Antibody data processing method and device, electronic equipment and storage medium

Abstract

The invention provides an antibody data processing method, and relates to the technical field of artificial intelligence, in particular to the technical fields of deep learning, antibody screening, biological calculation, heterogeneous calculation and the like. The specific implementation scheme is as follows: according to input antibody sequence data and input target sequence data, determining a first reference sequence feature and a first reference structure feature corresponding to the input antibody sequence data, and a second reference sequence feature and a second reference structure feature corresponding to the input target sequence data; determining conformation data of a compound to be screened according to the input antibody sequence data, the input target sequence data, the first reference sequence feature, the first reference structure feature, the second reference sequence feature and the second reference structure feature; and determining a target antibody according to the input antibody sequence data in response to determining that the conformation data of the to-be-screened compound meets a preset condition. The invention further provides an antibody data processing device, electronic equipment and a storage medium.

Description

Technical Field

[0001] The present disclosure relates to the field of artificial intelligence technology, and in particular to the technical fields of deep learning, antibody screening, biological computing, and heterogeneous computing. More specifically, the present disclosure provides an antibody data processing method, device, electronic device, and storage medium. Background Art

[0002] With the development of artificial intelligence technology, amino acid sequence data can be processed using artificial intelligence technology. Summary of the invention

[0003] The present disclosure provides an antibody data processing method, apparatus, device and storage medium.

[0004] According to one aspect of the present disclosure, a method for processing antibody data is provided, the method comprising: determining, based on input antibody sequence data and input target sequence data, a first reference sequence feature and a first reference structure feature corresponding to the input antibody sequence data, and a second reference sequence feature and a second reference structure feature corresponding to the input target sequence data; determining conformational data of a complex to be screened based on the input antibody sequence data, the input target sequence data, the first reference sequence feature, the first reference structure feature, the second reference sequence feature, and the second reference structure feature; in response to determining that the conformational data of the complex to be screened meets a preset condition, determining a target antibody based on the input antibody sequence data.

[0005] According to another aspect of the present disclosure, an antibody data processing device is provided, the device comprising: a first determination module, for determining, based on input antibody sequence data and input target sequence data, a first reference sequence feature and a first reference structure feature corresponding to the input antibody sequence data, and a second reference sequence feature and a second reference structure feature corresponding to the input target sequence data; a second determination module, for determining, based on the input antibody sequence data, the input target sequence data, the first reference sequence feature, the first reference structure feature, the second reference sequence feature and the second reference structure feature, conformational data of a complex to be screened; and a third determination module, for determining, in response to determining that the conformational data of the complex to be screened meets a preset condition, a target antibody based on the input antibody sequence data.

[0006] According to another aspect of the present disclosure, an electronic device is provided, comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the method provided according to the present disclosure.

[0007] According to another aspect of the present disclosure, a non-transitory computer-readable storage medium storing computer instructions is provided. The computer instructions are used to cause a computer to execute the method provided according to the present disclosure.

[0008] According to another aspect of the present disclosure, a computer program product is provided, including a computer program, and when the computer program is executed by a processor, the method provided according to the present disclosure is implemented.

[0009] It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present disclosure, nor is it intended to limit the scope of the present disclosure. Other features of the present disclosure will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] The accompanying drawings are used to better understand the present solution and do not constitute a limitation of the present disclosure.

[0011] Figure 1 is a schematic diagram of an exemplary system architecture to which an antibody data processing method and apparatus can be applied according to an embodiment of the present disclosure;

[0012] Figure 2 is a flow chart of an antibody data processing method according to an embodiment of the present disclosure;

[0013] Figure 3 is a schematic diagram of an antibody data processing method according to an embodiment of the present disclosure;

[0014] Figure 4 is a block diagram of an antibody data processing apparatus according to an embodiment of the present disclosure; and

[0015] Figure 5 is a block diagram of an electronic device to which the antibody data processing method can be applied according to an embodiment of the present disclosure. DETAILED DESCRIPTION

[0016] The following is a description of exemplary embodiments of the present disclosure in conjunction with the accompanying drawings, including various details of the embodiments of the present disclosure to facilitate understanding, which should be considered as merely exemplary. Therefore, it should be recognized by those of ordinary skill in the art that various changes and modifications may be made to the embodiments described herein without departing from the scope and spirit of the present disclosure. Similarly, for the sake of clarity and conciseness, descriptions of well-known functions and structures are omitted in the following description.

