adam optimizer to set the batch size, learning rate, weight decay, and training generation of the model training operation, and use the warm-up learning rate adjustment strategy to control the model training operation;

[0016] S5, downsample the global-local fusion features and embed them to obtain applicable features; wherein, convolutional layers, pooling layers, and residual connections are used alternately to perform layer-by-layer downsampling and feature embedding to retain high-frequency important information, and the contrastive learning loss function L is used. cl Adjust the distance between similar samples and heterogeneous samples to optimize the feature optimization results;

[0017] S6. In the prediction stage, the feature optimization results are sent to the fully connected layer to obtain rice m 6 A methylation site prediction probability to obtain rice sequence m 6 The A site contains the judgment result, wherein the fully connected layer includes: a σ function.

[0018] The present invention introduces multi-core feature extraction and fusion to obtain dimensional information with different core spaces, and enhances feature representation by effectively fusing multi-core features. In addition, the present invention proposes a method of downsampling feature embedding to effectively compress the fused multi-core features, ensuring effective information transmission and high computing efficiency.

[0019] The present invention realizes the rice m 6 Classification of A methylation sites. Experimental results show that compared with other methods, the present invention achieves better results on multiple data sets. At the same time, the model of the present invention has better robustness and generalization.

[0020] Specifically, compared with other existing species m 6 A prediction method is different, in order to be applied to rice m 6 For variable-length sequence data, the present invention does not use a feature encoding method based on nucleotide composition and nucleotide frequency, but uses category label encoding and padding operations to obtain fixed-dimensional features while retaining all complete sequence information.

[0021] In a more specific technical solution, in S3, the following logic is used to extract multi-core features:

[0022] O ebd =Cv1(Embed(F input ))

[0023] K1=Cv1(O ebd )

[0024] K2=Cv3(Cv1( ebd ))

[0025] K3=Cv5(Cv1( ebd ))

[0026] K4=Cv1(MP3(O ebd ))

[0027] MK=concat(K1,K2,K3,K4)

[0028] Where, Embed represents the embedding layer, Cv1, Cv3, and Cv5 represent the convolutional layers with kernel sizes set to 1, 3, and 5, respectively, MP3 represents the maximum pooling layer with kernel size set to 3, concat represents the concatenation operation, and ebd is the initial embedding vector, K1, K2, K3 and K4 are the features of different kernels obtained, and MK is the multi-kernel feature obtained.

[0029] The present invention extracts and fuses multi-core features to enhance feature representation, which means enhancing key information and suppressing sparse and invalid information. The present invention introduces multi-core feature extraction and fusion to extract key features across multiple receptive fields and reduce sparsity.

[0030] Specifically, with rice m 6 A prediction method is different. The present invention takes into account and alleviates the feature sparsity caused by the filling method, and correspondingly proposes a multi-core feature extraction function in the multi-core feature fusion module, which extracts multi-core features of different core sizes on the maximum length filling sequence, instead of using only one maximum length filling sequence like SMEP.

[0031] In more specific technical solutions, S3 also includes:

[0032] S31, input the result F input The initial embedding vector O is obtained through the embedding layer Embed and the first convolutional layer Cv1 ebd ;

[0033] S32, for the initial embedding vector O ebd , respectively use the first convolution layer Cv1, the second convolution layer Cv3 and the third convolution layer Cv5 to extract information of different spatial dimensions, and obtain the first kernel feature K1, the second kernel feature K2, the third kernel feature K3 and the fourth kernel feature K4;

[0034] S33, performing concat processing on the first core feature K1, the second core feature K2, the third core feature K3 and the fourth core feature K4 to obtain the multi-core feature MK.

[0035] In a more specific technical solution, S32 includes:

[0036] S321, in the initial acquisition stage of the first kernel feature K2 and the second kernel feature K3, executing the first convolution layer Cv1 to adjust the number of channels;

[0037] S322, the fourth kernel feature K4 uses MP3 to obtain feature information of the channel dimension, and uses the first convolutional layer Cv1 to change the number of channels.

[0038] In a more specific technical solution, in S4, the following logic is used to perform a global-local feature fusion operation:

[0039] MK=Cv(MK)

[0040]

[0041]

[0042] GL=Cv(concat(G,L))

[0043]

[0044] Where σ represents the sigmoid function and AP represents the average pooling layer.

