KR20120085136A - Multiple linear regression-artificial neural network model predicting ideal gas absolute entropy of pure organic compound for normal state - Google Patents

Abstract

PURPOSE: A MLR(Multiple Linear Regression)-ANN(Artificial Neuron Network) model, predicting an ideal gas absolute entropy of a standard state of a pure organic compound, is provided to reduce time and cost for an experiment and enable a value to be guessed when the experiment cannot be conducted, thereby vitalizing research and development of a related industry. CONSTITUTION: Experimental data of sample organic compounds is separated into a training set and a test set. An optimum MLRM(Multiple Linear Regression Model) for the training set is explored. The predicted performance of the optimum MLRM is tested on the test set. After an optimum ANNM(Artificial Neural Network Model) divides every samples into three sets, it is explored. If the absolute value of the difference of an ideal gas absolute entropy prediction value of a standard state, figured out by the MLRM and the ANNM, is greater than an over- suitability preventing standard value, the ideal gas absolute entropy prediction value of the standard state by the MLRM is selected as an ideal gas absolute entropy value of the standard state.

Description

Multiple Linear Regression? Artificial Neural Network Model Predicting Ideal Gas Absolute Entropy of Pure Organic Compound for Normal State

The present invention belongs to a field of physical chemistry called physical property prediction and relates to a method for predicting with high accuracy an absolute gas entropy of a standard state, which is one of several physical properties of an organic compound.

Knowing the exact values of the various properties of an organic compound in detail can be used to determine the feasibility of the use of the substance, to design the synthesis and purification processes, and to establish methods and conditions for storage, transport, use, and disposal. It is an important issue both industrially and academically because it is critical to all decision-making processes throughout the process. The most accurate way of knowing the value of the property of interest of an organic compound of interest is also an experiment, but it is true that it is quite costly and time consuming in many aspects, including the preparation of purified samples and the construction of an environment for accurate measurement. Therefore, it may not be possible. Therefore, as an alternative, many researchers have long tried to predict the exact value of various physical properties of organic compounds. As such, property prediction has a long history, and new prediction methods are constantly appearing. At present, several prediction models with different accuracy and scope of application coexist.

Several prediction models have been proposed to date for absolute gas entropy of standard state, which is the property of interest of the present invention. Standard State Absolute Entropy of Ideal Gas is the absolute gas absolute entropy when a pure substance is in standard state, ie 298.15K (absolute temperature) and 1 bar. The results of previous studies on the prediction of absolute gas entropy at standard state are described in Polling B. E., Prausnitz J. M., O'Connell J. P. The Properties of Gases and Liquids, (5 ed.). New York: McGraw Hill. (2000). The well-known and widely used models for predicting the absolute entropy of ideal gas at present are mainly based on quantum mechanical calculation or group contribution method. Quantum mechanics calculations are more accurate when performing higher-level calculations, but they require more time and resources to perform the higher-level calculations. Therefore, low-level quantum mechanical calculations are used a lot. Low-level quantum mechanical calculations can save time and resources required for the calculation, but have low accuracy.

One other method that can be an alternative to quantum mechanics in constructing prediction models is the group contribution method. Table 1 below shows the major group contribution models for the ideal state absolute gas entropy prediction methods that have been proposed in chronological order. A typical form of group contribution model is given by

year proponent 1968 Benson 1969 Benson & Buss 1971 Thinh, T.-P. & T. K. Trong 1984 Joback 1994 Constantinou & Gani 1994 Domalski 1998 Benson

In order to obtain the property value Y, first, the molecule of the compound whose value is to be determined is divided according to a plurality of predetermined fragment types, and the number n _i of each fragment type is obtained. The sum of this multiplied by the coefficient a _i assigned to the format is the predicted value Y. The coefficients a ₀ , a _i are determined by statistical methods to give the model the best performance from the compounds with experimental values.

These group contribution methods have been somewhat successful in the past, but lack the theoretical basis, and sometimes the only way to split them into pieces is not, or even nonexistent, which makes the calculation of values impossible. Also, as the model is improved to improve the predictive performance, it becomes more complicated and difficult to handle.

