Antibody modification method, device, equipment and storage medium
By receiving the antibody sequence to be modified and obtaining multiple antibody template sequences, selecting the appropriate template based on the consistency information for modification, solving the problem of inaccurate selection of antibody templates and improving the efficiency and effect of antibody modification.
Patent Information
- Application Number
- CN202410243159.X
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-03-01
- Publication Date
- 2024-11-22
AI Technical Summary
The existing antibody modification methods have inaccuracies when selecting antibody templates, resulting in low efficiency and unsatisfactory results.
By receiving the antibody sequence to be modified, multiple antibody template sequences are obtained, and appropriate template sequences are selected based on the consistency information for modification, including CDR transplantation and recovery mutations, improving the selection accuracy and modification efficiency of antibody templates.
The selection accuracy and transformation efficiency of antibody templates are improved, and the accuracy and effect of antibody transformation are improved.
Smart Images

Figure CN119007800A_ABST
Abstract
Description
Technical Field
[0001] The embodiments of the present application relate to the field of computer technology, and in particular to an antibody modification method, device, equipment and storage medium. Background Art
[0002] Antibodies are a class of immunoglobulins that can specifically bind to antigens. As an important component of the immune system, they play an important role in the prevention and treatment of many diseases. Antibody modification is the modification of amino acids in the antibody sequence to obtain antibodies with different characteristics. For example, antibody humanization modification refers to the humanization of mouse antibodies, which reduces the immunogenicity of the antibody while maintaining its ability to bind to the antigen target.
[0003] In current antibody modification methods, such as the process of antibody humanization, a human antibody template is first selected, and the CDR of the human antibody template is modified using a mouse antibody sequence, and then some positions are reversely mutated to select a suitable antibody sequence. However, in current antibody modification methods, when selecting an antibody template, there is an inaccurate selection of the antibody template, which leads to low antibody modification efficiency and unsatisfactory modification effect. Summary of the invention
[0004] The present application provides an antibody modification method, device, equipment and storage medium, which can improve the selection accuracy of antibody templates, thereby improving the modification efficiency and modification effect of antibodies.
[0005] In a first aspect, the present application provides an antibody modification method, comprising:
[0006] Receive a first species antibody sequence to be modified input by a subject, and obtain N second species antibody template sequences for modifying the first species antibody sequence, where N is a positive integer;
[0007] Determine the consistency information between the N second species antibody template sequences and the first species antibody sequence on M different indicators, where M is a positive integer;
[0008] Based on the consistency information between the N second species antibody template sequences and the first species antibody sequence on M different indicators, P second species antibody template sequences are selected from the N second species antibody template sequences, where P is a positive integer less than or equal to N;
[0009] Based on the P second species antibody template sequences, the first species antibody sequence is modified to obtain a modified target antibody sequence, wherein the modification is used to recombine some amino acids of the first species antibody template sequence with some amino acids of the second species antibody sequence.
[0010] In a second aspect, the present application provides an antibody modification device, comprising:
[0011] an acquisition unit, configured to receive a first species antibody sequence to be modified input by a subject, and to acquire N second species antibody template sequences for modifying the first species antibody sequence, wherein N is a positive integer;
[0012] a consistency determination unit, configured to determine consistency information between the N second species antibody template sequences and the first species antibody sequence on M different indicators, where M is a positive integer;
[0013] a template selection unit, configured to select P second species antibody template sequences from the N second species antibody template sequences based on consistency information between the N second species antibody template sequences and the first species antibody sequence on M different indicators, wherein P is a positive integer less than or equal to N;
[0014] A transformation unit is used to transform the first species antibody sequence based on the P second species antibody template sequences to obtain a transformed target antibody sequence, wherein the transformation is used to recombine some amino acids of the first species antibody template sequence with some amino acids of the second species antibody sequence.
[0015] In some embodiments, the consistency determination unit is specifically used to obtain a first antibody sequence numbering method, and use the first antibody sequence numbering method to number the amino acids included in the first species antibody sequence and the N second species antibody template sequences; extract the basic information of the numbered first species antibody sequence, and the basic information of the numbered N second species antibody template sequences; for the i-th second species antibody template sequence among the N second species antibody template sequences, based on the basic information of the first species antibody sequence and the basic information of the i-th second species antibody template sequence, determine the consistency information of the first species antibody sequence and the i-th second species antibody template sequence on the M different indicators, where i is a positive integer less than or equal to N.
[0016] In some embodiments, if the basic information includes at least one of an antibody initial sequence, a framework sequence, and key residues, and the M different indicators include at least one of a full sequence, a framework sequence, and key residues, the consistency determination unit is specifically configured to perform a full sequence comparison of the antibody initial sequence of the first species antibody sequence with the antibody initial sequence of the i-th second species antibody template sequence to determine the full sequence consistency information between the first species antibody sequence and the i-th second species antibody template sequence; compare the key residues of the first species antibody sequence with the key residues of the i-th second species antibody template sequence to determine the key residue consistency information between the first species antibody sequence and the i-th second species antibody template sequence; compare the framework sequence of the first species antibody sequence with the framework sequence of the i-th second species antibody template sequence to determine the framework sequence consistency information between the first species antibody sequence and the i-th second species antibody template sequence.
[0017] In some embodiments, the template selection unit is specifically used to display the consistency information of the N second species antibody template sequences and the first species antibody sequence on the M different indicators; in response to the object's selection operation of the P second species antibody template sequences among the N second species antibody template sequences based on the consistency information, the P second species antibody template sequences are selected.
[0018] In some embodiments, the transformation unit is specifically used to perform CDR transplantation on the jth second species antibody template sequence among the P second species antibody template sequences using the first species antibody sequence to obtain the jth antibody template sequence after transplantation, where j is a positive integer less than or equal to P; perform back mutation transformation on the jth antibody template sequence after transplantation to obtain Q candidate back mutation sequences, where Q is a positive integer; perform a first evaluation on each of the Q candidate back mutation sequences to obtain first evaluation information of each candidate back mutation list; based on the first evaluation information of the Q candidate back mutation sequences, select R candidate back mutation sequences from the Q candidate back mutation sequences, where R is a positive integer less than or equal to Q; based on the R candidate back mutation sequences, generate the jth target back mutation sequence, where the jth target back mutation sequence includes the mutated residues of the R candidate back mutation sequences; based on the P target back mutation sequences corresponding to the P second species antibody template sequences, obtain the transformed target antibody sequence.
[0019] In some embodiments, the transformation unit is specifically used to perform a second evaluation on the j-th antibody template sequence after transplantation to obtain second evaluation information of the j-th antibody template sequence after transplantation; if it is determined based on the second evaluation information that the j-th antibody template sequence after transplantation should continue to be transformed, then the j-th antibody template sequence after transplantation is subjected to a back mutation transformation to obtain Q candidate back mutation sequences.
[0020] In some embodiments, the first evaluation information includes the recommendation degree of the candidate back mutation sequence, and the transformation unit is specifically used to determine, for each of the Q candidate back mutation sequences, change information of the mutated residues in the candidate back mutation sequence before and after mutation on K indicators, wherein the K indicators include at least one of statistical frequency, residue type, key residue type, three-dimensional structure position and interaction, and K is a positive integer; based on the change information of the mutated residues in the candidate back mutation sequence before and after mutation on the K indicators, determine the recommendation degree of the candidate back mutation sequence.
[0021] In some embodiments, the transformation unit is specifically used to input the change information of the mutated residues in the candidate back mutation sequence on the K indicators before and after the mutation into the recommendation degree prediction model to obtain the recommendation degree of the candidate back mutation sequence.
[0022] In some embodiments, the first evaluation information includes rapid evaluation information of the candidate back mutation sequence, and the transformation unit is specifically used to quickly evaluate the mutated residues in the candidate back mutation sequence for each of the Q candidate back mutation sequences to obtain the rapid evaluation information of the candidate back mutation sequence.
[0023] In some embodiments, the rapid assessment information of the candidate back mutation sequence includes at least one of: mutation score, sequence position information, three-dimensional structure position information, humanization assessment and thermal stability.
[0024] In some embodiments, the transformation unit is specifically used to obtain an antibody transformation method, which includes a non-automatic transformation method and an automatic transformation method; if the antibody transformation method is the non-automatic transformation method, the first evaluation information of the Q candidate back mutation sequences is displayed, and the object receives a selection operation of the R candidate back mutation sequences among the Q candidate back mutation sequences based on the first evaluation information, and selects the R candidate back mutation sequences; if the antibody transformation method is the automatic transformation method, R candidate back mutation sequences whose first evaluation information meets the preset requirements are selected from the Q candidate back mutation sequences.
[0025] In some embodiments, the first evaluation information includes the recommendation level of the candidate back mutation sequence, and the transformation unit is specifically used to display the recommendation levels of the Q candidate back mutation sequences in grades based on the display formats corresponding to the preset different levels of recommendation levels.
[0026] In some embodiments, the transformation unit is specifically used to perform a second evaluation on each of the P target back mutation sequences to obtain second evaluation information of each target back mutation sequence; based on the second evaluation information of the P target back mutation sequences, determine the transformed target antibody sequence.
[0027] In some embodiments, the transformation unit is specifically used to display second evaluation information of the target back mutation sequence; in response to the transformation operation input by the subject based on the second evaluation information, the transformed target antibody sequence is obtained, and the transformation operation is used to indicate whether to continue to transform the target back mutation sequence.
[0028] In some embodiments, the transformation unit is specifically used to perform statistical distribution analysis on each evaluation indicator in the second evaluation information of the patent antibody data to obtain a reference threshold value for each evaluation indicator; compare each evaluation indicator in the second evaluation information of the target reverse mutation sequence with the corresponding reference threshold value to determine the display format of the numerical value of the evaluation indicator in the second evaluation information of the target reverse mutation sequence; based on the display format, display each evaluation indicator in the second evaluation information of the target reverse mutation sequence in a graded manner.
[0029] In some embodiments, the second evaluation information includes at least one of sequence evaluation information, structure evaluation information, and feasibility evaluation information of the antibody sequence.
[0030] In some embodiments, the transformation unit is further used to display the transformation information corresponding to the j-th second species antibody template sequence, wherein the transformation information includes the first species antibody sequence, the j-th second species antibody template sequence after transplantation and the j-th target back mutation sequence, and at least one of the humanization scores and structural consistency scores corresponding to the first species antibody sequence, the j-th second species antibody template sequence after transplantation and the j-th target back mutation sequence, respectively.
[0031] In some embodiments, the N second species antibody template series include template sequences of multiple antibody subfamilies, and second species antibody template series in patent antibody data.
[0032] In a third aspect, the present application provides an electronic device, comprising a processor and a memory, wherein the memory is used to store a computer program, and the processor is used to call and run the computer program stored in the memory to execute the method of the first aspect.
[0033] In a fourth aspect, a chip is provided for implementing the method in each implementation of the first aspect. Specifically, the chip includes: a processor for calling and running a computer program from a memory so that a device equipped with the chip executes the method in the first aspect.
[0034] In a fifth aspect, a computer-readable storage medium is provided for storing a computer program, wherein the computer program enables a computer to execute the method of the first aspect.
[0035] In a sixth aspect, a computer program product is provided, comprising computer program instructions, wherein the computer program instructions enable a computer to execute the method of the first aspect.
[0036] In a seventh aspect, a computer program is provided, which, when executed on a computer, enables the computer to execute the method of the first aspect.
[0037] In summary, the present application receives the first species antibody sequence input by the object, and determines the consistency information of the N second species antibody template sequences included in the template database with the first species antibody sequence on M different indicators. Then, based on the consistency information of the N second species antibody template sequences with the first species antibody sequence on M different indicators, P second species antibody template sequences are selected from the N second species antibody template sequences, and then based on the P second species antibody template sequences, the first species antibody sequence is transformed to obtain the transformed target antibody sequence. It can be seen from this that when the template is selected, the second species antibody template sequence and the first species antibody sequence are judged for consistency on M different indicators, thereby improving the selection accuracy of the second species antibody template sequence, so that when the first species antibody sequence is transformed based on the accurately selected second species antibody model sequence, the final transformed target antibody sequence can be obtained after a few rounds of transformation, which improves the transformation efficiency and transformation effect of the antibody, and the antibody transformation process is evaluated multiple times, which can achieve the accuracy of antibody transformation. BRIEF DESCRIPTION OF THE DRAWINGS
[0038] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.
[0039] Figure 1 A schematic diagram of an implementation environment of an antibody modification method provided in an embodiment of the present application;
[0040] Figure 2 A schematic diagram of a process for antibody modification provided in one embodiment of the present application;
[0041] Figure 3 An example diagram for consistency determination;
[0042] Figure 4 A specific schematic diagram determined for consistency;
[0043] Figure 5 A schematic diagram of antibody modification;
[0044] Figure 6 A schematic diagram for determining the degree of recommendation;
[0045] Figure 7 A schematic diagram for the second assessment;
[0046] Figure 8 A specific schematic diagram of the second assessment;
[0047] Fig. 9 A schematic diagram of the antibody modification method provided in one embodiment of the present application;
[0048] Fig.10 A schematic diagram of the antibody modification process;
[0049] Fig.11 A schematic diagram of the evaluation results of the humanization score for antibody humanization;
[0050] Fig.12 is a schematic block diagram of an antibody modification device provided in one embodiment of the present application;
[0051] Fig.13 It is a schematic block diagram of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION
[0052] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of this application.
[0053] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present application described here can be implemented in an order other than those illustrated or described here. In an embodiment of the present invention, "B corresponding to A" means that B is associated with A. In one implementation, B can be determined according to A. However, it should also be understood that determining B according to A does not mean that B is determined only according to A, but B can also be determined according to A and / or other information. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or server that includes a series of steps or units does not have to be limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices. In the description of the present application, unless otherwise specified, "multiple" refers to two or more than two.
[0054] The antibody modification method provided in the embodiments of the present application can be applied to various fields such as artificial intelligence, biopharmaceuticals, antibody engineering, and medicine, and can improve the accuracy of selecting the second species antibody template sequence during the antibody modification process, thereby improving the effect of antibody modification.
[0055] In order to facilitate understanding of the embodiments of the present application, the relevant concepts involved in the embodiments of the present application are first introduced:
[0056] Artificial Intelligence (AI) is the theory, method, technology and application system that uses digital computers or machines controlled by digital computers to simulate, extend and expand human intelligence, perceive the environment, acquire knowledge and use knowledge to obtain the best results. In other words, artificial intelligence is a comprehensive technology in computer science that attempts to understand the essence of intelligence and produce a new intelligent machine that can respond in a similar way to human intelligence. Artificial intelligence is to study the design principles and implementation methods of various intelligent machines so that machines have the functions of perception, reasoning and decision-making.
[0057] Artificial intelligence technology is a comprehensive discipline that covers a wide range of fields, including both hardware-level and software-level technologies. The basic technologies of artificial intelligence generally include sensors, dedicated artificial intelligence chips, cloud computing, distributed storage, big data processing technology, operation / interaction systems, mechatronics and other technologies. Artificial intelligence software technology mainly includes computer vision technology, speech processing technology, natural language processing technology, and machine learning / deep learning.
