A method, program, device and storage medium for predicting uranyl ion coordination bond length based on automatically generated dataset
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- HARBIN ENG UNIV
- Filing Date
- 2026-03-09
- Publication Date
- 2026-07-14
Smart Images
Figure CN122392683A_ABST
Abstract
Description
Technical Field
[0001] This invention belongs to the field of radionuclide coordination structure modeling and computational chemistry technology, specifically involving a method, program, device and storage medium for predicting uranyl ion coordination bond lengths based on automatically generated datasets. Background Technology
[0002] Uranyl ion (UO2) 2+ As one of the most common actinide forms in the nuclear fuel cycle and radioactive waste treatment, the coordination structure characteristics of uranyl ions directly affect extraction and separation behavior, coordination stability, and related thermodynamic properties. Therefore, accurately constructing a coordination structure model between uranyl ions and organic ligands is an important foundation for conducting coordination mechanism research and performance prediction.
[0003] In existing research, the initial configuration of uranyl ion coordination structures is typically constructed based on human experience, such as manually selecting coordinating atoms, setting coordination distances, and adjusting the spatial configuration. This approach not only relies on the professional experience of researchers but also suffers from low modeling efficiency, poor structural consistency, and difficulty in scaling up when dealing with a large number of different ligand molecules. This is especially true in organic ligand systems containing multiple functional groups, where the coordination ability of different functional groups to uranyl ions varies significantly. For example, carbonyl groups, amide oxygen, phosphoryl oxygen, and nitrogen atoms can all serve as potential coordination sites. Without a systematic identification and differentiation of the types and spatial distribution of functional groups in the ligands, it is often difficult to construct a reasonable uranyl ion coordination structure model.
[0004] The structural parameters of actinide coordination bonds, especially bond length, are key indicators characterizing the stability, reactivity, and separation selectivity of their complexes. The geometry of a particular actinide metal-ligand coordination bond is not solely determined by the properties of the ligand itself, but is significantly influenced by the presence, quantity, and spatial distribution of other metal-ligand coordination bonds around the metal center. Spatial repulsion and coordination competition between different ligands near the actinide metal center lead to significant mutual coupling between the coordination bonds; this phenomenon is commonly referred to as the multi-coordination competition effect. This effect is particularly pronounced in high coordination number systems such as actinides, often resulting in a significant change in the bond length of the target metal-ligand coordination bond compared to the single-coordination case.
[0005] On the other hand, in actual structural modeling and quantum chemical calculations, the coordination structure of actinide multi-coordination systems typically undergoes a gradual evolution from an initial configuration to a stable configuration. The fully converged structure obtained through high-precision quantum chemical calculations can accurately reflect the combined effect of multi-coordination competition in the final stable configuration, but its computational cost is high and the modeling cycle is long, making it difficult to directly apply to the rapid prediction of large-scale systems. In contrast, the low-precision or incompletely converged structures obtained in the early or intermediate stages of structural optimization, although still exhibiting some deviations in geometric parameters, already contain the basic spatial information of the target coordination bonds and their surrounding coordination environment, and preliminarily demonstrate the characteristics of the multi-coordination competition effect.
[0006] However, in existing technologies, most methods for predicting the length of actinide metal-ligand coordination bonds still rely solely on the fully converged structure obtained from high-precision quantum chemical calculations for modeling, typically using this structure as the sole learning or prediction target. This approach not only heavily depends on high-precision calculation results, making it difficult to reduce data construction costs, but also fails to effectively utilize the coordination environment information contained in low-precision or intermediate structures, making it difficult to balance accuracy and computational efficiency in the prediction process. Particularly in multi-coordination systems where the actinide metal coordination environment is filled with water molecules or other small molecules, these molecules already coordinate with the actinide metal center at the low-precision or intermediate structure stage, significantly influencing the geometric parameters of the target metal-ligand coordination bond. If the prediction method only uses the final high-precision converged structure as input, without establishing an effective correlation between the low-precision and high-precision coordination structures, it is difficult to accurately reflect the true multi-coordination competition effect while reducing computational costs. Summary of the Invention
[0007] The purpose of this invention is to provide a method for predicting the coordination bond length of uranyl ions based on automatically generated datasets.
