Membrane bioreactor (MBR)是用微生物分解工厂废水和生活污水等污水,然后用膜分离处理水和微生物的装置。由于可以在短时间内节省空间进行水处理,因此在大楼和工厂等地分散设置MBR进行无人驾驶作为缺水问题的解决方案而备受关注。但是,膜上微生物和固体等的堆积会产生浮标,膜差压的上升和运转成本的上升是很大的课题,膜差压达到一定水准后就用药品清洗膜,除去膜上的沉积物。必须去。因此,在本研究中,为了估计膜清洗时期,在1周以上的长期内,尝试精确地预测膜差压。根据水质以外的变量预测膜电阻(resistance, R)的模型,以及根据水质相关变量预测浮士兰易堆积性(deposition rate,DR)构建预测模型,提出了根据各个模型进行长期膜差压预测的方法。作为模型构建方法,使用了作为线性方法的partial least squares (PLS)法和作为非线性方法的支援vector regression (SVR)法。在预测R的模型中,在使用PLS方法和SVR方法的情况下都显示出了较高的预测性能,而在预测DR的模型中,在使用SVR方法的情况下的预测性能要高于PLS方法。之后长期预测了膜差压,确认了与预测R的模型相比,使用预测DR的模型能够更好地进行预测。通过活用提案手法,期待MBR的分散设置和无人驾驶化的扩大。
{"title":"Construction of Long-Term Transmembrane Pressure Estimation Model for a Membrane Bioreactor","authors":"Kyung-mo Sung, H. Kaneko, K. Funatsu","doi":"10.2751/JCAC.13.10","DOIUrl":"https://doi.org/10.2751/JCAC.13.10","url":null,"abstract":"Membrane bioreactor (MBR) は工場排水や生活下水などの汚水を微生物で分解し、その後処理水と微生物を膜で分離する装置のことである。短時間かつ省スペースでの水処理が可能であるため、ビルや工場などにMBRを分散設置して無人運転を行うことは水不足問題の解決策として注目されている。しかし、膜に微生物や固形物などが堆積することでファウリングが発生し、膜差圧の上昇および運転コストの上昇は大きな課題となっており、膜差圧が一定水準に到達すると膜を薬品で洗浄し膜に付着した堆積物を除去しなければならない。そこで本研究では膜洗浄時期の推定のために1週間以上の長期にわたり、精度良く膜差圧を予測することを試みた。水質以外の変数から膜抵抗(resistance, R)を予測するモデルと水質関連変数からファウラントの堆積しやすさ(deposition rate, DR)を予測するモデルを構築し、それぞれのモデルから長期膜差圧予測を行う手法を提案した。モデル構築手法として線形手法であるpartial least squares (PLS)法と非線形手法であるsupport vector regression (SVR)法を使用した。Rを予測するモデルでは、PLS法とSVR法を用いた場合の両方とも高い予測性能を示したが、DRを予測するモデルでは、PLS法よりSVR法を用いた場合の方が予測性能は高かった。その後長期的に膜差圧を予測したが、Rを予測するモデルよりDRを予測するモデルを用いた方が精度良く予測できることが確認された。提案手法を活用することで、MBRの分散設置や無人運転化の拡大が期待される。","PeriodicalId":41457,"journal":{"name":"Journal of Computer Aided Chemistry","volume":"13 1","pages":"10-19"},"PeriodicalIF":0.0,"publicationDate":"2012-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"69254903","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 a Prediction Model for Mutagenicity - Validation of Ames Test Data","authors":"Masamoto Arakawa, K. Funatsu","doi":"10.2751/JCAC.13.20","DOIUrl":"https://doi.org/10.2751/JCAC.13.20","url":null,"abstract":"","PeriodicalId":41457,"journal":{"name":"Journal of Computer Aided Chemistry","volume":"13 1","pages":"20-28"},"PeriodicalIF":0.0,"publicationDate":"2012-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"69254942","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":"Powerful Integrative Tool Combining Structure Generator and Chemical Space Visualization","authors":"K. Hasegawa, K. Funatsu","doi":"10.2751/JCAC.13.1","DOIUrl":"https://doi.org/10.2751/JCAC.13.1","url":null,"abstract":"本研究では、薬物設計における2つの基本的な手法を紹介する。すなわち、構造発生と化学構造図示化である。構造発生は、リード最適化で利用され、構造ホッピングに有用である。我々は、定量的構造活性相関に基づく構造発生に注目する。すなわち、逆定量的構造活性相関手法である。逆定量的構造活性相関手法の目的は、定量的構造活性相関モデルから生物活性が高いと予測される化学構造を提案することである。化学構造図示化は、リード最適化の別の重要な手法である。化学構造図示化は、合成化合物が化学空間上どこに存在しているかということ、あるいは、どこまで合成を行えばリード最適化が達成できるかを示す良いコンパスとなる。図示化は、複数のターゲットタンパク質に対する分子選択性を理解するのにも役立つ。一般に、化合物が複数のターゲットタンパク質に対して生物活性を示すと望ましくない副作用を引き起こす可能性があるので、化学構造図示化は安全性の面からも非常に価値がある。われわれの研究を含めて、2つの基本的な手法である構造発生と化学構造図示化を、それぞれ簡単に総説する。","PeriodicalId":41457,"journal":{"name":"Journal of Computer Aided Chemistry","volume":"13 1","pages":"1-9"},"PeriodicalIF":0.0,"publicationDate":"2012-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"69254892","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}