[0045] In a more specific technical solution, S4 includes:

[0046] S41, obtain the global attention weight of the multi-core feature MK through the average pooling layer;

[0047] S42, using the convolutional layer, obtain the local attention weight of the multi-core feature MK;

[0048] S43, multiplying the global attention weight and the local attention weight by the elements of the multi-core feature MK respectively, to obtain the global feature G and the local feature L of the multi-core feature MK;

[0049] S44, concatenate the global feature G and the local feature L, and the initial embedding vector O ebd Perform residual connection operation Processing to obtain the global-local fusion feature O GL .

[0050] The present invention performs feature fusion by focusing on the global-local features of multiple cores, ensuring effective feature migration and reducing information loss. Specifically, in order to better fuse features from different sources, the present invention proposes a global-local fusion function in the multi-core feature fusion module, rather than directly stacking features from different sources like PEA-m6A.

[0051] In a more specific technical solution, in S5, the following contrastive learning loss function L is used:cl Optimize to obtain feature space:

[0052]

[0053] In the formula, Z indicates whether two samples i and j belong to the same category, the same category is assigned a value of 0, and different categories are assigned a value of 1; D represents the Euclidean distance; M represents the optimized distance threshold.

[0054] The present invention proposes a downsampling feature embedding module, which uses downsampling to embed features, while reducing feature maps and improving computational memory efficiency, while ensuring efficient and effective transmission of key features, thereby improving rice m 6 A site prediction accuracy. The present invention introduces downsampling feature embedding for effective feature compression to alleviate invalid features caused by padding and the complexity and low computational efficiency of high-dimensional features brought about by padding.

[0055] In a more specific technical solution, S6 includes:

[0056] S61. Determine rice m 6 A. Whether the predicted probability of the methylation site is less than the preset threshold;

[0057] S62, if yes, then determine that the current rice sequence does not contain m 6 A site;

[0058] S63, if not, determine that the current rice sequence contains m 6 A site.

[0059] In a more specific technical solution, in S6, the following binary cross entropy loss function is used as the classification objective function to perform a minimization optimization operation:

[0060]

[0061] Where N represents the batch size, y n is the true label, is the predicted probability.

[0062] In a more specific technical solution, rice m 6 A methylation site prediction system includes:

[0063] Dataset acquisition module, used to obtain data from m 6 In A-seq sequence data, obtain rice m 6 A dataset;

[0064] Input representation module, used to perform input representation operation, rice m 6In the A dataset, all variable-length sequences are padded to the preset maximum length to obtain the maximum-length padded sequence. The maximum-length padded sequence is label-encoded to obtain the input representation result F. input , the input representation module is connected with the dataset acquisition module;

[0065] Multi-core feature extraction module, used to represent the result F based on the input input , extracting multi-core features, the multi-core feature extraction module is connected with the input representation module;

[0066] The feature fusion module is used to perform global-local feature fusion operations on multi-core features in the model training operation to obtain global-local fusion features; the Adam optimizer is used to set the batch size, learning rate, weight decay and training algebra of the model training operation, and the warm-up learning rate adjustment strategy is used to control the model training operation. The feature fusion module is connected to the multi-core feature extraction module;

[0067] The downsampling feature embedding module is used to downsample the global-local fusion features and embed them to obtain applicable features. Convolutional layers, pooling layers, and residual connections are used alternately to perform layer-by-layer downsampling and feature embedding to retain high-frequency important information. The contrastive learning loss function L is used to cl Adjust the distance between similar samples and heterogeneous samples to optimize the feature optimization results, and connect the downsampling feature embedding module with the feature fusion module;

[0068] The site contains a judgment module, which is used to send the feature optimization results to the fully connected layer in the prediction stage to obtain rice m 6 A methylation site prediction probability to obtain rice sequence m 6 A site contains the judgment result, wherein the fully connected layer includes: a σ function, and the site contains the judgment module and the downsampling feature embedding module are connected.

[0069] Compared with the prior art, the present invention has the following advantages:

[0070] The present invention introduces multi-core feature extraction and fusion to obtain dimensional information with different core spaces, and enhances feature representation by effectively fusing multi-core features. In addition, the present invention proposes a method of downsampling feature embedding to effectively compress the fused multi-core features, ensuring effective information transmission and high computing efficiency.

[0071] The present invention realizes the rice m 6 Classification of A methylation sites. Experimental results show that compared with other methods, the present invention achieves better results on multiple data sets. At the same time, the model of the present invention has better robustness and generalization.

