Ligand escape path determination method and device, electronic equipment and storage medium

Abstract

The invention relates to a ligand escape path determination method and device, electronic equipment and a storage medium, and the method comprises the steps: obtaining a first structure model of a protein and a ligand in a binding state, the first structure model comprising a protein structure model and a ligand structure model; performing dissociation operation on the ligand structure model to dissociate the ligand structure model and the protein structure model, and monitoring a spatial relationship between the ligand structure model and the protein structure model in the dissociation process to obtain a monitoring result; and under the condition that the monitoring result represents that the ligand structure model enters an external area for the first time, the dissociation operation is terminated, an escape path of the ligand structure model in the dissociation process is obtained, and the external area is an area which is outside the protein structure model and takes the surface of the protein structure model as a boundary. And the efficiency and effectiveness of determining the escape path are improved.

Description

TECHNICAL FIELD

[0001] The present disclosure relates to the technical field of data processing, and in particular, to a ligand escape path determination method and device, an electronic device, and a storage medium. BACKGROUND

[0002] In the process of ligand dissociation from a protein, the movement path of the ligand is referred to as an escape path. The determination of the escape path is a technology in the intersection field of computational biology and biophysics, which improves the scientific understanding of the dynamic regulation mechanism of the life system. Its core value not only lies in the exploration of the essential laws of life phenomena, but also shows revolutionary driving force in the key link of the pharmaceutical and health industry.

[0003] For example, in drug research and development, accurate analysis of the dissociation kinetics characteristics of target proteins and candidate drugs can significantly improve the efficiency of lead compound optimization; in precision medicine, by simulating the dynamic interaction between disease-related proteins and therapeutic molecules, a theoretical basis is provided for the development of individualized drug use plans; in the biotechnology industry, this technology helps to make innovative breakthroughs in enzyme engineering, biosensor design, and other fields, and promotes the evolution of synthetic biology towards intelligentization.

[0004] However, in terms of related technologies, the efficiency of determining the escape path and the effectiveness of the escape path need to be improved. SUMMARY

[0005] Therefore, the present disclosure provides a ligand escape path determination scheme.

[0006] According to an aspect of the present disclosure, a ligand escape path determination method is provided, including: obtaining a first structure model of a protein and a ligand in a combined state, the first structure model including a protein structure model and a ligand structure model; performing a dissociation operation on the ligand structure model, so that the ligand structure model is dissociated from the protein structure model, and monitoring the spatial relationship between the ligand structure model and the protein structure model during the dissociation process to obtain a monitoring result; in the case that the monitoring result represents that the ligand structure model first enters an external region, terminating the dissociation operation, and obtaining an escape path of the ligand structure model in the dissociation process, the external region being a region outside the protein structure model and bounded by the surface of the protein structure model.

[0007] In one possible implementation, the method further includes: obtaining surface geometric element information of the protein structure model; determining an internal geometric element of the protein structure model based on the surface geometric element information to obtain an internal region of the first structure model; and determining a region outside the internal region as the external region.

[0008] In a possible implementation, the obtaining the first structure model of the protein and the ligand in the binding state comprises: obtaining an initial structure model of the protein and the ligand in the binding state; and performing pre-equilibrium processing on the initial structure model to obtain the first structure model.

[0009] In a possible implementation, the monitoring the spatial relationship between the ligand structure model and the protein structure model in the dissociation process to obtain a monitoring result comprises: obtaining surface geometric element information of the protein structure model; obtaining equivalent geometric body structures with surface geometric elements as geometric body centers based on the surface geometric element information; obtaining energy generated due to a collision between the ligand structure model and the equivalent geometric body structures in a case where the collision occurs; and obtaining the monitoring result according to the energy.

[0010] In a possible implementation, the surface geometric element information comprises surface grid information or surface collision sphere information.

[0011] In a possible implementation, before the dissociation operation is performed on the ligand structure model, the method further comprises: detecting the spatial relationship between the ligand structure model and the protein structure model to obtain a detection result; and performing the dissociation operation in a case where the detection result indicates that the ligand structure model does not enter the external region.

[0012] In a possible implementation, the dissociation operation performed on the ligand structure model to dissociate the ligand structure model from the protein structure model comprises: obtaining an initial velocity set corresponding to the ligand structure model and a first thrust force, the initial velocity set comprising initial velocities of atoms in the ligand structure model; and applying the first thrust force to a center of mass of the ligand structure model and applying the initial velocities to the corresponding atoms to dissociate the ligand structure model from the protein structure model.

[0013] In a possible implementation, the escape path contains kinetic information, and the dissociation operation performed on the ligand structure model to dissociate the ligand structure model from the protein structure model comprises: obtaining a plurality of candidate escape paths with the same starting point and the same ending point based on a plurality of initial velocity sets and the first thrust force; and the method further comprises: obtaining an average dissociation time corresponding to the starting point and the ending point based on kinetic information contained in the plurality of candidate escape paths; and determining a target escape path based on the average dissociation time.

[0014] According to another aspect of the present disclosure, there is provided a ligand escape path determination apparatus, which comprises:

[0015] The first structure model acquisition unit is configured to acquire a first structure model of a protein and a ligand in a binding state, the first structure model comprising a protein structure model and a ligand structure model.

[0016] The monitoring result determination unit is configured to perform a dissociation operation on the ligand structure model, dissociate the ligand structure model from the protein structure model, and monitor a spatial relationship between the ligand structure model and the protein structure model during the dissociation operation to obtain a monitoring result.