One alternative that can be an alternative to the group contribution method in constructing a predictive model of a compound is the QSPR (quantitative structure-property relationship) method. This method basically starts with the assumption that the properties of a compound are a function of the structural properties of the molecule and uses various molecular descriptors that reflect different structural properties. The number of molecular descriptors proposed to date has been thousands, and many kinds of molecular descriptors range from simple ones such as the number of carbons or hydrogens in a molecule to complex ones such as the shape, connection state, and electrochemical properties of molecules. Calculation methods 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 some of these molecular descriptors and sometimes, in addition, some of the other physicochemical properties of the compound, which are also functions of structural properties.

At this time, the most frequently adopted form of this function is the linear combination function of the following expressions X _i and each coefficient c ₀ , c _{i is} mainly determined from the experimental data through multiple linear regression analysis.

Another way to create a QSPR model is to use an artificial neural network. Artificial neural network technique is one of the long-time research results of human beings who want to make intelligent machines by modeling human nerve cells with intelligence, and is an information processing technology that has been applied in various fields since it appeared in the middle of the 20th century. . 2 shows a typical example of an artificial neural network. As can be seen, the artificial neural network has an input layer for receiving input data, an output layer for producing output data, and a hidden layer located between them, each layer having one or more nodes. ) Each node in the hidden layer are connected with the input layer and the output layer nodes, each of the connection has been given a weight (weight), it called the amount w _ij, a _ij w'. Each node in the hidden layer and output layer are to make the output value by processing them after being input via this connection from the node of the previous step is applied wherein the active function (activation function) called the function f _1, f _2. In order to actually use such an artificial neural network, first, the neural network is trained using a sample set in which various input values and output values corresponding to the input values are bundled together. This means optimizing the weight of each connection using a back propagation algorithm to minimize the difference. The neural network that has undergone such training does not provide the necessary rules or knowledge to solve the problem, but it establishes general rules through learning and gives valid output for unknown inputs. It is widely used as a very useful means in the field.

To date, many QSPR prediction models for predicting absolute gas phase entropy of a normal state using artificial neural networks have not been proposed, and the proposed ones also have disadvantages in that the number of sample compounds is not large or the application targets are limited to a specific series of compounds. Some of them are described in A. Fazeli et al. Prediction of absolute entropy of ideal gas at 298 K of pure chemicals through GAMLR and FFNN. Energy Conversion and Management, 52 (2011) 630-634, presents models and results.

The technical problem to be solved by the present invention is to overcome the shortcomings of the existing models mentioned above and to show more wide and accurate prediction performance, hydrogen (H), carbon (C), nitrogen (N), oxygen (O), sulfur (S). QSPR model for the absolute state entropy of ideal gas ideal state of pure organic compound composed of less than 5 elements and 25 or less atoms except hydrogen.

We have achieved this goal by constructing a multiple linear regression-artificial neural network hybrid model that considers a wider variety of molecular presenters based on more experimental data on the basis of quantum mechanical calculations of the absolute state entropy of the ideal gas. In particular, the neural network has the advantage of reflecting the nonlinear functional relationship between independent and dependent variables, which cannot be reflected by the multiple linear regression model, so that a model with higher predictive performance can be realized. However, the artificial neural network has a disadvantage in that its stability is lower than that of the multiple linear regression model due to its high degree of freedom in rule setting. In the present invention, when the prediction value of the artificial neural network model and the prediction value of the multiple linear regression model show a large difference, the method of adopting the prediction value of the multiple linear regression model compensates for these shortcomings. We established an excellent prediction model that takes advantage of the neural network model.

The above-mentioned limitations on the range of organic compounds to which the predictive model can be applied are mainly due to the current state of the art when some of the molecular descriptors used require quantum mechanical calculations. This is due to the fact that for the compounds beyond the stated range, problems arise in terms of accuracy and calculation time. However, even within the above limitations, since there are a great many compounds and industrially important compounds are included in a large amount, it is determined that the present invention can greatly benefit human society.