[0072] The present invention extracts and fuses multi-core features to enhance feature representation, which means enhancing key information and suppressing sparse and invalid information. The present invention introduces multi-core feature extraction and fusion to extract key features across multiple receptive fields and reduce sparsity.

[0073] The present invention performs feature fusion by focusing on the global-local features of multiple cores, thereby ensuring effective feature migration and reducing information loss.

[0074] The present invention uses downsampling to embed features, which reduces feature maps, improves computational memory efficiency, and ensures efficient and effective transmission of key features. 6 A site prediction accuracy. The present invention introduces downsampling feature embedding for effective feature compression to alleviate the high-dimensional features and low computational efficiency caused by invalid filling.

[0075] Based on the defects of the prior art, the present invention proposes a rice m 6 A prediction method for methylation sites. In order to alleviate the feature sparsity caused by the filling operation, the rice m 6 After the initial features of A, the patent constructs a multi-core feature fusion module, which includes a multi-core feature extraction function and a global-local fusion function. The multi-core feature extraction function mines the maximum length filling m through different core sizes. 6 The different scale essential information in the A sequence enriches the extracted features. The global-local fusion function performs effective feature information fusion and transmission by focusing on the global channel and local space of the extracted multi-core features, thereby improving the rice m 6 A. The accuracy of methylation site prediction. Considering the complexity and computational efficiency of high-dimensional features caused by invalid filling, the patent designs a downsampling feature embedding module, which performs layer-by-layer downsampling and feature embedding by alternating the use of convolutional layers, pooling layers, and residual connections, optimizes the compression of feature space while retaining high-frequency important information, and achieves accurate feature expression and efficient computing performance.

[0076] The present invention solves the existing rice m 6 A methylation site prediction method adopts a filling method for variable-length sequences, resulting in sparse and invalid features, and directly stacking features from different sources, which leads to rice m 6 A technical problem of low prediction accuracy and poor prediction effect of methylation sites. BRIEF DESCRIPTION OF THE DRAWINGS

[0077] Figure 1 The rice m based on feature extraction and fusion of Example 1 of the present invention 6 A. Schematic diagram of the basic steps of the methylation site prediction method;

[0078] Figure 2This is a schematic diagram of a multi-core feature extraction structure of Embodiment 2 of the present invention;

[0079] Figure 3 Schematic diagram of the global-local feature fusion structure of Example 2 of the present invention;

[0080] Figure 4 Schematic diagram of the downsampling feature embedding structure of embodiment 2 of the present invention;

[0081] Figure 5 This is a schematic diagram of the prediction process of Example 2 of the present invention;

[0082] Figure 6 The figure is a ROC and PR curve diagram of the experimental prediction results of Example 2 of the present invention. DETAILED DESCRIPTION

[0083] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described in combination with the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0084] Example 1

[0085] like Figure 1 As shown, the rice m based on feature extraction and fusion provided by the present invention 6 A methylation site prediction method includes the following basic steps:

[0086] Get the rice m to be predicted 6 A dataset, using label encoding and padding strategy to construct a maximum length padding sequence to obtain a variable length m 6 The initial characteristics of the A sequence will become m long 6 The initial features of the A sequence are input into the trained rice m 6 A methylation site prediction model was used to obtain rice m 6 A. Methylation site prediction results;

[0087] The trained rice 6 A methylation site prediction model is obtained by:

[0088] S1. Obtain rice m 6 A’s dataset;

[0089] In this embodiment, rice m 6 A sequence collected from m 6 A-seq sequence data was obtained after removing homology deviation and redundancy through CD-HIT.

[0090] S2. In the input representation process, rice m 6 All variable length sequences of A are padded to the maximum length to obtain the maximum length padded sequence, and then label encoding is performed to obtain the input representation F input ;

[0091] In this example, padding and label encoding are performed to obtain the maximum length padded sequence, so that rice m 6 The characteristic of the A sequence indicates that the maximum integrity is retained. Specifically, the length of the aforementioned maximum filling sequence can be set to, for example, 800 as required.

[0092] S3, based on the input representation result F obtained in the above step S2 input Extract multi-core features;

[0093] In this embodiment, the number of output channels of the first convolutional neural network is 128, and the number of output channels of the remaining convolutional neural networks is 32.