[0017] Antibody screening can be performed based on wet experimental techniques. Wet experimental techniques, for example, can include gene mutation combined with phage display, yeast display and other technologies, which can be used to screen antibodies that can bind to targets. Antibody libraries can also be screened by immunizing animals (such as mice, cats, dogs, etc.). In order to implement wet experimental techniques, high manpower and time costs are required for a large number of screenings, and the experimental cycle is long. In addition, the binding sites and binding modes of the antibodies with affinity obtained by screening are difficult to determine, and other downstream physical and chemical experiments are required to determine the properties of the antibodies.

[0018] In some embodiments, based on standard phage display technology or yeast display technology, some biotechnology service companies can screen private antibody libraries for antigen targets provided by customers, or screen based on antibody library sequences provided by customers. However, the experimental cycle of standard phage display technology or yeast display technology is more than two months, and it is difficult to concretely determine the docking status between the antibodies screened from the antibody library and the target. The docking site between the antibody and the target is also unclear.

[0019] In some embodiments, antibody screening can also be performed through computer-assisted virtual screening schemes. However, virtual screening often cannot achieve end-to-end predictions. Moreover, based on the virtual screening scheme, the effect of antigen-antibody prediction is also poor. For example, based on the Alphafold-Multimer algorithm, antibody screening can be performed. However, the algorithm also has poor conformational prediction accuracy for antigen-antibody complexes. For scenarios that rely on conformation for evaluation, it is also difficult to obtain effective evaluation indicators. In addition, the algorithm has poor interaction capabilities with users, resulting in poor user experience for users in fields such as biology and chemistry, and is difficult to apply on a large scale.

[0020] Therefore, in order to efficiently perform antibody screening, the present disclosure provides an antibody data processing method, which will be described below.

[0021] Figure 1 is a schematic diagram of an exemplary system architecture to which the antibody data processing method and apparatus can be applied according to an embodiment of the present disclosure. It should be noted that: Figure 1 What is shown is merely an example of a system architecture to which the embodiments of the present disclosure can be applied, in order to help those skilled in the art understand the technical content of the present disclosure, but it does not mean that the embodiments of the present disclosure cannot be used in other devices, systems, environments or scenarios.

[0022] like Figure 1As shown, the system architecture 100 according to this embodiment may include terminal devices 101, 102, 103, a network 104 and a server 105. The network 104 is used to provide a medium for communication links between the terminal devices 101, 102, 103 and the server 105. The network 104 may include various connection types, such as wired and / or wireless communication links, etc.

[0023] Users can use terminal devices 101, 102, 103 to interact with server 105 through network 104 to receive or send messages, etc. Terminal devices 101, 102, 103 can be various electronic devices with display screens and supporting web browsing, including but not limited to smart phones, tablet computers, laptops, desktop computers, etc.

[0024] The server 105 may be a server that provides various services, such as a background management server (only as an example) that provides support for websites browsed by users using the terminal devices 101, 102, and 103. The background management server may analyze and process the received data such as user requests, and feed back the processing results (such as web pages, information, or data obtained or generated according to user requests) to the terminal device.

[0025] It should be noted that the antibody data processing method provided in the embodiment of the present disclosure can generally be executed by the server 105. Accordingly, the antibody data processing device provided in the embodiment of the present disclosure can generally be set in the server 105. The antibody data processing method provided in the embodiment of the present disclosure can also be executed by a server or server cluster that is different from the server 105 and can communicate with the terminal devices 101, 102, 103 and / or the server 105. Accordingly, the antibody data processing device provided in the embodiment of the present disclosure can also be set in a server or server cluster that is different from the server 105 and can communicate with the terminal devices 101, 102, 103 and / or the server 105.

[0026] Figure 2 is a flowchart of an antibody data processing method according to an embodiment of the present disclosure.

[0027] like Figure 2 As shown, the method 200 may include operations S210 to S230.

[0028] In operation S210, a first reference sequence feature and a first reference structural feature corresponding to the input antibody sequence data, and a second reference sequence feature and a second reference structural feature corresponding to the input target sequence data are determined based on the input antibody sequence data and the input target sequence data.

[0029] In the disclosed embodiments, the input antibody sequence data may be one or more. The input target sequence data may be one or more.

