Second Near-Infrared Region Fluorescent Molecule Screening Method, Device, Equipment and Storage Medium

Abstract

The present application discloses a method, device, equipment and storage medium for screening second near-infrared region fluorescent molecules, which relates to the technical field of quantum chemistry. In the case of known molecular structures, this method optimizes and adjusts the most suitable long-range correction parameter ω of the molecule through the relatively fast LC-DFTB method, and then calculates the corresponding emission peak positions of organic fluorescent molecules efficiently and accurately through the LC-TD-DFTB method. It can be seen that by pre-optimizing the target long-range correction parameter of the target chemical molecule, the emission peak position of the target chemical molecule can be accurately determined, improving the accuracy of screening NIR-II region fluorescent molecules. In addition, when finding the optimal long-range correction parameter, this method uses a relatively fast long-range correction density functional theory model, greatly improving the calculation speed and enhancing the screening efficiency of screening NIR-II region fluorescent molecules.

Description

Technical Field

[0001] The present application relates to the technical field of quantum chemistry, and provides a method, a device, equipment and a storage medium for screening fluorescent molecules in the second near-infrared region. Background Technique

[0002] Due to the advantages of fast reaction, multi-signal capture, high sensitivity and no ionizing radiation of fluorescent probes, imaging technologies based on fluorescent probes have been widely used in medical diagnosis and treatment. Compared with visible light, near-infrared light (NIR) has stronger tissue penetration, which is more conducive to observing deeper organs and tissues. Initial studies found that although the light in the first near-infrared (NIR-I) region (wavelength 780-900 nm) has improved penetration, it cannot meet the penetration requirement of reaching the millimeter level. However, with the discovery of fluorophores in the second near-infrared (NIR-II) region (wavelength 1000-1700 nm), the penetration of fluorescence imaging has been further enhanced. Moreover, since NIR-II fluorophores can provide better resolution and higher signal-to-noise ratio, such fluorophores have become the focus of attention and research.

[0003] At present, NIR-II fluorophores can be divided into organic NIR-II fluorophores and inorganic NIR-II fluorophores. Although many inorganic NIR-II fluorophores have been widely used, such as single-walled carbon nanotubes, quantum dots and rare-earth element-doped nanoparticles, due to their biocompatibility, especially fluorophores containing heavy metals, their long-term unknown toxicity in the body is inevitably worrying. Organic NIR-II fluorophores have better biocompatibility and can be degraded in the body. Therefore, there is an urgent need to develop more organic NIR-II fluorophores. For a newly designed or existing organic molecule in the database with unknown properties, the entity and various spectra of the molecule can be obtained through experimental preparation methods and spectroscopic equipment, so as to know whether the organic molecule has the property of emitting fluorescence in the NIR-II region, and then be applied to practices such as biological imaging. More ideally, before synthesizing this molecule at the cost of a large amount of manpower and material resources, its properties can be predicted by some low-loss means, so as to reduce the R & D cost.

[0004] However, currently, for the screening of NIR-II fluorescent organic molecules, an experimental experience-guided approach can be adopted, that is, small modifications are made to organic molecules known to have fluorescence emission properties in the NIR-II region, such as increasing the length of the conjugated chain or replacing certain atoms within the main functional groups, etc., to discover new molecules. However, the number of molecules that can be generated by this method is limited, and it is rarely possible to develop new types. It relies more on experience and luck, is time-consuming and laborious, and the results have a high degree of uncertainty. Additionally, quantum chemical calculation methods such as DFT and TD-DFT can be used. They can calculate the corresponding molecular energy from the molecular structure and the positions of each atom, and thus calculate the photophysical properties of the molecule.

[0005] However, since NIR-II organic fluorescent molecules usually have large delocalized chemical bonds, the traditional DFT and TD-DFT methods are not highly accurate for NIR-II organic fluorescent molecules, and often consume a large amount of computing resources due to the excessive number of atoms in the molecule, which is not conducive to the large-scale screening of NIR-II organic fluorescent molecules.

[0006] Therefore, there is an urgent need for a more efficient method for screening NIR-II organic fluorescent molecules currently. Summary of the Invention

[0007] Embodiments of the present application provide a method, device, equipment, and storage medium for screening fluorescent molecules in the second near-infrared region, which are used to improve the accuracy and efficiency of screening NIR-II organic fluorescent molecules.

[0008] On the one hand, a method for screening fluorescent molecules in the NIR-II region is provided. The method includes:

[0009] Determine the position information of each atom in the target chemical molecule to be analyzed;

[0010] Using a first model, based on the position information of each atom, determine the target long-range correction parameter when the loss value of the target chemical molecule is minimized, and obtain the target ground state energy corresponding to the target long-range correction parameter; wherein, the first model is a density functional theory model based on long-range correction, and the loss value represents the difference degree between the molecular orbital energy and the ionization energy and electron affinity;

[0011] Input the position information of each atom into a second model using the target long-range correction parameter to obtain the excited state energy set of the target chemical molecule; wherein, the second model is a time-dependent density functional theory model based on long-range correction;

[0012] Based on the target ground state energy and the excited state energy set, when it is determined that the emission peak position of the target chemical molecule is in the NIR-II region, determine that the target chemical molecule belongs to the NIR-II region fluorescent molecule.

[0013] On the one hand, a screening device for NIR-II region fluorescent molecules is provided, and the device includes:

[0014] A molecular information acquisition unit for determining the position information of each atom in a target chemical molecule to be analyzed;

[0015] A parameter optimization unit for determining a target long-distance correction parameter that minimizes the loss value of the target chemical molecule and obtaining the target ground state energy corresponding to the target long-distance correction parameter based on the position information of each atom by using a first model; wherein, the first model is a density functional theory model based on long-distance correction, and the loss value represents the difference degree between the molecular orbital energy and the ionization energy and the electron affinity;

[0016] An excited state energy determination unit for inputting the position information of each atom into a second model using the target long-distance correction parameter to obtain an excited state energy set of the target chemical molecule; wherein, the second model is a time-dependent density functional theory model based on long-distance correction;

[0017] A molecular screening unit for determining that the target chemical molecule belongs to a NIR-II region fluorescent molecule when it is determined that the emission peak position of the target chemical molecule is in the NIR-II region based on the target ground state energy and the excited state energy set.

[0018] Optionally, the parameter optimization unit is specifically configured to:

[0019] Construct atomic orbitals of each atom based on the position information of each atom and a distance separation threshold, and perform a linear combination on the obtained multiple atomic orbitals to obtain multiple molecular orbitals;

[0020] Taking the condition that the multiple molecular orbitals are mutually orthogonal as a constraint, determine a set of molecular orbital coefficients corresponding to each molecular orbital when the total energy of the system of the target chemical molecule is minimized, where each molecular orbital coefficient represents the proportion of the corresponding atomic orbital in the corresponding molecular orbital;

[0021] Obtain a reduced density matrix between two atomic orbitals based on the obtained sets of molecular orbital coefficients;

[0022] Obtain the molecular orbital energies of the multiple molecular orbitals respectively based on the obtained multiple reduced density matrices.

[0023] Optionally, the parameter optimization unit is specifically configured to:

[0024] Determine the short-range Coulomb interaction energy of the target chemical molecule based on the obtained reduced density matrix and the zero-order density matrix;

[0025] Determine the long-range exchange interaction energy of the target chemical molecule based on the obtained reduced density matrix, zero-order density matrix, and the target long-range correction parameter;

[0026] Based on the density functional theory method, obtain the Hamiltonian matrix between pairwise atomic orbitals;

[0027] Based on the obtained reduced density matrix, Hamiltonian matrix, the short-range Coulomb interaction energy, long-range exchange interaction energy, and the repulsive potential energy between pairwise atoms, respectively obtain the molecular orbital energies of the multiple molecular orbitals.

[0028] Optionally, the parameter optimization unit is specifically configured to:

[0029] Determine the total energy of the system of the target chemical molecule based on the obtained multiple molecular orbital energies;

[0030] Then obtaining the target ground state energy corresponding to the target long-range correction parameter includes:

[0031] From the obtained multiple total energies of the system, take the total energy of the system corresponding to the target long-range correction parameter as the target ground state energy.

[0032] Optionally, the parameter optimization unit is specifically configured to:

[0033] Determine the ionization energy based on the difference between the total energy of the system and the total energy of the system of the monovalent positive ion corresponding to the target chemical molecule;

[0034] Obtain the electron affinity based on the difference between the total energy of the system and the total energy of the system of the monovalent negative ion corresponding to the target chemical molecule.

[0035] Optionally, the molecular screening unit is specifically configured to:

[0036] Obtain the target excited state energy corresponding to the first excited state from the set of excited state energies;

[0037] Determine the emission peak position of the target chemical molecule based on the difference between the target excited state energy and the target ground state energy.

[0038] Optionally, the molecular information acquisition unit is specifically configured to:

[0039] Determine the position information of each atom in the target chemical molecule based on the input molecular structure formula of the target chemical molecule; or,

[0040] Convert the Simplified Molecular Input Line Entry Specification (SMILES) string of the input target chemical molecule into a molecular structural formula, and based on the converted molecular structural formula, determine the position information of each atom in the target chemical molecule.

[0041] On the one hand, a computer device is provided, including a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the computer program, the steps of any of the above methods are implemented.

[0042] On the one hand, a computer storage medium is provided, on which computer program instructions are stored. When the computer program instructions are executed by a processor, the steps of any of the above methods are implemented.

[0043] On the one hand, a computer program product or a computer program is provided. The computer program product or the computer program includes computer instructions, and the computer instructions are stored in a computer-readable storage medium. The processor of the computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device executes the steps of any of the above methods.