[0094] In this embodiment, the formula for extracting multi-core features is as follows:

[0095] O ebd =Cv1(Embed(F input ))

[0096] K1=Cv1(O ebd )

[0097] K2=Cv3(Cv1( ebd ))

[0098] K3=Cv5(Cv1( ebd ))

[0099] K4=Cv1(MP3(O ebd ))

[0100] MK=concat(K1,K2,K3,K4)

[0101] Among them, Embed represents the embedding layer, Cv1, Cv3 and Cv5 represent the convolution layers with the convolution kernel size set to 1, 3 and 5 respectively, MP3 represents the maximum pooling layer with the kernel size set to 3, concat represents the concatenation operation, ebd is the initial embedding vector, K1, K2, K3 and K4 are the features of different kernels obtained, and MK is the multi-kernel feature obtained;

[0102] Specifically, in F input The initial embedding vector O is obtained by Embed and Cv1 ebd . For O ebdUse Cv1, Cv3 and Cv5 to extract information of different spatial dimensions to obtain K1, K2 and K3. K2 and K3 perform Cv1 in the initial acquisition to reduce the number of channels, thereby reducing the number of parameters and the complexity of the model. K4 uses MP3 to obtain feature information of the channel dimension and uses Cv1 to change the number of channels; concat the features of these different kernels to obtain the final MK;

[0103] S4, during the training process, the multi-core features obtained in the above step S3 are subjected to global-local feature fusion;

[0104] In the training process of this embodiment, the Adam optimizer is used, and the batch size, learning rate, weight decay and training generations are set as needed, and the warm-up learning rate adjustment strategy is used. Specifically, the batch size is set to 128, the learning rate is set to 0.001, the weight decay is set to 1e-6, and the warm-up learning rate adjustment strategy is used to avoid the model converging too quickly in the early stage of training, thereby falling into a local optimal solution. The training generation is set to 100 generations.

[0105] The convolution kernel sizes of the convolutional neural network of this embodiment can be set to, for example, 1, 5, 5, 5, 1 respectively; the number of output channels can be set to, for example, 32, 8, 32, 1, 128 respectively.

[0106] In this embodiment, the formula for performing the aforementioned global-local feature fusion operation is as follows:

[0107] MK=Cv(MK)

[0108]

[0109]

[0110] GL=Cv(concat(G,L))

[0111]

[0112] Among them, σ represents the sigmoid function, AP represents the average pooling layer;

[0113] Specifically, the global attention weight and local attention weight of MK are obtained through the average pooling layer and the convolution layer, and then these weights are multiplied with the MK elements to obtain the global features and local features of MK, namely G and L. After G and L are concatenated, they are combined with O ebd Perform residual connection Reduce distortion to obtain the final global-local fusion feature O GL .

[0114] S5. During the training process, downsampling the fused features obtained in the above step S4 is performed on the features to embed them into high-level features;

[0115] In this embodiment, in order to solve the problem of high feature dimension and low computational efficiency caused by invalid padding, convolutional layers, pooling layers and residual connections are used alternately to perform layer-by-layer downsampling and feature embedding; while reducing the size of the feature map, the consistency of the feature map space is ensured, and high-frequency important information is retained. In addition, using the contrastive learning loss function L cl The feature space obtained by optimization is as follows:

[0116]

[0117] Among them, Z indicates whether two samples i and j belong to the same category, the same category is assigned 0, and different categories are assigned 1; D represents the Euclidean distance; M represents the optimized distance threshold;

[0118] Specifically, L cl The function is to achieve feature optimization during the training process by making the distances between samples of the same type closer and the distances between samples of different types farther apart.

[0119] In this embodiment, the optimized distance threshold M may be set to, for example, 2.

[0120] S6. In the prediction stage, the feature optimization result obtained in the above step S5 is sent to the fully connected layer with the σ function to obtain the rice m 6 A methylation site prediction probability; when the prediction probability is less than the threshold, it is determined that the rice sequence does not contain m 6 A site, otherwise the rice sequence contains m 6 A site. And, the binary cross entropy loss function is used as the classification objective function for minimization optimization:

[0121]

[0122] Where N is the batch size, y n is the true label, is the predicted probability.

[0123] In this embodiment, the number of neurons in the fully connected layer can be set to, for example, 12800. The threshold of the prediction probability can be set to, for example, 0.5.