[0017] The escape path determination unit is configured to, in a case where the monitoring result indicates that the ligand structure model enters an external region for the first time, terminate the dissociation operation, and obtain an escape path of the ligand structure model during the dissociation operation, the external region being a region outside the protein structure model and being bounded by a surface of the protein structure model.

[0018] In a possible implementation, the apparatus further includes:

[0019] The surface geometric element information determination unit is configured to acquire surface geometric element information of the protein structure model.

[0020] The internal region determination unit is configured to determine an internal geometric element of the protein structure model based on the surface geometric element information, and obtain an internal region of the first structure model.

[0021] The external region determination unit is configured to determine a region outside the internal region as the external region.

[0022] In a possible implementation, the first structure model acquisition unit is further configured to:

[0023] The initial structure model acquisition unit is configured to acquire an initial structure model of the protein and the ligand in the binding state.

[0024] The pre-equilibrium unit is configured to perform a pre-equilibrium process on the initial structure model to obtain the first structure model.

[0025] In a possible implementation, the monitoring result determination unit is further configured to:

[0026] Acquire surface geometric element information of the protein structure model.

[0027] Based on each of the surface geometric element information, obtain an equivalent geometric body structure with a surface geometric element as a geometric center.

[0028] In a case where the ligand structure model collides with the equivalent geometric body structure, acquire energy generated due to the collision.

[0029] The monitoring results are obtained based on the energy.

[0030] In one possible implementation, the surface geometric element information includes: surface grid information, or surface collision sphere information.

[0031] In one possible implementation, the device further includes:

[0032] A spatial relationship detection unit is used to detect the spatial relationship between the ligand structure model and the protein structure model, and obtain the detection result.

[0033] The dissociation operation execution unit is used to perform the dissociation operation when the detection result indicates that the ligand structure model has not entered the external region.

[0034] In one possible implementation, the monitoring result determination unit is further configured to:

[0035] Obtain the initial velocity set corresponding to the ligand structure model, and the first thrust, wherein the initial velocity set includes the initial velocity of each atom in the ligand structure model;

[0036] The first thrust is applied to the center of mass of the ligand structure model, and the initial velocity is applied to the corresponding atom, causing the ligand structure model to dissociate from the protein structure model.

[0037] In one possible implementation, the escape path includes dynamic information, and the monitoring result determination unit is further configured to:

[0038] Based on multiple initial velocity sets and the first thrust, multiple candidate escape paths with the same starting point and the same ending point are obtained;

[0039] The device further includes:

[0040] The average dissociation time determination unit is used to obtain the average dissociation time corresponding to the starting point and the ending point based on the dynamic information contained in the multiple candidate escape paths.

[0041] The target escape path determination unit is used to determine the target escape path based on the average dissociation time.

[0042] In one possible implementation, the device further includes:

[0043] An accessibility probability determination unit is used to determine the accessibility probability of each escape path.

[0044] The terrain contour determination unit is used to determine the terrain contours inside the protein structure model based on the accessibility probability.

[0045] In a possible implementation, the apparatus further includes:

[0046] a clustering unit configured to cluster the plurality of escape paths to obtain at least one cluster, the cluster representing an exit position of the ligand from the protein.

[0047] According to another aspect of the present disclosure, an electronic device is provided, which includes a memory, a processor, and a computer program stored in the memory, and the processor executes the computer program to implement the steps of the above method.

[0048] According to another aspect of the present disclosure, a non-volatile computer readable storage medium is provided, which stores a computer program, and the computer program is executed by a processor to implement the steps of the above method.

[0049] According to another aspect of the present disclosure, a computer program product is provided, which includes a computer program, or a non-volatile computer readable storage medium carrying the computer program, and the computer program is executed by a processor to implement the steps of the above method.

[0050] In the embodiments of the present disclosure, when the ligand structure model first enters the external region, the dissociation operation is stopped, and the ligand structure model does not move away from the protein structure model, which improves the effectiveness of the escape path. Moreover, since the dissociation operation is stopped in time in the case of an effective escape path, the probability of an ineffective escape path is reduced, the time for determining the escape path is shortened, and the efficiency of determining the escape path is improved.

[0051] Other features and aspects of the present disclosure will become apparent from the following detailed description of the exemplary embodiments with reference to the drawings. BRIEF DESCRIPTION OF DRAWINGS

[0052] The accompanying drawings, which are incorporated in and constitute a part of the specification, illustrate exemplary embodiments, features, and aspects of the present disclosure and serve to explain the principles of the present disclosure.

[0053] Figure 1 A flowchart of a ligand escape path determination method provided by the embodiments of the present disclosure.

[0054] Figure 2 A structural diagram of a ligand escape path determination apparatus provided by the embodiments of the present disclosure.

[0055] Figure 3 A structural diagram of an electronic device for determining a ligand escape path provided by the embodiments of the present disclosure. DETAILED DESCRIPTION

[0056] Various exemplary embodiments, features, and aspects of the present disclosure will be described in detail below with reference to the accompanying drawings. The same reference numbers in different drawings represent the same or similar elements / function. Although various aspects of embodiments are illustrated in the drawings, the drawings are not necessarily drawn to scale unless specifically noted.

[0057] As used herein, the terms "comprise", "comprising", "have", "having", "include", "including", "contain", "containing", or variants thereof are open-ended, and include one or more stated features, integers, elements, steps, components or functions but do not preclude the presence or addition of one or more other features, integers, elements, steps, components, functions or groups thereof.