[0044] In the embodiments of the present application, by determining the position information of each atom in the target chemical molecule to be analyzed, a first model based on the long-range corrected density functional theory model is adopted. According to the position information of each atom, the target long-range correction parameter when the loss value of the target chemical molecule is minimized is determined. Then, the position information of each atom is input into a second model using the target long-range correction parameter. The second model is a time-dependent density functional theory model based on long-range correction to obtain the excited state energy set of the target chemical molecule, so as to determine whether the emission peak position of the target chemical molecule is in the NIR-II region based on the target ground state energy and the excited state energy set, and determine whether the target chemical molecule belongs to a NIR-II region fluorescent molecule. It can be seen that the method provided by the embodiments of the present application accurately determines the excited state energy set of the target chemical molecule by pre-determining the target long-range correction parameter most suitable for the target chemical molecule and combining the target long-range correction parameter, so as to accurately determine the emission peak position of the target chemical molecule and determine whether the chemical molecule belongs to a NIR-II region fluorescent molecule. In addition, when searching for the optimal long-range correction parameter, the method adopts a relatively fast long-range corrected density functional theory model, greatly improving the calculation speed and the screening efficiency of chemical molecules. Description of the Drawings

[0045] To more clearly illustrate the technical solutions in the embodiments of the present application or the related art, the following will briefly introduce the drawings required for use in the description of the embodiments or the related art. Obviously, the drawings described below are only the embodiments of the present application. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on the provided drawings.

[0046] Figure 1 Schematic diagram of the application scenario provided by the embodiment of the present application;

[0047] Figure 2 Schematic flowchart of the method for screening second near-infrared region fluorescent molecules provided by the embodiment of the present application;

[0048] Figure 3 Schematic flowchart of optimizing the ω value provided by the embodiment of the present application;

[0049] Figure 4 Schematic flowchart of the processing flow of the first model provided by the embodiment of the present application;

[0050] Figure 5 Schematic flowchart of the processing flow of the second model provided by the embodiment of the present application;

[0051] Figure 6 Schematic flowchart of the screening process of NIR-II region fluorescent molecules provided by the embodiment of the present application;

[0052] Figure 7 Schematic structural diagram of a device for screening NIR-II region fluorescent molecules provided by the embodiment of the present application;

[0053] Figure 8 Schematic structural diagram of a computer device provided by the embodiment of the present application;

[0054] Figure 9 Another schematic structural diagram of a computer device provided by the embodiment of the present application. Detailed implementation manners

[0055] To make the objectives, technical solutions, and advantages of the present application clearer and more understandable, the following will clearly and completely describe the technical solutions in the embodiments of the present application in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments of the present application, all other embodiments obtained by those of ordinary skill in the art without creative efforts belong to the scope of protection of the present application. Without conflict, the embodiments in the present application and the features in the embodiments can be arbitrarily combined with each other. And although the logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in a different order than here.

[0056] To facilitate the understanding of the technical solutions provided by the embodiments of the present application, some key terms used in the embodiments of the present application are explained here first:

[0057] NIR-II region fluorescent molecule: It refers to a chemical molecule whose emission peak position is in the NIR-II region (i.e., 1000 - 1700 nm), which can be an inorganic chemical molecule or an organic chemical molecule. Since in actual clinical use, the harmfulness of organic chemical molecules is relatively small and the applicability is wider, usually the organic chemical molecules with NIR-II region fluorescence characteristics need to be screened.

[0058] First model: The first model is a density functional theory (DFT) model based on long-range corrected (LC). In traditional DFT, the exchange-correlation functional is used. However, the self-interaction error of the exchange-correlation functional will sometimes make the results of DFT unreliable. One solution is to use the local exchange-correlation functional at short distances and the Hartree-Fock exchange functional at long distances. The formula is as follows:

[0059]

[0060] Among them, r is the distance between electrons, ω is the long-range correction parameter, and erf represents the error function. The functional using this improved method is called the long-range corrected or range-separated functional. Such functionals can effectively solve the self-interaction error in traditional functionals, and the long-range correction parameter can be used to assist in judging the boundary threshold between short distances and long distances. It should be noted that the first model can adopt the DFT model based on LC or the tight-binding density functional theory (DFTB) model based on LC. DFTB is a semi-empirical method of DFT.

[0061] Second Model: The second model is a time-dependent density functional theory (TD-DFT) model based on LC. TD-DFT is an extension of DFT. Although the computational complexity increases, the introduction of TD-DFT makes it possible to calculate the excited state energies and properties of the computational system. Therefore, the TD-DFT method can be used to calculate the positions of the emission and absorption peaks of organic molecules. Similarly, for the first model, either the LC-TD-DFT model or the LC-TD-DFTB model can be adopted. TD-DFTB is a semi-empirical method of TD-DFT.

[0062] Density functional theory and tight-binding density functional methods reveal the mechanism of atomic interaction based on the energy beam method by describing atomic structures, interaction energies, minimum energy paths, and the probability of atomic transfer; the time-dependent density functional theory method reveals the interaction mechanism between light and matter and between particle beams and matter and its dependence on time by describing light absorption, photoreaction, photoexcitation, and electron stopping and excitation processes. DFTB and TD-DFTB are both semi-empirical methods based on DFT and TD-DFT. Therefore, the former two inherit the advantages and disadvantages of the latter two. Thus, for traditional DFTB and TD-DFTB, the influence of self-interference errors also exists. Therefore, the introduction of LC-DFTB and LC-TD-DFTB can effectively eliminate self-interference errors.

[0063] Atomic orbital (AO): Also known as atomic orbital function, it describes the wave-like behavior of electrons in an atom using mathematical functions. This wave function can be used to calculate the probability of finding an electron in a specific space outside the atomic nucleus and indicate the possible positions of the electron in three-dimensional space. The meaning of "orbital" is the region where the probability of an electron appearing outside the atomic nucleus is relatively large under the definition of the wave function. Specifically, an atomic orbital is the possible quantum state of an individual electron among the many electrons (electron cloud) surrounding an atom and is described by an orbital wave function.

[0064] Molecular Orbital (MO): The electron energy levels in a molecule are called molecular orbitals, which are wave functions used to describe the motion of electrons in a molecule. It refers to the region where the probability of a certain electron with a specific energy appearing near the space of two or more bonded atomic nuclei is the greatest. Molecular orbitals are formed by the interaction of atomic orbitals that make up the molecule. Molecular orbitals can be formed by the linear combination of atomic orbitals (Linear Combination of Atomic Orbital, LCAO), which is also a commonly used method for constructing molecular orbitals. The number of molecular orbitals formed is equal to the number of atomic orbitals combined, and the linear combination coefficients can be determined by the variational method or other methods. For two atomic orbitals to effectively combine into a molecular orbital, three conditions must be met: symmetry matching, similar energy levels, and maximum orbital overlap. Among them, symmetry matching is the prerequisite, and the other conditions affect the bonding efficiency.

[0065] Highest Occupied Molecular Orbital (HOMO): It refers to the orbital with the highest energy level that has occupied electrons during a chemical reaction.

[0066] Lowest Unoccupied Molecular Orbital (LUMO): It refers to the orbital with the lowest energy level that has not occupied electrons during a chemical reaction. HOMO and LUMO are collectively called frontier orbitals, and the electrons in the frontier orbitals are called frontier electrons. The frontier orbital theory holds that there are electrons in a molecule similar to the "valence electrons" of a single atom, and the valence electrons of a molecule are the frontier electrons. Therefore, during the chemical reaction between molecules, the first molecular orbitals to act are the frontier orbitals, and the key electrons are the frontier electrons. This is because the HOMO of a molecule has a relatively loose binding to its electrons and has the property of an electron donor, while the LUMO has a stronger affinity for electrons and has the property of an electron acceptor. These two orbitals are most likely to interact with each other and play an extremely important role during a chemical reaction.

[0067] Ground state energy and excited state energy: Electrons can only move in specific, discrete orbits. Electrons in each orbit have discrete energies, and these energy values are the energy levels. The energy level with the lowest energy is called the ground state, and other energy levels are called excited states. The ground state refers to the state where, under normal conditions, an atom is in the lowest energy level, and at this time, the electrons move in the orbit closest to the nucleus. The ground state energy is the total energy of the system in this state. The excited state refers to the state where an atom or molecule absorbs a certain amount of energy and the electrons are excited to a higher energy level but not yet ionized. Electrons can make transitions between different orbits. Electrons can absorb energy and transition from a lower energy level to a higher energy level or from a higher energy level to a lower energy level, thereby emitting photons. The excited state energy is the total energy of the system in this state.

[0068] Ionization energy: Also known as ionization potential, ionization energy is the energy required for a gaseous atom in the ground state to lose an electron and become a gaseous cation, which must overcome the attraction of the nuclear charge for the electron. For a multi-electron atom, the energy required for a gaseous atom in the ground state to form a gaseous monovalent cation is called the first ionization energy.

[0069] Electron affinity: Also known as electron affinity potential, it is the energy characterizing the affinity between electrons. Electron affinity is the energy released when a gaseous atom in the ground state gains an electron and becomes a gaseous anion. The energy released when a ground state gaseous atom of an element gains an electron to form a -1 valence gaseous anion is called the first electron affinity of the element.

[0070] This application relates to the screening of organic fluorescent molecules using artificial intelligence methods. Artificial Intelligence (AI) is the theory, method, technology, and application system that uses a digital computer or a machine controlled by a digital computer to simulate, extend, and expand human intelligence, perceive the environment, acquire knowledge, and use knowledge to obtain the best results. In other words, artificial intelligence is a comprehensive technology in computer science. It attempts to understand the essence of intelligence and produce a new intelligent machine that can react in a way similar to human intelligence. Artificial intelligence also studies the design principles and implementation methods of various intelligent machines to enable the machine to have the functions of perception, reasoning, and decision-making.

