Target determination method and device, computer device, and computer program

A computer-assisted method for protein-directed evolution accelerates the process by predicting index values and selecting target objects, addressing the inefficiencies of traditional techniques.

JP2024544637AActive Publication Date: 2024-12-03TENCENT TECHNOLOGY (SHENZHEN) CO LTD
View PDF 6 Cites 0 Cited by

Patent Information

Application Number
JP2024532391
Authority / Receiving Office
JP · JP
Patent Type
Applications
Current Assignee / Owner
Priority Date
2022-05-09
Filing Date
2023-03-29
Publication Date
2024-12-03
Estimated Expiration
2043-03-29

AI Technical Summary

Technical Problem

Traditional protein-directed evolution techniques are labor-intensive and time-consuming, requiring multiple cycles of mutation, recombination, and screening to achieve desired protein properties.

Method used

A method and apparatus utilizing a computer-based approach to predict index values, screen objects, determine mapping relationships, and select target objects that satisfy predetermined index requirements, thereby accelerating the protein-directed evolution process.

Benefits of technology

Reduces the time and cost of determining target proteins by efficiently identifying objects that meet specific index requirements, enhancing the speed and efficiency of protein evolution.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure 2024544637000001_ABST
    Figure 2024544637000001_ABST
Patent Text Reader

Abstract

The present application relates to the technical field of artificial intelligence, in particular to a method and apparatus for determining an object, and a computer device and program. The method includes the steps of: obtaining an index predicted value for each predetermined index of each object in a first object set (202); screening an object whose index predicted value satisfies an index value screening condition from the first object set to obtain a second object set (204); determining a mapping relationship between the predetermined index and the object features based on the index experimental values ​​for the predetermined index of a plurality of objects in the first object set and the object features (206); and determining a target object that meets the index requirements of the predetermined index from the second object set based on the mapping relationship (208).
Need to check novelty before this filing date? Find Prior Art

Description

[Technical field]

[0001] This application claims priority from a Chinese patent application bearing application number 202210498684.7 and entitled "Object Determination Method, Apparatus, Computer Device, and Storage Medium" filed with the China Patent Office on May 9, 2022, the entire contents of which are incorporated herein by reference.

[0002] The present application relates to the field of computer technology, and in particular to a target determination method and apparatus, a computer device and a computer program. [Background technology]

[0003] With the development of computer technology, directed evolution technology has emerged. Directed evolution can obtain proteins with new functions and properties in a relatively short period of time. By setting clear goals, molecules can be redesigned. Directed evolution has already become an important research tool in fields such as drug development and chemical engineering.

[0004] Traditional protein directed evolution involves establishing an initial protein for a target function, constructing a mutant library at one or more positions, determining the most common mutants by screening, randomly recombining and screening these mutants, and using the screened mutants for another round of "mutation, recombination and screening" cycles (loops), and so on, until the desired protein properties are reached.

[0005] However, to date, most directed evolution techniques are labor-intensive and time-consuming, resulting in high time costs. Summary of the Invention [Problem to be solved by the invention]

[0006] The embodiments provided in the present application aim to provide a target determination method and apparatus, a computer device, and a computer program. [Means for solving the problem]

[0007] According to one aspect, the present application provides a method for determining an object, the method being implemented by a computer device, the method comprising: obtaining an index prediction value for each predetermined index for each subject in the first subject set, the index prediction value being a value for the predetermined index for the subject predicted by a pre-trained model; Screening objects from the first object set whose index prediction values ​​satisfy an index value screening condition to obtain a second object set; Determine a mapping relationship between the predetermined index and the object features based on index experimental values ​​and object features of a plurality of objects in the first object set, where the index experimental values ​​refer to values ​​of the objects for the predetermined index obtained by experiment; and Determining target objects from the second object set that satisfy index requirements of the predetermined index based on the mapping relationship.

[0008] According to another aspect, the present application further provides an object determination apparatus, the apparatus comprising: a prediction value obtaining module for obtaining an index prediction value for each predetermined index of each subject in the first subject set, the index prediction value being a value for the predetermined index of a subject predicted by a pre-trained model; an object set obtaining module for screening objects whose index prediction values ​​satisfy an index value screening condition from the first object set to obtain a second object set; a mapping relationship determination module for determining a mapping relationship between a predetermined index and an object feature based on an index experimental value for the predetermined index and an object feature of a plurality of objects in the first object set, wherein the index experimental value refers to an object value for the predetermined index obtained by an experiment; and A target object determining module is configured to determine a target object from the second object set that satisfies an index requirement of the predetermined index based on the mapping relationship.

[0009] According to another aspect, the present application further provides a computing device, the computing device including a storage device and one or more processors, the storage device storing computer readable instructions which, when executed by the processors, cause the one or more processors to perform steps in the target determination method described above.

[0010] According to another aspect, the present application further provides one or more non-volatile readable storage media having computer readable instructions stored thereon that, when executed by one or more processors, cause the one or more processors to perform steps in the target determination method described above.

[0011] According to another aspect, the present application further provides a computer program product (computer program), the computer program product including computer readable instructions which, when executed by a processor, implement the steps of the target determination method described above.

[0012] The details of one or more embodiments of the application are set forth in the drawings and description which follow. Other features, objects, and advantages of the application will become apparent from the description, drawings, and claims. [Brief description of the drawings]

[0013] In order to more clearly describe the technical solutions in the embodiments of the present application, the following will briefly introduce the drawings that need to be used in the description of the embodiments. It is obvious that the drawings described below are only some embodiments of the present application, and those skilled in the art can obtain other drawings based on these drawings without creative work. [Figure 1] FIG. 1 illustrates an application environment for a target determination method in some embodiments. [Diagram 2] 1 is a flow chart of a method for targeting in some embodiments. [Figure 3A] FIG. 1 illustrates the application of enzymes in some examples. [Figure 3B] FIG. 1 illustrates the principle of machine learning assisted directed evolution in some embodiments. [Figure 4] FIG. 1 shows the average fitness of amino acids in some examples. [Diagram 5] 1 is a flow chart of a method for targeting in some embodiments. [Figure 6] FIG. 1 illustrates the principle of the targeting method in some embodiments. [Figure 7] FIG. 1 illustrates the principle of the targeting method in some embodiments. [Figure 8] FIG. 1 illustrates an application environment for a target determination method in some embodiments. [Figure 9] FIG. 1 illustrates an application environment for a target determination method in some embodiments. [Figure 10] FIG. 1 illustrates fitness distributions for different datasets in some embodiments. [Figure 11] FIG. 1 shows the effect of different methods in some embodiments on four protein directed evolution data sets. [Figure 12] FIG. 13 illustrates the effect of different methods on a data set in some embodiments. [Figure 13] FIG. 2 is a block diagram illustrating a configuration of an object determination device according to some embodiments. [Figure 14] FIG. 2 illustrates the internal configuration of a computing device according to some embodiments. [Figure 15] FIG. 2 illustrates the internal configuration of a computing device according to some embodiments. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0014] In order to make the purpose, technical solution and advantages of the present application clearer, the present application will be described in more detail below in conjunction with the drawings and examples. It can be understood that the specific examples described herein are only for the purpose of interpreting the present application, and do not limit the present application.

[0015] The object determination method provided in the embodiment of the present application can be used in an application environment as shown in Fig. 1. Wherein, a terminal 102 communicates with a server 104 through a network. A data storage system can store data that the server 104 needs to process. The data storage system can be integrated into the server 104 or can be located in the cloud or another server.

[0016] Specifically, the server 104 can obtain index prediction values ​​for each predetermined index of each object in the first object set, screen objects whose index prediction values ​​satisfy index value screening conditions from the first object set, obtain a second object set, and determine a mapping relationship between the predetermined indexes and the object features based on the index experimental values ​​for the predetermined indexes of the multiple objects in the first object set and the object features, and then determine target objects that satisfy the index requirements of the predetermined indexes from the second object set based on the mapping relationship. After determining the target objects, the server 104 can store the target objects, and further send the target objects to the terminal 102, and the terminal 102 can display related information of the target objects.

[0017] Wherein, the terminal 102 may be, but is not limited to, various desktop computers, laptops, smartphones, tablet computers, IoT devices, and portable wearable devices, and the IoT devices may be smart speakers, smart TVs, smart air conditioners, intelligent vehicle-mounted devices, etc. The portable wearable devices may be smart watches, smart bracelets, head-mounted devices, etc. The server 104 may be an independent server or a server group consisting of multiple servers.

[0018] In some embodiments, the indicator prediction value may be predicted by a trained indicator detection model, which may be based on artificial intelligence and machine learning, for example, a neural network model.

[0019] The scheme (technical solution) provided in the embodiments of the present application relates to technologies such as artificial intelligence neural networks, and is specifically illustrated by the following embodiments.

[0020] In some embodiments, a target determination method is provided, which may be executed by a terminal or a server, or may be executed jointly by a terminal and a server, as shown in Fig. 2. The method is described by taking the server 104 in Fig. 1 as an example, and specifically includes the following steps:

[0021] Step 202: Obtain index prediction values ​​for each predetermined index for each subject in the first subject set.

[0022] Wherein, the first object set includes a plurality of objects. The objects may be real substances, including but not limited to at least one of proteins, materials, batteries, etc. The objects may also be abstract concrete concepts, for example, the object may be a fast charging protocol for a battery.

[0023] An object may have a number of corresponding indices, and a given index may be any one of the number of indices of the object, for example, if the object is a protein, the index of the object may include at least one of, but is not limited to, fitness, enrichment score, activity, brightness, etc., if the object is a material, the index of the object may include at least one of, but is not limited to, material composition or composition ratio, etc., if the object is a fast charging protocol for a battery, the index of the object may include, but is not limited to, each parameter in the fast charging protocol for a battery.

[0024] The index predicted value is a value corresponding to the predetermined index predicted for the object. The index predetermined value is a value of the object corresponding to the predetermined index predicted by a pre-trained model, which is capable of predicting the value of the object corresponding to the predetermined index. The index predicted value can be predicted by a trained index detection model. The index detection model can be a neural network model.

[0025] Each object in the first object set may belong to an object category, which may include at least one of substances such as proteins or materials, but is not limited thereto, and may further include abstract concepts such as battery charging protocols. For example, each object in the first object set may belong to a certain type of protein, for example, each object is a mutant protein obtained after mutating the same type of protein. Among them, the mutant protein is for a wild-type protein, and the wild-type protein is a protein that has never been mutated, and the mutant protein is a protein obtained after mutation is added to the wild-type protein. Protein-directed evolution can obtain a required protein by mutation. Protein-directed evolution includes two mutation scenarios, one is a k-site saturation mutagenesis scenario and the other is a non-saturation mutagenesis scenario.

[0026] The k-site saturation mutagenesis scenario is used to mutate amino acids at k designated (predetermined) mutation sites, and in the mutant protein generated by the scenario, an amino acid at at least one of the k designated mutation sites is obtained after mutation. For example, when k=4, an amino acid at at least one of the four designated mutation sites in the mutant protein obtained is obtained by mutation. That is, the positions and number of mutation sites in the k-site saturation mutagenesis scenario are fixed, and mutations can only occur at the k designated mutation sites. A mutation site refers to a position in a protein where a mutation can occur. Thus, a mutation site may also be referred to as a mutation position, and there is one amino acid at each position in a protein.

[0027] In the non-saturation mutagenesis scenario, the mutation sites are not fixed, but the number of amino acids at which mutations occur is fixed. For example, if each mutant protein obtained in the non-saturation mutagenesis scenario has two amino acids at positions obtained by mutation, the positions at which the mutations occur may be the same or different, for example, one mutation occurs at positions 1 and 2, and the other mutation occurs at positions 3 and 4.

[0028] When the object category is proteins, each object in the first object set may be a mutant protein generated in a k-site saturation mutagenesis scenario or a mutant protein generated in a non-saturation mutagenesis scenario. A mutant protein may also be referred to as a variant. A protein may be represented by an amino acid sequence. For example, if the first object set includes n mutant proteins, the first object set may be:

[0029]

number

[0030] Specifically, for each object in the first object set, the server can predict an index prediction value for a specified index for each object, and obtain an index prediction value for each object, for example, by using a trained index detection model to predict and obtain the index prediction value.

