Method for determining relationships between molecules and electronic device

Abstract

Embodiments of the present disclosure relate to a method for determining relationship between molecules and an electronic device. The method comprises: determining a first chemical feature of a first molecule based on eigenfunctions of a Laplacian operator on a surface Riemannian manifold of the first molecule; determining a second chemical feature of a second molecule based on eigenfunctions of the Laplacian operator on a surface Riemannian manifold of the second molecule; determining a functional mapping matrix between the first chemical feature and the second chemical feature by a functional mapping; and determining a similarity between the first molecule and the second molecule based on the functional mapping matrix. In this way, embodiments of the present disclosure can determine a functional mapping matrix based on chemical features determined based on eigenfunctions of a Laplacian operator on a Riemannian manifold, so that the similarity between different molecules can be compared in a manifold space. This avoids comparing the three-dimensional geometric structure of molecules by alignment and the like, reduces the amount of calculation, and improves the efficiency of processing.

Description

Technical Field

[0001] This disclosure generally relates to the fields of computer science and bioinformatics, and more specifically to methods and electronic devices for determining relationships between molecules. Background Technology

[0002] Different chemical compositions and geometric structures determine the roles of biomolecules in life activities; therefore, in the field of biopharmaceuticals, the structure-activity relationship of molecules is a crucial factor. For example, antibody proteins bind to specific antigens (such as viruses) to inhibit disease. Thus, understanding the interactions between molecules is essential in the biopharmaceutical field (e.g., new drug development).

[0003] Traditionally, wet experiments are used to obtain information about the interactions between biomolecules. This includes measuring the dissociation equilibrium constant between small drug molecules and receptor proteins, observing the 3D structure of the complexes formed after molecular binding, and then screening for suitable drug molecules for optimization. However, this method is costly and time-consuming, resulting in low efficiency and impacting the efficiency of tasks in the biopharmaceutical field (such as new drug development). Summary of the Invention

[0004] According to an example embodiment of this disclosure, a method for determining relationships between molecules is provided, which determines the similarity between molecules based on a functional mapping matrix.

[0005] In a first aspect of this disclosure, a method for determining relationships between molecules is provided, comprising: determining a first chemical feature of a first molecule based on the eigenfunctions of a Laplace operator on a surface Riemannian manifold of a first molecule; determining a second chemical feature of a second molecule based on the eigenfunctions of a Laplace operator on a surface Riemannian manifold of a second molecule; determining a functional mapping matrix between the first chemical feature and the second chemical feature through a functional mapping; and determining the similarity between the first molecule and the second molecule based on the functional mapping matrix.

[0006] In a second aspect of the present disclosure, an electronic device is provided, comprising: at least one processing unit; and at least one memory coupled to the at least one processing unit and storing instructions for execution by the at least one processing unit, the instructions causing the electronic device to perform the method described in the first aspect of the present disclosure when executed by the at least one processing unit.

[0007] In a third aspect of the present disclosure, a computer-readable storage medium is provided having machine-executable instructions stored thereon, which, when executed by a device, cause the device to perform the method described in the first aspect of the present disclosure.

[0008] In a fourth aspect of the present disclosure, a computer program product is provided, including computer-executable instructions, wherein the computer-executable instructions, when executed by a processor, implement the method described in the first aspect of the present disclosure.

[0009] In a fifth aspect of this disclosure, an electronic device is provided, including: a processing circuit configured to perform the method described in the first aspect of this disclosure.

[0010] The summary section is provided to introduce a series of concepts in a simplified form, which will be further described in the detailed description below. The summary section is not intended to identify key or essential features of this disclosure, nor is it intended to limit the scope of this disclosure. Other features of this disclosure will become readily apparent from the following description. Attached Figure Description

[0011] The above and other features, advantages, and aspects of the embodiments of this disclosure will become more apparent from the accompanying drawings and the following detailed description. In the drawings, the same or similar reference numerals denote the same or similar elements, wherein:

[0012] Figure 1 A schematic diagram of the electron density field of a benzene molecule according to some embodiments of the present disclosure is shown;

[0013] Figure 2 A schematic diagram of a molecular surface represented by triangulation according to some embodiments of the present disclosure is shown;

[0014] Figure 3A A schematic diagram is shown of nodes that project chemical information of atoms onto the surface of molecules according to some embodiments of the present disclosure;

[0015] Figure 3B A schematic diagram of the electrostatic potential energy function of a molecular surface according to some embodiments of the present disclosure is shown;

[0016] Figure 4 A schematic diagram showing the distribution of the first six eigenfunctions of a molecule on the molecular surface according to some embodiments of the present disclosure is illustrated.

