T. Ikeda, M. Altaf-Ul-Amin, A. Parvin, S. Kanaya, T. Yonetani, E. Fukusaki
A rapid and easy method for extracting features from spectra obtained from Fourier transform near-infrared (FT-NIR) reflectance spectroscopy was examined by using the 1 and 2 derivatives and Spearman’s rank correlation. This method can select features from the overall wavelength. Therefore, this method can be considered suitable for the quality estimation of foods. Practically, a set of ranked green tea samples from a Japanese commercial tea contest were analyzed by FT-NIR in order to create a reliable quality-prediction model. The 2 derivative was determined for reducing noise and amplifying the fundamental features. Feature selection from the amplified data was performed using relations between the tea ranks and the derivative coefficients. Finally, a reliable quality-prediction model of green tea was formulated by using single linear and PLS regressions. Furthermore, we discuss possibility of the derivative coefficients as feature representation in FT-NIR.
{"title":"Predicting Rank of Japanese Green Teas by Derivative Profiles of Spectra Obtained from Fourier Transform Near-Infrared Reflectance Spectroscopy","authors":"T. Ikeda, M. Altaf-Ul-Amin, A. Parvin, S. Kanaya, T. Yonetani, E. Fukusaki","doi":"10.2751/JCAC.9.37","DOIUrl":"https://doi.org/10.2751/JCAC.9.37","url":null,"abstract":"A rapid and easy method for extracting features from spectra obtained from Fourier transform near-infrared (FT-NIR) reflectance spectroscopy was examined by using the 1 and 2 derivatives and Spearman’s rank correlation. This method can select features from the overall wavelength. Therefore, this method can be considered suitable for the quality estimation of foods. Practically, a set of ranked green tea samples from a Japanese commercial tea contest were analyzed by FT-NIR in order to create a reliable quality-prediction model. The 2 derivative was determined for reducing noise and amplifying the fundamental features. Feature selection from the amplified data was performed using relations between the tea ranks and the derivative coefficients. Finally, a reliable quality-prediction model of green tea was formulated by using single linear and PLS regressions. Furthermore, we discuss possibility of the derivative coefficients as feature representation in FT-NIR.","PeriodicalId":41457,"journal":{"name":"Journal of Computer Aided Chemistry","volume":"9 1","pages":"37-46"},"PeriodicalIF":0.0,"publicationDate":"2008-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.2751/JCAC.9.37","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"69257611","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Although it is possible to analyze chemical reactions in detail using molecular orbital (MO) and Density Functional Theory (DFT) calculations, these results simulate reactions at 0 K in the vacuum. Usual organic reactions proceed in solvents such as water, acetnitrile, alcohol and so on. In order to simulate the reactions in solution, it is necessary to investigate the mechanisms including solvent effects. The SCRF calculations have been used for this purpose while the method regards solvents as simple dielectric constants, and then, it is impossible to analyze the role of each solvent molecule for the reactions. Molecular dynamic (MD) calculations and Monte Carlo (MC) simulations have been used for calculating difference in free energy solvation. These theories usually use classical force fields so that it is very difficult to obtain good parameters for organic solvents used in organic synthesis. We have been developing Monte Carlo simulations using quantum mechanical calculations, called the QM/MC simulations. This approach makes it possible to analyze solvent effects from the quantum chemical view point. As an example of the simulation, we adopted alkaline hydrolysis of methyl acetate. A combination of ab initio calculations at the MP2/6-31++G** level of theory for analyzing the reaction mechanisms in the vacuum and the MC simulations using the PM3 method produced results consistent with experimental results very much.