[0031] In some embodiments, the server can screen a plurality of objects from the first object set, obtain a reference object set, and determine object features of each object in the reference object set, where the object features refer to the features of the objects, and can also obtain values ​​corresponding to a predetermined index of each object in the reference object set through an experiment, and obtain an index experimental value of each object in the reference object set, where the index experimental value refers to the value of the object corresponding to the predetermined index obtained through an experiment, that is, the index experimental value of the object is the true value of the predetermined index of the object. For example, if the object is a protein and the predetermined index is fitness, the index experimental value refers to the value related to the fitness of the protein obtained through an experiment. The server can train an index detection model using the object features of each object in the reference object set and the index experimental value of each object to obtain a trained index detection model, determine object features of each object in the first object set, input the object features of each object in the first object set into the trained index detection model, and use the trained index detection model to predict and obtain a corresponding index prediction value of each object in the first object set.

[0032] In some embodiments, the target is a mutant protein, the target feature is a protein feature, and the protein feature may be a feature obtained by encoding based on amino acids at mutation sites in the mutant protein. For example, amino acids can be encoded based on index experimental values ​​for a predetermined index of the mutant protein to obtain amino acid features corresponding to the amino acids, and the protein feature of the mutant protein can be obtained based on the amino acid features corresponding to the amino acids at each mutation position. For example, for a mutant protein generated in a scenario of saturation mutagenesis at a k site, the protein feature of the mutant protein can be obtained using the amino acid feature of the amino acid at the k site. For a mutant protein generated in a scenario of non-saturation mutagenesis, when mutations occur at two positions, a vector consisting of the amino acid features of the amino acids at these two positions can be determined as the protein feature of the mutant protein.

[0033] Step 204: From the first object set, objects whose index prediction values ​​satisfy the index value screening condition are screened to obtain a second object set.

[0034] Wherein, the index value screening condition includes that the index predicted value is greater than a first index threshold, the first index threshold may be preset or may be set according to needs, the second object set is a set of objects screened from the first object set, and the index predicted value of the objects in the second object set satisfies the index value screening condition.

[0035] Specifically, the server can compare the predicted index value of each object in the first object set with the first index threshold, and form a second object set from each object whose predicted index value is greater than the first index threshold. For example, if the object is a mutant protein, the predetermined index is affinity, and the first index threshold is an affinity threshold, the second object set can be formed from each object in the first object set whose affinity is greater than the affinity threshold, and the affinity threshold can be preset or set according to needs.

[0036] Step 206: Determine a mapping relationship between the predetermined index and the object feature based on the index experimental values ​​for the predetermined index of the multiple objects in the first object set and the object feature.

[0037] Wherein, the plurality of objects in the first object set may refer to each object in the above-mentioned reference object set. The mapping relationship between the predetermined index and the object feature is used to reflect the change of the value of the predetermined index with the change of the object feature, and a curve can be used to represent the mapping relationship between the predetermined index and the object feature, for example, the mapping relationship can be represented by a curve y1=f1(x), where y1 represents the predetermined index and x represents the object feature.

[0038] Specifically, after obtaining a reference object set, the server can not only use the reference object set to train an index detection model, but also use index experimental values ​​and object features for a specific index of each object in the reference object set to determine a mapping relationship between the specific index and the object features.

[0039] In some embodiments, after obtaining the index experimental value of each subject in the reference subject set, for each subject in the reference subject set, the server sets the subject's object features and index experimental value as points on a curve y1=f1(x), and uses multiple points on multiple curves to perform fitting to the obtained multiple points, thereby obtaining a curve y1=f1(x) representing the mapping relationship.

[0040] Step 208: Determine target objects that satisfy the index requirement of the predetermined index from the second object set based on the mapping relationship.

[0041] Among them, the index requirement of the specified index may be, for example, at least one of the following: the index experimental value is as large as possible, or the index experimental value is greater than a second index threshold value, and the target object is an object in the second object set that satisfies the index requirement of the specified index.

[0042] Specifically, the mapping relationship between the predetermined index and the object feature is a first mapping relationship, the server performs statistical calculation based on the first mapping relationship to obtain a second mapping relationship between the target statistical index and the object feature, determines a statistical index value for the target statistical index of each object in the second object set based on the second mapping relationship, determines a selection object from each object in the second object set based on the statistical index value of each object, and obtains an object that satisfies the index requirement of the predetermined index based on the selection object. The first mapping relationship represents a rule that the value of the predetermined index changes with the change of the object feature, and the second mapping relationship represents a rule that the value of the target statistical index changes with the change of the object feature. For example, the second mapping relationship may be represented by a curve y2=f2(x), where y2 represents the target statistical index and x represents the object feature.

[0043] There may be one or more target statistical indicators. For example, the target statistical indicators include, but are not limited to, at least one of Expected Improvement (EI), Probability of Improvement (PI), Upper Confidence Bound (UCB), or Thompson Sampling (TS), etc. The first mapping relationship may be further referred to as a probabilistic surrogate model, and the second mapping relationship may be further referred to as an acquisition function. The acquisition function is constructed according to the posterior probability distribution obtained by the probabilistic surrogate model, and the acquisition function is maximized to select the next most "potential" experimental point. The acquisition function is responsible for testing the proposed new point based on the trade-off between exploration and exploitation. Exploration refers to selecting a point as far away from the known point as possible for the next experiment, i.e., exploring the unknown area as much as possible, and exploitation refers to selecting a point as close to the known point as possible for the next experiment, i.e., mining points around the known point as much as possible.

[0044] In some embodiments, the server can determine a statistical index value for the target statistical index of each object in the second object set according to the second mapping relationship, and determine a selection object from each object in the second object set according to the statistical index value of each object, specifically, there can be one or more selection objects, and the object corresponding to the maximum statistical index value can be determined as the selection object, or the object whose statistical index value is greater than a third index threshold can be determined as the selection object, and the third index threshold can be set according to needs. The server can obtain an object that meets the index requirements of the predetermined index according to the selection object, for example, the server can determine the selection object as the object that meets the index requirements of the predetermined index.

[0045] In some embodiments, after obtaining the selection object, the server obtains the index experimental value of the selection object, compares the index experimental value of the selection object with a second index threshold, and when it is determined that the index experimental value of the selection object reaches the second index threshold, it can determine the selection object as the target object; where, after obtaining the selection object, it can determine to select the corresponding index experimental value through experiment; when it is determined that the index experimental value of the selection object does not reach the second index threshold, it adds the selection object to the reference object set, and again uses the index experimental value and the object feature for the predetermined index of each object in the reference object set to determine a first mapping relationship between the predetermined index and the object feature, so as to again determine the target object that meets the index requirement of the predetermined index from the second object set based on the first mapping relationship; in this way, it continuously loops, and when it finds the selection object whose index experimental value reaches the second index threshold, it ends the loop, and determines the selection object whose index experimental value reaches the second index threshold as the target object, or when the number of loops reaches the number of times threshold, it determines the screened selection object as the target object.

[0046] In the above-mentioned target determination method, a predicted index value for each of the targets in a first target set is obtained, and an object whose predicted index value satisfies an index value screening condition is selected from the first target set, and a second target set is obtained, and a mapping relationship between the predetermined index and the target feature is determined based on the experimental index value for the predetermined index of the multiple targets in the first target set and the target feature, and a target object that satisfies the index requirement of the predetermined index is determined from the second target set based on the mapping relationship. Since the second target set is screened from the first target set, the efficiency of determining the target object that satisfies the index requirement of the predetermined index from the second target set is higher than the efficiency of screening the target object from the first target set. Therefore, the time cost of determining the target object can be reduced.

[0047] In real design and application scenarios, for example, when an environmental scientist obtains environmental conditions by designing the placement positions of sensors, a chemist obtains new substances by designing experiments, and a pharmaceutical company fights diseases by designing new drugs, these design problems are usually considered and solved as optimization problems such as the following (only maximization problems are considered, and minimization problems can be converted into maximization problems by simply taking the negative sign):

[0048]

number

[0049] In contrast, the object determination method provided in the present application can accelerate the process of obtaining the required object and improve the efficiency, thereby reducing time costs. For example, the object determination method provided in the present application can be used in computationally assisted protein evolution to obtain the required protein. As shown in FIG. 3A, proteins play an important role in people's lives, and enzymes play an important role in human society from daily life to industry. Some of the detergents we use every day contain enzymes to promote the decomposition of oil stains, and enzymes are indispensable in processes such as fermentation and degradation in the food industry. In pharmaceuticals and fine chemicals, enzymes are environmentally friendly and efficient catalysts that have already replaced some production processes that require the involvement of heavy metals and consume a lot of energy in traditional chemistry. Enzymes also play the most important role in the generation of bioenergy. Directed evolution can obtain proteins with new functions and properties in a relatively short period of time. By artificially setting clear goals, scientists can redesign molecules, and directed evolution has already become an important research tool in fields such as new drug development and chemical engineering. Machine learning assisted directed evolution can be adopted, as shown in FIG. 3B, for example, the process of machine learning assisted directed evolution may include four steps: 1) establish an initial protein for a target function and build a mutant library at k positions; 2) train a model using existing data; 3) predict other mutants in the mutant library by the trained model; and 4) select the best mutant for experimental testing, and add it to the training set for the next round of model training. Computation assisted directed evolution can accelerate optimization and reduce the experimental burden.

[0050] In some embodiments, the objects in the first object set are mutant proteins, and the method further includes obtaining a reference object set by screening based on the first object set, where the reference object set satisfies a condition that each type of amino acid occurs at least a target number of times at each mutation position. The step of obtaining a predicted index value for each predetermined index of each object in the first object set includes training an index detection model based on the object features and the index experimental value of each object in the reference object set; and predicting the predicted index value of each object in the first object set using the trained index detection model.

[0051] Wherein, each object in the reference object set may be a mutant protein, or the reference object set may include wild-type proteins and mutant proteins. The object in the first object set is a mutant protein, and the target number of times may be preset or may be set according to needs, for example, 2 times. The mutation position is a mutation site. The reference object set satisfies the condition that each amino acid occurs at each mutation position at least the target number of times. For example, when there are 20 kinds of amino acids and the target number is 2, in each protein in the reference object set, the 20 amino acids occur at least twice at each mutation site. Take the mutant protein generated in the k-site saturation mutagenesis scenario as an example, there are 4 mutation sites, and each amino acid among the 20 kinds of amino acids appears twice at each mutation site, and 40 samples can be selected as the initial samples from the sample space. In this way, it is possible to ensure that the coverage of the coding information of the amino acids contained in the initial sample is maximized and the number of experiments required is minimized, thereby reducing the experiment cost. Wherein, the sample space may include mutant proteins and may further include wild-type proteins, the sample refers to the protein, the reference set may be constantly changing, and the initial sample refers to the initially determined reference set.

[0052] The indicator detection model is used to determine the target value corresponding to a predetermined indicator based on the target features, i.e., to determine the indicator prediction value for the predetermined indicator of the target, and the indicator detection model can be a neural network model, such as XGBOD (Improving Supervised Outlier Detection with Unsupervised Representation Learning), or of course, can be other models, but not limited thereto. Among them, the basic process of XGBOD is to adopt various unsupervised models to learn the original data to obtain the outlier score of each sample, and then use the outlier score as a new data representation form; then, merge with the original features to generate a new feature space; finally, train the XGBoost classifier in the new feature space, and regard the output as the prediction result.

[0053] Specifically, the server can obtain an index experimental value (referred to as an index experimental value corresponding to the target) for a predetermined index of each target in the reference target set, and obtain an object feature of each target in the reference target set based on the index experimental value for the predetermined index of each target in the reference target set. The server can input the object feature of the target into an index detection model waiting to be trained to make a prediction, thereby obtaining an index predicted value (referred to as an index predicted value corresponding to the target) for the predetermined index of the target, and then adjust the model parameters of the index detection model based on the difference between the index experimental value corresponding to the target and the corresponding index predicted value until the model converges, thereby obtaining a trained index detection model. The server can input the object feature of each target in the first target set into the trained index detection model to make a prediction, thereby obtaining an index predicted value corresponding to each target in the first target set.

[0054] In some embodiments, the server determines the amino acid signature of each type of amino acid based on the index experimental value of each subject in the reference subject set, and when determining the subject signature (i.e., protein signature) of the subject in the first subject set, the server can use the amino acid signature of each type of amino acid determined based on the reference subject set to determine the protein signature of the subject in the first subject set. For example, in the scenario of k-site saturation mutagenesis, the server can determine the amino acid signature at each mutation position of each type of amino acid based on the index experimental value of each subject in the reference subject set, and for the subject in the first subject set, determine each amino acid at the mutation position in the subject, and from the determined "amino acid signature at each mutation position of each type of amino acid", determine the amino acid signature corresponding to the amino acid at each mutation position in the subject, and then determine the vector consisting of each determined amino acid signature as the subject signature (i.e., protein signature).