[0008] A method for predicting the coordination bond length of uranyl ions based on automatically generated datasets includes the following steps:
[0009] A sample of ligand molecules of uranyl ions was obtained. Functional groups with potential coordination ability in the ligand molecules of each sample were identified and screened. The types of atoms that can act as coordinating atoms in each functional group and their spatial position information were determined. With uranium atom as the metal center, a multi-coordination system of uranyl ions that satisfies the distance constraint between non-bonded atoms and the angle constraint between adjacent coordinating atoms was constructed, and a sample set of multi-coordination system of uranyl ions was obtained.
[0010] For each group of uranyl ion multi-coordination system samples, structural data of the low-convergence stage and the high-convergence stage are obtained. One coordinating atom is selected as the target coordinating atom, and the remaining coordinating atoms are selected as competing coordinating atoms. Competitive coordination context information is constructed based on the structural data of the low-convergence stage. The bond length of the target coordinating bond is calculated based on the structural data of the low-convergence stage and the high-convergence stage, respectively, and the bond length error of the target coordinating bond is determined.
[0011] Construct and train a prediction model that can output the bond length error of the target coordination bond based on the input competitive coordination context information;
[0012] To predict the target uranyl ion multi-coordinate system, obtain structural data during the low-convergence phase. Select one coordinate bond as the target coordinate bond and determine its bond length and competing coordination context information. Input the competing coordination context information into the trained prediction model to obtain the bond length error of the target coordinate bond. Use the sum of the target coordinate bond length and the bond length error as the predicted bond length of the target coordinate bond. Repeat the above process by selecting other coordinate bonds as target coordinate bonds until the predicted bond lengths of all coordinate bonds are obtained.
[0013] Furthermore, the construction of a uranyl ion multi-coordination system that satisfies the distance constraints between non-bonded atoms and the angle constraints between adjacent coordinating atoms specifically involves:
[0014] For the ligand molecule sample, an initial coordination structure is generated between the uranyl ion center and the ligand molecule;
[0015] The axial uranium-oxygen bond length of the uranyl ion in the initial coordination structure It is 1.7~1.9 For the initial coordination distance between the coordinating atom and the uranium atom at the equatorial plane It ranges from 2.3 to 2.7. ;
[0016] Perform geometric adjustments on the initial coordination structure to ensure that the adjusted coordination structure satisfies the distance constraints between non-bonded atoms and the angle constraints between adjacent coordinating atoms.
[0017] Furthermore, the distance constraint between non-bonded atoms is: the distance between any two non-bonded coordinating atoms is not less than a set threshold. , 1.2~2 ;
[0018] The constraint of the included angle between adjacent coordinating atoms is: adjacent coordinating atoms and The angle formed with the center of the metal Not less than the set threshold , , for .
[0019] Furthermore, the axial uranium-oxygen bond length of the uranyl ion in the initial coordination structure The calculation method is as follows:
[0020]
[0021] in, The axial uranium-oxygen bond length under ligand-free or weakly ligand conditions; The modulation coefficient; Functional group coordination capacity factor;
[0022] The initial coordination distance between the coordinating atoms and uranium atoms in the equatorial plane The calculation method is as follows:
[0023]
[0024] in, The equatorial coordination distance under conditions of no ligand or weak ligand; The coordination shrinkage coefficient; , For the first Coordination ability factor of functional groups of each ligand.
[0025] Furthermore, the competitive coordination context information for:
[0026]
[0027] The competing coordinate key information for:
[0028]
[0029] in, For the first The first sample of the uranyl ion multicoordination system The bond length of the competitive coordination bond between the competing coordinating atoms and the metal center. To calculate the average, To calculate the standard deviation; , For the first The number of competing coordinating atoms in a group of uranyl ion multicoordination systems;
[0030] The distance information between the target coordinating atom and the competing coordinating atom for:
[0031]
[0032] in, For the first The first sample of the uranyl ion multicoordination system The distance between the competing coordinating atom and the target coordinating atom;
[0033] The angle information between the target coordinate bond and the competing coordinate bond for:
[0034]
[0035] in, For the first The first sample of the uranyl ion multicoordination system The angle formed between the competing coordinate bond and the target coordinate bond at the metal center;
[0036] The coordination environment asymmetric parameters for:
[0037]
[0038] in, For the first In the group of uranyl ion multicoordination system samples, from the metal center to the first Vectors of competing coordinating atoms;
[0039] The spatial occlusion parameters for:
[0040]
[0041] in, For the first The first sample of the uranyl ion multicoordination system The van der Waals radius of competing coordinating atoms.