In chemical plants, soft sensors have been widely used to estimate difficult-to-measure process variables online. The predictive accuracy of soft sensors decreases due to changes in the state of chemical plants, and soft sensor models based on time difference (TD) have been constructed for reducing the effects of deterioration with age such as the drift. However, details on models based on TD (TD models) remain to be clarified. In this study, therefore, TD models were discussed in terms of noise and variance in data, auto-correlation in process variables, degree of model accuracy, and so on. Then, we theoretically clarified and formulated the difference of predictive accuracy between normal models and TD models. The relationships and the formulas of TD were verified through the analysis of simulation data. Furthermore, we analyzed dynamic simulation data with considering observed disturbances and unobserved disturbances, and confirmed that predictive accuracy of TD models increased by setting appropriate intervals of TD.
{"title":"Consideration of Soft Sensor Methods Based on Time Difference and Discussion on Intervals of Time Difference","authors":"H. Kaneko, K. Funatsu","doi":"10.2751/JCAC.13.29","DOIUrl":"https://doi.org/10.2751/JCAC.13.29","url":null,"abstract":"In chemical plants, soft sensors have been widely used to estimate difficult-to-measure process variables online. The predictive accuracy of soft sensors decreases due to changes in the state of chemical plants, and soft sensor models based on time difference (TD) have been constructed for reducing the effects of deterioration with age such as the drift. However, details on models based on TD (TD models) remain to be clarified. In this study, therefore, TD models were discussed in terms of noise and variance in data, auto-correlation in process variables, degree of model accuracy, and so on. Then, we theoretically clarified and formulated the difference of predictive accuracy between normal models and TD models. The relationships and the formulas of TD were verified through the analysis of simulation data. Furthermore, we analyzed dynamic simulation data with considering observed disturbances and unobserved disturbances, and confirmed that predictive accuracy of TD models increased by setting appropriate intervals of TD.","PeriodicalId":41457,"journal":{"name":"Journal of Computer Aided Chemistry","volume":"13 1","pages":"29-43"},"PeriodicalIF":0.0,"publicationDate":"2012-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"69254950","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}
本研究では、有機化合物の変異原性を予測するためのクラス分類モデルの構築を行った。変異原性を評価するための標準的な方法である復帰突然変異試験を対象とし、その評価結果を高い精度で予測することの出来るモデルの構築を目指した。クラス分類モデル構築のための手法として、複数のSupport Vector Machine(SVM)モデルをサブモデルとして構築し、それらを組み合わせることで予測を行うアンサンブル手法を提案する。データセットから一部の化合物および構造記述子をランダムに抜き出し、SVMを用いてサブモデルを構築する。このとき、SVMのパラメータについても乱数によって無作為に決定する。この操作を複数回繰り返した後、精度の高いサブモデルの予測結果を統合することで変異原性の予測を行う。Hansenら[K. Hansen, et al., J. Chem. Inf. Model., 49, 2077-2081] が収集・整理した、6,512化合物からなる復帰突然変異試験のデータセットを用い、モデルの構築および評価を行った。その結果、テストセットに対する予測正解率79.6%のモデルを構築することに成功した。これは、通常のSVMによって得られるモデルと比較し高い精度を示すものであった。また、The Area Under ROC-Curve(AUC)は0.866であり、Hansenらの結果と同等以上の結果であることが確認された。これらのことから、変異原性の予測にあたってはSVMおよびアンサンブルモデルを用いることが有力であるとの結論が得られた。
