Method for predicting standard boiling point of pure compound by using multiple linear regression model

Abstract

Provided is a mathematical model with which it is possible to accurately predict the standard boiling point of a pure compound having 25 or less atoms (excluding hydrogen), said pure compound comprising 12 or less elements such as hydrogen, carbon, nitrogen, oxygen, sulfur, fluorine, chlorine, bromine, iodine, silicon, phosphorus, and arsenic. Wherein the model, as a universal quantitative structure-property relationship model, is obtained by determining an optimal model from a plurality of multiple linear regression models by means of a stepwise selection method, and the model takes some of the various molecular descriptors as independent variables, takes a standard boiling point as a dependent variable, and takes the standard boiling point as a dependent variable; according to the present invention, the values of the molecule descriptors included in the model can be received and input in a short time and the standard boiling point can be output, so that the standard boiling point of the compound purely composed of the molecule can be predicted for any molecule satisfying the requirements of the present invention as long as the specific values of the molecule descriptors included in the model are known.

Description

Technical Field

[0001] The present invention belongs to the field of physical property prediction, which is one of the fields of physical chemistry, and relates to a method for predicting the normal boiling point, which is one of the various physical properties of a compound, with high accuracy. Background Art

[0002] Today, humanity relies on a vast array of chemical compounds, including plastics, fibers, rubber, paints, fertilizers, pharmaceuticals, and fuels, and this trend is expected to intensify. According to the American Chemical Society (ACS), the total number of registered chemical substances as of 2023 is over 204 million. In comparison, the number of compounds for which even a single physical property is experimentally known is only in the tens of thousands, a tiny fraction of the total number of chemical substances. However, the physical properties of chemical compounds are essential for a better material life, including the development of new substances and drugs, the optimal design of chemical equipment, improving the productivity of existing equipment, developing and conserving resources, ensuring safety, and protecting the environment.

[0003] Specifically, understanding the exact values ​​of various physical properties of a compound plays a decisive role in various decision-making matters throughout the production and consumption process, such as determining the rationality of the substance's use or designing synthesis and purification processes, setting methods and conditions for storage, transportation, use, and disposal. Therefore, it is of great significance both industrially and academically.

[0004] Currently, the most accurate way to obtain the relevant physical property values ​​of the compound of interest is through experimental measurement. However, this requires considerable cost and time in various aspects, such as preparing purified samples and constructing an environment for accurate measurement, and may sometimes be impossible to achieve depending on the actual situation.

[0005] Therefore, as an alternative, many researchers have long been working on predicting the accurate values ​​of various physical properties of compounds. Since physical property prediction has a long history and new prediction methods continue to emerge, various prediction models that differ from each other currently coexist according to physical properties, accuracy, and application range.

[0006] As a model for predicting physical properties, the main method currently widely known and used is the group contribution method determined by statistical methods. This method has the best performance for predicting physical properties of compounds with experimental values.

[0007] This group contribution method has previously achieved some impressive results, but due to its lack of theoretical basis, it sometimes encounters problems with segmentation based on fragment form, sometimes with non-unique or even non-existent segmentation, resulting in inability to calculate numerical values. Furthermore, the need to continuously refine the model to improve predictive performance ultimately leads to increased complexity and difficulty in handling.

[0008] In the process of building prediction models, one of the alternatives to the group contribution method is the quantitative structure-property relationship (QSPR) method. The basis of this method is the assumption that the physical properties of a compound are functions of the structural characteristics of the molecule, and it uses a variety of molecular descriptors that reflect a variety of different structural characteristics. The types of molecular descriptors proposed so far in this method have reached thousands, ranging from simple molecular descriptors such as the number of carbon or hydrogen atoms in a molecule to complex molecular descriptors such as the shape, connection state, and electrochemical properties of the molecule. In addition, many types of calculation methods for molecular descriptors have been developed [Todeschini R., V. Consonni V., Molecular Descriptors for Chemoinformatics: Second, Revised and Enlarged Edition: Volume I / II, Wiley-VCH, 2009]. The QSPR prediction model is presented in the form of a function that includes these molecular descriptors and, sometimes, other physicochemical properties of the predicted compound (which are also functions of structural characteristics) as independent variables.