[0030] In the disclosed embodiment, a multiple sequence alignment (MSA) may be performed based on the sequence data to determine a first reference sequence feature of the input antibody sequence data and a second reference sequence feature of the input target sequence data.

[0031] In the disclosed embodiment, a template query may be performed based on the sequence data to determine a first reference structural feature of the input antibody sequence data and a second reference structural feature of the input target sequence data.

[0032] In operation S220, the conformational data of the complex to be screened is determined based on the input antibody sequence data, the input target sequence data, the first reference sequence feature, the first reference structure feature, the second reference sequence feature, and the second reference structure feature.

[0033] In the disclosed embodiments, the conformational data of the complex to be screened may represent the docking status between the input antibody and the input target.

[0034] In operation S230, in response to determining that the conformational data of the complex to be screened meets a preset condition, a target antibody is determined according to the input antibody sequence data.

[0035] In the disclosed embodiments, the preset conditions may be related to the docking condition of the complex to be screened. For example, the complex to be screened may correspond to one or more index values. If the index value is greater than or equal to the preset index threshold, it can be determined that the conformation of the complex to be screened meets the preset conditions.

[0036] Through the embodiments of the present disclosure, the conformation of the complex can be determined based on the input antibody, input target, reference sequence characteristics and reference structure characteristics, and clear complex conformation data can be provided to the user, so that the user has a more intuitive understanding of the docking status of the antigen and the target, which can effectively improve the user experience.

[0037] It can be understood that the method of the present disclosure is described above, and the method of the present disclosure will be further described below.

[0038] Figure 3 is a schematic diagram of antibody data processing according to one embodiment of the present disclosure.

[0039] In some embodiments, the input antibody sequence data may be N. The input target sequence data may be M. N may be an integer greater than or equal to 1. M may be an integer greater than or equal to 1. Figure 3As shown, taking N and M as examples both greater than 1, the N input antibody sequence data may include input antibody sequence data src31, input antibody sequence data src32, ... input antibody sequence data src33. The M input target sequence data may include input target sequence data tgt31, ... input target sequence data tgt32.

[0040] like Figure 3 As shown, for N input antibody sequence data and M input target sequence data, operation S310 can be performed to perform multiple sequence alignment and template query. It can be understood that the above description of operation S210 is also applicable to operation S310, and operation S310 will be further described below based on the above description of operation S210.

[0041] In some embodiments, determining the first reference sequence feature and the first reference structural feature corresponding to the input antibody sequence data, the second reference sequence feature and the second reference structural feature corresponding to the input target sequence data according to the input antibody sequence data and the input target sequence data may include: determining at least one first reference sequence data corresponding to the input antibody sequence data and at least one second reference sequence data corresponding to the input target sequence data from a reference sequence database. Determining at least one first reference template data corresponding to the input antibody sequence data and at least one second reference template data corresponding to the input target sequence data from a reference template database. Determining the first reference sequence feature and the second reference sequence feature according to the at least one first reference sequence data and the at least one second reference sequence data. Determining the first reference structural feature and the second reference structural feature according to the at least one first reference template data and the at least one second reference template data.

[0042] In the embodiments of the present disclosure, the reference sequence database may include multiple reference sequence data. The sequence data may be amino acid sequence data. Figure 3As shown, according to the input antibody sequence data src31, multiple sequence alignment is performed, and one or more first reference sequence data can be determined from the reference sequence database. According to the one or more first reference sequence data, the first reference sequence feature of the input antibody sequence data src31 can be determined. It can be understood that the method of determining the first reference sequence feature of the input antibody sequence data src32 and the input antibody sequence data src33 is the same or similar to the method of determining the first reference sequence feature of the input antibody sequence data src31, and the present disclosure will not repeat it here. In addition, according to the input target sequence data tgt31, multiple sequence alignment can be performed, and one or more second reference sequence data can be determined from the reference sequence database. According to the one or more second reference sequence data, the second reference sequence feature of the input target sequence data tgt31 can be determined. It can be understood that the method of determining the second reference sequence feature of the input target sequence data tgt32 is the same or similar to the method of determining the second reference sequence feature of the input target sequence data tgt31, and the present disclosure will not repeat it here.