[0124] Example 2

[0125] In this embodiment, the trained rice m is obtained. 6A methylation site prediction model. In the input representation process, we first use the rice m 6 A public dataset. The positive samples of this dataset are extracted from the leaves of Japanese naked seedlings of rice m 6 A-seq peak sequence data, sample length is 20 to 800. Negative samples are obtained by cutting off the upper and lower parts of the corresponding positive samples without including m 6 The equal length sequences of site A were obtained. They also used CD-HIT[2]FuL,Niu B,Zhu Z,et al.CD-HIT:accelerated for clustering the next-generationsequencing data[J].Bioinformatics,2012,28(23):3150-3152 to reduce homology bias and remove redundancy in the dataset. After data cleaning and duplicate data removal, 80% of positive and negative samples were randomly selected from the dataset as a benchmark dataset to evaluate the model performance. In addition, in order to verify the generalization ability of the model, the remaining samples were used as independent test sets. The information of the above datasets is shown in Table 1:

[0126] dataset positive samples negative samples total samples Benchmark Datasets 19,844 39,692 59,536 Independent test set 4,963 9,923 14,886

[0127] Table 1

[0128] In this embodiment, the data set is divided into a training set and a validation set according to a ratio of 4:1, and a 5-fold cross validation is performed during the experiment.

[0129] Specifically, rice 6 A sequence is variable length data. In order to retain the complete sequence information and incorporate it into the model, this embodiment fills all sequences to a maximum length of 800. At the same time, in order to adapt to the model, this embodiment uses label encoding to convert rice m 6 A sequence is converted to a numeric representation, which assigns a unique numeric identifier to each character class.

[0130] In this embodiment, assuming that the maximum sequence length is 10, the sequence "ATTCG" consists of four types of bases, namely A, T, G and C. "P" is used to represent padding, so the padded sequence is "PPPPPATTCG". Then, the five types of characters (P, A, T, G and C) are assigned numbers according to the label encoding, which are 0, 1, 2, 3 and 4 respectively. Therefore, this padded sequence can be expressed as "0,0,0,0,0,1,2,2,4,3".

[0131] like Figure 2 As shown, during the training process, the rice m 6 A sequence input represents multi-core feature extraction.

[0132] Specifically, rice m 6 A sequence input represents F input After that, the initial embedding vector is obtained through the embedding layer and the convolution layer. For the initial embedding vector, convolution layers with different kernel sizes and maximum pooling layers are used respectively to extract information in different spatial dimensions to obtain multi-kernel features. The convolution layer with a kernel size of 1 is used to reduce the number of channels, thereby reducing the number of parameters and the complexity of the model. The relevant calculation formula is as follows:

[0133] O ebd =Cv1(Embed(F input ))

[0134] K1=Cv1(O ebd )

[0135] K2=Cv3(Cv1( ebd ))

[0136] K3=Cv5(Cv1( ebd ))

[0137] K4=Cv1(MP3(O ebd ))

[0138] MK=concat(K1,K2,K3,K4)

[0139] Among them, Embed represents the embedding layer, Cv1, Cv3 and Cv5 represent the convolution layers with the convolution kernel size set to 1, 3 and 5 respectively, MP3 represents the maximum pooling layer with the kernel size set to 3, concat represents the concatenation operation, ebd is the initial embedding vector, K1, K2, K3 and K4 are the features of different kernels obtained, and MK is the multi-kernel feature obtained.

[0140] like Figure 3 As shown, in this embodiment, the obtained multi-core features are subjected to global-local feature fusion.

[0141] Specifically, the global attention weight and local attention weight of the multi-core feature are obtained through the average pooling layer and the convolution layer, and then these weights are element-wise multiplied with the multi-core feature to obtain its global feature and local feature. After the global feature and the local feature are concatenated, the final global-local fusion feature is obtained by performing a residual connection with the initial embedding vector obtained previously to reduce distortion. The relevant calculation formula is as follows:

[0142] MK=Cv(MK)

[0143]

[0144]

[0145] GL=Cv(concat(G,L))

[0146]

[0147] Among them, σ represents the sigmoid function, AP represents the average pooling layer; It represents the bitwise multiplication of elements; Represents residual connection. G and L represent global features and local features respectively. GL It is a global-local fusion feature.

[0148] like Figure 4 As shown, in this embodiment, downsampling feature embedding is performed on the obtained fusion features to obtain high-level features.