[0058] With the research and advancement of artificial intelligence technology, artificial intelligence technology has been studied and applied in many fields, such as common smart homes, smart wearable devices, virtual assistants, smart speakers, smart marketing, unmanned driving, automatic driving, drones, robots, smart medical care, smart customer service, etc. I believe that with the development of technology, artificial intelligence technology will be applied in more fields and play an increasingly important role.
[0059] In the examples of the present application, artificial intelligence technology is applied to antibody modification to achieve rapid and effective modification of antibodies.
[0060] Antibodies are a type of immunoglobulin that can specifically bind to antigens. The antibody sequence is composed of four polypeptide chains. Among these four heterologous polypeptide chains, the two chains with larger molecular weight are called heavy chains (heavy chain, referred to as H), and the two chains with smaller molecular weight are called light chains (Light chain, referred to as L). The region near the N-terminus of the light chain and heavy chain where the amino acid sequence changes greatly is called the variable region (variable region, referred to as V), accounting for 1 / 4 and 1 / 2 of the heavy chain and light chain respectively. The region near the C-terminus where the amino acid sequence is relatively stable is called the constant region (constant region, referred to as C), accounting for 3 / 4 and 1 / 2 of the heavy chain and light chain respectively. The V region of the heavy chain and light chain is called VH and VL respectively.
[0061] Complementarity determining region (CDR): Located in the variable region of an antibody, it is the place where the antigen and antibody come into contact, so it is also called the antigen binding site, or the hypervariable region (HVR). The amino acid sequence of the variable region of an antibody has three CDRs (CDR1, CDR2, and CDR3), which are non-continuous and distributed on two polypeptide chains (light chain and heavy chain).
[0062] Framework region (FR): Located in the variable region of the antibody, it is the part that supports the CDR conformation. There are four FRs on each peptide chain, which are represented by FR1, FR2, FR3 and FR4 respectively.
[0063] CDR transplantation: The CDR sequence in the variable region of the mouse antibody sequence is used to replace the corresponding CDR sequence in the human antibody sequence that is most similar to its own framework region (FR).
[0064] Antibody immunogenicity: refers to the property of an antibody drug that can act on the antigen recognition receptors of T cells and B cells in the immune system, thereby inducing the body to produce humoral and / or cell-mediated immune responses, producing anti-drug antibodies (Anti-Drug Antibody, abbreviated as ADA) reactions, thereby reducing the efficacy of the antibody and producing adverse reactions.
[0065] Antibody humanization: Humanization of mouse antibodies reduces the immunogenicity of the antibodies while maintaining their ability to bind to antigen targets.
[0066] The current antibody modification methods, such as antibody humanization modification, mainly include two methods. The first is the traditional CDR transplantation method, and the second is the humanization modification method based on deep learning. In the traditional CDR transplantation method, a human antibody template is first selected, and the mouse antibody sequence is used to perform CDR modification on the human antibody template, and then some positions are reversely mutated to select a suitable antibody sequence. In the humanization modification method based on deep learning, the residues at each position of the entire mouse antibody sequence and their surrounding environment are encoded and learned to obtain an embedded representation of each position, and a candidate residue list and score are generated for each position. The mutant residue with the highest score is selected for replacement, and the replacement is stopped after reaching the specified iteration round or score threshold. However, in the traditional CDR transplantation method, there is a problem of inaccurate selection when selecting a human antibody template. In the humanization modification method based on deep learning, the mutation modification accuracy is inaccurate because the mouse antibody sequence is directly modified without considering the human antibody template or considering a small number of human antibody templates. It can be seen from this that in the current antibody modification process, the subsequent antibody modification effect is not ideal due to the inaccurate selection of antibody templates.
[0067] In order to solve the above technical problems, the embodiment of the present application receives the first species antibody sequence input by the object during antibody transformation, and determines the consistency information of the N second species antibody template sequences included in the template database with the first species antibody sequence on M different indicators. Then, based on the consistency information of the N second species antibody template sequences with the first species antibody sequence on M different indicators, P second species antibody template sequences are selected from the N second species antibody template sequences, and then based on the P second species antibody template sequences, the first species antibody sequence is transformed to obtain the transformed target antibody sequence. It can be seen from this that when the template is selected, the embodiment of the present application judges the consistency of the second species antibody template sequence and the first species antibody sequence on M different indicators, thereby improving the selection accuracy of the second species antibody template sequence, so that when the first species antibody sequence is transformed based on the accurately selected second species antibody model sequence, the final transformed target antibody sequence can be obtained after a few rounds of transformation, which improves the transformation efficiency and transformation effect of the antibody, and the antibody transformation process is evaluated multiple times, which can achieve the accuracy of antibody transformation.
[0068] The implementation environment of the embodiments of the present application is introduced below.
[0069] Figure 1 A schematic diagram of an implementation environment for antibody modification provided in an embodiment of the present application, such as Figure 1 As shown, the implementation environment includes: a terminal device 101 and a server 102.
[0070] The terminal device 101 is connected to the server 102 via a wired or wireless connection.
[0071] In the embodiment of the present application, the client of the antibody modification system is installed on the terminal device 101, and the server 102 can be understood as the server or backend of the antibody modification program. The object (such as a user) can interact with the client of the antibody modification system installed on the terminal device 101. The server 102 stores multiple second species antibody template sequences.
[0072] In some embodiments, the antibody modification method provided in the embodiment of the present application is performed by the terminal device 101. At this time, the terminal device 101 can be any terminal device that can provide antibody modification services. The server 102 can be any server that can provide data download services. In one example, the server 102 stores multiple second species antibody template sequences, for example, stores N second species antibody template sequences, and the terminal device 101 is installed with a client of the antibody modification system, which can request N second species antibody template sequences from the server 102 based on the request of the object. Further, the object can input the first species antibody sequence to be modified in the client. The client responds to the first species antibody sequence to be modified input by the object, and the N second species antibody template sequences obtained from the server 102 for modifying the first species antibody sequence, and the first species antibody sequence is modified. For example, the terminal device 101 determines the consistency information of the N second species antibody template sequences with the first species antibody sequence on M different indicators, for example, determines the consistency information of the N second species antibody template sequences with the first species antibody sequence on the full sequence, framework sequence and key residues. Next, the terminal device 101 selects P second species antibody template sequences from the N second species antibody template sequences based on the consistency information of the N second species antibody template sequences and the first species antibody sequences on M different indicators, and then transforms the first species antibody sequence based on the P second species antibody template sequences to improve the selection accuracy of the second species antibody template sequence, thereby improving the efficiency and effect of antibody transformation. At the same time, multiple evaluations are performed in the process of transforming the first species antibody sequence based on the P second species antibody template sequences, and the transformed target antibody sequence is obtained based on the evaluation results. Optionally, in order to improve the interactivity in the antibody transformation process, the terminal device 101 displays the evaluation results in the antibody transformation process in the embodiment of the present application, so that the object selects the required transformation path based on the evaluation results for transformation to obtain the transformation result that meets the requirements of the object, thereby improving the personalized needs of antibody transformation.
[0073] In some embodiments, the antibody modification method provided in the embodiments of the present application is jointly performed by the terminal device 101 and the server 102. For example, the object starts the client of the antibody modification system on the terminal device 101, and the client displays the input interface of the antibody to be modified, and the object enters the first species antibody sequence to be modified in the input interface. At the same time, the object can also enter the modification target on the client, for example, the input modification target is humanization modification, so that the terminal device 101 can send the first species antibody sequence and the modification target to the server 102. Based on the modification target sent by the terminal device 101, the server 102 queries the N second species antibody template sequences used to modify the first species antibody sequence in the template database, and then the server 102 can determine the consistency information of the N second species antibody template sequences with the first species antibody sequence on M different indicators, for example, determine the consistency information of the N second species antibody template sequences with the first species antibody sequence in the full sequence, framework region sequence and key residues. Next, the server 102 selects P second species antibody template sequences from the N second species antibody template sequences based on the consistency information of the N second species antibody template sequences and the first species antibody sequences on M different indicators, and then transforms the first species antibody sequence based on the P second species antibody template sequences. At the same time, the server 102 performs multiple evaluations in the process of transforming the first species antibody sequence based on the P second species antibody template sequences, and obtains the transformed target antibody sequence based on the evaluation results. Optionally, in order to improve the interactivity during the antibody transformation process, the server 102 sends the evaluation results during the antibody transformation process to the terminal device 101 for display, so that the object selects the required transformation path based on the evaluation results for transformation, so as to obtain the transformation result that meets the requirements of the object, thereby improving the personalized needs of antibody transformation.
[0074] In some embodiments, the terminal device 101 includes but is not limited to: desktop computers, laptop computers, smart phones, tablet computers, IoT devices, and portable wearable devices. IoT devices can be smart speakers, smart TVs, smart air conditioners, smart car devices, etc. Portable wearable devices can be smart watches, smart bracelets, head-mounted devices, etc. Terminal devices are often equipped with display devices, which can also be displays, display screens, touch screens, etc., and touch screens can also be touch screens, touch panels, etc.
[0075] In some embodiments, the server 102 may be one or more servers. When there are multiple servers, there are at least two servers for providing different services, and / or there are at least two servers for providing the same service, such as providing the same service in a load balancing manner, which is not limited in the embodiments of the present application. Among them, the server may be an independent physical server, or a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, CDN (Content Delivery Network), and big data and artificial intelligence platforms. The server can also become a node of the blockchain.
[0076] It should be noted that the implementation environment of the embodiments of the present application includes but is not limited to Figure 1 shown.
[0077] The technical solutions of the embodiments of the present application are described in detail below through some embodiments. The following embodiments can be combined with each other, and the same or similar concepts or processes may not be repeated in some embodiments.
[0078] Figure 2 This is a flow chart of an antibody modification method provided in one embodiment of the present application. The execution subject of the embodiment of the present application can be a device with an antibody modification function, such as an antibody modification device. The antibody modification device can be the above Figure 1 The server 102 or terminal device 101 shown may also be Figure 1 The system is composed of the server 102 or 101 shown. For the convenience of description, the following embodiments take electronic devices as an example to illustrate the method of the embodiments of the present application.
[0079] like Figure 2 As shown, the antibody modification method of the embodiment of the present application includes:
[0080] S101, receiving a first species antibody sequence to be modified input by a subject, and obtaining N second species antibody template sequences used for modifying the first species antibody sequence.
[0081] Wherein, N is a positive integer.
[0082] It should be noted that the data used in the embodiments of the present application and the process of obtaining these data are in compliance with the provisions of relevant laws and regulations.
[0083] The antibody modification method of the embodiment of the present application can be used in the antibody modification of any type of species, for example, it can be applied to the antibody modification of two different species, and can also be applied to the antibody modification process of the same species, and the embodiment of the present application does not limit this.
[0084] The embodiments of the present application do not limit the specific types of the first species antibody sequence and the second species antibody template sequence.
[0085] In one example, the first species and the second species are different species. For example, when the antibody modification method of the embodiment of the present application is applied to humanized antibody modification, the first species antibody sequence can be a mouse antibody sequence or an antibody sequence of other animals, and the second species antibody template sequence can be a human antibody template sequence.
[0086] For example, if the antibody modification method of the embodiment of the present application is applied to antibody humanization, it can be applied to the antibody biopharmaceutical research and development process, for example, to humanize mouse antibodies, while retaining the affinity of mouse antibodies, humanize the mouse components on their surface, thereby enhancing their potential to become candidate antibody drugs.
[0087] In one example, the first species and the second species may be the same species, but the first species antibody sequence and the second species antibody template sequence are not completely the same. In other words, the first species antibody sequence and the second species antibody template sequence may be two different antibody sequences of the same species.
[0088] In the present embodiment, if the subject needs to undergo antibody modification, the first species antibody sequence to be modified is input. The present embodiment does not limit the specific method of obtaining the first species antibody sequence to be modified.
[0089] In a possible implementation, if the antibody modification method of the present application embodiment is Figure 1 When the terminal device in is completed, the object inputs the first species antibody sequence file to be transformed on the client of the antibody transformation system of the terminal device.
[0090] In a possible implementation, if the antibody modification method of the present application embodiment is Figure 1 When the server in is completed, the subject inputs the first species antibody sequence file to be transformed on the client of the antibody transformation system of the terminal device. Then, the terminal device sends the first species antibody sequence input by the subject to the server.
[0091] In the embodiment of the present application, the subject inputs the first species antibody sequence in the client of the antibody modification system installed on the terminal device in at least the following ways:
[0092] Mode 1: The client includes an input box for the antibody to be modified, and the subject can input the first species antibody sequence in the input box. For example, the subject triggers the input box for the antibody to be modified, and displays a file upload interface. The subject can drag the first species antibody sequence file to be modified to the upload interface to input the first species antibody sequence.
[0093] Mode 2: The subject can perform related operations by inputting a command line on the client. For example, the subject inputs a command line of the first species antibody sequence file to be modified on the client to complete the input of the first species antibody sequence.
[0094] In some embodiments, in addition to inputting the first species antibody sequence on the client, the object also needs to input task configuration information. The task configuration information can be understood as the configuration of various parameters required when the first species antibody sequence is transformed. In an embodiment of the present application, the method for the object to input the task configuration parameters can be the same as the above-mentioned method of inputting the first species antibody sequence. For example, enter the task configuration parameters in the corresponding input box of the client, or enter the task configuration parameters by means of a command line. Of course, the object can also enter the task configuration information of this antibody transformation in other ways.
[0095] In one example, the task configuration parameters also include indication information of the transformation target of the first species antibody sequence, that is, indicating the antibody sequence with what characteristics the first species antibody sequence is to be transformed into. In this way, the electronic device can obtain N second species antibody template sequences for transforming the first species antibody sequence based on the indication information of the transformation target.
[0096] For example, the first species antibody sequence is a non-human animal antibody sequence (e.g., a mouse antibody sequence), and the modification target of the first species antibody sequence is humanization modification. In this case, the second species antibody template sequence can be determined to be a human antibody template sequence. In this way, the electronic device can obtain N human antibody template sequences for modifying the first species antibody sequence.
[0097] In some embodiments, the task configuration information of the embodiments of the present application also includes specifying antibody sequence encoding tools and encoding schemes, CDR region definition schemes, thresholds for humanized evaluation indicators, setting parameters for automated tasks, and general parameters for evaluation indicators.
[0098] In an example, the task configuration information of the embodiment of the present application is shown in Table 1:
[0099] Table 1
[0100]
[0101] Among them, project_name: represents the name of this antibody modification project, for example, demo_task (demonstration task);
[0102] number_tool: tool used for antibody sequence numbering, such as anarci, where anarci is a sequence numbering tool;
[0103] scheme_type: antibody numbering system, such as kabat, where kabat is an antibody numbering system;
[0104] cdr_definition: definition of CDR, for example, definition of CDR according to the provisions of the International Immunogenetics Information System (imgt);
[0105] Humanity threshold: indicates the humanness threshold, including loose, relaxed, medium, and strict thresholds;
[0106] oasis_min_subject_set: relaxed, indicating that the humanized threshold selection in oasis antibody modification is relaxed;
[0107] common task config: represents the automated task configuration;
[0108] humanize_cdrs:false means that human cdrs will not be transformed;
[0109] auto_optim:true: means that subsequent transformation is automatically performed in automatic mode;
[0110] CDR RMSD only considers the same residue: means that only the same residues are considered in the calculation process of CDR RMSD;
[0111] rmsd_only_same_res:true: When the rmsd_only_same_res field is set to true, it means that only the same residues are considered in the calculation of CDR RMSD during this antibody modification process.