本研究构建了用于预测有机化合物变异源性的类别分类模型。以作为评价变原性的标准方法的回归突变试验为对象,目标是构建能够高精度预测其评价结果的模型。作为一种用于构建类分类模型的方法,我们提出了一种通过将多个辅助向量机(SVM)模型作为子模型构建并组合它们来进行预测的协同方法。我们从数据集中随机抽取一些化合物和结构描述符,利用SVM建立子模型。此时,也通过随机数随机地确定SVM的参数。重复多次该操作后,通过综合准确度较高的子模型预测结果来预测变异源性。汉森等[K.汉森,et al., J. Chem. Inf. Model., 49,2077-2081]收集整理的由6512个化合物组成的回归突变试验数据集,用于建立和评估模型。结果,成功建立了对测试集的预测正确率为79.6%的模型。与普通SVM得到的模型相比,这显示了更高的精度。另外,The Area Under ROC-Curve (AUC)为0.866,与Hansen等人的结果相同或更高。由此得出结论,在预测变异源性时,使用SVM和合奏模型是最有力的方法。
{"title":"Prediction of Mutagenicity of Organic Molecules by Ensemble Learning","authors":"Masamoto Arakawa, K. Funatsu","doi":"10.2751/JCAC.12.26","DOIUrl":"https://doi.org/10.2751/JCAC.12.26","url":null,"abstract":"本研究では、有機化合物の変異原性を予測するためのクラス分類モデルの構築を行った。変異原性を評価するための標準的な方法である復帰突然変異試験を対象とし、その評価結果を高い精度で予測することの出来るモデルの構築を目指した。クラス分類モデル構築のための手法として、複数のSupport Vector Machine(SVM)モデルをサブモデルとして構築し、それらを組み合わせることで予測を行うアンサンブル手法を提案する。データセットから一部の化合物および構造記述子をランダムに抜き出し、SVMを用いてサブモデルを構築する。このとき、SVMのパラメータについても乱数によって無作為に決定する。この操作を複数回繰り返した後、精度の高いサブモデルの予測結果を統合することで変異原性の予測を行う。Hansenら[K. Hansen, et al., J. Chem. Inf. Model., 49, 2077-2081] が収集・整理した、6,512化合物からなる復帰突然変異試験のデータセットを用い、モデルの構築および評価を行った。その結果、テストセットに対する予測正解率79.6%のモデルを構築することに成功した。これは、通常のSVMによって得られるモデルと比較し高い精度を示すものであった。また、The Area Under ROC-Curve(AUC)は0.866であり、Hansenらの結果と同等以上の結果であることが確認された。これらのことから、変異原性の予測にあたってはSVMおよびアンサンブルモデルを用いることが有力であるとの結論が得られた。","PeriodicalId":41457,"journal":{"name":"Journal of Computer Aided Chemistry","volume":"12 1","pages":"26-36"},"PeriodicalIF":0.0,"publicationDate":"2011-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"69254821","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 SOAP API Service in Mass Spectral Database MassBank","authors":"H. Horai, Yoshito Nihei, T. Nishioka","doi":"10.2751/JCAC.12.11","DOIUrl":"https://doi.org/10.2751/JCAC.12.11","url":null,"abstract":"質量分析スペクトルデータベースMassBankにおいてSOAP APIサービスを新たに開発した。このサービスを用いることで、任意のアプリケーション・ソフトウェアからMassBankを利用することが可能となる。すなわち、ユーザの意図どおりにMassBankが提供する機能を組み合わせるプログラム、大量データについて一連の処理を繰り返し実行するプログラム、他のインターネットサービスと連携するプログラム等をユーザが作成することが可能となる。また、既存の質量分析解析ツールにMassBank検索機能を付け加えることも容易になる。MassBankはインターネット上の分散データベースであるが、本SOAP APIを用いてmassbank.jpにアクセスすることで、すべての分散データベースサーバに一括して検索することが可能であり、あるスペクトルデータがどのサーバに存在するかを意識せずにそれを取得することも可能である。","PeriodicalId":41457,"journal":{"name":"Journal of Computer Aided Chemistry","volume":"12 1","pages":"11-25"},"PeriodicalIF":0.0,"publicationDate":"2011-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"69254807","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}
In quantitative structure-activity relationships (QSAR), partial least squares (PLS) are of particular interest as a statistical method. Since successful applications of PLS to QSAR data set, PLS has evolved for coping with more demands associated with complex data structures. Especially, PLS variants focusing on visualization and chemical interpretation are highly desirable in modeling multi-target structure-activity relationships. In this paper, we employed the self-organized PLS (SOMPLS) approach to predict multiple inhibitory activities against three serine protease receptors (Thrombin, Trypsin and Factor Xa). Volsurf descriptors were used as chemical descriptors. From the SOMPLS analysis, we could catch rough trends about what chemical features are essential to each serine protease protein. Their chemical features could be successfully validated from X-ray crystal structures and the corresponding alignment residues.