[0043] In the disclosed embodiment, the reference template database may include a plurality of reference template data. The template data may be related to at least one of the spatial structure and the planar structure of the antibody or the target. Figure 3 As shown, according to the input antibody sequence data src31, a template query is performed, and one or more first reference template data can be determined from the reference template database. According to the one or more first reference template data, the first reference structural feature of the input antibody sequence data src31 can be determined. It can be understood that the method of determining the first reference structural feature of the input antibody sequence data src32 and the input antibody sequence data src33 is the same or similar to the method of determining the first reference structural feature of the input antibody sequence data src31, and the present disclosure will not repeat it here. In addition, according to the input target sequence data tgt31, a template query can be performed, and one or more second reference template data can be determined from the reference template database. According to the one or more second reference template data, the second reference structural feature of the input target sequence data tgt31 can be determined. It can be understood that the method of determining the second reference structural feature of the input target sequence data tgt32 is the same or similar to the method of determining the second reference structural feature of the input target sequence data tgt31, and the present disclosure will not repeat it here.

[0044] It can be understood that some methods for determining reference sequence characteristics and reference structure characteristics are described above, and some methods for determining the conformation of the complex to be screened will be described below.

[0045] like Figure 3As shown, after obtaining the input sequence data, the reference sequence features and the reference structure features, operation S320 may be performed to determine the conformational data of the complex to be screened. It can be understood that the above description of operation S220 is also applicable to operation S320, and operation S320 will be further described below based on the above description of operation S220.

[0046] In some embodiments, determining the conformational data of the complex to be screened based on input antibody sequence data, input target sequence data, a first reference sequence feature, a first reference structure feature, a second reference sequence feature, and a second reference structure feature includes: determining the conformational data of the complex to be screened based on user uploaded data, input antibody sequence data, input target sequence data, a first reference sequence feature, a first reference structure feature, a second reference sequence feature, and a second reference structure feature.

[0047] In the disclosed embodiment, the user uploaded data includes at least one of antigen conformation data and antigen epitope location data. For example, the user may upload the above-mentioned antigen conformation data and antigen epitope location data. Through the disclosed embodiment, a user upload method is provided, and the complex conformation can be determined more specifically based on the user uploaded data, which can effectively improve the user experience, especially the user experience of users in the fields of biology, chemistry, etc.

[0048] In the disclosed embodiment, when the number of input antibody sequence data is N and the number of input target sequence data is M, the number of conformational data of the complex to be screened may be N×M. For example, the conformational data of the complex to be screened between each input antibody sequence data and each input target sequence data may be determined. For another example, the conformational data of the complex to be screened may be determined using a helixfold-multimer model.

[0049] It can be understood that some methods for determining the conformational data of the complex to be screened are described above, and some methods for post-processing based on the conformational data of the complex to be screened will be described below.

[0050] like Figure 3As shown, the first index calculation tool postp31 can be used to determine at least one index value of each of the N×M complex conformation data to be screened. The at least one index value may include at least one of confidence, predicted alignment error (pAE), predicted template modeling (ptm) evaluation value (score), interface predicted template modeling (iptm) evaluation value, etc. The first index calculation tool postp31 can be, for example, an index calculation tool for helical folding-polymers.

[0051] like Figure 3 As shown, the second indicator calculation tool postp32 can also be used to determine one or more indicator values. The second indicator calculation tool postp32 can be a tool selected by users such as FoldX. It is understandable that users can select various indicator calculation tools as the second indicator calculation tool.

[0052] like Figure 3 As shown, the calculation results of the first index calculation tool postp31 and the second index calculation tool postp32 can form an output result with the conformational data of the complex to be screened. The output result can be a table. The table can include N×M entries. Each entry corresponds to a conformational data of the complex to be screened.

[0053] like Figure 3 As shown, the docking information processing tool postp33 can also be used to determine the docking information of N×M complex conformation data to be screened. For example, the complex conformation data to be screened corresponds to at least one of the complex conformation coordinate data, the antibody target connection position, and the residue type. Based on the above-mentioned complex conformation coordinate data, the docking information of the complex to be screened can be determined. The docking information may include the connection position between the antibody and the target, the docking angle, the scale of the contact surface, etc. The residue type corresponding to the complex to be screened can also be determined. Through the embodiments of the present disclosure, the complex conformation can be evaluated from multiple angles to determine whether the corresponding input antibody can be used as the target antibody.

[0054] Next, based on the docking information and residue types, a visualization can be performed, which will be explained below.