[0112] evaluate set represents the evaluation unit;
[0113] sasa_threshold: indicates the SASA threshold, for example, the SASA threshold is 0.3. SASA (solvent accessible surface area) refers to the solvent accessible surface area, which is an important parameter to describe the solvation characteristics of a molecule. If SASA is greater than 0.3, it means that the residue is exposed outside the antibody.
[0114] if_skip_complex_calc: Indicates whether to skip complex evaluation.
[0115] It should be noted that the task configuration information shown in Table 1 above is only an example. The task configuration information of the embodiment of the present application may include more or less configuration information than Table 1, or configuration information different from Table 1, and the embodiment of the present application does not limit this.
[0116] In an embodiment of the present application, after the subject inputs the first species antibody sequence to be modified and the task configuration information, the electronic device can obtain N second species antibody template sequences for modifying the first species antibody sequence, and modify the first species antibody sequence based on the task configuration information and the N second species antibody template sequences.
[0117] In some embodiments, in order to improve the effect of antibody modification, the N second species antibody template sequences of the embodiments of the present application include template sequences of multiple antibody subfamilies, and the second species antibody template series in the patent antibody data. For example, when the second species antibody template sequence is a human antibody template sequence, the electronic device can obtain N human antibody template sequences from the human gene antibody sequence library, the human antibody sequence library, the human template sequences of multiple antibody subfamilies, and the human antibody template series in the patent antibody data. In this way, the diversity of the N second species antibody template sequences can be increased, so that when the first species antibody sequence is modified based on the diverse N second species antibody template sequences, the diversity of the modification can be increased, thereby improving the modification effect of the antibody modification.
[0118] S102, determining consistency information between N second species antibody template sequences and the first species antibody sequence on M different indicators.
[0119] Wherein, M is a positive integer.
[0120] In the present application example, when selecting a template sequence that is ultimately used to transform the first species antibody sequence from N second species antibody template sequences, such as Figure 3As shown, each of the N second species antibody template sequences is matched with the first species antibody sequence on M different indicators, thereby improving the accuracy of template sequence selection. In this way, when subsequent modification is performed based on the accurately selected template sequence, not only can the modification effect of the first species antibody sequence be improved, but also the modification of the first species antibody sequence can be completed after a few rounds of modification, which can improve the efficiency of antibody modification.
[0121] The specific process of determining the consistency information between N second species antibody template sequences and the first species antibody sequence on M different indicators is introduced below.
[0122] In the embodiment of the present application, there is no specific limitation on the M different indicators, which can be understood as M different dimensions or M different aspects.
[0123] The antibody sequence includes a variable region, a constant region, and the variable region includes a CDR region and a framework region (also referred to as a skeleton region). The constant region and the variable region include multiple amino acid residues, and these amino acid residues include key amino acids. In some embodiments, M different characteristic information in the above-mentioned structural characteristic information of the antibody sequence can be used as M different indicators.
[0124] In one example, the above-mentioned M different indicators include at least one of the full sequence, framework region sequence and key residues. It should be noted that the M different indicators in the embodiment of the present application include at least one of the full sequence, framework region sequence and key residues, and may also include other indicators, such as constant region sequence, that is, determining the consistency of the constant region sequence of the second species antibody template sequence with the constant region sequence of the first species antibody sequence. In some embodiments, the above-mentioned M is greater than 1, that is, the M different indicators of the embodiment of the present application include at least 2 different indicators, such as at least two indicators including the full sequence, framework region sequence and key residues.
[0125] In the embodiment of the present application, the specific process of determining the consistency information of each second species antibody template sequence in the N second species antibody template sequences with the first species antibody sequence on M different indicators is basically the same. For ease of description, an i-th second species antibody template sequence in the N second species antibody template sequences is used as an example for description.
[0126] In one example, if the M different indicators include the entire sequence, the entire sequence of the i-th second species antibody template sequence is compared with the entire sequence of the first species antibody sequence to determine the consistency information of the i-th second species antibody template sequence and the first species antibody sequence in the entire sequence.
[0127] In one example, if the M different indicators include a framework sequence, the framework sequence of the i-th second species antibody template sequence is extracted, and the framework sequence of the first species antibody sequence is extracted. The framework sequence of the i-th second species antibody template sequence is then compared with the framework sequence of the first species antibody sequence to determine the consistency information between the framework sequence of the i-th second species antibody template sequence and the framework sequence of the first species antibody sequence.
[0128] In one example, if the M different indicators include key residues, the key residues of the i-th second species antibody template sequence are extracted, and the key residues of the first species antibody sequence are extracted. The key residues of the i-th second species antibody template sequence are then compared with the key residues of the first species antibody sequence to determine the consistency information between the key residues of the i-th second species antibody template sequence and the key residues of the first species antibody sequence.
[0129] In some embodiments, if it is detected that the first species antibody sequence and the second species antibody template sequence are not numbered, or the first species antibody sequence is not numbered, or the numbering method of the first species antibody sequence is inconsistent with the numbering method of the second species antibody template sequence, such as Figure 4 As shown, the above S102 includes the following steps S102-A to S102-C:
[0130] S102-A, obtaining a first antibody sequence numbering method, and using the first antibody sequence numbering method to number the amino acids included in the first species antibody sequence and the N second species antibody template sequences;
[0131] S102-B, extracting basic information of the numbered first species antibody sequence and basic information of the numbered N second species antibody template sequences;
[0132] S102-C. For the i-th second species antibody template sequence among the N second species antibody template sequences, based on the basic information of the first species antibody sequence and the basic information of the i-th second species antibody template sequence, determine the consistency information between the first species antibody sequence and the i-th second species antibody template sequence on M different indicators, where i is a positive integer less than or equal to N.
[0133] In the antibody modification process of the embodiment of the present application, the numbering method of the second species antibody template sequence needs to be consistent with the numbering method of the first species antibody sequence. Therefore, before determining the consistency information of the N second species antibody template sequences with the first species antibody sequence on M different indicators, it is first necessary to detect whether the second species antibody template sequence is consistent with the first species antibody sequence, or whether the numbering method of the first species antibody sequence is inconsistent with the numbering method of the second species antibody template sequence. If it is detected that the first species antibody sequence and the second species antibody template sequence are not numbered, or the first species antibody sequence is not numbered, or the numbering method of the first species antibody sequence is inconsistent with the numbering method of the second species antibody template sequence, then the first species antibody sequence and the second species antibody template sequence need to be numbered.
[0134] First, obtain the primary antibody sequence numbering method.
[0135] In one example, the first antibody sequence numbering method may be a default antibody sequence numbering method of the antibody modification platform.
[0136] In one example, the first antibody sequence numbering method can be an antibody sequence numbering method indicated by the object. Exemplarily, the object can input task configuration information in the antibody modification system, and the task configuration information includes the first antibody sequence numbering method. For example, as shown in Table 1, the object indicates that the first antibody sequence numbering tool is anarci and the antibody numbering system used is kabat.
[0137] Next, the amino acids included in the first species antibody sequence and the N second species antibody template sequences are numbered using the first antibody sequence numbering method.
[0138] In this way, the basic information of the numbered first species antibody sequence and the basic information of the numbered N second species antibody template sequences can be extracted. For example, at least one of the antibody initial sequence, framework region sequence, and key residues of the numbered first species antibody sequence is extracted, and at least one of the antibody initial sequence, framework region sequence, and key residues of the second species antibody template sequence is extracted.
[0139] For the i-th second species antibody template sequence among the N second species antibody template sequences, based on the above steps, after extracting the basic information of the numbered first species antibody sequence and the basic information of the i-th second species antibody template sequence, the consistency information between the first species antibody sequence and the i-th second species antibody template sequence on the M different indicators is determined based on the basic information of the first species antibody sequence and the basic information of the i-th second species antibody template sequence.
[0140] In the embodiment of the present application, the basic information of the antibody sequence corresponds to the above-mentioned M different indicators. For example, if the M different indicators include at least one of the full sequence, the framework sequence and the key residues, the basic information of the antibody sequence includes at least one of the antibody initial sequence, the framework sequence and the key residues.
[0141] In one example, if the basic information of the first species antibody sequence includes the antibody initial sequence of the first species antibody sequence, the basic information of the i-th second species antibody template sequence includes the antibody initial sequence of the i-th second species antibody template sequence, and the M different indicators include the full sequence, then the antibody initial sequence of the first species antibody sequence is fully aligned with the antibody initial sequence of the i-th second species antibody template sequence to determine the full sequence consistency information of the first species antibody sequence and the i-th second species antibody template sequence. For example, the amino acid with sequence number a in the first species antibody sequence is compared with the amino acid with sequence number a in the i-th second species antibody template sequence to determine the consistency between the two amino acids, and the amino acid with sequence number b in the first species antibody sequence is compared with the amino acid with sequence number b in the i-th second species antibody template sequence to determine the consistency between the two amino acids, so that the consistency between the amino acids with the same sequence number in the first species antibody sequence and the i-th second species antibody template sequence can be determined, and then based on the consistency between these amino acids, the consistency of the first species antibody sequence and the i-th second species antibody template sequence in the full sequence can be determined. For example, the sum of the identities between the amino acids with the same sequence number in the first species antibody sequence and the i-th second species antibody template sequence is determined as the identity of the first species antibody sequence and the i-th second species antibody template sequence over the entire sequence.
[0142] In one example, if the basic information of the first species antibody sequence includes the framework region sequence of the first species antibody sequence, the basic information of the i-th second species antibody template sequence includes the framework region sequence of the i-th second species antibody template sequence, and the M different indicators include the framework region sequence, then the framework region sequence of the first species antibody sequence is fully aligned with the framework region sequence of the i-th second species antibody template sequence to determine the framework region sequence consistency information between the first species antibody sequence and the i-th second species antibody template sequence. For example, the amino acid with the sequence number a1 in the framework sequence of the antibody sequence of the first species is compared with the amino acid with the sequence number a1 in the framework sequence of the i-th second species antibody template sequence to determine the consistency between the two amino acids, and the amino acid with the sequence number b1 in the framework sequence of the antibody sequence of the first species is compared with the amino acid with the sequence number b1 in the framework sequence of the i-th second species antibody template sequence to determine the consistency between the two amino acids. In this way, the consistency between the amino acids with the same sequence number in the framework sequence of the antibody sequence of the first species and the framework sequence of the i-th second species antibody template sequence can be determined, and then based on the consistency between these amino acids, the consistency between the framework sequence of the antibody sequence of the first species and the framework sequence of the i-th second species antibody template sequence is determined. For example, the sum of the consistency between the amino acids with the same sequence number in the framework sequence of the antibody sequence of the first species and the framework sequence of the i-th second species antibody template sequence is determined as the consistency between the framework sequence of the antibody sequence of the first species and the framework sequence of the i-th second species antibody template sequence.
[0143] In one example, if the basic information of the first species antibody sequence includes the key residues of the first species antibody sequence, the basic information of the i-th second species antibody template sequence includes the key residues of the i-th second species antibody template sequence, and M different indicators include the key residues, the key residues of the first species antibody sequence are fully aligned with the key residues of the i-th second species antibody template sequence to determine the key residue consistency information of the first species antibody sequence and the i-th second species antibody template sequence. For example, the amino acid with the sequence number a2 in the key residues of the first species antibody sequence is compared with the amino acid with the sequence number a2 in the key residues of the i-th second species antibody template sequence to determine the consistency between the two amino acids, and the amino acid with the sequence number b2 in the key residues of the first species antibody sequence is compared with the amino acid with the sequence number b2 in the key residues of the i-th second species antibody template sequence to determine the consistency between the two amino acids, so that the consistency between the key residues of the first species antibody sequence and the amino acids with the same sequence number in the key residues of the i-th second species antibody template sequence can be determined, and then based on the consistency between these amino acids, the consistency between the key residues of the first species antibody sequence and the key residues of the i-th second species antibody template sequence can be determined. For example, the sum of the identities of the amino acids with the same serial number in the key residues of the first species antibody sequence and the i-th second species antibody template sequence is determined as the identity of the key residues of the first species antibody sequence and the i-th second species antibody template sequence.
[0144] In one example, if the basic information of the first species antibody sequence includes the antibody initial sequence, framework sequence and key residues of the first species antibody sequence, the basic information of the i-th second species antibody template sequence includes the antibody initial sequence, framework sequence and key residues of the i-th second species antibody template sequence, and the M different indicators include the full sequence, framework sequence and key residues, then the antibody initial sequence of the first species antibody sequence is compared with the antibody initial sequence of the i-th second species antibody template sequence to determine the full sequence consistency information of the first species antibody sequence and the i-th second species antibody template sequence. The specific process can refer to the description of the example. At the same time, the key residues of the first species antibody sequence are compared with the key residues of the i-th second species antibody template sequence to determine the key residue consistency information of the first species antibody sequence and the i-th second species antibody template sequence. The specific process can refer to the description of the example. At the same time, the framework sequence of the first species antibody sequence is compared with the framework sequence of the i-th second species antibody template sequence to determine the framework sequence consistency information of the first species antibody sequence and the i-th second species antibody template sequence. The specific process can refer to the description of the example.
[0145] The embodiments of the present application do not limit the specific method of determining consistency, for example, the consistency can be determined by determining the similarity. For example, the similarity between two amino acids is determined as the consistency information between the two amino acids.
[0146] The above describes the process of determining the consistency between the i-th second species antibody template sequence and the first species antibody sequence. Referring to the above method, the consistency information between each second species antibody template sequence in the N second species antibody template sequences and the first species antibody sequence can be determined. Next, the following step S103 is performed.
[0147] S103, selecting P second species antibody template sequences from the N second species antibody template sequences based on consistency information between the N second species antibody template sequences and the first species antibody sequence on M different indicators.
[0148] Wherein, P is a positive integer less than or equal to N.
[0149] In the embodiment of the present application, based on the above steps, after determining the consistency information of N second species antibody template sequences with the first species antibody sequence on M different indicators, P second species antibody template sequences are selected from the N second species antibody template sequences based on the consistency information. In this way, P second species antibody template sequences with strong consistency with the first species antibody sequence on M indicators can be selected from the N second species antibody template sequences to transform the first species antibody sequence, which can improve the transformation effect of the first species antibody sequence, and a target antibody sequence that meets the requirements can be found through a small number of transformation attempts, thereby improving the transformation speed of the first species antibody sequence.
[0150] In the embodiment of the present application, based on the consistency information, the method of selecting P second species antibody template sequences from N second species antibody template sequences includes at least the following:
[0151] Method 1: Automatically select P second species antibody template sequences from the N second species antibody template sequences based on the consistency information between the N second species antibody template sequences and the first species antibody sequence on M different indicators.