{"title":"Visualization and Chemical Interpretation of Multi-Target Structure-Activity Relationships Using SOMPLS","authors":"清 長谷川, 船津 公人","doi":"10.2751/JCAC.12.47","DOIUrl":"https://doi.org/10.2751/JCAC.12.47","url":null,"abstract":"In quantitative structure-activity relationships (QSAR), partial least squares (PLS) are of particular interest as a statistical method. Since successful applications of PLS to QSAR data set, PLS has evolved for coping with more demands associated with complex data structures. Especially, PLS variants focusing on visualization and chemical interpretation are highly desirable in modeling multi-target structure-activity relationships. In this paper, we employed the self-organized PLS (SOMPLS) approach to predict multiple inhibitory activities against three serine protease receptors (Thrombin, Trypsin and Factor Xa). Volsurf descriptors were used as chemical descriptors. From the SOMPLS analysis, we could catch rough trends about what chemical features are essential to each serine protease protein. Their chemical features could be successfully validated from X-ray crystal structures and the corresponding alignment residues.","PeriodicalId":41457,"journal":{"name":"Journal of Computer Aided Chemistry","volume":"37 1","pages":"47-53"},"PeriodicalIF":0.0,"publicationDate":"2011-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"69254872","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}
Toshiaki Kusaba, S. Miyamoto, Masamoto Arakawa, K. Funatsu
A prediction system for the quantity of an adsorbed organic compound on zeolite has been developed. The regression model useful for a various combinations of zeolite and solvent has readily been developed using genetic algorithm partial least squares (GAPLS). In the models, the molecular descriptor of the organic compound is used as an explanatory variable and the partition coefficient is used as an objective variable. As a result, the system can provide accurate predictions for almost of all combinations. Additionally, with the GA-PLS method, we applied the system to selecting the optimal combination of zeolite and solvent for simulated moving bed (SMB) processes. The validity of the system was evaluated for separation of 2-adamantanone and 2-adamantanol as a representative case. The combinations selected by the system were almost the same as those selected by experiment. This system is intended to shorten the time for selecting the optimal zeolite/solvent combination and to ensure good selection accuracy for developing SMB methods.
{"title":"Development of System for Selecting Optimal Combination of Zeolite and Solvent for Simulated Moving Bed Processes","authors":"Toshiaki Kusaba, S. Miyamoto, Masamoto Arakawa, K. Funatsu","doi":"10.2751/JCAC.12.54","DOIUrl":"https://doi.org/10.2751/JCAC.12.54","url":null,"abstract":"A prediction system for the quantity of an adsorbed organic compound on zeolite has been developed. The regression model useful for a various combinations of zeolite and solvent has readily been developed using genetic algorithm partial least squares (GAPLS). In the models, the molecular descriptor of the organic compound is used as an explanatory variable and the partition coefficient is used as an objective variable. As a result, the system can provide accurate predictions for almost of all combinations. Additionally, with the GA-PLS method, we applied the system to selecting the optimal combination of zeolite and solvent for simulated moving bed (SMB) processes. The validity of the system was evaluated for separation of 2-adamantanone and 2-adamantanol as a representative case. The combinations selected by the system were almost the same as those selected by experiment. This system is intended to shorten the time for selecting the optimal zeolite/solvent combination and to ensure good selection accuracy for developing SMB methods.","PeriodicalId":41457,"journal":{"name":"Journal of Computer Aided Chemistry","volume":"12 1","pages":"54-64"},"PeriodicalIF":0.0,"publicationDate":"2011-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"69254881","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":"Analysis of Quality in Fruit by NIR Spectrum","authors":"Yosuke Yamashita, Masamoto Arakawa, K. Funatsu","doi":"10.2751/JCAC.12.37","DOIUrl":"https://doi.org/10.2751/JCAC.12.37","url":null,"abstract":"りんごについて測定された近赤外スペクトル用いて、内部品質である糖度および蜜・褐変の有無を推定する情報化学的手法の確立を行った。糖度に関しては、近赤外スペクトルを説明変数、糖度を目的変数とした回帰モデルを構築した。遺伝的アルゴリズムを応用した領域選択手法であるGenetic Algorithm-based Wavelength Selection (GAWLS)法を適用し、従来手法であるGenetic Algorithm-based Partial Least Squares (GAPLS)法によるモデルとの比較を行った。その結果、GAWLS法によるモデルの精度は従来手法と同程度であったが、糖度を説明するために重要である波長領域を明確に特定することが可能であることが示された。蜜・褐変の有無に関しては、GAWLS法をk-Nearest Neighbor (k-NN)法と組み合わせることでクラス分類問題へと適用する新規手法を提案し、k-NN法およびSupport Vector Machine (SVM)によるモデルとの比較を行った。その結果、糖度に関する解析と同様に、GAWLS法は重要な波長領域を明確に求めることが可能であった。以上の結果から、GAWLS法は近赤外スペクトルを用いた果物の内部品質解析において有用な手法であるとの結論が得られた。","PeriodicalId":41457,"journal":{"name":"Journal of Computer Aided Chemistry","volume":"12 1","pages":"37-46"},"PeriodicalIF":0.0,"publicationDate":"2011-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.2751/JCAC.12.37","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"69254860","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}