[0017] Figure 5 A schematic diagram is shown of two different three-dimensional conformations X and Y of the same molecule according to some embodiments of the present disclosure, and the corresponding Riemann manifolds M and N;

[0018] Figure 6 Exemplary representations of functional mappings according to some embodiments of this disclosure are shown;

[0019] Figure 7 A schematic flowchart illustrating the process of determining relationships between molecules according to some embodiments of the present disclosure is shown;

[0020] Figure 8 A schematic diagram of functional mapping according to some embodiments of the present disclosure is shown;

[0021] Figure 9 Block diagrams of example apparatuses according to some embodiments of the present disclosure are shown; and

[0022] Figure 10 A block diagram of an example device that can be used to implement embodiments of the present disclosure is shown. Detailed Implementation

[0023] Embodiments of this disclosure will now be described in more detail with reference to the accompanying drawings. While some embodiments of this disclosure are shown in the drawings, it should be understood that this disclosure can be implemented in various forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided to provide a more thorough and complete understanding of this disclosure. It should be understood that the accompanying drawings and embodiments of this disclosure are for illustrative purposes only and are not intended to limit the scope of protection of this disclosure.

[0024] As mentioned earlier, determining the relationships between different molecules (such as similarity) is crucial in the field of molecular pharmaceutics. However, current methods for determining these relationships are too inefficient, thus impacting the efficiency of tasks in the biopharmaceutical field, such as new drug development.

[0025] To address at least the aforementioned problems and other potential issues, embodiments of this disclosure provide a scheme for determining relationships between molecules. Specifically, the chemical characteristics of different molecules can be determined separately, and a functional mapping matrix between the chemical characteristics of different molecules can be determined to identify the similarity between different molecules. This scheme can be implemented based on artificial intelligence technologies (such as deep learning), enabling faster determination of relationships between molecules and thus ensuring the efficiency of tasks in the biopharmaceutical field (such as new drug development).

[0026] The chemical features in the embodiments of this disclosure are determined based on a molecular representation method based on Riemannian manifolds. For ease of description, the following description is combined with... Figures 1 to 6 Describe molecular representation methods based on Riemannian manifolds and functional mappings.

[0027] In some exemplary embodiments of this disclosure, the molecular surface of a molecule can be determined based on the isosurface of the electron density field of the molecule.

[0028] Biomolecules are generally measured in units of 10⁻⁶. -10Using the meter (angstrom) as the unit, at this microscopic scale, biomolecules generally follow the physical laws described by quantum mechanics and statistical mechanics, rather than Newtonian mechanics at the macroscopic scale. From the perspective of microscopic electronic structure, molecules consist of positively charged atomic nuclei and negatively charged electron clouds. Intuitively, molecules can be understood as electron density fields. Different biomolecules have different chemical compositions and 3D geometric structures, thus exhibiting different physicochemical properties. For example, specific drug molecules bind to certain protein receptors in the human body to achieve therapeutic effects. That is to say, different molecules have their unique electron density fields, and therefore, different molecules can be represented by describing the shape and chemical properties of this density field. Specifically, the isosurface of the density field can be determined, which is called the molecular surface of the molecule.

[0029] As an example, such as Figure 1 The electron density field 100 of a benzene molecule, as shown in an embodiment of this disclosure, is... Figure 1 In the diagram, curve 110 represents the isosurface.

[0030] For example, the analyzed electron density field can be represented as the electron density function of a molecule. Optionally, the electron density function of a molecule can be determined by quantum chemical simulations. Further, the molecular surface can be determined based on the isosurface of the electron density function of the molecule. For example, the electron density function of a molecule may have multiple isosurfaces, and in some embodiments of this disclosure, the molecular surface can be determined by selecting one of these isosurfaces.

[0031] In some exemplary embodiments of this disclosure, the molecular surface can also be determined using other molecular surface calculation methods. For example, the molecular surface can be determined using MSMS calculation software.

[0032] In some exemplary embodiments of this disclosure, the molecular surface of a molecule can also be determined based on sampling of the solvent-accessible or inaccessible surfaces of the molecule.

[0033] It is understood that in other examples, other methods may be used to determine the molecular surface of the molecule in the embodiments of this disclosure, and this disclosure is not limited thereto.

[0034] In some examples, a molecular surface can be represented as a discrete set of surface nodes and the connections between them. Exemplarily, surface information can be further determined based on the defined molecular surface. For instance, mesh representation methods such as triangulation can be used to store the surface information. Figure 2A schematic diagram of a molecular surface represented by triangulation is shown. As shown, the surface is shown with triangulation nodes (referred to as "nodes"), and these nodes may be connected. That is, the molecular surface includes multiple surface nodes, such as multiple triangulation nodes.

[0035] Exemplarily, the surface encapsulates molecules and can represent the shape of the molecules. In embodiments of this disclosure, the stored surface information may include: atomic information within the molecule, and the 3D coordinates of each node on the molecular surface and the connections between nodes. For example, the atomic information within the molecule includes the three-dimensional coordinates of atoms and related chemical information such as atom types. It is understood that the molecular surface is a two-dimensional Riemannian manifold, which is itself continuous and smooth. In subsequent processing of embodiments of this disclosure, this continuous and smooth Riemannian manifold can be discretized, for example, by triangulating the nodes.