[0058] When an element is referred to as being "connected", "coupled", "responsive", or "related" to another element, it can be directly connected, coupled, responsive, or related to the other element, or intervening elements can be present.

[0059] Although the terms first, second, third, etc. can be used herein to describe various elements / operations, these elements / operations should not be limited by these terms. These terms are only used to distinguish one element / operation from another element / operation. Thus, a first element / operation in some embodiments can be termed a second element / operation in other embodiments without departing from the teachings of the present inventive concept.

[0060] The word "exemplary" is used herein to mean "serving as an example, instance, or illustration." Any implementation described herein as "exemplary" is not necessarily to be construed as preferred or advantageous over other implementations.

[0061] In addition, for the purpose of convenience and brevity, detailed descriptions of well-known functions and structures incorporated herein can not be described in detail. It should be apparent to those skilled in the art that the present disclosure can be practiced without such specific details.

[0062] After the ligand is dissociated from the protein and moves away from the protein, it can not react with the target substance, but with water. If the dissociation operation is not stopped in time, part of the escape path obtained can be invalid. Not only does it increase the time to determine the escape path, affecting efficiency, but also reduces the effectiveness of the escape path.

[0063] In view of this, the present application provides a ligand escape path determination method.

[0064] Figure 1 A flowchart of a ligand escape path determination method provided by an embodiment of the present disclosure is shown. The method comprises:

[0065] S11, obtaining a first structure model of a protein and a ligand in a binding state, the first structure model comprising a protein structure model and a ligand structure model.

[0066] The first structure model can be constructed by using a computational biology method or an experimental technique, and is used to reflect a digital representation of a three-dimensional spatial conformation of the protein and the ligand in the binding state. The protein structure model can be a digital representation of a three-dimensional spatial conformation of the protein. The ligand structure model can be a digital representation of a three-dimensional spatial conformation of the ligand. In the following, the protein and the ligand in the binding state are named as a protein-ligand binding body for convenience of description.

[0067] The first structure model can be represented by using a triangular mesh. The triangular mesh can be a combination of geometric elements and edges. The first structure model can contain one or more aspects of information. These aspects include a structural morphology of the protein-ligand binding body, an atomic type, a spatial relationship between atoms, and the like. In the first structure model, the ligand structure model can be located entirely within the protein structure model, or the ligand structure model can be located partially within the protein structure model, or the ligand structure model can be located entirely outside the protein structure model.

[0068] S12, performing a dissociation operation on the ligand structure model to dissociate the ligand structure model from the protein structure model, and monitoring a spatial relationship between the ligand structure model and the protein structure model in the dissociation process to obtain a monitoring result.

[0069] The dissociation operation can be an operation of moving the ligand structure model and finally partially or entirely leaving the protein structure model. In the dissociation operation, an initial force can be applied to the ligand structure model, and based on the connection relationship between the atoms represented by the ligand structure model and the initial force, the movement speed of each atom in the ligand is estimated to perform the dissociation of the ligand and the protein. The above is only an example, and the specific form of the dissociation operation is not limited in the embodiments of the present disclosure.

[0070] In the process of dissociating the ligand from the protein, the spatial relationship between the ligand structure model and the protein structure model can be monitored. The spatial relationship can include a containing relationship, an intersection relationship, and a separation relationship. The containing relationship represents that the ligand structure model is entirely located within the protein structure model. The intersection relationship represents that the ligand structure model is partially located within the protein structure model and has at least one intersection point with the protein structure model. The separation relationship represents that the ligand structure model is entirely located outside the protein structure model.

[0071] The monitoring result contains the spatial relationship between the ligand structure model and the protein structure model. The monitoring result can represent whether the spatial relationship contained in the monitoring result first appears in the monitoring process.

[0072] S13, in the case that the monitoring result represents that the ligand structure model enters the external region for the first time, terminating the dissociation operation, and obtaining an escape path of the ligand structure model in the dissociation process, the external region being a region outside the protein structure model and being a region bounded by the surface of the protein structure model.

[0073] In the present disclosure, the escape path not only contains the motion path of the ligand in the dissociation process, but also can contain the position information of the ligand in the dissociation process, for example: the three-dimensional coordinates of the head or the center of mass of the ligand. The head of the ligand can be the end point of one end pointed by the vector direction of the interatomic line in the ligand. The center of mass of the ligand can be the mass center of the ligand. The escape path can also contain the kinetic information of the ligand at each position in the dissociation process, for example: the motion speed, the motion direction, the energy, etc. of each atom of the ligand. In the present disclosure, the escape path can be the kinetic trajectory of the ligand in the dissociation process.

[0074] If the monitoring result represents that the spatial relationship between the ligand structure model and the protein structure model is the intersecting relationship for the first time, it means that the ligand structure model enters the external region for the first time. Exemplarily, the external region can correspond to a coordinate range. When the center of mass coordinate of the ligand structure model is monitored to fall into the coordinate range for the first time, it means that the ligand structure model enters the external region for the first time.

[0075] In one example, for the intersecting relationship, the monitoring result can include: a first proportion of the part of the ligand structure model in the protein structure model to the entire ligand structure model. In the case that the first proportion falls into a preset proportion interval, it means that the ligand structure model enters the external region for the first time. The above is only an example, and the method for determining the spatial relationship and judging whether the ligand structure model enters the external region for the first time is not limited in the present disclosure.