[0071] Artificial intelligence technology is an interdisciplinary subject with a wide range of fields, including both hardware-level technologies and software-level technologies. The basic technologies of artificial intelligence generally include technologies such as sensors, dedicated artificial intelligence chips, cloud computing, distributed storage, big data processing technology, operation / interaction systems, and mechatronics. The software technologies of artificial intelligence mainly include several major directions such as computer vision technology, speech processing technology, natural language processing technology, and machine learning / deep learning.

[0072] Next, a brief introduction to the design concept of the embodiments of the present application will be given:

[0073] Currently, for the exploration and screening of NIR-II region fluorescent organic molecules, there are mainly the following methods:

[0074] (1) The first method is to completely use experimental experience as guidance to make small modifications to known organic molecules with NIR-II region fluorescence characteristics, such as increasing the length of the conjugated chain and replacing certain atoms within the main functional groups to discover new molecules. Although this method can discover some new molecules, the quantity is limited, and it is rarely possible to develop new types. It depends more on experience and luck. Most importantly, it is time-consuming and laborious, and the result has a great degree of uncertainty.

[0075] (2) The second method is to use quantum chemical calculation methods such as DFT and TD-DFT. However, since NIR-II organic fluorescent molecules usually have large delocalized chemical bonds, the accuracy of traditional DFT and TD-DFT methods for NIR-II organic fluorescent molecules is not high, and they often consume a large amount of computing resources due to the excessive number of atoms in the molecules, which is not conducive to the large-scale screening of NIR-II organic fluorescent molecules.

[0076] (3) The third method is to use machine learning methods to predict the fluorescence emission peak positions of organic molecules, that is, to predict the photophysical properties of organic molecules through a machine learning model trained based on a large number of experimental data points. The prediction results are closer to the experimental values. However, due to the limited number of sample data of NIR-II organic fluorescent molecules, the difficulty of training the model is increased, which limits the accuracy and applicability of the model.

[0077] Based on this, the embodiments of the present application provide a method for screening NIR-II region fluorescent molecules. In this method, by determining the position information of each atom in the target chemical molecule to be analyzed, a first model based on the long-range corrected density functional theory model is adopted. According to the position information of each atom, the target long-range correction parameter when the loss value of the target chemical molecule is minimized is determined. Then, the position information of each atom is input into a second model using the target long-range correction parameter. The second model is a time-dependent density functional theory model based on long-range correction to obtain the excited state energy set of the target chemical molecule, so as to determine whether the emission peak position of the target chemical molecule is in the NIR-II region and determine whether the target chemical molecule belongs to the NIR-II region fluorescent molecule. It can be seen that the method provided by the embodiments of the present application accurately determines the excited state energy set of the target chemical molecule by pre-determining the target long-range correction parameter most suitable for the target chemical molecule and combining the target long-range correction parameter, so as to accurately determine the emission peak position of the target chemical molecule and determine whether the chemical molecule belongs to the NIR-II region fluorescent molecule. In addition, when finding the optimal long-range correction parameter, this method adopts a faster long-range corrected density functional theory model, greatly improving the calculation speed and the screening efficiency of chemical molecules.

[0078] The following briefly introduces some application scenarios applicable to the technical solutions of the embodiments of the present application. It should be noted that the following introduced application scenarios are only used to illustrate the embodiments of the present application rather than to limit them. In the specific implementation process, the technical solutions provided by the embodiments of the present application can be flexibly applied according to actual needs.

[0079] The solution provided by the embodiments of the present application can be applied to the scenario of determining the emission peak position of most chemical molecules, especially applicable to the scenario of screening NIR-II region fluorescent molecules. As Figure 1 shown, it is a schematic diagram of an application scenario provided by the embodiments of the present application. In this scenario, it may include a terminal device 101 and a server 102.

[0080] The terminal device 101 can be, for example, a mobile phone, a tablet computer (PAD), a laptop computer, a desktop computer, a smart TV, a smart vehicle-mounted device, and a smart wearable device, etc. The terminal device 101 can be installed with a target application for inputting information of chemical molecules and displaying the characteristic recognition results of chemical molecules. The application involved in the embodiments of the present application can be a software client, or a web page, a mini-program, etc. The server 102 is a background server corresponding to the software, web page, mini-program, etc., and the specific type of the client is not limited. For example, it can be an independent physical server, or a server cluster or a distributed system composed of multiple physical servers, or a cloud server providing basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, i.e., Content Delivery Network (CDN), and big data and artificial intelligence platforms, but it is not limited thereto.

[0081] It should be noted that the method for screening the second near-infrared region fluorescent molecules in the embodiments of the present application can be executed alone by the terminal device 101 or the server 102, or jointly executed by the server 102 and the terminal device 101. For example, the server 102 determines the position information of each atom of the chemical molecule, and based on this, pre-determines the target long-distance correction parameter most suitable for the target chemical molecule, and combines the target long-distance correction parameter to accurately determine the excited state energy set of the target chemical molecule, so as to accurately determine the emission peak position of the target chemical molecule and determine whether the chemical molecule belongs to the NIR-II region fluorescent molecule. Or, the above steps are executed by the terminal device 101. Or, the terminal device 101 determines the position information of each atom based on the input information of the chemical molecule and transmits it to the server. The server 102 determines the target long-distance correction parameter most suitable for the target chemical molecule, and combines the target long-distance correction parameter to accurately determine the excited state energy set of the target chemical molecule, so as to accurately determine the emission peak position of the target chemical molecule, determine whether the chemical molecule belongs to the NIR-II region fluorescent molecule, and feedback it to the terminal device 101 to present the corresponding result interface. The present application does not make specific limitations here, and the following mainly takes the server 102 as an example for illustration.

[0082] Taking the execution of the above steps by server 102 as an example, server 102 may include one or more processors 1021, a memory 1022, an I / O interface 1023 for interacting with the terminal, etc. Among them, program instructions for the NIR-II region fluorescent molecule screening method provided by the embodiments of the present application may also be stored in the memory 1022 of the server 102. When these program instructions are executed by the processor 1021, they can be used to implement the steps of the NIR-II region fluorescent molecule screening method provided by the embodiments of the present application to realize the NIR-II region fluorescent molecule screening process.

[0083] In the embodiments of the present application, the terminal device 101 and the server 102 may be directly or indirectly communicatively connected through one or more networks 103. The network 103 may be a wired network or a wireless network. For example, the wireless network may be a mobile cellular network or a Wireless-Fidelity (WIFI) network. Of course, it may also be other possible networks, and the embodiments of the present invention do not limit this.

[0084] It should be noted that Figure 1 The above is only an example. In fact, the number of terminal devices and servers is not limited and is not specifically defined in the embodiments of the present application.

[0085] Next, in combination with the above-described application scenario, the NIR-II region fluorescent molecule screening method provided by the exemplary embodiments of the present application will be described with reference to the accompanying drawings. It should be noted that the above application scenario is only shown for the convenience of understanding the spirit and principle of the present application, and the embodiments of the present application are not limited in this regard.

[0086] See Figure 2 As shown, it is a schematic flowchart of the NIR-II region fluorescent molecule screening method provided by the embodiments of the present application. Here, taking the server as the execution subject as an example, the specific implementation process of the method is as follows:

[0087] Step 201: Determine the position information of each atom in the target chemical molecule to be analyzed.

[0088] In the embodiments of the present application, considering that chemical molecules can be expressed in multiple ways, when determining the position information, it can be based on the expression method of the input target chemical molecule.

[0089] In a possible implementation manner, the target chemical molecule may be expressed by a molecular structural formula. For example, a structural formula drawing interface may be provided to the user, and the user can operate on this interface to draw the molecular structure of the target chemical molecule to be analyzed. Then, based on the molecular structural formula of the input target chemical molecule, the position information of each atom in the target chemical molecule to be analyzed can be determined.

[0090] In a possible implementation, a Simplified Molecular Input Line Entry System (SMILES) string can be used to represent the target chemical molecule. SMILES is a specification that clearly describes the molecular structure using ASCII (a computer encoding language) strings. For example, a text box editing interface for inputting SMILES strings can be provided to the user. The user can input the SMILES string of the target chemical molecule in the editing interface, and then by parsing the SMILES string, the molecular structural formula of the target chemical molecule can be obtained. Furthermore, based on the obtained molecular structural formula of the target chemical molecule, the position information of each atom in the target chemical molecule to be analyzed can be determined.

[0091] In the embodiments of the present application, for the input target chemical molecule, a conversion tool can be called to obtain the position information of each atom. For example, tools such as RDKit can be used. Of course, other possible tools can also be used, and the embodiments of the present application do not limit this.

[0092] Among them, the position information may refer to the coordinate information of each atom included in the chemical molecule in a specified coordinate system.

[0093] Step 202: Use the first model to determine the target long-range correction parameter that minimizes the loss value of the target chemical molecule based on the position information of each atom, and obtain the target ground state energy corresponding to the target long-range correction parameter. The loss value represents the degree of difference between the molecular orbital energy and the ionization energy and electron affinity.

[0094] In the embodiments of the present application, considering that the long-range correction parameter ω is an adjustable empirical parameter and its value has a great influence on the calculation results. For most molecular systems, ω = 0.33 can improve the accuracy of the calculation results. However, for some relatively special systems, such as organic molecules in the NIR-II region with a large conjugated system, ω = 0.33 cannot obtain calculation results consistent with the experimental results, so the prediction of the fluorescence characteristics of this type is not accurate.