[0055] In some embodiments, the method of obtaining the reference object set by screening based on the first object set is a sample selection strategy for determining the first sample in Bayesian optimization, which can improve the optimization efficiency and reduce the time cost of Bayesian optimization, thereby ensuring that the coverage of the coding information of the amino acids contained in the first sample is maximized and the number of required experiments is minimized, thereby reducing the experiment cost. Among them, Bayesian optimization usually adopts Gaussian process (GP) regression based on Gaussian distribution as the a priori probabilistic surrogate model. GP is flexible and extensible, and in theory, can surrogate any linear / nonlinear function. Of course, Gaussian process regression based on Student-t a priori may be adopted as the a priori probabilistic surrogate model, and robust regression (Gaussian process based on Student-t distribution) and outlier detection may be combined to divide data points into outliers and inliers, thereby eliminating the impact of outliers on model fitting. The Gaussian process based on the student-t prior can be abbreviated as "Robust GP", and the Gaussian process based on the Gaussian distribution can be abbreviated as "GP".

[0056] In this embodiment, since the reference target set satisfies the condition that "each type of amino acid appears at least the target number of times at each mutation position", the number of each amino acid in the obtained reference target set can be balanced, and thus, by training the index detection model based on the reference target set, the accuracy of the training can be improved, and therefore the accuracy of the index prediction value predicted by the trained index detection model can be improved.

[0057] In some embodiments, the step of determining a mapping relationship between the predetermined index and the target feature based on the index experimental values ​​for the predetermined index and the target feature of a plurality of objects in the first object set includes the steps of: determining the target feature of each object in the reference object set based on the index experimental values ​​for the predetermined index of each object in the reference object set; and determining the mapping relationship between the predetermined index and the target feature based on the index experimental values ​​for the predetermined index and the target feature of each object in the reference object set.

[0058] Specifically, the server can obtain the object features of each object in the reference object by performing statistical calculations on the index experimental values ​​corresponding to each object in the reference object set, where the index experimental values ​​corresponding to the object refer to the index experimental values ​​related to a predetermined index of the object, and the statistical calculations include, but are not limited to, at least one of the following calculations: average value, maximum value, or minimum value.

[0059] In some embodiments, the mapping relationship between the predetermined index and the object feature is a first mapping relationship, and the mapping relationship may be represented by a curve, for example, the first mapping relationship is represented by a curve y1=f1(x), and for each object in the reference object set, the server can set the object feature and the index experimental value of the object as a point on the curve y1=f1(x), and use multiple points on multiple curves to perform fitting to the obtained multiple points to generate a curve y1=f1(x) representing the mapping relationship.

[0060] In this embodiment, since the reference target set satisfies the condition that "each type of amino acid occurs at least the target number of times at each mutation position", each amino acid in the obtained reference target set can be balanced, so that determining the target features of each target in the reference target set based on the experimental index values ​​for a specified index of each target in the reference target set can make the range covered by the encoded information of amino acids relatively large, that is, the information range covered by the target features can be expanded.

[0061] In some embodiments, the step of obtaining a reference target set by screening based on the first target set may include the steps of: obtaining a current score set, where the current score set includes a current score corresponding to each type of amino acid; obtaining a second protein set based on the first target set, and selecting a target protein from the second protein set based on the current score set; decrementing the current scores corresponding to each amino acid at each mutation position in the target protein in the current score set, and transferring the target protein from the second protein set to the first protein set; and returning to the step of screening (selecting) a target protein from the second protein set based on the current score set if the current score set indicates that the first protein set does not satisfy the condition that "each type of amino acid occurs at least the target number of times at each mutation position", and performing such a process until the current score set indicates that the first protein set satisfies the condition that "each type of amino acid occurs at least the target number of times at each mutation position", and then determining the first protein set as the reference target set.

[0062] Wherein, the current score set includes a current score corresponding to each type of amino acid. The current score is an integer, for example, 2. The current scores corresponding to each type of amino acid may be different or the same, and each type of amino acid may correspond to one current score or to multiple current scores, for example, the same type of amino acid has a corresponding current score at different mutation positions. The current score set changes constantly. A target protein is selected from the second protein set according to the current score set, and there may be one or more target proteins.

[0063] Specifically, the server may determine the first object set as a second protein set, i.e., the objects in the second protein set match the objects in the first object set, or the server may obtain objects from the first object set other than the objects in the reference object set to form the second object set.

[0064] In some embodiments, the current score set is determined as the current protein score of each mutant protein in the second protein set, and the mutant protein corresponding to the maximum current protein score is determined as the target protein. The server can obtain a first protein sequence by sorting each mutant protein in the second protein set according to the order of the current protein score from highest to lowest, and determine the mutant protein arranged before the sorting threshold in the first protein sequence as the target protein, and the sorting threshold can be preset or can be set according to needs, for example, can be any one of the first place or second place, etc.

[0065] In some embodiments, the server can decrement the current scores corresponding to each amino acid at each mutation position in the target protein in the current score set and transfer the target protein from the second protein set to the first protein set.

[0066] For example, when the object in the first object set is a mutant protein generated in a scenario of saturation mutagenesis of k sites, the current score set includes the current scores of each type of amino acid at each type of mutation position, and taking the example of four mutation positions, the current score set can be expressed in the form of a matrix, and the current score set can further be referred to as a current score matrix, and in the matrix corresponding to the current score set, the uth row and wth column represent the current score corresponding to the uth type of amino acid at the wth mutation position, where 1≦u≦m, 1≦w≦k, m represents the number of types of amino acids, e.g., 20 types, and k represents the number of mutation positions, e.g., 4. For example, when the amino acid at the first mutation position in the mutant protein is the first type of amino acid, the corresponding current score is the score in the first row and first column of the matrix.

[0067] When the object in the first object set is a mutant protein generated in a non-saturation mutagenesis scenario, the current score set includes a current score corresponding to each type of amino acid, and the current score set may be represented by a vector, which may further be referred to as a current score vector, and the score at the uth position in the vector represents the current score of the uth type of amino acid. For example, when the amino acid at the first mutation position in the mutant protein is the first type of amino acid, the corresponding current score is the first score in the vector.

[0068] In some embodiments, when the current score set indicates that the first protein set does not satisfy the condition that "each type of amino acid occurs at least the target number of times at each mutation position", the server returns to the step of selecting a target protein from the second protein set based on the current score set, and continues this process until the current score set indicates that the first protein set satisfies the condition that "each type of amino acid occurs at least the target number of times at each mutation position", and then determines the first protein set as the reference set. Specifically, the first protein set is constantly changing, and when no protein is included in the initial first protein set, the scores in the initial current score set are all equal to the target number of times, for example, when the target number is 2, each current score in the initial current score set is equal to 2. After the target protein is determined, the target protein is transferred from the second protein set to the first protein set, and the amino acids at each mutation position in the target protein have their corresponding current scores in the current score matrix decremented by 1 each time, for example, from 2 to 1 or from 1 to 0, thereby constantly updating the current score matrix; if there is no score greater than 0 in the current score matrix, it is determined that the first protein set satisfies the condition that "each type of amino acid occurs at least the target number of times at each mutation position", and the first protein set is determined as the reference set.

[0069] In this embodiment, a second protein set is obtained based on the first target set, the target protein value is screened from the second protein set, the current score set is updated based on the target protein, and the target protein is transferred from the second protein set to the first protein set, thereby constantly selecting proteins and updating the current score. If the current score set indicates that the first protein set satisfies "the condition that each type of amino acid appears at least the target number of times at each mutation position", the first protein set is determined as the reference target set. This makes it possible to quickly select a reference target set from the first target set that satisfies the condition that each type of amino acid appears at least the target number of times at each mutation position, and reduce the number of experiments for determining the reference target set, thereby reducing the experimental costs and time costs.

[0070] In some embodiments, the step of obtaining a current score set includes the steps of obtaining an initial score set, where the initial scores corresponding to each type of amino acid in the initial score set are the target number of times; and decreasing the initial scores corresponding to each amino acid at each mutation position in the wild-type protein in the initial score set to obtain a current score set; and determining a first protein set based on the wild-type protein, where the wild-type protein is a protein without any mutations.

[0071] Wherein, the first score corresponding to each type of amino acid in the first score set is the target number of times, and when the target number is an integer, for example, 2, the first score is 2. For example, when the target in the first target set is a mutant protein generated in the scenario of saturation mutagenesis of k sites, the first score set includes the first scores on each type of mutation position of each type of amino acid, and taking the example of there being 4 mutation positions, the first obtained set is represented in the form of a matrix, and each element in the matrix can be 2, and in the matrix corresponding to the first obtained set, the uth row and wth column represent the first score corresponding to the uth type of amino acid at the wth mutation position, where 1≦u≦m and 1≦w≦k, m represents the number of types of amino acids, for example, 20 types, and k represents the number of mutation positions, for example, 4. For example, when the amino acid at the first mutation position in the mutant protein is the first type of amino acid, the corresponding first score is the first score in the first row and first column in the matrix.

[0072] When the object in the first object set is a mutant protein generated in a non-saturation mutagenesis scenario, the first score set includes a first score corresponding to each type of amino acid, the first score set is represented by a vector, and all elements in the vector may be 2, and the score at the uth position in the vector represents the first score of the uth type of amino acid. When the amino acid at the first mutation position in the mutant protein is the first type of amino acid, the corresponding first score is the first score in the vector.

[0073] Specifically, in the case of k-site saturation mutagenesis scenario, there are k mutation positions, and the server determines the amino acid corresponding to each mutation position from the wild-type protein, and gradually decreases the current score corresponding to the amino acid in the initial score set, subtracting 1 each time, to obtain the current score set. Taking the four-site saturation mutagenesis scenario as an example, when there are four mutation positions, and the amino acids corresponding to the four mutation positions in the wild-type protein are the first amino acid A1, the second amino acid A2, the third amino acid A3, and the fourth amino acid A4, respectively, the scores in the first row, first column, the second row, second column, the third row, third column, and the fourth row, fourth column in the matrix corresponding to the initial score set are each subtracted by 1, and the initial score set after subtracting 1 is determined as the current score set.

[0074] In the case of a non-saturation mutagenesis scenario, each type of mutant protein has a corresponding target number of mutation positions, the target number is, for example, 2, and the server can obtain a mutation position set by counting (statistics) the mutation positions corresponding to each of the multiple mutant proteins in the non-saturation mutagenesis scenario, the server can determine from the wild-type protein the amino acid corresponding to each mutation position in the mutation position set, the server can determine from the wild-type protein the amino acid corresponding to each mutation position in the mutation position set in the wild-type protein, and gradually reduce the current scores corresponding to each type of amino acid determined in the initial score set, subtracting 1 each time, to obtain a current score set.

[0075] In some embodiments, the server may determine a set consisting of wild-type proteins as the first protein set, ie, the initial first protein set includes one wild-type protein.

[0076] In this embodiment, the initial score set is updated based on the wild-type protein without any mutations, and the current score set is obtained, thereby accelerating the speed of score reduction, improving the efficiency of obtaining the reference target set, and reducing the time cost.

[0077] In some embodiments, the step of selecting a target protein from the second protein set based on the current score set includes the steps of: for each mutant protein in the second protein set, determining a current score from the current score set, respectively corresponding to an amino acid at each mutation position in the mutant protein; determining a current protein score for the mutant protein based on each obtained current score; and selecting and obtaining a target protein from the second protein set based on the current protein score.

[0078] Specifically, for each mutant protein in the second protein set, a current score corresponding to each amino acid at each mutation position in the mutant protein is determined from the current score set, the obtained current scores are summed, and the result of the sum is regarded as the current protein score of the mutant protein.

[0079] In some embodiments, the server can sort each mutant protein in the second protein set according to the order of the current protein score from highest to lowest to obtain a first protein sequence, and determine the mutant protein arranged before a sorting threshold in the first protein sequence as the target protein, where the sorting threshold may be preset or may be set according to needs, for example, any one of first place or second place, etc.

[0080] In this embodiment, mutant proteins whose current protein scores satisfy the condition that the score is relatively large are screened from the second protein set to obtain the target protein; the higher the current protein score, the higher the strength of the update to the current score set. This accelerates the speed at which the current score set indicates that the first protein set satisfies "the condition that each type of amino acid appears at least the target number of times at each mutation position," thereby improving the efficiency of obtaining the reference target set.

