Anticancer peptide prediction method and system based on protein language model

Abstract

The present invention relates to a method and system for predicting anticancer peptides based on a protein language model. The method comprises: collecting and screening anticancer peptide samples and non-anticancer peptide samples to construct a data set; inputting the data set into a protein language model for feature processing to extract high-dimensional biological features from the sample sequence; performing convolution operations on the high-dimensional biological features using a convolutional neural network through the protein language model, and dynamically adjusting the weights of the high-dimensional biological features through a self-attention mechanism to capture global features in the peptide sequence; and predicting anticancer peptides through a fully connected layer in the protein language model to obtain prediction results. By performing feature processing through a protein language model and capturing global features based on a convolutional neural network and a self-attention mechanism, the method eliminates the need for complex feature engineering steps, fully exploits key information in the peptide sequence, and thereby improves the model's anticancer peptide prediction performance. Anticancer peptides can be predicted quickly, at low cost, and with high accuracy.

Description

Technical Field

[0001] The present invention relates to the field of bioinformatics, and in particular to a method and system for predicting anticancer peptides based on a protein language model. Background Art

[0002] Anticancer peptides (ACPs) are a class of short peptides with anticancer properties that can target and kill cancer cells through multiple mechanisms while minimizing damage to normal cells. ACPs typically consist of 5 to 50 amino acids. Their primary mechanism of action is interaction with cancer cell membranes, leading to cell membrane lysis or permeation. ACPs can also exert their anticancer effects through inhibiting angiogenesis, inducing tumor cell apoptosis, and targeting key proteins. In recent years, ACPs have garnered widespread attention due to their high efficacy and low toxicity, becoming a hot topic in cancer therapy research. Compared with traditional chemotherapy and radiotherapy, the selective killing effects of ACPs significantly reduce treatment side effects and improve patients' quality of life. In the study of ACPs, not only is identifying their presence crucial; predicting their potency and activity is also crucial for optimizing anticancer therapy. Accurately predicting the anticancer activity of ACPs can accelerate drug development, help researchers better understand their mechanisms of action, and ultimately facilitate the implementation of personalized treatment plans. Therefore, the development of accurate and effective ACP prediction tools is crucial for the future development of cancer therapy.

[0003] Currently, the application of anticancer peptides (ACPs) is still in the research stage. Traditional cancer treatments mainly include chemotherapy, radiotherapy and surgery. Chemotherapy inhibits the proliferation of cancer cells through chemical drugs, while radiotherapy kills cancer cells through high-energy radiation.

[0004] Therefore, traditional cancer treatments are often associated with serious side effects, such as damage to normal cells, immune system suppression, and decreased quality of life for patients. With the rapid development of artificial intelligence (AI) technologies, anticancer peptide prediction tools based on machine learning and deep learning have gradually emerged. These tools can rapidly predict potential anticancer peptides by analyzing protein sequences and physicochemical properties, reducing the time and cost of experimental screening. However, traditional anticancer peptide prediction methods are costly and have low accuracy. Summary of the Invention

[0005] Based on this, in order to solve the above technical problems, a method and system for predicting anticancer peptides based on a protein language model are provided, which can predict anticancer peptides quickly, at low cost and with high accuracy.

[0006] A method for predicting anticancer peptides based on a protein language model, comprising:

[0007] Collecting and screening anticancer peptide samples and non-anticancer peptide samples from a database, and constructing a data set based on the anticancer peptide samples and non-anticancer peptide samples;

[0008] Inputting the data set into a protein language model, performing feature processing on the sample sequences in the data set by the protein language model, and extracting high-dimensional biological features from the sample sequences;

[0009] The protein language model uses a convolutional neural network to perform a convolution operation on the high-dimensional biological features, and dynamically adjusts the weights of the high-dimensional biological features through a self-attention mechanism to capture the global features in the peptide sequence;

[0010] The high-dimensional biological features and global features are input into the fully connected layer of the protein language model to predict anticancer peptides to obtain prediction results.

[0011] In one embodiment, anticancer peptide samples and non-anticancer peptide samples are collected and screened from a database, and a data set is constructed based on the anticancer peptide samples and non-anticancer peptide samples, including:

[0012] Collecting anticancer peptides from a database, and performing homology elimination on the anticancer peptides to obtain eliminated anticancer peptides;

[0013] Performing PSSM matrix extraction on the eliminated anticancer peptides to obtain a final anticancer peptide sample;

[0014] collecting non-anti-cancer peptides from a database, and eliminating the non-anti-cancer peptides by homology to obtain eliminated non-anti-cancer peptides;

[0015] Performing PSSM matrix extraction on the eliminated non-anticancer peptides to obtain a final non-anticancer peptide sample;

[0016] Anti-cancer peptide sequences are selected from the final anti-cancer peptide sample, and non-anti-cancer peptide sequences are selected from the final non-anti-cancer peptide sample to form a data set.