[0042] Furthermore, the bond length of the target coordination bond is calculated based on the structural data during the low-convergence phase. The bond lengths of the target coordination bonds are calculated based on the structural data from the high-convergence phase. Determine the bond length error of the target coordinate bond. ;
[0043] Construct a training set, where each group of training samples is... ;
[0044] The prediction model is trained using a training set, enabling it to predict based on the input competitive coordination context information. Output the bond length error of the target coordinate bond .
[0045] Furthermore, the prediction model is specifically as follows:
[0046]
[0047] in, For local interference terms, This is a global statistical item. This refers to three-dimensional environmental statistics. For constant terms;
[0048]
[0049]
[0050]
[0051] in, , , , and These are the weight coefficients to be trained.
[0052] A computer device includes a memory, a processor, and a computer program stored in the memory, wherein the processor executes the computer program to implement the steps of the above-described method for predicting the coordination bond length of uranyl ions based on automatically generated datasets.
[0053] A computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of a method for predicting the coordination bond length of uranyl ions based on an automatically generated dataset.
[0054] A computer program product includes computer instructions that, when executed by a processor, implement steps of a method for predicting the coordination bond length of uranyl ions based on an automatically generated dataset.
[0055] The beneficial effects of this invention are as follows:
[0056] This invention automatically identifies functional groups in ligand molecules to determine potential coordination sites and their spatial distribution characteristics involved in uranyl ion coordination. It introduces uranyl ions into the ligand molecule space, generating an initial three-dimensional coordination structure model that satisfies the linear structural constraints and coordination geometry requirements of uranyl ions. The model is then geometrically validated and structurally adjusted to obtain samples of uranyl ion multi-coordination systems. This reduces the reliance on experience in manual modeling steps, improves the automation and consistency of uranyl ion coordination structure construction, and is applicable to uranyl ion coordination systems with different functional group types and multiple coordination modes. By explicitly considering multi-coordination competition effects during bond length prediction and fully utilizing coordination environment information already formed in low-precision or intermediate structures, this invention avoids strong dependence on high-precision fully converged structures, enabling a more realistic and efficient reflection of the structural response behavior of target coordination bonds in complex multi-coordination environments. This invention is suitable for structural analysis and rapid screening of multi-coordination metal coordination systems, featuring a clear methodology, strong applicability, and high prediction efficiency, and has promising engineering application prospects. Attached Figure Description
[0057] Figure 1 This is a schematic diagram of a uranyl ion multicoordination system.
[0058] Figure 2 This is a flowchart illustrating the process of generating a sample set of uranyl ion multi-coordination systems in this invention.
[0059] Figure 3 This is a flowchart illustrating the prediction of coordinate bond lengths in a uranyl ion multicoordination system in this invention. Detailed Implementation
[0060] The present invention will now be further described with reference to the accompanying drawings.
[0061] This invention first provides a method for generating a sample set of uranyl ion multi-coordination systems. The method takes the structure of the ligand molecule to be coordinated as input, performs structural analysis on the ligand molecule, and identifies the element types, connection relationships, and spatial distribution information of the atoms in the molecule. Based on this, the functional groups in the ligand molecule are determined according to a preset functional group identification rule, and functional groups with potential coordination ability and their corresponding coordinating atoms are screened out. Then, based on the identified functional group types and coordinating atom information, uranyl ions are introduced and an initial coordination relationship between them and the ligands is constructed. Under the condition of satisfying the linear structure constraint of uranyl ions, a uranyl ion coordination structure model is generated.