[0081] In some embodiments, each type of amino acid has a corresponding amino acid, and the scores in the current score set are uniquely labeled by the amino acid and the mutation position, and the step of determining from the current score set a current score corresponding to each amino acid at each mutation position in the mutant protein includes the steps of: for an amino acid at each mutation position, determining from the current score set a current score corresponding to the amino acid at the mutation position based on the amino acid corresponding to the amino acid and the mutation position.

[0082] Specifically, when the object in the first object set is a mutant protein generated in the scenario of saturation mutagenesis of k sites, the current score set includes the current scores of each type of amino acid at each type of mutation position, that is, the scores in the current score matrix are uniquely labeled by amino acid and mutation position, and taking the example of four mutation positions, the current score set can be expressed in the form of a matrix, and in the matrix corresponding to the current score set, the uth row and wth column represent the current score corresponding to the uth type of amino acid at the wth mutation position, where 1≦u≦m, 1≦w≦k, m represents the number of types of amino acids, e.g., 20 types, and k represents the number of mutation positions, e.g., 4. For example, when the amino acid at the first mutation position in the mutant protein is the first type of amino acid, the corresponding current score is the score in the first row and first column in the matrix.

[0083] In the case of a non-saturation mutagenesis scenario, when the current score set is a current score vector, the uth element in the current score vector is the score of the uth type of amino acid, and when the mutant protein has two mutation positions, the amino acids at the two mutation positions are the third type of amino acid and the tenth type of amino acid, respectively, and then the score corresponding to the third type of amino acid is the score of the third position in the current score vector, and the score corresponding to the tenth type of amino acid is the score of the tenth position in the current score vector.

[0084] In some embodiments, in the case of a k-site saturation mutagenesis scenario, the server can determine the reference set to be screened and obtained by the following algorithm:

[0085] The input data of the algorithm is p, a set D train ={(S 0 ,y 0 )}, matrix M.

[0086] Where, p refers to the number of occurrences of each type of amino acid at each mutation site, i.e., the target number, e.g., 2. train refers to the first protein set, (S 0 ,y 0 ) in S 0 represents the wild-type protein, and y 0 represents the experimental index value of the wild-type protein. M refers to the current score matrix.

[0087]

number

[0088] The step of initializing the current score matrix is ​​as follows: 0 When it appears at the wth mutation position of M uw = p-1, otherwise, M uw = p, and M uw is the element in the uth row and wth column of M, where 1≦w≦k.

[0089] The output data of the algorithm is the updated set D train The algorithm outputs D train is the initial referent set.

[0090] The steps of the algorithm are as follows:

[0091] Step 1: while ∃M uw >0 do, which means that if there is an element in the matrix M that is less than 0, execute steps 2 to 5.

[0092] Step 2: Score each variant

[0093]

number

[0094] Step 3: Maximum score mutant protein i*=argmaxScore i is selected, and this step is used to determine the mutant protein with the highest current protein score.

[0095] Wherein, i* indicates that the mutant protein with the maximum current protein score is the i*th mutant protein in the first subject set.

[0096] Step 4: Update the set, D train ←(S i *,y i *), which means that the i*th mutant protein in the first subject set is added to the first protein set.

[0097] Of these, (S i *,y i*) S i * represents the i*th mutant protein in the first subject set, and y i * represents the index experimental value of the i*th mutant protein.

[0098] Step 5: Update the score matrix M so that the uth amino acid is S i * appears at the wth mutation position, M uw =M uw -1, otherwise M uw =M uw It is.

[0099] Step 6: end while, if there is no element in M ​​greater than 0, execute step 7.

[0100] Step 7:D train Output.

[0101] In some embodiments, in the case of a non-saturation mutagenesis scenario, the server can screen and obtain a reference subject set by the following algorithm:

[0102] The input data of the algorithm is p, and the set D train ={(S 0 ,y 0 )}, vector Q.

[0103] Where, p refers to the number of occurrences of each type of amino acid at each mutation site, i.e., the target number, e.g., 2. train refers to the first protein set, (S 0 ,y 0 ) in S 0 represents the wild-type protein, and y 0 represents the experimental index value of the wild-type protein. Vector Q refers to the current score vector,

[0104]

number

[0105] The step of initializing the current score vector is as follows: 0 When it appears at the mutation position of Q u = p-1, otherwise Q u = p, and Q u is the u-th element in vector Q.

[0106] The output data of the algorithm is the updated set D train The algorithm outputs D train is the initial referent set.

[0107] Step 1: while ∃Qu>0 do, which means that if there is an element smaller than 0 in the matrix Q, execute steps 2 to 5.

[0108] Step 2: Score each variant

[0109]

number

[0110] Step 3: Maximum score variant i*=argmaxScore i is selected, and this step is used to determine the mutant protein with the highest current protein score.

[0111] Wherein, i* indicates that the mutant protein with the maximum current protein score is the i*th mutant protein in the first subject set.

[0112] Step 4: Update the set, D train ←(S i *,y i *), which means adding the i*th mutant protein in the first subject set to the first protein set.

[0113] Step 5: Update the score matrix Q so that the uth amino acid is S i * appears at the mutation position of Q u = p-1, otherwise Q u = p, and Qu is the u-th element in vector Q.

[0114] Step 6: end while, if there is no element in Q greater than 0, execute step 7.

[0115] Step 7:D train Output.

[0116] In this embodiment, each type of amino acid has a corresponding amino acid, and the scores in the current score set are uniquely labeled by the amino acid and the mutation position, and for the amino acid at each mutation position, the current score corresponding to the amino acid at the mutation position is determined from the current score set based on the amino acid and mutation position corresponding to the amino acid, thereby allowing the current score at each mutation position of each amino acid to be quickly and accurately determined.

[0117] The protein encoding method (i.e., the method for determining protein features) provided in the present application can assist protein evolution in conjunction with Bayesian optimization, and the process of encoding proteins to obtain protein features may be referred to as the process of protein feature representation, and an effective protein feature representation is crucial to finding optimal protein variants through Bayesian optimization. In order to build an accurate and information-rich low-dimensional feature representation in conjunction with knowledge of the related field, the present application proposes a new low-dimensional encoding scheme to represent each amino acid at each site. Specifically, two methods are given to calculate the amino acid representation at each site for two experimental scenarios in protein directed evolution, namely, the scenario of saturation mutagenesis of k sites and the scenario of non-saturation mutagenesis.

[0118] In some embodiments, the target feature is a protein feature, and the step of determining the target feature of each subject in the reference subject set based on the index experimental value for a predetermined index of each subject in the reference subject set includes the steps of: for each mutation position, dividing the reference subject set according to the type of amino acid at the mutation position, and obtaining a first sub-subject set respectively corresponding to each type of amino acid; for each type of amino acid at each mutation position, determining an amino acid feature at the mutation position of the amino acid based on the index experimental value of each subject in the first sub-subject set corresponding to the amino acid; and obtaining a protein feature of the subject based on the amino acid feature of the amino acid at each mutation position in the subject.

[0119] Wherein, the first sub-object set is a subset of the reference object set, and the first sub-object set includes at least some objects in the reference object set. The first sub-object set is uniquely determined by the mutation position and the type of amino acid, for example, there are four mutation positions, which are the first mutation position, the second mutation position, the third mutation position, and the fourth mutation position, and there are 20 types of amino acids, which are the iith type of amino acid, and 1≦ii≦20, then 80 first sub-object sets are generated, and at least one of the mutation positions and amino acids corresponding to different first sub-object sets is different, for example, the first sub-object set 1 is the first sub-object set corresponding to the first mutation position and the first type of amino acid, and the first sub-object set 2 is the first sub-object set corresponding to the first mutation position and the second type of amino acid.

[0120] Specifically, for each mutation position, the server can divide the reference object set according to the type of amino acid at the mutation position, and obtain a first sub-object set corresponding to each type of amino acid. For example, for the kkth mutation position, the server can obtain the amino acid at the kkth mutation position from each object in the reference object set, and construct an amino acid set corresponding to the kkth mutation position; for example, when the parameter object set includes 40 objects, the amino acid set includes 40 amino acids, and the types of amino acids at the kkth mutation position in different objects may be the same or different. After obtaining the amino acid set corresponding to the kkth mutation position, the server can divide the amino acid set based on the types of amino acids to obtain multiple subsets, classifying the same type of amino acids into the same subset and classifying different amino acids into different subsets, each subset includes only one type of amino acid, and each subset obtained by dividing is a first sub-object set corresponding to each type of amino acid at the kkth mutation position. For example, when the jth position in a protein is a mutation position, the first sub-object set corresponding to the mutation position is V j (a)={i|S ij= a}, where j represents the mutation position, i is the ordinal number of the object in the reference object set, and S ij represents an amino acid at mutation position j in the i-th object Si in the reference object set, and a represents any one type of amino acid. For example, if there are 20 types of amino acids, a represents any one type of the 20 amino acids, and if a is the first type of amino acid (denoted as A1), then the first sub-object set corresponding to amino acid A1 at mutation position j is V j (A1)={i|S ij =A1}.

[0121] In some embodiments, for each type of amino acid at each mutation position, the server can determine the amino acid characteristics at the mutation position of the amino acid based on the index experimental value of each object in the first sub-object set corresponding to the amino acid. For example, if the first sub-object set corresponding to amino acid A1 at mutation position j is V j (A1)={i|S ij = A1}, when calculating the amino acid feature at the mutation position j of the amino acid A1, V j (A1)={i|S ij The experimental index values ​​of the subjects corresponding to the sequence numbers of each subject in {=A1} can be used to calculate the amino acid characteristics at the mutation position j of amino acid A1.

[0122] In this embodiment, for each type of amino acid at each mutation position, the amino acid feature at the mutation position of the amino acid is determined based on the index experimental value of each subject in the first sub-subject set corresponding to the amino acid, so that the amino acid features at different mutation positions of the same type of amino acid are related to the mutation position, that is, the same amino acid has different feature expressions at different positions, for example, the features of the same type of amino acid at different mutation positions may be different from each other, thereby improving the accuracy of encoding for amino acids. The protein feature determination method provided in this embodiment can be used to encode mutant proteins generated in a k-site saturation mutagenesis scenario and obtain the protein features of the mutant proteins.

[0123] The target determination method provided in this application can be applied to Bayesian optimization, and the Bayesian optimization method can be used to assist protein directed evolution. Bayesian optimization can effectively explore the combinatorial space and find the optimal solution in the sample space by balancing exploration and exploitation with a small number of experimental runs as few as possible in a small number of measurement samples. However, in the application of Bayesian optimization, the encoding strategy currently faces several problems. On the one hand, high-dimensional encoding strategies are difficult for Bayesian optimization because accurate and information-rich low-dimensional representations are required to successfully perform global optimization searches. On the other hand, classification labels (e.g., one-hot encoding) may cause knowledge of death variants to be lost from the available experimental data of a particular protein. This can be seen in Figure 4, where each letter corresponding to the abscissa in Figure 4 represents one type of amino acid, for example, V is one type of amino acid, and in Figure 4, the average fitness of 20 types of amino acids (AA, Amino Acid) on four mutation sites of 384 experimental samples (GB1 mutants) selected from the GB1 dataset is calculated. The average fitness of each type of amino acid on each mutation site is obtained by calculating the average value of the affinity measurements at the mutation site, and the corresponding standard deviation is shown as the error bar (i.e., the vertical line in FIG. 4). As can be seen from FIG. 4, the presence of some death variants at a particular mutation site can directly result in low or zero fitness, regardless of the choice of amino acids at other positions. Therefore, applying traditional protein encoding schemes to Bayesian optimization methods to support protein directed evolution is usually ineffective.

[0124] In contrast, according to the protein encoding method (i.e., the protein feature determination method) provided in the present application, the protein features obtained by encoding are accurate and information-rich low-dimensional features, so that by applying the target determination method provided in the present application to Bayesian optimization, it is possible to rapidly assist protein directed evolution using Bayesian optimization.

[0125] In some embodiments, the step of determining an amino acid characteristic at the mutation position of the amino acid based on the index experimental value of each subject in the first sub-subject set corresponding to the amino acid includes the steps of: performing statistical calculations on the index experimental value of each subject in the first sub-subject set corresponding to the amino acid to obtain at least one index experimental statistical value; and determining an amino acid characteristic at the mutation position of the amino acid based on the at least one index experimental statistical value.

[0126] Among them, the index experimental statistics may be one or more, and more than one refers to at least two. The calculation of the statistics includes at least one of the following, but is not limited to: average value, minimum value, or minimum value calculation, etc.

[0127] Specifically, the server can perform statistical calculations on the index experimental values ​​of each object in the first sub-object set corresponding to the amino acid to obtain at least one index experimental statistical value, and determine an amino acid characteristic at a mutation position of the amino acid based on the at least one index experimental statistical value.