[0017] In one embodiment, the method further comprises:

[0018] The final anti-cancer peptide sample is used as a positive sample, and the final non-anti-cancer peptide sample is used as a negative sample;

[0019] Randomly selecting anticancer peptide samples from the positive samples as anticancer peptide sequences, and randomly selecting non-anticancer peptide samples from the negative samples as non-anticancer peptide sequences as a data set;

[0020] The remaining anticancer peptide sequences in the positive samples and the remaining non-anticancer peptide sequences in the negative samples are used as test sets.

[0021] In one embodiment, the dataset is input into a protein language model, and the protein language model is used to perform feature processing on the sample sequences in the dataset to extract high-dimensional biological features from the sample sequences, including:

[0022] Inputting the data set into a protein language model, performing feature processing on the anticancer peptide sequences in the data set through the protein language model to capture implicit patterns, long-term dependencies, and contextual information in the anticancer peptide sequences;

[0023] Based on the implicit patterns, long-term dependencies, and contextual information, high-dimensional biological features in the anticancer peptide sequence are generated.

[0024] In one embodiment, the protein language model is used to perform a convolution operation on the high-dimensional biological features using a convolutional neural network, and the weights of the high-dimensional biological features are dynamically adjusted through a self-attention mechanism to capture the global features in the anticancer peptide sequence, including:

[0025] Performing a convolution operation on the context information using a convolutional neural network through the protein language model to obtain convolved information;

[0026] Adjusting the weights of the high-dimensional biological features through a self-attention mechanism to identify the long-term dependencies;

[0027] Based on the convolved information, the weights of the high-dimensional biological features, and the long-term dependencies, global context information is integrated to obtain global features.

[0028] In one embodiment, the protein language model is used to perform a convolution operation on the context information using a convolutional neural network to obtain the convolved information, including:

[0029] Using a convolutional neural network to perform a nonlinear transformation on each of the context information to obtain nonlinearly transformed information;

[0030] One-dimensional convolution is used to perform a convolution operation on the information after the nonlinear transformation, and batch normalization processing is added after each convolution layer, and the convolved information is obtained through the output of the pooling layer.

[0031] In one embodiment, adjusting the weight of the high-dimensional biological features through a self-attention mechanism includes:

[0032] Performing a linear transformation on the high-dimensional biological features through a self-attention mechanism to obtain a transformation matrix;

[0033] Get the self-attention mechanism weight matrix and the key vector dimensions of each attention head;

[0034] The weight of the high-dimensional biological feature is adjusted based on the transformation matrix, the self-attention mechanism weight matrix, and the key vector dimension.

[0035] In one embodiment, the method further comprises:

[0036] Determining a model evaluation index, and performing a model evaluation on the protein language model according to the model evaluation index to obtain an evaluation result;

[0037] The protein language model is optimized based on the evaluation results.

[0038] A protein language model-based anticancer peptide prediction system, comprising:

[0039] A data set construction module is used to collect and screen anticancer peptide samples and non-anticancer peptide samples from a database, and to construct a data set based on the anticancer peptide samples and non-anticancer peptide samples;

[0040] a high-dimensional biological feature extraction module, configured to input the data set into a protein language model, perform feature processing on the sample sequences in the data set using the protein language model, and extract high-dimensional biological features from the sample sequences;

[0041] A global feature extraction module is used to perform a convolution operation on the high-dimensional biological features using a convolutional neural network through the protein language model, and dynamically adjust the weights of the high-dimensional biological features through a self-attention mechanism to capture the global features in the peptide sequence;

[0042] The anticancer peptide prediction module is used to input the high-dimensional biological features and global features into the fully connected layer in the protein language model to predict anticancer peptides and obtain prediction results.

