Neural Network Prediction of Carcinogenicity of Diverse Organic Compounds

広範囲の化学物質について構造活性相関により化学構造から有害性を高い精度で予測するモデルを開発することを目指して、ニューラルネットワークを用いて発ガン性のデータを解析した。Predictive Toxicology Challenge 2000-2001で公開された454種類の有機化合物についての記述子と発ガン性のデータを用いてニューラルネットワークの学習とテストを行った。分子軌道計算から求まるhomoやlumoなどの軌道エネルギー、分子表面積、log Pなど37種類の記述子について主成分分析を行い、得られた10個の主成分データをニューラルネットワークに入力した。Error-back-propagation法によりニューラルネットワークを学習する際の過学習、over-fitting、局所解などの問題を解決するために、学習回数や中間層ユニット数などの条件を最適化した。モデルの作成に用いなかった化合物を用いて判別テストを行った結果、的中率73.7 %の予測モデルを開発することができた。

[1]  Takashi Okada,et al.  Characteristic Substructures and Properties in Chemical Carcinogens Studied by the Cascade Model , 2003, Bioinform..

[2]  F. Burden,et al.  A quantitative structure--activity relationships model for the acute toxicity of substituted benzenes to Tetrahymena pyriformis using Bayesian-regularized neural networks. , 2000, Chemical research in toxicology.

[3]  S Hatrík,et al.  Neural Network Approach to the Prediction of the Toxicity of Benzothiazolium Salts from Molecular Structure , 1996, J. Chem. Inf. Comput. Sci..

[4]  K. Enslein,et al.  Mutagenicity (Ames): a structure-activity model. , 1983, Teratogenesis, carcinogenesis, and mutagenesis.

[5]  Zhigang Zhou,et al.  A QSAR Model of PAHs Carcinogenesis Based on Thermodynamic Stabilities of Biactive Sites , 2003, J. Chem. Inf. Comput. Sci..

[6]  Marjan Vracko,et al.  A Study of Structure-Carcinogenic Potency Relationship with Artificial Neural Networks. The Using of Descriptors Related to Geometrical and Electronic Structures , 1997, J. Chem. Inf. Comput. Sci..

[7]  H S Rosenkranz,et al.  International Commission for Protection Against Environmental Mutagens and Carcinogens. Approaches to SAR in carcinogenesis and mutagenesis. Prediction of carcinogenicity/mutagenicity using MULTI-CASE. , 1994, Mutation research.

[8]  D. Lewis,et al.  A prospective toxicity evaluation (COMPACT) on 40 chemicals currently being tested by the National Toxicology Program. , 1990, Mutagenesis.

[9]  Min Xiao,et al.  Artificial Neural Networks Applied to Classification of Mutagenic Activity of Nitro-substituted Polycyclic Aromatic Hydrocarbons , 1994, Comput. Chem..

[10]  Qian Liu,et al.  Fuzzy Adaptive Least Squares and Its Application to Structure‐Activity Studies , 1992 .

[11]  Hongmao Sun,et al.  Prediction of Chemical Carcinogenicity from Molecular Structure , 2004, J. Chem. Inf. Model..

[12]  Didier Villemin,et al.  Predicting Carcinogenicity of Polycyclic Aromatic Hydrocarbons from Back-Propagation Neural Network , 1994, Journal of chemical information and computer sciences.

[13]  Y. Takahata,et al.  Structure-Activity Relationship Studies of Carcinogenic Activity of Polycyclic Aromatic Hydrocarbons Using Calculated Molecular Descriptors with Principal Component Analysis and Neural Network Methods , 1999, J. Chem. Inf. Comput. Sci..

[14]  Frank R. Burden,et al.  Use of Automatic Relevance Determination in QSAR Studies Using Bayesian Neural Networks , 2000, J. Chem. Inf. Comput. Sci..

[15]  Alessandro Giuliani,et al.  Putting the Predictive Toxicology Challenge Into Perspective: Reflections on the Results , 2003, Bioinform..

[16]  Romualdo Benigni,et al.  Quantitative Structure-Activity Relationship (QSAR) Models of Mutagens and Carcinogens , 2003 .

[17]  Ashwin Srinivasan,et al.  Statistical Evaluation of the Predictive Toxicology Challenge 2000-2001 , 2003, Bioinform..

[18]  G. Klopman.  Artificial intelligence approach to structure-activity studies. Computer automated structure evaluation of biological activity of organic molecules , 1985 .

[19]  David W. Opitz,et al.  Use of Statistical and Neural Net Approaches in Predicting Toxicity of Chemicals , 2000, J. Chem. Inf. Comput. Sci..

[20]  Takatoshi Matsumoto,et al.  Prediction of Carcinogenicity of Chlorine-containing Organic Compounds by Neural Network. , 2002 .

[21]  Giuseppina C. Gini,et al.  Predictive Carcinogenicity: A Model for Aromatic Compounds, with Nitrogen-Containing Substituents, Based on Molecular Descriptors Using an Artificial Neural Network , 1999, J. Chem. Inf. Comput. Sci..

[22]  K. Enslein,et al.  Use of SAR in computer-assited prediction of carcinogenicity and mutagenicity of chemicals by the TOPKAT program , 1994 .

[23]  G. Klopman.  MULTICASE 1. A Hierarchical Computer Automated Structure Evaluation Program , 1992 .

[24]  Stefan Kramer,et al.  A Survey of the Predictive Toxicology Challenge 2000-2001 , 2003, Bioinform..

[25]  H. Rosenkranz,et al.  Structural alerts to genotoxicity: the interaction of human and artificial intelligence. , 1990, Mutagenesis.

[26]  Sergei O. Kuznetsov,et al.  Toxicology Analysis by Means of the JSM-method , 2003, Bioinform..

[27]  Carol Wellington,et al.  Symbolic, Neural, and Bayesian Machine Learning Models for Predicting Carcinogenicity of Chemical Compounds , 2000, J. Chem. Inf. Comput. Sci..

[28]  H. Rosenkranz,et al.  Prediction of the carcinogenicity in rodents of chemicals currently being tested by the US National Toxicology Program: structure-activity correlations. , 1990, Mutagenesis.

[29]  Hongmao Sun,et al.  A Universal Molecular Descriptor System for Prediction of LogP, LogS, LogBB, and Absorption , 2004, J. Chem. Inf. Model..

[30]  Li-Yu Daisy Liu,et al.  Fuzzy Adaptive Least Squares Applied to Structure-Activity and Structure-Toxicity Correlations , 1992 .

[31]  R. Tennant,et al.  Prediction of the outcome of rodent carcinogenicity bioassays currently being conducted on 44 chemicals by the National Toxicology Program. , 1990, Mutagenesis.

[32]  P. N. Craig,et al.  Carcinogenesis: a predictive structure-activity model. , 1982, Journal of toxicology and environmental health.

[33]  Mehdi Jalali-Heravi,et al.  Use of Artificial Neural Networks in a QSAR Study of Anti-HIV Activity for a Large Group of HEPT Derivatives , 2000, J. Chem. Inf. Comput. Sci..

[34]  R Benigni,et al.  QSAR prediction of rodent carcinogenicity for a set of chemicals currently bioassayed by the US National Toxicology Program. , 1991, Mutagenesis.

[35]  S. Hirono,et al.  Fuzzy adaptive least squares and its use in quantitative structure-activity relationships. , 1990, Chemical & pharmaceutical bulletin.