Humans today depend on a wide variety of organic compounds, including plastics, fibers, rubber, paints, fertilizers, medicines and fuels, and this trend is expected to intensify. According to the American Chemical Society (ACS), as of July 2010, the total number of compounds registered was over 54,000,000. In comparison, even if the physical property value is only one, the number of experimentally known compounds is only tens of thousands. The physical property value of compounds is essential for the better life of mankind, such as the development of new materials and new drugs, the optimal design of chemical plants, the improvement of the productivity of existing facilities, the development and saving of resources, the securing of safety, and the protection of the environment. Absolute entropy of standard gas abnormalities is a property that commercial programs such as AspenPlus and Pro / II, which are well known as the optimum design program for chemical plants, are urgently requesting the exact values. However, at present, the number of compounds whose experimental values are known is only a few thousand, and depending on the compounds, the work of obtaining data through experiments may be past due to toxicity, instability, and difficulty of purification. From this point of view, the present invention, which obtains the absolute value of absolute entropy of a standard state abnormal gas of a large number of compounds without any experiment, not only saves the cost and time required for the experiment, but also the value even when the experiment is impossible. It makes it possible to make researches and development activities of related industries easier, and furthermore, to provide appropriate information to all places that need such values, such as academia and academia, to make the activities more smoothly. Will give birth.

1 is a flowchart illustrating a process of constructing a multiple linear regression-artificial neural network hybrid model for the ideal gas absolute entropy of the standard state provided by the present invention.
Figure 2 is a view showing the structure of the artificial neural network used in the present invention.
FIG. 3 is a parity diagram of 1269 experimental data calculated by density functional theory, which is a quantum mechanical calculation model of absolute gas entropy of an ideal gas.
4 is a parity diagram of 1269 experimental data of a multiple linear regression-artificial neural network model for the ideal gas absolute entropy of the standard state provided by the present invention.
FIG. 5 is a histogram diagram of 1269 experimental data calculated by the density functional theory, a quantum mechanical calculation model.
FIG. 6 is a histogram plot of 1269 experimental data of a multiple linear regression-artificial neural network hybrid model.

FIG. 1 is a simplified flowchart illustrating a process of constructing a multiple linear regression-artificial neural network hybrid model for absolute gas entropy of a standard state.

The first thing to do when building the model is to collect and review the experimental data as specified in step 1. As a result of extensive research on all literatures and data that can be referred to through various papers, books, and Internet sites for the present invention, the absolute gas entropy of the standard state for a total of 2540 compounds meeting the conditions of the present invention. Data was collected. The collected data were examined in a variety of ways to determine whether they were truly valid values that could be used to build the model.They were not experimental values, errors in data notation, or values for the same compound. After carefully analyzing data such as unreliably distant values or values for molecular descriptors that are difficult to prepare immediately, data were modified or deleted to finally select data for a total of 1312 compounds. . In the present invention, the 'organic compound' or 'compound' is composed of five elements such as hydrogen (H), carbon (C), nitrogen (N), oxygen (O), and sulfur (S), and atoms except hydrogen Refers to a substance consisting of molecules of 25 or less.

The next step is to prepare the values of the molecular descriptors for these compounds. The values for various molecular descriptors totaling up to 1978 are computed in batches using a computer from files containing information on the molecules of each compound. In order to calculate the electronic structure of molecules, the Schrodinger equation is usually solved by a pure theory to solve the electron energy. However, in the case of systems with many electrons, Hartley uses an approximation method that ignores electron correlation. Hartree-Fock (HF) method [CCJ Roothan, Rev. Mod. Phys. , 23, 69 (1951)]. This approximation introduces a fundamental error in the calculated results and adds a multidimensional theoretical perturbation term to the Post Hartree-Fock method [C. Moller and MS Plesset, Phys. Rev. 46, 618 (1934)], to obtain a more accurate solution, but require a relatively large amount of computation. In this way, it is too costly or time-consuming to calculate large molecules.

See also the Gaussian method combining Hartley-Fork and Post Hartley-Fork [LA Curtiss, K. Raghavachari, GW Trucks, and JA Pople, J., Chem. Phys. 94, 7221 (1991); LA Curtiss, K. Raghavachari, PC Redfern, V. Rassolov, and JA Pople, J. Chem. Phys ., 109, 7764 (1998) show very little error in energy prediction, but more calculations are required because they perform energy calculations for several post-Hartley-Fork methods.