[0043] The above-mentioned anticancer peptide prediction method and system based on the protein language model performs feature processing through the protein language model to extract high-dimensional biological features, and captures global features based on convolutional neural networks and self-attention mechanisms. Without the need for complex feature engineering steps, it can fully mine the key information in the peptide sequence, thereby improving the model's anticancer peptide prediction performance, and can predict anticancer peptides quickly, at low cost and with high accuracy. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] Figure 1 FIG1 is an application environment diagram of an anticancer peptide prediction method based on a protein language model in one embodiment;

[0045] Figure 2 FIG1 is a flow chart of a method for predicting anticancer peptides based on a protein language model in one embodiment;

[0046] Figure 3Schematic diagram of the model framework of ACP-ESM2 in one embodiment;

[0047] Figure 4 Schematic diagram for feature visualization after training;

[0048] Figure 5 Schematic diagram of feature visualization before training;

[0049] Figure 6 FIG1 is a structural block diagram of an anticancer peptide prediction system based on a protein language model in one embodiment;

[0050] Figure 7 FIG. 1 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0051] In order to make the purpose, technical solutions and advantages of this application more clear, the following further describes this application in detail with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain this application and are not intended to limit this application.

[0052] The anticancer peptide prediction method based on protein language model provided in the embodiment 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 and screen anticancer peptide samples and non-anticancer peptide samples from a database and construct a dataset based on the anticancer peptide samples and non-anticancer peptide samples. The computer device 110 can input the dataset into a protein language model, perform feature processing on the sample sequences in the dataset through the protein language model, and extract high-dimensional biological features from the sample sequences. The computer device 110 can use a convolutional neural network to perform convolution operations on the high-dimensional biological features through the protein language model, and dynamically adjust the weights of the high-dimensional biological features through a self-attention mechanism to capture global features in the peptide sequence. The computer device 110 can input the high-dimensional biological features and global features into the fully connected layer of the protein language model to predict anticancer peptides and obtain prediction results. The computer device 110 can be, but is not limited to, various personal computers, laptops, smartphones, robots, unmanned aerial vehicles, and other devices.

[0053] In one embodiment, Figure 2 As shown, a method for predicting anticancer peptides based on a protein language model is provided, comprising the following steps:

[0054] Step 202 : Collect and screen anticancer peptide samples and non-anticancer peptide samples from a database, and construct a data set based on the anticancer peptide samples and non-anticancer peptide samples.

[0055] To train the protein language model, a dataset can be constructed first. Specifically, experimentally verified anticancer peptides and non-anticancer peptide samples can be collected and screened from public databases. After homology filtering and PSSM matrix extraction, a training set can be constructed for model training.

[0056] In one embodiment, a provided method for predicting anticancer peptides based on a protein language model may further include a process for constructing a data set, the specific process including: collecting anticancer peptides from a database, and performing homology elimination on the anticancer peptides to obtain eliminated anticancer peptides; performing PSSM matrix extraction on the eliminated anticancer peptides to obtain a final anticancer peptide sample; collecting non-anticancer peptides from a database, and performing homology elimination on the non-anticancer peptides to obtain eliminated non-anticancer peptides; performing PSSM matrix extraction on the eliminated non-anticancer peptides to obtain a final non-anticancer peptide sample; selecting anticancer peptide sequences from the final anticancer peptide sample, and selecting non-anticancer peptide sequences from the final non-anticancer peptide sample to construct a data set.

[0057] In this example, a total of 1,350 experimentally verified anticancer peptides can be collected from the public databases CancerPPD, APD3, and SATPd, and anticancer peptide samples with a homology of more than 90% can be eliminated to eliminate the high recognition accuracy caused by homology bias. Next, the Seqkit tool is used to extract sequences with lengths from 5 to 50, and only sequences that can access the PSSM matrix through the PSI-BLAST tool are retained. At the same time, the non-anticancer peptides can be subjected to homology bias elimination and PSSM matrix extraction in the same manner, ultimately obtaining 1,839 non-anticancer peptide samples.

[0058] In one embodiment, a provided anticancer peptide prediction method based on a protein language model may further include a process of dividing a data set, the specific process including: taking the final anticancer peptide sample as a positive sample, and taking the final non-anticancer peptide sample as a negative sample; randomly selecting anticancer peptide samples from the positive samples as anticancer peptide sequences, and randomly selecting non-anticancer peptide samples from the negative samples as non-anticancer peptide sequences as a data set; and taking the remaining anticancer peptide sequences in the positive samples and the remaining non-anticancer peptide sequences in the negative samples as a test set.

[0059] For example, in this embodiment, 487 sequences can be randomly selected from anticancer peptide-positive samples, and 1,479 sequences can be randomly selected from anticancer peptide-negative samples to construct a training dataset. In addition, two test sets, Test1 and Test2, are constructed to verify the generalization ability of the protein language model for predicting anticancer peptide ACPs. Both constructed test sets are also subjected to homology filtering and PSSM matrix extraction. Among them, the number of positive samples in Test1 is 135, and the number of negative samples is 360, which is the remaining part of the constructed anticancer peptide dataset. Test2 can be composed of 99 positive samples and 157 negative samples.