[0036] In some exemplary embodiments of this disclosure, for each of a plurality of surface nodes, the chemical environment characteristics of the node are obtained by mapping the atomic information of a plurality of atoms associated with the node to the node; based on the chemical environment characteristics of each of the plurality of surface nodes, a fully connected neural network is used to determine the chemical characteristics. Exemplarily, the plurality of atoms associated with the node may include: a plurality of atoms whose distance from the node is less than a distance threshold. Or, exemplarily, the plurality of atoms associated with the node may include: a fixed number of neighboring atoms (e.g., 8 nearest neighbor atoms) closest to the node. For example, the atoms may be sorted according to their distance from the node, and a fixed number (e.g., 8) of the nearest neighbors may be determined from the sorted atoms.

[0037] Specifically, the chemical potential distribution on a molecular surface can be determined based on the surface information of the molecule. Alternatively, the chemical potential distribution can also be referred to as the chemical function distribution, such as the electrostatic potential distribution.

[0038] For example, for any node on an analytical surface, the distances between that node and all atoms within a specific distance range can be determined. For instance, atoms within a distance threshold range can be termed neighboring atoms. Subsequently, the angle between each neighboring atom and the normal to the tangent plane of the surface containing the node, as well as the corresponding atom type, can be determined, serving as an initial representation of the node's chemical environment. For example, the chemical function distribution of a molecular surface can be extracted using a fully connected neural network. That is, a fully connected neural network can learn the representation of the chemical environment surrounding a surface node.

[0039] In this way, by mapping (also known as projecting) the chemical information of the internal atoms onto the nodes on the surface, the chemical information of the entire molecule can be characterized through the nodes on the molecular surface. Figure 3AA schematic diagram is shown of projecting the chemical information of atoms onto nodes on a molecular surface. As shown, for node 310, atoms within a specific distance range 320 can be identified. The chemical information of the identified atoms can then be projected onto node 310 to determine an initial representation of the chemical environment of node 310, such as the chemical environment characteristics of the node.

[0040] It should be noted that in the embodiments of this disclosure, the chemical information of atoms can be used to update the chemical representation of nodes on the molecular surface. However, the node information does not feed back or change the chemical information of atoms; that is, this projection belongs to a one-way information transmission relationship. This differs from the bidirectional updating of molecular graph neural networks. It is understood that although graph neural networks can achieve long-distance information exchange through graph information transmission, this exchange mechanism is inefficient when the number of nodes is large (e.g., the triangulation representation of a molecule's surface typically has tens of thousands of nodes). Conversely, the embodiments of this disclosure, through the one-way information transmission relationship from atomic information to nodes, can improve the processing efficiency of information exchange.

[0041] For example, a fully connected neural network can be used to determine the chemical characteristics of a molecular surface based on the chemical environment characteristics of each node in a multi-dimensional network. Alternatively, as an example, the chemical information of atoms can be represented as a multi-dimensional (e.g., 5-dimensional) array, and the surface chemical characteristics can be represented as a multi-dimensional (e.g., 16-dimensional) array.

[0042] Figure 3B A schematic diagram of the electrostatic potential energy function 330 of a molecular surface is shown. For example, this electrostatic potential energy function can be obtained by extraction based on, for example, the first dimension of a chemical feature in a 16-dimensional array. It is understood that, although... Figure 3B The electrostatic potential energy function is used as an example for illustration, but the embodiments disclosed herein are not limited to this. For example, users can customize other chemical information, or learn other chemical representations through neural networks or other means.

[0043] In this way, the distribution of chemical potential on the molecular surface can simultaneously contain both geometric and chemical information. For example, the distribution of chemical potential functions, such as the electrostatic potential function, on the molecular surface belongs to the surface Riemannian manifold space representation of the molecule; that is, chemical information can exist in the surface Riemannian manifold space of the molecule in the form of functions. In other words, in the embodiments of this disclosure, the surface of the molecule is regarded as a continuous and smooth Riemannian manifold space, and chemically related functions are defined in this two-dimensional manifold space.

[0044] In some exemplary embodiments of this disclosure, the eigenfunctions and eigenvalues ​​of a Laplace operator on a molecular surface (Riemannian manifold) can be determined.

[0045] For example, the eigenfunctions and eigenvalues ​​of the Laplace-Beltramioperator on the Riemannian manifold of each molecular surface can be determined as follows: (1)

[0046] Δφ i =λ i φ i (1)

[0047] In equation (1), Δ represents the Laplace operator, and its meaning is as follows in equation (2):

[0048]

[0049] In equation (1), Let λ represent the i-th eigenfunction. i Let represent the i-th eigenvalue. In equation (2), Let f denote the gradient operator, and let f denote any function distributed on the Riemannian manifold. Eigenfunctions can be determined using known algorithms (e.g., SciPy numerical computation software) or algorithms developed in the future, but this disclosure is not limited in this regard.

[0050] In some examples, the Laplace eigenfunctions and their corresponding eigenvalues ​​of each molecular surface manifold are unique and depend only on the shape of the molecule itself, unaffected by the molecule's position and orientation in three-dimensional space. Therefore, the eigenfunctions of Riemannian manifolds are also referred to as "shape DNA." For each molecule's surface manifold, all its eigenfunctions and eigenvalues ​​can be determined. Exemplarily, the eigenvalues ​​can be further sorted by magnitude, for example, in ascending order, and then the first k eigenvalues ​​(e.g., k = 100 or other values) can be selected, thus reducing computational complexity.