[0009] In this case, the most common function is the random variable (representer) X shown below: i The linear combination function, the coefficients c0 and c i It was mainly determined by multiple linear regression analysis based on experimental data.

[0010]

[0011] Another way to create a QSPR model is to use artificial neural networks. Artificial neural network technology is a widely used information processing technology that uses models based on human neural cells to create machines with artificial intelligence.

[0012] By training an artificial neural network using a sample set that binds various input values ​​to the output values ​​corresponding to those input values, the artificial neural network can establish general rules through learning, even without the rules or knowledge required to solve the problem. This allows it to output appropriate outputs even for unknown inputs. Therefore, artificial neural networks are widely used as a very useful tool in fields that lack basic theory, such as predicting the physical properties of compounds.

[0013] When using computers to uniformly calculate the values ​​of more than 3,779 molecular descriptors of compounds required for the QSPR model for predicting physical properties, in order to calculate the electronic structure of the molecule, the electron energy solution is usually obtained by solving the Schrödinger equation. However, for systems with a large number of electrons, the calculation time required is very long, and the following attempts have been made in the prior art.

[0014] The calculation theories tried to select the best quantum mechanical calculation method are Hartree-Fock method [CCJ Roothan, Rev. Mod. Phys. 23, 69 (1951)], various post-Hartree-Fock methods [C. Moller and MSPlesset, Phys. Rev. 46, 618 (1934)], Gauss method combining Hartree-Fock and post-Hartree-Fock methods [LA Curtiss, K. Raghavachari, GW Trucks, and JA Popple, J. Chem. Phys. 94, 7221 (1991); LA Curtiss, K. Raghavachari, PC Redfern, V. Rassolov, and J.A.Pople, J.Chem.Phys.109,7764(1998)], density functional theory (DFT) [R.Seeger and J.A.Pople, J.Chem.Phys.66,3045(1977)] which uses electron density function instead of wave function with multi-dimensional perturbation term to consider the correlation between electrons in molecules composed of many electrons and uses total energy functional to find the ground state. However, these methods still require a very large amount of calculation, so when calculating large molecules, there are still difficulties in cost and time.

[0015] In addition, although some QSPR prediction models for the normal boiling point of interest in the present invention have been proposed, they have not yet been widely used. Although Yalkowsky and his colleagues proposed a model that combines QSPR elements with the group contribution method [Yalkowsky SH, Dannenfelser R.-M., Myrdal P., Simamora P., Chemosphere, 28:1657 (1994); Krzyzaniak JF, Myrdal PB, Simamora P., Yalkowsky SH, IEC Res., 34:2530 (1995); Zhao L., Yalkowsky SH, IEC Res., 38:3581 (1999).], it is known that the prediction performance is lower than that of the latest group contribution model.

[0016] Jurs et al. showed that the prediction performance of 633 substances was improved with a root mean square error of 8.9 K by introducing more complex selected molecular descriptors [Wessel MD, Jurs PC, J. Chem. Inf. Comput. Sci., 35: 68, 841 (1995).]. In addition, Katritzky et al. proposed prediction results for nearly 900 compounds using a model using 8 molecular descriptors [Katritzky AR, Mu L., Lobanov V.S., Karelson M., J. Phys. Chem., 100: 10400 (1996); Katritzky AR, Lobanov V.S., Karelson M., J. Chem. Inf. Comput. Sci., 38: 28 (1998); Katritzky AR, Tamm T., Wang Y., Sild S., Karelson M., J. Chem. Inf. Comput. Sci., 39: 684 (1999).]. However, the prediction performance still did not meet the accuracy level of a coefficient of determination of 0.965 and a standard error of 15.5 K.