[0076] Since the escape path determined in the present disclosure contains kinetic information, the free energy surface near the protein pocket can be further determined according to the escape path to provide reliable basis for drug research and development.

[0077] In the present disclosure, when the ligand structure model enters the external region for the first time, the dissociation operation is stopped, and the ligand structure model does not move away from the protein structure model, which improves the effectiveness of the escape path. Moreover, since the dissociation operation is stopped in time in the case that the escape path is effective, the probability of invalid escape path is reduced, the time for determining the escape path is shortened, and the efficiency for determining the escape path is improved.

[0078] In a possible implementation, the method further includes: obtaining surface geometric element information of the protein structure model; determining, based on the surface geometric element information, internal geometric elements of the protein structure model to obtain an internal region of the first structure model; and determining a region outside the internal region as the external region.

[0079] The first structure model includes geometric elements. The geometric elements can be divided into surface geometric elements and internal geometric elements according to positions. For example, the geometric elements can be grid points. For another example, the geometric elements can be collision spheres. The collision sphere is a spherical structure.

[0080] In a possible implementation, the surface geometric element information includes surface grid point information or surface collision sphere information.

[0081] In the embodiments of the present disclosure, the surface geometric elements and the surface geometric element information can be obtained by starting searching from a position far away from the first structure model. For example, a depth-first algorithm or a breadth-first algorithm can be used to search from a preset infinite distance or a manually specified position. The surface geometric element information can include geometric element identifiers and three-dimensional coordinates of the surface geometric elements.

[0082] After the surface geometric elements are removed from the geometric elements included in the first structure model according to the surface geometric element information, the remaining geometric elements can be regarded as internal geometric elements. The internal region can be a space region occupied by the internal geometric elements. The external region can be a region outside the internal region.

[0083] Most proteins are irregular in shape. The method of the present disclosure can improve the monitoring accuracy of the spatial relationship by determining the external region instead of setting a regular-shaped external region, thereby improving the accuracy of determining the timing of terminating the dissociation operation.

[0084] In a possible implementation, the obtaining of the first structure model of the protein and the ligand in the combined state includes: obtaining an initial structure model of the protein and the ligand in the combined state; and performing pre-equilibrium processing on the initial structure model to obtain the first structure model.

[0085] For example, the homology modeling can obtain a comparison sequence of the protein-ligand complex and a homologous protein, an amino acid sequence of the protein-ligand complex, and the like, and obtain the initial structure model based on a modeling tool. Alternatively, the initial structure model can be obtained from a protein structure database. The process of obtaining the initial structure model is not the focus of the present disclosure, and is not expanded here.

[0086] The pre-equilibration can include energy minimization processing, temperature equilibration processing, pressure equilibration processing, etc. For example, the pre-equilibration can be achieved by adjusting the relative positions of atoms in the initial structure model, adding or removing atoms. For the sake of distinction, the initial structure model after the pre-equilibration can be named as a first structure model.

[0087] In the embodiments of the present disclosure, the pre-equilibration of the initial structure model can enhance the stability of the model. The process of determining the escape path can proceed smoothly, reducing the probability of collapse of the first structure model in the process of determining the escape path, thereby reducing the probability of rework and improving the efficiency of determining the escape path.

[0088] In a possible implementation, the monitoring the spatial relationship between the ligand structure model and the protein structure model in the dissociation process to obtain a monitoring result includes: obtaining surface geometric element information of the protein structure model; obtaining an equivalent geometric body structure with a surface geometric element as a geometric center based on each surface geometric element information; obtaining energy generated by a collision between the ligand structure model and the equivalent geometric body structure in the case of the collision; and obtaining the monitoring result according to the energy.

[0089] In the embodiments of the present disclosure, the radius can be preset, and an equivalent geometric body structure can be established according to the preset radius with a surface geometric element as a geometric center. For example, the equivalent geometric body can be an equivalent sphere, and the surface geometric element can be a sphere center of the equivalent sphere. Alternatively, the equivalent geometric body can be an equivalent cube, and the surface geometric element can be a center of the equivalent cube. Part of the equivalent geometric body structure can occupy an external region, and part of the equivalent geometric body structure can occupy an internal region. The ligand structure model can collide with the equivalent geometric body structure during the movement. Thus, the monitoring result can be determined by monitoring the energy generated by the collision. In the case that the energy generated by the collision is greater than a first energy threshold for the first time, it is determined that the ligand structure model enters the external region for the first time.

[0090] For example, an interval duration can be preset. The energy generated by the collision between the ligand structure model and the equivalent geometric body structure during the movement of the ligand structure model can be collected every interval duration, and the energy can be a harmonic potential. In the case that the energy is greater than the first energy threshold for the first time, it is determined that the ligand structure model enters the external region for the first time, and the dissociation operation is terminated.

[0091] For example, an interval step number can be preset. The energy generated by the collision between the ligand structure model and the equivalent geometric body structure during the movement of the ligand structure model can be collected every interval step number. In the case that the energy is greater than the first energy threshold for the first time, it is determined that the ligand structure model enters the external region for the first time, and the dissociation operation is terminated.

[0092] If the center of mass leaves the protein structure model, it means that the ligand structure model has left the protein structure model, but the ligand structure model as a whole is not far away from the protein structure model. Thus, monitoring the collision of the center of mass with the equivalent sphere to determine the escape path can improve the effectiveness of the escape path.