[0152] In one example, a consistency threshold is set for M different indicators, for example, the consistency threshold corresponding to the full sequence is threshold 1, the consistency threshold corresponding to the framework region sequence is threshold 2, and the consistency threshold corresponding to the key residue is threshold 3. In this way, based on the consistency information of the N second species antibody template sequences with the first species antibody sequence on M different indicators, the second species antibody template sequence whose full sequence consistency with the first species antibody sequence is greater than or equal to threshold 1, the framework region sequence consistency with the first species antibody sequence is greater than or equal to threshold 2, and the key residue consistency with the first species antibody sequence is greater than or equal to threshold 3 can be selected from the N second species antibody template sequences, and then the selected second species antibody template sequences are recorded as P second species antibody template sequences. It should be noted that the consistency thresholds corresponding to the above M different indicators can be the default for the antibody modification sequence or can be input by the object.
[0153] In another example, a specific value of P is set, for example, P is 5, and then based on the consistency information of the N second species antibody template sequences with the first species antibody sequence on M different indicators, 5 second species antibody template sequences are selected from the N second species antibody template sequences. For example, for each second species antibody template sequence, based on the consistency information of the second species antibody template sequence with the first species antibody sequence on M different indicators, the comprehensive consistency score of the second species antibody template sequence with the first species antibody sequence is determined. In this way, based on the comprehensive consistency score of the N second species antibody template sequences with the first species antibody sequence, the P second species antibody template sequences with the highest scores can be selected from the N second species antibody template sequences.
[0154] Method 2: present the consistency information of the N determined second species antibody template sequences with the first species antibody sequence on M different indicators to the subject, so that the subject selects P second species antibody template sequences from the N second species antibody template sequences. At this time, the above S103 includes the following S103-A and S103-B steps:
[0155] S103-A, displaying the consistency information between N second species antibody template sequences and first species antibody sequences on M different indicators;
[0156] S103-B, in response to the subject's selection operation on P second species antibody template sequences from N second species antibody template sequences based on the consistency information, P second species antibody template sequences are selected.
[0157] In an embodiment of the present application, in order to further enhance the participation of the subject in the antibody modification process, the above-determined N second species antibody template sequences are respectively displayed with the first species antibody sequence on M different indicators. The consistency information is displayed. Specifically, if the above-mentioned electronic device is a terminal device, the terminal device determines the consistency information of the N second species antibody template sequences and the first species antibody sequence on M different indicators based on the above steps, and then directly displays the consistency information of the N second species antibody template sequences and the first species antibody sequence on M different indicators. If the above-mentioned electronic device is a server, the server sends the determined consistency information of the N second species antibody template sequences and the first species antibody sequence on M different indicators to the terminal device, and the terminal device displays it.
[0158] In this way, the object can select P second species antibody template sequences from the N second species antibody template sequences based on the consistency information between the currently displayed N second species antibody template sequences and the first species antibody sequence on M different indicators. In this way, the electronic device selects P second species antibody template sequences from the N second species antibody template sequences in response to the object's selection operation on the P second species antibody template sequences from the N second species antibody template sequences based on the consistency information.
[0159] In some embodiments, in order to improve the accuracy of the subject's selection of P second species antibody template sequences, in addition to displaying the consistency information of the N second species antibody template sequences and the first species antibody sequence on M different indicators, the basic feature information of each second species antibody template sequence in the N second species antibody template sequences can also be displayed. The embodiment of the present application does not limit the basic feature information of the second species antibody template sequence, for example, including the structural information, hydrophilicity, hydrophobicity and other physical properties of the second species antibody template sequence.
[0160] S104. Based on the P second species antibody template sequences, the first species antibody sequence is modified to obtain a modified target antibody sequence.
[0161] In an embodiment of the present application, the electronic device selects P second species antibody template sequences with high consistency with the first species antibody sequence in M different indicators from the N second species antibody template sequences based on the above steps, and then transforms the first species antibody sequence based on these P second species antibody template sequences. At the same time, in order to further improve the effect of antibody transformation, in the process of using these P second species antibody template sequences to transform the first species antibody sequence, the intermediate products obtained are evaluated multiple times, and then based on the evaluation results of the intermediate products, it is determined whether to continue the transformation and the direction of the transformation, and finally a target antibody sequence that meets the requirements is obtained, further improving the antibody transformation effect.
[0162] The specific process of modifying the first species antibody sequence based on P second species antibody template sequences is introduced below.
[0163] The embodiment of the present application does not limit the specific method of modifying the first species antibody sequence based on P second species antibody template sequences.
[0164] In some embodiments, based on a preset antibody modification target, the first species antibody sequence is modified using P second species antibody template sequences. For example, for each second species antibody template sequence in the P second species antibody template sequences, the first species antibody sequence is modified using the second species antibody template sequence.
[0165] The modification of the antibody in the embodiment of the present application refers to the recombination of some amino acids of the first species antibody template sequence with some amino acids of the second species antibody sequence, so that the recombinant antibody sequence includes some characteristics of the first antibody sequence and some characteristics of the second species antibody template sequence.
[0166] For example, one or several amino acids in the variable region of the second species antibody template sequence are replaced with the corresponding amino acids in the first species antibody sequence to obtain an improved antibody template sequence. Alternatively, one or more amino acids in the first species antibody template sequence are replaced with one or more corresponding amino acids in the second species antibody sequence to obtain an improved antibody template sequence. In this way, an improved antibody template sequence corresponding to each of the P second species antibody template sequences can be obtained, and then each improved antibody template sequence is evaluated, and one or more improved antibody template sequences that meet the requirements are selected for subsequent mutation improvement, and the above steps are repeated until the target antibody sequence that meets the final requirements is obtained.
[0167] In some embodiments, when the antibodies of the present application are transformed into humanized antibodies, Figure 5 As shown, the above S104 includes the following steps S104-A to S104-F:
[0168] S104-A, for the j-th second species antibody template sequence among P second species antibody template sequences, using the first species antibody sequence to perform CDR transplantation on the j-th second species antibody template sequence to obtain a transplanted j-th antibody template sequence, where j is a positive integer less than or equal to P;
[0169] S104-B, performing back mutation modification on the j-th antibody template sequence after the transplantation to obtain Q candidate back mutation sequences, where Q is a positive integer
[0170] S104-C, performing a first evaluation on each of the Q candidate back mutation sequences to obtain first evaluation information of each candidate back mutation list;
[0171] S104-D, based on the first evaluation information of the Q candidate back mutation sequences, selecting R candidate back mutation sequences from the Q candidate back mutation sequences, where R is a positive integer less than or equal to Q;
[0172] S104-E, generating a j-th target back mutation sequence based on the R candidate back mutation sequences, wherein the target back mutation sequence includes the mutated residues of the R candidate back mutation sequences;
[0173] S104-F. Based on the target reverse mutation sequences corresponding to the P second species antibody template sequences, a modified target antibody sequence is obtained.
[0174] In this embodiment, the specific process of modifying the first species antibody sequence based on each of the selected P second species antibody template sequences is basically the same. For the convenience of description, the jth second species antibody template sequence among the P second species antibody template sequences is taken as an example for description.
[0175] Specifically, for the jth second species antibody template sequence among the P second species antibody template sequences, the first species antibody sequence is used to perform CDR transplantation on the jth second species antibody template sequence to obtain the transplanted jth antibody template sequence. For example, the CDR sequence in the jth second species antibody template sequence is replaced with the CDR sequence of the first species antibody sequence to obtain the transplanted jth antibody template sequence.
[0176] When the CDR sequence of the first species antibody sequence is directly transplanted onto the second species antibody template sequence, the antibody affinity of the second species antibody template sequence will be significantly reduced. For example, when the mouse antibody is humanized, some residues in the mouse antibody framework region have been shown to affect the conformation of the CDR loop and the affinity of the antibody, which are called vernier region residues. These residues are located near the β-folding of the CDR region. Therefore, after selecting the desired human antibody framework region, these residues need to be reverse mutated so that they are retained in the humanized antibody. In addition, mutations of amino acid residues outside the variable region have also been used to give humanized antibodies new properties. Based on this, the embodiment of the present application performs a reverse mutation transformation on the jth antibody template sequence after transplantation to obtain Q candidate reverse mutation sequences. For example, when there are 3 residues in the jth antibody template sequence after transplantation that need to be reverse mutated, these 3 residues are respectively reverse mutated to obtain 3 candidate reverse mutation sequences. In other words, these Q candidate reverse mutation sequences are all single reverse mutation sequences.
[0177] Next, a first evaluation is performed on the Q candidate back mutation sequences corresponding to the j-th antibody template sequence after transplantation to obtain first evaluation information of each of the Q candidate back mutation sequences.
[0178] The embodiment of the present application does not limit the specific method of determining the first evaluation of each of the Q candidate back mutation sequences and obtaining the first evaluation information of each of the Q candidate back mutation sequences. For example, the existing antibody sequence evaluation method is sampled, and the candidate back mutation sequence is subjected to humanization evaluation, stability evaluation, mutation evaluation, etc. to obtain the first evaluation information of the candidate back mutation sequence.
[0179] In some embodiments, Figure 6 As shown, the above S104-C includes the following steps S104-C-a1 to S104-C-a2:
[0180] S104-C-a1. For each of the Q candidate back mutation sequences, determine the change information of the mutated residues in the candidate back mutation sequence before and after the mutation on K indicators, where the K indicators include at least one of statistical frequency, residue type, key residue type, three-dimensional structure position and interaction, and K is a positive integer;
[0181] S104-C-a2. Determine the recommendation degree of the candidate back mutation sequence based on the change information of the mutated residues in the candidate back mutation sequence before and after the mutation on K indicators.
[0182] In the embodiment of the present application, the specific process of performing the first evaluation on each of the Q candidate back mutation sequences is basically the same. For the sake of ease of description, one of the Q candidate back mutation sequences is taken as an example for illustration.
[0183] In the embodiment of the present application, in order to improve the accurate evaluation of the candidate back mutation sequence, the embodiment of the present application determines the recommendation degree of the candidate back mutation sequence when performing the first evaluation on the candidate back mutation sequence. In other words, the first evaluation information of the embodiment of the present application includes the recommendation degree of the candidate back mutation sequence.
[0184] The specific process of determining the recommendation level of candidate back mutation sequences is introduced below.
[0185] Specifically, for each of the Q candidate back mutation sequences, the candidate back mutation sequence is compared with the first species antibody sequence to determine the change information of the mutated residues in the candidate back mutation sequence before and after the mutation on K indicators.
[0186] In one example, if the K indicators include statistical frequencies, the statistical frequency of the antibody subfamily refers to the frequency of occurrence of residues at each position in each subfamily of human antibodies. For example, the heavy chain mainly includes 7 major families: IGHV1, IGHV2, IGHV3…IGHV7. When the antibody is subjected to CDR transplantation, the selected template belongs to one of these 7 families. Then when a residue of the antibody is mutated, it is necessary to refer to the residue frequency of the subfamily to which the template belongs, such as the H5 position mutated from residue T (residue frequency of 0.01) to S (residue frequency of 0.9). Usually, if the position is not a key residue position, it needs to mutate into a high-frequency residue when it is highly conserved (for example, the frequency of S at this position is 0.95). Based on this, the change information of the statistical frequency of the mutant residue in the candidate back mutation sequence before and after the mutation is determined. For example, the change value between the statistical frequency of the residue at the position of the mutant residue in the antibody sequence of the first species and the statistical frequency of the mutant residue in the candidate back mutation sequence is determined, and then the change value is determined as the change information of the statistical frequency of the mutant residue in the candidate back mutation sequence before and after the mutation.
[0187] In one example, if the K indicators include residue types, that is, for the mutant residue in the candidate back mutation sequence, the change information between the residue type of the residue at the corresponding position of the mutant residue in the first species antibody sequence and the residue type of the mutant residue in the candidate back mutation sequence is determined. For example, if the residue type of the residue at the corresponding position of the mutant residue in the first species antibody sequence is hydrophilic, and the residue type of the mutant residue in the candidate back mutation sequence is hydrophobic, then it can be determined that the change information of the residue type of the mutant residue in the candidate back mutation sequence before and after the mutation is from hydrophilic to hydrophobic.
[0188] In one example, if the K indicators include key residue types, that is, for the mutated residue in the candidate back mutation sequence, determine whether the residue at the position corresponding to the mutated residue in the antibody sequence of the first species is a key residue, and which type of key residue it belongs to, and determine whether the mutated residue in the candidate back mutation sequence is a key residue, and which type of key residue it belongs to, and then determine the change information of the mutated residue in the candidate back mutation sequence in the key residue type before and after mutation.
[0189] In one example, if the K indicators include three-dimensional structural positions, that is, for the mutant residue in the candidate back mutation sequence, the three-dimensional structural position of the residue at the position corresponding to the mutant residue in the first species antibody sequence is determined, and the three-dimensional structural position of the mutant residue in the candidate back mutation sequence is determined, and then based on the three-dimensional structural position of the residue at the position corresponding to the mutant residue in the first species antibody sequence and the three-dimensional structural position of the mutant residue in the candidate back mutation sequence, the change information of the three-dimensional structural position of the mutant residue in the candidate back mutation sequence before and after the mutation is determined. Exemplarily, the change information of the three-dimensional structural position of the mutant residue before and after the mutation includes the distance between the mutant residue and the CDR before and after the mutation, the distance between the heavy chain and the nearest light chain before and after the mutation of the mutant residue, etc.
[0190] In one example, if the K indicators include interactions, that is, for the mutant residue in the candidate back mutation sequence, the interactions of the residues at the corresponding positions of the mutant residue in the first species antibody sequence, and the interactions of the mutant residue in the candidate back mutation sequence are determined, and then based on the interactions of the residues at the corresponding positions of the mutant residue in the first species antibody sequence and the interactions of the mutant residue in the candidate back mutation sequence, the change information of the interaction of the mutant residue in the candidate back mutation sequence before and after the mutation is determined. For example, before the mutation, the interaction between the residue at the corresponding position of the mutant residue in the first species antibody sequence and the surrounding amino acids is a hydrophobic interaction, and the interaction between the mutant residue in the candidate back mutation sequence and the surrounding amino acids is a hydrophilic interaction, then it can be determined that the change information of the interaction of the mutant residue in the candidate back mutation sequence before and after the mutation is a change from a hydrophobic interaction to a hydrophilic interaction.
[0191] It should be noted that the K indicators in the embodiment of the present application may include other spatial positions and / or physical indicators in addition to statistical frequency, residue type, key residue type, three-dimensional structure position and at least one of interactions, and the embodiment of the present application is not limited to this.
[0192] Based on the above steps, the electronic device determines the change information of the mutant residues in the candidate back mutation sequence on K indicators before and after the mutation, and then determines the recommendation degree of the candidate back mutation sequence based on the change information of the mutant residues in the candidate back mutation sequence on K indicators before and after the mutation.
[0193] In the embodiment of the present application, there is no limitation on the specific method of determining the recommendation degree of the candidate back mutation sequence based on the change information of the mutated residues in the candidate back mutation sequence on K indicators before and after the mutation.