[0017] Although some QSPR models that use artificial neural networks to predict standard boiling points have been proposed, most of them have the problem of a small number of sample compounds or are limited to a specific series of compounds. Some of these models and results are described in the literature [Cherqaoui D., Villemin D., Mesbah A., Cense J.-M., Kvasniccka V., J. Chem. Soc., Faraday Trans., 1994, 90, 2015-2019; Balaban AT, Basak SC, Colburn T., Grunwald G.D., J. Chem. Inf. Comput. Sci., 1994, 34(5), 1118-1121].

[0018] Therefore, the present invention provides a method for predicting the normal boiling point as follows: in order to shorten the calculation time that is a problem of the above-mentioned conventional methods and improve the accuracy of predicted physical properties, molecular descriptors that can serve as independent variables are screened out from molecular descriptors, and without adding the use of artificial neural networks, an optimal multiple linear regression model for the normal boiling point of the compound is established to predict the accurate normal boiling point of the pure compound. Summary of the Invention

[0019] The technical problem to be solved by the present invention is to provide a more reliable QSPR model for the standard boiling points of compounds composed of no more than 12 elements, including hydrogen (H), carbon (C), nitrogen (N), oxygen (O), sulfur (S), fluorine (F), chlorine (Cl), bromine (Br), iodine (I), silicon (Si), phosphorus (P), and arsenic (As), based on more experimental data.

[0020] This model is expected to overcome the shortcomings of the model constructed by the group contribution method described above and to show fast and accurate prediction performance for a wider range of elements. The range of compounds to which the prediction model can be applied is limited to compounds composed of no more than 12 elements, including hydrogen (H), carbon (C), nitrogen (N), oxygen (O), sulfur (S), fluorine (F), chlorine (Cl), bromine (Br), iodine (I), silicon (Si), phosphorus (P), and arsenic (As). This is mainly because the model is based on experimental values ​​and is therefore limited to the constituent elements of the compound for which experimental values ​​exist, but the number of each atom is not limited.

[0021] As a predictive model capable of matching the composition of the constituent elements or molecular sizes of compounds with experimental values, it can be expanded to encompass a wider range of constituent elements and a greater number of atoms. Even within the aforementioned limited range of compounds, there are a vast number of compounds, including a significant number of industrially important ones. Based on the molecular structure of a compound, physical properties can be predicted in a very short time, facilitating the processing and analysis of physical property information on a large amount of compounds. Therefore, the present invention is expected to have significant beneficial effects on human society.

[0022] To achieve this purpose, an example of the present invention is a method for calculating the standard boiling point of a compound using a multiple linear regression model, comprising the following steps: (1) inputting the collected experimental data of the sample compound; (2) preparing the molecular descriptors of the sample compound inputted above; (3) screening the best molecular descriptors from step (2); (4) separating the experimental data of step (1) into a training set and a test set; (5) constructing the best multiple linear regression model that conforms to the training set using the molecular descriptors described in step (3); (6) judging the rationality of the multiple linear regression model; (7) if the multiple linear regression model is not rational in step (6), repeating steps (5) and (6); if it is rational, testing the prediction performance of the model using the test set; (8) in the test of step (7), if the performance does not meet the standard, repeating steps (4) to (7); if it meets the standard, adopting the predicted value of the standard boiling point obtained using the multiple linear regression model as the actual value of the standard boiling point.

[0023] The sample compound in step (1) is a pure compound composed of one or more elements selected from the group consisting of hydrogen, carbon, nitrogen, oxygen, sulfur, fluorine, chlorine, bromine, iodine, silicon, phosphorus, and arsenic.

[0024] The sample compound in step (1) is one of the following: a. a hydrocarbon compound containing carbon and hydrogen elements; b. a non-hydrocarbon type I compound containing one or more of carbon, hydrogen, nitrogen, oxygen, and sulfur; c. a non-hydrocarbon type II compound containing one or more of carbon, hydrogen, fluorine, chlorine, bromine, iodine, silicon, phosphorus, and arsenic.