Density functional theory is used to find the ground state using the function of the total energy using the electron density function instead of the wave function with the multidimensional perturbation term to consider the correlation between the electrons of the molecules of many electrons. R. Seeger and JA Pople, J. Chem. Phys . 66, 3045 (1977). The advantage of the density functional theory is that the electron density only needs to be taken into account so that more accurate results can be obtained with comparable calculations to the Hartree-Fock method. The combination of exchange functions and correlation functions for calculating the exchange-correlation energy of the electrons is used to obtain more improved results without increasing the calculation amount.

The computational theories previously attempted to select an optimal quantum mechanical calculation method are the density ranges of the aforementioned Hartley-Fork method, various Post-Hartley-Fork methods, Gaussian (G2, G3) methods, and various combinations of functional functions. Function theory. Among them, one method of density functional theory, which is the best performance calculation time, was selected.

Therefore, in the present invention, the optimization of the molecular structure and the frequency calculation are performed by applying the calculation method of the specified density functional theory using a commercial quantum mechanical calculation program.

In the optimized structure, molecular descriptors represented by various meaningful values reflecting the properties of molecules as well as the above-described physical property information can be obtained. Some molecular presenters can express the features of two-dimensional structures, while others present the features of three-dimensional structures. Divided into 24 categories, including detailed presenters in each category. After calculating the molecular descriptor values, we picked out those that were not suitable, that is, the values were the same for all sample compounds and could not be independent variables in the model. This is because it prevents irrelevant molecular expressions from being included in the prediction model, thereby increasing the reliability of the model and reducing the computation time required to find the optimal model by reducing the number of molecular expressions.

In step 4, the sample compounds are divided into two parts: the training set used to explore the predictive model, and the test set used to test the predicted performance of the determined model. The samples were divided in a ratio of 5: 5 to 8: 2, preferably 6 to 4, taking care not to distribute similar molecules on one side only.

이며 이들을 다 조사하는 것은 현실적으로 불가능하다.We then find the best multiple linear regression model based on the training set. The term 'best' is used in the sense of relative meaning that it can be obtained in a relatively short time and has a performance very close to the optimal solution in the absolute sense. The reason for not finding the optimal solution directly is because of the long computation time. For example, when there are 1700 suitable molecular representations out of 1978 molecular representations, you can choose from five different linear regression models. The total number is

It is practically impossible to investigate them all.

In order to obtain useful results within a limited time, the present invention uses a genetic algorithm [Judson, "Genetic Algorithms and Their Uses in Chemistry", Reviews in Computational Chemistry, Lipkowitz & Boyd, Eds., Vol. 10, pp. 1 -73 (VCH Publishers, NY, 1997)]. First, a population of multiple linear regression models is created by randomly drawing a certain number of molecular descriptors from a pool of molecular descriptors. For example, let's say we created a population of 1000 different polylinear regression models that were randomly drawn from 5 of the 1700 suitable molecular descriptors.

Individuals, called chromosomes, are coded by combining the numbers of extracted molecular descriptors. For example, the chromosome of the multiple linear regression model formed by the 45th, 167, 684, 1033, and 1502th molecular descriptors among 1700 molecular descriptors can be expressed as (45, 167, 684, 1033, 1502). Two parent chromosomes are selected from the populations thus generated and crossed over to generate children. In the present invention, the Roulette Wheel method is adopted as a selection method for selecting the parent chromosomes.

The Roulette Wheel method is the most commonly used selection algorithm, which allocates a roulette region to the chromosome in proportion to the fitness of each chromosome, and then rotates the roulette to select the chromosome of the corresponding region. Therefore, in this method, the higher the fit, the more likely it is to be selected. The coefficient of determination (R ² ) or average absolute error (AAE) of the regression model was used to calculate the fitness of each chromosome to determine the selection probability. In other words, the larger the coefficient of determination or the smaller the mean absolute error, the higher the probability of selection.

The single point crossover method is adopted as the breeding method. The most common breeding method is to generate a child by selecting one crossing point on the parent chromosome and exchanging chromosomal parts before and after the point. For example, if the parent chromosome is given as (24, 262, 343, 789, 1290), (38, 454, 554, 1322, 1449), and there is a crossing point between the third and fourth elements, then the child chromosomes are (24, 262, 343, 1322, 1449), (38, 454, 554, 789, 1290).