[0062] Step 1: Obtain the ligand molecule structure and perform functional group identification to achieve preliminary identification of potential coordination functional regions in the ligand molecule, providing basic structural information for subsequent coordination site analysis;
[0063] For the target uranyl ion coordination system, the structural information of the ligand molecule to be modeled is obtained, and the ligand molecule is subjected to functional group identification processing to determine the types of functional groups that may participate in metal coordination in the ligand molecule, such as carbonyl, hydroxyl, aldehyde, phosphoryl, nitro, amino and other oxygen- or nitrogen-containing functional groups.
[0064] Potential coordinating atoms are oxygen or nitrogen atoms in the functional group that can form coordination interactions with uranyl ions. Coordination modes include monodentate, bidentate, or polydentate coordination, which are determined by the spatial arrangement of the functional groups and the coordination preference of the uranyl ion.
[0065] The ligand molecule structure information can be derived from the molecular formula, two-dimensional structural formula, or three-dimensional initial configuration; functional group identification is used to classify and label the functional groups contained in the ligand molecule. The functional group identification process includes influencing factors such as functional group type, atomic composition characteristics, bond connection relationship, and local geometric configuration, and can be achieved by using a functional group matching rule judgment method based on SMARTS description.
[0066] Step 2: Construct a representation of coordination site information based on functional groups;
[0067] The identified functional groups are further analyzed to determine the types of atoms that can serve as metal coordinating atoms in each functional group and their spatial positions, thereby constructing a representation of coordination site information to characterize the coordination ability of ligands.
[0068] The coordination site information includes at least: the type of functional group; the type of atom that can participate in coordination within the functional group; and the spatial position of the atom in the ligand molecule.
[0069] Step 3: Generate the initial coordination structure of the uranyl ion-ligand;
[0070] Based on the constructed coordination site information, an initial coordination structure is generated between the uranyl ion center and the ligand molecule, which is used as the input configuration for subsequent quantum chemical calculations; wherein, the construction process of the initial coordination structure is based on the coordination ability of functional groups, and key coordination parameters are set in a regular manner.
[0071] The construction of the coordination structure of uranyl ions involves factors such as the selection of coordinating atoms, the setting of initial coordination distances, and the adjustment of spatial orientation. Uranyl ions are introduced in the form of a linear O=U=O structure, and this linear structure remains unchanged during the modeling process.
[0072] The initial coordination distance is set to a reasonable value within a predetermined range according to different functional group types to avoid atomic overlap or unreasonable spatial configuration.
[0073] (1) Determination of axial structural parameters
[0074] Uranyl ions are represented using a linear axial structure, and their axial oxygen-uranium-oxygen configuration satisfies:
[0075] O=U=O
[0076] The axial uranium-oxygen bond length is denoted as (where ax represents the axial direction).
[0077] To reflect the influence of equatorial plane coordination on axial bonding, Represented as a parametric function related to coordination functional groups:
[0078]
[0079] in, The reference axial bond length under ligand-free or weakly ligand conditions is preferably 1.75. ; Functional group coordination capacity factor; The modulation coefficient is used to control the intensity of the influence of equatorial plane coordination on the axial bond length, and its preferred value is 0.02~0.05. The result Limited to 1.7~1.9 Within a reasonable range, to ensure the physical rationality of the structure and the convergence of the calculation.
[0080] Axial uranium-oxygen bond length In basic bond length The functional group coordination ability factor is introduced to modulate the electron feedback effect of changes in the equatorial coordination environment on the axial U=O bond order, thereby reflecting the response relationship of axial bond length to changes in equatorial coordination electronic structure: when strong ligands appear in the equatorial plane, equatorial electron donation is enhanced, the occupancy of axial U=O antibonding orbitals increases slightly, and axial bonds are slightly elongated.
[0081] (2) Determination of the initial distance of equatorial coordination
[0082] For the coordination structure at the equatorial plane, let the initial coordination distance between the coordinating atom and the uranium atom be . .
[0083] This invention is the first to explicitly represent the initial equatorial coordination distance as a functional group-related calculation parameter, and its expression is as follows:
[0084]
[0085] in, For reference to the equatorial coordination distance, 2.6 is preferred. ; Functional group coordination capacity factor; The coordination contraction coefficient is preferably taken as 0.1 to 0.2. . The value is limited to 2.3~2.7. Within the range.