[0025] The step (2) of preparing molecular descriptors refers to preparing molecular descriptors related to the standard boiling point.

[0026] The optimal molecular descriptor in step (3) includes one or more of the following: P1: a hyper-Wiener index from a chi matrix, wherein the hyper-Wiener index is a logarithmic function; P2: an eta x shape index; P3: a topological charge index of order 2; P4: the number of quaternary carbon atoms in a sp3 hybridized ring; P5: an eigenvalue n.3 from a dipole moment weighted enhanced edge adjacency matrix; P6: a pyridazine number; and P7: a hydrophilic factor.

[0027] P8: number of urea derivatives or thiourea derivatives; P9: number of N in hydrazine; P 10 : imide or thioimide number; P 11 : number of aromatic bonds; P 12 : Narumi harmonic topology index; P 13 : maximum negative change in electronic topology; P 14 : 5-order autoregressive path count; P 15 : Molecular multipath counting of order 1.

[0028] The optimal molecular descriptor in step (3) is an independent molecular descriptor having different values ​​for all sample compounds.

[0029] In step (4), the training set and the test set are divided in a ratio of 5-8:2-5.

[0030] The step (5) of finding the best multiple linear regression model of the training set is to apply a stepwise selection method to the training set to construct a multiple linear regression model.

[0031] The optimal multiple linear regression model in step (5) is found by judging the prediction performance by the coefficient of determination or mean absolute error of the regression model.

[0032] The rationality of step (6) is determined by the t-test value, wherein the model is rational when the t-test value is greater than or equal to 3, otherwise it is not rational.

[0033] The test in step (7) is to test the multiple linear regression model using the test set.

[0034] The satisfaction standard in step (8) is achieved by comparing the difference between the training set and the test set. If the difference between the training set and the test set does not exceed 20% of the mean absolute error obtained for the training set, it is judged that the performance meets the standard; otherwise, the performance does not meet the standard.

[0035] The physical properties of chemical compounds are essential for the development of new substances and drugs, the optimization of chemical equipment design, improving the productivity of existing equipment, developing and conserving resources, ensuring safety, and protecting the environment. In particular, the normal boiling point, a property that can be used to predict other physical properties such as critical temperature, serves as an indicator of a compound's volatility. Its accurate value is highly sought after in commonly used programs such as Aspen Plus and Pro / II, well-known programs for optimizing chemical equipment design. International regulations governing the production and consumption of chemical compounds, such as REACH, also require its value. However, currently, the number of compounds for which experimental values ​​are known does not exceed several thousand, and obtaining experimental data is often extremely difficult due to the harmfulness, toxicity, instability, and difficulty in purification of vapors.

[0036] From this perspective, the present invention, which can obtain highly accurate normal boiling point values ​​for many compounds using only molecular information without conducting experiments, not only saves the cost and time required for experiments, but also allows the value to be estimated even when experiments are not possible, thereby facilitating research and development activities in related industries. Furthermore, appropriate information can be provided to all places such as academia and government that require the value, allowing such activities to be carried out more smoothly.

[0037] Furthermore, although three-dimensional molecular descriptors are insufficient because quantum chemical calculations are not performed, the physical properties of unknown compounds can be predicted in a very short time. Furthermore, the prediction time can be further shortened without using additional models such as artificial neural networks, thereby enabling real-time prediction of physical properties. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] Figure 1 is a flow chart schematically illustrating a process of constructing a standard boiling point QSPR model.

[0039] Figure 2 is a scatter plot showing the prediction performance of the multiple linear regression model.

[0040] Figure 3 It is a histogram of 4946 experimental data of the QSPR model. DETAILED DESCRIPTION

[0041] Hereinafter, a method for predicting the normal boiling point of a pure compound using a multiple linear regression model according to the present invention will be described in detail with reference to the accompanying drawings so that persons having ordinary knowledge in the technical field to which the present invention pertains can easily implement the present invention.

