Processing method and device for protein mutation effect and electronic equipment

Abstract

The invention relates to the cross technical field of artificial intelligence and biotechnology, and provides a protein mutation effect processing method and device and electronic equipment.The protein mutation effect processing method comprises the steps that an amino acid sequence of protein before mutation and an amino acid sequence of protein after mutation are obtained; performing feature extraction on the amino acid sequence of the protein before mutation and the amino acid sequence of the protein after mutation through a pre-trained protein language model to obtain features of the protein before mutation and features of the protein after mutation; determining protein mutation characteristics based on the characteristics of the protein before mutation and the characteristics of the protein after mutation; and inputting the protein mutation characteristics into a pre-trained first natural language model to generate text description corresponding to the protein mutation. According to the method, the interpretability of the protein mutation effect is improved by combining a protein language model and a natural language processing technology.

Description

Technical Field

[0001] The present invention relates to the interdisciplinary technical field of artificial intelligence and biotechnology, and in particular to a method, device and electronic equipment for processing protein mutation effects. Background Art

[0002] In the field of modern life sciences, proteins are basic molecules that perform functions in organisms. The study of their structure and function is crucial to understanding biological processes, disease mechanisms, and the development of new drugs. Amino acid mutations in protein sequences are an important means to study the functional diversity and evolution of proteins. With the development of bioinformatics and computational biology, the use of computational models to predict and design protein mutations has become an active research field.

[0003] Studying amino acid mutations in protein sequences is of great significance in life sciences. Protein language models have demonstrated powerful capabilities in a wide range of biological applications. However, they are insufficient in explaining protein mutations due to their architectural design and lack of supervision. Summary of the invention

[0004] The present invention provides a method, device and electronic device for processing protein mutation effects, which are used to solve the defect of insufficient explanation of protein mutation in the prior art. By combining protein language model and natural language processing technology, the interpretability of protein mutation effects is improved.

[0005] The present invention provides a method for processing protein mutation effects, comprising: obtaining an amino acid sequence of a protein before mutation and an amino acid sequence of the protein after mutation; extracting features of the amino acid sequence of the protein before mutation and the amino acid sequence of the protein after mutation using a pre-trained protein language model to obtain features of the protein before mutation and features of the protein after mutation; determining protein mutation features based on the features of the protein before mutation and the features of the protein after mutation; and inputting the protein mutation features into a pre-trained first natural language model to generate a text description corresponding to the protein mutation.

[0006] According to the method for processing protein mutation effects provided by the present invention, the protein mutation characteristics are determined based on the characteristics of the protein before mutation and the characteristics of the protein after mutation, including: determining the characteristic difference between the characteristics of the protein before mutation and the characteristics of the protein after mutation; encoding the characteristic difference based on the encoder branch of the protein mutation network of the pre-trained encoder-decoder architecture to obtain the protein mutation characteristics.

[0007] According to the method for processing protein mutation effects provided by the present invention, the encoder of the protein mutation network uses a cross-attention mechanism to map the feature difference into a number of fixed-length mutation features.

[0008] According to the method for processing protein mutation effects provided by the present invention, the decoder of the protein mutation network adopts a cross-attention mechanism symmetrical to the encoder to map the mutation features to the difference of the features before encoding.

[0009] According to the method for processing protein mutation effects provided by the present invention, the decoder branch of the protein mutation network also includes a mutation position prediction head and a mutation amino acid prediction head, the mutation position prediction head is used to predict the position of the mutation, and the mutation amino acid prediction head is used to predict the mutated amino acid, and the inputs of the mutation position prediction head and the mutation amino acid prediction head are the characteristics of the post-mutation protein calculated based on the difference between the pre-encoding characteristics obtained by the decoder mapping and the characteristics of the pre-mutation protein.