{"title":"Monte Carlo Simulation Using Quantum Mechanical Calculations (QM/MC Simulation). An Application to Alkaline Hydrolysis of Methylacetate","authors":"Toru Yamaguchi, Michinori Sumimoto, K. Hori","doi":"10.2751/jcac.9.62","DOIUrl":"https://doi.org/10.2751/jcac.9.62","url":null,"abstract":"Although it is possible to analyze chemical reactions in detail using molecular orbital (MO) and Density Functional Theory (DFT) calculations, these results simulate reactions at 0 K in the vacuum. Usual organic reactions proceed in solvents such as water, acetnitrile, alcohol and so on. In order to simulate the reactions in solution, it is necessary to investigate the mechanisms including solvent effects. The SCRF calculations have been used for this purpose while the method regards solvents as simple dielectric constants, and then, it is impossible to analyze the role of each solvent molecule for the reactions. Molecular dynamic (MD) calculations and Monte Carlo (MC) simulations have been used for calculating difference in free energy solvation. These theories usually use classical force fields so that it is very difficult to obtain good parameters for organic solvents used in organic synthesis. We have been developing Monte Carlo simulations using quantum mechanical calculations, called the QM/MC simulations. This approach makes it possible to analyze solvent effects from the quantum chemical view point. As an example of the simulation, we adopted alkaline hydrolysis of methyl acetate. A combination of ab initio calculations at the MP2/6-31++G** level of theory for analyzing the reaction mechanisms in the vacuum and the MC simulations using the PM3 method produced results consistent with experimental results very much.","PeriodicalId":41457,"journal":{"name":"Journal of Computer Aided Chemistry","volume":"1 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2008-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.2751/jcac.9.62","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"69257179","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Molecular Mechanics and Molecular Orbital Simulations on The Specific Interactions between Lactose Repressor Protein and Its Inducer and Anti-Inducer Molecules","authors":"Shin Nishikawa, Shinsaku Kozakai, Y. Sengoku, N. Kurita","doi":"10.2751/JCAC.9.17","DOIUrl":"https://doi.org/10.2751/JCAC.9.17","url":null,"abstract":"転写制御タンパク質であるラクトースリプレッサー(LacR)は、Ligand依存型タンパク質であり、結合するLigandの種類に依存してDNAの転写を抑制あるいは促進する。本研究では、Ligandの結合によりLacRの構造と電子状態がどのように変化するかを、古典分子力学計算、及び半経験的分子軌道計算により解析し、Ligand結合によりLacRとDNAの結合が変化する原因の解明を試みた。具体的には、LacR単体の構造、インデューサであるIPTGが結合したLacR-IPTG複合体構造、アンチインデューサであるONPFが結合したLacR-ONPF複合体構造を、古典分子力場AMBERを用いて水中で最適化し、最適化した構造の電子状態を半経験的分子軌道計算により解析した。その結果、LacRとLigandの結合にはLigand周辺の結晶水が重要な働きをしていることが明らかになった。また、LigandがLacRに結合することにより、LacRのDNA結合部位の構造が変化し、LacRとDNA間の結合エネルギーが変化することも明らかになった。","PeriodicalId":41457,"journal":{"name":"Journal of Computer Aided Chemistry","volume":"9 1","pages":"17-29"},"PeriodicalIF":0.0,"publicationDate":"2008-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"69257549","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Theoretical Study on Emission Spectra of Bioluminescent Luciferases by Fragment Molecular Orbital Method","authors":"Ayumu Tagami, Nobuhiro Ishibashi, D. Kato, Naoki Taguchi, Y. Mochizuki, Hirofumi Watanabe, Mika Ito, S. Tanaka","doi":"10.2751/JCAC.9.47","DOIUrl":"https://doi.org/10.2751/JCAC.9.47","url":null,"abstract":"フラグメント分子軌道（FMO）法は、生体高分子をフラグメントに分割することにより計算時間を大幅に短縮し、タンパク質やDNAなどの巨大分子系全体を量子論的に扱う計算方法として近年注目を集めている。