[0060] In step 204 , the data set is input into a protein language model, and the protein language model is used to perform feature processing on the sample sequences in the data set to extract high-dimensional biological features from the sample sequences.

[0061] In one embodiment, a provided method for predicting anticancer peptides based on a protein language model may further include a process for extracting high-dimensional biological features. The specific process includes: inputting a data set into a protein language model, performing feature processing on the anticancer peptide sequences in the data set through the protein language model, capturing implicit patterns, long-term dependencies, and contextual information in the anticancer peptide sequences; and generating high-dimensional biological features in the anticancer peptide sequences based on the implicit patterns, long-term dependencies, and contextual information.

[0062] Among them, the protein language model ESM2 performs feature processing on anti-cancer peptides through a deep learning pre-training model, which can deeply understand the complex structure and functional information of protein sequences; and the pre-training process based on large-scale data enables the model to capture the implicit patterns and long-term dependencies in anti-cancer peptides and generate high-dimensional sequence representations.

[0063] In step 206 , a convolutional neural network is used to perform convolution operations on the high-dimensional biological features through a protein language model, and the weights of the high-dimensional biological features are dynamically adjusted through a self-attention mechanism to capture the global features in the peptide sequence.

[0064] In one embodiment, a provided method for predicting anticancer peptides based on a protein language model may further include a convolution operation process, specifically comprising: performing a convolution operation on contextual information using a convolutional neural network through a protein language model to obtain convolved information; adjusting the weights of high-dimensional biological features through a self-attention mechanism to identify long-term dependencies; and integrating global contextual information based on the convolved information, the weights of high-dimensional biological features, and long-term dependencies to obtain global features.

[0065] Computer equipment can extract high-dimensional biological features through ESM2. The convolutional neural network (CNN) no longer processes the original sequence, but instead performs convolution operations on the contextual information extracted by ESM2, making the features extracted by CNN more representative and helping the model capture important local patterns more efficiently.

[0066] In one embodiment, a provided method for predicting anticancer peptides based on a protein language model may also include a process of adjusting weights using a self-attention mechanism. The specific process includes: performing a linear transformation on high-dimensional biological features through a self-attention mechanism to obtain a transformation matrix; obtaining a self-attention mechanism weight matrix and obtaining a key vector dimension for each attention head; and adjusting the weights of high-dimensional biological features based on the transformation matrix, the self-attention mechanism weight matrix, and the key vector dimension.

[0067] Computer devices can dynamically adjust the weights of each feature through the self-attention mechanism to identify key long-distance dependencies in the sequence. This local feature extraction capability combined with the self-attention mechanism allows the model to more accurately integrate global contextual information, capturing important global features of anti-cancer peptides, thereby improving the classification and prediction performance of anti-cancer peptides.

[0068] Among them, the self-attention mechanism of ESM2 can be described as:

[0069]

[0070] Among them, Q, K and V represent the query, key and value matrices obtained by performing different linear transformations on the input sequence, respectively. and represents the weight matrix, d k Represents the dimension of the key vector for each attention head in the key matrix.

[0071] The feedforward neural network sublayer of ESM2 performs a nonlinear transformation on the context representation of each position. This sublayer usually includes an activation function and two linear transformations. The calculation process is as follows:

[0072] output(x)=max(0,xW1+b1)W2+b2

[0073] Among them, x represents the input, W1 represents the convolution kernel of the first layer, W2 represents the convolution kernel of the second layer, and b1 and b2 represent bias.

[0074] In one embodiment, the computer device can use a convolutional neural network to perform a nonlinear transformation on each context information to obtain nonlinearly transformed information; use one-dimensional convolution to perform a convolution operation on the nonlinearly transformed information, and add batch normalization processing after each convolution layer to obtain the convolved information through the pooling layer output.

[0075] Specifically, three one-dimensional convolutional layers can be applied to process the extracted features through convolution operations. Batch normalization is also added after each convolutional layer to normalize the features of each small batch of data, thereby accelerating the network training process and improving the robustness of the model. Let the input be x and the convolution kernel of the i-th layer be W i , bias is b i , then the convolution operation is: i =x*W i +b i .

[0076] In order to obtain more accurate results, it is very important to use pooling layers to reduce the dimensionality of the final convolutional layer output. Pooling layers usually include average pooling layers and maximum pooling layers. After three convolutional layers, average pooling can be applied to the obtained features to obtain a lower dimensional representation. The calculation formula can be expressed as: Where Y = {y1, y2, ..., y m} is the sample in the pooling area, m is the number of samples in the pooling area. The final output is the average of all values ​​in the pooling area.