[0010] According to the method for processing protein mutation effects provided by the present invention, the protein mutation network is jointly trained with the first natural language model and the second natural language model used to map text descriptions to mutation features, and the mutation features are obtained by inputting virtual words into the second natural language model. The joint training includes a pre-training stage. In the pre-training stage, sample protein amino acid sequences and sample documents are accepted as inputs, and training is performed through a conditionally controlled next word prediction task and a conditionally controlled mask prediction task, respectively, to achieve preliminary alignment of text modality and protein sequence modality.

[0011] According to the method for processing protein mutation effects provided by the present invention, the joint training also includes a fine-tuning stage, which adopts a two-round dialogue thinking chain form. The first round of dialogue requires the model to predict its function based on the protein before mutation, and the second round of dialogue requires the model to integrate the results of the previous round of dialogue, predict the mutation effect based on the mutation characteristics, or predict the location and content of the mutation based on the mutation effect description.

[0012] According to the method for processing protein mutation effects provided by the present invention, the sample protein amino acid sequence and the sample literature are derived from a pre-established sample data set, and the steps of processing data in the sample data set include: obtaining a mutation record of the protein from a pre-established protein knowledge database, the mutation record including a description of the mutation effect written by an expert; performing a search based on reference information associated with the mutation record to obtain an abstract of the publication associated with the mutation record; processing the abstract of the retrieved publication based on a large language model to obtain an enriched description of the mutation effect; balancing the sample data set by constructing reverse samples for benign and malignant mutations; and removing low-quality descriptions in the description of the sample data set through a large language model.

[0013] According to the method for processing protein mutation effects provided by the present invention, the method also includes: obtaining text instructions corresponding to the mutation; inputting the text instructions into a pre-trained second natural language model to generate mutation characteristics of the protein; extracting features of the amino acid sequence of the protein before mutation through the pre-trained protein language model to obtain features of the protein before mutation; obtaining features of the protein after mutation based on the mutation features of the protein generated by the second natural language model and the features of the protein before mutation; and restoring the amino acid sequence of the protein after mutation based on the features of the protein after mutation.

[0014] The present invention also provides a device for processing protein mutation effects, comprising: an acquisition module, configured to acquire the amino acid sequence of the protein before mutation and the amino acid sequence of the protein after mutation; an extraction module, configured to perform feature extraction on the amino acid sequence of the protein before mutation and the amino acid sequence of the protein after mutation through a pre-trained protein language model to obtain features of the protein before mutation and features of the protein after mutation; a determination module, configured to determine protein mutation features based on the features of the protein before mutation and the features of the protein after mutation; and a generation module, configured to input the protein mutation features into a pre-trained first natural language model to generate a text description corresponding to the protein mutation.

[0015] The present invention also provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the method for processing the protein mutation effect as described above is implemented.

[0016] The present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements any of the above-described methods for processing protein mutation effects.

[0017] The present invention also provides a computer program product, comprising a computer program, wherein when the computer program is executed by a processor, the method for processing the protein mutation effect as described in any one of the above is implemented.

[0018] The protein mutation effect processing method, device and electronic device provided by the present invention improve the interpretability of protein mutation effects by combining protein language model and natural language processing technology. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0020] Figure 1 It is a schematic flow chart of the method for processing protein mutation effects provided by the present invention.

[0021] Figure 2 It is a schematic diagram of the data processing flow of the protein mutation network provided by the present invention.

[0022] Figure 3 It is a schematic diagram of the joint training process of the protein mutation network provided by the present invention.

[0023] Figure 4 It is a schematic diagram of the structure of the device for processing protein mutation effects provided by the present invention.

[0024] Figure 5 It is a structural schematic diagram of the electronic device provided by the present invention. DETAILED DESCRIPTION

[0025] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be clearly and completely described below in conjunction with the drawings 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.

[0026] Unless otherwise defined, the technical terms or scientific terms used in the present invention should be understood by people with ordinary skills in the field to which the present invention belongs. The words "first", "second" and similar words used in the present invention do not indicate any order, quantity or importance, but are only used to distinguish different components. Similarly, words such as "one", "one" or "the" do not indicate a quantitative limitation, but indicate the existence of at least one. Words such as "include" or "comprise" mean that the elements or objects appearing before the word include the elements or objects listed after the word and their equivalents, without excluding other elements or objects. Words such as "connect" or "connected" are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect.