[0095] Considering that the role of ω is to divide the long distance and the short distance, that is, the distance separation threshold between the long distance and the short distance can be determined. Therefore, due to the different structural distributions of different molecules, the optimal value of ω should theoretically also be different. And through experiments, it is shown that in fact, the optimal value of ω is very sensitive to the structure and electron distribution of the molecule. Therefore, in order to improve the accuracy of the final prediction result, it is necessary to find the optimal value of ω suitable for the current target chemical molecule.

[0096] In a system, different electron arrangements correspond to different system energies. The electron arrangement that results in the lowest system energy represents the actual state, indicating that the corresponding ω is most suitable for the current chemical molecule at this time. According to Koopmans' theorem, that is, under the Hartree-Fock approximation of a closed shell, the first ionization energy of a system is equal to the negative value of its HOMO energy. Therefore, a loss function can be constructed based on the first ionization energy and HOMO energy.

[0097] In one possible implementation, the following loss function J 2 (ω) can be used:

[0098] J 2 (ω) = [ε HOMO (ω) + I(ω)] 2 + [ε LOMO (ω) + E A (ω)] 2

[0099] Where ε represents energy, ε HOMO (ω) and ε LOMO (ω) represent the energies of HOMO and LUMO at a specific ω respectively, I(ω) represents the ionization energy at a specific ω, and E A (ω) represents the electron affinity at a specific ω.

[0100] Based on the above loss function, it can be known that in actual situations, the sum between ε HOMO (ω) and I(ω) tends to zero, and the sum between ε LOMO (ω) and E A (ω) also tends to zero. Therefore, in the ideal case, J 2 (ω) should be zero. Excluding the existence of error factors, the optimal value of ω can be found by minimizing J 2 (ω) in the above equation.

[0101] In actual applications, a large number of different ω values can be used, and each term on the right side of the above equation can be calculated through the first model to obtain J 2 (ω), so as to determine the minimum J 2 (ω) from them, and then determine the optimal ω, which is the target long-distance correction parameter in the embodiments of this application.

[0102] Specifically, the first model is a density functional theory model based on long-range correction. Considering the large computational cost brought about by a large number of ω values, the first model can use a computational method with lower computational resource consumption and faster computational speed. For example, it can be a model using the LC-DFT method or a model using the LC-DFTB method. Taking LC-DFTB as an example, for the atomic and coordinate information of the target chemical molecule, a large number of relatively fast LC-DFTB calculations for different ω values can be performed on it, so that the corresponding ε HOMO (ω), I(ω), ε LOMO (ω) and E A (ω) can be obtained, so that the minimum value of J 2 (ω) can be found, thereby finding the optimal ω value for this target chemical molecule.

[0103] At the same time, in each calculation process, the total energy of the system corresponding to the target chemical molecule, that is, the ground state energy, can be calculated. Then, after selecting the optimal ω value, the ground state energy obtained during the calculation of the optimal ω value can be obtained as the basis for determining the emission peak subsequently.

[0104] In addition, considering that calculations can be performed on a given chemical molecule based on ω to obtain its different physical quantities, physical quantities with different meanings but the same value (or approximate value) can be found to verify whether ω is applicable to the current chemical molecule. Or, different computational methods can be used based on ω to calculate the same physical quantity to verify whether ω is applicable to the current chemical molecule.

[0105] Step 203: Input the position information of each atom into the second model using the target long-range correction parameter to obtain the excited state energy set of the target chemical molecule.

[0106] Based on the above process to obtain the optimal ω, the parameter ω in the second model can be set to the obtained optimal value, and then calculations can be performed based on the position information of each atom to obtain the excited state energy set of the target chemical molecule. The excited state energy set contains the excited state energies of the target chemical molecule corresponding to different energy levels.

[0107] Specifically, the second model is a time-dependent density functional theory model based on long-range correction. And in order to be able to calculate the excited state energy of the system, it is necessary to introduce the time-dependent density functional theory. Therefore, the second model can adopt a method that can correctly calculate the excited state energy. For example, it can be a model using the LC-TD-DFT method or a model using the LC-TD-DFTB method. Taking LC-TD-DFTB as an example, set the ω parameter of LC-TD-DFTB with the obtained ω value and input the atomic and coordinate information of the target chemical molecule to calculate the excited state energy set of the target chemical molecule.

[0108] Step 204: When it is determined that the emission peak position of the target chemical molecule is in the NIR-II region based on the target ground state energy and the set of excited state energies, it is determined that the target chemical molecule belongs to the NIR-II region fluorescent molecule.

[0109] When the electrons of the ground state or low-energy-level atoms absorb energy, the electrons will transition to a higher energy level and become excited state atoms. Through the above process, the total energy of the system corresponding to the target chemical molecule at different energy levels, that is, the excited state energy, can be obtained.

[0110] In an actual scenario, considering the possibility of practical applications, more attention is paid to the energy difference between the ground state and the first excited state (First Excited State), and the first excited state is the excited state with the lowest energy among the excited states. Furthermore, the target excited state energy corresponding to the first excited state can be obtained from the set of excited state energies, and then based on the difference between the target excited state energy and the target ground state energy, the emission peak position of the target chemical molecule can be determined. The emission peak position refers to the position of the wavelength of the fluorescence emitted by the target chemical molecule during the transition in the emission spectrum. Through the above energy difference, the wavelength of the emitted fluorescence can be converted, so as to determine the emission peak position. Furthermore, according to the relative position relationship between the emission peak position and the NIR-II region, it is judged whether the target chemical molecule belongs to the NIR-II region fluorescent molecule. When the emission peak position is in the NIR-II region, the target chemical molecule belongs to the NIR-II region fluorescent molecule. On the contrary, when the emission peak position is not in the NIR-II region, the target chemical molecule does not belong to the NIR-II region fluorescent molecule.

[0111] Similarly, based on the energy obtained above, the absorption peak position of the target chemical molecule in the absorption spectrum can also be determined for the requirements of the actual scenario.

[0112] In the embodiment of the present application, the process of step 202 can be implemented by using the method flow as Figure 3 shown, Figure 3 which is a schematic flow chart for optimizing the ω value provided by the embodiment of the present application.

[0113] In the embodiment of the present application, for multiple given candidate long-distance correction parameters ω, a first model can be used to calculate the corresponding loss values J 2 (ω) respectively, and the candidate long-distance correction parameter corresponding to the minimum loss value J 2 (ω) is determined as the target long-distance correction parameter for calculating the set of excited state energies by the second model. Since the calculation process of each candidate long-distance correction parameter ω is similar, here mainly an example of the calculation of one ω is introduced.

[0114] Step 2021: Determine the corresponding distance separation threshold based on the candidate long-distance correction parameter ω.

[0115] In the embodiments of the present application, the long-distance correction parameter mainly helps to divide long distances and short distances, and different functionals are used for short distances and long distances respectively.

[0116] In a possible implementation manner, the long-distance correction parameter ω can be a proportional value, and multiplying it by a distance base number can obtain the corresponding distance separation threshold. Among them, the distance base number can be a certain distance in the molecule or a preset fixed distance value.

[0117] Step 2022: Based on the position information of each atom and the distance separation threshold, use the first model to determine the molecular orbital energies corresponding to multiple molecular orbitals of the target chemical molecule.

[0118] In the embodiments of the present application, the first model can adopt the LC-DFT method or the LC-DFTB method to calculate the energy values related to the target chemical molecule.

[0119] See Figure 4 As shown, it is a schematic diagram of the processing flow of the first model. Taking the LC-DFTB method as an example here, the following steps can be used to implement it:

[0120] Step 20221: Based on the position information of each atom and the distance separation threshold, construct the atomic orbitals of each atom, and perform a linear combination of the obtained multiple atomic orbitals to obtain multiple molecular orbitals.

[0121] In the embodiments of the present application, similar to other semi-empirical quantum chemistry methods, the interaction between atomic orbitals (denoted by μ, v) can be represented as a Hamiltonian matrix and its overlap matrix (S μv ). The matrix elements of these matrices depend on the structure of the molecule and can be obtained through DFT calculations.

[0122] First, the matrix elements of the atomic valence electron orbitals between a pair of atoms obtained by DFT calculations in different directions, such as the directions of ppπ, ssσ, ppσ, etc. bonds, are listed in a table according to different distances, and the slopes of the matrix elements in each direction can be obtained from this table through the Slater-Koster rules.

[0123] The molecular orbitals occupied by electrons (denoted by letters i, j) can be expressed as a linear combination of atomic orbitals:

[0124]

[0125] Among them, The wave function representing the molecular orbital i The wave function representing the atomic orbital μ, C μi is the molecular orbital coefficient of the atomic orbital μ with respect to the molecular orbital i. The molecular orbital coefficient can characterize the proportion of the corresponding atomic orbital in the corresponding molecular orbital and is the overlap integral of the molecular orbital i and the atomic orbital μ, which can be expressed as:

[0126]

[0127] The reduced density matrix can be expressed as:

[0128]

[0129] where P μv characterizes the reduced density matrix corresponding to the atomic orbitals μ and v, characterizes C μi 's conjugate complex number, and N elec represents the total number of electrons within the molecule. The reduced density matrix is an operator. Multiplying it by the wave functions of the corresponding two atomic orbitals and integrating can obtain the contribution of these two atomic orbitals to the atomic density of the molecular orbital.