[0086] Equatorial Coordination Distance At the base distance A coordination ability factor is introduced for negative correction to characterize the coordination bond distance contraction effect caused by the enhanced electron-donating ability of ligands, resulting in electrostatic attraction between metal and coordinating atoms and the enhancement of covalent composition.
[0087] (3) Definition of functional group coordination ability factor
[0088] The functional group coordination ability factor Used to characterize the relative coordination strength between different functional groups and uranyl ions, its value is discretized based on the functional group type and the properties of the donor atom. In one embodiment of the present invention, the carbonyl group: Phosphoryl group: ; Nitro: ; Hydroxyl group: The above values are not unique and can be replaced or adjusted according to the needs of the system, but they all follow the basic principle that "strong coordination functional groups correspond to smaller equatorial coordination distances".
[0089] (4) Parameter extension in the case of multiple coordination
[0090] When multiple coordinating atoms participate in coordination simultaneously, the coordination ability factor of the functional group is taken as an average or weighted sum:
[0091]
[0092] The parameters are then substituted into the above formula to determine a uniform initial coordination parameter, thereby generating initial coordination configurations under different coordination number conditions.
[0093] Based on the adjusted initial coordination configuration, the output satisfies the axial coordination distance. Constraints and equatorial coordination distance The coordinates of the constrained uranyl ion-ligand coordination structure; during the adjustment of the coordination distance, the relative spatial relationships between atoms within the ligand molecule remain unchanged.
[0094] Step 4: Geometric normalization and validity determination of coordination configurations;
[0095] After obtaining the initial coordination configuration of uranyl ions and ligands, the configuration is geometrically adjusted and discriminated to ensure that it meets the structural rationality requirements for subsequent quantum chemical calculations.
[0096] (1) Configuration alignment and spatial adjustment
[0097] Using the uranium atom U in the uranyl ion as the origin of the coordinate system, and taking the coordinating atom as the center, the ligand as a whole is subjected to rigid translation and rotation operations to ensure that the distance between it and the uranium atom meets the set coordination distance range.
[0098] The translation and rotation operations do not change the bonding relationships and relative geometry within the ligand.
[0099] (2) Key geometric parameter constraints
[0100] For the adjusted configuration, define and check the following geometric parameters:
[0101] Non-bonded interatomic distance: (Any two non-bonding atoms i and j)
[0102] Adjacent coordinating atoms and The angle formed with the metal center U:
[0103] Where X = oxygen atom or nitrogen atom.
[0104] (3) Criteria for judging the rationality of structure
[0105] A configuration is considered valid only if it simultaneously meets the following conditions:
[0106] The distance between any non-bonding atom pairs is not less than a given threshold, i.e. To avoid unreasonable overlap between atoms, the settings are based on the combination of atom types. The preferred Å value is 1.2~2.0 Å; this is used to avoid unreasonable spatial overlap or strong repulsive interactions between non-bonding atoms, so as to ensure that the generated structure satisfies the van der Waals repulsion boundary conditions.
[0107] Depending on the coordination number, the coordination angle Falling within the allowed angle range To ensure the geometric rationality of the coordination direction, The preferred angle is 60° to 90°. This is used to ensure the proper arrangement of equatorial coordinating atoms on the equatorial plane of uranyl ions, maintaining the rationality of the coordination environment and the stability of the coordination polyhedron.
[0108] The uranyl ion-ligand coordination structures selected through geometric and coordination rationality screening are output, and quantum chemical calculations are performed on these coordination structures to quickly verify the rationality of their geometric configurations. The calculations employ density functional theory to perform low-cost structural optimization or single-point energy calculations on the uranyl ion-ligand coordination system.
[0109] The preliminary calculations confirmed that the coordinates of the uranyl ion coordination structure model with a reasonable structure can be used as the input structure for subsequent high-precision structure optimization calculations, coordination bond parameter analysis, or large-scale ligand screening applications.
[0110] Repeat the above process to generate batches of uranyl ion multi-coordination system samples with various ligands.