[0027] The following is a brief explanation of the terms involved in the present invention.

[0028] Combine the following Figure 1-Figure 5 The method, device and electronic device for processing the protein mutation effect of the present invention are described.

[0029] Figure 1 It is a schematic diagram of the process of the method for processing the protein mutation effect provided by the present invention, such as Figure 1 As shown, the method includes the following: Step 101: Obtain the amino acid sequence of the protein before mutation and the amino acid sequence of the protein after mutation.

[0030] In this embodiment, the protein before mutation may include a wild-type protein, which is a protein existing in nature.

[0031] Step 102: Using a pre-trained protein language model, extract features from the amino acid sequence of the protein before mutation and the amino acid sequence of the protein after mutation to obtain features of the protein before mutation and features of the protein after mutation.

[0032] In this embodiment, the protein language model (PLM) is a type of computational model specifically used to process and analyze protein sequences. These models can capture the complex relationships and patterns between amino acids by learning a large amount of protein sequence data, and are thus used for various tasks, such as protein structure prediction, functional annotation, mutation effect prediction, etc. Representative protein language models include ESM, ProteinBERT, and ProtTrans, etc. The protein language model can be pre-trained on an evolutionary scale database or other sample database.

[0033] Step 103: Determine the protein mutation characteristics based on the characteristics of the protein before mutation and the characteristics of the protein after mutation.

[0034] In this embodiment, the protein mutation characteristics can be determined based on the characteristics of the protein before mutation and the characteristics of the protein after mutation to perform differential analysis to obtain the protein mutation characteristics, or the differential analysis results can be further feature extracted or transformed by establishing a model to obtain the protein mutation characteristics.

[0035] Step 104: Input the protein mutation feature into a pre-trained first natural language model to generate a text description corresponding to the protein mutation.

[0036] In this embodiment, the first natural language model is used to characterize the correspondence between the protein mutation feature and the text description corresponding to the protein mutation. The first natural language model can be trained by the sample protein mutation feature and the text description corresponding to the sample protein mutation, or it can be initialized using an existing large language model (Large Language Model, LLM), such as BioMedGPT-LM, BERT and other models. BioMedGPT-LM is a scientific language model built through continuous pre-training on a large-scale biomedical corpus. BERT is a pre-trained language representation model that understands natural language through deep bidirectional representation.

[0037] The models for explaining the effects of protein mutations in the prior art are often designed for static protein sequences, and the explanation of the effects of protein mutations can only predict the numerical value of evolutionary fitness. In the invention, the changes introduced by mutations are modeled using protein mutation features. Combined with the pre-trained first natural language model, the invention can generate a detailed text description of protein mutations, revealing the potential effects of mutations on protein function, stability, and interactions, greatly enriching the amount of information in mutation analysis and enabling human experts to understand mutation effects more intuitively.

[0038] In some optional implementations, the protein mutation feature is determined based on the features of the protein before mutation and the features of the protein after mutation, including: determining the feature difference between the features of the protein before mutation and the features of the protein after mutation; encoding the feature difference based on the encoder branch of the protein mutation network of the pre-trained encoder-decoder architecture to obtain the protein mutation feature. The feature difference between the features of the protein before mutation and the features of the protein after mutation contains rich mutation information and is suitable for extracting mutation features. The protein mutation network of the encoder-decoder architecture can explicitly model protein mutations, deeply understand the impact of mutations on protein structure and function, and help provide a more accurate interpretation of mutation effects.