[0194] In a possible implementation, the change information of the mutated residues in the candidate back mutation sequence before and after the mutation on K indicators is converted into a corresponding recommendation score value, wherein the smaller the change information, the higher the corresponding recommendation score value, and the method of determining the recommendation score value corresponding to different indicators in the K indicators may be different. In this way, based on the change information of the mutated residues in the candidate back mutation sequence before and after the mutation on K indicators, K recommendation scores can be obtained, and then based on the K recommendation scores, the recommendation degree of the candidate back mutation sequence can be obtained. For example. The sum or weighted sum or average or weighted average or other calculation results of the K recommendation scores are determined as the recommendation degree of the candidate back mutation sequence.
[0195] In a possible implementation, the change information of the mutated residues in the candidate back mutation sequence before and after the mutation on K indicators can be input into a recommendation degree prediction model to obtain the recommendation degree of the candidate back mutation sequence. The recommendation degree prediction model is extracted and trained.
[0196] The above describes the process of determining the recommendation level of one of the Q candidate back mutation sequences. Referring to this method, the recommendation level of each of the Q candidate back mutation sequences can be determined.
[0197] From the above, it can be seen that in the embodiment of the present application, when performing the first evaluation of the candidate restored antibody sequence, the statistical frequency, residue type, key residue type, three-dimensional structural position and interaction of the antibody subfamily are combined to comprehensively evaluate the mutated residues of the candidate restored antibody sequence to improve the accuracy of the residue mutation.
[0198] In some embodiments, if the recommendation levels of the candidate reverting antibody sequences are displayed, different display modes may be used to display the recommendation levels in a graded manner, so that the subject can select the candidate reverting antibody sequences based on the intuitively displayed recommendation levels.
[0199] In some embodiments, the first evaluation information of the embodiment of the present application includes not only the recommendation degree information of the candidate back mutation sequence, but also the rapid evaluation information of the candidate back mutation sequence. At this time, the above S104-C also includes the following step S104-Cb:
[0200] S104-Cb. For each of the Q candidate back mutation sequences, quickly evaluate the mutated residues in the candidate back mutation sequence to obtain rapid evaluation information of the candidate back mutation sequence.
[0201] In an embodiment of the present application, in order to further improve the first evaluation of the candidate reverted mutation sequence, in addition to determining the recommendation degree of the candidate reverted mutation sequence, the candidate reverted mutation sequence is quickly evaluated to obtain the rapid evaluation information of the candidate reverted mutation sequence. In this way, the recommendation degree and rapid evaluation information of the candidate reverted mutation sequence can be used as the first evaluation information of the candidate reverted mutation sequence, and then when the candidate reverted mutation sequence is selected based on the first evaluation information, the selection accuracy of the candidate reverted mutation sequence can be improved, and the effect of antibody modification can be further improved.
[0202] The embodiment of the present application performs a rapid assessment of the mutated residues in the candidate back mutation sequence, and the specific method of obtaining the rapid assessment information of the candidate back mutation sequence is not limited.
[0203] In a possible implementation, the rapid evaluation information of the candidate back mutation sequence includes at least one of: mutation score, sequence position information, three-dimensional structure position information, humanization evaluation and thermal stability.
[0204] In a possible implementation, the rapid evaluation information of the candidate back mutation sequence may include, in addition to at least one of mutation score, sequence position information, three-dimensional structure position information, humanization assessment and thermal stability, high-frequency residue mutations of the candidate back mutation sequence, humanization model recommendation, key_pos_hit (number of key residue types hit), canonical_hit_count (number of canonical hits, canonical types include distance from cdr region <5.0A, distance from interaction interface <5.0, and existence of internal interactions) of the candidate back mutation sequence, vernier_back: the mutation position is in the vernier region and is a back mutation, SASA: sasa value is a value used to measure the degree of exposure of the residue to the solvent. If sasa value>sasa_thershold, it is marked as 1, which can be understood as the mutation position is an antibody surface residue.
[0205] In the embodiment of the present application, the electronic device can determine the first evaluation information of each candidate back mutation sequence in the Q candidate back mutation sequences corresponding to the j-th second species antibody template sequence in the P second species antibody template sequences based on the above steps. Then, the above step S104-D is performed to select R candidate back mutation sequences from the Q candidate back mutation sequences based on the first evaluation information of the Q candidate back mutation sequences.
[0206] The embodiment of the present application does not limit the specific method of selecting R candidate back mutation sequences from Q candidate back mutation sequences based on the first evaluation information of the Q candidate back mutation sequences.
[0207] In some embodiments, the electronic device selects R candidate back mutation sequences whose first evaluation information meets preset requirements from the Q candidate back mutation sequences based on the first evaluation information of the Q candidate back mutation sequences.
[0208] In some embodiments, the above S104-D includes the following steps S104-D1 to S104-D3:
[0209] S104-D1. Obtaining antibody modification methods, including non-automatic modification methods and automatic modification methods;
[0210] S104-D2. If the antibody modification method is a non-automatic modification method, first evaluation information of Q candidate back mutation sequences is displayed, and the receiving subject performs a selection operation on R candidate back mutation sequences among the Q candidate back mutation sequences based on the first evaluation information to select R candidate back mutation sequences;
[0211] S104-D3. If the antibody modification method is an automatic modification method, R candidate reverse mutation sequences whose first evaluation information meets preset requirements are selected from the Q candidate reverse mutation sequences.
[0212] In some embodiments of the present application, when modifying the antibody sequence of the first species, the subject inputs an antibody modification method, wherein the antibody modification method includes an automatic modification method and a non-automatic modification method.
[0213] Among them, the automatic transformation method refers to the transformation of the first species antibody sequence based on the pre-set rules during the transformation of the first species antibody sequence. For example, when the object sets automatic optimization (auto_optim:true) in the task configuration information, the electronic device will select mutations and evaluate acceptance rules according to the system preset rules, as well as continue or stop mutation optimization rules. Exemplarily, the automatic antibody optimization will only perform one round of CDR transplantation and one round of back mutation optimization by default, and other settings need to be set separately.
[0214] Among them, the non-automatic transformation method refers to completing the transformation of the first species antibody sequence by interacting with the object during the transformation of the first species antibody sequence.
[0215] Based on this, when the electronic device selects R candidate back mutation sequences from Q candidate back mutation sequences based on the first evaluation information of the Q candidate back mutation sequences, it first obtains the antibody modification method, for example, reads the field auto_optim in the task configuration information input by the object. If auto_optim is true, it indicates that the sampled antibody modification method is an automated antibody modification method; if auto_optim is false, it indicates that the sampled antibody modification method is a non-automated antibody modification method.
[0216] Example 1: If the antibody modification method is the non-automatic modification method, the electronic device displays the first evaluation information of Q candidate back mutation sequences, and then the receiving object performs a selection operation on R candidate back mutation sequences among the Q candidate back mutation sequences based on the first evaluation information to select R candidate back mutation sequences.
[0217] For example, it is assumed that the Q candidate back mutation sequences corresponding to the j-th second species antibody template sequence include 6 candidate back mutation sequences, and the 6 candidate back mutation sequences are all single-point residue mutations. Exemplarily, the mutated residues of the 6 candidate back mutation sequences are respectively mutating the residue at the H94 position in the j-th second species antibody template sequence from R to S, mutating the residue at the H48 position in the j-th second species antibody template sequence from I to L, mutating the residue at the H67 position in the j-th second species antibody template sequence from V to L, mutating the residue at the H27 position in the j-th second species antibody template sequence from G to F, mutating the residue at the H71 position in the j-th second species antibody template sequence from V to K, and mutating the residue at the H30 position in the j-th second species antibody template sequence from S to T. Referring to the above method, the above 6 candidate back mutation sequences are respectively first evaluated to obtain the first evaluation information of the 6 candidate back mutation sequences.
[0218] Exemplarily, the first evaluation information of these 6 candidate back mutation sequences is shown in Table 2:
[0219] Table 2
[0220]
[0221] Among them, idx in Table 2 represents the index of the 6 candidate back mutation sequences, and candiate represents the ID of the candidate back mutation sequence. Mutation config represents the position of the mutated residues of the 6 candidate back mutation sequences and the changes before and after the mutation. Mutation desc represents the description of the mutation, including these 5 variables: mut_score (mutation score, the higher the better), key_pos_hit (indicates the number of key residue types hit), canonical_hit_count (indicates the number of canonical hits, canonical types include distance from the cdr region <5.0A, distance from the interaction interface <5.0, and the existence of internal interactions), vernier_back (indicates that the mutation position is in the vernier region and is a back mutation), SASA (a value used to measure the degree of exposure of the residue to the solvent. If sasa value>sasa_thershold, it is marked as 1, which can be understood as the mutation position is an antibody surface residue). Mutation Result indicates the mutation result, including three variables: Stability (indicates the thermal stability score of single-point mutations, which is only available for single-point mutations. The lower the better, and negative numbers indicate more stability), OASis identity and OASis percentile, where OASis identity and OASis percentile are two humanized scoring indicators, the higher the better. Color indicates the recommendation degree of the six candidate back mutation sequences, for example, the level of recommendation is represented by different colors, such as GREEN, PURPLE, and YELLOW.
[0222] It should be noted that Table 2 only shows a part of the first evaluation information.
[0223] The electronic device displays the first evaluation information of the six candidate back mutation sequences shown in Table 2, so that the subject can select one or more candidate back mutation sequences of the six candidate back mutation sequences based on the first evaluation information of the six candidate back mutation sequences, for example, select R candidate back mutation sequences from the six candidate back mutation sequences. The electronic device obtains R candidate back mutation sequences based on the subject's selection operation on the R candidate back mutation sequences from the six candidate back mutation sequences.
[0224] In some embodiments, in order to enable the subject to quickly and accurately select the candidate back mutation sequence, if the first evaluation information includes the recommendation degree of the candidate back mutation sequence, the recommendation degrees of the Q candidate back mutation sequences are displayed in grades based on the preset display formats corresponding to the different levels of recommendation degrees. As shown in Table 2, the recommendation degrees of the 6 candidate back mutation sequences are displayed in grades, for example, using different colors for graded display.
[0225] In some embodiments, the rapid evaluation results of the candidate back mutation sequences, such as thermal stability and humanization scores, are also displayed in a hierarchical manner. In this way, the subject can quickly and accurately select R candidate back mutation sequences from the R candidate back mutation sequences based on the recommended degree and / or rapid evaluation results displayed in a hierarchical manner.
[0226] It can be seen that the antibody modification system of the embodiment of the present application provides an interactive command line operation interface, and the object can obtain the final result and intermediate result of the modification through command line operation, and can perform flexible operations to create a new modification path from the intermediate modification steps. At the same time, the antibody modification system of the embodiment of the present application provides a friendly display interface, which facilitates the object to determine the candidate mutation modification direction by displaying the recommendation degree and rapid evaluation information in a graded manner.
[0227] Example 2: If the antibody modification method is an automatic modification method, the electronic device automatically selects R candidate reversion mutation sequences whose first evaluation information meets the preset requirements from the Q candidate reversion mutation sequences. Optionally, in this example 2, the first evaluation information selected from the Q candidate reversion mutation sequences can also be displayed to the subject.
[0228] That is, the embodiments of the present application provide a unified antibody modification framework with a unified interface and standardized processes, which facilitates and quickly accesses multiple antibody evaluation methods. At the same time, an interactive antibody optimization operation mode is provided to meet the needs of automatic optimization and manual optimization and evaluation, so that the subject can quickly obtain candidate reverse mutation sequences with better effects, further improving the effect and efficiency of antibody modification.
[0229] After selecting R candidate back mutation sequences from the Q candidate back mutation sequences based on the first evaluation information of the Q candidate back mutation sequences, the electronic device performs the above-mentioned step S104-E to generate the jth target back mutation sequence based on the R candidate back mutation sequences, wherein the generated jth target back mutation sequence includes the mutated residues of the R candidate back mutation sequences. For example, the mutated residues of the R candidate back mutation sequences are combined to generate the jth target back mutation sequence. Exemplarily, assuming that the Q candidate back mutation sequences are as shown in Table 2, including 6 mutated residues, the selected R candidate back mutation sequences are respectively the 3 candidate back mutation sequences indexed as 0, 3 and 5 in Table 2, the mutated residues included in the 3 candidate back mutation sequences are merged to generate the jth target back mutation sequence, at which time the jth target back mutation sequence includes 3 mutated residues, namely, the residue at position H94 is mutated from R to S, the residue at position H27 is mutated from G to F, and the residue at position H30 is mutated from S to T.
[0230] The above describes the specific process of the electronic device determining the jth target reverse mutation sequence corresponding to the jth second species antibody template sequence in P second species antibody template sequences. Referring to the above method, the target reverse mutation sequence corresponding to each second species antibody template sequence in the P second species antibody template sequences can be determined, and P target reverse mutation sequences can be obtained. Then, the above step S104-E is performed to obtain the modified target antibody sequence based on the P target reverse mutation sequences corresponding to the P second species antibody template sequences.
[0231] The following introduces the specific process of obtaining the modified target antibody sequence by the electronic device based on P target reverse mutation sequences corresponding to P second species antibody template sequences.
[0232] The embodiment of the present application does not limit the specific method of obtaining the modified target antibody sequence based on the P target back mutation sequences corresponding to the P second species antibody template sequences.
[0233] In some embodiments, P target back mutation sequences can be determined as the modified target antibody sequences.
[0234] In some embodiments, the above S104-E includes the following steps S104-E1 and S104-E2:
[0235] S104-E1, performing a second evaluation on each of the P target reverse mutation sequences to obtain second evaluation information of each target reverse mutation sequence;
[0236] S104-E2. Based on the second evaluation information of the P target reverse mutation sequences, determine the modified target antibody sequence.
[0237] In this embodiment, in order to further improve the effect of antibody modification, when the electronic device obtains P target reverse mutation sequences corresponding to P second species antibody template sequences based on the above steps, as follows Figure 7 As shown, a second evaluation is performed on each of the P target back mutation sequences to obtain second evaluation information of each target back mutation sequence.
[0238] In the embodiment of the present application, the specific process of the electronic device performing the second evaluation on each of the P target reverse mutation sequences is basically the same. For ease of description, one of the P target reverse mutation sequences is used as an example for description.
[0239] In the embodiment of the present application, the specific manner in which the electronic device performs a second evaluation on the target reverse mutation sequence to obtain the second evaluation information of the target reverse mutation sequence is not limited.
[0240] In some embodiments, Figure 8 As shown, the second evaluation includes at least one of sequence evaluation, structure evaluation and derivability evaluation, and the corresponding second evaluation information includes at least one of sequence evaluation information, structure evaluation information and derivability evaluation information.
[0241] In one example, if the second evaluation includes sequence evaluation, a sequence evaluation is performed on the target back mutation sequence to obtain sequence evaluation information of the target back mutation sequence.
[0242] Exemplarily, the sequence evaluation information includes at least one of a sequence consistency evaluation score, a humanization evaluation score, basic feature information, and paratope prediction information.
[0243] In one example, if the second evaluation includes a structural evaluation, a structural evaluation is performed on the target back mutation sequence to obtain structural evaluation information of the target back mutation sequence.
[0244] Exemplarily, the structural evaluation information includes at least one of a change in CDR RMSD, a change in the stacking angle between the heavy and light chains, and a change in the interaction between the heavy and light chains.
