Modeling of adipose/blood partition coefficient for environmental chemicals.

A Quantitative Structure Activity Relationship (QSAR) model was developed in order to predict the adipose/blood partition coefficient of environmental chemical compounds. The first step of QSAR modeling was the collection of inputs. Input data included the experimental values of adipose/blood partition coefficient and two sets of molecular descriptors for 67 organic chemical compounds; a) the descriptors from Linear Free Energy Relationship (LFER) and b) the PaDEL descriptors. The datasets were split to training and prediction set and were analysed using two statistical methods; Genetic Algorithm based Multiple Linear Regression (GA-MLR) and Artificial Neural Networks (ANN). The models with LFER and PaDEL descriptors, coupled with ANN, produced satisfying performance results. The fitting performance (R2) of the models, using LFER and PaDEL descriptors, was 0.94 and 0.96, respectively. The Applicability Domain (AD) of the models was assessed and then the models were applied to a large number of chemical compounds with unknown values of adipose/blood partition coefficient. In conclusion, the proposed models were checked for fitting, validity and applicability. It was demonstrated that they are stable, reliable and capable to predict the values of adipose/blood partition coefficient of "data poor" chemical compounds that fall within the applicability domain.

[1]  K. Gnana Sheela,et al.  Review on Methods to Fix Number of Hidden Neurons in Neural Networks , 2013 .

[2]  Martin P. Payne,et al.  COMPARISON OF MODELS FOR THE ESTIMATION OF BIOLOGICAL PARTITION COEFFICIENTS , 2002, Journal of toxicology and environmental health. Part A.

[3]  Tim Morris,et al.  Physiological Parameters in Laboratory Animals and Humans , 1993, Pharmaceutical Research.

[4]  Bernd Freisleben.  Stock Market Prediction with Backpropagation Networks , 1992, IEA/AIE.

[5]  Harpreet S. Chadha,et al.  Hydrogen bonding. 33. Factors that influence the distribution of solutes between blood and brain. , 1994, Journal of pharmaceutical sciences.

[6]  A. Worth,et al.  The prospects for using (Q)SARs in a changing political environment--high expectations and a key role for the european commission's joint research centre , 2004, SAR and QSAR in environmental research.

[7]  Mark T. D. Cronin,et al.  Recent Advances in QSAR Studies , 2010 .

[8]  Viera Lukacova,et al.  A Model‐based Dependence of the Human Tissue/Blood Partition Coefficients of Chemicals on Lipophilicity and Tissue Composition , 1999 .

[9]  H. E. Buist,et al.  Characterization and application of physiologically based pharmacokinetic models in risk assessment , 2010 .

[10]  Farhad Gharagheizi,et al.  QSPR Studies for Solubility Parameter by Means of Genetic Algorithm-Based Multivariate Linear Regression and Generalized Regression Neural Network , 2008 .

[11]  M. Delp,et al.  Physiological Parameter Values for Physiologically Based Pharmacokinetic Models , 1997, Toxicology and industrial health.

[12]  Ronald H Laessig,et al.  Polybrominated diphenyl ethers (PBDEs): new pollutants-old diseases. , 2003, Clinical medicine & research.

[13]  Magnitude and mechanistic determinants of the interspecies toxicokinetic uncertainty factor for organic chemicals. , 2004, Regulatory toxicology and pharmacology : RTP.

[14]  Harpreet S. Chadha,et al.  Hydrogen bonding. 32. An analysis of water-octanol and water-alkane partitioning and the delta log P parameter of seiler. , 1994, Journal of pharmaceutical sciences.

[15]  Kannan Krishnan,et al.  Physiologically-based pharmacokinetic (PBPK) models in toxicity testing and risk assessment. , 2012, Advances in experimental medicine and biology.

[16]  Chi-Chung Lam,et al.  FINANCIAL TIME SERIES FORECASTING BY NEURAL NETWORK USING CONJUGATE GRADIENT LEARNING ALGORITHM AND MULTIPLE LINEAR REGRESSION WEIGHT INITIALIZATION , 2000 .

[17]  Ewelina Rutkowska,et al.  LIPOPHILICITY ñ METHODS OF DETERMINATION AND ITS ROLE IN MEDICINAL CHEMISTRY , 2012 .

[18]  M. Rowland,et al.  Physiologically based pharmacokinetic modelling 2: predicting the tissue distribution of acids, very weak bases, neutrals and zwitterions. , 2006, Journal of pharmaceutical sciences.

[19]  M. Karelson,et al.  Quantum-Chemical Descriptors in QSAR/QSPR Studies. , 1996, Chemical reviews.

[20]  H. Kaiser.  The Application of Electronic Computers to Factor Analysis , 1960 .

[21]  Ruisheng Zhang,et al.  Prediction of the tissue/blood partition coefficients of organic compounds based on the molecular structure using least-squares support vector machines , 2005, J. Comput. Aided Mol. Des..

