Ikebata H.,Graduate University for Advanced Studies |
Hongo K.,Japan Advanced Institute of Science and Technology |
Hongo K.,Japan National Institute of Materials Science |
Hongo K.,Japan Science and Technology Agency |
And 5 more authors.
Journal of Computer-Aided Molecular Design | Year: 2017
The aim of computational molecular design is the identification of promising hypothetical molecules with a predefined set of desired properties. We address the issue of accelerating the material discovery with state-of-the-art machine learning techniques. The method involves two different types of prediction; the forward and backward predictions. The objective of the forward prediction is to create a set of machine learning models on various properties of a given molecule. Inverting the trained forward models through Bayes’ law, we derive a posterior distribution for the backward prediction, which is conditioned by a desired property requirement. Exploring high-probability regions of the posterior with a sequential Monte Carlo technique, molecules that exhibit the desired properties can computationally be created. One major difficulty in the computational creation of molecules is the exclusion of the occurrence of chemically unfavorable structures. To circumvent this issue, we derive a chemical language model that acquires commonly occurring patterns of chemical fragments through natural language processing of ASCII strings of existing compounds, which follow the SMILES chemical language notation. In the backward prediction, the trained language model is used to refine chemical strings such that the properties of the resulting structures fall within the desired property region while chemically unfavorable structures are successfully removed. The present method is demonstrated through the design of small organic molecules with the property requirements on HOMO-LUMO gap and internal energy. The R package iqspr is available at the CRAN repository. © 2017 The Author(s)
Fukunaga K.,Mitsubishi Group |
Sakai D.,Mitsubishi Group |
Watanabe K.,Mitsubishi Group |
Nakayama K.,Mitsubishi Group |
And 13 more authors.
Bioorganic and Medicinal Chemistry Letters | Year: 2015
We herein describe the results of further evolution of GSK-3β inhibitors for Alzheimer's disease from our promising compounds with in vivo tau phosphorylation inhibitory activity by oral administration. Introduction of a low alkyl group instead of the phenyl group at the 3-position of the morpholine moiety aiming to improve pharmacokinetic profiles resulted in potent low molecular weight GSK-3β inhibitors with good in vitro pharmacokinetic profiles, which also showed in vivo tau phosphorylation inhibitory activity by oral administration. Effect of the stereochemistry of the alkyl moiety is also discussed using docking models. © 2015 Elsevier Ltd. All rights reserved.