[0042] In the process of describing the present invention, if it is determined that the detailed description of the related known technology may cause unnecessary obscurity to the gist of the present invention, the detailed description will be omitted.

[0043] When using the words "including," "having," "forming," "comprising," and the like in this specification, other parts may be added unless "only" is used. When describing a component in the singular, the plural is included unless otherwise specified.

[0044] Figure 1 A flow chart schematically illustrates the process of constructing a QSPR model of standard boiling point.

[0045] The first task in building the model is to collect experimental data and analyze and classify them as specified in the first step.

[0046] For the present invention, we conducted an extensive search of all available reference materials and documents, including various papers, monographs, and websites, to collect experimental data on the standard boiling points of compounds meeting the criteria of the present invention. We extensively examined whether this data represented truly reasonable values ​​for model construction. We carefully analyzed and modified or deleted data for compounds that (i) were non-experimental values, (ii) had data labeling errors, (iii) had values ​​that differed significantly even for the same compound, (iv) were unreliably deviated from those of other similar compounds, or (v) had values ​​for which molecular descriptors were difficult to readily generate. This resulted in a final selection of data for 4,946 compounds.

[0047] In addition, when constructing the physical property prediction model, the sample compounds were divided into (a) hydrocarbons composed only of C and H, (b) non-hydrocarbon 1 compounds containing one or more of the elements C, H, N, O, and S, and (c) non-hydrocarbon 2 compounds containing one or more of the elements C, H, F, Cl, Br, I, Si, P, and As, and models were established for each type.

[0048] Because the above three classifications showed more effective prediction performance, they were divided into 823 hydrocarbon compounds, 2462 non-hydrocarbon type 1 compounds, and 1661 non-hydrocarbon type 2 compounds, and models were established for each. In addition, in this invention, "compound" refers to a substance formed by molecules composed of no more than 12 elements: hydrogen (H), carbon (C), nitrogen (N), oxygen (O), sulfur (S), fluorine (F), chlorine (Cl), bromine (Br), iodine (I), silicon (Si), phosphorus (P), and arsenic (As).

[0049] The second step is to prepare molecular descriptor values ​​for these compounds. Molecular descriptors suitable for use as model variables are calculated using the following method for the values ​​of over 3,779 molecular descriptors: a file (MOL or SDF file) containing structural information, including the X, Y, and Z coordinates of each molecule's constituent elements and the bonding patterns between them, is input into a computer program. Based on this input, molecular descriptors representing the diversity of molecules are calculated using various theoretical mathematical formulas, moving beyond simple element and bond counts. Furthermore, the process of extracting these 3,779 molecular descriptors is repeated for all sample compounds used to construct the physical property prediction model.

[0050] The theoretical mathematical formulas used in the calculation are known in the art and are used in various forms, for example, a large number of theoretical mathematical formulas including Chi Connectivity Indices, Topological Descriptors, Information Indices, Walk and Path Counts, 2D Autocorrelation Descriptors, etc.

[0051] In the best results, not only physical property information but also molecular descriptors expressed as a variety of meaningful numerical values ​​reflecting the characteristics of the molecules can be obtained.

[0052] For pure substances, there are molecular descriptors that can characterize both two-dimensional and three-dimensional structures. However, three-dimensional molecular descriptors are affected by molecular structure and are more complex to compute. Therefore, in this invention, in order to rapidly process physical property predictions without performing quantum mechanical calculations for structure optimization, three-dimensional molecular descriptors are not used. This approach significantly reduces the computational time and cost of quantum mechanical calculations.

[0053] Furthermore, in the third step, after calculating the molecular descriptor values, it is necessary to screen out inappropriate molecular descriptor values. Specifically, by applying a theoretical mathematical formula to the molecular descriptors of the sample compounds, the system screens out molecular descriptor values ​​that yield the same value for all sample compounds and therefore cannot serve as independent variables in the model. This screening of molecular descriptors prevents the inclusion of irrelevant molecular descriptors in the prediction model, thereby improving model reliability while reducing the number of molecular descriptors, the number of calculations, and the computational effort, ultimately shortening the computational time required to find the optimal model.