[0093] In the embodiments of the present disclosure, the energy generated by the collision between the ligand structure model and the equivalent geometric structure is determined only when the collision occurs, which reduces the calculation frequency and amount, and further reduces the occupation of hardware resources. Moreover, the monitoring result is determined by the energy generated by the collision between the ligand structure model and the equivalent geometric structure to determine whether to terminate the dissociation operation, which can accurately identify the moment when the ligand structure model has walked out of the protein structure model, and has not moved away from the protein structure model structure, and can fully react with the target object. The accuracy of determining the timing of terminating the dissociation operation is improved, and the effectiveness of the equivalent path can be further improved.

[0094] In a possible implementation, before the dissociation operation is performed on the ligand structure model, the method further includes: detecting a spatial relationship between the ligand structure model and the protein structure model to obtain a detection result; and performing the dissociation operation in a case where the detection result is that the ligand structure model has not entered the external region.

[0095] In the embodiments of the present disclosure, the spatial relationship between the ligand structure model and the protein structure model can be detected before the dissociation operation. In the case of a non-inclusion relationship, it indicates that the ligand structure model has entered the external region, that is, the ligand has been dissociated from the protein or is in the dissociation process, and the dissociation path is incomplete, and the dissociation operation does not need to be started. Only in the case of an inclusion relationship, it indicates that the ligand structure model has not entered the external region, and the dissociation operation is started to determine the complete escape path.

[0096] Therefore, before the dissociation operation, the spatial relationship between the ligand structure model and the protein structure model is detected, and then it is determined whether to perform the dissociation operation, which can reduce unnecessary dissociation operations, reduce hardware resource and time consumption, and also reduce the probability of incomplete escape path, and improve the completeness and effectiveness of the escape path.

[0097] In a possible implementation, the dissociation operation performed on the ligand structure model to dissociate the ligand structure model from the protein structure model includes: obtaining an initial velocity set corresponding to the ligand structure model, and a first thrust, the initial velocity set including initial velocities of atoms in the ligand structure model; and applying the first thrust to a center of mass of the ligand structure model, and applying the initial velocities to the corresponding atoms to dissociate the ligand structure model from the protein structure model.

[0098] The initial velocity set can include initial velocities (numerical values and directions) of atoms in the ligand structure model. The initial velocity set is not the focus of the present disclosure and is not expanded here. Each atom can start moving according to the respective initial velocity. In addition, the ligand structure model can move under the action of the first force applied to the center of mass. The initial velocity set accelerates the dissociation process together with the first force, improving the efficiency of determining the escape path.

[0099] In a possible implementation, the escape path contains kinetic information, and the dissociation operation on the ligand structure model to dissociate the ligand structure model from the protein structure model includes: obtaining a plurality of candidate escape paths with the same starting point and the same ending point based on a plurality of initial velocity sets and the first force; and the method further includes: obtaining an average dissociation time corresponding to the same starting point and the same ending point based on kinetic information contained in the plurality of candidate escape paths; and determining a target escape path based on the average dissociation time.

[0100] In the embodiments of the present disclosure, a plurality of initial velocity sets can be generated differently. The plurality of initial velocity sets can not be the same. The ligand structure model can move under the action of each initial velocity set and the first force to obtain a plurality of escape paths. These escape paths are all determined under the action of the first force, and each escape path has the same starting point and the same ending point. For ease of description, these escape paths corresponding to the same ligand structure model, the same starting point and the same ending point are named as candidate escape paths. The process of determining these candidate escape paths can be completed on different hardware without interference. Among them, the process of determining a single candidate escape path can be completed by the ligand structure model under the action of a single initial velocity set and the first force.

[0101] As described above, the escape path can contain kinetic information of the ligand at each position in the dissociation process. Each candidate escape path contains its own kinetic information. Therefore, the first speed of the ligand dissociating from the protein according to each candidate escape path can be determined. Further, based on each first speed, the average dissociation time from the same starting point to the same ending point can be calculated.

[0102] The target average dissociation time suitable for the scene can be selected according to the actual scene needs. The target average dissociation time can correspond to a target starting point and a target ending point. The target starting point and the target ending point can correspond to a plurality of candidate escape paths. Further, a target escape path can be selected from the plurality of candidate escape paths corresponding to the target starting point and the target ending point. Exemplarily, the target escape path can be determined based on specific needs, for example: according to the length of the plurality of candidate escape paths corresponding to the target starting point and the target ending point, and / or the corresponding dissociation speed. The above is only an example, and the embodiments of the present disclosure do not limit the specific method of determining the target escape path.

[0103] In the embodiments of the present disclosure, multiple initial speed combinations can be generated for the same ligand structure model. The differences between candidate escape paths with the same starting point and the same ending point are increased, which provides more choices for selecting the target escape path and improves the probability of selecting the target escape path that is highly consistent with the scene. Dissociation speed is a key indicator for determining the target escape path. Thus, the average dissociation time from the same starting point to the same ending point can be determined based on the kinetic information contained in the candidate escape path, and the target escape path is determined according to the average dissociation time, which improves the consistency of the target escape path with the scene.

[0104] In a possible implementation, the method further includes: determining positions passed by the escape paths in the protein structure model based on kinetic information contained in the multiple escape paths; determining an accessible probability of each position based on each position and each escape path; and determining a topographic contour inside the protein structure model based on the accessible probability.

[0105] The accessible probability of a single escape path can represent the probability of selecting the single escape path for the movement of the ligand from inside the protein to outside the protein.