When the offspring are created, they have a chance of mutating a portion of their chromosomes, which randomly replaces several elements with completely new values. This new information does not exist in the current population. It is a process that makes it possible to search to compensate for the case where there is no proper solution in the initial set combination.

In this way, a new generation of populations are created by replacing some or all of the existing populations with newly obtained entities. Repeat this process until the number of generations reaches a pre-determined value (usually between 10 and 1000), and then select and end up the regression model with the best predictive performance.

Once this best multiple linear regression model has been selected, the next step is to examine its validity. If a problem is found that the t-test value of the molecular descriptors included in the model is not good, go back and look 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 for one of the molecular descriptors is 3.3 or higher, then the probability that the molecular descriptor is irrelevant to that property is 0.1 It means less than%. In the present invention, when there is a molecular presenter having a t-test value of less than about 3, the selected model is discarded and another model is found. In addition, even if the values of the molecular descriptors for the sample compounds are the same except for a few few compounds, they are not considered to be reliable models. In general, increasing the number of molecular expressions included in the model increases the predictive performance, but such problems occur. Therefore, the final model is usually obtained by repeating these steps through several trials and errors while changing the number of molecular expressions. If the problem no longer appears in the selected model, proceed to the next step.

Next, in Step 7, assess the predictive performance of the found model using test sets that did not participate in model formation. If a problem is found in the training set that results in much lower predictive performance or samples that are significantly off predicted, go to step 4 and readjust the training and test sets before proceeding. If the difference between the training set and the test set does not exceed 20% of the absolute mean error (AAE) obtained for the training set, it is judged that the predictive performance is satisfied.

In this way, once the multiple linear regression model for the normal state absolute gas entropy is established, the first step is to standardize the data of molecular presenters and the experimental data of the normal state absolute gas entropy to establish the artificial neural network model. Subtract the mean of the data from the values and divide by the standard deviation. The entire sample thus prepared is divided into a training set, a validation set, and a test set in an approximately 6: 2: 2 ratio.

와 같이 주어지며 은닉층이 m개의 노드로 이루어져 있을 때 출력층 출력노드의 최종 출력값은

와 같이 주어진다. 여기서 T는 문턱 가중치(threshold weight)를 의미한다.We then use them to find the best artificial neural network model. In this case, the search range is limited to a neural network having a hidden layer between the input layer and the output layer as shown in FIG. 2 and having three structures connected only in a feed forward direction, that is, in a direction from the input to the output. It was. The input layer is composed of the same number of nodes that receive the values of the molecular descriptors included in the already established multiple linear regression model, and the output layer is composed of one node that outputs the critical volume. In addition, the sigmoid function f ₁ (x) = (1 + e ^-x ) ^-1 is adopted as the activation function of the hidden layer, and the linear function f ₂ (x) = x is adopted as the activation function of the output layer. Therefore, the input values received by each node of the input layer are I ₁ , I ₂ ,... , I _l , the output value of the jth node of the hidden layer is

When the hidden layer consists of m nodes, the final output value of the output layer output node is

Is given by Here T denotes a threshold weight.

The search proceeds from increasing the number of hidden nodes to one in order. Usually, the search proceeds to twice the number of input nodes. However, if a satisfactory model is not found, the search proceeds further. The detailed procedure is as follows. First, for each number of hidden nodes, various initial value sets (usually 1000 sets or less) of weights T, w _ij , and w´ _ij generated by using a random number generation function are prepared, and a neural network initialized with each set using a training set. Iteratively trains through the backpropagation algorithm to find the optimized values of the weights T, w _ij , w´ _ij . The judgment of the optimization is that the mean square error is minimized when the model, which is determined by the updated weights after each training, is applied to the test set. Normally this will occur within 3000 to 5000 repetitions. The optimized neural network model corresponding to each set of initial values thus obtained is applied to the training set, the test set, and the test set, respectively, to collect only those whose mean square errors are smaller than those of the multiple linear regression model. If there are several of these, choose the best model based on the coefficient of determination or the absolute absolute error.

