投稿者: 博佐藤

[Published online Journal of Computer Chemistry, Japan -International Edition Vol.10, -, by J-STAGE]
<Title:> A Study of Deep Learning for Quantitative Analysis of Vitamin A in Cattle Blood
<Author(s):> Mizuki SHIBASAKI, Tetsuhito SUZUKI, Moriyuki FUKUSHIMA, Shin-ichi NAGAOKA, Yuichi OGAWA, Naoshi KONDO
<Corresponding author E-Mill:> nagaoka.shinichi.3c(at)kyoto-u.ac.jp
<Abstract:> Deep learning in combination with fluorescence excitation-emission spectroscopy was studied to quantitatively analyze vitamin A (retinol) in cattle blood. The neural network model being obtained with the deep learning predicted the vitamin-A levels with a coefficient of determination (R²) of 0.93 with respect to the experimental values. The combination of the deep learning and fluorescence excitation-emission spectroscopy has a potential to predict the vitamin-A level in the cattle blood accurately, rapidly and inexpensively and to improve production of marbled beef with maintaining cattle health. It could also be applied to quantitative vitamin-A assays of various biological tissues, foods and so on as well as to those of blood samples besides cattle.
<Keywords:> Deep learning, Neural network, Fluorescence excitation-emission spectroscopy, Vitamin A, Retinol, Cattle blood, random forest
<URL:> https://www.jstage.jst.go.jp/article/jccjie/10/0/10_2024-0012/_html

[Published online Journal of Computer Chemistry, Japan -International Edition Vol.10, -, by J-STAGE]
<Title:> Development of a Simultaneous Quantification for Hydrogen and Ammonia Using Deep Neural Network and The Rotating Ring Disk Electrode Method
<Author(s):> Yusuke HIRUMA, Hyunho KANG, Hidenobu SHIROISHI
<Corresponding author E-Mill:> h-shiroishi(at)tokyo-ct.ac.jp
<Abstract:> Ammonia is considered as a viable candidate for a hydrogen carrier in a hydrogen-based society. Currently, real-time analysis of products in the development of highly active ammonia electrolytic synthesis catalysts is limited to the extremely expensive technique of electrochemical mass spectrometry. In this study, we aimed to develop a real-time simultaneous quantification method for hydrogen and ammonia concentrations using the rotating ring-disk electrode technique. We adopted deep neural network-based machine learning technology using the data from cyclic voltammogram (CV) measurements on a Pt ring electrode. The sum of squared residuals decreased to 1/0.645 at hydrogen partial pressure and 1/92.8 at ammonia concentration compared to the conventional combination of nonlinear least-squares method and solving simultaneous equations. Moreover, classifying concentrations through image recognition based on the obtained CV images resulted in successful concentration determination with an accuracy of 78.9%.
<Keywords:> Nitrogen reduction, Rotating ring disk, Real-time, Quantitative analysis, Deep neural network
<URL:> https://www.jstage.jst.go.jp/article/jccjie/10/0/10_2024-0011/_html

[Published online Journal of Computer Chemistry, Japan Vol.23, 80-83, by J-STAGE]
<Title:> 分子軌道エネルギーを説明変数とした機械学習による薬効予測
<Author(s):> 寺前　裕之, 三浦　優太, 色摩　光一, 玄　美燕, 高山　淳, 岡﨑　真理, 坂本　武史
<Corresponding author E-Mill:> teramae(at)gmail.com
<Abstract:> We constructed a mathematical model to predict the 2,2-diphenyl-1-picrylhydrazyl (DPPH) free radical scavenging capacity (IC₅₀) for recently synthesized ferulic acid derivatives by machine learning with molecular orbital energy as an explanatory variable and IC₅₀ as an objective variable. We compared 96 regression models including xgbLinear and neuralnet included in R/caret package. We were able to construct IC₅₀ prediction models for these new ferulic acids by using xgbLinear, M5, ppr, and neuralnet as regression methods.
<Keywords:> DPPH free radical scavenging capacity, pharmalogical activity, ferulic acid, IC50, machine learning
<URL:> https://www.jstage.jst.go.jp/article/jccj/23/3/23_2024-0020/_article/-char/ja/