[0054] In the present invention, when the sample compound is (a) a hydrocarbon composed only of C and H, the optimal molecular descriptor obtained includes a hyper-Wiener-like index from the chi matrix, wherein the hyper-Wiener-like index is a logarithmic function, an eta x shape index, a topological charge index of order 2, a quaternary carbon number in the sp3 hybridized ring, and an eigenvalue n.3 from the enhanced edge adjacency matrix weighted by the dipole moment; when the sample compound is (b) a non-hydrocarbon 1 including one or more of the elements C, H, N, O, and S, the optimal molecular descriptor obtained includes a pyridazine number, a hydrophilic factor, a urea derivative or thiourea derivative number, a N number in hydrazine, and an imide or thioimide number; when the sample compound is (c) a non-hydrocarbon 2 including one or more of the elements C, H, F, Cl, Br, I, Si, P, and As, the optimal molecular descriptor obtained includes the number of aromatic bonds, a Narumi harmonic topological index, a maximum negative electronic topological change, a 5th-order autoregressive path count, and a 1st-order molecular multipath count.

[0055] In the fourth step, the sample compounds are divided into a training set and a test set. The training set will be used to find the prediction model, and the test set will be used to test the predictive performance of the determined model. While taking care not to bias the distribution of similar molecules to one side, the training set and test set are divided in a ratio of 5-8:2-5, preferably 7:3.

[0056] Then, in the fifth step, the optimal multiple linear regression model is found based on the training set. Here, "optimal" is used in a relative sense, meaning that it can be found in a relatively short time while having performance very close to the optimal solution in an absolute sense.

[0057] The reason for not directly finding the optimal solution is that the calculation time is long. For example, when the number of suitable molecular descriptors among 3779 molecular descriptors is 1700, the total number of multiple linear regression models that can be made by extracting 5 different molecular descriptors is It is therefore practically impossible to investigate them all.

[0058] In order to obtain useful results within a limited time, a stepwise selection method is adopted in the present invention.

[0059] The stepwise selection method is a common method for selecting variables from data with many independent variables. During each step of creating a regression equation, the following steps are repeated: Among the independent variables not already in the equation, variables with high correlations with the dependent variable are added by entering a benchmark, and among the independent variables already in the equation, variables with low correlations with the dependent variable are removed by removing the benchmark. If no further variables are added or removed during this process, the selection of independent variables ends, and the model based on the stepwise selection method is finally completed.

[0060] In other words, a method of using the so-called hypothesis test to determine whether the hypothesis about the population is statistically correct. The significance level is generally set to 0.05 (5%), and the p-value (p-value) as the probability of significance is calculated. When the p-value is less than 0.05, the null hypothesis is rejected and the alternative hypothesis is adopted. By performing hypothesis testing on the selected variables, the process of adopting newly added variables or removing existing variables is repeated. Ultimately, when there are no new variables to be added or removed, the stepwise selection process ends. After the stepwise selection is successful, the molecular descriptor information obtained will perform a more advanced search, and a model with reliable accuracy will be obtained after the statistical test is passed, as shown below:

[0061]

[0062] Where P represents the molecular descriptor after stepwise selection, Y is the property to be predicted, and C is the parameter estimated from the experimental data by the multivariate regression method.

[0063] Preferably, the least square residual is used to estimate the parameter C. The specific calculation process is as follows:

[0064]

[0065] Where n is the number of substances to be predicted and Pn is the number of optimal molecular descriptors.

[0066] Once the best multiple linear regression model is selected, the rationality of the model is determined in the sixth step, which is the next step. Specifically, the rationality of the model can be tested using the t-test method, and the calculation process is as follows:

[0067]

[0068] If the t-test value for a molecular descriptor included in the model is found to be poor according to the above method, the process returns to the previous step and searches for another model. For example, if the number of sample compounds is 1005 and the selected model consists of five molecular descriptors, if the t-test value for one molecular descriptor is 3.3 or higher, the probability that the molecular descriptor is unrelated to the corresponding physical property is less than 0.1%.