[0128] In some embodiments, the step of calculating statistics for the index experimental values ​​of each object in the first sub-object set corresponding to the amino acid to obtain at least one index experimental statistic includes the steps of: calculating an average value for the index experimental values ​​of each object in the first sub-object set corresponding to the amino acid to obtain a first index average value; and determining a maximum index experimental value from the index experimental values ​​of each object in the first sub-object set corresponding to the amino acid to obtain a first index maximum value, where the at least one index experimental statistic includes at least one of the first index average value or the first index maximum value. For example, when the first sub-object set corresponding to amino acid A1 at mutation position j has V j (A1)={i|S ij = A1}, when calculating the amino acid feature at the mutation position j of the amino acid A1, V j (A1)={i|S ij=A1}, obtain the index experimental value of the object corresponding to each sequence number, calculate the average value of each obtained index experimental value to obtain the first index average value, determine the maximum value from each index experimental value to obtain the first index maximum value, the first index average value is an index experimental statistical value, and the maximum value is also an index experimental statistical value, and determine the amino acid characteristic at the mutation position j of the amino acid A1 based on at least one of the first index average value or the first index maximum value. In this embodiment, the first index average value and the first index maximum value are obtained by statistics, so that the characteristics of the amino acid can be reflected, and thus the accuracy of the index experimental statistical value can be improved by using the first index average value or the first index maximum value as the index experimental statistical value.

[0129] In some embodiments, the step of determining the amino acid feature at the mutation position of the amino acid based on at least one index experimental statistic includes a step of configuring the amino acid feature at the mutation position of the amino acid by a first index average value and a first index maximum value. For example, the amino acid feature may be configured as a feature value of each of the first index average value and the first index maximum value, that is, the amino acid feature includes the first index average value and the first index maximum value. For example, the first index average value may be expressed as formula (1), and the first index maximum value may be expressed as formula (2). y in formula (1) and formula (2) i represents the index experimental value for a given index of the i-th object in the reference object set. In formula (1) and formula (2), a represents an amino acid. In this embodiment, the first index average value and the first index maximum value are used to configure the amino acid feature at the mutation position of the amino acid, so that the amino acid feature can be related to the index experimental value, thereby improving the accuracy of the target object screened based on the amino acid feature.

[0130]

number

[0131] In this embodiment, the indicator experimental value of each mutant protein in the first sub-object set corresponding to an amino acid is subjected to statistical calculation, and the amino acid feature at the mutation position of the amino acid is determined based on the statistical indicator experimental statistical value, and the data is statistically performed to improve the accuracy of the amino acid feature obtained by encoding. The protein feature determination method provided in this embodiment is applied to the encoding of the mutant protein generated in the k-site saturation mutagenesis scenario, so that the protein feature of the mutant protein can be obtained.

[0132] In some embodiments, the target feature is a protein feature, and the step of determining the target feature of each subject in the reference subject set based on the index experimental value for a predetermined index of each subject in the reference subject set includes the steps of: for each type of amino acid, determining an amino acid target included in the amino acid at the mutation position from the reference subject set, and obtaining a second sub-subject set corresponding to the amino acid; for each type of amino acid, determining an amino acid feature of the amino acid based on the index experimental value of each subject in the second sub-subject set corresponding to the amino acid; and obtaining a protein feature of the subject based on the amino acid feature of the amino acid at each mutation position in the subject.

[0133] Wherein, the second sub-object sets are subsets of the reference object set, the second sub-object sets including at least some of the objects in the reference object set, each second sub-object set corresponding to one type of amino acid, and different second sub-object sets differ with respect to one amino acid.

[0134] Specifically, the objects in the reference object set are proteins, and the reference object set may include mutant proteins and wild-type proteins. For each type of amino acid, the server can determine the object of the amino acid contained in the amino acid at the mutation position from the reference object set to construct a second sub-object set corresponding to the amino acid. For example, in the case of a first type of amino acid A1, for each object, the amino acid at each mutation position of the object is determined to construct an amino acid set corresponding to the object, and after obtaining the amino acid sets corresponding to each object in the reference object set, an amino acid set including the first type of amino acid A1 is determined from the amino acid sets corresponding to each object, and the object corresponding to the amino acid set including A1 is used to construct a second sub-object set corresponding to the amino acid A1.

[0135] In some embodiments, for each object in the reference object set, for each type of amino acid, the server can determine from the object a corresponding mutation position for each type of amino acid, where when the amino acid at mutation position 1 is A1, the corresponding mutation position for amino acid A1 is mutation position 1. Each type of amino acid may correspond to zero, one or multiple mutation positions, where multiple refers to at least two, for example, for the i-th object S in the reference object set, ij For each type of amino acid, a set N i(a) may be expressed as formula (3), where j is the mutation position. For each type of amino acid, a second sub-object set corresponding to each type of amino acid may be determined based on the set of mutation positions in each amino acid corresponding to each type of amino acid. For example, the second sub-object set V(a) may be expressed as formula (4), where for amino acid a, the number of mutation positions corresponding to amino acid a in the i-th object (i.e., |N i (a) If |N i (a) | is a set N i Represents the number of elements contained in (a).

[0136]

number

[0137]

number

[0138] In this embodiment, since the amino acid at the mutation position of each mutant protein in the second sub-subject set corresponding to a certain amino acid contains the amino acid, for each type of amino acid, the amino acid feature of the amino acid is obtained according to the indicator experimental value of each mutant protein in the second sub-subject set corresponding to the amino acid, and the amino acid is encoded according to the indicator experimental value of the protein containing the amino acid, thereby improving the accuracy of amino acid encoding. The protein feature determination method provided in this embodiment can be applied to the encoding of mutant proteins generated in the scenario of non-saturation mutagenesis to obtain the protein feature of the mutant protein.

[0139] In some embodiments, the step of determining a target object that satisfies the index requirement of the specified index from the second object set based on the mapping relationship includes the following steps: determine a statistical index value for the target statistical index of each object in the second object set based on the mapping relationship, and determine a selected object from the second object set based on the statistical index value; add the selected object to the reference object set if the iteration stop (termination) condition is not satisfied; return to the step of determining the object features of each object in the reference object set based on the index experimental value for the specified index of each object in the reference object set, and perform such processing until the iteration stop condition is satisfied; and the selected object obtained when the iteration stop condition is satisfied is the target object that satisfies the index requirement of the specified index.

[0140] Wherein, the mapping relationship between the predetermined index and the target feature is a first mapping relationship. The iteration stopping condition includes at least one of the following: the iteration number (i.e., the number of loops) reaches a number threshold, and the index experimental value of the selected object reaches a second index threshold, and the selected object can change at any time, and the selected object determined in different loops is different.

[0141] Specifically, the server can perform statistical calculation according to the first mapping relationship to obtain a second mapping relationship between the target statistical indicator and the object feature, and determine a statistical indicator value for the target statistical indicator of each object in the second object set according to the second mapping relationship, where the statistical indicator value refers to the value for the target statistical indicator of the object. For example, the second mapping relationship is represented by a curve y2=f2(x), and the index statistical value for the target statistical indicator of the object can be determined by calculating the value of y2 in the curve y2=f2(x) where x is the object feature of the object, and the value of y2 is the index statistical value for the target statistical indicator of the object.

[0142] In some embodiments, the selection target may be one or more, and the target corresponding to the maximum statistical index value may be determined as the selection target, or the target whose statistical index value is greater than a third index threshold may be determined as the selection target, and the third index threshold may be set according to needs. The server may obtain an object that satisfies the index requirement of a predetermined index based on the selection target, for example, the server may determine the selection target as the object that satisfies the index requirement of a predetermined index.

[0143] In some embodiments, if the iteration stop condition is not satisfied, the server can add the selected object to the reference object set, and return to the step of determining the object features of each object in the reference object set based on the index experimental value for the predetermined index of each object in the reference object set, and perform such processing until the iteration stop condition is satisfied, and the selected object obtained when the iteration stop condition is satisfied can be determined as the target object that satisfies the index requirement of the predetermined index. For example, the iteration stop condition is that the number of iterations (i.e., the number of loops) reaches a number threshold, and in this case, the selected object is determined as the target object when the number of iterations (i.e., the number of loops) reaches the number threshold.

[0144] In this embodiment, if the iteration stopping condition is not satisfied, a new selection target is determined again, so that a target target that meets the index requirements of the specified index can be gradually found; and by adding a selection target to the reference target set, the number of targets in the reference target set increases. Therefore, in the process of determining a new selection target each time, a step of determining the target features of each target in the reference target set is performed, so that the accuracy of the target features obtained by encoding can be gradually improved, and the accuracy of the target object finally selected can be improved.

[0145] In some embodiments, as shown in FIG. 5, a target determination method is provided, in which the target of the method is a mutant protein, and the method may be executed by a terminal or a server, or may be jointly executed by a terminal and a server. The method is described as being applied to a server, and includes the following steps:

[0146] Step 502: An initial score set is obtained, and the initial scores corresponding to each type of amino acid in the initial score set are the target frequencies.

[0147] Step 504: Subtract the initial scores corresponding to the amino acids at each mutation position in the wild-type protein in the initial score set to obtain a current score set, and determine a first protein set based on the wild-type protein, where the wild-type protein is a protein without any mutation, and obtain a second protein set based on the first target set.

[0148] Step 506: For each mutant protein in the second protein set, determine a current score from the current score set, respectively corresponding to the amino acid at each mutation position in the mutant protein, determine a current protein score for the mutant protein based on each obtained current score, and select and obtain a target protein from the second protein set based on the current protein score.

[0149] Step 508: Decrease the current scores corresponding to the amino acids at each mutation position in the target protein in the current score set, and transfer the target protein from the second protein set to the first protein set.

[0150] Step 510: Determine if there is a score greater than 0 in the current score set; if yes, return to step 506; if no, execute step 512.

[0151] Step 512: Determine the first protein set as a reference set.

[0152] Please refer to Fig. 6, which shows the principle of the target determination method, which is used to determine mutant proteins with relatively high affinity. The candidate sample space includes wild-type proteins and multiple mutant proteins. The reference target set in step 508 is an initial reference target set, and the reference target set can be changed afterwards, and the initial reference target set is, for example, the initial sample set in Fig. 6, and according to the method for determining the initial reference target set provided in this application, the initial sample set is obtained by screening from the candidate sample space, and the samples in the initial sample set are any one of wild-type proteins or mutant proteins.

[0153] Step 514: Train an index detection model based on the object features and index experimental values ​​of each object in the reference object set, and use the trained index detection model to predict the index predicted value of each object in the first object set, and screen objects whose index predicted values ​​satisfy the index value screening conditions from the first object set to obtain a second object set.

[0154] As shown in Figure 6, after obtaining the initial sample set, the "affinity" step obtains the affinity of the samples in the initial sample set (obtained by experimental measurement); after obtaining the affinity, the "protein feature representation" step encodes the proteins in the initial sample set, obtains the protein features of each protein in the initial sample set, and trains the indicator detection model using the protein affinity (obtained by experimental measurement) and the protein features; after training, inputs the protein features corresponding to the proteins in the candidate sample space into the indicator detection waiting model, and obtains the affinity prediction value of the protein by prediction; and selects proteins whose affinity prediction value is greater than the affinity threshold from the candidate sample space to form a second target set.

[0155] By screening the first sample set from the candidate sample space (i.e., by screening the second target set based on the first target set), a search space pre-screening strategy is provided. Since the affinity values ​​of many variants in the candidate sample space are relatively low, the sample search space pre-screening strategy can be adopted to remove samples with low affinity values ​​in advance, reduce the sample space that needs to be searched in Bayesian optimization, and improve the efficiency of calculation. For example, by adopting XGBOD, low affinity variants can be removed from the sample search space. Specifically, in each iteration process of Bayesian optimization, samples in the candidate sample space are pre-screened first, and samples below the threshold can be determined as low fitness (removal point, Postive class) by setting a threshold, and samples above the threshold can be determined as high fitness (non-removal point, Negative class). By training XGBOD using existing experimental samples (i.e., proteins whose affinities have been experimentally determined) as a training set and screening samples in the candidate sample space to remove potential sample points with very low affinity in advance, the number of samples in the sampling space can be reduced and the efficiency of the model can be improved.

[0156] The process of determining one selection target from the second target set each time can be regarded as one Bayesian optimization. For example, in FIG. 6, the process of using the acquisition function each time to screen samples from the remaining samples after samples with relatively low affinity are removed is one Bayesian optimization.