[0130] In an actual scenario, the formation of chemical bonds between different atoms causes electrons to flow from atoms with low electronegativity to atoms with high electronegativity, resulting in charge redistribution and the formation of partial charges. Thus, the energy E of the entire system of the target chemical molecule LC-DFTB can be expressed as:

[0131]

[0132] where V repulsive represents the repulsive potential energy between atoms (denoted by A, B, etc.), which only depends on the distance R between the atoms AB , and V repulsive includes the interaction between the atomic nucleus and the nuclear electrons and can be expressed as:

[0133]

[0134] where characterizes the electrostatic repulsive force between atomic nuclei. According to Coulomb's law, it can be expressed as:

[0135]

[0136] where k is the electrostatic constant in Coulomb's law, and Z A and Z B represent the electric charges carried by atomic nuclei A and B, respectively.

[0137] In an actual scenario, strictly speaking, a new V is required after long-distance correction repulsive , but this change can be ignored in practical applications.

[0138] E Coulomb and For the electron-electron interaction, it can be divided into short-range Coulomb interaction E Coulomb and long-range exchange interaction which are respectively expressed as:

[0139]

[0140]

[0141] where μσ|λv represents the two-electron integral of the Coulomb force, and (μλ|σv) lr represents the two-electron integral of the long-range exchange interaction.

[0142] The Hamiltonian matrix of the zero order already includes the interactions of all electrons within a neutral atom, E Coulomb and are from the charge redistribution, which is expressed by the formula as the difference in the reduced density matrices Assuming the atom is isolated, since all atomic energy levels (n, l, m) in the reference system are occupied, the zero-order density matrix is diagonalized:

[0143]

[0144] where δ μv is the Kronecker delta function, that is, it is 1 when μ and v are the same (the same atomic orbital) and 0 when they are not equal, and the resulting matrix is diagonalized, A μ represents the atomic orbital μ of atom A.

[0145] According to the tight-binding approximation, the two-electron integral in the electron-electron interaction formula can be expressed as:

[0146]

[0147]

[0148] where 1 and 2 each represent a different electron. In the above electron interaction formula, φ μ (1) represents the wave function of atomic orbital μ at electron 1, and φ σ (2) represents the wave function of atomic orbital σ at electron 2, r 12represents the distance between electrons 1 and 2, d1 represents the integral over all possible coordinate positions of electron 1, and d2 represents the integral over all possible coordinate positions of electron 1.

[0149] The transition charge on atom A can be expressed as:

[0150]

[0151]

[0152] If the atomic orbital μ is centered at atom A, then δ(μ∈A) = 1, otherwise δ(μ∈A) = 0, γ AB and are respectively expressed as:

[0153]

[0154]

[0155] where

[0156]

[0157]

[0158] D AB represents the interaction between atoms A and B, σ A and σ B are the charge cloud widths of atoms A and B, U A is the Hubbard parameter, which depends on different atomic species.

[0159] Step 20222: With the constraint that multiple molecular orbitals are mutually orthogonal, determine the set of molecular orbital coefficients corresponding to each molecular orbital when the total energy of the system of the target chemical molecule is minimized.

[0160] In the embodiments of the present application, under the condition that all molecular orbitals are mutually orthogonal, the total energy E μi of the system is minimized with the molecular orbital coefficient C LC-DFTB as the variable, that is, the following equation is satisfied:

[0161]

[0162] This equation is solved in a self-consistent manner, so that a set of molecular orbital coefficients can be obtained. Each set of molecular orbital coefficients contains the molecular orbital coefficients of each atomic orbital relative to each molecular orbital.

[0163] Step 20223: Based on the obtained sets of molecular orbital coefficients, obtain the reduced density matrix between pairwise atomic orbitals.

[0164] After obtaining the coefficients of each molecular orbital, they can be substituted into the formula of the above reduced density matrix to calculate the corresponding reduced density matrix. For example, after obtaining C μi then it can be substituted into the above to obtain the reduced density matrix.

[0165] Step 20224: Based on the obtained multiple reduced density matrices, obtain the molecular orbital energies of multiple molecular orbitals respectively.

[0166] In the embodiments of the present application, based on the obtained reduced density matrix and the zero-order density matrix, determine the short-range Coulomb interaction energy E of the target chemical molecule Coulomb and, based on the obtained reduced density matrix, zero-order density matrix and the target long-range correction parameter, determine the long-range exchange interaction energy of the target chemical molecule And the Hamiltonian matrix between two atomic orbitals can be obtained by using the above DFT method to obtain the short-range Coulomb interaction energy E based on the obtained reduced density matrix and Hamiltonian matrix the long-range exchange interaction energy Coulomb and the repulsive potential energy V between two atoms respectively obtain the molecular orbital energies of multiple molecular orbitals. repulsive

[0167] Step 2023: Based on the difference degree between the molecular orbital energy of HOMO in multiple molecular orbitals and the ionization energy of the target chemical molecule, and the difference degree between the molecular orbital energy of LUMO and the electron affinity of the target chemical molecule, determine the corresponding loss value.

[0168] In the embodiments of the present application, the molecular orbital energy ε of HOMO HOMO and the molecular orbital energy ε of LUMO LOMO can be obtained by solving the energies of different molecular orbitals in the molecule through the above LC-DFTB method.

[0169] Thus, based on the obtained multiple molecular orbital energies, the total energy of the system of the target chemical molecule can be determined. The total energy of the system is the sum of all molecular orbital energies. For example, after obtaining the molecular orbital coefficients as above, the reduced density matrix can be obtained, and thus E Coulomb and Finally, the total energy E of the system can be obtained LC-DFTB .

[0170] Furthermore, substitute the parameter values required for calculating the loss value into the following formula to obtain J 2 (ω), and thus find the minimum J 2 (ω).

[0171] J 2 (ω) = [ε HOMO (ω) + I(ω)] 2 + [ε LOMO (ω) + E A (ω)] 2

[0172] Among them, I(ω) can be obtained by calculating the energy difference between the total energy of the target chemical molecule in the neutral state and the total energy of its corresponding monovalent (+1) positive ion, that is, the difference between the total system energy and the total system energy of the monovalent positive ion corresponding to the target chemical molecule; E A (ω) can be obtained by calculating the energy difference between the total energy of the target chemical molecule in the neutral state and the total energy of its corresponding -1 negative ion, that is, the difference between the total system energy and the total system energy of the monovalent negative ion corresponding to the target chemical molecule. It should be noted that the total system energy of the monovalent positive ion and the total system energy of the monovalent negative ion can also be obtained by using the above LC-DFTB method.

[0173] It should be noted that in each calculation process involving the long-range correction parameter ω, the corresponding total system energy can be calculated. Then, after selecting the optimal ω value, the total system energy corresponding to the target long-range correction parameter can be used as the target ground state energy of the target chemical molecule from the obtained multiple total system energies.

[0174] In the embodiments of the present application, considering that the positions of the emission peak and the absorption peak are obtained from the energy difference between the excited state and the ground state, TD-DFTB needs to be introduced to calculate the excited state energy.

[0175] In a possible implementation manner, the process of step 203 can be implemented by using the method flow as Figure 5 shown, Figure 5 which is a schematic diagram of the processing flow of the second model.

[0176] In the embodiments of the present application, the second model can use the LC-TD-DFT method or the LC-TD-DFTB method to calculate the excited state energy value related to the target chemical molecule. Here, taking the LC-TD-DFTB method as an example, it can be implemented by the following steps:

[0177] Step 2031: Based on the position information of each atom of the target chemical molecule, and the ground state energies of each molecular orbital and atomic orbital corresponding to the target long-range correction parameter, construct a non-Hermitian matrix diagonalization equation based on the excited state energy.

[0178] In linear response TD-DFT, the singlet excitation energy ε can be obtained from the non-Hermitian eigenvalue problem:

[0179]

[0180] Under the tight-binding theory assumption, the matrix elements in M (the first matrix) and N (the second matrix) are expressed as:

[0181] M iμ，jv = δ ij δ μv (∈ μ - ∈ i ) + 2(iμ|jv) - (ij|μv) lr

[0182] Ni μ，jv = 2(iμ|jv) - (iv|μj) lr

[0183] Where ∈ μ is the ground-state energy of atomic orbital μ, and ∈ i represents the ground-state energy of molecular orbital i, which can be obtained in the above LC-DFTB calculation process. Characterizes the density matrix after being perturbed (by an external electric field), that is, by artificially applying an external electric field, the density matrix will have a small change. When using the DFT method, the A and B matrices are very complex and the solution process is very slow. Therefore, in the embodiments of the present application, the A and B can be simplified through the tight-binding approximation to make it easier to obtain the overall eigenvalue. The eigenvalue ε of this formula is the energy of the excited state, and the vector is the coefficient of the atomic orbitals that make up this molecular orbital.

[0184] Step 2032: Based on the position information of each atom of the target chemical molecule, obtain the first matrix-vector product and the second matrix-vector product. The first matrix-vector product is the dot product of the sum of the first matrix and the second matrix and the target vector, and the second matrix-vector product is the dot product of the difference between the first matrix and the second matrix and the target vector. The first matrix and the second matrix are determined by the atomic energy orbitals and molecular orbitals corresponding to the target chemical molecule, and the target vector is a vector composed of the molecular orbital coefficients corresponding to the atomic orbitals of the unoccupied molecular orbitals.

[0185] The eigenvector and eigenvalue in this non-Hermitian eigenvalue problem can be obtained by using a Davidson-like iterative algorithm. Using this algorithm requires the first matrix-vector product and the second matrix-vector product values, (the target vector) is a vector composed of the linear combination coefficients of the atomic orbitals of the unoccupied molecular orbitals. Under the tight-binding theory assumption, the above two matrix-vector products can be expressed as:

[0186]

[0187] And

[0188]

[0189] Step 2033: Determine the eigenvalues of the non-Hermitian matrix diagonalization equation based on the first matrix-vector product and the second matrix-vector product, where the eigenvalues are the excited state energies of the target chemical molecule.

