Solubility is one of the important parameters for designing new compounds. However, it is difficult to get solubility of all candidate compound, so quantitative structure-property relationships (QSPR) is widely used. In this study, we use the deep learning, which is popular in the field of informatics. Deep learning model can represent complex non-linear relationship between the descriptor and the property. To simulate the chemical phenomena, we divided the model in two parts. One is feature extraction part, which converts descriptors into solubility-based information. The other one is interaction representation part, which represents the interaction between the solvent and the solute. The proposed method showed high accuracy. For chemical interpretation, we visualized the intermediate output of the model using Isomap. On the visualization map, the similarity of solubility behavior between structures is expressed as distance. This result is useful in the following cases: searching for an alternative solvent or choosing solvent pairs with different solubility behaviors.
In order to efficiently discover novel materials with desirable properties, it is necessary to develop a method to predict physical properties from only compositional formula. In this study, we constructed a regression model expressing relationship between compositional formula and the physical properties. The composition formula of the inorganic material were converted into descriptors, and were used as explanatory variables. We proposed a total of 387 diverse and general descriptors using the numbers of atomic elements and their parameters such as atomic weight, electronegativity, etc., enabling prediction of various physical properties. As a case study, we built predictive models by random forest regression using our proposed descriptors, and predicted three physical properties, i.e., crystal formation energy, density and refractive index. The obtained R2 values were 0.970, 0.977 and 0.766, respectively. In addition to the successful predictive performance, we were also able to statistically select the descriptors that contributed to the prediction models, and they were reasonable from the viewpoint of chemical knowledge.
In order to explain the strong basicity of guanidine, the concept of Y-aromaticity was proposed. As a typical compound of a Y-aromatic compound, a system in which three methylene of trimethylene methane is replaced by a chain conjugated system composed of n carbon atoms was proposed. The energy spectrum of the π-electron conjugated system of this compound was generally obtained within the Hückel approximation. The magic number of Y-aromatic compounds was determined by setting the conjugated system to a closed shell as a necessary condition for the energy stabilization of the system. The stabilization energies of several typical compounds were determined with the chain conjugated system as the reference system and the effectiveness of the magic number was investigated. The calculation of energy was done within the Hückel approximation. Although the tendency of magic number and energy stabilization did not perfectly agree, when the number of π electron system coincided with the magic number, energy destabilization tended to decrease.