本研究ではその中の1手法である多層FMO（MLFMO）を用いて、ホタルルシフェラーゼの励起状態計算を行った。計算に用いた構造は、野生型（緑色に発光）と橙色、赤色に発光する変異体の計4つである。発光体オキシルシフェリンと活性中心を含む比較的小規模な系で計算を行い、その結果4つの構造に対する発光エネルギーを実験値と相関して再現することに成功した。タンパク質の全体構造においても励起状態計算を行い、実験値と計算値の差を比較したところ、4つの構造において最大でも0.27eVの差と、実験値を定量的に再現することにも成功した。本報告ではその詳細と、発光色制御における周辺環境場の重要性について述べる。","PeriodicalId":41457,"journal":{"name":"Journal of Computer Aided Chemistry","volume":"9 1","pages":"47-54"},"PeriodicalIF":0.0,"publicationDate":"2008-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"69257619","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
A. Tanaka, T. Kawai, Tsutomu Matsumoto, T. Takabatake, Hideho Okamoto, K. Funatsu
An evaluation technique was developed to prioritize synthetic strategic sites (a set of bonds to make precursors by cut and connection) for the purpose of effective retro-synthesis in synthetic route design system, AIPHOS. In this paper, the relationship between the strategic sites proposed by AIPHOS and the reaction centers in reaction databases was discussed. The correlation has been analyzed by logistic regression analysis (LoRA) with molecular centrality, bond dissociation energy (BDE), and the number of bonds. We used the equation to clarify the importance of synthetic strategy sites. The correlation models showed high similarity among three reaction databases. In addition, from the model, reaction centers in reaction databases were found to be located in the center of the whole structures, to have fewer bonds, and to have smaller bond dissociation energies.
{"title":"Development of Evaluation Model for Strategic Sites in Synthetic Route Design System AIPHOS","authors":"A. Tanaka, T. Kawai, Tsutomu Matsumoto, T. Takabatake, Hideho Okamoto, K. Funatsu","doi":"10.2751/JCAC.9.81","DOIUrl":"https://doi.org/10.2751/JCAC.9.81","url":null,"abstract":"An evaluation technique was developed to prioritize synthetic strategic sites (a set of bonds to make precursors by cut and connection) for the purpose of effective retro-synthesis in synthetic route design system, AIPHOS. In this paper, the relationship between the strategic sites proposed by AIPHOS and the reaction centers in reaction databases was discussed. The correlation has been analyzed by logistic regression analysis (LoRA) with molecular centrality, bond dissociation energy (BDE), and the number of bonds. We used the equation to clarify the importance of synthetic strategy sites. The correlation models showed high similarity among three reaction databases. In addition, from the model, reaction centers in reaction databases were found to be located in the center of the whole structures, to have fewer bonds, and to have smaller bond dissociation energies.","PeriodicalId":41457,"journal":{"name":"Journal of Computer Aided Chemistry","volume":"9 1","pages":"81-91"},"PeriodicalIF":0.0,"publicationDate":"2008-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"69257200","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Parallelization of Crystal Calculation for Large-Scale Molecular Crystal Structure Analysis","authors":"S. Obata, H. Goto","doi":"10.2751/JCAC.9.8","DOIUrl":"https://doi.org/10.2751/JCAC.9.8","url":null,"abstract":"計算化学技術による結晶構造解析は、機能材料や医薬品の開発など広範囲な研究分野において重要な役割が期待されている。一般に結晶計算では、計算対象となる結晶モデルを大きくするとより実在系に近づき、より高精度な計算結果を期待できるが、それに伴う分子間相互作用の計算量は爆発的に増加する。このため、利用可能な計算機の演算性能に応じて計算できる結晶モデルの大きさは制限されてしまう。