[0077] In step 208 , the high-dimensional biological features and global features are input into the fully connected layer of the protein language model to perform anticancer peptide prediction to obtain prediction results.

[0078] After processing by the self-attention mechanism, the generated feature vector is passed to the fully connected classification module for further processing. In this classification module, the feature vector is transformed through two fully connected layers, and finally the result is mapped to the range of 0 to 1 through the sigmoid function to perform the final binary classification task. For samples with an output probability less than 0.5, they are classified as non-anticancer peptides (non-ACP), while for samples with an output probability equal to or greater than 0.5, they are classified as anticancer peptides (ACP). The specific formula can be expressed as: The definition of the fully connected layer is: i =q i-1 W i +b i ; Among them, q i-1 is the input data of the i-th layer, q i is the output data of this layer, q i is the weight matrix of this layer, b i is the bias term of this layer. The function is to map the input real value so that it falls within the interval of (0,1). It is usually used in the output layer of binary classification problems.

[0079] In one embodiment, a method for predicting anticancer peptides based on a protein language model is provided that may further include a model evaluation process, the specific process including: determining a model evaluation index, and performing a model evaluation on the protein language model according to the model evaluation index to obtain an evaluation result; and optimizing the protein language model based on the evaluation result.

[0080] In this embodiment, the following four commonly used indicators can be used for evaluation: sensitivity (SN), specificity (SP), accuracy (ACC), and Matthews correlation coefficient (MCC). The formulas for these indicators are described as follows:

[0081]

[0082] TP, FN, TN, and FP represent the number of true positive, false negative, true negative, and false positive samples, respectively. SN represents the proportion of true ACPs, while SP represents the proportion of non-ACP samples correctly identified by the model. MCC and ACC are used to measure the overall predictive performance of the model. These metrics are used to quantitatively assess the overall effectiveness of the prediction model. For each of the aforementioned metrics, higher values ​​indicate better model performance.

[0083] In one embodiment, a method for predicting anticancer peptides based on a protein language model can be applied to Figure 3 The model framework of ACP-ESM2 is shown.

[0084] like Figure 3 As shown in the figure, the model framework of ACP-ESM2 can include the ESM2 protein language model, convolutional neural network-self-attention mechanism, fully connected layer, and Web server. Among them, the ESM2 protein language model can perform feature extraction and extract high-dimensional biological features in the sample sequence; the convolutional neural network-self-attention mechanism can adjust the weights after performing convolution operations on high-dimensional biological features to capture global features; the fully connected layer can perform classification and prediction based on high-dimensional biological features and global features to obtain anti-cancer peptide prediction results; the Web server can visualize the prediction results for easy viewing.

[0085] In one embodiment, an experiment was conducted on a model framework of a method for predicting anticancer peptides based on a protein language model, wherein 487 sequences can be randomly selected from anticancer peptide positive samples and 1479 sequences can be randomly selected from anticancer peptide negative samples to construct a training data set. In addition, two test sets Test1 and Test2 are constructed to verify the generalization ability of the protein language model for predicting anticancer peptides ACP, and the two constructed test sets are also subjected to homology filtering and PSSM matrix extraction. Among them, the number of positive samples in Test1 is 135 and the number of negative samples is 360, which is the remaining part of the constructed anticancer peptide data set. Test2 can be composed of 99 positive samples and 157 negative samples.

[0086] The experimental results of ACP-ESM2, a model framework for predicting anticancer peptides based on a protein language model, provided in this example, were compared with those of traditional predictors on benchmark datasets. Based on the results from test sets 1 and 2, ACP-ESM2 performed exceptionally well across all metrics, demonstrating particularly strong generalization capabilities in test set 2. The ACC reached 0.976 and the MCC reached 0.950 in test set 2, demonstrating that the model not only possesses excellent classification capabilities but also excels in balancing positive and negative samples. In comparison, ACP-ML also performed relatively consistently, but slightly lacked in the MCC and SP metrics. Although MACPpred and ACPred showed some improvement on both test sets, their performance remained significantly lower than OurWork. ACP-MHCNN and ACPred-BMF performed the worst, particularly in SP and MCC, reflecting their significant shortcomings in negative sample prediction. Overall, OurWork not only achieved the best prediction performance on both test sets, but its excellent generalization capabilities, particularly in test set 2, further underscored the model's advantages. The comparison results of test set 1 and the traditional predictor, and the comparison results of test set 2 and the traditional predictor are shown in the following tables:

[0087] Table 1: Comparison with existing methods on test set 1

[0088]