[0106] In the embodiments of the present disclosure, the dissociation operation can be performed multiple times to determine multiple escape paths. As described above, an escape path contains position information of the ligand in the dissociation process. The escape paths with the same position information can be determined according to the position information to form an escape path group. Then, the accessible probability of each escape path is determined according to the number of escape paths in each escape path group.

[0107] For example, 10 ligand structure models and protein structure models are subjected to dissociation operations to obtain 10 escape paths. Among them, 5 escape paths are the same, and for ease of distinction, the 5 escape paths are named as escape path A. Among the remaining 5 escape paths, 3 escape paths are the same, and for ease of distinction, the 3 escape paths are named as escape path B. The remaining 2 escape paths are the same, and for ease of distinction, the 2 escape paths are named as escape path C. Thus, the accessible probability of the escape path A is 50%, the accessible probability of the escape path B is 30%, and the accessible probability of the escape path C is 20%.

[0108] The free energy of the escape path is in logarithmic relationship with the accessible probability. Thus, the value of the free energy can be determined according to the accessible probability. The topographic contour is drawn according to the value of the free energy. The points on the plane surrounded by a single topographic contour have the same potential energy, and the plane is an equipotential energy surface.

[0109] In the embodiments of the present disclosure, the topographic contour inside the protein structure model can be determined according to multiple escape paths, which provides a reliable reference for studying the energy inside the protein structure model.

[0110] In a possible implementation, the method further includes: clustering the multiple escape paths to obtain at least one category, and the category represents an exit position of the escape path from the protein.

[0111] In the embodiments of the present disclosure, the dissociation operation can be performed multiple times to determine multiple escape paths. The starting points of the multiple escape paths can be the same, but the ending points of the multiple escape paths can not be the same. The ending points of the multiple escape paths can all be different or partially the same. The ending points of the multiple escape paths can indicate the exit position of the protein.

[0112] In the embodiments of the present disclosure, the clustering can be performed according to the ending points of the escape paths. The categories obtained through the clustering can represent the ending points of the escape paths, that is, represent the exit position.

[0113] In the scenario of obtaining a large number of escape paths, the escape paths are clustered first, and then the exit position is determined, instead of analyzing each escape path, which can simplify the process and improve the efficiency of locating the exit position.

[0114] Figure 2 A structural schematic diagram of a ligand escape path determination apparatus provided by the embodiments of the present disclosure is provided. The apparatus 20 includes:

[0115] A first structure model acquisition unit 21 is configured to acquire a first structure model of a protein and a ligand in a combined state, and the first structure model includes a protein structure model and a ligand structure model.

[0116] A monitoring result determination unit 22 is configured to perform a dissociation operation on the ligand structure model, dissociate the ligand structure model from the protein structure model, and monitor a spatial relationship between the ligand structure model and the protein structure model during the dissociation process to obtain a monitoring result.

[0117] An escape path determination unit 23 is configured to terminate the dissociation operation when the monitoring result indicates that the ligand structure model enters an external region for the first time, and obtain an escape path of the ligand structure model in the dissociation process, where the external region is a region outside the protein structure model and is bounded by a surface of the protein structure model.

[0118] In a possible implementation, the apparatus 20 ， further includes:

[0119] A surface geometric element information determination unit is configured to acquire surface geometric element information of the protein structure model.

[0120] An internal region determination unit is configured to determine an internal geometric element of the protein structure model based on the surface geometric element information to obtain an internal region of the first structure model.

[0121] An external region determination unit is configured to determine a region outside the internal region as the external region.

[0122] In a possible implementation, the first structure model acquisition unit 21 is further configured to:

[0123] An initial structure model acquisition unit is configured to acquire an initial structure model of a protein and a ligand in a binding state.

[0124] A pre-equilibrium unit is configured to perform pre-equilibrium processing on the initial structure model to obtain the first structure model.

[0125] In a possible implementation, the monitoring result determination unit 22 is further configured to:

[0126] Acquire surface geometric element information of the protein structure model.

[0127] Based on each piece of surface geometric element information, obtain an equivalent geometric body structure with a surface geometric element as a geometric center of the equivalent geometric body structure.

[0128] In a case where the ligand structure model collides with the equivalent geometric body structure, acquire energy generated due to the collision.

[0129] Obtain the monitoring result according to the energy.

[0130] In a possible implementation, the surface geometric element information includes surface grid point information or surface collision sphere information.

[0131] In a possible implementation, the apparatus 20 further includes:

[0132] A spatial relationship detection unit is configured to detect a spatial relationship between the ligand structure model and the protein structure model to obtain a detection result.

[0133] A dissociation operation execution unit is configured to execute the dissociation operation in a case where the detection result is that the ligand structure model does not enter the external region.

[0134] In a possible implementation, the monitoring result determination unit 22 is further configured to:

[0135] Acquire an initial velocity set corresponding to the ligand structure model, and a first thrust force, the initial velocity set including initial velocities of atoms in the ligand structure model.

[0136] Apply the first thrust force to a center of mass of the ligand structure model, and apply the initial velocities to the corresponding atoms, so as to dissociate the ligand structure model from the protein structure model.

[0137] In a possible implementation, the escape paths contain kinetic information, and the monitoring result determination unit 22 is further configured to:

[0138] obtain a plurality of candidate escape paths with the same start point and the same end point based on the plurality of initial speed sets and the first thrust;

[0139] The device 20 further includes:

[0140] an average dissociation duration determination unit configured to obtain an average dissociation duration corresponding to the start point and the end point based on the kinetic information contained in the plurality of candidate escape paths;

[0141] a target escape path determination unit configured to determine a target escape path based on the average dissociation duration.