[0190] Through the above matrix-vector products, the eigenvalues and eigenvectors can be solved, thereby obtaining the energies of each excited state and its molecular orbitals. By comparing the energies of the excited state and the ground state, the positions of the absorption peak and emission peak of the organic molecule can be calculated.

[0191] In the embodiments of the present application, in the above solution process, a Davidson-like iterative algorithm is adopted to implement. Thus, for the above large matrix, it is not necessary to perform overall diagonalization, but to calculate the eigenvalues of interest, that is, the excited state energies such as the first excited state energy, the second excited state energy, etc., thereby saving computational cost.

[0192] In the embodiments of the present application, the LC-TD-DFTB method in the embodiments of the present application can also be replaced by other semi-empirical quantum chemistry methods, such as CNDO / 2, INDO, MOPAC or ZINDO, etc. The greatest advantage of such methods is that they occupy less computational resources while maintaining a certain degree of accuracy.

[0193] In the embodiments of the present application, the above screening process of the NIR-II fluorescent organic molecules can be integrated as a function and provided to the user. See Figure 6 As shown, the embodiments of the present application provide a possible schematic diagram of the screening process. As Figure 6 shown, a front-end user interface (UI) can be provided to the user, including but not limited to a client interface or a website UI interface. The UI can include a molecular structure drawing area and a text editing area. The molecular structure drawing area can be used to draw the molecular structure of the target chemical molecule to be analyzed, and the text editing area can be used to input the SMILES string of the target chemical molecule to be analyzed. After the input is completed, the molecular structure or the SMILES string can be transmitted to the server background. In this way, the server background can obtain the structural information of the target chemical molecule by converting the structural formula or the SMILES into a structural formula.

[0194] Furthermore, the server background can combine the structural information of the target chemical molecule and use the LC-DFTB method to find the optimal ω value of the molecule, so as to optimize the parameters of LC-TD-DFTB. Then, the LC-TD-DFTB method is used to combine the structural information of the target chemical molecule to calculate the emission peak position and absorption peak position of the organic molecule in the NIR-II region quickly, accurately and with only a small amount of computing resources, and determine whether the molecule belongs to the NIR-II region fluorescent molecule. For example, if the calculated emission peak position is 1300nm, which is within the NIR-II region, then the molecule belongs to the NIR-II region fluorescent molecule. The calculation results are returned to the front-end UI interface for display, and the front-end interface jumps to a new page to display the final calculation results. This method can help users quickly and accurately screen potential organic molecules with fluorescence properties in the NIR-II region for further experiments.

[0195] In summary, the embodiments of the present application can generate the atoms and their coordinate information of a molecule when the molecular structure formula or its SMILES string is known, and optimize and adjust the most suitable long-range correction parameter ω of the molecule through the relatively fast LC-DFTB method. Then, through the LC-TD-DFTB method, the emission peak position of the organic fluorescent molecule can be calculated efficiently and accurately. Among them, the LC-DFTB method is used to find the optimal ω value in the embodiments of the present application, which greatly reduces the search time. Moreover, compared with LC-TD-DFT, the calculation speed of LC-TD-DFTB is also greatly improved, and the calculation time is reduced from hundreds of CPU hours to the minute level. And this method does not rely very much on the size of the database like the machine learning method, so it is very suitable for the current situation where the number of known NIR-II organic fluorescent molecules is limited.

[0196] Please refer to Figure 7 , based on the same inventive concept, the embodiments of the present application also provide a screening device 70 for NIR-II region fluorescent molecules, and the device includes:

[0197] A molecular information acquisition unit 701, configured to determine the position information of each atom in the target chemical molecule to be analyzed;

[0198] A parameter optimization unit 702, configured to use a first model to determine the target long-range correction parameter when the loss value of the target chemical molecule is minimized based on the position information of each atom, and obtain the target ground state energy corresponding to the target long-range correction parameter; wherein, the first model is a density functional theory model based on long-range correction, and the loss value represents the difference degree between the molecular orbital energy and the ionization energy and electron affinity;

[0199] An excited state energy determination unit 703 is configured to input the position information of each atom into a second model using target long-range correction parameters to obtain an excited state energy set of the target chemical molecule; wherein, the second model is a time-dependent density functional theory model based on long-range correction.

[0200] A molecule screening unit 704 is configured to determine that the target chemical molecule belongs to a NIR-II region fluorescent molecule when it is determined that the emission peak position of the target chemical molecule is in the NIR-II region based on the target ground state energy and the excited state energy set.

[0201] Optionally, the parameter optimization unit 702 is specifically configured to:

[0202] For each candidate long-range correction parameter, perform the following process using the first model to obtain a corresponding loss value, and determine the candidate long-range correction parameter corresponding to the minimum loss value as the target long-range correction parameter:

[0203] For a candidate long-range correction parameter, determine a corresponding distance separation threshold;

[0204] Based on the position information of each atom and the distance separation threshold, use the first model to determine the molecular orbital energies corresponding to multiple molecular orbitals of the target chemical molecule;

[0205] Based on the difference between the molecular orbital energy of the highest occupied molecular orbital in multiple molecular orbitals and the ionization energy of the target chemical molecule, and the difference between the molecular orbital energy of the lowest unoccupied molecular orbital and the electron affinity of the target chemical molecule, determine the corresponding loss value.

[0206] Optionally, the parameter optimization unit 702 is specifically configured to:

[0207] Based on the position information of each atom and the distance separation threshold, construct atomic orbitals of each atom, and perform a linear combination of the obtained multiple atomic orbitals to obtain multiple molecular orbitals;

[0208] With the constraint that multiple molecular orbitals are mutually orthogonal, determine the set of molecular orbital coefficients corresponding to each molecular orbital when the total energy of the system of the target chemical molecule is minimized, where each molecular orbital coefficient represents the proportion of the corresponding atomic orbital in the corresponding molecular orbital;

[0209] Based on the obtained sets of molecular orbital coefficients, obtain the reduced density matrix between pairwise atomic orbitals;

[0210] Based on the obtained multiple reduced density matrices, obtain the molecular orbital energies of multiple molecular orbitals respectively.

[0211] Optionally, the parameter optimization unit 702 is specifically configured to:

[0212] Determine the short-range Coulomb interaction energy of the target chemical molecule based on the obtained reduced density matrix and the zero-order density matrix;

[0213] Determine the long-range exchange interaction energy of the target chemical molecule based on the obtained reduced density matrix, zero-order density matrix, and the target long-range correction parameter;

[0214] Obtain the Hamiltonian matrix between pairwise atomic orbitals based on the density functional theory method;

[0215] Based on the obtained reduced density matrix, Hamiltonian matrix, short-range Coulomb interaction energy, long-range exchange interaction energy, and the pairwise atomic repulsive potential energy, obtain the molecular orbital energies of multiple molecular orbitals respectively.

[0216] Optionally, the parameter optimization unit 702 is specifically used for:

[0217] Determine the total energy of the system of the target chemical molecule based on the obtained multiple molecular orbital energies;

[0218] Then obtain the target ground state energy corresponding to the target long-range correction parameter, including:

[0219] From the obtained multiple total energies of the system, take the total energy of the system corresponding to the target long-range correction parameter as the target ground state energy.

[0220] Optionally, the parameter optimization unit 702 is specifically used for:

[0221] Determine the ionization energy based on the difference between the total energy of the system and the total energy of the system of the monovalent positive ion corresponding to the target chemical molecule;

[0222] Obtain the electron affinity based on the difference between the total energy of the system and the total energy of the system of the monovalent negative ion corresponding to the target chemical molecule.

[0223] Optionally, the excited state energy determination unit 703 is specifically used for:

[0224] Construct a non-Hermitian matrix diagonalization equation for the excited state energy based on the position information of each atom of the target chemical molecule, and the ground state energies of each molecular orbital and atomic orbital corresponding to the target long-range correction parameter;

[0225] Based on the position information of each atom of the target chemical molecule, obtain the first matrix-vector product and the second matrix-vector product. The first matrix-vector product is the dot product of the sum of the first matrix and the second matrix and the target vector, and the second matrix-vector product is the dot product of the difference between the first matrix and the second matrix and the target vector. The first matrix and the second matrix are determined by the atomic energy orbitals and molecular orbitals corresponding to the target chemical molecule, and the target vector is a vector composed of the molecular orbital coefficients corresponding to the atomic orbitals of the unoccupied molecular orbitals;

[0226] Based on the first matrix-vector product and the second matrix-vector product, determine the eigenvalues of the non-Hermitian matrix diagonalization equation, and the eigenvalues are the excited state energies of the target chemical molecule.

[0227] Optionally, the molecule screening unit 704 is specifically configured to:

[0228] Obtain the target excited state energy corresponding to the first excited state from the set of excited state energies;

[0229] Based on the difference between the target excited state energy and the target ground state energy, determine the emission peak position of the target chemical molecule.

[0230] Optionally, the molecule information acquisition unit 701 is specifically configured to:

[0231] Based on the molecular structure formula of the input target chemical molecule, determine the position information of each atom in the target chemical molecule; or,

[0232] Convert the input Simplified Molecular-Input Line-Entry System (SMILES) string of the target chemical molecule into a molecular structure formula, and based on the converted molecular structure formula, determine the position information of each atom in the target chemical molecule.

[0233] Through the above device, by pre-determining the target long-distance correction parameter most suitable for the target chemical molecule and combining the target long-distance correction parameter to accurately determine the set of excited state energies of the target chemical molecule, so as to accurately determine the emission peak position of the target chemical molecule, and determine whether the chemical molecule belongs to a NIR-II region fluorescent molecule. In addition, when finding the optimal long-distance correction parameter, this method adopts a relatively fast long-distance correction density functional theory model, greatly improving the calculation speed and the screening efficiency of organic chemical molecules.