[0157] Step 516: Based on the index experimental value for the predetermined index of each object in the reference object set, determine the object feature of each object in the reference object set, and based on the index experimental value for the predetermined index of each object in the reference object set and the object feature, determine the mapping relationship between the predetermined index and the object feature.

[0158] Among them, the mapping relationship between the specified index and the target feature is, for example, the probabilistic surrogate model in FIG. 6, and the probabilistic surrogate model may be any one of a Gaussian process regression model based on Gaussian distribution, or a Gaussian process regression model based on Student-t distribution, etc.

[0159] Step 518: Determine a statistical index value for the target statistical index of each object in the second object set based on the mapping relationship, and determine a selection object from the second object set based on the statistical index value.

[0160] As shown in FIG. 6, the target statistical index is, for example, the acquisition function in FIG. 6, and the mapping relationship between the predetermined index and the target feature is used to determine the acquisition function, and a sample is selected from the remaining samples based on the acquisition function.

[0161] Step 520: Determine whether the iteration stopping condition is satisfied; if not, execute step 522; if yes, execute step 524.

[0162] Step 522: Add the selected object to the reference object set, and return to step 514.

[0163] Step 524: The selected object obtained when the iteration stopping condition is satisfied is determined as a target object that satisfies the index requirement of the predetermined index.

[0164] For example, the server may utilize an algorithm such as Bayesian optimization with prescreened search space via outlier detection (ODBO), which realizes the process of determining target objects from a second object set based on a reference object set.

[0165] The input data for the algorithm is the initial sample set D t and the number of experiments is T (i.e., the number of loops is T).

[0166] Among them, the first sample set D t is the initial referent set, i.e., the referent set employed during the first iteration.

[0167] The output data of the algorithm is the optimum (s*,y*) in the sample space, where s* represents the optimal variant and y* represents the affinity of s* (obtained by experimental measurement).

[0168] The process of the algorithm is as follows:

[0169] T←1; / / Let 1 be t, where t represents the number of the current iteration; while t≦T do; / / Continue if t≦T, where T is the number of experiments (i.e., the number of loops); if Robust GP then; / / Run next if Robust GP is adopted as the probabilistic surrogate model; D t Train a Gaussian process regression model based on the Student-t distribution using t Based on the fact that is equal to D1, represents the first sample set, i.e., the first referent set (the referent set adopted at the first iteration); D tin ={(S i ,y i )│|f t (S i )-y i |≦α}, and remove outliers based on the rejection threshold α and keep normal points; / / D tin D t represents the set of samples remaining after removing outliers (samples) from; D tin Train a Gaussian process regression model based on the Gaussian distribution using; else if GP then; / / Continue if Robust GP is adopted as the probabilistic surrogate model; D tUse to train a Gaussian process regression model based on Gaussian,distribution; if Naivo BO then; / / Run next if Naivo Bayes optimization is used, where Naivo BO refers to Naive Bayes optimization; Acquisition function based on current posterior probability

[0170]

number

[0171]

number

[0172] Among them, TuRBO is a kind of global optimization method. By constructing a series of local GPS surrogate models, it can avoid over-searching the height uncertainty area in the search space from a global perspective, and can achieve a highly efficient solution by making full use of the quadratic convergence of the local reliable method.

[0173] An example is taken to describe the basic flow of the target determination method provided in this application. As shown in Figure 7, it mainly includes four steps: 1) obtain initial experimental data; 2) obtain feature representation of data; 3) perform pre-screening of the search space; and 4) use the Bayesian optimization algorithm to train a probabilistic surrogate model based on the initial experimental data for the search space after screening. After training the surrogate model, optimize the acquisition function to select the next round of experimental samples from the search space. Validate the given experimental design, add the experimental results to the training set, and update the posterior probability of the surrogate model. This process is repeated until the design is maximized, resources are exhausted, or the condition for space exploration to be improved cannot be found. FIG. 7(a) is the first experimental data obtained, i.e., the first reference target set screened from the first target set, and eight mutants are shown in FIG. 7(a), each mutant has a corresponding score, where the score represents the fitness, for example, the mutant “H76L,K78R” represents one mutant, and the score of “H76L,K78R” is 0.18. FIG. 7(b) is to obtain the feature representation of the data (i.e., the process of determining the amino acid features by encoding), and the bar graph in FIG. 7(b) is the average fitness at the i-th mutation site of 20 kinds of amino acids, and the table in FIG. 7(b) shows the average fitness at the i-th mutation site of 5 kinds of amino acids, for example, the average fitness of the amino acid “V” is 1.12. Fig. 7(c) shows the process of search space pre-screening, in which the features of mutants in the initial experimental data are determined, and "P1 P2 A1 A2" in Fig. 7(c) are the features of mutants, where P is the abbreviation for position, A is the abbreviation for Amino Acid, P1 and P2 respectively represent the positions of amino acids in the mutant, and A1 and A2 respectively represent the features of amino acids. The determined features of mutants are used to perform pre-screening on the search space, and in Fig. 7(c), the solid circles represent outliers (i.e., mutants with relatively low fitness) and the solid triangles represent normal points (i.e., mutants with relatively high fitness).Figure 7(d) shows the process of the Bayesian optimization algorithm. The four processes in Figure 7 allow us to determine a mutant with high fitness.

[0174] For computational method-assisted experimental design, the technical proposal of the present application provides a framework for highly efficient experimental design. The search space pre-screening strategy pre-screens samples in the candidate sample space (i.e., screens from the first target set to obtain the second target set), and combines with the Bayesian optimization algorithm to balance exploration and utilization, effectively search the sample space, and find the optimal experimental design scheme in as few steps as possible. For the actual application scenario of protein directed evolution, the technical proposal of the present application designs an amino acid encoding strategy (i.e., a method for obtaining amino acid features) based on average fitness to accurately and effectively realize feature representation. To better assist the experimenter in experimental design, a screening strategy for the first sample (i.e., a method for determining the reference target set) is further provided to assist the experimenter in selecting the first experimental sample, which can ensure that the coverage of amino acid encoding information contained in the first number of samples is maximized and the number of first experiments required is minimized. The Bayesian optimization algorithm of search space pre-screening can reduce the experimental cost and time cost. The technical solution of this application realizes a framework for efficient experiment design, which is called ODBO (Bayesian optimization with prescreened search space via outlier detection). The method can assist experiment design through search space screening plus Bayesian optimization, and help experimenters reduce experiment costs and time costs. For the real adaptation scenario of protein directed evolution, an amino acid encoding strategy based on average fitness is provided to realize feature representation accurately and effectively.In order to better assist the experimenter in experimental design, the present technical solution further provides an initial sample screening strategy to assist the experimenter in selecting the initial experimental sample, which can ensure that the coverage of amino acid coding information contained in the initial sample number is maximized and the number of required experiments is minimized, thereby reducing the experimental cost.

[0175] The present invention may be used to perform computationally assisted protein directed evolution experimental design, in which the proposed Bayesian optimization combined with search space prescreening can also be applied to automated experimental design in other fields, such as new materials development and fast charging protocols for batteries.

[0176] In materials science, discovering and creating materials with specific properties is expensive and time consuming. With each new composition or material parameter, the space of candidate experiments grows exponentially. For example, to study the effect of one new parameter (e.g., the effect of introducing a dopant), about 10 experiments need to be performed within the range of parameters, so that N parameters are 10 N times of experiments are required. With the emergence of each new parameter, the number of candidate experiments quickly exceeds the feasibility of exhaustive search. The diversity and complexity of material composition-structure-property (CSP) relationships, as well as material-processing parameters and atomic disorder, can further confound research. Combined with the scarcity of optimal materials, these challenges threaten innovation and industrial progress. A Bayesian optimization-based material discovery support method can guide laboratory experimenters to design experiments, which can accelerate the speed of material discovery and spend less resources in material exploration experiments by balancing between exploring unknown functions using experiments and identifying extreme values ​​using prior knowledge.

[0177] Lithium-ion batteries are one of the most commonly used energy storage devices in electric vehicles. With the advancement of battery chemistry technology, one important issue is how to effectively determine the charging protocol to balance the need for fast charging with maximizing the battery's service life. However, determining the appropriate charging protocol is not easy. On the one hand, it takes months to years to evaluate the cycle life of the battery. On the other hand, the huge parameter adjustment space and the diversity of samples make the experiments even more difficult. How to reduce the parameter range and shorten the experiment time is very important for the development of lithium-ion batteries. Computational experimental design methods can be used to reduce the cost of experimental optimization, and the feedback of completed experiments can be used to inform the decision of subsequent experiments, balancing the experimental results and needs, i.e., testing and exploring the experimental parameter space with high uncertainty, and predicting promising parameters based on the completed experimental results. Ultimately, the number and time of required experiments can be reduced, and the cost can be reduced to find an effective charging protocol.

[0178] The present application further provides an application scenario, which is a scenario for developing new materials. The above-mentioned target determination method is used in the application scenario. Specifically, the application of the target determination method in the application scenario is as follows: the server obtains the index prediction value for each of the materials in the first material set for the predetermined index, selects the materials from the first material set whose index prediction value meets the index value screening condition to obtain a second material set, determines the mapping relationship between the predetermined index and the material characteristic based on the index experimental value and the material characteristic for the predetermined index of the plurality of materials in the first material set, and determines the target material that meets the index requirement of the predetermined index from the second material set based on the mapping relationship. This allows the material with the specified property to be quickly determined. Among them, at least one composition of each material in the first material set is different, or the content of at least one composition is different. As shown in FIG. 8, the closed-loop optimization of perovskite electrolyte based on machine learning is shown, and the Bayesian optimization can be used to find an effective experimental search for high-speed lithium ion conductor from perovskite solid electrolyte.

[0179] The present application further provides another application scenario, which is a scenario of a battery fast charging protocol, and the above-mentioned target determination method is used in the application scenario. Specifically, the application of the target determination method in the application scenario is as follows: the server obtains an index prediction value for each predetermined index of each battery charging protocol in a first battery charging protocol set, selects a battery charging protocol from the first battery charging protocol set whose index prediction value satisfies an index value screening condition to obtain a second battery charging protocol set, obtains a mapping relationship between the predetermined index and the battery charging protocol characteristics based on the index experimental value and the battery charging protocol characteristics for the predetermined index of the plurality of battery charging protocols in the first battery charging protocol set, and determines a target battery charging protocol that meets the index requirements of the predetermined index from the second battery charging protocol set based on the mapping relationship. Thus, a battery charging protocol with a specified performance can be quickly determined. Wherein, at least one parameter of each battery charging protocol in the first battery charging protocol set is different, or at least one parameter value is different. As shown in FIG. 9, a closed-loop optimization of a battery fast charging protocol based on machine learning is shown. Machine learning methods can effectively optimize the parameter space to identify the current and voltage setting parameters of the fast charging protocol to maximize battery life.

[0180] The target determination method provided in this application is based on the Python language and the Botorch library, and can be configured on a server equipped with a Linux operating system or a Windows operating system and CPU / GPU computing resources.

[0181] To verify the effectiveness of the target determination method provided in the present application in supporting protein directed evolution, tests were conducted on four protein directed evolution datasets, namely, 1) GB1 dataset (containing 55 mutation sites); 2) GB1 dataset (containing 4 mutation sites); 3) BRCA1 dataset; and 4) Green Fluorescent Protein dataset.

[0182] Among them, GB1 refers to the B1 structural domain of protein G. Protein G is an immunoglobulin-binding protein and is expressed in C and G streptococci. The B1 structural domain of protein G (GB1) interacts with the Fc structural domain of immunoglobulin. Experiments have been carried out on the generated GB1 datasets. Saturation mutagenesis has been carried out on four carefully selected residue sites 39, 40, 41 and 51 from GB1. The 149,361 mutants have fitness values ​​measured in the experiment. The fitness standard is the binding affinity with IgG-Fc. One or two amino acids have been mutated throughout the random regions of 55 codons in the GB1 protein, and a total of 536,944 mutant data have been collected.

[0183] BRCA1 is a multi-domain protein that belongs to the tumor suppressor gene family and is most commonly mutated in three domains: the N-terminal RING domain, exons 11-13, and the BRCT domain. The BRCA1 RING structural domain is responsible for the E3 ubiquitin ligase activity of BRCA1 and mediates the interaction between BRCA1 and other proteins. The effects of single or multiple point mutations in BRCA1 residues on the function of E3 ubiquitin ligase activity have been investigated. The dataset contains a total of 98,300 mutants with E3 scores.