[0055] In the disclosed embodiment, the method may further include: determining at least one visual image based on the conformational data of the complex to be screened. Displaying at least one of the conformational data of the complex to be screened and the at least one visual image using a visual interface. For example, a three-dimensional image may be generated based on the coordinate data of the complex to be screened for display on the visual interface.

[0056] It can be understood that some methods for post-processing based on the conformational data of the complex to be screened are described above, and some methods for screening the complex will be described below.

[0057] In some embodiments, in some embodiments of the above operation S230, in response to determining that the conformational data of the complex to be screened meets a preset condition, the target antibody is determined according to the input antibody sequence data. The preset condition may, for example, include a confidence level greater than or equal to a preset confidence threshold. One or more conformational data of the complex to be screened having a confidence level greater than or equal to a preset confidence threshold may be used as one or more target complex conformational data. Based on one or more input antibody sequence data corresponding to one or more target complex conformational data, the target antibody may be determined.

[0058] It is understood that one or more preset conditions may be set based on the above-mentioned prediction alignment error, prediction template modeling evaluation value, and interface prediction template modeling evaluation value. In addition, preset conditions may also be set based on visual images, which is not limited by the present disclosure.

[0059] Through the embodiments of the present disclosure, the complex can be evaluated based on one or more indicators and multiple dimensions such as visual images, and the reliability of different complex conformations can be determined. It can also provide a basis for wet experiments, improve the success rate of wet experiments, and efficiently determine positive antibodies. It can also reduce the number of wet experiments, shorten the experimental cycle, and reduce experimental costs.

[0060] In some embodiments, in response to determining that the conformational data of the complex to be screened does not meet a preset condition, the input antibody corresponding to the conformational data of the complex to be screened may not be used as the target antibody corresponding to the input target data.

[0061] It can be understood that the method of the present disclosure is described above. In some embodiments, the method of the present disclosure can be performed using a homogeneous computing device, or a heterogeneous computing device. The computing units of the homogeneous computing device can be computing units of the same type, for example, all are central processing units (CPUs) or all are graphics processing units (GPUs). The multiple computing units of the heterogeneous computing device can be computing units of different types, which will be described below.

[0062] In some embodiments, in some implementations of the above operation S210, based on the input antibody sequence data and the input target sequence data, a first reference sequence feature and a first reference structural feature corresponding to the input antibody sequence data, and a second reference sequence feature and a second reference structural feature corresponding to the input target sequence data are determined using a first computing unit. For example, the first computing unit may be a central computing unit. The first computing unit may perform the above multiple sequence alignment and template query operations.

[0063] In some embodiments, in some embodiments of the above operation S220, the conformational data of the complex to be screened is determined using a second computing unit based on the input antibody sequence data, the input target sequence data, the first reference sequence feature, the first reference structure feature, the second reference sequence feature, and the second reference structure feature. For example, the second computing unit may be an artificial intelligence computing unit such as a graphics processing unit, a neural network processing unit (NPU), etc. The second computing unit is different from the first computing unit. The above helical folding-polymer model may be deployed in the second computing unit to perform reasoning using the second computing unit.

[0064] Through the embodiments of the present disclosure, by utilizing the first computing unit and the second computing unit to perform different operations, different computing units can perform intensive computing at the same time, thus avoiding idle computing power, effectively improving the utilization of computing resources, and also improving computing efficiency.

[0065] It can be understood that the method of the present disclosure is described above, and the device of the present disclosure will be described below.

[0066] Figure 4 is a block diagram of an antibody data processing apparatus according to an embodiment of the present disclosure.

[0067] like Figure 4 As shown, the apparatus 400 may include a first determination module 410 , a second determination module 420 , and a third determination module 430 .

[0068] The first determination module 410 is used to determine the first reference sequence feature and the first reference structure feature corresponding to the input antibody sequence data, and the second reference sequence feature and the second reference structure feature corresponding to the input target sequence data according to the input antibody sequence data and the input target sequence data.

[0069] The second determination module 420 is used to determine the conformation data of the complex to be screened based on the input antibody sequence data, the input target sequence data, the first reference sequence feature, the first reference structure feature, the second reference sequence feature and the second reference structure feature.

[0070] The third determination module 430 is used to determine the target antibody according to the input antibody sequence data in response to determining that the conformation data of the complex to be screened meets the preset conditions.