[0089] Table 2: Comparison with existing methods on test set 2

[0090]

[0091] In this embodiment, an ablation experiment was also conducted on the model framework of the provided anti-cancer peptide prediction method based on a protein language model. The ablation experiment results are shown in the following table:

[0092] Table 3: Model ablation experiment on the training set

[0093]

[0094] Ablation experiments show that model performance gradually improves with the addition of components, particularly the combination of CNN and self-attention, which demonstrates significant synergy. When using ESM2 alone, the ACC is 0.916 and the MCC is 0.756. While capable of extracting basic features, it performs relatively poorly in terms of SN (0.760), indicating limited ability to identify positive samples. With the addition of CNN, the ACC and MCC of the ESM2+CNN model improve to 0.938 and 0.820, respectively, and the SN increases to 0.796, demonstrating the effectiveness of CNN in extracting local features. Further incorporating the self-attention mechanism, the ESM2+CNN+Attention model achieves improvements across all metrics, reaching ACC of 0.942 and MCC of 0.832. The model particularly performs well in terms of SP (0.982) and SN (0.810), demonstrating that the self-attention mechanism effectively enhances the model's ability to capture important information in the sequence, thereby improving overall performance. This combination enables the models to complement each other in feature extraction and information integration, further improving the accuracy of anticancer peptide identification.

[0095] Then, you can visualize the dataset before model training and the dataset after model training. Figure 4 As shown in , through feature visualization, it can be clearly seen that the data after model training is clustered into two obvious clusters, and Figure 5 As shown, the two types of untrained datasets are scattered together.

[0096] It should be understood that, although the various steps in the above flow chart are shown in sequence as indicated by the arrows, these steps are not necessarily performed in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and these steps can be performed in other orders. Moreover, at least a portion of the steps in the above flow chart may include multiple sub-steps or multiple stages, and these sub-steps or stages are not necessarily performed at the same time, but can be performed at different times, and the execution order of these sub-steps or stages is not necessarily to be performed in sequence, but can be performed in turn or alternately with other steps or at least a portion of the sub-steps or stages of other steps.

[0097] In one embodiment, Figure 6 As shown, a system for predicting anticancer peptides based on a protein language model is provided, comprising: a data set construction module 610, a high-dimensional biological feature extraction module 620, a global feature extraction module 630, and an anticancer peptide prediction module 640, wherein:

[0098] A data set construction module 610 is used to collect and screen anticancer peptide samples and non-anticancer peptide samples from a database, and to construct a data set based on the anticancer peptide samples and non-anticancer peptide samples;

[0099] The high-dimensional biological feature extraction module 620 is used to input the data set into the protein language model, perform feature processing on the sample sequences in the data set through the protein language model, and extract high-dimensional biological features from the sample sequences;

[0100] A global feature extraction module 630 is used to perform convolution operations on high-dimensional biological features using a convolutional neural network through a protein language model, and dynamically adjust the weights of the high-dimensional biological features through a self-attention mechanism to capture the global features in the peptide sequence;

[0101] The anticancer peptide prediction module 640 is used to input high-dimensional biological features and global features into the fully connected layer of the protein language model to predict anticancer peptides and obtain prediction results.

[0102] In one embodiment, the data set construction module 610 is also used to collect anti-cancer peptides from the database, and perform homology elimination on the anti-cancer peptides to obtain the eliminated anti-cancer peptides; perform PSSM matrix extraction on the eliminated anti-cancer peptides to obtain the final anti-cancer peptide sample; collect non-anti-cancer peptides from the database, and perform homology elimination on the non-anti-cancer peptides to obtain the eliminated non-anti-cancer peptides; perform PSSM matrix extraction on the eliminated non-anti-cancer peptides to obtain the final non-anti-cancer peptide sample; select anti-cancer peptide sequences from the final anti-cancer peptide sample, and select non-anti-cancer peptide sequences from the final non-anti-cancer peptide sample to form a data set.

[0103] In one embodiment, the data set construction module 610 is further used to take the final anti-cancer peptide sample as a positive sample and the final non-anti-cancer peptide sample as a negative sample; randomly select anti-cancer peptide samples from the positive samples as anti-cancer peptide sequences, and randomly select non-anti-cancer peptide samples from the negative samples as non-anti-cancer peptide sequences as a data set; and take the remaining anti-cancer peptide sequences in the positive samples and the remaining non-anti-cancer peptide sequences in the negative samples as a test set.