そこで本研究では、我々が開発してきた結晶構造最適化プログラムKESSHOUの結晶計算法を、汎用分子計算プログラムCONFLEXに導入したCONFLEX/KESSHOUにおいて、分子間相互作用の計算部分に並列分散処理技術を適用することによって、結晶構造のエネルギー計算や構造最適化の効率的な高速化を実現した。また、結晶モデルの大規模化に伴う分子間相互作用エネルギーの加算誤差を最小限に抑えるため、Kahanの加算アルゴリズムを適用した。並列分散計算環境を利用して、アスピリン結晶の構造最適化を行なったところ、その並列化効率が90％以上に達することを確認した。また、結晶モデルの大きさ（有効結晶半径）に依存した結晶エネルギー揺らぎを調べたところ、有効結晶半径80A以上の結晶モデルの結晶エネルギーは10-3 kcal/mol以内の精度で求められることが分かった。","PeriodicalId":41457,"journal":{"name":"Journal of Computer Aided Chemistry","volume":"9 1","pages":"8-16"},"PeriodicalIF":0.0,"publicationDate":"2008-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"69257192","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
本論文では、ルールマイニング手法として知られているRough Set Theory (RST)を構造活性相関に応用することで、高活性に必要なルールが導けるかどうかを検証した。これまでルールマイニング手法としては、Inductive Logic Programming (ILP)が知られているが、学習の準備、特に、background knowledgeを事前に作成することが大変で、実際の応用は限定されていた。RSTはあいまいなものや粗いデータなどの不正確、不完全なものを類別するための理論である。これをルールマイニングの手法として用いる事で、あるサンプルと別のサンプルを区別するのに必要最小限の変数セット(reduct)を選択し、選択されたセットからルールを導くことが出来る。構造活性データとしては、Dihydrofolate reductase (DHFR)阻害剤を利用した。このデータセットは、これまで数多く解析され、構造要求性がよく知られている。得られたルールは、この構造要求性と類似しており、RSTの有効性を証明することができた。今回、母核構造が一定で活性値が定量的なデータで検証したが、多様な化合物を含むデータや活性値が不正確なデータへの応用も期待できる。
本文通过将Rough Set Theory (RST)这种被称为规则挖掘方法应用于结构活性相关，验证了能否推导出高活性所需的规则。到目前为止，作为规则挖掘方法，Inductive Logic Programming (ILP)是众所周知的，但在学习的准备上，特别是background事先制作knowledge非常困难，实际应用受到限制。RST是一种用于分类模糊、粗糙数据等不准确、不完整数据的理论。通过将其用作规则挖掘的方法，可以选择区分一个样本和另一个样本所需的最小变量集合，并从所选择的集合导出规则。作为结构活性数据，利用了Dihydrofolate reductase (DHFR)抑制剂。该数据集至今已被大量解析，其结构要求性广为人知。所得到的规则类似于这种结构要求，从而能够证明RST的有效性。此次通过母核结构一定、活性值定量的数据进行了验证，但也有望应用于含有多种化合物或活性值不准确的数据。
{"title":"Rough Set Theoryによるルールマイニングと構造活性相関への応用","authors":"清 長谷川, 倫央 光山, 正幹 荒川, 公人 船津","doi":"10.2751/JCAC.9.1","DOIUrl":"https://doi.org/10.2751/JCAC.9.1","url":null,"abstract":"本論文では、ルールマイニング手法として知られているRough Set Theory (RST)を構造活性相関に応用することで、高活性に必要なルールが導けるかどうかを検証した。これまでルールマイニング手法としては、Inductive Logic Programming (ILP)が知られているが、学習の準備、特に、background knowledgeを事前に作成することが大変で、実際の応用は限定されていた。RSTはあいまいなものや粗いデータなどの不正確、不完全なものを類別するための理論である。これをルールマイニングの手法として用いる事で、あるサンプルと別のサンプルを区別するのに必要最小限の変数セット(reduct)を選択し、選択されたセットからルールを導くことが出来る。構造活性データとしては、Dihydrofolate reductase (DHFR)阻害剤を利用した。このデータセットは、これまで数多く解析され、構造要求性がよく知られている。得られたルールは、この構造要求性と類似しており、RSTの有効性を証明することができた。今回、母核構造が一定で活性値が定量的なデータで検証したが、多様な化合物を含むデータや活性値が不正確なデータへの応用も期待できる。","PeriodicalId":41457,"journal":{"name":"Journal of Computer Aided Chemistry","volume":"9 1","pages":"1-7"},"PeriodicalIF":0.0,"publicationDate":"2008-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.2751/JCAC.9.1","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"69257537","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
An algorithm and a tool for automatic generation of structures of Phospholipids are proposed. The input is a compact representation of the variable part of phospholipids in a systematic way. The output is a structure of the phospholipid represented in the MDL Molfile format. The output molfile describes not only the topological connectivity of atoms but also the 2D coordinate of each atom in order to draw the structure without any overlapping. The variation of phospholipids that the tool covers includes glycerophospholipids (phosphatidylcholines, phosphatidylethanolamines, phosphatidylglicerols, phosphatidylinositols and phosphatidylserines) and sphingophospholipids with arbitrary length and arbitrary number of double bonds at arbitrary positions and in arbitrary cis/trans isomerism.