[0111] Based on a sample set of uranyl ion multi-coordination systems, this invention provides a method for predicting coordination bond lengths that considers multi-stage structural information transfer and coordination competition effects, comprising the following steps:
[0112] Step 1: For each group of uranyl ion multi-coordination system samples, obtain structural data for the low-convergence and high-convergence phases;
[0113] The structural data includes the spatial coordinates of the metal center, the spatial coordinates of each coordinating atom, and the bond lengths of the coordinate bonds between the metal center and each coordinating atom.
[0114] (1) Structured data in the low convergence stage:
[0115] The approximate coordination configuration is obtained by reducing the number of structural optimization iterations or relaxing the structural optimization convergence threshold, and is used to characterize the coordination structure when the coordination structure is not yet fully stable and the coordination competition effect is not yet fully manifested.
[0116] (2) High convergence stage structure data:
[0117] The stable coordination configuration is obtained by quantum chemical structure optimization calculations using strict convergence criteria, and is used to characterize the stable coordination configuration after the multi-coordination competition effect is fully realized.
[0118] In one embodiment of the invention, structural data is obtained through quantum chemical calculations. Structural optimization calculations are performed using density functional theory (DFT), with the exchange-correlation functional chosen as the PBE functional, and a D3BJ dispersion correction introduced to describe the weak interaction effects in the system. The basis set system uses the def2-SVP basis set, introducing an effective core potential (ECP) including core electrons to reasonably account for the influence of relativistic effects on the coordination structure. The solvent environment is described using a continuous medium solvent model, preferably an aqueous environment, to reflect the actual coordination behavior of the multi-coordination system under solution conditions. During structural optimization, rotational and translational degrees of freedom constraints are disabled, and a combination of self-consistent field iteration and geometric optimization is used to complete the structural evolution calculations.
[0119] To construct multi-stage structural data reflecting the structural evolution process, structural data for both the low-convergence and high-convergence stages were obtained under the same theoretical methods, basis set systems, and solvent models. The low-convergence stage structural data consisted of intermediate structures (the results of the fifth round of structural optimization) obtained under the preset maximum number of iterations in geometric optimization. These structures did not yet meet the final geometric convergence criterion but had already formed stable metal-ligand coordination relationships. The high-convergence stage structural data consisted of fully converged structures obtained after continuing geometric optimization under the same computational conditions until all convergence criteria were met.
[0120] Step 2: For each group of multi-coordination system samples, select one coordinating atom as the target coordinating atom, and the remaining coordinating atoms as competing coordinating atoms;
[0121] Competing coordination bonds can be formed by different types of ligands. These ligands differ in spatial position, coordination direction, and donor atom properties, thus exerting steric repulsion and coordination competition on the target coordination bond under multi-coordination conditions. For the same multi-coordination metal coordination system, by changing the method of selecting the target coordination bond, multi-coordination competition analysis scenarios targeting different target coordination bonds can be constructed.
[0122] Calculate the bond length of the target coordination bond based on the structural data during the low-convergence phase. The bond lengths of the target coordination bonds are calculated based on the structural data from the high-convergence phase. Determine the bond length error of the target coordinate bond. ;
[0123] Construct competitive coordination context information based on structural data from the low-convergence stage. :
[0124]
[0125] For the first The number of competing coordinating atoms in a multi-coordination system sample is used to distinguish the complexity of the competitive environment under different coordination number conditions such as monocoordination, dicoordination, and tricoordination.
[0126] For the first Information on competing coordination bonds in a multi-coordination system is used to characterize the overall spatial proximity of competing coordination bonds.
[0127]
[0128] For the first The first group of multi-coordination system samples The bond length of the competitive coordination bond between the competing coordinating atoms and the metal center. To calculate the average, To calculate the standard deviation;
[0129] For the first The distance information between the target coordinating atom and the competing coordinating atom in a multi-coordination system sample is used to characterize the spatial repulsion or proximity relationship between the target coordinating atom and the competing coordinating atom.