[0051] Understandably, different biomolecules have different shapes, and therefore different surface manifold eigenfunctions. Figure 4 The diagram illustrates the distribution of the first six eigenfunctions of a molecule on its surface according to some embodiments of the present disclosure. Exemplarily, the first six eigenfunctions are distributed on... Figure 4 The middle is shown as In some examples, the eigenfunctions are in Figure 4 The region exhibits regional fluctuations, and correspondingly, the eigenfunctions can be understood as Fourier basis functions in two-dimensional manifold space (for example, they can be understood as two-dimensional standing waves), which correspond to sine and cosine functions on a one-dimensional straight line.

[0052] As described above Figure 1 and Figure 2As shown, embodiments of this disclosure can determine the molecular surface of a molecule, and that the molecular surface is a continuous Riemannian manifold. It is understood that the interactions between molecules in real systems (such as the human body) are dynamic processes, and the molecular configuration (also called conformation) constantly changes. For example, for a given molecule, assuming there are two different conformations, X and Y, then the molecular surfaces of conformations X and Y can be determined, assuming they are Riemannian manifolds M and N, respectively. Figure 5 A schematic diagram showing two different three-dimensional conformations X and Y of the same molecule and their corresponding Riemannian manifolds M and N is presented.

[0053] For any two points a and b on a Riemannian manifold M, the Riemannian metric between these two points can be determined. That is, the distance on the surface. Similarly, for two corresponding points f(a) and f(b) on a Riemannian manifold N, the Riemannian metric between these two points can be determined. It can be observed that these two Riemannian metrics satisfy equation (3):

[0054]

[0055] Therefore, Riemannian manifolds M and N are approximately isomorphic. Isomorphism, also known as a distance-preserving mapping, refers to an isomorphic relationship that maintains distance in a metric space. For example, f can be a distance-preserving mapping from Riemannian space M to Riemannian space N, for instance, denoted as...

[0056] Based on isomorphism, embodiments of this disclosure provide a scheme for comparing the similarity of two molecules in a two-dimensional Riemannian manifold. This eliminates the need for alignment comparisons in three-dimensional space, avoiding the problem of rotational and translational invariance in three-dimensional space.

[0057] The following is combined with, for example Figure 5 The functional mapping is described by two Riemannian manifolds M and N. The problem solved by the functional mapping technique can be understood as transforming a function f on manifold M into a corresponding function g on manifold N. Since a manifold is essentially a space, the functional mapping can be understood as a function transformation (denoted as T) on two spaces, i.e., T: M→N, which can be expressed as the following equation (4):

[0058]

[0059] Based on the aforementioned equations (1) and (2), and They can be represented as:

[0060]

[0061] In other words, it can and Let each be represented as an expansion of its respective basis function, with coefficients a and a' respectively. i and b i Therefore, based on equations (4) and (5), the following functional mapping can be determined:

[0062]

[0063] Alternatively, it can be expressed as:

[0064]

[0065] Or CA = B (8)

[0066] In equation (8), A is the coefficient matrix corresponding to multiple functions (f1, f2, ...,), B is the coefficient matrix corresponding to multiple functions (g1, g2, ...), and C is the functional mapping matrix.

[0067] As mentioned above, manifolds M and N satisfy an approximately isomorphic relationship, therefore their basis functions are also similar. Thus, when functions f and g are in one-to-one correspondence, the functional mapping matrix C is approximately a diagonal matrix, with elements on the diagonal being positive and negative 1. For example... Figure 6 An exemplary representation of functional mapping is shown.

[0068] For example, the one-to-one correspondence of functions f and g can be molecular-related functions, such as curvature, chemical potential energy, charge, etc.

[0069] As described above Figures 1 to 6 Molecular representations based on Riemannian manifolds and functional mappings have been described. The following will further describe a scheme for determining the similarity between different molecules according to embodiments of this disclosure.

[0070] Figure 7 A schematic flowchart of a process 700 for determining relationships between molecules according to some embodiments of the present disclosure is shown. At block 710, a first chemical characteristic of the first molecule is determined based on the eigenfunctions of the Laplace operator on the surface Riemannian manifold of the first molecule. At block 720, a second chemical characteristic of the second molecule is determined based on the eigenfunctions of the Laplace operator on the surface Riemannian manifold of the second molecule. At block 730, a functional mapping matrix between the first and second chemical characteristics is determined by functional mapping. At block 740, the similarity between the first and second molecules is determined based on the functional mapping matrix.

[0071] In embodiments of this disclosure, the eigenfunctions of the Laplace operator on the Riemannian manifold represent the geometry of the molecule, for example, determining the geometric characteristics of the manifold. In embodiments of this disclosure, the chemical characteristics of the molecule can be represented in functional form, for example, determining the functional distribution on the manifold. For example, the first and second chemical characteristics can be represented as electrostatic potential energy functions of the molecular surface.

[0072] In some embodiments, for any molecule, the molecular surface of the molecule can be determined, as described above. Figures 1 to 2 The relevant description is as follows: It can be understood that the molecular surface is a continuous Riemannian manifold, represented as multiple surface nodes and the connections between these nodes.