[0142] In a possible implementation, the device 20 further includes:

[0143] a reachable probability determination unit configured to determine a reachable probability of each of the escape paths;

[0144] a terrain contour determination unit configured to determine a terrain contour inside the protein structure model based on the reachable probability.

[0145] In a possible implementation, the device 20 further includes:

[0146] a clustering unit configured to cluster the plurality of escape paths to obtain at least one cluster, the cluster representing an exit position of a ligand from a protein.

[0147] In some embodiments, the device provided by the embodiments of the present disclosure has functions or includes modules that can be used to execute the methods described in the above method embodiments, and the specific implementation can refer to the description of the above method embodiments. For brevity, details are not described here.

[0148] The embodiments of the present disclosure also provide an electronic device, including a memory, a processor, and a computer program stored in the memory, and the processor executes the computer program to implement the steps of the above method.

[0149] The embodiments of the present disclosure also provide a non-volatile computer readable storage medium having a computer program stored thereon, and the computer program is executed by a processor to implement the steps of the above method.

[0150] The embodiments of the present disclosure also provide a computer program product, including a computer program or a non-volatile computer readable storage medium carrying a computer program, and the computer program is executed by a processor to implement the steps of the above method.

[0151] Figure 3 A structural diagram of an electronic device for determining ligand escape paths is provided for embodiments of the present disclosure. For example, the electronic device 1900 can be provided as a server or a terminal device. Referring to Figure 3 , the electronic device 1900 includes a processing component 1922, further including one or more processors, and a memory resource represented by a memory 1932, for storing instructions executable by the processing component 1922, such as an application program. The application program stored in the memory 1932 can include one or more than one module each corresponding to a set of instructions. In addition, the processing component 1922 is configured to execute the instructions to perform the above method.

[0152] The electronic device 1900 can also include a power supply component 1926 configured to perform power management of the electronic device 1900, a wired or wireless network interface 1950 configured to connect the electronic device 1900 to a network, and an input / output interface 1958 (I / O interface). The electronic device 1900 can operate based on an operating system stored in the memory 1932, such as Windows Server TM , Mac OS X TM , Unix TM , Linux TM , FreeBSD TM or the like.

[0153] In an exemplary embodiment, a non-volatile computer readable storage medium, such as the memory 1932 including computer program instructions executable by the processing component 1922 of the electronic device 1900 to complete the above method is also provided.

[0154] Computer readable storage media can be any media that can be read by a machine. Such media can include, but is not limited to, optical discs, magnetic discs, magnetic tapes, electronic memories, and / or any combination thereof. Computer readable storage media can be non-transitory, in that it can be a tangible medium. In some embodiments, computer readable storage media can be non-transitory, in that it can not be a signal per se. In other embodiments, computer readable storage media can be a transitory medium, in that it can be a signal. In some embodiments, computer readable storage media can be non-transitory, in that it can not be a signal per se, but can be a tangible medium. In other embodiments, computer readable storage media can be a transitory medium, in that it can be a signal. In some embodiments, computer readable storage media can be non-transitory, in that it can not be a signal per se, but can be a tangible medium. In other embodiments, computer readable storage media can be a transitory medium, in that it can be a signal.

[0155] The computer programs (or computer readable program instructions) described herein can be downloaded from a computer readable storage medium to respective computing / processing devices or to external computers or external storage devices via a network, for example, the Internet, a local area network, a wide area network and / or a wireless network. The network can comprise copper transmission cables, optical transmission fibers, wireless transmission, routers, firewalls, switches, gateway computers and / or edge servers. A network adapter card or network interface in each computing / processing device receives computer readable program instructions from the network and forwards the computer readable program instructions for storage in a computer readable storage medium within the respective computing / processing device.

[0156] Computer readable program instructions for carrying out operations of the present disclosure can be assembler instructions, instruction-set-architecture (ISA) instructions, machine instructions, machine dependent instructions, microcode, firmware instructions, state-setting data, or either source code or object code written in any combination of one or more programming languages, including an object oriented programming language such as Smalltalk, C++ or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The computer readable program instructions can execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the latter scenario, the remote computer can be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or the connection can be made to an external computer (for example, through the Internet using an Internet Service Provider). In some embodiments, electronic circuitry including, for example, programmable logic circuitry, field-programmable gate array (FPGA), or programmable logic array (PLA) can execute the computer readable program instructions by utilizing state information of the computer readable program instructions to personalize the electronic circuitry, in order to perform aspects of the present disclosure.

[0157] The computer readable program instructions can also be loaded onto a computer, other programmable data processing apparatus, or other device to cause a series of operational steps to be performed on the computer, other programmable apparatus or other device to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide processes for implementing the functions / acts specified in the flowchart and / or block diagram block or blocks.

[0158] These computer readable program instructions can be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions / acts specified in the flowchart and / or block diagram block or blocks. These computer readable program instructions can also be stored in a computer readable storage medium that can include random access memory (RAM), read only memory (ROM), electrically erasable programmable read only memory (EEPROM), flash memory or other data storage device. When the computer readable program instructions are loaded into the computer and other programmable data processing apparatus, a series of operational steps are implemented that provide processes such that the computer or other programmable apparatus provide processes for implementing the functions / acts specified in the flowchart and / or block diagram block or blocks.