When the artificial neural network model is selected, an overfitting prevention standard is finally set. This is a measure to improve the instability that the artificial neural network gives wrong answer to the unknown input as a result of overtraining. When the absolute value of the difference exceeds the reference value, the predictive value of the multiple linear regression model is adopted, and when it is smaller than this, the artificial neural network model is adopted.

The results of establishing the QSPR model for the absolute gas entropy of the standard state through this process are summarized in Table 2.

Main contents of QSPR prediction model for absolute gas entropy of standard state Number of sample compounds 1312 Number of molecular descriptors 6 Names of Molecular Presenters P ₁ : Absolute entropy of ideal gas from quantum mechanics
P ₂ : Total charge weighted partial positive charge surface area fraction weight (WPSA-2 Weighted PPSA (PPSA2 * TMSA / 1000))
P ₃ : XY Shadow / XY Rectangle
P ₄ : Kier & Hall index (order 2)
P ₅ : Topographic electronic index (all bonds)
P ₆ : Maximum net atomic charge for a C atom Regression Model Decision Coefficients 0.993631 Regression Model Mean Absolute Error 2.256084 cal / (mol * K) Regression model

Standard state absolute entropy

Artificial Neural Network Determination Coefficient 0.994454 Artificial neural network mean absolute error 1.89726 cal / (mol * K) Artificial Neural Network Model Standard state absolute entropy

Overconformity Prevention Criteria 5 kcal / (mol * K)

In order to show that the present invention is superior to the existing technology, the data of 1269 compounds in which the multiple linear regression-artificial neural network hybrid model and the conventional quantum mechanical calculation model widely used, that is, the prediction performance by the density functional theory, are experimentally known. Comparison was made using. As a result, it was found that the quantum mechanical model has a coefficient of determination of 0.986307 and an average absolute error of 8.8606cal / (mol * K). On the other hand, the multiple linear regression-artificial neural network hybrid model was found to be superior to the previous model with a coefficient of determination of 0.993523 and an average absolute error of 2.2631cal / (mol * K). 3 and 4 are parity diagrams showing the predictive performance of each model, and it can be seen from these figures that the multilinear regression-artificial neural network hybrid model has better performance than the conventional model. Meanwhile, among the experimental data of 1269 compounds, the average error of the known experimental error is about 3 cal / (mol * K), and the error between the experimental value and the predicted value is drawn as a histogram based on this value. These figures show that the quantum mechanical model predicts the absolute gas entropy of the ideal gas within the range of the mean experimental error with a probability of 32.15% in the quantum mechanical model and 77.28% in the hybrid neural network hybrid model. The neural network hybrid model proves more accurate than the existing model.

The present invention is not limited to the embodiments of the above-described features, and various modifications can be made by those skilled in the art without departing from the gist of the present invention as claimed in the claims. Such changes will fall within the scope of the claims.

Claims (14)