[0069] In the present invention, when there is a molecular descriptor with a t-test value less than about 3, the selected model is discarded and other models are sought. In addition, the situation that the value of a molecular descriptor for the sample compound is the same except for a few compounds cannot be regarded as a model with reliability, so measures are also taken. Usually, if the number of molecular descriptors included in the model is increased, the prediction performance will improve, but the above-mentioned problems will occur. Therefore, usually, the final model is obtained by repeatedly performing these steps by changing the number of molecular descriptors and through multiple trial and error. If the selected model no longer has problems, then proceed to the next step.

[0070] Next, in the seventh step, the prediction performance of the found model is evaluated using a test set that does not participate in forming the model.

[0071] If significant performance degradation or significant deviations are observed in the training set, the training and test sets are readjusted in step 4 before proceeding to the subsequent steps. If the difference between the training and test sets does not exceed 20% of the mean absolute error (AAE) obtained for the training set, the prediction performance is considered satisfactory and a multiple linear regression model for standard boiling point is established.

[0072] The results of the models finally established through this process are briefly shown in Tables 1 to 3 below.

[0073] Table 1

[0074] Main contents of the QSPR prediction model for the standard boiling points of hydrocarbon compounds

[0075]

[0076]

[0077]

[0078] Table 2 Main contents of the QSPR prediction model for the standard boiling points of non-hydrocarbon compounds

[0079]

[0080]

[0081]

[0082]

[0083]

[0084] Table 3 Main contents of the QSPR prediction model for the standard boiling points of non-hydrocarbon type II compounds

[0085]

[0086]

[0087]

[0088]

[0089] Example

[0090] This example is used to further illustrate the accuracy of the present invention in predicting the normal boiling point of pure compounds, but the present invention is not limited thereto.

[0091] Table 4 below shows some results of predicting the normal boiling points of pure compounds using the model of the present invention:

[0092] Table 4

[0093]

[0094]

[0095]

[0096] To confirm the excellence of the present invention, the multiple linear regression model of the present invention was used to predict the standard boiling points of 4946 compounds with known experimental values, and a coefficient of determination value of 0.9836 and a mean absolute error value of 7.8548K were obtained, indicating that the prediction performance is excellent.

[0097] Figure 2 This is a scatter plot showing the predictive performance of a multiple linear regression model. It evaluates how closely experimental values ​​are aligned with predicted values. The X-axis represents the experimental values, and the Y-axis represents the predicted values. The experimental and predicted values ​​are plotted at the (X, Y) coordinates with dots (hollow blue circles), and the baseline representing Y=X is marked with a diagonal line (solid red line).

[0098] Points located on the baseline indicate that the predicted value is the same as the experimental value. Points located below the baseline indicate that the predicted value is smaller than the experimental value. Points located above the baseline indicate that the predicted value is larger than the experimental value. For example, if the experimental and predicted values ​​are (100, 100), they are on the baseline; if the experimental and predicted values ​​are (100, 90), they are below the baseline; and if the experimental and predicted values ​​are (100, 10), they are above the baseline.

[0099] exist Figure 2In the parity plot, we can observe that there are some points that are relatively separated from the baseline in the middle. However, in most areas, the points are concentrated on the baseline. The points are distributed on the baseline in a spindle shape and spread thinner upward and downward rather than widely. Therefore, the predicted value can be said to be close to the experimental value as a whole.

[0100] In addition, in the experimental data of 4946 compounds, the average error of the known experimental error is about 3.55%, Figure 3 The error between the experimental and predicted values ​​is plotted in a bar graph centered around this value. In this graph, the multiple linear regression model predicts normal boiling point values ​​within the average experimental error with 85.5% probability, demonstrating its high predictive performance.