[0234] This device can be used to execute the methods shown in the embodiments of the present application. Therefore, for the functions that can be realized by each functional module of this device, reference can be made to the description of the foregoing embodiments, and details will not be repeated.

[0235] Please refer to Figure 8 , based on the same technical concept, the embodiments of the present application also provide a computer device. In one embodiment, this computer device can be Figure 1 the server shown, and this computer device is as shown in Figure 8 , including a memory 801, a communication module 803, and one or more processors 802.

[0236] A memory 801 for storing computer programs executed by a processor 802. The memory 801 may mainly include a program storage area and a data storage area. Among them, the program storage area may store an operating system and programs required to run the instant messaging function, etc.; the data storage area may store various instant messaging information and operation instruction sets, etc.

[0237] The memory 801 may be a volatile memory, such as a random-access memory (RAM); the memory 801 may also be a non-volatile memory, such as a read-only memory, a flash memory, a hard disk drive (HDD) or a solid-state drive (SSD); or the memory 801 is any other medium that can be used to carry or store desired program code in the form of instructions or data structures and can be accessed by a computer, but is not limited thereto. The memory 801 may be a combination of the above memories.

[0238] The processor 802 may include one or more central processing units (CPUs) or be a digital processing unit, etc. The processor 802 is used to implement the above NIR-II region fluorescence molecule screening method when calling the computer program stored in the memory 801.

[0239] The communication module 803 is used to communicate with terminal devices and other servers.

[0240] In the embodiments of the present application, the specific connection medium between the above memory 801, communication module 803 and processor 802 is not limited. In the embodiments of the present application Figure 8 it is described that the memory 801 and the processor 802 are connected through a bus 804. The bus 804 is described in thick lines in Figure 8 The connection manners between other components are only for illustrative purposes and are not to be taken as limitations. The bus 804 may be divided into an address bus, a data bus, a control bus, etc. For the sake of convenience of description, Figure 8 only one thick line is used to describe it in

[0241] The memory 801 stores a computer storage medium, and the computer storage medium stores computer-executable instructions for implementing the NIR-II region fluorescence molecule screening method of the embodiments of the present application. The processor 802 is used to execute the NIR-II region fluorescence molecule screening method of the above embodiments.

[0242] In another embodiment, the computer device can also be other computer devices, such as Figure 1 the terminal device shown. In this embodiment, the structure of the computer device can be as Figure 9 shown, including components such as a communication component 910, a memory 920, a display unit 930, a camera 940, a sensor 950, an audio circuit 960, a Bluetooth module 970, a processor 980, etc.

[0243] The communication component 910 is used to communicate with the server. In some embodiments, it may include a Wireless Fidelity (WiFi) module. The WiFi module belongs to short-range wireless transmission technology, and the computer device can help users send and receive information through the WiFi module.

[0244] The memory 920 can be used to store software programs and data. The processor 980 executes various functions and data processing of the terminal device by running the software programs or data stored in the memory 920. The memory 920 can include high-speed random access memory, and can also include non-volatile memory, such as at least one disk storage device, a flash memory device, or other volatile solid-state storage devices. The memory 920 stores an operating system that enables the terminal device to run. In this application, the memory 920 can store the operating system and various application programs, and can also store the code for executing the NIR-II region fluorescence molecule screening method of the embodiments of this application.

[0245] The display unit 930 can also be used to display information input by the user or information provided to the user, as well as the graphical user interface (GUI) of various menus of the terminal device. Specifically, the display unit 930 can include a display screen 932 disposed on the front of the terminal device. Among them, the display screen 932 can be configured in the form of a liquid crystal display, a light-emitting diode, etc. The display unit 930 can be used to display various pages in the embodiments of this application, such as a molecular structure drawing page, a molecular text box editing page, and a result display page, etc.

[0246] The display unit 930 can also be used to receive input digital or character information, and generate signal inputs related to the user settings and function control of the terminal device. Specifically, the display unit 930 can include a touch screen 931 disposed on the front of the terminal device, which can collect touch operations of the user on or near it, such as clicking buttons, dragging scroll boxes, etc.

[0247] Among them, the touch screen 931 can cover the display screen 932, or the touch screen 931 and the display screen 932 can be integrated to implement the input and output functions of the terminal device. After integration, it can be simply called a touch display screen. In this application, the display unit 930 can display application programs and corresponding operation steps.

[0248] The camera 940 can be used to capture static images. Users can post comments on the images captured by the camera 940 through an application. There can be one or more cameras 940. An object generates an optical image through a lens and projects it onto a photosensitive element. The photosensitive element can be a charge coupled device (CCD) or a complementary metal-oxide-semiconductor (CMOS) phototransistor. The photosensitive element converts the optical signal into an electrical signal, and then transmits the electrical signal to the processor 980 to be converted into a digital image signal.

[0249] The terminal device may further include at least one sensor 950, such as an acceleration sensor 951, a distance sensor 952, a fingerprint sensor 953, and a temperature sensor 954. The terminal device may also be configured with other sensors such as a gyroscope, a barometer, a hygrometer, a thermometer, an infrared sensor, a light sensor, and a motion sensor.

[0250] The audio circuit 960, the speaker 961, and the microphone 962 can provide an audio interface between the user and the terminal device. The audio circuit 960 can transmit the electrical signal converted from the received audio data to the speaker 961, and the speaker 961 converts it into a sound signal for output. The terminal device may also be configured with a volume button for adjusting the volume of the sound signal. On the other hand, the microphone 962 converts the collected sound signal into an electrical signal, which is received by the audio circuit 960 and then converted into audio data. The audio data is then output to the communication component 910 to be sent to, for example, another terminal device, or the audio data is output to the memory 920 for further processing.

[0251] The Bluetooth module 970 is used to interact with other Bluetooth devices having a Bluetooth module through the Bluetooth protocol. For example, the terminal device can establish a Bluetooth connection with a wearable computer device (such as a smart watch) that also has a Bluetooth module through the Bluetooth module 970, so as to perform data interaction.

[0252] The processor 980 is the control center of the terminal device, connecting various parts of the entire terminal through various interfaces and circuits. By running or executing software programs stored in the memory 920 and calling data stored in the memory 920, it performs various functions of the terminal device and processes data. In some embodiments, the processor 980 may include one or more processing units; the processor 980 may also integrate an application processor and a baseband processor. Among them, the application processor mainly processes the operating system, user interface, application programs, etc., and the baseband processor mainly processes wireless communication. It can be understood that the above baseband processor may not be integrated into the processor 980. In this application, the processor 980 can run the operating system, application programs, user interface display and touch response, as well as the NIR-II region fluorescence molecule screening method of the embodiments of this application. In addition, the processor 980 is coupled to the display unit 930.

[0253] In some possible implementation manners, various aspects of the NIR-II region fluorescence molecule screening method provided in this application can also be implemented in the form of a program product, which includes program code. When the program product runs on a computer device, the program code is used to cause the computer device to execute the steps in the NIR-II region fluorescence molecule screening method according to various exemplary embodiments described in this specification above. For example, the computer device can execute the steps of each embodiment.

[0254] The program product can adopt any combination of one or more readable media. The readable medium can be a readable signal medium or a readable storage medium. The readable storage medium can be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or component, or any combination of the above. More specific examples (non-exhaustive list) of the readable storage medium include: an electrical connection with one or more wires, a portable disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above.

[0255] The program product of the embodiments of this application can adopt a portable compact disk read-only memory (CD-ROM) and include program code, and can run on a computing device. However, the program product of this application is not limited to this. In this application document, the readable storage medium can be any tangible medium that contains or stores a program, and this program can be used by or in combination with a command execution system, device, or component.

[0256] A readable signal medium can include a data signal propagated in a baseband or as part of a carrier wave, in which readable program code is carried. Such a propagated data signal can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. The readable signal medium can also be any readable medium other than a readable storage medium, which can send, propagate, or transmit a program for use by or in conjunction with a command execution system, apparatus, or device.

[0257] The program code contained on the readable medium can be transmitted by any appropriate medium, including but not limited to wireless, wired, optical fiber cable, RF, etc., or any suitable combination of the above.

[0258] The program code for performing the operations of this application can be written in any combination of one or more programming languages, including object-oriented programming languages such as Java, C++, etc., and also including conventional procedural programming languages such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computing device, partially on the user's device, executed as a stand-alone software package, partially on the user's computing device and partially on a remote computing device, or entirely on a remote computing device or server. In the case of a remote computing device, the remote computing device can be connected to the user's computing device through any type of network, including a local area network (LAN) or a wide area network (WAN), or, it can be connected to an external computing device (e.g., by using an Internet service provider to connect through the Internet).

[0259] It should be noted that although several units or subunits of the apparatus are mentioned in the above detailed description, this division is merely exemplary and not mandatory. In fact, according to the embodiments of this application, the features and functions of the two or more units described above can be embodied in one unit. Conversely, the features and functions of one unit described above can be further divided and embodied by multiple units.

[0260] In addition, although the operations of the method of this application are described in a specific order in the drawings, this does not require or imply that these operations must be performed in that specific order, or that all the operations shown must be performed to achieve the desired result. Additionally or alternatively, some steps can be omitted, multiple steps can be combined into one step for execution, and / or one step can be decomposed into multiple steps for execution.

[0261] Those skilled in the art should understand that the embodiments of the present application can be provided as a method, a system, or a computer program product. Therefore, the present application can take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present application can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code.

[0262] Although the preferred embodiments of the present application have been described, those skilled in the art can make additional changes and modifications to these embodiments once they know the basic creative concept. Therefore, the appended claims are intended to be construed as including the preferred embodiments as well as all changes and modifications that fall within the scope of the present application.