A first step of inputting experimental data of collected sample organic compounds;
Preparing a molecular presenter value for absolute gas entropy of a standard state of sample organic compounds;
Extracting optimal molecular descriptors;
A fourth step of separating the experimental data into a training set and a test set;
A fifth step of searching for an optimal multiple linear regression model for the training set;
A sixth step of examining the validity of the selected model;
A seventh step of repeating the fifth and sixth steps if there is no validity in the sixth step, and testing the predictive performance of the model with respect to the test set if it is valid;
An eighth step of repeating steps 4 to 7 if the performance does not satisfy the criterion in the seventh step test for the test set, and separating the three sets after sample normalization if the criterion is satisfied;
A ninth step of searching for an optimal artificial neural network model after dividing the entire sample into three sets;
The absolute gas absolute entropy prediction value of the standard state obtained by the optimal linear regression model satisfying the performance test in the eighth step and the abnormal gas absolute entropy prediction value of the standard state obtained by the optimal artificial neural network model found in the ninth step A tenth step of comparing the absolute value of the difference with a preset overfit prevention reference value;
When the difference is larger than the overfit prevention reference value, the absolute gas absolute entropy predicted value of the standard state by the multiple linear regression model obtained in step 8 is adopted as the absolute gas absolute entropy value of the standard state. The organic compound is obtained through the multiple linear regression-artificial neural network model including the eleventh step of adopting the absolute gas absolute entropy prediction value of the standard state by the artificial neural network model detected in the ninth step as the absolute gas absolute entropy value of the standard state. How to obtain absolute entropy of ideal gas in standard state.
The method of claim 1, wherein in the third step, the optimal molecular descriptors are independent molecular descriptors whose values are not the same for all the sample compounds. How to find the ideal gas absolute entropy.
2. The absolute gas phase entropy of the normal state of the organic compound through the multiple linear regression-artificial neural network model of claim 1, wherein the training set and the test set are divided in a ratio of 5: 5 to 8: 2. How to obtain.
2. The multiple linear regression-artificial neural network model according to claim 1, wherein in the fifth step, the multiple linear regression model searches for a multiple linear regression model by applying a genetic algorithm to the training set. The absolute entropy of ideal gas of organic compound is calculated through
The method of claim 4, wherein the genetic algorithm generates a population composed of a plurality of multiple linear regression models randomly drawn from a predetermined number of molecular representations in a pool of molecular representations. Making; Encoding each individual by combining the numbers of the extracted molecular presenters; Selecting two parent chromosomes from the created population by the Roulette Wheel method and generating offspring by a single point crossover method; Generating a new population by mutating a portion of the chromosomes of the generated offspring with a certain probability and then replacing a part of the existing population with them to create a new population. How to obtain absolute entropy of ideal gas in standard state.
The method of claim 1, wherein the fifth step is to determine the absolute gas phase entropy of the standard state of the organic compound through the multiple linear regression-artificial neural network model including determining the predictive performance by the coefficient of determination or the mean absolute error of the regression model Way.
The method of claim 1, wherein the ideal gas absolute entropy of the standard state of the organic compound is obtained through a multiple linear regression-artificial neural network model in which the validity in the sixth step is determined by a t-test value.
The method of claim 1, wherein in the eighth step, if the predictive performance of the test set is similar to the predicted performance of the training set, a multiple linear regression model is determined, and the predictive performance of the test set is different from the predicted performance of the training set. Then, the absolute gas entropy of the normal state of the organic compound is obtained through a multiple linear regression-artificial neural network model that reclassifies the training set and the test set.
The method of claim 1, wherein in the ninth step, the search range by the neural network has one hidden layer between the input layer and the output layer and is connected only in a feed forward. Determination of absolute entropy of ideal gas in organic state through neural network model.
10. The method of claim 9, wherein the ideal gas absolute entropy of the organic compound is obtained through a multiple linear regression-artificial neural network model using a sigmoid function as an activation function of the hidden layer.
2. The method of claim 1, wherein in the tenth step, the overfit prevention reference value is 5 kcal / (mol K), and the ideal gas absolute entropy of the standard state of the organic compound is obtained through a multiple linear regression-neural network model.
The method of claim 1, wherein the optimal molecular expression extracted in the third step is
P ₁ : Absolute entropy of ideal gas from quantum mechanics
P ₂ : Total charge weighted partial positive charge surface area fraction weight (WPSA-2 Weighted PPSA (PPSA2 * TMSA / 1000))
P ₃ : XY Shadow / XY Rectangle
P ₄ : Kier & Hall index (order 2)
P ₅ : Topographic electronic index (all bonds)
P ₆ : Maximum net atomic charge for a C atom
Method for obtaining the absolute gas entropy of the ideal state of the organic compound through a multiple linear regression-artificial neural network model comprising a.
In the method of determining absolute gas phase entropy of organic compounds in a standard state using a multiple linear regression-artificial neural network model,
P ₁ : Absolute entropy of ideal gas from quantum mechanics
P ₂ : Total charge weighted partial positive charge surface area fraction weight (WPSA-2 Weighted PPSA (PPSA2 * TMSA / 1000))
P ₃ : XY Shadow / XY Rectangle
P ₄ : Kier & Hall index (order 2)
P ₅ : Topographic electronic index (all bonds)
P ₆ : Maximum net atomic charge for a C atom
Absolute Entropy of Normal Gases of Organic Compounds Using Multiple Linear Regression-Artificial Neural Network Model
A computer-readable storage medium having recorded thereon a program for executing on a computer a method for obtaining an absolute gas entropy of a standard state of an organic compound according to any one of claims 1 to 13.

Images