[0101] The present invention is not limited to the above-mentioned embodiments. Without departing from the gist of the invention claimed for protection in the claims, anyone with general knowledge in the technical field to which the present invention belongs can make various modified implementations, and the above-mentioned changes fall within the scope of the claims.

Claims

1. A method for predicting the normal boiling point of a pure compound using a multiple linear regression model, comprising the following steps: (1) Input the collected experimental data of the sample compound; (2) preparing a molecular descriptor for the sample compound input above; (3) screening the best molecular descriptors from step (2); (4) separating the experimental data in step (1) into a training set and a test set; (5) constructing an optimal multiple linear regression model that matches the training set using the molecular descriptors described in step (3); (6) Determine the rationality of the above multiple linear regression model; (7) If the multiple linear regression model is not reasonable in step (6), repeat steps (5) and (6). If it is reasonable, test the prediction performance of the model using the test set; (8) In the test of step (7), if the performance does not meet the standard, steps (4) to (7) are repeated; if the standard is met, the predicted value of the standard boiling point obtained using the multiple linear regression model is used as the actual value of the standard boiling point.

2. The method according to claim 1, wherein The sample compound in step (1) is a pure compound composed of one or more elements selected from the group consisting of hydrogen, carbon, nitrogen, oxygen, sulfur, fluorine, chlorine, bromine, iodine, silicon, phosphorus, and arsenic.

3. The method according to claim 2, wherein: The sample compound in step (1) is one of the following: a. Hydrocarbon compounds containing carbon and hydrogen elements; b. Non-hydrocarbon compounds containing one or more of carbon, hydrogen, nitrogen, oxygen and sulfur; c. Non-hydrocarbon compounds containing one or more of carbon, hydrogen, fluorine, chlorine, bromine, iodine, silicon, phosphorus, and arsenic.

4. The method according to any one of claims 1 to 3, wherein The step (2) of preparing molecular descriptors refers to preparing molecular descriptors related to the standard boiling point.

5. The method according to any one of claims 1 to 3, wherein The optimal molecular descriptor in step (3) includes one or more of the following: P1: hyper-Wiener-like index from the chi matrix, which is a logarithmic function; P2: eta x shape index; P3: topological charge index of order 2; P4: number of quaternary carbon atoms in the sp3 hybridized ring; P5: eigenvalue n.3 of the enhanced edge adjacency matrix from dipole moment weighting; P6: pyridazine number; P7: hydrophilic factor; P8: number of urea derivatives or thiourea derivatives; P9: N number in hydrazine; P 10 : imide or thioimide number; P 11 : number of aromatic bonds; P 12 : Narumi harmonic topology index; P 13 : Maximum negative change in electronic topology; P 14 : 5th order autoregressive path counting; P 15 : Molecular multipath counting of order 1.

6. The method according to claim 5, wherein: The optimal molecular descriptor in step (3) is an independent molecular descriptor having different values ​​for all sample compounds.

7. The method according to any one of claims 1 to 3, wherein In step (4), the training set and the test set are divided in a ratio of 5-8:2-5.

8. The method according to any one of claims 1 to 3, wherein The step (5) of finding the best multiple linear regression model of the training set is to apply a stepwise selection method to the training set to construct a multiple linear regression model.

9. The method according to claim 8, wherein The optimal multiple linear regression model in step (5) is found by judging the prediction performance by the coefficient of determination or mean absolute error of the regression model.

10. The method according to any one of claims 1 to 3, wherein The rationality of step (6) is determined by the t-test value, wherein the model is rational when the t-test value is greater than or equal to 3, otherwise it is not rational.

11. The method according to any one of claims 1 to 3, wherein The test in step (7) is to test the multiple linear regression model using the test set.

12. The method according to any one of claims 1 to 3, wherein The satisfaction standard in step (8) is achieved by comparing the difference between the training set and the test set. If the difference between the training set and the test set does not exceed 20% of the mean absolute error obtained for the training set, it is judged that the performance meets the standard; otherwise, the performance does not meet the standard.

Images