[0245] Optionally, the changes in the interaction between the heavy and light chains include at least one of the following: ionic (ionic bond), hbond (hydrogen bond interaction), hydrophobic (hydrophobic group interaction), t-stacking & pi-stacking (aromatic ring interaction), cation-stacking (interaction between cation and aromatic ring), and clash (steric conflict).
[0246] In one example, if the second evaluation includes a feasibility evaluation, a feasibility evaluation is performed on the target back mutation sequence to obtain feasibility evaluation information of the target back mutation sequence.
[0247] Exemplarily, the feasibility assessment information includes at least one of thermal stability changes, aggregation, TAP characteristics, post-translational modification risk sites, etc.
[0248] Based on the above steps, the electronic device can determine the second evaluation information of each of the P target reverse mutation sequences. Next, the above step S104-E2 is performed to determine the modified target antibody sequence based on the second evaluation information of the P target reverse mutation sequences.
[0249] In the embodiment of the present application, the implementation methods of S104-E2 include at least the following:
[0250] Method 1: The electronic device directly selects one or several target reverted mutation sequences with better second evaluation information from the P target reverted mutation sequences based on the second evaluation information of the P target reverted mutation sequences, and then obtains the modified target antibody sequence based on the one or several target reverted mutation sequences with better second evaluation information. For example, the one or several target reverted mutation sequences with better second evaluation information are directly determined as the modified target antibody sequence. For another example, the one or several target reverted mutation sequences with better second evaluation information are further mutated to obtain the modified target antibody sequence.
[0251] Method 2: In order to improve the interactivity during antibody modification, the above S104-E2 includes the following steps S104-E21 and S104-E22:
[0252] S104-E21, displaying the second evaluation information of the target reverse mutation sequence;
[0253] S104-E22. In response to the transformation operation input by the subject based on the second evaluation information, a transformed target antibody sequence is obtained, wherein the transformation operation is used to indicate whether to continue to transform the target reverse mutation sequence.
[0254] In this implementation, the second evaluation information of the determined target reverted mutation sequence can be displayed. For example, if the electronic device is a terminal device, the electronic device directly displays the second evaluation information of the determined target reverted mutation sequence. If the electronic device is a server, the electronic device sends the second evaluation information of the determined target reverted mutation sequence to the terminal device for display.
[0255] In one example, the second evaluation information of a certain target reverse mutation sequence among the P target reverse mutation sequences is as follows:
[0256]
[0257] The value before the front is the evaluation data before the transformation, and the value after the front is the evaluation data after the transformation (ie, the second evaluation information).
[0258] Mutation type indicates the mutation type, for example, mutation of the target reverse mutation sequence multimut;
[0259] Mutation configuration represents mutation information;
[0260] Mutation result indicates the changes of various indicators from non-mutation to mutation;
[0261] Humanity score: antibody humanization score;
[0262] Sequence identity score: sequence consistency score;
[0263] Developability: An antibody developability assessment indicator, including thermal stability score (only single-point mutations have this score, and multiple-point mutations are not calculated at the same time), aggregation score (Agg Score & Agg Scan), and other risk sites for post-translational modification;
[0264] Basic feature: antibody basic feature information;
[0265] Tap_feature: It is also an indicator of antibody developability, Therapeutic Antibody Profiler, with a total of 5 indicators. Color is used to grade the values of the five indicators, indicating the safety level of the druggable antibody within the range.
[0266] Cdr_info: indicates CDR RMSD changes;
[0267] Diff interact info: indicates the changes in the interactions between heavy and light chains, including ionic (ionic bond interaction), hbond (hydrogen bond interaction), hydrophobic (hydrophobic group interaction), t-stacking & pi-stacking (aromatic ring interaction), cation-stacking (cation and aromatic ring interaction), and clash (steric conflict);
[0268] Diff paratope info: Predicted changes in the complementary site of the binding antibody;
[0269] Angle info: Indicates the change in the stacking angle between the heavy and light chains.
[0270] In an embodiment of the present application, for each of the P second species antibody template sequences, the second species antibody template sequence is used to perform CDR transformation and back mutation on the first species antibody sequence, and after obtaining the target back mutation sequence corresponding to the second species antibody template sequence, the target back mutation sequence is evaluated for the second evaluation, and the second evaluation information of the target back mutation sequence is displayed to the object. In this way, the object can input the transformation operation of the target back mutation sequence based on the second evaluation information, and the electronic device responds to the transformation operation input by the object based on the second evaluation information to obtain the transformed target antibody sequence, wherein the transformation operation is used to indicate whether to continue to transform the target back mutation sequence. For example, if the object determines that the target back mutation sequence is used as the final target antibody sequence, the operation of stopping the transformation can be input, and the electronic device responds to the operation of stopping the transformation input by the object, ends the transformation of the target back mutation sequence, and outputs the target back mutation sequence. If the object determines that the target back mutation sequence is to be continued to be transformed, the operation of continuing the transformation can be input, and the electronic device responds to the operation of continuing the transformation input by the object, and continues to transform the target back mutation sequence. In one example, if the target back mutation sequence does not meet the requirements of the subject, the subject may also input an operation to abandon the target back mutation sequence, and the electronic device may delete the target back mutation sequence in response to the abandonment operation input by the subject.
[0271] It can be seen from this that the present application embodiment, by constructing an interactive antibody transformation system, selects the second species antibody template sequence based on multiple indicators, realizes the selection accuracy of the second species antibody template sequence, improves the accuracy of antibody transformation, and in the antibody transformation process, the CDR transformation result is reversed, and then while the antibody is transformed, the antibody and antigen binding affinity are maintained, and then the effect of antibody transformation is improved. Further, in the antibody transformation process, multiple dimensions such as sequence evaluation information, structure evaluation information and feasibility evaluation information of the antibody sequence are evaluated, and the evaluation system in the antibody transformation process is improved, and the evaluation accuracy in the antibody transformation process is improved, and the accuracy of antibody transformation is further improved. At the same time, the present application embodiment provides an overall and fine-grained evaluation perspective to the object through a visualization tool, and provides the object with a further transformation direction, which can realize the interactivity in the antibody transformation process, so that the antibody transformation is carried out in the direction expected by the object, and a modified antibody that meets the requirements of the object can be obtained.
[0272] In some embodiments, in order to further enhance the interactive effect, the embodiment of the present application can also display each evaluation index in the second evaluation information of the target reverse mutation sequence in a graded manner. Specifically, a statistical distribution analysis is performed on each evaluation index in the second evaluation information of the patent antibody data to obtain a reference threshold value for each evaluation index. Each evaluation index in the second evaluation information of the target reverse mutation sequence is compared with the corresponding reference threshold value to determine the display format of the numerical value of the evaluation index of the second evaluation information of the target reverse mutation sequence, and then based on the display format, each evaluation index in the second evaluation information of the target reverse mutation sequence is displayed in a graded manner. For example, for the evaluation index 1 in the second evaluation information, a statistical distribution analysis is performed on the evaluation index 1 of the patent antibody data to obtain a reference threshold value 1 of the evaluation index 1, so that the evaluation index 1 of the target reverse mutation sequence is compared with the reference threshold value 1 to determine the display format of the evaluation index 1 of the target reverse mutation sequence. Exemplarily, if the evaluation index 1 of the target reverse mutation sequence is in the interval of 0 to 66% of the reference threshold 1, the display format of the evaluation index 1 of the target reverse mutation sequence is determined to be 1, if the evaluation index 1 of the target reverse mutation sequence is in the interval of 66% to 95% of the reference threshold 1, the display format of the evaluation index 1 of the target reverse mutation sequence is determined to be 2, and if the evaluation index 1 of the target reverse mutation sequence is in the interval above 95% of the reference threshold 1, the display format of the evaluation index 1 of the target reverse mutation sequence is determined to be 3. Among them, display format 1, display format 2 and display format 3 are different, for example, they can be different colors or different fonts. It should be noted that the above-mentioned values 0, 66%, and 95% are all examples, which can be adjusted based on actual needs, and the embodiments of the present application are not limited to this.
[0273] In some embodiments, the embodiments of the present application may also display the transformation information corresponding to each of the P second species antibody template sequences, taking the jth second species antibody template sequence as an example. When the first species antibody sequence is transformed based on the jth second species antibody template sequence, the electronic device may display the transformation information corresponding to the jth second species antibody template sequence, the transformation information including the first species antibody sequence, the jth second species antibody template sequence after transplantation, and the jth target reverse mutation sequence, and at least one of the humanization score and the structural consistency score corresponding to the first species antibody sequence, the jth second species antibody template sequence after transplantation, and the jth target reverse mutation sequence.
[0274] For example, as shown in Table 3:
[0275] Table 3
[0276]
[0277] As shown in Table 3, index 0 represents the first species antibody sequence, index 1 represents the second species antibody template sequence after CDR modification, and index 3 represents the target back mutation sequence corresponding to the second species antibody template sequence. OASis represents the humanization score, and Identity Score represents the structural consistency score.
[0278] Based on the above steps, the electronic device can determine the second evaluation information of the target reverse mutation sequence corresponding to each second species antibody template sequence in the P second species antibody template sequences, and then determine the transformed target antibody sequence based on the second evaluation information of the target reverse mutation sequence corresponding to each second species antibody template sequence. For example, the target reverse mutation sequence whose second evaluation information in the P target reverse mutation sequences meets the preset requirements is determined as the transformed target antibody sequence. Alternatively, based on the second evaluation information, one or more of the P target reverse mutation sequences are selected for further transformation, and then the target reverse mutation sequence after the transformation is further transformed is determined as the transformed target antibody sequence. It should be noted that when the target reverse mutation sequence is further transformed, the first evaluation and / or second evaluation method of the embodiment of the present application can also be used for evaluation.
[0279] The antibody modification method provided in the embodiment of the present application, the first species antibody sequence input by the electronic receiving object, and the consistency information of the N second species antibody template sequences with the first species antibody sequence on M different indicators. Then, based on the consistency information of the N second species antibody template sequences with the first species antibody sequence on M different indicators, P second species antibody template sequences are selected from the N second species antibody template sequences, and then based on the P second species antibody template sequences, the first species antibody sequence is modified to obtain the modified target antibody sequence. It can be seen from this that when the template is selected, the second species antibody template sequence and the first species antibody sequence are judged for consistency on M different indicators, thereby improving the selection accuracy of the second species antibody template sequence, so that when the first species antibody sequence is modified based on the accurately selected second species antibody model sequence, the final modified target antibody sequence can be obtained after a few rounds of modification, which improves the modification efficiency and modification effect of the antibody, and the antibody modification process is evaluated multiple times, which can achieve the accuracy of antibody modification.
[0280] The above is an overall introduction to the antibody modification method provided in the embodiments of the present application. In some embodiments, the antibody modification method of the embodiments of the present application can be performed by the terminal device and the server together. Fig. 9 The method for a terminal device and a server to jointly execute an embodiment of the present application is introduced.
[0281] Combine the following Fig. 9The entire process of the antibody modification method provided in the examples of the present application is introduced. Fig. 9 It can be understood as a specific embodiment of the antibody modification method described in the above embodiment.
[0282] Fig. 9 A schematic diagram of the antibody modification method provided in one embodiment of the present application is shown in FIG. Fig. 9 and Fig.10 As shown, including:
[0283] S201. A terminal device receives a first species antibody sequence to be modified input by a subject, and sends the first species antibody sequence to a server.
[0284] In an embodiment of the present application, if the terminal device is used to interact with the object and the server is used for antibody modification, the terminal device sends the first species antibody sequence input by the object to the server so that the server performs modification of the first species antibody sequence.
[0285] S202: The server obtains a first antibody sequence numbering method, and uses the first antibody sequence numbering method to extract basic information of the first species antibody sequence after the numbering.
[0286] S203: The server performs a second evaluation on the first species antibody sequence based on the numbered basic information of the first object antibody sequence to obtain second evaluation information of the first species antibody sequence.
[0287] It should be noted that the second evaluation process of the server on the first species antibody sequence is basically the same as the second evaluation process on the target response antibody sequence in the above embodiment. Please refer to the specific description of the above embodiment, which will not be repeated here.
[0288] If the second evaluation information of the first species antibody sequence meets the preset requirements, the server executes the following step S204. Otherwise, a reminder message that the first species antibody sequence does not meet the requirements is sent to the terminal device, so that the terminal device displays the reminder message to the subject, so that the subject can re-enter the first species antibody sequence.
[0289] S204. The server obtains N second species antibody template sequences for modifying the first species antibody sequence, and numbers the amino acids included in the N second species antibody template sequences using the first antibody sequence numbering method.
[0290] S205. The server extracts basic information of the numbered N second species antibody template sequences.
[0291] The basic information includes at least one of the antibody initial sequence, framework region sequence and key residues.
[0292] S206. The server determines, for an i-th second species antibody template sequence among the N second species antibody template sequences, consistency information between the first species antibody sequence and the i-th second species antibody template sequence on M different indicators based on the basic information of the first species antibody sequence and the basic information of the i-th second species antibody template sequence.
[0293] Exemplarily, the M different indicators include at least one of the full sequence, the framework region sequence and the key residues, M is a positive integer, and i is a positive integer less than or equal to N.
[0294] For example, the server performs a full sequence comparison of the antibody initial sequence of the first species antibody sequence with the antibody initial sequence of the i-th second species antibody template sequence to determine the full sequence consistency information between the first species antibody sequence and the i-th second species antibody template sequence; compares the key residues of the first species antibody sequence with the key residues of the i-th second species antibody template sequence to determine the key residue consistency information between the first species antibody sequence and the i-th second species antibody template sequence; compares the framework region sequence of the first species antibody sequence with the framework region sequence of the i-th second species antibody template sequence to determine the framework region sequence consistency information between the first species antibody sequence and the i-th second species antibody template sequence.
[0295] The specific implementation process of the above S204 to S206 can refer to the relevant description of the above S102, which will not be repeated here.
[0296] S207. The server sends consistency information of the N second species antibody template sequences and the first species antibody sequence on M different indicators to the terminal device for display.
[0297] Wherein, P is a positive integer less than or equal to N.
[0298] S208: The terminal device selects P second species antibody template sequences in response to the object's selection operation on P second species antibody template sequences from N second species antibody template sequences based on the consistency information.
[0299] S209: The terminal device sends the selected P second species antibody template sequences to the server.
[0300] In the embodiment of the present application, in order to achieve interactivity with the object during the antibody modification process, the server sends the determined consistency information of the N second species antibody template sequences and the first species antibody sequence on M different indicators to the terminal device, so that the terminal device displays the consistency information to the object. In this way, the object can accurately select P second species antibody template sequences from the N second species antibody template sequences for modification of the first species antibody sequence based on the consistency information.
[0301] S210: The server performs CDR transplantation on the j-th second species antibody template sequence among the P second species antibody template sequences using the first species antibody sequence to obtain the j-th antibody template sequence after transplantation.
[0302] Wherein, j is a positive integer less than or equal to P.
[0303] S211. The server performs a second evaluation on the j-th antibody template sequence after transplantation to obtain second evaluation information of the j-th antibody template sequence after transplantation.
[0304] The specific implementation process of the above S2011 can refer to the relevant description of the above S104, which will not be repeated here.