[0130]
[0131] For the first The first group of multi-coordination system samples The distance between the competing coordinating atom and the target coordinating atom;
[0132] For the first The angle information between the target coordination bond and the competing coordination bond in the multi-coordination system samples is used to reflect the angular distribution characteristics of the competing coordination bonds around the metal center;
[0133]
[0134] For the first The first group of multi-coordination system samples The angle formed between the competing coordinate bond and the target coordinate bond at the metal center;
[0135] For the first The coordination environment asymmetry parameter of a group of multi-coordination system samples is used to characterize whether the competing coordination bonds are uniformly distributed in space. If the competing bonds are uniformly distributed in direction, the vector sum is close to 0. If the competing bonds are concentrated on one side, the vector sum becomes larger.
[0136]
[0137] For the first In the multi-coordination system samples, from the metal center to the first Vectors of competing coordinating atoms;
[0138] For the first Spatial occlusion parameters of multi-coordination system samples are used to characterize the degree of spatial shielding of the target coordinating atom by the competing atom;
[0139]
[0140] For the first The first group of multi-coordination system samples van der Waals radii of competing coordinating atoms;
[0141] Step 3: Use machine learning to predict the bond length correction of the target coordination bond during the evolution from a low-convergence approximate configuration to a high-convergence stable configuration;
[0142] Construct a training set, where each group of samples in the training set is... ;
[0143] A prediction model is constructed to realize a deviation compensation prediction model for the migration mapping from low convergence stage structure to high convergence stage structure, and the target coordination bond length is predicted based on the model.
[0144] Training with a training set enables the prediction model to utilize competitive coordination context information from the input low-convergence stage structural data. Output the bond length error of the target coordination bond between the high-convergence stage and the low-convergence stage. ;
[0145] The prediction model uses the structural quality transfer deviation function:
[0146]
[0147] in, For local interference terms, This is a global statistical item. This refers to three-dimensional environmental statistics. For constant terms;
[0148]
[0149]
[0150]
[0151] in, and These are the weighting coefficients for the local interference term; These are the weighting coefficients for the global statistical items; and These are the weighting coefficients for the three-dimensional environmental statistics items;
[0152] In one embodiment of the present invention, the aforementioned weight coefficients and constant terms can be solved by machine learning methods such as least squares or regression with regularization terms.
[0153] Step 4: Obtain the target uranyl ion multi-coordinate system to be predicted, acquire structural data during the low convergence phase, select one coordinate bond as the target coordinate bond, and determine the bond length and competing coordination context information of the target coordinate bond; input the competing coordination context information into the trained prediction model to obtain the bond length error of the target coordinate bond, and take the sum of the bond length of the target coordinate bond and the bond length error as the bond length prediction result of the target coordinate bond; sequentially select other coordinate bonds as target coordinate bonds, and repeat the above process until the bond length prediction results of all coordinate bonds are obtained.
[0154] The above description is merely a preferred embodiment of the present invention and is not intended to limit the invention. Various modifications and variations can be made to the present invention by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.
Claims
1. A method for predicting the coordination bond length of uranyl ions based on automatically generated datasets, characterized in that: A sample of ligand molecules of uranyl ions was obtained. Functional groups with potential coordination ability in the ligand molecules of each sample were identified and screened. The types of atoms that can act as coordinating atoms in each functional group and their spatial position information were determined. With uranium atom as the metal center, a multi-coordination system of uranyl ions that satisfies the distance constraint between non-bonded atoms and the angle constraint between adjacent coordinating atoms was constructed, and a sample set of multi-coordination system of uranyl ions was obtained. For each group of uranyl ion multi-coordination system samples, structural data of the low convergence stage and the high convergence stage are obtained. One coordinating atom is selected as the target coordinating atom, and the remaining coordinating atoms are selected as competing coordinating atoms. Competitive coordination context information is constructed based on the structural data of the low convergence stage. The bond length of the target coordination bond is calculated based on the structural data of the low convergence stage and the high convergence stage, respectively, and the bond length error of the target coordination bond is determined. Construct and train a prediction model that can output the bond length error of the target coordination bond based on the input competitive coordination context information; To obtain the target uranyl ion multi-coordinate system to be predicted, obtain the structural data in the low convergence stage, select one coordinate bond as the target coordinate bond, and determine the bond length and competing coordination context information of the target coordinate bond; input the competing coordination context information into the trained prediction model to obtain the bond length error of the target coordinate bond, and take the bond length of the target coordinate bond and the sum of the bond length error as the bond length prediction result of the target coordinate bond; Select other coordinate bonds in turn as target coordinate bonds and repeat the above process until the bond length prediction results of all coordinate bonds are obtained.