[22]  Thomas Peyret,et al.  A unified algorithm for predicting partition coefficients for PBPK modeling of drugs and environmental chemicals. , 2010, Toxicology and applied pharmacology.

[23]  Huabei Zhang.  A new nonlinear equation for the tissue/blood partition coefficients of neutral compounds. , 2004, Journal of pharmaceutical sciences.

[24]  Paola Gramatica,et al.  QSARINS‐chem: Insubria datasets and new QSAR/QSPR models for environmental pollutants in QSARINS , 2014, J. Comput. Chem..

[25]  G. David Garson,et al.  Interpreting neural-network connection weights , 1991 .

[26]  D. Levitt.  Quantitative relationship between the octanol/water partition coefficient and the diffusion limitation of the exchange between adipose and blood , 2010, BMC clinical pharmacology.

[27]  C. H. Pierce,et al.  Partition coefficients between human blood or adipose tissue and air for aromatic solvents. , 1996, Scandinavian journal of work, environment & health.

[28]  CHUN WEI YAP,et al.  PaDEL‐descriptor: An open source software to calculate molecular descriptors and fingerprints , 2011, J. Comput. Chem..

[29]  M. Abraham.  Application of solvation equations to chemical and biochemical processes , 1993 .

[30]  Roberto Todeschini,et al.  Comparison of Different Approaches to Define the Applicability Domain of QSAR Models , 2012, Molecules.

[31]  Ramazan Gençay,et al.  Linear, non-linear and essential foreign exchange rate prediction with simple technical trading rules , 1999 .

[32]  Peixun Liu,et al.  Current Mathematical Methods Used in QSAR/QSPR Studies , 2009, International journal of molecular sciences.

[33]  Huabei Zhang,et al.  Convenient nonlinear model for predicting the tissue/blood partition coefficients of seven human tissues of neutral, acidic, and basic structurally diverse compounds. , 2006, Journal of medicinal chemistry.

[34]  Kannan Krishnan,et al.  Quantitative structure-property relationships for physiologically based pharmacokinetic modeling of volatile organic chemicals in rats. , 2003, Toxicology and applied pharmacology.

[35]  Nina Nikolova-Jeliazkova,et al.  An Approach to Determining Applicability Domains for QSAR Group Contribution Models: An Analysis of SRC KOWWIN , 2005, Alternatives to laboratory animals : ATLA.

[36]  Robert P. Sheridan,et al.  Similarity to Molecules in the Training Set Is a Good Discriminator for Prediction Accuracy in QSAR , 2004, J. Chem. Inf. Model..

[37]  K Krishnan,et al.  An algorithm for predicting tissue: blood partition coefficients of organic chemicals from n-octanol: water partition coefficient data. , 1995, Journal of toxicology and environmental health.

[38]  P. Paixão,et al.  Prediction of Drug Distribution in Rat and Humans Using an Artificial Neural Networks Ensemble and a PBPK Model , 2014, Pharmaceutical Research.

[39]  Nina Nikolova-Jeliazkova,et al.  QSAR Applicability Domain Estimation by Projection of the Training Set in Descriptor Space: A Review , 2005, Alternatives to laboratory animals : ATLA.

[40]  K. Krishnan,et al.  QSARs for PBPK modelling of environmental contaminants , 2011, SAR and QSAR in environmental research.

[41]  Randy L. Haupt,et al.  Practical Genetic Algorithms , 1998 .

[42]  Roberto Todeschini,et al.  Handbook of Molecular Descriptors , 2002 .

[43]  J. DeJongh,et al.  A quantitative property-property relationship (QPPR) approach to estimate in vitro tissue-blood partition coefficients of organic chemicals in rats and humans , 1997, Archives of Toxicology.

[44]  E. Michael Azoff,et al.  Neural Network Time Series: Forecasting of Financial Markets , 1994 .

[45]  Heaton T. Jeff,et al.  Introduction to Neural Networks with Java , 2005 .

[46]  M. Abraham,et al.  Hydrogen bonding. 47. Characterization of the ethylene glycol-heptane partition system: hydrogen bond acidity and basicity of peptides. , 1999, Journal of pharmaceutical sciences.

[47]  M. Abraham,et al.  Supplemental Material for Correlation of Human and Animal Air-to-Blood Partition Coefficients with a Single Linear Free Energy Relationship Model , 2008 .

[48]  Paola Gramatica,et al.  QSARINS: A new software for the development, analysis, and validation of QSAR MLR models , 2013, J. Comput. Chem..

[49]  R. Harvey.  Polycyclic hydrocarbons and carcinogenesis , 1985 .

[50]  Roberto Todeschini,et al.  Assessing the validity of QSARs for ready biodegradability of chemicals: an applicability domain perspective. , 2014, Current computer-aided drug design.