[0149] Specifically, in order to solve the problem of high feature dimension and low computational efficiency caused by invalid padding, convolutional layers, pooling layers and residual connections are used alternately to perform layer-by-layer downsampling and feature embedding. This achieves the goal of reducing the size of feature maps while ensuring spatial consistency of feature maps and retaining high-frequency important information. In addition, the feature space obtained by optimizing the contrastive learning loss function is as follows:

[0150]

[0151] Among them, Z indicates whether two samples i and j belong to the same category, the same category is assigned a value of 0, and different categories are assigned a value of 1; D represents the Euclidean distance; M represents the optimized distance threshold.

[0152] The contrastive learning loss function L used in this embodiment is cl , it is possible to achieve feature optimization during the training process by making the distances between similar samples closer and the distances between heterogeneous samples farther apart.

[0153] like Figure 5As shown, in the prediction process steps of this embodiment, firstly, for the input sequence feature representation obtained by the previous feature encoding, the multi-core feature MK is extracted; MK is subjected to global and local feature fusion to obtain O GL ; For O GL , by downsampling feature embedding, high-level features are obtained by optimizing the contrastive learning loss function; the optimized features are flattened and sent to the fully connected layer with the σ function to obtain the rice m 6 A methylation site prediction probability; when the prediction probability is less than the threshold, it is determined that the rice sequence does not contain m 6 A site, otherwise the rice sequence contains m 6 A site.

[0154] In this embodiment, a binary cross entropy loss function is used as the classification objective function for minimization optimization:

[0155]

[0156] Where N is the batch size, y n is the true label, is the predicted probability.

[0157] In this embodiment, the area under the receiver operating characteristic curve (AUC) and the area under the precision-recall curve (AUPR) are used to judge the performance indicators of the model.

[0158] In this example, in order to verify the prediction of rice m 6 The effect of A methylation sites was studied by using the above two types of datasets, namely the benchmark dataset and the independent test set, and comparing them with the prediction of m 6 The main methods of site A, SMEP and PEA-m6A, were compared. For the benchmark dataset, a 5-fold cross validation was set up in the experiment, and the average of the results of the 5-fold cross validation was taken as the final result (see Figure 6 shown). Figure 6 The experimental results show that the comprehensive performance of the present invention is better than other existing methods, indicating that the present invention can more effectively predict rice m 6 A methylation site. In particular, the AUC of the present invention reached 0.9038 and the AUPR reached 0.8201, which is 9.55% higher than the suboptimal method SMEP. To further illustrate the superiority and generalization of the present invention, we compared it with the existing prediction methods on an independent test set. (The results are shown in Table 2 below, where the best results are bolded and the suboptimal results are underlined:

[0159] method AUC AUPR The present invention 0.8941 0.8068 SMEP <![CDATA[ 0.8687 ]]> <![CDATA[ 0.7602 ]]> PEA-m6A 0.8400 0.7074

[0160] Table 2

[0161] The experimental results in Table 2 above show that the present invention is more effective than the comparison method on the independent test set and has good generalization ability. Specifically, the present invention improves AUC and AUPR by 2.54% and 4.66% respectively compared with the suboptimal method SMEP. It is worth noting that the results on the independent test set are comparable to the 5-fold cross validation results, indicating that all methods show robustness and transfer performance.

[0162] The present invention has achieved better results on the aforementioned multiple data sets, with higher prediction accuracy. At the same time, the experimental results also show that the model used in the present invention has better robustness and generalization ability, and can be extended to rice m 6 A site prediction is a similar problem.

[0163] The present invention uses a global-local fusion multi-core feature extraction and downsampling feature embedding method to reduce the sparsity, high-dimensional features and low computational efficiency caused by padded sequence encoding. Specifically, since variable-length sequences contain a large amount of information, label encoding and padding strategies are used to construct maximum-length padded sequences to promote feature learning. However, lengthy and invalid sequence padding will lead to sparse and redundant features and weaken the model's ability to capture meaningful sequence-level information. Therefore, the multi-core feature extraction method we proposed can extract key features across multiple receptive fields to reduce the sparsity problem caused by maximum-length padded sequence encoding. At the same time, through the fusion of global and local features, the features extracted from the multi-core can be effectively migrated. In addition, in order to solve the problems of high feature dimensionality and low computational efficiency caused by invalid sequence padding, a downsampling feature embedding method is introduced to effectively compress the features and improve the computational performance. Experimental results show that the present invention has good prediction performance, robustness and generalization ability, which is conducive to enhancing feature representation and extraction and transmitting efficient information.