[Published online Journal of Computer Chemistry, Japan Vol.23, 78-79, by J-STAGE]
<Title:> BZ反応を利用した物理レザバー計算による時系列予測および音声認識
<Author(s):> 都城　宏治, 香取　勇一, 田中　吉太郎, 髙木　清二, 櫻沢　繁
<Corresponding author E-Mill:> sakura(at)fun.ac.jp
<Abstract:> It is known that it is possible to develop a chemically intelligent robot that can perceive spatial extent using the BZ reaction. If the BZ reaction can be used for learning, there is a possibility of developing a chemically intelligent robot that can make complex judgments about situations like living organisms. In the physical reservoir calculation, it is possible to construct a learning system using a material system, so in this study, we build a physical reservoir calculation using the BZ reaction and confirmed that learning is possible. The physical reservoir computation was capable of performing tasks such as time series prediction and speech recognition. BZ reaction, nonlinear chemical reaction, reservoir computing, time series prediction, speech recognition
<Keywords:> キーワードBZ反応, 非線形化学反応, レザバー計算, 時系列予測, 音声認識
<URL:> https://www.jstage.jst.go.jp/article/jccj/23/3/23_2024-0024/_article/-char/ja/

[Published online Journal of Computer Chemistry, Japan Vol.23, 92-104, by J-STAGE]
<Title:> ABINIT-MPプログラムの現状と今後
<Author(s):> 望月　祐志, 中野　達也, 坂倉　耕太, 土居　英男, 奥脇　弘次, 加藤　季広, 滝沢　寛之, 大島　聡史, 星野　哲也, 片桐　孝洋
<Corresponding author E-Mill:> fullmoon(at)rikkyo.ac.jp
<Abstract:> The fragment molecular orbital (FMO) program ABINIT-MP has a quarter-century history, and related research and development of the Open Version 2 series is currently underway. This paper first summarizes the current status of the latest Revision 8 (released on August 2023). It then describes future improvements and enhancements, including GPU support. The connection with coarse-grained simulation (dissipative particle dynamics) and the possibility of cooperation with quantum computation are also touched upon.
<Keywords:>
<URL:> https://www.jstage.jst.go.jp/article/jccj/23/4/23_2024-0022/_article/-char/ja/

[Published online Journal of Computer Chemistry, Japan Vol.23, 85-91, by J-STAGE]
<Title:> フラグメント分子軌道法で生成したデータを用いた機械学習モデルの開発
<Author(s):> 加藤　幸一郎, 松本　大夢, 喜多　亮介
<Corresponding author E-Mill:> kato.koichiro.957(at)m.kyushu-u.ac.jp
<Abstract:> フラグメント分子軌道(FMO)法はタンパク質全体を量子化学計算可能な稀有な手法である．そして，FMO法によって得られるデータもまた，現状ではタンパク質系の量子化学計算データとして唯一無二のものとなっている．汎用ソフトウェアでは生成が困難なタンパク質の量子化学計算データとそれを用いた様々な機械学習モデルの開発は，近年活性化が著しいAI創薬に大きなインパクトを与えることが期待される．本稿では，筆者らのグループで進めているFMOデータを用いた機械学習モデル(原子電荷予測モデル，相互作用予測モデル，機械学習力場)の開発状況を概説する．
<Keywords:> Keyword Fragment Molecular Orbital Method, Machine Learning Force Field, Inter Fragment Interaction Energy, Atomic Charge, Neural Network
<URL:> https://www.jstage.jst.go.jp/article/jccj/23/4/23_2024-0015/_article/-char/ja/

[Published online Journal of Computer Chemistry, Japan Vol.23, 71-74, by J-STAGE]
<Title:> 分子動力学計算を用いたNa₂O-K₂O-SiO₂系ガラスにおける混合アルカリ効果の再現
<Author(s):> 吉本　直樹, 澤口　直哉
<Corresponding author E-Mill:> nasawa(at)muroran-it.ac.jp
<Abstract:> Molecular dynamics simulation of y{(1-x)Na₂O-xK₂O}-(1-y)SiO₂ glasses used an improved interatomic potential was performed to investigate the mixed alkali effect. The relation of self-diffusion coefficient of potassium and of sodium was improved, but the trend with x of the self-diffusion coefficient of potassium has become worse than the previous work.
<Keywords:> Keywords Molecular dynamics, Silicate glass, Mixed-Alkali Effect
<URL:> https://www.jstage.jst.go.jp/article/jccj/23/3/23_2024-0025/_article/-char/ja/