[0305] S212. If the server determines based on the second evaluation information that the j-th antibody template sequence after transplantation needs to be further modified, the j-th antibody template sequence after transplantation is subjected to back mutation modification to obtain Q candidate back mutation sequences.
[0306] Wherein, Q is a positive integer.
[0307] As can be seen from the above, in order to ensure the effectiveness of antibody modification, the embodiment of the present application evaluates the intermediate product of the antibody modification process, and when the evaluation result of the intermediate product meets the preset requirements, the subsequent modification is continued. This can further improve the reliability of the antibody modification process and prevent the modification of unnecessary antibodies, resulting in a waste of time and resources.
[0308] S213. The server performs a first evaluation on each of the Q candidate back mutation sequences to obtain first evaluation information of each candidate back mutation list.
[0309] Exemplarily, the first evaluation information includes the recommendation degree of the candidate back mutation sequence, and the first evaluation is performed on each of the Q candidate back mutation sequences to obtain the first evaluation information of each candidate back mutation list, including:
[0310] For each of the Q candidate back mutation sequences, determine the change information of the mutated residues in the candidate back mutation sequence before and after the mutation on K indicators, where the K indicators include at least one of statistical frequency, residue type, key residue type, three-dimensional structure position and interaction; based on the change information of the mutated residues in the candidate back mutation sequence before and after the mutation on the K indicators, determine the recommendation degree of the candidate back mutation sequence.
[0311] The specific implementation process of the above S2013 can refer to the relevant description of the above S104, which will not be repeated here.
[0312] S214. The server sends first evaluation information of the Q candidate back mutation sequence pairs to the terminal device for display.
[0313] S215. The terminal device receives the object's selection operation on R candidate back mutation sequences from the Q candidate back mutation sequences based on the first evaluation information, and selects R candidate back mutation sequences.
[0314] S216. The terminal device sends the selected R candidate back mutation sequences to the server.
[0315] The specific implementation process of the above S2014 to S216 can refer to the relevant description of the above S104, which will not be repeated here.
[0316] S217. The server generates the jth target back mutation sequence based on the R candidate back mutation sequences.
[0317] Among them, the jth target back mutation sequence includes the mutated residues of R candidate back mutation sequences.
[0318] S218. The server performs a second evaluation on the j-th target back mutation sequence to obtain second evaluation information of the j-th target back mutation sequence.
[0319] S219. The server sends the second evaluation information of the j-th target reverse mutation sequence to the terminal device for display.
[0320] S220: The terminal device obtains a modified target antibody sequence in response to the modification operation input by the subject based on the second evaluation information.
[0321] The transformation operation is used to indicate whether to continue to transform the target reverse mutation sequence.
[0322] It can be seen from this that the present application embodiment provides an interactive antibody modification method. When the template is selected, the second species antibody template sequence and the first species antibody sequence are judged for consistency in multiple indicators such as the full sequence, framework region sequence and key residues, thereby improving the selection accuracy of the second species antibody template sequence. When the first species antibody sequence is modified based on the accurately selected second species antibody model sequence, the final modified target antibody sequence can be obtained after a few rounds of modification, thereby improving the modification efficiency and modification effect of the antibody. At the same time, the object can obtain the final result and intermediate result of the modification through command line operation, and can be flexibly operated to create a new modification path from the intermediate modification step. In addition, the present application embodiment also provides a friendly display interface, which can display the recommended degree of the candidate reply antibody sequence and the evaluation result of the antibody sequence in a graded manner, so that the object can determine the modification direction of the antibody sequence.
[0323] Furthermore, the technical solution of the embodiment of the present application is applied to the humanization modification of antibodies, and compared with the existing antibody modification methods as follows:
[0324] In one example, the antibody modification method provided in the embodiment of the present application is applied to the patent data of humanized mouse antibodies in the public data set Hu-mab25pairs, and the test results are shown in Table 4:
[0325] Table 4: Hu-mab 25pairs dataset test results
[0326] Metric Hu-mab Iter-1 Iter-2 Mutation Ratio 0.585 1.04 0.95 Overlap Ratio(OR) 0.725 0.85 0.905 Adjusted OR 0.81 0.915 0.95
[0327] In Table 4, Mutation Ratio indicates the ratio of the number of mutations to the number of mutations in the patented antibody, and Overlap Ratio indicates the ratio of residue consistency between the mutated antibody and the mutated antibody in the patented antibody. The higher the consistency between Mutation Ratio and Overlap Ratio, the better the effect. Adjusted OR indicates that similar antibodies are also considered to be overlaps. For example, if A and A are similar, and A and S are also similar, then if the mutated antibodies are similar, they are also considered to be consistent. Iter-1 indicates the first round of transformation, i.e., CDR transformation, and Iter-2 indicates the second round of transformation, i.e., reversion transformation. The results of the open source deep learning model Hu-mab[1] are used for comparison. In addition, on the same test data set, the overlap results reported by the commercial software MOE and WeMol are also 0.9, which is basically consistent with the results of this application. Moreover, the Mutation Ratio of the antibody transformation method provided in the embodiment of this application has reached a fairly high result (0.95), and the overlap using similarity adjustment has also reached 0.95, indicating that the antibody transformation method provided in the embodiment of this application is basically consistent with the transformation scheme of the patent.
[0328] In one example, if Fig.11 The humanization score evaluation of the antibody humanization transformation shown in the embodiment of the present application shows that in terms of humanization transformation, under multiple humanization degree threshold conditions, the humanization score of the overall transformation is maintained at 60% to 90%.
[0329] In one example, the test results of the embodiment of the present application in terms of consistency of the transformation of key positions are shown in Table 5:
[0330] Table 5: Key location consistency test results
[0331] Item Num Parent Template Final Upper 18 0.89 0.86 0.91 Lower 10 0.78 0.84 0.84 VH / VL Angle 13 0.84 0.92 0.94 Ag Contact 12 0.926 0.87 0.926 CSR 16 0.94 0.93 0.95 Charge Cluster 12 0.72 0.85 0.86 Phi Angle 18 0.84 0.9 0.92
[0332] Among them, Upper: is the upper hydrophobic core residue, which affects the conformational changes of CDR-H1;
[0333] Lower: lower hydrophobic core residues;
[0334] VH / VL Angle: residues that affect the stacking angle of the heavy and light chains;
[0335] Ag Contact: residues that affect antibody-antigen binding;
[0336] CSR: residues that affect the conformation of antibody CDR;
[0337] Charge Cluster: residues that affect the charge distribution on the antibody surface;
[0338] Phi Angle: Structural residues at the corners, residues that affect antibody folding.
[0339] The higher the consistency between the modified residues and the patent residues at the main key positions, the better the effect. Parent in Table 5 indicates the consistency between the mouse antibody residues and the patent residues, Template indicates the consistency with the patent residues after CDR transplantation and template replacement, and Final indicates the evaluation results after two rounds of transformation. As shown in Table 5, the technical solution of the embodiment of the present application, the overall consistency of the key positions with the patent antibody residues after humanization transformation reaches 0.91.
[0340] Combination of the above Figures 2 to 11 , describes in detail the method embodiment of the present application, and the following is combined with Figure 12 to Figure 13 , describe in detail the device embodiments of the present application.
[0341] Fig.12 It is a schematic block diagram of an antibody modification device provided in one embodiment of the present application.
[0342] like Fig.12 As shown, the antibody modification device 10 comprises:
[0343] An acquisition unit 11 is used to receive a first species antibody sequence to be modified input by a subject, and to acquire N second species antibody template sequences used to modify the first species antibody sequence, where N is a positive integer;
[0344] A consistency determination unit 12, configured to determine consistency information between the N second species antibody template sequences and the first species antibody sequence on M different indicators, wherein M is a positive integer;
[0345] A template selection unit 13, configured to select P second species antibody template sequences from the N second species antibody template sequences based on consistency information between the N second species antibody template sequences and the first species antibody sequence on M different indicators, wherein P is a positive integer less than or equal to N;
[0346] The transformation unit 14 is used to transform the first species antibody sequence based on the P second species antibody template sequences to obtain a transformed target antibody sequence, wherein the transformation is used to recombine some amino acids of the first species antibody template sequence with some amino acids of the second species antibody sequence.
[0347] In some embodiments, the consistency determination unit 12 is specifically used to obtain a first antibody sequence numbering method, and use the first antibody sequence numbering method to number the amino acids included in the first species antibody sequence and the N second species antibody template sequences; extract the basic information of the numbered first species antibody sequence, and the basic information of the numbered N second species antibody template sequences; for the i-th second species antibody template sequence among the N second species antibody template sequences, based on the basic information of the first species antibody sequence and the basic information of the i-th second species antibody template sequence, determine the consistency information of the first species antibody sequence and the i-th second species antibody template sequence on the M different indicators, where i is a positive integer less than or equal to N.
[0348] In some embodiments, if the basic information includes at least one of an antibody initial sequence, a framework sequence, and key residues, and the M different indicators include at least one of a full sequence, a framework sequence, and key residues, the consistency determination unit 12 is specifically configured to perform a full sequence comparison of the antibody initial sequence of the first species antibody sequence with the antibody initial sequence of the i-th second species antibody template sequence to determine the full sequence consistency information between the first species antibody sequence and the i-th second species antibody template sequence; compare the key residues of the first species antibody sequence with the key residues of the i-th second species antibody template sequence to determine the key residue consistency information between the first species antibody sequence and the i-th second species antibody template sequence; compare the framework sequence of the first species antibody sequence with the framework sequence of the i-th second species antibody template sequence to determine the framework sequence consistency information between the first species antibody sequence and the i-th second species antibody template sequence.
[0349] In some embodiments, the template selection unit 13 is specifically used to display the consistency information of the N second species antibody template sequences and the first species antibody sequence on the M different indicators; in response to the object's selection operation of the P second species antibody template sequences among the N second species antibody template sequences based on the consistency information, the P second species antibody template sequences are selected.
[0350] In some embodiments, the transformation unit 14 is specifically used to perform CDR transplantation on the jth second species antibody template sequence among the P second species antibody template sequences using the first species antibody sequence to obtain the jth antibody template sequence after transplantation, where j is a positive integer less than or equal to P; perform back mutation transformation on the jth antibody template sequence after transplantation to obtain Q candidate back mutation sequences, where Q is a positive integer; perform a first evaluation on each of the Q candidate back mutation sequences to obtain first evaluation information of each candidate back mutation list; based on the first evaluation information of the Q candidate back mutation sequences, select R candidate back mutation sequences from the Q candidate back mutation sequences, where R is a positive integer less than or equal to Q; based on the R candidate back mutation sequences, generate the jth target back mutation sequence, where the jth target back mutation sequence includes the mutated residues of the R candidate back mutation sequences; based on the P target back mutation sequences corresponding to the P second species antibody template sequences, obtain the transformed target antibody sequence.
[0351] In some embodiments, the transformation unit 14 is specifically used to perform a second evaluation on the j-th antibody template sequence after transplantation to obtain second evaluation information of the j-th antibody template sequence after transplantation; if it is determined based on the second evaluation information that the j-th antibody template sequence after transplantation should continue to be transformed, then the j-th antibody template sequence after transplantation is reversely mutated to obtain Q candidate reverse mutation sequences.
[0352] In some embodiments, the first evaluation information includes the recommendation degree of the candidate back mutation sequence, and the transformation unit 14 is specifically used to determine, for each of the Q candidate back mutation sequences, change information of the mutated residues in the candidate back mutation sequence before and after mutation on K indicators, wherein the K indicators include at least one of statistical frequency, residue type, key residue type, three-dimensional structure position and interaction, and K is a positive integer; based on the change information of the mutated residues in the candidate back mutation sequence before and after mutation on the K indicators, determine the recommendation degree of the candidate back mutation sequence.
[0353] In some embodiments, the transformation unit 14 is specifically used to input the change information of the mutated residues in the candidate back mutation sequence on the K indicators before and after the mutation into the recommendation degree prediction model to obtain the recommendation degree of the candidate back mutation sequence.
[0354] In some embodiments, the first evaluation information includes rapid evaluation information of the candidate back mutation sequence, and the transformation unit 14 is specifically used to quickly evaluate the mutated residues in the candidate back mutation sequence for each of the Q candidate back mutation sequences to obtain the rapid evaluation information of the candidate back mutation sequence.
[0355] In some embodiments, the rapid assessment information of the candidate back mutation sequence includes at least one of: mutation score, sequence position information, three-dimensional structure position information, humanization assessment and thermal stability.
[0356] In some embodiments, the transformation unit 14 is specifically used to obtain an antibody transformation method, which includes a non-automatic transformation method and an automatic transformation method; if the antibody transformation method is the non-automatic transformation method, the first evaluation information of the Q candidate back mutation sequences is displayed, and the object receives a selection operation of the R candidate back mutation sequences among the Q candidate back mutation sequences based on the first evaluation information, and selects the R candidate back mutation sequences; if the antibody transformation method is the automatic transformation method, R candidate back mutation sequences whose first evaluation information meets the preset requirements are selected from the Q candidate back mutation sequences.
[0357] In some embodiments, the first evaluation information includes the recommendation level of the candidate back mutation sequence, and the transformation unit 14 is specifically used to display the recommendation levels of the Q candidate back mutation sequences in grades based on the preset display formats corresponding to the different levels of recommendation levels.
[0358] In some embodiments, the transformation unit 14 is specifically used to perform a second evaluation on each of the P target reverse mutation sequences to obtain second evaluation information of each target reverse mutation sequence; based on the second evaluation information of the P target reverse mutation sequences, determine the transformed target antibody sequence.
[0359] In some embodiments, the transformation unit 14 is specifically used to display second evaluation information of the target back mutation sequence; in response to the transformation operation input by the subject based on the second evaluation information, the transformed target antibody sequence is obtained, and the transformation operation is used to indicate whether to continue to transform the target back mutation sequence.
[0360] In some embodiments, the transformation unit 14 is specifically used to perform a statistical distribution analysis on each evaluation indicator in the second evaluation information of the patent antibody data to obtain a reference threshold value for each evaluation indicator; compare each evaluation indicator in the second evaluation information of the target reverse mutation sequence with the corresponding reference threshold value to determine the display format of the numerical value of the evaluation indicator of the second evaluation information of the target reverse mutation sequence; based on the display format, display each evaluation indicator in the second evaluation information of the target reverse mutation sequence in a graded manner.
[0361] In some embodiments, the second evaluation information includes at least one of sequence evaluation information, structure evaluation information, and feasibility evaluation information of the antibody sequence.
[0362] In some embodiments, the transformation unit 14 is also used to display the transformation information corresponding to the j-th second species antibody template sequence, wherein the transformation information includes the first species antibody sequence, the j-th second species antibody template sequence after transplantation and the j-th target reverse mutation sequence, and at least one of the humanization scores and structural consistency scores corresponding to the first species antibody sequence, the j-th second species antibody template sequence after transplantation and the j-th target reverse mutation sequence, respectively.
[0363] In some embodiments, the N second species antibody template series include template sequences of multiple antibody subfamilies, and second species antibody template series in patent antibody data.
