著者

Norihito Kawashita Hiroyuki Yamasaki Tomoyuki Miyao Kentaro Kawai Yoshitake Sakae Takeshi Ishikawa Kenichi Mori Shinya Nakamura Hiromasa Kaneko

出版者

公益社団法人 日本化学会・情報化学部会

雑誌

Journal of Computer Aided Chemistry (ISSN:13458647)

巻号頁・発行日

vol.16, pp.15-29, 2015 (Released:2015-10-29)

参考文献数

192

被引用文献数

3 6

---

We have reviewed chemoinformatics approaches for drug discovery such as aromatic interactions, aromatic clusters, structure generation, virtual screening, de novo design, evolutionary algorithm, inverse-QSPR/QSAR, Monte Carlo, molecular dynamics, fragment molecular orbital method and matched molecular pair analysis from the viewpoint of young researchers. We intend to introduce various fields of chemoinformatics for non-expert researchers. The structure of this review is given as follows: 1. Introduction, 2. Analysis of Aromatic Interactions, 2.1 Aromatic Interactions, 2.2 Aromatic Clusters, 3. Ligand Based Structure Generation, 3.1 Virtual Screening, 3.2 De Novo Ligand Design, 3.3 Combinatorial Explosion, 3.4 Inverse-QSPR/QSAR, 4. Trends in Chemoinformatics-Based De Novo Drug Design, 5. Conformational Search Method Using Genetic Crossover for Bimolecular Systems, 6. Interaction Analysis using Fragment Molecular Orbital Method for Drug Discovery, 7. Matched Molecular Pair Analysis and SAR Analysis by Fragment Molecular Orbital Method, 8. Chemoinformatics Approach in Pharmaceutical Processes, 9. Conclusion.

著者

Hiromasa Kaneko Kimito Funatsu

出版者

The Society of Chemical Engineers, Japan

雑誌

JOURNAL OF CHEMICAL ENGINEERING OF JAPAN (ISSN:00219592)

巻号頁・発行日

vol.50, no.6, pp.422-429, 2017-06-20 (Released:2017-06-20)

参考文献数

18

被引用文献数

1 2

---

Multivariate statistical process control (MSPC) is important for monitoring multiple process variables and their relationships while controlling chemical and industrial plants efficiently and stably. Although many MSPC methods have been developed to improve the accuracy of fault detection, noise in the operating data, such as measurement noise and sensor noise, conceals important variations in process variables. This noise makes it difficult to recognize process states, but has not been fully considered in traditional MSPC methods. In this study, to improve the process state recognition performance, we apply several smoothing methods to each process variable. The best smoothing method and its hyperparameters are selected based on the normal distribution and variation of the reduced noise. Through case studies using numerical data and dynamic simulation data from a virtual plant, it is confirmed that the fault detection and identification accuracy are improved using the proposed method, which leads to enhanced state recognition performance.

著者

Naoto SHIMIZU Hiromasa KANEKO

出版者

Society of Computer Chemistry, Japan

雑誌

Journal of Computer Chemistry, Japan (ISSN:13471767)

巻号頁・発行日

pp.2020-0021, (Released:2021-08-14)

参考文献数

31

被引用文献数

5

---

Models for predicting properties/activities of materials based on machine learning can lead to the discovery of new mechanisms underlying properties/activities of materials. However, methods for constructing models that exhibit both high prediction accuracy and interpretability remain a work in progress because the prediction accuracy and interpretability exhibit a trade-off relationship. In this study, we propose a new model-construction method that combines decision tree (DT) with random forests (RF); which we therefore call DT-RF. In DT-RF, the datasets to be analyzed are divided by a DT model, and RF models are constructed for each subdataset. This enables global interpretation of the data based on the DT model, while the RT models improve the prediction accuracy and enable local interpretations. Case studies were performed using three datasets, namely, those containing data on the boiling point of compounds, their water solubility, and the transition temperature of inorganic superconductors. We examined the proposed method in terms of its validity, prediction accuracy, and interpretability.