[0073] In some embodiments, for any molecule, the chemical characteristics of the molecule can be determined by mapping atomic information to surface nodes, as described above. Figures 3A to 3B The relevant descriptions are as follows. It is understood that chemical characteristics, for example, can be electrostatic potential energy functions.

[0074] In some examples, chemical characteristics can be represented as linear combinations of their corresponding eigenfunctions. For instance, a first chemical characteristic is represented as a linear combination of the eigenfunctions of the Laplace operator on the surface Riemannian manifold of a first molecule, and a second chemical characteristic is represented as a linear combination of the eigenfunctions of the Laplace operator on the surface Riemannian manifold of a second molecule. To simplify the description, the first and second chemical characteristics can be represented as follows:

[0075]

[0076] In the above formula, and Let the surface Riemannian manifolds of the first molecule and the second molecule be represented respectively. Let the eigenfunctions of the Laplace operator on the surface Riemannian manifold of the first molecule be denoteed. Let a1 represent the eigenfunctions of the Laplace operator on the surface Riemannian manifold of the second molecule. i and b1 i These are the coefficients of the linear combination.

[0077] Based on the first and second chemical characteristics, the first coefficient matrix (e.g., denoted as A1) and the second coefficient matrix (e.g., denoted as B1) can be determined accordingly. Furthermore, the functional mapping matrix can be determined based on the first and second coefficient matrices.

[0078] For example, the functional mapping matrix can be a kernel function. By analyzing the properties of the functional mapping matrix, the similarity between two different molecules can be described, such as the similarity between geometric and chemical properties. For instance, if the functional mapping matrix is ​​represented as a diagonal matrix, it can be determined that the similarity between the first molecule and the second molecule is above a threshold. That is, the first molecule and the second molecule have similar geometric and chemical characteristics.

[0079] Understandable, despite Figure 7 The process 700 describes an embodiment for determining similarity in conjunction with the first and second molecules, but the embodiments of this disclosure can be applied to a greater number of molecules.

[0080] For example, if the first molecule can be an intermediate drug molecule with known biological activity, then one or more other potential molecules similar to this intermediate drug molecule can be found from a database, and the drug activity of the potential molecules can be tested. In this way, this scheme can realize computer-based virtual screening of drug molecules based on functional mapping and artificial intelligence models. This process is achieved through a data-driven approach using machine learning, and is therefore more efficient.

[0081] As an example, suppose the eigenfunction of the Laplace operator on the Riemannian manifold of an intermediate drug molecule can be represented as φ1, and its chemical characteristic f1 can be obtained through a neural network, for example, f1 = ∑ i a1 i φ1 i Let its coefficient matrix be A1. Suppose that for two molecules in the database, the eigenfunctions of the Laplace operator on their respective Riemannian manifolds can be represented as ξ1 and ξ2, respectively. Their chemical characteristics h1 and h2 can be obtained through a neural network, for example, h1 = ∑ i d1 i ξ1 i and h2=∑ i d2 i ξ2 i Their coefficient matrices are represented as D1 and D2, respectively.

[0082] Furthermore, based on the aforementioned description of functional mappings, the functional mapping matrices can be determined as follows:

[0083]

[0084]

[0085] in, This represents the value of C when the minimum value is reached.

[0086] Figure 8A schematic diagram illustrating the functional mapping between an intermediate drug molecule and two different molecules in a database is shown. From Figure 8 It can be seen that the functional mapping matrix C1 is closer to a diagonal matrix, while the functional mapping matrix C2 deviates more from a diagonal matrix.

[0087] In some examples, for multiple molecules in a database, multiple functional mapping matrices between the multiple molecules and the intermediate drug molecule can be determined separately, and a predetermined number (e.g., N) of potential molecules can be selected from the multiple molecules. For example, the N functional mapping matrices that are closest to the diagonal matrix can be selected from the multiple functional mapping matrices, and the N molecules corresponding to the selected N functional mapping matrices are the N potential molecules.

[0088] Optionally, in some embodiments, the biological activity of each of the N potential molecules can be determined individually using wet experiments.

[0089] In this way, embodiments of this disclosure map chemical properties to functions in a manifold space using a neural network model, thereby enabling the comparison of similarity between different molecules in the manifold space. This avoids comparing the three-dimensional geometry of different molecules through alignment or other methods, eliminating the need to consider molecular rotation and other properties, and reducing computational load while improving processing efficiency.

[0090] Additionally or optionally, the molecules in the embodiments of this disclosure may be protein molecules. Exemplarily, the first and second molecules may also be clustered based on the similarity between them.

[0091] For example, for multiple protein molecules, a functional mapping matrix can be determined for each pair of molecules, and the similarity between each pair can be determined. Further, based on the similarity between each pair of protein molecules, the multiple protein molecules can be divided into K classes, where K can be a user-defined value. It is understood that since the functional mapping matrix (i.e., kernel function) in the embodiments of this disclosure considers both geometric and chemical features, the resulting clustering results are classifications based on protein structure and function. Because clustering results are crucial for understanding the role of proteins in life activities and protein evolution, the solution disclosed in this disclosure can provide important and potentially valuable references for biopharmaceutical research.