[0184] Green fluorescent protein (GFP), also called green fluorescent protein, was first discovered in the jellyfish Aequorea victoria (avGFP) and emits green fluorescence when exposed to light. The local fitness landscape of avGFP has been analyzed by estimating the fluorescence levels of genotypes obtained by random mutagenesis of the avGFP sequence. The dataset contains 54,025 distinct protein sequences. Table 1 details the details of the four datasets used.

[0185] Table 1 provides detailed information about the protein directed evolution dataset.

[0186] [Table 1] Figure 10 shows the fitness distribution of different datasets. In Figure 10, the abscissa is the metric value and the ordinate is density. Figure 10(a) shows the fitness distribution of dataset GB1(4), Figure 10(b) shows the fitness distribution of dataset GB1(55), Figure 10(c) shows the fitness distribution of dataset BRCA1, and Figure 10(d) shows the fitness distribution of dataset avGFP.

[0187] An initial sample screening strategy is adopted to generate an initial sample set. For the GB1(4) dataset, which is consistent with the saturation mutation scenario, we set each amino acid to occur at least twice at each position, and obtain 40 initial training samples. For the GB1(55), Ube4b, and avGFP datasets, which are consistent with the non-saturation mutation scenario, we set each amino acid to occur at least once at every position, and obtain 136, 217, and 142 initial training samples, respectively. For the ODBO algorithm, the filtering threshold of the search space prescreening is set to 0.05. For each type of method, all experiments are performed using 10 different random seeds. For the GB1(55), Ube4b, and avGFP datasets, each method screens one sample from the sample space each time, and repeats 50 times. For the GB1(55) dataset, each method screens one sample from the sample space each time, and repeats 100 times. Expected improvement (EI) is adopted as the acquisition function. Ube4b and BRCA1 refer to the same protein.

[0188] Figure 11 summarizes the performance of different methods on four protein directed evolution datasets, where dataset 1 refers to dataset GB1(4), dataset 2 refers to dataset GB1(55), dataset 3 refers to dataset Ube4, and dataset 4 refers to avGFP. Method 1 refers to the random screening method, method 2 refers to the combination of TuRBO and GP, method 3 refers to the combination of ODBO, uRBO, and GP, method 4 refers to the combination of ODBO, TuRBO, and RobustGP, and method 5 refers to the combination of ODBO, TuRBO, and RobustGP. (outside 1) JPEG2024544637000014.jpg16121 refers to the combination of ODBO with GP, method 6 refers to the combination of ODBO with BO and GP, and method 7 refers to the combination of ODBO with BO and RobustGP. Each of the four graphs in Figure 11 contains a line, which indicates the true maximum fitness.

[0189] Figure 12 summarizes the comparison of four protein directed evolution data sets of different methods, and each curve represents the average value obtained by each method with 10 different random seeds, where F1 represents the method of combining ODBO with TuRBO and GP, and q=1, F2 represents the method of combining ODBO with TuRBO and GP, and q=5, F3 represents the method of combining ODBO with TuRBO and GP, and q=10, F4 represents the method of combining ODBO with TuRBO and RobustGP, and q=1, F5 represents the method of combining ODBO with TuRBO and RobustGP, and q=5, and F6 represents the method of combining ODBO with TuRBO and RobustGP, and q=10. G1 represents the combination of ODBO with TuRBO and GP, and the acquisition function is expected improvement, G2 represents the combination of ODBO with TuRBO and GP, and the acquisition function is upper confidence limit, G3 represents the combination of ODBO with TuRBO and GP, and the acquisition function is Thompson sampling, and Q represents the number of samples selected at each iteration to carry out the next round of experiments.

[0190] Therefore, we can find that ODBO obtains the optimal performance in all datasets. The search space pre-screening step can provide more effective sample collection and is favorable for finding variants with optimal properties faster. For example, for the saturated mutation scenario (i.e., GB1(4) dataset), the combined method of ODBO with TuRBO and RobustGP can obtain the optimal variant (fitness=8.76) in one large sample space (204=16000) with less than 50 evaluations. However, in the methods where the pre-screening strategy is not adopted, the Bayesian optimization algorithm (e.g., (outside 2) JPEG2024544637000015.jpg16121RBO, TuRBO) can usually converge to a single bad local optimum, resulting in poor average performance. This shows the importance of search space prescreening. For the case of non-saturating mutations, (Outside 3) Besides the method of combining BO and GP, almost all Bayesian optimization methods adopt a given low-dimensional protein coding strategy to find optimal variants. All methods can only find near-optimal variants in the GB1(55) and avGFP datasets, but the method proposed in this technical proposal outperforms other methods.

[0191] Table 2 shows the proportion of samples belonging to the previous 1%, 2% and 5% affinity values ​​in the sample space in the 50 rounds of recommendation screening, which are screened by different calculation methods in the GB1(4) dataset. As can be seen, the adoption of sample space pre-screening is more advantageous in selecting better samples from each round of sample screening for the next round of experimental testing.

[0192] [Table 2] The performance of Bayesian optimization algorithms with different acquisition functions and probabilistic surrogate models in protein directed evolution has also been tested. As shown in Figure 10, the performance of Bayesian optimization algorithms with different acquisition functions and probabilistic surrogate models on the GB1(4) dataset is shown. Figure 10(a) shows the performance of the “ODBO,TuRBO+GP” method when the batch size of each iteration is different, Figure 10(b) shows the performance of the “ODBO,TuRBO+RobustGP” method when the acquisition functions are EI, UCB, PI, and TS, respectively, and Figure 10(c) shows the performance of the “ODBO,TuRBO+RobustGP” method when the acquisition functions are EI, UCB, PI, and TS, respectively.

[0193] In addition, the computational resources consumed when each method was performed on the GB1 dataset were also calculated, as shown in Table 3. When adopting the conventional encoding scheme (shown here is feature georgiev encoding using physicochemical properties), there are 76 dimensional features, and using TuRBO consumes considerable computational resources and time, whereas when using the amino acid encoding scheme given here, the feature dimension of amino acids can be reduced to 4 dimensions, and the computational time and resource consumption can be significantly reduced. In addition, by adopting a search space pre-screening strategy, the time and resources consumed for calculation can be significantly reduced. In addition, ODBO can find the optimum in the sample space from the fewest experimental steps, which is favorable for reducing experimental and time costs.

[0194] [Table 3] As can be understood, although each step in the flowchart according to each embodiment as described above may be displayed in sequence according to the direction of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless otherwise specified, the execution of these steps is not limited to the order, and these steps may be executed in other orders. In addition, at least some of the steps in the flowchart according to each embodiment as described above may include multiple steps or multiple stages, and these steps or stages may be executed at the same time or at different times, and these steps or stages may be executed sequentially or alternately with other steps or at least some of the steps or stages in other steps.

[0195] In addition, based on the same inventive concept, an embodiment of the present application further provides an object determination device for realizing the above-mentioned object determination method. The realization scheme of the device to solve the problem is similar to the realization scheme described in the above-mentioned method, so that the specific limitations of one or more embodiments of the object determination device provided below can refer to the limitations of the above-mentioned object determination method, and detailed description thereof will be omitted here.

[0196] In some embodiments, as shown in FIG. 13, an object determining device is provided, which includes a predicted value obtaining module 1302, an object set obtaining module 1304, a mapping relationship determining module 1306 and a target object determining module 1308.

[0197] The obtain predicted value module 1302 is used to obtain an index predicted value for each predetermined index for each object in the first object set.

[0198] The object set acquisition module 1304 is used to screen objects whose index prediction values ​​satisfy the index value screening conditions from the first object set, and acquire a second object set.

[0199] The mapping relationship determination module 1306 is used to determine a mapping relationship between the predetermined index and the object feature based on index experimental values ​​for the predetermined index and the object feature of a plurality of objects in the first object set.

[0200] The target object determining module 1308 is used to determine target objects that satisfy the index requirement of the predetermined index from the second object set based on the mapping relationship.

[0201] In some embodiments, the objects in the first object set are mutant proteins, and the apparatus further includes a reference object set screening module for obtaining a reference object set by screening based on the first object set, wherein the reference object set satisfies a condition that each type of amino acid occurs at least a target number of times at each mutation position, and the predicted value acquisition module further trains an index detection model based on the object features and the index experimental value of each object in the reference object set; and uses the trained index detection model to predict the index predicted value of each object in the first object set.

[0202] In some embodiments, the mapping relationship determination module is further used for obtaining an object feature of each object in the reference object set based on an index experimental value for a predetermined index of each object in the reference object set; and for determining a mapping relationship between the predetermined index and the object feature based on the index experimental value for the predetermined index of each object in the reference object set and the object feature.

[0203] In some embodiments, the reference target set screening module further includes: obtaining a current score set, the current score set including a current score corresponding to each type of amino acid; obtaining a second protein set based on the first target set, and selecting a target protein from the second protein set based on the current score set; decrementing the current scores corresponding to each amino acid at each mutation position in the target protein in the current score set, and transferring the target protein from the second protein set to the first protein set; if the current score set indicates that the first protein set does not satisfy the condition that "each type of amino acid occurs at least the target number of times at each mutation position", returning to the step of selecting a target protein from the second protein set based on the current score set, and performing such a process until the current score set indicates that the first protein set satisfies the condition that "each type of amino acid occurs at least the target number of times at each mutation position", and then using the first protein set as the reference target set.

[0204] In some embodiments, the reference set screening module further obtains an initial score set, where the initial scores corresponding to each type of amino acid in the initial score set are target numbers; and reduces the initial scores corresponding to each amino acid at each mutation position in the wild-type protein in the initial score set to obtain a current score set, which is used to determine a first protein set based on the wild-type protein, where the wild-type protein is a protein without any mutations.

[0205] In some embodiments, the mapping relationship determination module is further used to determine, for each mutant protein in the second protein set, a current score from the current score set, each corresponding to an amino acid at each mutation position in the mutant protein; determine a current protein score for the mutant protein based on each obtained current score; and select and obtain a target protein from the second protein set based on the current protein score.

[0206] In some embodiments, each type of amino acid has a corresponding amino acid, and the scores in the current score set are uniquely labeled by the amino acid and the mutation position, and the mapping relationship determination module is further used to determine, for the amino acid at each mutation position, a current score corresponding to the amino acid at the mutation position from the current score set based on the amino acid corresponding to the amino acid and the mutation position.

[0207] In some embodiments, the target feature is a protein feature, and the mapping relationship determination module is further used to: for each mutation position, divide the reference target set according to the type of amino acid at the mutation position to obtain a first sub-target set respectively corresponding to each type of amino acid; for each type of amino acid at each mutation position, determine an amino acid feature at the mutation position of the amino acid based on the index experimental value of each target in the first sub-target set corresponding to the amino acid; and obtain a protein feature of the target based on the amino acid feature of the amino acid at each mutation position in the target.

[0208] In some embodiments, the mapping relationship determination module is further used to perform statistical calculations on the index experimental values ​​of each object in the first sub-object set corresponding to the amino acid to obtain at least one index experimental statistical value; and to determine an amino acid characteristic at the mutation position of the amino acid based on the at least one index experimental statistical value.

[0209] In some embodiments, the mapping relationship determination module is further used to perform an average calculation for the index experimental values ​​of each object in the first sub-object set corresponding to the amino acid to obtain a first index average value; and to determine a maximum index experimental value from the index experimental values ​​of each object in the first sub-object set corresponding to the amino acid to obtain a first index maximum value, and the at least one index experimental statistical value includes at least one of the first index average value or the first index maximum value.

[0210] In some embodiments, the mapping relationship determination module is further used to configure an amino acid signature at the mutation position of the amino acid according to the first index average value and the first index maximum value.

[0211] In some embodiments, the target feature is a protein feature, and the mapping relationship determination module is further used to determine, for each type of amino acid, a target amino acid included in the amino acid at the mutation position from the reference target set, and obtain a second sub-target set corresponding to the amino acid; for each type of amino acid, determine an amino acid characteristic of the amino acid based on the index experimental value of each target in the second sub-target set corresponding to the amino acid; and obtain a protein feature of the target based on the amino acid characteristic of the amino acid at each mutation position in the target.

[0212] In some embodiments, the target object determination module is further used to determine a statistical index value for the target statistical index of each object in the second object set based on the mapping relationship, and determine a selected object from the second object set based on the statistical index value; if the iteration stop condition is not satisfied, add the selected object to the reference object set, and return to the step of determining the object features of each object in the reference object set based on the index experimental value for the predetermined index of each object in the reference object set, and perform such processing until the iteration stop condition is satisfied; and if the iteration stop condition is satisfied, the selected object obtained is used to determine a target object that meets the index requirement of the predetermined index.