[0039] In some optional implementations, the encoder of the protein mutation network uses a cross-attention mechanism to map feature differences into several fixed-length mutation features. Figure 2 , Figure 2It is a schematic diagram of the data processing flow of the protein mutation network provided by the present invention. The encoder and decoder of the protein mutation network promote the two-way conversion between the feature difference and the protein mutation feature. In the encoder branch of the protein mutation network, given the feature difference, the encoder is expected to extract information retaining the mutation feature in a unified feature space. However, the length of protein sequences varies greatly, ranging from dozens to thousands of amino acids. Using a cross-attention module, the sequence representation can be converted into a fixed number of potential features. This module part uses K trainable features as queries and generates outputs with sequence representations as keys and values. In addition, two parallel modules can be used for encoding wild-type proteins and mutations to further enrich the interpretation of protein mutation effects.

[0040] In some optional implementations, the decoder of the protein mutation network uses a cross-attention mechanism symmetrical to the encoder to map the mutation features to the difference of the features before encoding. As an example, the feature representation of the wild-type protein can be used as a query, and the mutation features can be used as keys and values. The output can then be processed through a two-layer feedforward network (FFN) or other neural network structure to reconstruct the difference in protein features before and after mutation.

[0041] In some optional implementations, the decoder branch of the protein mutation network may also include a mutation position prediction head and a mutation amino acid prediction head, the mutation position prediction head is used to predict the position of the mutation, the mutation amino acid prediction head is used to predict the mutated amino acid, and the input of the mutation position prediction head and the mutation amino acid prediction head is the difference between the pre-encoding features obtained by the decoder mapping and the features of the protein before mutation to calculate the features of the mutated protein. The mutation position prediction head can be a fully connected layer or other neural network structure that can predict whether an amino acid should be replaced. The mutation amino acid prediction head can be initialized from a protein language model to predict the probability distribution of mutated amino acids. In order to facilitate the subsequent use of text instructions for protein engineering, K trainable virtual words are introduced, which are additionally input into the word embedding so that the large language model can summarize the text semantics. The output representation of the virtual word is processed by the decoder to generate mutations.

[0042] In addition, the prediction of mutation location and type can be integrated in the final output layer of the model, or by designing features that can indicate the possibility of mutation, these features can be directly input into the model for training instead of through an independent prediction head. It is also possible to use known biological rules and patterns, such as protein domain knowledge, known mutation hotspots, etc., to predict possible mutation locations, or to compare the target protein sequence with proteins with known mutations based on sequence comparison to predict the location and potential impact of mutations.

[0043] In some optional implementations, the protein mutation network is jointly trained with a first natural language model and a second natural language model for mapping text descriptions to mutation features. The mutation features are obtained by inputting virtual words (Soft Token) into the second natural language model. The joint training includes a pre-training stage. In the pre-training stage, sample protein amino acid sequences and sample documents are accepted as inputs, and training is performed through conditional next token prediction tasks and conditional mask prediction tasks, respectively, to achieve preliminary alignment of text modality and protein sequence modality. Virtual words are trainable parameters that are embedded in the model to help capture and represent mutation features. The first natural language model and the second natural language model constitute a forward language model and a reverse language model. The joint training process of the protein mutation network and the two natural language models aims to integrate protein knowledge and text descriptions in scientific literature to improve the understanding and prediction of protein mutations.

[0044] refer to Figure 3 , Figure 3 It is a schematic diagram of the joint training process of the protein mutation network provided by the present invention, the goal is to integrate protein knowledge from sample literature, using a bidirectional language modeling objective. For the encoding workflow, the output representation of the wild-type encoder can be used as the first natural language model input, and the next word prediction objective is calculated to generate descriptive text. For the decoding workflow, a conditional masked prediction (Conditional Masked Language Modeling) objective can be used on the protein sequence. As an example, 15% of the amino acids can be masked, and the PLM is required to recover the masked amino acids based on the remaining amino acid sequence and mutation characteristics. In general, the sum of these two language modeling objectives can be optimized.