[0092] It is understood that the methods for determining the similarity between molecules in the embodiments of this disclosure can be applied to downstream biopharmaceutical applications. For example, they can be used for molecular docking to facilitate new drug development. Because this disclosure can efficiently determine similarity, the solution disclosed herein can accelerate the subsequent new drug development process.

[0093] It should be understood that in the embodiments of this disclosure, "first," "second," "third," etc., are only used to indicate that multiple objects may be different, but at the same time, it does not exclude that two objects are the same, and should not be interpreted as any limitation on the embodiments of this disclosure.

[0094] It should also be understood that the methods, situations, categories, and classifications of embodiments in this disclosure are for the convenience of description only and should not constitute a special limitation. Various methods, categories, situations, and features in embodiments can be combined with each other where logically consistent.

[0095] It should also be understood that the foregoing is merely to help those skilled in the art better understand the embodiments of this disclosure, and is not intended to limit the scope of the embodiments of this disclosure. Those skilled in the art can make various modifications, variations, or combinations based on the foregoing. Such modifications, variations, or combinations are also within the scope of the embodiments of this disclosure.

[0096] It should also be understood that the above description focuses on highlighting the differences between the various embodiments. Similarities or commonalities can be referenced or learned from each other, and for the sake of brevity, they will not be repeated here.

[0097] Figure 9 A schematic block diagram of an example device 900 according to some embodiments of the present disclosure is shown. Device 900 can be implemented by software, hardware, or a combination of both. Figure 9 As shown, the device 900 includes a first chemical feature determination module 910, a second chemical feature determination module 920, a functional mapping matrix determination module 930, and a similarity determination module 940.

[0098] The first chemical feature determination module 910 is configured to determine the first chemical feature of the first molecule based on the eigenfunctions of the Laplace operator on the surface Riemannian manifold of the first molecule. The second chemical feature determination module 920 is configured to determine the second chemical feature of the second molecule based on the eigenfunctions of the Laplace operator on the surface Riemannian manifold of the second molecule. The functional mapping matrix determination module 930 is configured to determine the functional mapping matrix between the first and second chemical features through functional mapping. The similarity determination module 940 is configured to determine the similarity between the first and second molecules based on the functional mapping matrix.

[0099] In some embodiments, the apparatus 900 may further include: a first molecular surface determination module configured to determine a first molecular surface of a first molecule, the first molecular surface being a continuous Riemannian manifold and including a discrete plurality of first surface nodes; and a second molecular surface determination module configured to determine a second molecular surface of a second molecule, the second molecular surface being a continuous Riemannian manifold and including a discrete plurality of second surface nodes.

[0100] Optionally, the first molecule surface determination module may be specifically configured to: determine the first molecule surface based on the isosurface of the electron density field of the first molecule; or determine the first molecule surface based on sampling of the solvent-accessible or inaccessible surface of the first molecule.

[0101] In some examples, the first chemical feature determination module 910 can be configured to: for each of the multiple first surface nodes on the surface Riemann manifold of the first molecule, obtain the chemical environment features of the node by mapping the atomic information of the multiple atoms associated with the node to the node; and determine the first chemical feature using a fully connected neural network based on the chemical environment features of each of the multiple first surface nodes.

[0102] Optionally, the multiple atoms associated with a node include: multiple atoms within a range where the distance between them and the node is less than a distance threshold; or a fixed number of atoms that are closest to the node.

[0103] For example, the first chemical characteristic is represented as a linear combination of the eigenfunctions of the Laplace operator on the surface Riemannian manifold of the first molecule, and the second chemical characteristic is represented as a linear combination of the eigenfunctions of the Laplace operator on the surface Riemannian manifold of the second molecule.

[0104] In some embodiments, the functional mapping matrix determination module 930 may be configured to: determine a first coefficient matrix of a first chemical feature; determine a second coefficient matrix of a second chemical feature; and determine a functional mapping matrix based on the first and second coefficient matrices.

[0105] In some embodiments, the similarity determination module 940 may be configured to: determine that the similarity between the first molecule and the second molecule is higher than a threshold if the functional mapping matrix is ​​represented as a diagonal matrix.

[0106] In some examples, the device 900 may also include a clustering module configured to cluster the first molecule and the second molecule based on the similarity between the first molecule and the second molecule.

[0107] Optionally, both the first molecule and the second molecule are protein molecules. Optionally, the first molecule is a protein molecule with known chemical activity, and the device 900 may further include a verification module configured to perform a wet experiment on the second molecule to verify its biological activity when the similarity between the first molecule and the second molecule is higher than a threshold.

[0108] Figure 9 The device 900 can be used to achieve the above-mentioned combination. Figures 7 to 8 For the sake of brevity, the process described will not be repeated here.

[0109] The division of modules or units in the embodiments of this disclosure is illustrative and only represents one logical functional division. In actual implementation, there may be other division methods. Furthermore, the functional units in the disclosed embodiments may be integrated into one unit, exist as separate physical entities, or two or more units may be integrated into one unit. The integrated unit described above can be implemented in hardware or as a software functional unit.