[0071] In some embodiments, the first determination module includes: a first determination unit, used to determine at least one first reference sequence data corresponding to the input antibody sequence data and at least one second reference sequence data corresponding to the input target sequence data from a reference sequence database. A second determination unit, used to determine at least one first reference template data corresponding to the input antibody sequence data and at least one second reference template data corresponding to the input target sequence data from a reference template database. A third determination unit, used to determine the first reference sequence feature and the second reference sequence feature based on at least one first reference sequence data and at least one second reference sequence data. A fourth determination unit, used to determine the first reference structure feature and the second reference structure feature based on at least one first reference template data and at least one second reference template data.

[0072] In some embodiments, the complex conformation data to be screened corresponds to at least one of complex conformation coordinate data, antibody target binding position, and residue type.

[0073] In some embodiments, the preset condition includes: the confidence level of the conformational data of the complex to be screened is greater than or equal to a preset confidence threshold.

[0074] In some embodiments, the first determination module includes: a fifth determination unit, which is used to determine, based on the input antibody sequence data and the input target sequence data, a first reference sequence feature and a first reference structure feature corresponding to the input antibody sequence data, and a second reference sequence feature and a second reference structure feature corresponding to the input target sequence data using the first calculation unit.

[0075] In some embodiments, the second determination module includes: a sixth determination unit, for determining the conformational data of the complex to be screened using a second calculation unit based on the input antibody sequence data, the input target sequence data, the first reference sequence feature, the first reference structure feature, the second reference sequence feature, and the second reference structure feature. The second calculation unit is different from the first calculation unit.

[0076] In some embodiments, the number of input antibody sequence data is N, the number of input target sequence data is M, the number of conformational data of the complex to be screened is N×M, N is an integer greater than or equal to 1, and M is an integer greater than or equal to 1.

[0077] In some embodiments, the method further comprises: a fourth determination module for determining at least one visual image according to the conformational data of the complex to be screened; and a display module for displaying at least one of the conformational data of the complex to be screened and the at least one visual image using a visual interface.

[0078] In some embodiments, the second determination module includes: a seventh determination unit, which permanently determines the conformational data of the complex to be screened based on user uploaded data, input antibody sequence data, input target sequence data, first reference sequence characteristics, first reference structure characteristics, second reference sequence characteristics and second reference structure characteristics, wherein the user uploaded data includes at least one of antigen conformational data and antigen epitope position data.

[0079] In the technical solution of the present disclosure, the collection, storage, use, processing, transmission, provision and disclosure of user personal information involved are in compliance with the provisions of relevant laws and regulations and do not violate public order and good morals.

[0080] According to an embodiment of the present disclosure, the present disclosure also provides an electronic device, a readable storage medium and a computer program product.

[0081] Figure 5 A schematic block diagram of an example electronic device 500 that can be used to implement an embodiment of the present disclosure is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present disclosure described and / or required herein.

[0082] like Figure 5 As shown, the device 500 includes a computing unit 501, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 502 or a computer program loaded from a storage unit 508 to a random access memory (RAM) 503. In the RAM 503, various programs and data required for the operation of the device 500 can also be stored. The computing unit 501, the ROM 502, and the RAM 503 are connected to each other via a bus 504. An input / output (I / O) interface 505 is also connected to the bus 504.

[0083] A number of components in the device 500 are connected to the I / O interface 505, including: an input unit 506, such as a keyboard, a mouse, etc.; an output unit 507, such as various types of displays, speakers, etc.; a storage unit 508, such as a disk, an optical disk, etc.; and a communication unit 509, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 509 allows the device 500 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0084] The computing unit 501 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the computing unit 501 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, digital signal processors (DSP), and any appropriate processors, controllers, microcontrollers, etc. The computing unit 501 performs the various methods and processes described above, such as a text processing method and / or a deployment method of a deep learning framework. For example, in some embodiments, the text processing method and / or the deployment method of a deep learning framework may be implemented as a computer software program, which is tangibly contained in a machine-readable medium, such as a storage unit 508. In some embodiments, part or all of the computer program may be loaded and / or installed on the device 500 via the ROM 502 and / or the communication unit 509. When the computer program is loaded into RAM 503 and executed by computing unit 501, one or more steps of the text processing method and / or the method for deploying a deep learning framework described above may be performed. Alternatively, in other embodiments, computing unit 501 may be configured to execute the text processing method and / or the method for deploying a deep learning framework in any other appropriate manner (e.g., by means of firmware).