[0045] In some optional implementations, joint training also includes a fine-tuning phase, which uses a two-round dialogue chain of thought. The first round of dialogue requires the model to predict its function based on the protein before mutation, and the second round of dialogue requires the model to integrate the results of the previous round of dialogue and predict the mutation effect based on the mutation feature, or predict the location and content of the mutation based on the description of the mutation effect. The two-round dialogue chain of thought (CoT) is an effective strategy to improve the performance of the model on specific tasks. The fine-tuning phase can further refine the model's capabilities, especially in understanding and predicting the effects of protein mutations.

[0046] like Figure 3As shown, protein evolution knowledge can be used to guide the model training process and fine-tuning can be used to promote mutation interpretation and design. Since mutation effects usually involve enhancing or weakening protein function, a chain of thoughts (CoT) strategy can be adopted to seamlessly connect protein function and mutation effect in a two-round dialogue. In the first round, the natural language model can be prompted to describe the function of the wild-type protein using an encoding workflow. In the second round, two tasks can be introduced, namely describing the effect of the mutation and predicting the mutation based on text instructions. Both tasks use the predicted function and potential wild-type representation in the first round of dialogue as additional input. Specifically, the overall goal of fine-tuning is the sum of the following three parts: (1) next token prediction based on protein function, (2) next token prediction based on mutation effect, and (3) cross-entropy loss between the predicted position and amino acid and the true mutation.

[0047] In some optional implementations, the sample protein amino acid sequence and sample literature are derived from a pre-established sample data set, and the steps of processing the data in the sample data set include: obtaining a mutation record of the protein from a pre-established protein knowledge database, the mutation record including an expert-written description of the mutation effect; searching based on the reference information associated with the mutation record to obtain the abstract of the publication associated with the mutation record; processing the abstract of the retrieved publication based on a large language model to obtain an enriched description of the mutation effect; balancing the sample data set by constructing reverse samples for benign and malignant mutations; and removing low-quality descriptions from the description of the sample data set through a large language model. The protein knowledge database can be established based on an existing database, such as the Universal Protein Knowledge Database (Universal Protein Knowledge Database, UniProtKB), which is a widely used protein database containing 107,000 single-point mutations. The descriptions written by experts of the mutation effect can be collected from the database, and the abstracts of the corresponding publications can be retrieved based on the available reference information. The abstracts of the publications can be retrieved from literature retrieval platforms such as PubMed and Web of Science. Given that descriptions in UniProtKB are usually short and homogeneous, large language models such as GPT-3.5-turbo can be used to retrieve relevant descriptions from the original PubMed abstracts to enrich text annotations. GPT-3.5-turbo is an advanced natural language processing (NLP) model developed by the artificial intelligence research laboratory OpenAI. It is one of the subsequent versions of the GPT-3 (third generation generative pre-trained Transformer) series of models, designed to provide more efficient and faster text generation capabilities.

[0048] In addition, the dataset can be balanced by constructing reverse samples for benign and malignant mutations. Specifically, for each protein mutation, you can try to create another reverse data sample by swapping the wild type and mutant and prompting GPT-3.5-turbo to write a description that is opposite to the original mutation effect. You can also prompt GPT-3.5-turbo to filter out low-quality descriptions, such as those that only mention the original species. This step helps ensure that the dataset contains high-quality and informative annotations. Finally, you can also split the dataset into training, validation, and test sets.

[0049] In some optional implementations, the method also includes: obtaining text instructions corresponding to the mutation; inputting the text instructions into a pre-trained second natural language model to generate mutation characteristics of the protein; extracting features of the amino acid sequence of the protein before mutation through the pre-trained protein language model to obtain features of the protein before mutation; obtaining features of the protein after mutation based on the mutation features of the protein generated by the second natural language model and the features of the protein before mutation; and restoring the amino acid sequence of the protein after mutation based on the features of the protein after mutation.