[0110] Figure 10 A block diagram of an example device 1000 that can be used to implement embodiments of the present disclosure is shown. It should be understood that... Figure 10 The device 1000 shown is merely exemplary and should not be construed as limiting the functionality and scope of the implementation described herein. For example, device 1000 can be used to perform the functions described above. Figures 7 to 8 The process described herein. For example, device 1000 can be implemented as a classical computer and / or a quantum computer.

[0111] like Figure 10 As shown, device 1000 is in the form of a general-purpose computing device. Components of computing device 1000 may include, but are not limited to, one or more processors or processing units 1010, memory 1020, storage device 1030, one or more communication units 1040, one or more input devices 1050, and one or more output devices 1060. Processing unit 1010 may be a physical or virtual processor and is capable of performing various processes according to programs stored in memory 1020. In a multiprocessor system, multiple processing units execute computer-executable instructions in parallel to improve the parallel processing capability of computing device 1000.

[0112] Computing device 1000 typically includes multiple computer storage media. Such media can be any available media accessible to computing device 1000, including but not limited to volatile and non-volatile media, removable and non-removable media. Memory 1020 can be volatile memory (e.g., registers, cache, random access memory (RAM)), non-volatile memory (e.g., read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory), or some combination thereof). Storage device 1030 can be removable or non-removable media and may include machine-readable media, such as flash drives, disks, or any other media capable of storing information and / or data (e.g., training data for training) and accessible within computing device 1000.

[0113] The computing device 1000 may further include additional removable / non-removable, volatile / non-volatile storage media. Although not explicitly stated... Figure 10 As shown, disk drives for reading from or writing to removable, non-volatile disks (e.g., "floppy disks") and optical disk drives for reading from or writing to removable, non-volatile optical disks can be provided. In these cases, each drive can be connected to a bus (not shown) via one or more data media interfaces. Memory 1020 may include computer program product 1025 having one or more program modules configured to perform various methods or actions of various implementations of this disclosure.

[0114] The communication unit 1040 enables communication with other computing devices via a communication medium. Additionally, the components of the computing device 1000 can function as a single computing cluster or multiple computing machines capable of communicating via communication connections. Therefore, the computing device 1000 can operate in a networked environment using logical connections to one or more other servers, network personal computers (PCs), or another network node.

[0115] Input device 1050 can be one or more input devices, such as a mouse, keyboard, trackball, etc. Output device 1060 can be one or more output devices, such as a monitor, speaker, printer, etc. Computing device 1000 can also communicate with one or more external devices (not shown) via communication unit 1040 as needed. These external devices include storage devices, display devices, etc., and can communicate with one or more devices that enable user interaction with computing device 1000, or with any device that enables computing device 1000 to communicate with one or more other computing devices (e.g., network card, modem, etc.). Such communication can be performed via an input / output (I / O) interface (not shown).

[0116] According to an exemplary implementation of this disclosure, a computer-readable storage medium is provided that stores computer-executable instructions thereon, wherein the computer-executable instructions are executed by a processor to implement the methods described above. According to an exemplary implementation of this disclosure, a computer program product is also provided, which is tangibly stored on a non-transitory computer-readable medium and includes computer-executable instructions, which are executed by a processor to implement the methods described above. According to an exemplary implementation of this disclosure, a computer program product is provided that stores a computer program thereon, which, when executed by a processor, implements the methods described above.

[0117] Various aspects of this disclosure are described herein with reference to flowchart illustrations and / or block diagrams of methods, apparatuses, devices, and computer program products implemented according to this disclosure. It should be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer-readable program instructions.

[0118] These computer-readable program instructions can be provided to a processing unit of a general-purpose computer, a special-purpose computer, or other programmable data processing apparatus to produce a machine such that, when executed by the processing unit of the computer or other programmable data processing apparatus, they create means for implementing the functions / actions specified in one or more blocks of the flowchart and / or block diagram. These computer-readable program instructions can also be stored in a computer-readable storage medium that causes a computer, programmable data processing apparatus, and / or other device to operate in a particular manner. Thus, the computer-readable medium storing the instructions comprises an article of manufacture that includes instructions for implementing aspects of the functions / actions specified in one or more blocks of the flowchart and / or block diagram.

[0119] Computer-readable program instructions can 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, thereby causing the instructions that execute on the computer, other programmable data processing apparatus, or other device to perform the functions / actions specified in one or more boxes of a flowchart and / or block diagram.

[0120] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this disclosure. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of an instruction, which contains one or more executable instructions for implementing the specified logical function. In some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutive blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, may be implemented using a dedicated hardware-based system that performs the specified function or action, or using a combination of dedicated hardware and computer instructions.

[0121] Various implementations of this disclosure have been described above. These descriptions are exemplary and not exhaustive, nor are they limited to the disclosed implementations. Many modifications and variations will be apparent to those skilled in the art without departing from the scope and spirit of the described implementations. The terminology used herein is chosen to best explain the principles, practical applications, or improvements to technology in the market, or to enable others skilled in the art to understand the various implementations disclosed herein.