[0085] Various embodiments of the systems and techniques described above herein may be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard parts (ASSPs), system on chip systems (SOCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0086] The program code for implementing the method of the present disclosure may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that the program code, when executed by the processor or controller, enables the functions / operations specified in the flow chart and / or block diagram to be implemented. The program code may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0087] In the context of the present disclosure, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or equipment. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or device, or any suitable combination of the foregoing. More specific examples of machine-readable storage media may include electrical connections based on one or more lines, portable computer disks, hard disks, random access memories, read-only memories, erasable programmable read-only memories (EPROM) or flash memories, optical fibers, portable compact disk read-only memories (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0088] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device (e.g., a cathode ray tube (CRT) display or a liquid crystal display (LCD)) for displaying information to the user; and a keyboard and a pointing device (e.g., a mouse or a trackball) through which the user can provide input to the computer. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0089] The systems and techniques described herein may be implemented in a computing system that includes backend components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes frontend components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such backend components, middleware components, or frontend components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a Local Area Network (LAN), a Wide Area Network (WAN), and the Internet.

[0090] A computer system may include clients and servers. Clients and servers are generally remote from each other and usually interact through a communication network. The relationship of client and server is generated by computer programs running on respective computers and having a client-server relationship to each other.

[0091] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps recorded in this disclosure can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solutions disclosed in this disclosure can be achieved, and this document does not limit this.

[0092] The above specific implementations do not constitute a limitation on the protection scope of the present disclosure. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present disclosure shall be included in the protection scope of the present disclosure.

Claims

1. A method for processing antibody data, include: Determine, according to the input antibody sequence data and the input target sequence data, a first reference sequence feature and a first reference structural feature corresponding to the input antibody sequence data, and a second reference sequence feature and a second reference structural feature corresponding to the input target sequence data; Determining conformational data of the complex to be screened according to the input antibody sequence data, the input target sequence data, the first reference sequence feature, the first reference structure feature, the second reference sequence feature, and the second reference structure feature; In response to determining that the conformational data of the complex to be screened meets a preset condition, a target antibody is determined according to the input antibody sequence data.

2. The method according to claim 1, in, The step of determining, according to the input antibody sequence data and the input target sequence data, a first reference sequence feature and a first reference structural feature corresponding to the input antibody sequence data, and a second reference sequence feature and a second reference structural feature corresponding to the input target sequence data comprises: Determine, from a reference sequence database, at least one first reference sequence data corresponding to the input antibody sequence data and at least one second reference sequence data corresponding to the input target sequence data; Determine, from a reference template database, at least one first reference template data corresponding to the input antibody sequence data and at least one second reference template data corresponding to the input target sequence data; Determine the first reference sequence feature and the second reference sequence feature according to at least one of the first reference sequence data and at least one of the second reference sequence data, respectively; The first reference structural feature and the second reference structural feature are determined respectively according to at least one of the first reference template data and at least one of the second reference template data.

3. The method according to claim 1, in, The conformational data of the complex to be screened corresponds to at least one of the conformational coordinate data of the complex, the antibody target connection position, and the residue type.

4. The method according to claim 1, in, The preset condition includes: the confidence of the conformational data of the complex to be screened is greater than or equal to a preset confidence threshold.

5. The method according to claim 1, in, The step of determining, according to the input antibody sequence data and the input target sequence data, a first reference sequence feature and a first reference structural feature corresponding to the input antibody sequence data, and a second reference sequence feature and a second reference structural feature corresponding to the input target sequence data comprises: According to the input antibody sequence data and the input target sequence data, a first calculation unit is used to determine a first reference sequence feature and a first reference structural feature corresponding to the input antibody sequence data, and a second reference sequence feature and a second reference structural feature corresponding to the input target sequence data.

6. The method according to claim 5, in, Determining the conformational data of the complex to be screened according to the input antibody sequence data, the input target sequence data, the first reference sequence feature, the first reference structure feature, the second reference sequence feature, and the second reference structure feature comprises: The conformational data of the complex to be screened is determined using a second computing unit based on the input antibody sequence data, the input target sequence data, the first reference sequence feature, the first reference structure feature, the second reference sequence feature and the second reference structure feature, wherein the second computing unit is different from the first computing unit.