[0050] Obtaining the features of the mutated protein based on the protein mutation features and the features of the protein before mutation may include: decoding the protein mutation features based on a decoder branch of a protein mutation network of a pre-trained encoder-decoder architecture to obtain a feature difference between the features of the protein before mutation and the features of the protein after mutation. Obtaining the features of the mutated protein based on the feature difference and the features of the protein before mutation.

[0051] In the prior art, in terms of mutation design, protein language models can only propose evolutionarily plausible mutations, which may be inconsistent with human preferences for directed evolution in the real world. For example, enhancing the catalytic activity of an enzyme from bacteria may be detrimental to its survival due to its increased energy cost of survival, but beneficial for industrial applications. In this case, the utility of protein language models in assisting protein engineering is greatly impaired.

[0052] In this implementation, natural language is used to explicitly model protein mutations, which effectively improves the customizability of mutation design and improves the user experience of researchers.

[0053] The device for processing protein mutation effects provided by the present invention is described below. The device for processing protein mutation effects described below and the method for processing protein mutation effects described above can be referenced to each other.

[0054] Figure 4 A schematic diagram of the structure of a device for processing protein mutation effects provided in an embodiment of the present application, such as Figure 4As shown, it specifically includes: an acquisition module 401, which is configured to acquire the amino acid sequence of the protein before mutation and the amino acid sequence of the protein after mutation; an extraction module 402, which is configured to extract features of the amino acid sequence of the protein before mutation and the amino acid sequence of the protein after mutation through a pre-trained protein language model to obtain features of the protein before mutation and features of the protein after mutation; a determination module 403, which is configured to determine protein mutation features based on the features of the protein before mutation and the features of the protein after mutation; a generation module 404, which is configured to input the protein mutation features into a pre-trained first natural language model to generate a text description corresponding to the protein mutation.

[0055] In some optional implementations, the determination module 404 is further configured to: determine the feature difference between the feature of the protein before mutation and the feature of the protein after mutation; encode the feature difference based on the encoder branch of the protein mutation network of the pre-trained encoder-decoder architecture to obtain the protein mutation feature.

[0056] In some optional implementations, the encoder of the protein mutation network uses a cross-attention mechanism to map feature differences into several fixed-length mutation features.

[0057] In some optional implementations, the decoder of the protein mutation network obtains mutation features by adding virtual words, and uses a cross-attention mechanism symmetrical to the encoder to map the mutation features to the difference of the features before encoding.

[0058] In some optional implementations, the decoder branch of the protein mutation network also includes a mutation position prediction head and a mutation amino acid prediction head. The mutation position prediction head is used to predict the position of the mutation, and the mutation amino acid prediction head is used to predict the mutated amino acid. The input of the mutation position prediction head and the mutation amino acid prediction head is the feature of the protein after mutation, which is calculated based on the difference between the pre-encoding feature obtained by the decoder mapping and the feature of the protein before mutation.

[0059] In some optional implementations, the protein mutation network is jointly trained with a first natural language model and a second natural language model for mapping text descriptions to mutation features. The joint training includes a pre-training stage. In the pre-training stage, sample protein amino acid sequences and sample documents are accepted as input and trained through a conditionally controlled next word prediction task and a conditionally controlled mask prediction task, respectively, to achieve preliminary alignment of text modality and protein sequence modality.

[0060] In some optional implementations, the joint training also includes a fine-tuning phase, which adopts a two-round dialogue chain form. The first round of dialogue requires the model to predict the function of the protein based on the pre-mutation protein, and the second round of dialogue requires the model to integrate the results of the previous round of dialogue and predict the mutation effect based on the mutation characteristics, or predict the location and content of the mutation based on the mutation effect description.

[0061] In some optional implementations, the sample protein amino acid sequence and the sample literature are derived from a pre-established sample data set, and the steps of processing the data in the sample data set include: obtaining a mutation record of the protein from a pre-established protein knowledge database, the mutation record including an expert-written description of the mutation effect; searching based on reference information associated with the mutation record to obtain an abstract of the publication associated with the mutation record; processing the abstracts of the retrieved publications based on a large language model to obtain an enriched description of the mutation effect; balancing the sample data set by constructing reverse samples for benign and malignant mutations; and removing low-quality descriptions in the description of the sample data set through a large language model.