[0164] The prediction method of the present invention has a strong feature enhancement effect on data. The prediction method of the present invention can be used in the future rice m 6 It plays a beneficial role in the prediction task of A methylation sites and has application prospects in more similar fields.

[0165] In summary, the present invention introduces multi-core feature extraction and fusion to obtain dimensional information with different kernel spaces, and enhances feature representation by effectively fusing multi-core features. In addition, the present invention proposes a method of downsampling feature embedding to effectively compress the fused multi-core features, thereby ensuring effective information transmission and high computing efficiency.

[0166] The present invention realizes the rice m 6Classification of A methylation sites. Experimental results show that compared with other methods, the present invention achieves better results on multiple data sets. At the same time, the model of the present invention has better robustness and generalization.

[0167] The present invention extracts and fuses multi-core features to enhance feature representation, which means enhancing key information and suppressing sparse and invalid information. The present invention introduces multi-core feature extraction and fusion to extract key features across multiple receptive fields and reduce sparsity.

[0168] The present invention performs feature fusion by focusing on the global-local features of multiple cores, thereby ensuring effective feature migration and reducing information loss.

[0169] The present invention uses downsampling to embed features, which reduces feature maps, improves computational memory efficiency, and ensures efficient and effective transmission of key features. 6 A site prediction accuracy. The present invention introduces downsampling feature embedding for effective feature compression to alleviate the high-dimensional features and low computational efficiency caused by invalid filling.

[0170] The present invention solves the existing rice m 6 A methylation site prediction method adopts a filling method for variable-length sequences, resulting in sparse and invalid features, and directly stacking features from different sources, which leads to rice m 6 A technical problem of low prediction accuracy and poor prediction effect of methylation sites.

[0171] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. Rice m based on feature extraction and fusion 6 A methylation site prediction method, characterized in that: The method comprises: S1, from m 6 In A-seq sequence data, obtain rice m 6 A dataset; S2, perform input representation operation, and input the rice m 6 In the A data set, all variable-length sequences are padded to the preset maximum length to obtain the maximum-length padded sequence, and the maximum-length padded sequence is label-encoded to obtain the input representation result F. input ; S3, based on the input representation result F input , extract multi-core features; S4. In the model training operation, a global-local feature fusion operation is performed on the multi-core features to obtain global-local fusion features; using the Adam optimizer, the batch size, learning rate, weight decay and training algebra of the model training operation are set, and a warm-up learning rate adjustment strategy is used to control the model training operation; S5, downsampling the global-local fusion feature and embedding it to obtain applicable features; wherein, convolutional layers, pooling layers and residual connections are alternately used to perform layer-by-layer downsampling and feature embedding to retain high-frequency important information, and the contrastive learning loss function L is used. cl Adjust the distance between similar samples and heterogeneous samples to optimize the feature optimization results; S6. In the prediction stage, the feature optimization result is sent to the fully connected layer to obtain rice m 6 A methylation site prediction probability to obtain rice sequence m 6 The A site includes a determination result, wherein the fully connected layer includes: a σ function.

2. The rice m based on feature extraction and fusion according to claim 1 6 A methylation site prediction method, characterized in that: In S3, the multi-core features are extracted using the following logic: O ebd =Cv1(Embed(F input )) K1=Cv1(O ebd ) K2=Cv3(Cv1(O ebd )) K3=Cv5(Cv1(O ebd )) K4=Cv1(MP3(O ebd )) MK=concat(K1,K2,K3,K4) Where, Embed represents the embedding layer, Cv1, Cv3, and Cv5 represent the convolutional layers with kernel sizes set to 1, 3, and 5, respectively, MP3 represents the maximum pooling layer with kernel size set to 3, concat represents the concatenation operation, and ebd is the initial embedding vector, K1, K2, K3 and K4 are the features of different kernels obtained, and MK is the multi-kernel feature obtained.

3. The rice m based on feature extraction and fusion according to claim 1 6 A methylation site prediction method, characterized in that: The S3 further includes: S31, the input represents the result F input The initial embedding vector O is obtained through the embedding layer Embed and the first convolutional layer Cv1 ebd ; S32, for the initial embedding vector O ebd , respectively use the first convolution layer Cv1, the second convolution layer Cv3 and the third convolution layer Cv5 to extract information of different spatial dimensions, and obtain the first kernel feature K1, the second kernel feature K2, the third kernel feature K3 and the fourth kernel feature K4; S33, performing concat processing on the first core feature K1, the second core feature K2, the third core feature K3 and the fourth core feature K4 to obtain the multi-core feature MK.