7. The method according to claim 1, in, The number of input antibody sequence data is N, the number of input target sequence data is M, and the number of conformational data of the complex to be screened is N×M, where N is an integer greater than or equal to 1, and M is an integer greater than or equal to 1.

8. The method according to claim 1, further comprising: include: Determining at least one visible image based on the conformational data of the complex to be screened; At least one of the conformational data of the complex to be screened and at least one visual image is displayed using a visual interface.

9. The method according to claim 1, in, Determining the conformational data of the complex to be screened according to the input antibody sequence data, the input target sequence data, the first reference sequence feature, the first reference structure feature, the second reference sequence feature, and the second reference structure feature comprises: The conformational data of the complex to be screened is determined based on the user uploaded data, the input antibody sequence data, the input target sequence data, the first reference sequence feature, the first reference structure feature, the second reference sequence feature and the second reference structure feature, wherein the user uploaded data includes at least one of the antigen conformational data and the positional data of the antigen epitope.

10. An antibody data processing device, include: A first determination module is used to determine, based on the input antibody sequence data and the input target sequence data, a first reference sequence feature and a first reference structure feature corresponding to the input antibody sequence data, and a second reference sequence feature and a second reference structure feature corresponding to the input target sequence data; A second determination module is used to determine the conformation data of the complex to be screened according to the input antibody sequence data, the input target sequence data, the first reference sequence feature, the first reference structure feature, the second reference sequence feature and the second reference structure feature; The third determination module is used to determine the target antibody according to the input antibody sequence data in response to determining that the conformation data of the complex to be screened meets a preset condition.

11. The device according to claim 10, in, The first determining module comprises: A first determining unit is used to determine at least one first reference sequence data corresponding to the input antibody sequence data and at least one second reference sequence data corresponding to the input target sequence data from a reference sequence database; A second determining unit is used to determine at least one first reference template data corresponding to the input antibody sequence data and at least one second reference template data corresponding to the input target sequence data from a reference template database; a third determining unit, configured to determine the first reference sequence feature and the second reference sequence feature respectively according to at least one of the first reference sequence data and at least one of the second reference sequence data; The fourth determining unit is used to determine the first reference structure feature and the second reference structure feature respectively according to at least one of the first reference template data and at least one of the second reference template data.

12. The device according to claim 10, in, The preset condition includes: the confidence of the conformational data of the complex to be screened is greater than or equal to a preset confidence threshold.

13. The device according to claim 10, in, The first determining module comprises: a fifth determination unit, configured to determine, based on the input antibody sequence data and the input target sequence data, a first reference sequence feature and a first reference structural feature corresponding to the input antibody sequence data, and a second reference sequence feature and a second reference structural feature corresponding to the input target sequence data using the first calculation unit.

14. The device according to claim 15, in, The second determining module comprises: a sixth determination unit, configured to determine the conformational data of the complex to be screened using a second calculation unit based on the input antibody sequence data, the input target sequence data, the first reference sequence feature, the first reference structure feature, the second reference sequence feature, and the second reference structure feature, wherein the second calculation unit is different from the first calculation unit.

15. The device according to claim 10, in, The number of input antibody sequence data is N, the number of input target sequence data is M, and the number of conformational data of the complex to be screened is N×M, where N is an integer greater than or equal to 1, and M is an integer greater than or equal to 1.

16. The device according to claim 10, further comprising: include: A fourth determination module, used to determine at least one visible image according to the conformational data of the complex to be screened; A display module is used to display at least one of the conformational data of the complex to be screened and at least one visual image using a visual interface.

17. The device according to claim 10, in, The second determining module comprises: The seventh determination unit determines the conformation data of the complex to be screened based on the user uploaded data, the input antibody sequence data, the input target sequence data, the first reference sequence characteristics, the first reference structure characteristics, the second reference sequence characteristics and the second reference structure characteristics, wherein the user uploaded data includes at least one of the antigen conformation data and the position data of the antigen epitope.

18. An electronic device, include: at least one processor; as well as a memory communicatively connected to the at least one processor; wherein, The memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method according to any one of claims 1 to 9.

19. A non-transitory computer-readable storage medium storing computer instructions, in, The computer instructions are used to cause the computer to execute the method according to any one of claims 1 to 9.

20. A computer program product comprising a computer program, which, when executed by a processor, implements the method according to any one of claims 1 to 9.

Images