2. The method for predicting the coordination bond length of uranyl ions based on automatically generated datasets according to claim 1, characterized in that: The construction of a uranyl ion multi-coordination system that satisfies the distance constraints between non-bonded atoms and the angle constraints between adjacent coordinating atoms is specifically as follows: For the ligand molecule sample, an initial coordination structure is generated between the uranyl ion center and the ligand molecule; The axial uranium-oxygen bond length of the uranyl ion in the initial coordination structure It is 1.7~1.9 For the initial coordination distance between the coordinating atom and the uranium atom at the equatorial plane It ranges from 2.3 to 2.
7. ; Perform geometric adjustments on the initial coordination structure to ensure that the adjusted coordination structure satisfies the distance constraints between non-bonded atoms and the angle constraints between adjacent coordinating atoms.
3. The method for predicting the coordination bond length of uranyl ions based on automatically generated datasets according to claim 2, characterized in that: The distance constraint between non-bonded atoms is: the distance between any two non-bonded coordinating atoms is not less than a set threshold. , 1.2~2 ; The constraint of the included angle between adjacent coordinating atoms is: adjacent coordinating atoms and The angle formed with the center of the metal Not less than the set threshold , , for .
4. The method for predicting the coordination bond length of uranyl ions based on automatically generated datasets according to claim 2, characterized in that: The axial uranium-oxygen bond length of the uranyl ion in the initial coordination structure The calculation method is as follows: in, The axial uranium-oxygen bond length under ligand-free or weakly ligand conditions; The modulation coefficient; Functional group coordination capacity factor; The initial coordination distance between the coordinating atoms and uranium atoms in the equatorial plane The calculation method is as follows: in, The equatorial coordination distance under conditions of no ligand or weak ligand; The coordination shrinkage coefficient; , For the first Coordination ability factor of functional groups of ligands.
5. The method for predicting the coordination bond length of uranyl ions based on automatically generated datasets according to claim 1, characterized in that: The competitive coordination context information for: The competing coordinate key information for: in, For the first The first sample of the uranyl ion multicoordination system The bond length of the competitive coordination bond between the competing coordinating atoms and the metal center. To calculate the average, To calculate the standard deviation; , For the first The number of competing coordinating atoms in a group of uranyl ion multicoordination systems; The distance information between the target coordinating atom and the competing coordinating atom for: in, For the first The first sample of the uranyl ion multicoordination system The distance between the competing coordinating atom and the target coordinating atom; The angle information between the target coordinate bond and the competing coordinate bond for: in, For the first The first sample of the uranyl ion multicoordination system The angle formed between the competing coordinate bond and the target coordinate bond at the metal center; The coordination environment asymmetric parameters for: in, For the first In the group of uranyl ion multicoordination system samples, from the metal center to the first Vectors of competing coordinating atoms; The spatial occlusion parameters for: in, For the first The first sample of the uranyl ion multicoordination system The van der Waals radius of competing coordinating atoms.
6. The method for predicting the coordination bond length of uranyl ions based on automatically generated datasets according to claim 5, characterized in that: The bond length of the target coordination bond is calculated based on the structural data during the low-convergence phase. The bond lengths of the target coordination bonds are calculated based on the structural data from the high-convergence phase. Determine the bond length error of the target coordinate bond. ; Construct a training set, where each group of training samples is... ; The prediction model is trained using a training set, enabling it to predict based on the input competitive coordination context information. Output the bond length error of the target coordinate bond .
7. The method for predicting the coordination bond length of uranyl ions based on automatically generated datasets according to claim 5, characterized in that: The prediction model is specifically as follows: in, For local interference terms, This is a global statistical item. This refers to three-dimensional environmental statistics. For constant terms; in, , , , and These are the weight coefficients to be trained.
8. A computer 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 7.
9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When executed by a processor, the computer program implements the steps of the method according to any one of claims 1 to 7.
10. A computer program product comprising computer instructions, characterized in that: When executed by a processor, the computer instructions implement the steps of the method according to any one of claims 1 to 7.