{"title":"Automatic Generation of Structure of Phospholipids","authors":"H. Horai, T. Nishioka","doi":"10.2751/JCAC.9.55","DOIUrl":"https://doi.org/10.2751/JCAC.9.55","url":null,"abstract":"An algorithm and a tool for automatic generation of structures of Phospholipids are proposed. The input is a compact representation of the variable part of phospholipids in a systematic way. The output is a structure of the phospholipid represented in the MDL Molfile format. The output molfile describes not only the topological connectivity of atoms but also the 2D coordinate of each atom in order to draw the structure without any overlapping. The variation of phospholipids that the tool covers includes glycerophospholipids (phosphatidylcholines, phosphatidylethanolamines, phosphatidylglicerols, phosphatidylinositols and phosphatidylserines) and sphingophospholipids with arbitrary length and arbitrary number of double bonds at arbitrary positions and in arbitrary cis/trans isomerism.","PeriodicalId":41457,"journal":{"name":"Journal of Computer Aided Chemistry","volume":"15 1","pages":"55-61"},"PeriodicalIF":0.0,"publicationDate":"2008-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"69257628","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Rika Nishikiori, Y. Makino, Yukino Ochi, Noriyuki Yamashita, Kousuke Okamoto, N. Kawashita, J. Takahara, T. Yasunaga, T. Takagi, M. Kawase
In a previous study {Takagi, T. et al., Chem. Pharm. Bull., 52(12), 1427-1432 (2004)}, we applied a slightly revised neural Independent Component Analysis (ICA) for profiling illegally distributed methamphetamine. Using ICA and an hourglass type Hierarchical Neural Network (HNN), we obtained better classification results than by using Principal Component Analysis (PCA), CATegorical PCA (CATPCA) and the MultiDimensional Scaling method (MDS). The HNN is a nonlinear machine learning method, and the ICA applied in that study exhibited nonlinear characteristics. The results indicated that nonlinear analysis is more efficient than linear analysis for profiling confiscated methamphetamine. Consequently, in this study, we applied Self-Organizing Maps (SOMs) to impurity profiling of methamphetamine. While SOM is currently a frequently employed nonlinear classification method, the ordinary SOM uses only that information contained by the winner neuron for classification and the information of other grid points is neglected. We therefore attempted to simultaneously utilize the information of loser neurons in order to avoid information loss. First, we visualized the resultant reference vectors using a contour map of each sample. Although considerable information can be visually compared using the SOM contour maps, metric comparisons are difficult. We therefore used MDS to construct a similarity matrix using the data of the resultant reference vectors to visualize metric data. To assess the results, we assumed that there are four synthetic routes (Nagai, Leuckart, Emde and reductive amination methods), and that each of these can be identified by comparing route-specific impurities.