[Published online Journal of Computer Chemistry, Japan Vol.23, 68-70, by J-STAGE]
<Title:> 実時間TDDFTの時系列データに関する特異スペクトル解析
<Author(s):> 谷　直樹, 狩野　覚, 善甫　康成
<Corresponding author E-Mill:> naoki.tani.7x(at)stu.hosei.ac.jp
<Abstract:> Optical spectrum prediction based on first-principles calculations is important for the development of optical materials. In particular, Time Dependent Density Functional Theory (TDDFT) in real-time is one of the most widely used calculation methods. In real-time TDDFT, the dynamic dipole moment is used to obtain the polarizability by Fourier transform (FT). The optical spectrum can be obtained from this polarizability. However, if the time length is not sufficient, the spectrum becomes ambiguous. To solve this problem, we introduced singular spectrum analysis (SSA), which decomposes time series data into multiple orthogonal oscillations. By extracting only the main components related to the peak of interest, the corresponding time series data is reproduced. In this process, high-frequency oscillations recognized as noise are removed. We applied this method to TDDFT time-series data for ethylene and small molecules of benzene, naphthalene, anthracene and tetracene. We focused on band edges, which are important for understanding optical properties, to clarify the signals. Even when the time-series data is insufficient, we found that it is possible to obtain time-series data of sufficient time length by isolating the oscillation components contributing to the band edges and expanding and complementing them with time-series prediction.
<Keywords:> Keywords TDDFT, Singular Spectrum Analysis (SSA), Fourier Transform (FT)
<URL:> https://www.jstage.jst.go.jp/article/jccj/23/3/23_2024-0021/_article/-char/ja/

[Published online Journal of Computer Chemistry, Japan Vol.23, 65-67, by J-STAGE]
<Title:> ポリスチレン解重合のシミュレーション方法の検討
<Author(s):> 三枝　俊亮
<Corresponding author E-Mill:> mieda.sd(at)om.asahi-kasei.co.jp
<Abstract:> To verify the possibility to simulate depolymerization, simulations of the depolymerization of polystyrene were performed. Molecular Dynamics simulations (MD) using neural network potentials were found to be similar in accuracy to MD using density functional theory calculations. It was also found that long-time simulations using neural network potential-MD predicted styrene monomer yields close to those obtained experimentally, and that the monomer yields tended to decrease with increasing pressure.
<Keywords:> Key words depolymerization of polystyrene, long-time simulation using NNP-MD, ReaxFF, DFT-MD, Neural Network Potential
<URL:> https://www.jstage.jst.go.jp/article/jccj/23/3/23_2024-0017/_article/-char/ja/

[Published online Journal of Computer Chemistry, Japan Vol.23, 59-61, by J-STAGE]
<Title:> Wulffの定理と第一原理計算を用いた金属クラスターの構造予測
<Author(s):> 大西　未優, 大野　彰太, 中田　彩子, 中井　浩巳
<Corresponding author E-Mill:> nakai(at)waseda.jp
<Abstract:> Metal nanoparticles are useful as catalysts having specific reactivity owing to highly reactive site and strong size dependency. Structural information of metal nanoparticles is essential for interpretation and prediction of their reactivity. Wulff theorem predicts the equilibrium structures of crystals by using the surface energies of plane indices such as (111), (110), and (100). In this study, we evaluated the surface energies of well-defined Rh surfaces by the first principles calculations, followed by systematically constructing various sizes of Rh nanoparticles based on the Wulff theorem. For small nanoparticles with radii of 2 nm or less, only the (111) and (100) planes were present. On the other hand, high index surfaces appeared at large nanoparticles, of which the radii were more than 2.5 nm.
<Keywords:> Metal nanoparticle, Wulff construction, First principles calculation, Surface energy, Plane index
<URL:> https://www.jstage.jst.go.jp/article/jccj/23/3/23_2024-0023/_article/-char/ja/