[0104] In one embodiment, the high-dimensional biological feature extraction module 620 is further used to input the data set into a protein language model, perform feature processing on the anti-cancer peptide sequences in the data set through the protein language model, capture the implicit patterns, long-term dependencies, and contextual information in the anti-cancer peptide sequences; and generate high-dimensional biological features in the anti-cancer peptide sequences based on the implicit patterns, long-term dependencies, and contextual information.

[0105] In one embodiment, the global feature extraction module 630 is also used to perform convolution operations on context information using a convolutional neural network through a protein language model to obtain convolved information; adjust the weights of high-dimensional biological features through a self-attention mechanism to identify long-term dependencies; and integrate global context information based on the convolved information, the weights of high-dimensional biological features, and long-term dependencies to obtain global features.

[0106] In one embodiment, the global feature extraction module 630 is also used to use a convolutional neural network to perform a nonlinear transformation on each context information to obtain the information after the nonlinear transformation; use one-dimensional convolution to perform a convolution operation on the information after the nonlinear transformation, and add batch normalization processing after each convolution layer, and obtain the convolved information through the pooling layer output.

[0107] In one embodiment, the global feature extraction module 630 is also used to perform linear transformation on high-dimensional biological features through the self-attention mechanism to obtain a transformation matrix; obtain the self-attention mechanism weight matrix and the key vector dimension of each attention head; and adjust the weight of the high-dimensional biological features based on the transformation matrix, the self-attention mechanism weight matrix, and the key vector dimension.

[0108] In one embodiment, a protein language model-based anticancer peptide prediction system is provided that also includes a model evaluation module for determining a model evaluation index, and performing a model evaluation on the protein language model according to the model evaluation index to obtain an evaluation result; and optimizing the protein language model based on the evaluation result.

[0109] In one embodiment, a computer device is provided. The computer device may be a terminal, and its internal structure diagram may be as follows: Figure 7 As shown. The computer device includes a processor, a memory, a network interface, a display screen and an input device connected via a system bus. 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 via a network connection. When the computer program is executed by the processor, a method for predicting anticancer peptides based on a protein language 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 covering the display screen, or a button, trackball or touchpad provided on the computer device housing, or an external keyboard, touchpad or mouse, etc.

[0110] Those skilled in the art will understand that Figure 7The 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 shown in the figure, or combine certain components, or have a different component arrangement.

[0111] In one embodiment, a computer device is provided, comprising 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 the method for predicting anticancer peptides based on a protein language model are implemented.

[0112] 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 the method for predicting anti-cancer peptides based on a protein language model are implemented.

[0113] Those skilled in the art will appreciate that all or part of the processes in the above-mentioned embodiments can be implemented by instructing the relevant hardware through a computer program. 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. By way of illustration and not limitation, RAM is available in various 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).

[0114] The technical features of the above embodiments can 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.

[0115] The above-described embodiments merely represent several implementation methods of the present application. While the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the present invention. It should be noted that a person skilled in the art could make various modifications and improvements without departing from the spirit of the present application, all of which fall within the scope of protection of the present application. Therefore, the scope of protection of the present patent application shall be determined by the appended claims.

Claims

1. A method for predicting anticancer peptides based on a protein language model, characterized in that: The method comprises: Collecting and screening anticancer peptide samples and non-anticancer peptide samples from a database, and constructing a data set based on the anticancer peptide samples and non-anticancer peptide samples; Inputting the data set into a protein language model, performing feature processing on sample sequences in the data set using the protein language model, and extracting high-dimensional biological features from the sample sequences, including: inputting the data set into a protein language model, performing feature processing on anticancer peptide sequences in the data set using the protein language model, capturing implicit patterns, long-term dependencies, and contextual information in the anticancer peptide sequences; and generating high-dimensional biological features in the anticancer peptide sequences based on the implicit patterns, long-term dependencies, and contextual information; The protein language model is used to convolve the high-dimensional biological features using a convolutional neural network, and the weight of the high-dimensional biological features is dynamically adjusted using a self-attention mechanism to capture global features in the peptide sequence, including: using the protein language model, a convolutional neural network is used to convolve the context information to obtain convolved information; adjusting the weight of the high-dimensional biological features using a self-attention mechanism to identify the long-term dependency; and integrating the global context information based on the convolved information, the weight of the high-dimensional biological features, and the long-term dependency to obtain a global feature; The high-dimensional biological features and global features are input into the fully connected layer of the protein language model to predict anticancer peptides to obtain prediction results.