[0159] The computer readable program instructions can also be loaded onto a computer, other programmable data processing apparatus, or other device to cause a series of operational steps to be performed on the computer, other programmable data processing apparatus or other device to produce a computer implemented process such that the instructions which execute on the computer, other programmable data processing apparatus, or other device implement the functions / acts specified in the flowchart and / or block diagram block or blocks.

[0160] The computer readable program instructions can also be loaded onto a computer, other programmable data processing apparatus, or other device to cause a series of operational steps to be performed on the computer, other programmable data processing apparatus or other device to produce a computer implemented process such that the instructions which execute on the computer, other programmable data processing apparatus, or other device implement the functions / acts specified in the flowchart and / or block diagram block or blocks.

[0161] Embodiments of the present disclosure have been described above, and the description is intended to be illustrative, and not restrictive, of the disclosed embodiments. Many modifications and variations of the described embodiments are possible, and all such modifications and variations are intended to be within the scope of the described embodiments. The description used herein is intended to best explain the principles of the various embodiments, the practical application, and the best mode of using the present disclosure, and to enable others skilled in the art to understand the disclosure, various embodiments, and / or various implementations detailed herein. Any terminology used herein should not be considered limiting of the disclosure, various embodiments, and / or various implementations detailed herein.

Claims

1. A method for determining ligand escape paths, characterized in that, include: Obtain a first structural model of a protein and a ligand in a bound state, wherein the first structural model includes a protein structural model and a ligand structural model; The ligand structure model is dissociated from the protein structure model, and the spatial relationship between the ligand structure model and the protein structure model is monitored during the dissociation process to obtain the monitoring results. If the monitoring results indicate that the ligand structure model has entered the external region for the first time, the dissociation operation is terminated to obtain the escape path of the ligand structure model during the dissociation process. The external region is the region outside the protein structure model and bounded by the surface of the protein structure model.

2. The method according to claim 1, characterized in that, Also includes: Obtain the surface geometric element information of the protein structure model; Based on the surface geometric element information, the internal geometric elements of the protein structure model are determined, and the internal region of the first structure model is obtained; The area outside the inner area is defined as the outer area.

3. The method according to claim 1, characterized in that, The monitoring of the spatial relationship between the ligand structure model and the protein structure model during the dissociation process, and the resulting monitoring results, include: Obtain the surface geometric element information of the protein structure model; Based on the surface geometric element information, an equivalent geometric structure with the surface geometric element as the geometric center is obtained; In the event of a collision between the ligand structure model and the equivalent geometric structure, the energy generated by the collision is obtained; The monitoring results are obtained based on the energy.

4. The method according to claim 2 or 3, characterized in that, The surface geometric element information includes: surface grid information, or surface collision sphere information.

5. The method according to claim 1, characterized in that, Before performing the dissociation operation on the ligand structure model, the following is also included: The spatial relationship between the ligand structure model and the protein structure model is detected to obtain the detection results; If the detection result indicates that the ligand structure model has not entered the external region, the dissociation operation is performed.

6. The method according to claim 1, characterized in that, The dissociation operation on the ligand structure model, causing the ligand structure model to dissociate from the protein structure model, includes: Obtain the initial velocity set corresponding to the ligand structure model, and the first thrust, wherein the initial velocity set includes the initial velocity of each atom in the ligand structure model; The first thrust is applied to the center of mass of the ligand structure model, and the initial velocity is applied to the corresponding atom, causing the ligand structure model to dissociate from the protein structure model.

7. The method according to claim 6, characterized in that, The escape path contains dynamic information, and the dissociation operation on the ligand structure model, causing the ligand structure model to dissociate from the protein structure model, includes: Based on multiple initial velocity sets and the first thrust, multiple candidate escape paths with the same starting point and the same ending point are obtained; The method further includes: Based on the dynamic information contained in the multiple candidate escape paths, the average dissociation time corresponding to the starting point and the ending point is obtained; The target escape path is determined based on the average dissociation time.

8. The method according to claim 1, characterized in that, The acquisition of the first structural model of the protein and ligand in the bound state includes: Obtain the initial structural model of the protein and ligand in the bound state; The initial structural model is pre-balanced to obtain the first structural model.

9. The method according to claim 1, characterized in that, The method further includes: Determine the accessibility probability of each escape path; Based on the accessibility probability, the terrain contour lines inside the protein structure model are determined.

10. The method according to claim 1, characterized in that, The method further includes: The multiple escape paths are clustered to obtain at least one category, which represents the exit location where the ligand leaves the protein.

11. A device for determining ligand escape paths, characterized in that, include: The first structural model acquisition unit is used to acquire the first structural model of the protein and ligand in the binding state, wherein the first structural model includes a protein structural model and a ligand structural model. The monitoring result determination unit is used to perform a dissociation operation on the ligand structure model, so that the ligand structure model is dissociated from the protein structure model, and to monitor the spatial relationship between the ligand structure model and the protein structure model during the dissociation process to obtain the monitoring result; An escape path determination unit is used to terminate the dissociation operation when the monitoring results indicate that the ligand structure model has entered the external region for the first time, thereby obtaining the escape path of the ligand structure model during the dissociation process. The external region is the region outside the protein structure model and bounded by the surface of the protein structure model.

12. An electronic device comprising a memory, a processor, and a computer program stored in the memory, characterized in that, The processor executes the computer program to implement the steps of the method according to any one of claims 1 to 10.

13. A non-volatile computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 10.

Images