[0213] Each module in the above-mentioned object determination device may be realized in whole or in part by software, hardware, or a combination thereof. Each module may be embedded in the form of hardware, or may be separate from the processor in the computer device, or may be stored in the form of software in the memory of the computer device, so that the processor can call and execute the operation (step) corresponding to each module.

[0214] In some embodiments, a computer device is provided, which may be a server, and its internal configuration may be as shown in FIG. 14. The computer device may include a processor, a memory, an input / output interface (Input / Output, I / O) and a communication interface. Wherein, the processor, the memory and the input / output interface are connected via a system bus, and the communication interface is connected to the system bus via the input / output interface. Wherein, the processor of the computer device is used to provide calculation and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal storage. The non-volatile storage medium stores an operating system, computer-readable instructions and a database. The internal storage is used to provide an environment for the execution of the operating system and the computer-readable instructions in the non-volatile storage medium. The database of the computer device is used to store data related to the object determination method. The input / output interface of the computer device is used for the processor to exchange information with an external device. The communication interface of the computer device is used for communicating with an external terminal via a network connection. The computer-readable instructions are used to realize the object determination method when executed by the processor.

[0215] In some embodiments, a computer device is provided, which may be a terminal, and its internal configuration may be as shown in FIG. 15. The computer device may include a processor, a memory, an input / output interface, a communication interface, a display unit, and an input device. The processor, the memory, and the input / output interface are connected via a system bus, and the communication interface, the display unit, and the input device are connected to the system bus via the input / output interface. The processor of the computer device is used to provide calculation 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 computer-readable instructions. The internal memory is used to provide an environment for the execution of the operating system and the computer-readable instructions in the non-volatile storage medium. The input / output interface of the computer device is used for the processor to exchange information with an external device. The communication interface of the computer device is used for communicating with an external terminal in a wired or wireless manner, and the wireless manner may be realized by WIFI, mobile cellular network, NFC, or other technologies. The computer readable instructions are used to realize the object determination method when executed by a processor. The display unit of the computing device is used to generate a visible image, and may be a display screen, a projection device, or a virtual reality imaging device, the display screen may be a liquid crystal display screen or an electronic ink display screen, and the input device of the computing device may be a touch layer (film) covering the display screen, a key, a trackball, or a touch panel installed on the outer shell of the computing device, or even an external keyboard, touch panel, mouse, etc.

[0216] As can be understood by those skilled in the art, the configurations shown in Figures 14 and 15 are only some of the configurations related to the technical solution of the present application, and do not limit the computer equipment to which the technical solution of the present application is applicable, and a specific computer equipment may include more or fewer components than those shown, or may combine several components, or may have a different component layout.

[0217] In some embodiments, a computing device is provided that includes a memory and one or more processors, the memory having computer readable instructions stored therein that, when executed by the processor, cause the one or more processors to perform steps in the target determination method described above.

[0218] In some embodiments, one or more non-volatile readable storage media are provided having computer readable instructions stored thereon that, when executed by one or more processors, cause the one or more processors to perform steps in the target determination method described above.

[0219] In some embodiments, a computer program product is provided that includes computer readable instructions that, when executed by a processor, can implement the steps in the target determination method described above.

[0220] All user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data for analysis, data for storage, data for display, etc.) related to this application are information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of related data must comply with the relevant laws, regulations and standards of the relevant countries and regions.

[0221] As can be understood by those skilled in the art, the execution of all or part of the flow of the method according to the above-mentioned embodiments can be completed by instructing relevant hardware by computer-readable instructions, and the above-mentioned computer-readable instructions can be stored in a non-volatile computer-readable storage medium, and the computer-readable instructions may include the flow of each method embodiment as described above when executed. Any references to storage, database, or other medium used in each embodiment provided in this application may include at least one of non-volatile and volatile storage. The non-volatile storage may include ROM (Read-Only Memory), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, ReRAM, MRAM (Magnetoresistive Random Access Memory), FRAM (Ferroelectric Random Access Memory), PCM (Phase Change Memory), graphene memory, etc. The volatile storage may include RAM (Random Access Memory) or external high-speed cache memory, etc. By way of example and not limitation, the RAM may be in multiple forms, such as, for example, a static random access memory (SRAM) or a dynamic random access memory (DRAM). The database according to each embodiment provided herein may include at least one of a relational database and a non-relational database. The non-relational database may be, but is not limited to, a distributed database based on a blockchain. The processor according to the embodiment provided herein may be, but is not limited to, a general purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a quantum computing-based data processing logic device, and the like.

[0222] Although the preferred embodiment of the present application has been described above, the present application is not limited to this embodiment, and any modification to the present application falls within the technical scope of the present application as long as it does not depart from the spirit of the present application.

Claims

1. 1. A computer device implemented method for determining an object, comprising: obtaining a metric prediction value for each of the predetermined metrics for each subject in the first subject set, the metric prediction value being a value for the predetermined metric for the subject predicted by a pre-trained model; screening objects whose index prediction values ​​satisfy an index value screening condition from the first object set to obtain a second object set; Determining a mapping relationship between the predetermined index and the target feature based on the index experimental value of the predetermined index and the target feature of a plurality of objects in the first object set, the index experimental value referring to the value of the object for the predetermined index obtained by an experiment; and determining, based on the mapping relationship, target objects from the second object set that meet index requirements of the predetermined index.

2. 2. The method of claim 1, the objects in said first object set are mutant proteins; The method further comprises: Obtaining a reference subject set by screening based on the first subject set, the reference subject set satisfying the condition that "each type of amino acid occurs at least a target number of times at each mutation position"; The step of obtaining a metric prediction for each of the predetermined metrics for each of the objects in the first object set comprises: training an indicator detection model based on the object features and indicator experimental values ​​of each object in the reference object set; and Utilizing the trained indicator detection model to predict an indicator prediction value for each object in the first object set.

3. 3. The method of claim 2, The step of determining a mapping relationship between the predetermined index and the target feature based on the index experimental value for the predetermined index and the target feature of a plurality of objects in the first object set includes: determining a target characteristic for each of the subjects in the reference subject set based on an index experimental value for the predetermined index for each of the subjects in the reference subject set; and The method includes determining a mapping relationship between a predetermined index and a target feature based on an index experimental value for the predetermined index and a target feature for each subject in the reference subject set.

4. 3. The method of claim 2, Obtaining a reference subject set by screening based on the first subject set includes: obtaining a current score set, the current score set including a current score corresponding to each type of amino acid; obtaining a second protein set based on the first object set, and selecting a target protein from the second protein set based on a current score set; decrementing the current scores corresponding to the amino acids at each mutation position in the target protein in the current score set and transferring the target protein from the second protein set to the first protein set; and the method includes a step of returning to and continuing with the step of selecting a target protein from the second protein set based on the current score set when the current score set indicates that the first protein set does not satisfy "the condition that each type of amino acid occurs at least the target number of times at each mutation position," and a step of determining the first protein set as a reference set when the current score set indicates that the first protein set satisfies "the condition that each type of amino acid occurs at least the target number of times at each mutation position."

5. 5. The method of claim 4, The step of obtaining the current score set includes: obtaining an initial score set, the initial scores corresponding to each type of amino acid in the initial score set being a target number; and The method includes a step of decreasing an initial score corresponding to each amino acid at each mutation position in the wild-type protein in the initial score set to obtain a current score set, and determining a first protein set based on the wild-type protein, wherein the wild-type protein is a protein in which no mutations occur.

6. 5. The method of claim 4, Selecting a target protein from the second protein set based on the current score set includes: determining, for each mutant protein in said second set of proteins, a current score from a set of current scores corresponding to the amino acid at each mutation position in said mutant protein; determining a current protein score for the mutant protein based on each of the obtained current scores; and Obtaining a target protein by screening from said second protein set based on the current protein score.

7. 7. The method of claim 6, each type of amino acid has a corresponding amino acid, and the scores in the current score set are uniquely labeled with the amino acid and the mutation position; determining from the set of current scores a current score corresponding to each amino acid at each mutation position in the mutant protein, For each amino acid at the mutation position, determining a current score corresponding to the amino acid at the mutation position from a current score set based on the amino acid corresponding to the amino acid and the mutation position.

8. 4. The method of claim 3, the feature of interest is a protein feature; The step of determining an object characteristic of each object in the reference object set based on an index experimental value for the predetermined index of each object in the reference object set includes: for each mutation position, dividing the reference object set according to the type of amino acid at the mutation position to obtain a first sub-object set respectively corresponding to each type of amino acid; For each type of amino acid at each of the mutation positions, determining an amino acid signature at the mutation position of the amino acid based on the index experimental value of each subject in the first sub-subject set corresponding to the amino acid; and obtaining a protein signature for the subject based on an amino acid signature of the amino acid at each mutation position in the subject.

9. 9. The method of claim 8, Determining an amino acid signature at the mutation position of the amino acid based on an index experimental value of each subject in the first sub-subject set corresponding to the amino acid, performing a statistical calculation on the index experimental value of each subject in the first sub-subject set corresponding to the amino acid to obtain at least one index experimental statistical value; and determining an amino acid signature at said mutation position of said amino acid based on said at least one indicative experimental statistic.

10. 10. The method of claim 9, The step of calculating statistics for the index experimental value of each subject in the first sub-subject set corresponding to the amino acid to obtain at least one index experimental statistical value includes: calculating an average value for the index experimental value of each subject in the first sub-subject set corresponding to the amino acid to obtain a first index average value; and determining a maximum index experimental value from the index experimental values ​​of each subject in the first sub-subject set corresponding to the amino acid and obtaining it as a first index maximum, wherein the at least one index experimental statistical value comprises at least one of the first index average value or the first index maximum value.

11. 11. The method of claim 10, Determining an amino acid signature at the mutation position of the amino acid based on the at least one indicative experimental statistic comprises: forming an amino acid signature for the amino acid at the mutation position by the first index average value and the first index maximum value.

12. 4. The method of claim 3, the feature of interest is a protein feature; The step of determining an object characteristic of each object in the reference object set based on an index experimental value for the predetermined index of each object in the reference object set includes: for each type of amino acid, determining a target of said amino acid from said reference target set that is included in the amino acid at the mutation position, and obtaining a second sub-target set corresponding to said amino acid; For each type of amino acid, determining an amino acid signature for the amino acid based on the index experimental value of each subject in the second sub-subject set corresponding to the amino acid; and obtaining a protein signature for the subject based on an amino acid signature of the amino acid at each mutation position in the subject.

13. 4. The method of claim 3, The step of determining a target object that satisfies the index requirement of the predetermined index from the second object set based on the mapping relationship includes: determining a statistical index value for a target statistical index of each object in the second object set based on the mapping relationship, and determining a selection object from the second object set based on the statistical index value; adding the selected object to a reference object set if the iteration stopping condition is not satisfied; Returning to the step of determining the object features of each object in the reference object set based on the index experimental value for the predetermined index of each object in the reference object set, and continuing the iteration until a stopping condition is satisfied; and The method includes a step of determining a selected object obtained when an iteration stopping condition is satisfied as a target object that satisfies an index requirement of the predetermined index.

14. An apparatus for determining an object, comprising: a prediction value obtaining module for obtaining an index prediction value for each of the predetermined indexes of each of the objects in the first object set, the index prediction value being a value for the predetermined index of the object predicted by a pre-trained model; an object set obtaining module for screening objects whose index prediction values ​​satisfy an index value screening condition from the first object set to obtain a second object set; A mapping relationship determination module for determining a mapping relationship between a predetermined index and an object feature based on an index experimental value for the predetermined index and an object feature of a plurality of objects in the first object set, wherein the index experimental value refers to an object value for the predetermined index obtained by an experiment; and and a target object determination module for determining target objects from the second object set that meet index requirements of the predetermined index based on the mapping relationship.

15. A computing device including a memory and a processor coupled to the memory, The storage device stores a computer program, A computing device, the processor being configured to execute the computer program to implement the method of any one of claims 1 to 13.

16. A program for causing a computer to execute the method according to any one of claims 1 to 13.

Citation Information

Patent Citations

  • Novel protein molecular orientation evolvement method

    CN101353372A

  • Method of acquiring proteins with high affinity by computer aided design

    CN102511045A

  • Protein prediction model generation method, device and equipment and storage medium

    CN111048145A

  • Cyclic peptide design method, compound structure generation method, device and electronic equipment

    CN114333985A

  • Method and electronic system for predicting at least one fitness value of a protein, related computer program product

    EP3082056A1