Claims

1. A method for determining relationships between molecules, comprising: Based on the eigenfunctions of the Laplace operator on the surface Riemannian manifold of the first molecule, a first chemical characteristic of the first molecule is determined, wherein the first chemical characteristic is represented as a linear combination of the eigenfunctions of the Laplace operator on the surface Riemannian manifold of the first molecule and has a first coefficient matrix. The second chemical characteristic of the second molecule is determined based on the eigenfunctions of the Laplace operator on the surface Riemannian manifold of the second molecule, wherein the second chemical characteristic is represented as a linear combination of the eigenfunctions of the Laplace operator on the surface Riemannian manifold of the second molecule and has a second coefficient matrix. By using functional mapping, the functional mapping matrix between the first chemical feature and the second chemical feature is determined based on the first coefficient matrix and the second coefficient matrix; as well as By analyzing the properties of the functional mapping matrix, the similarity between the first molecule and the second molecule is determined, wherein the properties include whether the functional mapping matrix is ​​represented as a diagonal matrix.

2. The method according to claim 1, further comprising: The first molecular surface of the first molecule is determined, wherein the first molecular surface is a continuous Riemannian manifold and includes a plurality of discrete first surface nodes; The second molecular surface of the second molecule is determined, wherein the second molecular surface is a continuous Riemannian manifold and includes a plurality of discrete second surface nodes.

3. The method of claim 2, wherein determining the first molecular surface of the first molecule comprises: The surface of the first molecule is determined based on the isosurface of the electron density field of the first molecule; or The surface of the first molecule is determined based on sampling of the solvent-accessible or inaccessible surfaces of the first molecule.

4. The method of claim 1, wherein determining the first chemical characteristic comprises: For each of the multiple first surface nodes on the surface Riemann manifold of the first molecule, the chemical environment characteristics of the node are obtained by mapping the atomic information of multiple atoms associated with the node to the node. Based on the chemical environment characteristics of each of the plurality of first surface nodes, a fully connected neural network is used to determine the first chemical characteristics.

5. The method of claim 4, wherein the plurality of atoms associated with the node comprises: Multiple atoms within a range where the distance between them and the node is below a distance threshold; or A fixed number of atoms that are closest to the node.

6. The method of claim 1, wherein determining the similarity between the first molecule and the second molecule comprises: If the functional mapping matrix is ​​represented as a diagonal matrix, then the similarity between the first molecule and the second molecule is determined to be higher than a threshold.

7. The method according to any one of claims 1 to 6, further comprising: Based on the similarity between the first molecule and the second molecule, the first molecule and the second molecule are clustered.

8. An electronic device, comprising: At least one processing unit; At least one memory coupled to the at least one processing unit and storing instructions for execution by the at least one processing unit, the instructions causing the electronic device to perform an action when executed by the at least one processing unit, the action including: Based on the eigenfunctions of the Laplace operator on the surface Riemannian manifold of the first molecule, a first chemical characteristic of the first molecule is determined, wherein the first chemical characteristic is represented as a linear combination of the eigenfunctions of the Laplace operator on the surface Riemannian manifold of the first molecule and has a first coefficient matrix. The second chemical characteristic of the second molecule is determined based on the eigenfunctions of the Laplace operator on the surface Riemannian manifold of the second molecule, wherein the second chemical characteristic is represented as a linear combination of the eigenfunctions of the Laplace operator on the surface Riemannian manifold of the second molecule and has a second coefficient matrix. By using functional mapping, based on the first coefficient matrix and the second coefficient matrix, a functional mapping matrix between the first chemical feature and the second chemical feature is determined; and By analyzing the properties of the functional mapping matrix, the similarity between the first molecule and the second molecule is determined, wherein the properties include whether the functional mapping matrix is ​​represented as a diagonal matrix.

9. An apparatus for determining relationships between molecules, comprising: The first chemical feature determination module is configured to determine the first chemical feature of the first molecule based on the eigenfunctions of the Laplace operator on the surface Riemann manifold of the first molecule, wherein the first chemical feature is represented as a linear combination of the eigenfunctions of the Laplace operator on the surface Riemann manifold of the first molecule and has a first coefficient matrix. The second chemical feature determination module is configured to determine the second chemical feature of the second molecule based on the eigenfunctions of the Laplace operator on the surface Riemann manifold of the second molecule, wherein the second chemical feature is represented as a linear combination of the eigenfunctions of the Laplace operator on the surface Riemann manifold of the second molecule and has a second coefficient matrix. The functional mapping matrix determination module is configured to determine the functional mapping matrix between the first chemical feature and the second chemical feature based on the first coefficient matrix and the second coefficient matrix through functional mapping. as well as A similarity determination module is configured to determine the similarity between the first molecule and the second molecule by analyzing the properties of the functional mapping matrix, wherein the properties include whether the functional mapping matrix is ​​represented as a diagonal matrix.

10. A computer-readable storage medium having a computer program stored thereon, the program, when executed by a processor, implementing the method according to any one of claims 1 to 7.

Images