[0062] In some optional implementations, the device also includes a mutation design module, which is configured to: obtain text instructions corresponding to the mutation; input the text instructions into a pre-trained second natural language model to generate a mutation feature of the protein; extract features of the amino acid sequence of the protein before mutation through the pre-trained protein language model to obtain features of the protein before mutation; obtain features of the protein after mutation based on the mutation features of the protein generated by the second natural language model and the features of the protein before mutation; and restore the amino acid sequence of the protein after mutation based on the features of the protein after mutation.

[0063] The protein mutation effect processing device provided by the present invention improves the interpretability of the protein mutation effect by combining a protein language model and a natural language processing technology.

[0064] Figure 5 An example of a physical structure diagram of an electronic device is shown in FIG. Figure 5As shown, the electronic device may include: a processor 510, a communication interface 520, a memory 530 and a communication bus 540, wherein the processor 510, the communication interface 520 and the memory 530 communicate with each other through the communication bus 540. The processor 510 may call the logic instructions in the memory 530 to execute the method for processing the protein mutation effect, the method comprising: obtaining the amino acid sequence of the protein before mutation and the amino acid sequence of the protein after mutation; extracting the features of the amino acid sequence of the protein before mutation and the amino acid sequence of the protein after mutation through a pre-trained protein language model to obtain the features of the protein before mutation and the features of the protein after mutation; determining the protein mutation features based on the features of the protein before mutation and the features of the protein after mutation; inputting the protein mutation features into the pre-trained first natural language model to generate a text description corresponding to the protein mutation.

[0065] In addition, the logic instructions in the above-mentioned memory 530 can be implemented in the form of a software functional unit and can be stored in a computer-readable storage medium when it is sold or used as an independent product. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc. Various media that can store program codes.

[0066] On the other hand, the present invention also provides a computer program product, which includes a computer program, and the computer program can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer can execute the protein mutation effect processing method provided by the above-mentioned methods, and the method includes: obtaining the amino acid sequence of the protein before mutation and the amino acid sequence of the protein after mutation; using a pre-trained protein language model, extracting features of the amino acid sequence of the protein before mutation and the amino acid sequence of the protein after mutation to obtain features of the protein before mutation and features of the protein after mutation; determining protein mutation features based on the features of the protein before mutation and the features of the protein after mutation; inputting the protein mutation features into a pre-trained first natural language model to generate a text description corresponding to the protein mutation.

[0067] On the other hand, the present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, is implemented to execute the protein mutation effect processing method provided by the above-mentioned methods, the method comprising: obtaining the amino acid sequence of the protein before mutation and the amino acid sequence of the protein after mutation; extracting features of the amino acid sequence of the protein before mutation and the amino acid sequence of the protein after mutation through a pre-trained protein language model to obtain features of the protein before mutation and features of the protein after mutation; determining protein mutation features based on the features of the protein before mutation and the features of the protein after mutation; inputting the protein mutation features into a pre-trained first natural language model to generate a text description corresponding to the protein mutation.

[0068] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative labor.

[0069] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0070] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. 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. A method for processing protein mutation effects, characterized in that: include: Obtaining the amino acid sequence of the protein before mutation and the amino acid sequence of the protein after mutation; Using a pre-trained protein language model, feature extraction is performed on the amino acid sequence of the protein before mutation and the amino acid sequence of the protein after mutation to obtain features of the protein before mutation and features of the protein after mutation; Determining protein mutation characteristics based on the characteristics of the protein before mutation and the characteristics of the protein after mutation; The protein mutation feature is input into a pre-trained first natural language model to generate a text description corresponding to the protein mutation.

