Molecular Design of Novel Herbicide and Insecticide Seed Compounds with Machine Learning.

Pesticides are widely used to improve crop productivity by eliminating weeds and pests. Conventional pesticide development involves synthesizing compounds, testing their activities, and studying their effects on the ecosystem. However, as pesticide discovery has an extremely low success rate, many compounds must be synthesized and tested. To overcome the high human, financial, and time costs of this process, machine learning is attracting increasing attention. In this study, we used machine learning for the molecular design of novel seed compounds for herbicides and insecticides. Classification models were constructed by using compounds that had been tested as herbicides and insecticides, and an inverse analysis of the constructed models was conducted. In the molecular design of herbicides, we proposed 186 new samples as herbicides using ensemble learning and a method for expressing explanatory variables that consider the relationships among eight weed species. For the molecular design of insecticides, we used undersampling and ensemble learning for the analysis of unbalanced data. Based on approximately 340,000 compounds, 12 potential insecticides were proposed, of which 2 exhibited actual activity when tested. These results demonstrate the potential of the developed machine-learning method for rapidly identifying novel herbicides and insecticides.

Preparation and CO(2) adsorption properties of aminopropyl-functionalized mesoporous silica microspheres.

Aminopropyl-functionalized mesoporous silica microspheres (AF-MSM) were synthesized by a simple one-step modified Stöber method. Dodecylamine (DDA) was used as the catalyst for the hydrolysis and condensation of the silica source and as the molecular template to prepare the ordered mesopores. The mesoporous silica surfaces were modified to aminopropyl groups by the co-condensation of tetraethoxysilane (TEOS) with 3-aminopropyltriethoxysilane (APTES), up to a maximum of 20mol.% APTES content in the silica source. The particle size, Brunauer-Emmet-Teller (BET) specific surface area, and mesoporous regularity decreased with increasing APTES content. It is believed that this result is caused by a decreasing amount of DDA incorporated into AF-MSM with increasing APTES content. It was also confirmed that the spherical shape and the mesostructure were maintained even if 20mol.% of APTES was added to the silica source. Moreover, AF-MSM was applied to the CO(2) adsorbent. The breakthrough time of the CO(2) and CO(2) adsorption capacities increased with increasing APTES content. The adsorption capacity of CO(2) for AF-MSM, prepared at 20mol.% APTES, was 0.54mmolg(-1). Carbon dioxide adsorbed onto AF-MSM was completely desorbed by heating in a N(2) purge at 423K for 30min.