[0364] It should be understood that the device embodiment and the method embodiment may correspond to each other, and similar descriptions may refer to the method embodiment. To avoid repetition, they will not be described here. Specifically, Fig.12 The device shown can execute the embodiments of the above method, and the aforementioned and other operations and / or functions of each module in the device are respectively for realizing the embodiments of the above method, which will not be described in detail here for the sake of brevity.
[0365] The above describes the device of the embodiment of the present application from the perspective of the functional module in conjunction with the accompanying drawings. It should be understood that the functional module can be implemented in hardware form, can be implemented by instructions in software form, and can also be implemented by a combination of hardware and software modules. Specifically, the steps of the method embodiment in the embodiment of the present application can be completed by the hardware integrated logic circuit and / or software form instructions in the processor, and the steps of the method disclosed in the embodiment of the present application can be directly embodied as a hardware decoding processor to perform, or a combination of hardware and software modules in the decoding processor to perform. Optionally, the software module can be located in a mature storage medium in the field such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory, an electrically erasable programmable memory, a register, etc. The storage medium is located in a memory, and the processor reads the information in the memory, and completes the steps in the above method embodiment in conjunction with its hardware.
[0366] Fig.13 It is a schematic block diagram of an electronic device provided in an embodiment of the present application, and the electronic device may be the above-mentioned terminal device or server.
[0367] like Fig.13 As shown, the electronic device 40 may include:
[0368] The memory 41 and the processor 42, the memory 41 is used to store the computer program 43 and transmit the program code 43 to the processor 42. In other words, the processor 42 can call and run the computer program 43 from the memory 41 to implement the method in the embodiment of the present application.
[0369] For example, the processor 42 may be configured to execute the steps in the above method according to the instructions in the computer program 43 .
[0370] In some embodiments of the present application, the processor 42 may include but is not limited to:
[0371] General-purpose processor, digital signal processor (DSP), application-specific integrated circuit (ASIC), field programmable gate array (FPGA) or other programmable logic device, discrete gate or transistor logic device, discrete hardware components, etc.
[0372] In some embodiments of the present application, the memory 41 includes but is not limited to:
[0373] Volatile memory and / or non-volatile memory. Among them, the non-volatile memory can be read-only memory (ROM), programmable ROM (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM) or flash memory. The volatile memory can be random access memory (RAM), which is used as an external cache. By way of example and not limitation, many forms of RAM are available, such as static random access memory (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDR SDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous link DRAM (SLDRAM), and direct RAM bus random access memory (DR RAM).
[0374] In some embodiments of the present application, the computer program 43 may be divided into one or more modules, which are stored in the memory 41 and executed by the processor 42 to complete the method for recording pages provided by the present application. The one or more modules may be a series of computer program instruction segments capable of completing specific functions, and the instruction segments are used to describe the execution process of the computer program 43 in the electronic device.
[0375] like Fig.13 As shown, the electronic device 40 may further include:
[0376] The transceiver 44 may be connected to the processor 42 or the memory 41 .
[0377] The processor 42 may control the transceiver 44 to communicate with other devices, specifically, to send information or data to other devices, or to receive information or data sent by other devices. The transceiver 34 may include a transmitter and a receiver. The transceiver 44 may further include an antenna, and the number of antennas may be one or more.
[0378] It should be understood that the various components in the electronic device 40 are connected via a bus system, wherein the bus system includes not only a data bus but also a power bus, a control bus and a status signal bus.
[0379] According to one aspect of the present application, a computer storage medium is provided, on which a computer program is stored, and when the computer program is executed by a computer, the computer can perform the method of the above method embodiment. In other words, the present application embodiment also provides a computer program product containing instructions, and when the instructions are executed by a computer, the computer can perform the method of the above method embodiment.
[0380] According to another aspect of the present application, a computer program product or computer program is provided, the computer program product or computer program includes computer instructions, the computer instructions are stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device executes the method of the above method embodiment.
[0381] In other words, when implemented using software, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the process or function according to the embodiment of the present application is generated in whole or in part. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions may be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions may be transmitted from a website site, a computer, a server, or a data center by wired (e.g., coaxial cable, optical fiber, digital subscriber line (digital subscriber line, DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) mode to another website site, computer, server, or data center. The computer-readable storage medium may be any available medium that a computer can access or a data storage device such as a server or a data center that includes one or more available media integrated. The available medium may be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a digital video disc (digital video disc, DVD)), or a semiconductor medium (e.g., a solid state drive (solid state disk, SSD)), etc.
[0382] Those of ordinary skill in the art will appreciate that the modules and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.
[0383] In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the module is only a logical function division. There may be other division methods in actual implementation, such as multiple modules or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or modules, which can be electrical, mechanical or other forms.
[0384] The modules described as separate components may or may not be physically separated, and the components displayed as modules may or may not be physical modules, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. For example, each functional module in each embodiment of the present application may be integrated into a processing module, or each module may exist physically separately, or two or more modules may be integrated into one module.
[0385] The above contents are only specific implementation methods of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.
Claims
1. A method for antibody modification, characterized in that: include: Receive a first species antibody sequence to be modified from a subject, and obtain N second species antibody template sequences for modifying the first species antibody sequence, where N is a positive integer; Determine the consistency information between the N second species antibody template sequences and the first species antibody sequence on M different indicators, where M is a positive integer; Based on the consistency information between the N second species antibody template sequences and the first species antibody sequence on M different indicators, P second species antibody template sequences are selected from the N second species antibody template sequences, where P is a positive integer less than or equal to N; Based on the P second species antibody template sequences, the first species antibody sequence is modified to obtain a modified target antibody sequence, wherein the modification is used to recombine some amino acids of the first species antibody template sequence with some amino acids of the second species antibody sequence.
2. The method according to claim 1, characterized in that Determining the consistency information between the N second species antibody template sequences and the first species antibody sequence on M different indicators includes: Obtaining a first antibody sequence numbering method, and using the first antibody sequence numbering method to number the amino acids included in the first species antibody sequence and the N second species antibody template sequences; Extracting basic information of the numbered first species antibody sequence and basic information of the numbered N second species antibody template sequences; For the i-th second species antibody template sequence among the N second species antibody template sequences, based on the basic information of the first species antibody sequence and the basic information of the i-th second species antibody template sequence, the consistency information between the first species antibody sequence and the i-th second species antibody template sequence on the M different indicators is determined, where i is a positive integer less than or equal to N.
3. The method according to claim 2, characterized in that If the M different indicators include at least one of the full sequence, the framework sequence, and the key residues, and the basic information includes at least one of the antibody initial sequence, the framework sequence, and the key residues, determining the consistency information between the first species antibody sequence and the i-th second species antibody template sequence on the M different indicators based on the basic information of the first species antibody sequence and the basic information of the i-th second species antibody template sequence includes: Performing a full sequence comparison of the antibody initial sequence of the first species antibody sequence with the antibody initial sequence of the i-th second species antibody template sequence to determine full sequence identity information between the first species antibody sequence and the i-th second species antibody template sequence; Comparing the key residues of the first species antibody sequence with the key residues of the i-th second species antibody template sequence to determine the key residue consistency information between the first species antibody sequence and the i-th second species antibody template sequence; The framework region sequence of the first species antibody sequence and the framework region sequence of the i-th second species antibody template sequence are compared to determine the framework region sequence identity information between the first species antibody sequence and the i-th second species antibody template sequence.
4. The method according to claim 1, characterized in that: The selecting P second species antibody template sequences from the N second species antibody template sequences based on the consistency information between the N second species antibody template sequences and the first species antibody sequence on M different indicators comprises: Display the consistency information of the N second species antibody template sequences and the first species antibody sequence on the M different indicators; In response to the object selecting the P second species antibody template sequences from the N second species antibody template sequences based on the consistency information, the P second species antibody template sequences are selected.
5. The method according to any one of claims 1 to 4, characterized in that: The method of modifying the first species antibody sequence based on the P second species antibody template sequences to obtain a modified target antibody sequence comprises: For the j-th second species antibody template sequence among the P second species antibody template sequences, using the first species antibody sequence to perform CDR transplantation on the j-th second species antibody template sequence to obtain a transplanted j-th antibody template sequence, where j is a positive integer less than or equal to P; Performing back mutation transformation on the j-th antibody template sequence after the transplantation to obtain Q candidate back mutation sequences, where Q is a positive integer; Performing a first evaluation on each of the Q candidate back mutation sequences to obtain first evaluation information of each candidate back mutation list; Based on the first evaluation information of the Q candidate back mutation sequences, select R candidate back mutation sequences from the Q candidate back mutation sequences, where R is a positive integer less than or equal to Q; Based on the R candidate back mutation sequences, generating the j-th target back mutation sequence, wherein the j-th target back mutation sequence includes the mutated residues of the R candidate back mutation sequences; Based on the P target back mutation sequences corresponding to the P second species antibody template sequences, the modified target antibody sequence is obtained.
6. The method according to claim 5, characterized in that The j-th antibody template sequence after the transplantation is subjected to back mutation modification to obtain Q candidate back mutation sequences, including: Performing a second evaluation on the j-th antibody template sequence after the transplantation to obtain second evaluation information of the j-th antibody template sequence after the transplantation; If it is determined based on the second evaluation information that the j-th antibody template sequence after the transplantation is to be further modified, then the j-th antibody template sequence after the transplantation is subjected to back mutation modification to obtain Q candidate back mutation sequences.
7. The method according to claim 5, characterized in that The first evaluation information includes the recommendation degree of the candidate back mutation sequence, and the first evaluation is performed on each of the Q candidate back mutation sequences to obtain the first evaluation information of each candidate back mutation list, including: For each of the Q candidate back mutation sequences, determining the change information of the mutated residues in the candidate back mutation sequence before and after the mutation on K indicators, wherein the K indicators include at least one of statistical frequency, residue type, key residue type, three-dimensional structure position and interaction, and K is a positive integer; Based on the change information of the mutated residues in the candidate back mutation sequence on the K indicators before and after the mutation, the recommendation degree of the candidate back mutation sequence is determined.
8. The method according to claim 7, characterized in that The step of determining the recommendation degree of the candidate back mutation sequence based on the change information of the mutated residues in the candidate back mutation sequence on the K indicators before and after the mutation comprises: The change information of the mutated residues in the candidate back mutation sequence on the K indicators before and after the mutation is input into the recommendation degree prediction model to obtain the recommendation degree of the candidate back mutation sequence.
9. The method according to claim 5, characterized in that The first evaluation information includes rapid evaluation information of the candidate back mutation sequence, and the first evaluation is performed on each of the Q candidate back mutation sequences to obtain first evaluation information of each candidate back mutation list, including: For each of the Q candidate back mutation sequences, a rapid evaluation is performed on the mutated residues in the candidate back mutation sequence to obtain rapid evaluation information of the candidate back mutation sequence.
10. The method according to claim 9, characterized in that The rapid assessment information of the candidate back mutation sequence includes at least one of mutation score, sequence position information, three-dimensional structure position information, humanization assessment and thermal stability.
11. The method according to claim 5, characterized in that The step of selecting R candidate back mutation sequences from the Q candidate back mutation sequences based on the first evaluation information of the Q candidate back mutation sequences comprises: Obtaining an antibody modification method, wherein the antibody modification method includes a non-automatic modification method and an automatic modification method; If the antibody modification method is the non-automatic modification method, the first evaluation information of the Q candidate back mutation sequences is displayed, and a selection operation of the subject on the R candidate back mutation sequences among the Q candidate back mutation sequences based on the first evaluation information is received to select the R candidate back mutation sequences; If the antibody modification method is the automatic modification method, R candidate back mutation sequences whose first evaluation information meets preset requirements are selected from the Q candidate back mutation sequences.
12. The method according to claim 5, characterized in that The step of obtaining the modified target antibody sequence based on the P target reverse mutation sequences corresponding to the P second species antibody template sequences comprises: Performing a second evaluation on each of the P target reverse mutation sequences to obtain second evaluation information of each target reverse mutation sequence; Based on the second evaluation information of the P target back mutation sequences, the modified target antibody sequence is determined.
13. The method according to claim 12, characterized in that The step of determining the modified target antibody sequence based on the second evaluation information of the P target back-mutated sequences comprises: Displaying second evaluation information of the target reverse mutation sequence; In response to the transformation operation input by the subject based on the second evaluation information, the transformed target antibody sequence is obtained, and the transformation operation is used to indicate whether to continue to transform the target reverse mutation sequence.
14. The method according to claim 13, characterized in that The second evaluation information showing the target reverse mutation sequence includes: Performing statistical distribution analysis on each evaluation indicator in the second evaluation information of the patent antibody data to obtain a reference threshold value for each evaluation indicator; Comparing each evaluation index in the second evaluation information of the target back mutation sequence with the corresponding reference threshold, and determining a display format of the numerical value of the evaluation index in the second evaluation information of the target back mutation sequence; Based on the display format, each evaluation index in the second evaluation information of the target back mutation sequence is displayed in grades.
15. The method according to any one of claims 6, 12 and 14, characterized in that: The second evaluation information includes at least one of sequence evaluation information, structure evaluation information and feasibility evaluation information of the antibody sequence.
16. The method according to claim 5, characterized in that The method further comprises: The transformation information corresponding to the j-th second species antibody template sequence is displayed, wherein the transformation information includes the first species antibody sequence, the j-th second species antibody template sequence after transplantation, and the j-th target reverse mutation sequence, and at least one of the humanization scores and the structural consistency scores corresponding to the first species antibody sequence, the j-th second species antibody template sequence after transplantation, and the j-th target reverse mutation sequence, respectively.
17. The method according to claim 1, characterized in that The N second species antibody template series include template sequences of multiple antibody subfamilies, and second species antibody template series in patent antibody data.
18. An antibody modification device, characterized in that: include: an acquisition unit, configured to receive a first species antibody sequence to be modified input by a subject, and to acquire N second species antibody template sequences for modifying the first species antibody sequence, wherein N is a positive integer; a consistency determination unit, configured to determine consistency information between the N second species antibody template sequences and the first species antibody sequence on M different indicators, where M is a positive integer; a template selection unit, configured to select P second species antibody template sequences from the N second species antibody template sequences based on consistency information between the N second species antibody template sequences and the first species antibody sequence on M different indicators, wherein P is a positive integer less than or equal to N; A transformation unit is used to transform the first species antibody sequence based on the P second species antibody template sequences to obtain a transformed target antibody sequence, wherein the transformation is used to recombine some amino acids of the first species antibody template sequence with some amino acids of the second species antibody sequence.
19. An electronic device comprising a processor and a memory; The memory is used to store computer programs; The processor is used to execute the computer program to implement the method according to any one of claims 1 to 17.
20. A computer-readable storage medium, characterized in that: For storing computer programs; The computer program enables a computer to execute the method according to any one of claims 1 to 17.
Citation Information
Patent Citations
Method for reforming antibody in humanized way
CN102863533A
Antibody humanization transformation method
CN103145834A
Method for antibody humanization based on three-dimensional structure
CN116052760A
Construction method for humanized antibody sequence evaluation model and use thereof
US20260148804A1
Cited By
Multi-modal protein design method, device and system and storage medium thereof
CN119943206A
A multi-modal protein design method, device, system and storage medium thereof
CN119943206B
