2. Courses & Staff
  3. Courses
  4. Data Driven Chemistry Laboratory

Data Driven Chemistry Laboratory

Staff & Contact

Educational Staff Prof. Yukiharu Uraoka
Prof. Kimito Funatsu
Associate Prof. Tomoyuki Miyao
Assistant Prof. Swarit Jasial
Contact TEL: +81-743-72-5393
URL http://www-dsc.naist.jp/data-driven_chemistry/

Education and Research Activities in the Laboratory

Chemoinformatics is a research area where chemical problems are tackled using tools coming from informatics. The scale of problems varies from representations of a molecule to prediction of products at a chemical plant in the field of chemical engineering. These data can be efficiently and consistently handled with the use of computers, which is the main learning goal of this laboratory. An example topic may involve developing a methodology for affinity prediction using chemical structures. Constructing soft sensors, which are prediction models for unmeasured (or hard-to-measure) plant variables, is another topic required to handle increasing data in computers. Starting from the basics of machine learning, you will learn how to curate chemistry-related data and analyze them in order to obtain useful information.

Research Themes

1.Methodology development for affinity prediction

Virtual screening is a process which selects potential candidate compounds for a specific target from a compound pool. In ligand-based approaches, the principle that similar compounds show similar biological activity holds. This principle, however, is not necessarily true when focusing on ligand-protein binding mechanisms. Methodology development for extracting key information for this phenomenon in ligand-based approaches furthers improvement of virtual screening.

2.Constructing high predictive soft sensor models using limited data sources

Soft sensors are used to predict a property (i.e. yield or concentration of chemicals). Normally, constructing high-predictive soft sensors needs constant model updating and an adequate number of data. On the other hand, obtaining hard-to-measure data costs much (this is why soft sensors are needed in the first place). Reducing measuring frequency for the property but keeping high prediction ability is an important topic in this field.

Recent Research Papers and Achievements

  1. S. Shibayama, H. Kaneko, K. Funatsu, Comput. Chem. Eng. 113, 86-97, 2018
  2. T. Miyao, K. Funatsu, J. Bajorath, F1000Research, 2017, 6 :1285
  3. T. Miyao, H. Kaneko, K. Funatsu, J. Chem. Inf. Model., 2016, 56, 286-299