2. The method for treating protein mutation effects according to claim 1, characterized in that: The determining of the protein mutation feature based on the feature of the protein before mutation and the feature of the protein after mutation comprises: Determine a characteristic difference between a characteristic of the protein before the mutation and a characteristic of the protein after the mutation; The encoder branch of the protein mutation network based on the pre-trained encoder-decoder architecture encodes the feature difference to obtain the protein mutation feature.

3. The method for processing protein mutation effects according to claim 2, characterized in that: The encoder of the protein mutation network uses a cross-attention mechanism to map the feature difference into several fixed-length mutation features.

4. The method for treating protein mutation effects according to claim 3, characterized in that: The decoder of the protein mutation network uses a cross-attention mechanism symmetrical to the encoder to map the mutation features to the difference of the features before encoding.

5. The method for treating protein mutation effects according to claim 4, characterized in that: The decoder branch of the protein mutation network also includes a mutation position prediction head and a mutation amino acid prediction head, wherein the mutation position prediction head is used to predict the mutation position, and the mutation amino acid prediction head is used to predict the mutated amino acid, and the inputs of the mutation position prediction head and the mutation amino acid prediction head are the characteristics of the mutated protein calculated based on the difference between the pre-encoding characteristics obtained by the decoder mapping and the characteristics of the pre-mutation protein.

6. The method for treating protein mutation effects according to claim 2, characterized in that: The protein mutation network is jointly trained with the first natural language model and a second natural language model for mapping text descriptions into mutation features. Mutation features are obtained by inputting virtual words into the second natural language model. The joint training includes a pre-training stage. In the pre-training stage, sample protein amino acid sequences and sample documents are accepted as inputs, and training is performed through a conditionally controlled next word prediction task and a conditionally controlled mask prediction task, respectively, to achieve preliminary alignment of text modality and protein sequence modality.

7. The method for treating protein mutation effects according to claim 6, characterized in that: The joint training also includes a fine-tuning stage, which adopts a two-round dialogue chain form. The first round of dialogue requires the model to predict the function of the protein based on the pre-mutation protein, and the second round of dialogue requires the model to integrate the results of the previous round of dialogue and predict the mutation effect based on the mutation characteristics, or predict the location and content of the mutation based on the mutation effect description.

8. The method for treating protein mutation effects according to claim 4, characterized in that: The sample protein amino acid sequence and the sample document are derived from a pre-established sample data set, and the steps of processing the data in the sample data set include: Obtaining a mutation record of a protein from a pre-established protein knowledge database, wherein the mutation record includes an expert-written description of the effect of the mutation; Searching according to the reference information associated with the mutation record to obtain the abstract of the publication associated with the mutation record; Processing the abstracts of retrieved publications based on a large language model to obtain enriched descriptions of mutation effects; The sample dataset was balanced by constructing reverse samples for benign and malignant mutations; Use a large language model to remove low-quality descriptions from the descriptions of the sample dataset.

9. The method for treating protein mutation effects according to claim 1, characterized in that: The method further comprises: Get the text instructions corresponding to the mutation; Inputting the text instruction into a pre-trained second natural language model to generate a mutation signature of the protein; The features of the protein before mutation are obtained by extracting features from the amino acid sequence of the protein before mutation through the pre-trained protein language model; Obtaining features of the protein after mutation according to the mutation features of the protein generated by the second natural language model and features of the protein before mutation; The amino acid sequence of the mutated protein is restored based on the characteristics of the mutated protein.

10. A device for processing protein mutation effects, characterized in that: include: An acquisition module is configured to acquire an amino acid sequence of the protein before mutation and an amino acid sequence of the protein after mutation; An extraction module is configured to extract features of the amino acid sequence of the protein before mutation and the amino acid sequence of the protein after mutation by using a pre-trained protein language model to obtain features of the protein before mutation and features of the protein after mutation; A determination module, configured to determine a protein mutation feature based on the feature of the protein before mutation and the feature of the protein after mutation; The generation module is configured to input the protein mutation feature into a pre-trained first natural language model to generate a text description corresponding to the protein mutation.

Images