在之前的一项研究中{Takagi, T. et al.， Chem。制药。公牛。， 52(12)， 1427-1432(2004)}，我们应用稍微改进的神经独立成分分析(ICA)来分析非法分销的甲基苯丙胺。采用ICA和沙漏型层次神经网络(HNN)进行分类，得到了比主成分分析(PCA)、分类主成分分析(CATPCA)和多维尺度方法(MDS)更好的分类结果。HNN是一种非线性机器学习方法，该研究中应用的ICA具有非线性特征。结果表明，非线性分析比线性分析更有效。因此，在本研究中，我们将自组织图谱(SOMs)应用于甲基苯丙胺的杂质分析。SOM是目前常用的一种非线性分类方法，但普通的SOM只使用赢家神经元所包含的信息进行分类，而忽略了其他网格点的信息。因此，我们试图同时利用失败神经元的信息，以避免信息丢失。首先，我们使用每个样本的等高线图来可视化生成的参考向量。虽然可以使用SOM等高线地图直观地比较大量信息，但度量比较是困难的。因此，我们使用MDS来构建一个相似矩阵，使用所得参考向量的数据来可视化度量数据。为了评估结果，我们假设有四种合成路线(Nagai, Leuckart, Emde和还原胺化方法)，并且每一种都可以通过比较路线特定的杂质来识别。
{"title":"Development of Fingerprint Verification Type Self-Organized Map Applied to Profiling Seized Methamphetamine","authors":"Rika Nishikiori, Y. Makino, Yukino Ochi, Noriyuki Yamashita, Kousuke Okamoto, N. Kawashita, J. Takahara, T. Yasunaga, T. Takagi, M. Kawase","doi":"10.2751/JCAC.9.30","DOIUrl":"https://doi.org/10.2751/JCAC.9.30","url":null,"abstract":"In a previous study {Takagi, T. et al., Chem. Pharm. Bull., 52(12), 1427-1432 (2004)}, we applied a slightly revised neural Independent Component Analysis (ICA) for profiling illegally distributed methamphetamine. Using ICA and an hourglass type Hierarchical Neural Network (HNN), we obtained better classification results than by using Principal Component Analysis (PCA), CATegorical PCA (CATPCA) and the MultiDimensional Scaling method (MDS). The HNN is a nonlinear machine learning method, and the ICA applied in that study exhibited nonlinear characteristics. The results indicated that nonlinear analysis is more efficient than linear analysis for profiling confiscated methamphetamine. Consequently, in this study, we applied Self-Organizing Maps (SOMs) to impurity profiling of methamphetamine. While SOM is currently a frequently employed nonlinear classification method, the ordinary SOM uses only that information contained by the winner neuron for classification and the information of other grid points is neglected. We therefore attempted to simultaneously utilize the information of loser neurons in order to avoid information loss. First, we visualized the resultant reference vectors using a contour map of each sample. Although considerable information can be visually compared using the SOM contour maps, metric comparisons are difficult. We therefore used MDS to construct a similarity matrix using the data of the resultant reference vectors to visualize metric data. To assess the results, we assumed that there are four synthetic routes (Nagai, Leuckart, Emde and reductive amination methods), and that each of these can be identified by comparing route-specific impurities.","PeriodicalId":41457,"journal":{"name":"Journal of Computer Aided Chemistry","volume":"9 1","pages":"30-36"},"PeriodicalIF":0.0,"publicationDate":"2008-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"69257560","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Development of Drug-likeness Model and Its Visualization","authors":"Masamoto Arakawa, Tomoyuki Miyao, K. Funatsu","doi":"10.2751/JCAC.9.70","DOIUrl":"https://doi.org/10.2751/JCAC.9.70","url":null,"abstract":"","PeriodicalId":41457,"journal":{"name":"Journal of Computer Aided Chemistry","volume":"9 1","pages":"70-80"},"PeriodicalIF":0.0,"publicationDate":"2008-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.2751/JCAC.9.70","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"69257189","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：