[0263] Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the claims of the present application and their equivalent technologies, the present application is also intended to include these changes and modifications.

Claims

1. A method for screening second near-infrared (NIR-II) region fluorescent molecules, characterized in that, The method includes: Determining the position information of each atom in the target chemical molecule to be analyzed; Using a first model, based on the position information of each atom, to determine a target long-range correction parameter when the loss value of the target chemical molecule is minimized, and obtaining the target ground state energy corresponding to the target long-range correction parameter; wherein, the first model is a density functional theory model based on long-range correction, and the loss value characterizes the difference degree between the molecular orbital energy and the ionization energy and the electron affinity; Inputting the position information of each atom into a second model using the target long-range correction parameter to obtain an excited state energy set of the target chemical molecule; wherein, the second model is a time-dependent density functional theory model based on long-range correction; Based on the target ground state energy and the excited state energy set, when it is determined that the emission peak position of the target chemical molecule is in the NIR-II region, determining that the target chemical molecule belongs to a NIR-II region fluorescent molecule.

2. The method according to claim 1, characterized in that, Using a first model, based on the position information of each atom, to determine a target long-range correction parameter when the loss value of the target chemical molecule is minimized, including: Using the first model to perform the following process for each candidate long-range correction parameter to obtain a corresponding loss value, and determining the candidate long-range correction parameter corresponding to the minimum loss value as the target long-range correction parameter: For a candidate long-range correction parameter, determining a corresponding distance separation threshold; Based on the position information of each atom and the distance separation threshold, using the first model to determine the molecular orbital energies corresponding to multiple molecular orbitals of the target chemical molecule; Based on the difference degree between the molecular orbital energy of the highest occupied molecular orbital in the multiple molecular orbitals and the ionization energy of the target chemical molecule, and the difference degree between the molecular orbital energy of the lowest unoccupied molecular orbital and the electron affinity of the target chemical molecule, determining the corresponding loss value.

3. The method according to claim 2, wherein Based on the position information of each atom and the distance separation threshold, using the first model to determine the molecular orbital energies corresponding to multiple molecular orbitals of the target chemical molecule, including: Based on the position information of each atom and the distance separation threshold, constructing atomic orbitals of each atom, and performing a linear combination of the obtained multiple atomic orbitals to obtain multiple molecular orbitals; Taking the condition that the multiple molecular orbitals are all orthogonal to each other as a constraint, determining a set of molecular orbital coefficients corresponding to each molecular orbital when the total energy of the system of the target chemical molecule is minimized, wherein each molecular orbital coefficient characterizes the proportion of the corresponding atomic orbital in the corresponding molecular orbital; Based on the obtained sets of molecular orbital coefficients, obtaining the reduced density matrix between two atomic orbitals; Based on the obtained multiple reduced density matrices, respectively obtaining the molecular orbital energies of the multiple molecular orbitals.

4. The method according to claim 3, wherein Based on the obtained multiple reduced density matrices, respectively obtaining the molecular orbital energies of the multiple molecular orbitals, including: Based on the obtained reduced density matrix and the zero-order density matrix, determining the short-range Coulomb interaction energy of the target chemical molecule; Determine the long-range exchange interaction energy of the target chemical molecule based on the obtained reduced density matrix, zero-order density matrix, and the target long-range correction parameter; Based on the density functional theory method, obtain the Hamiltonian matrix between pairwise atomic orbitals; Based on the obtained reduced density matrix, Hamiltonian matrix, the short-range Coulomb interaction energy, long-range exchange interaction energy, and the repulsive potential energy between pairwise atoms, respectively obtain the molecular orbital energies of the multiple molecular orbitals.

5. The method according to claim 2, wherein After determining the molecular orbital energies corresponding to the multiple molecular orbitals of the target chemical molecule by using the first model based on the position information of each atom and the distance separation threshold, the method further includes: Determine the total energy of the system of the target chemical molecule based on the obtained multiple molecular orbital energies; Then obtaining the target ground state energy corresponding to the target long-range correction parameter includes: Among the obtained multiple total energies of the system, take the total energy of the system corresponding to the target long-range correction parameter as the target ground state energy.

6. The method according to claim 5, wherein After determining the total energy of the system of the target chemical molecule based on the obtained multiple molecular orbital energies, the method further includes: Determine the ionization energy based on the difference between the total energy of the system and the total energy of the system of the monovalent positive ion corresponding to the target chemical molecule; Obtain the electron affinity based on the difference between the total energy of the system and the total energy of the system of the monovalent negative ion corresponding to the target chemical molecule.

7. The method according to any one of claims 1 to 6, characterized in that Input the position information of each atom into the second model using the target long-range correction parameter to obtain the set of excited state energies of the target chemical molecule, including: Based on the position information of each atom of the target chemical molecule and the ground state energies of the respective molecular orbitals and atomic orbitals corresponding to the target long-range correction parameter, construct a non-Hermitian matrix diagonalization equation based on the excited state energy; Based on the position information of each atom of the target chemical molecule, obtain the first matrix-vector product and the second matrix-vector product. The first matrix-vector product is the dot product of the sum of the first matrix and the second matrix and the target vector, and the second matrix-vector product is the dot product of the difference between the first matrix and the second matrix and the target vector. The first matrix and the second matrix are determined by the atomic energy orbitals and molecular orbitals corresponding to the target chemical molecule, and the target vector is a vector composed of the molecular orbital coefficients corresponding to the atomic orbitals of the unoccupied molecular orbitals; Based on the first matrix-vector product and the second matrix-vector product, determine the eigenvalues of the non-Hermitian matrix diagonalization equation, and the eigenvalues are the excited state energies of the target chemical molecule.

8. The method according to any one of claims 1 to 6, characterized in that Based on the target ground state energy and the set of excited state energies, determine the emission peak position of the target chemical molecule, including: From the set of excited state energies, obtain the target excited state energy corresponding to the first excited state; Determine the emission peak position of the target chemical molecule based on the difference between the target excited state energy and the target ground state energy.

9. The method according to any one of claims 1 to 6, characterized in that Determine the position information of each atom in the target chemical molecule to be analyzed, including: Based on the molecular structural formula of the target chemical molecule as input, determine the position information of each atom in the target chemical molecule; or, Convert the Simplified Molecular-Input Line-Entry System (SMILES) string of the target chemical molecule as input into a molecular structural formula, and based on the converted molecular structural formula, determine the position information of each atom in the target chemical molecule.

10. A screening device for NIR-II region fluorescent molecules, characterized in that, The device includes: A molecular information acquisition unit, configured to determine the position information of each atom in the target chemical molecule to be analyzed; A parameter optimization unit, configured to use a first model to determine the target long-range correction parameter when the loss value of the target chemical molecule is minimized based on the position information of each atom, and obtain the target ground state energy corresponding to the target long-range correction parameter; wherein, the first model is a density functional theory model based on long-range correction, and the loss value represents the degree of difference between the molecular orbital energy and the ionization energy and electron affinity; An excited state energy determination unit, configured to input the position information of each atom into a second model using the target long-range correction parameter to obtain a set of excited state energies of the target chemical molecule; wherein, the second model is a time-dependent density functional theory model based on long-range correction; A molecular screening unit, configured to determine that the target chemical molecule belongs to a NIR-II region fluorescent molecule when it is determined that the emission peak position of the target chemical molecule is in the NIR-II region based on the target ground state energy and the set of excited state energies.

11. The device according to claim 10, characterized in that, The parameter optimization unit is specifically configured to: Use the first model to perform the following processes for each candidate long-range correction parameter to obtain the corresponding loss value, and determine the candidate long-range correction parameter corresponding to the minimum loss value as the target long-range correction parameter: For a candidate long-range correction parameter, determine the corresponding distance separation threshold; Based on the position information of each atom and the distance separation threshold, use the first model to determine the molecular orbital energies corresponding to multiple molecular orbitals of the target chemical molecule; Based on the degree of difference between the molecular orbital energy of the highest occupied molecular orbital in the multiple molecular orbitals and the ionization energy of the target chemical molecule, and the degree of difference between the molecular orbital energy of the lowest unoccupied molecular orbital and the electron affinity of the target chemical molecule, determine the corresponding loss value.

12. The device according to claim 10, characterized in that, The excited state energy determination unit is specifically configured to: Based on the position information of each atom of the target chemical molecule and the ground state energies of each molecular orbital and atomic orbital corresponding to the target long-range correction parameter, construct a non-Hermitian matrix diagonalization equation based on the excited state energy; Based on the position information of each atom of the target chemical molecule, obtain a first matrix-vector product and a second matrix-vector product. The first matrix-vector product is the dot product of the sum of a first matrix and a second matrix and a target vector, and the second matrix-vector product is the dot product of the difference between the first matrix and the second matrix and the target vector. The first matrix and the second matrix are determined by the atomic energy orbitals and molecular orbitals corresponding to the target chemical molecule, and the target vector is a vector composed of the molecular orbital coefficients corresponding to the atomic orbitals of the unoccupied molecular orbitals. Based on the first matrix-vector product and the second matrix-vector product, determine the eigenvalues of the non-Hermitian matrix diagonalization equation, where the eigenvalues are the excited state energies of the target chemical molecule.

13. A computer device, comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, characterized in that when the processor executes the computer program, the steps of the method according to any one of claims 1 to 9 are implemented.

14. A computer storage medium, on which computer program instructions are stored, characterized in that when the computer program instructions are executed by a processor, the steps of the method according to any one of claims 1 to 9 are implemented.

15. A computer program product, comprising computer program instructions, characterized in that when the computer program instructions are executed by a processor, the steps of the method according to any one of claims 1 to 9 are implemented.

Images