2. The method for predicting anticancer peptides based on a protein language model according to claim 1, characterized in that: Anticancer peptide samples and non-anticancer peptide samples are collected and screened from the database, and a data set is constructed based on the anticancer peptide samples and non-anticancer peptide samples, including: Collecting anticancer peptides from a database, and performing homology elimination on the anticancer peptides to obtain eliminated anticancer peptides; Performing PSSM matrix extraction on the eliminated anticancer peptides to obtain a final anticancer peptide sample; collecting non-anti-cancer peptides from a database, and eliminating the non-anti-cancer peptides by homology to obtain eliminated non-anti-cancer peptides; Performing PSSM matrix extraction on the eliminated non-anticancer peptides to obtain a final non-anticancer peptide sample; Anti-cancer peptide sequences are selected from the final anti-cancer peptide sample, and non-anti-cancer peptide sequences are selected from the final non-anti-cancer peptide sample to form a data set.

3. The method for predicting anticancer peptides based on a protein language model according to claim 2, wherein: The method further comprises: The final anti-cancer peptide sample is used as a positive sample, and the final non-anti-cancer peptide sample is used as a negative sample; Randomly selecting anticancer peptide samples from the positive samples as anticancer peptide sequences, and randomly selecting non-anticancer peptide samples from the negative samples as non-anticancer peptide sequences as a data set; The remaining anticancer peptide sequences in the positive samples and the remaining non-anticancer peptide sequences in the negative samples are used as test sets.

4. The method for predicting anticancer peptides based on a protein language model according to claim 1, wherein: The protein language model is used to perform a convolution operation on the context information using a convolutional neural network to obtain convolved information, including: Using a convolutional neural network to perform a nonlinear transformation on each of the context information to obtain nonlinearly transformed information; One-dimensional convolution is used to perform a convolution operation on the information after the nonlinear transformation, and batch normalization processing is added after each convolution layer, and the convolved information is obtained through the output of the pooling layer.

5. The method for predicting anticancer peptides based on a protein language model according to claim 1, wherein: The weights of the high-dimensional biological features are adjusted through the self-attention mechanism, including: Performing a linear transformation on the high-dimensional biological features through a self-attention mechanism to obtain a transformation matrix; Get the self-attention mechanism weight matrix and the key vector dimensions of each attention head; The weight of the high-dimensional biological feature is adjusted based on the transformation matrix, the self-attention mechanism weight matrix, and the key vector dimension.

6. The method for predicting anticancer peptides based on a protein language model according to claim 1, wherein: The method further comprises: Determining a model evaluation index, and performing a model evaluation on the protein language model according to the model evaluation index to obtain an evaluation result; The protein language model is optimized based on the evaluation results.

7. An anticancer peptide prediction system based on a protein language model, characterized in that: The system comprises: A data set construction module is used to collect and screen anticancer peptide samples and non-anticancer peptide samples from a database, and to construct a data set based on the anticancer peptide samples and non-anticancer peptide samples; a high-dimensional biological feature extraction module, configured to input the dataset into a protein language model, perform feature processing on sample sequences in the dataset using the protein language model, and extract high-dimensional biological features from the sample sequences, comprising: inputting the dataset into a protein language model, performing feature processing on anticancer peptide sequences in the dataset using the protein language model, capturing implicit patterns, long-term dependencies, and contextual information in the anticancer peptide sequences; and generating high-dimensional biological features in the anticancer peptide sequences based on the implicit patterns, long-term dependencies, and contextual information; A global feature extraction module is configured to convolve the high-dimensional biological features using a convolutional neural network through the protein language model, and dynamically adjust the weights of the high-dimensional biological features through a self-attention mechanism to capture global features in the peptide sequence, including: convolving the context information using a convolutional neural network through the protein language model to obtain convolved information; adjusting the weights of the high-dimensional biological features through a self-attention mechanism to identify the long-term dependencies; and integrating the global context information based on the convolved information, the weights of the high-dimensional biological features, and the long-term dependencies to obtain global features. The anticancer peptide prediction module is used to input the high-dimensional biological features and global features into the fully connected layer in the protein language model to predict anticancer peptides and obtain prediction results.

8. The anticancer peptide prediction system based on protein language model according to claim 7, characterized in that: The data set construction module is also used to: collect anticancer peptides from the database, and perform homology elimination on the anticancer peptides to obtain eliminated anticancer peptides; perform PSSM matrix extraction on the eliminated anticancer peptides to obtain a final anticancer peptide sample; collect non-anticancer peptides from the database, and perform homology elimination on the non-anticancer peptides to obtain eliminated non-anticancer peptides; perform PSSM matrix extraction on the eliminated non-anticancer peptides to obtain a final non-anticancer peptide sample; select anticancer peptide sequences from the final anticancer peptide sample, and select non-anticancer peptide sequences from the final non-anticancer peptide sample to form a data set.

Images