4. The rice m based on feature extraction and fusion according to claim 3 6 A methylation site prediction method, characterized in that: The S32 includes: S321, in the initial acquisition stage of the first kernel feature K2 and the second feature K3, executing the first convolutional layer Cv1 to adjust the number of channels; S322. The fourth kernel feature K4 uses MP3 to obtain feature information of the channel dimension, and uses the first convolutional layer Cv1 to change the number of channels.

5. The rice m based on feature extraction and fusion according to claim 1 6 A methylation site prediction method, characterized in that: In S4, the global-local feature fusion operation is performed using the following logic: MK=Cv(MK) GL=Cv(concat(G,L)) Where σ represents the sigmoid function and AP represents the average pooling layer.

6. The rice m based on feature extraction and fusion according to claim 1 6 A methylation site prediction method, characterized in that: The S4 includes: S41, obtaining the global attention weight of the multi-core feature MK through an average pooling layer; S42, using a convolutional layer to obtain a local attention weight of the multi-core feature MK; S43, multiplying the global attention weight and the local attention weight by the elements of the multi-core feature MK respectively to obtain the global feature G and the local feature L of the multi-core feature MK; S44, concatenate the global feature G and the local feature L, and the initial embedding vector O ebd Perform residual connection operation ⊕ to obtain the global-local fusion feature O GL .

7. The rice m based on feature extraction and fusion according to claim 1 6 A methylation site prediction method, characterized in that: In S5, the following contrastive learning loss function L is used: cl Optimize to obtain feature space: In the formula, Z indicates whether two samples i and j belong to the same category, the same category is assigned a value of 0, and different categories are assigned a value of 1; D represents the Euclidean distance; M represents the optimized distance threshold.

8. The rice m based on feature extraction and fusion according to claim 1 6 A methylation site prediction method, characterized in that: The S6 includes: S61, determining the rice m 6 A. Whether the predicted probability of the methylation site is less than the preset threshold; S62, if yes, then determine that the current rice sequence does not contain m 6 A site; S63, if not, determining that the current rice sequence contains the m 6 A site.

9. The rice m based on feature extraction and fusion according to claim 1 6 A methylation site prediction method, characterized in that: In S6, the following binary cross entropy loss function is used as the classification objective function to perform a minimization optimization operation: Where N is the batch size, y n is the true label, is the predicted probability.

10. Rice m based on feature extraction and fusion 6 A methylation site prediction system, characterized in that The system comprises: Dataset acquisition module, used to obtain data from m 6 In A-seq sequence data, obtain rice m 6 A dataset; An input representation module is used to perform an input representation operation, wherein the rice m 6 In the A data set, all variable-length sequences are padded to the preset maximum length to obtain the maximum-length padded sequence, and the maximum-length padded sequence is label-encoded to obtain the input representation result F. input , the input representation module is connected to the data set acquisition module; A multi-core feature extraction module is used to represent the result F based on the input input , extracting multi-core features, the multi-core feature extraction module is connected to the input representation module; A feature fusion module is used to perform a global-local feature fusion operation on the multi-core features in a model training operation to obtain a global-local fusion feature; an Adam optimizer is used to set the batch size, learning rate, weight decay and training algebra of the model training operation, and a warm-up learning rate adjustment strategy is used to control the model training operation. The feature fusion module is connected to the multi-core feature extraction module; The downsampling feature embedding module is used to downsample the global-local fusion features to obtain applicable features; wherein, convolutional layers, pooling layers and residual connections are used alternately to perform layer-by-layer downsampling and feature embedding to retain high-frequency important information, and the contrastive learning loss function L is used. cl Adjusting the distance between samples of the same type and the distance between samples of different types to optimize the feature optimization result, the downsampling feature embedding module is connected with the feature fusion module; The site includes a judgment module, which is used to send the feature optimization results to the fully connected layer in the prediction stage to obtain rice m 6 A methylation site prediction probability to obtain rice sequence m 6 A site contains a judgment result, wherein the fully connected layer includes: a σ function, and the site contains a judgment module connected to the downsampling feature embedding module.

Images