Modelling Inhalational Anaesthetics Using Bayesian Feature Selection and QSAR Modelling Methods

The development of robust and predictive QSAR models is highly dependent on the use of molecular descriptors that contain information relevant to the property being modelled. Selection of these relevant features from a large pool of possibilities is difficult to achieve effectively. Modern Bayesian methods provide substantial advantages over conventional feature selection methods for feature selection and QSAR modelling. We illustrate the importance of descriptor choice and the beneficial properties of Bayesian methods to select context‐dependent relevant descriptors and build robust QSAR models, using data on anaesthetics. Our results show the effectiveness of Bayesian feature selection methods in choosing the best descriptors when these are mixed with less informative descriptors. They also demonstrate the efficacy of the Abraham descriptors and identify deficiencies in ParaSurf descriptors for modelling anaesthetic action.

[1]  E. Eger,et al.  Nonimmobilizers and transitional compounds may produce convulsions by two mechanisms. , 1999, Anesthesia and analgesia.

[2]  Frank R. Burden,et al.  Predictive Human Intestinal Absorption QSAR Models Using Bayesian Regularized Neural Networks , 2005 .

[3]  Paul A. Smith,et al.  Comparison of Linear and Nonlinear Classification Algorithms for the Prediction of Drug and Chemical Metabolism by Human UDP-Glucuronosyltransferase Isoforms , 2003, J. Chem. Inf. Comput. Sci..

[4]  R. Olsen,et al.  The molecular mechanism of action of general anesthetics: structural aspects of interactions with GABAA receptors , 1998 .

[5]  R A Smith,et al.  Physicochemical Approaches to the Mode of Action of General Anesthetics , 1972, Anesthesiology.

[6]  David A Winkler,et al.  Predictive Bayesian neural network models of MHC class II peptide binding. , 2005, Journal of molecular graphics & modelling.

[7]  E. Bertaccini,et al.  Molecular modelling of specific and non-specific anaesthetic interactions. , 2002, British journal of anaesthesia.

[8]  M. Bleckwenn,et al.  Concepts and correlations relevant to general anaesthesia. , 2002, British journal of anaesthesia.

[9]  B W Urban,et al.  The site of anesthetic action. , 2008, Handbook of experimental pharmacology.

[10]  David T Manallack,et al.  The use of local surface properties for molecular superimposition , 2008, Journal of molecular modeling.

[11]  Adam Ibrahim,et al.  Air to lung partition coefficients for volatile organic compounds and blood to lung partition coefficients for volatile organic compounds and drugs. , 2007, European journal of medicinal chemistry.

[12]  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.

[13]  I. Tetko,et al.  Application of ALOGPS to predict 1-octanol/water distribution coefficients, logP, and logD, of AstraZeneca in-house database. , 2004, Journal of pharmaceutical sciences.

[14]  Steven L Shafer,et al.  Is a New Paradigm Needed to Explain How Inhaled Anesthetics Produce Immobility? , 2008, Anesthesia and analgesia.

[15]  Timothy Clark,et al.  New Molecular Descriptors Based on Local Properties at the Molecular Surface and a Boiling-Point Model Derived from Them , 2004, J. Chem. Inf. Model..

[16]  Peter Politzer,et al.  The complementary roles of molecular surface electrostatic potentials and average local ionization energies with respect to electrophilic processes , 2002 .

[17]  Frank R. Burden,et al.  Optimal Sparse Descriptor Selection for QSAR Using Bayesian Methods , 2009 .

[18]  F. Burden,et al.  Robust QSAR models using Bayesian regularized neural networks. , 1999, Journal of medicinal chemistry.

[19]  Timothy Clark,et al.  Local molecular properties and their use in predicting reactivity , 2003, Journal of molecular modeling.

[20]  M. Abraham,et al.  Effect of anesthetic structure on inhalation anesthesia: implications for the mechanism. , 2008, Journal of pharmaceutical sciences.

[21]  J L Robinson,et al.  The stereospecific effects of isoflurane isomers in vivo. , 1994, European journal of pharmacology.

[22]  H. Meyer.  Zur Theorie der Alkoholnarkose , 1899, Archiv für experimentelle Pathologie und Pharmakologie.

[23]  E. Eger,et al.  Anesthetic Potencies of n-Alkanols: Results of Additivity and Solubility Studies Suggest a Mechanism of Action Similar to That for Conventional Inhaled Anesthetics , 1997, Anesthesia and analgesia.

[24]  David A Winkler,et al.  Modelling blood-brain barrier partitioning using Bayesian neural nets. , 2004, Journal of molecular graphics & modelling.

[25]  E. Eger,et al.  The Effect of Rigidity, Shape, Unsaturation, and Length on the Anesthetic Potency of Hydrocarbons , 2001, Anesthesia and analgesia.

[26]  Peter Politzer,et al.  Molecular surface electrostatic potentials and anesthetic activity , 2007, Journal of molecular modeling.

[27]  E. Eger,et al.  Polyhalogenated and perfluorinated compounds that disobey the Meyer-Overton hypothesis. , 1994, Anesthesia and analgesia.

[28]  N. P. Franks,et al.  Where do general anaesthetics act? , 1978, Nature.

[29]  Frank R. Burden,et al.  Toward Novel Universal Descriptors: Charge Fingerprints , 2009, J. Chem. Inf. Model..

[30]  H. Flohr,et al.  The role of the NMDA synapse in general anesthesia. , 1998, Toxicology letters.

[31]  Jc Sewell,et al.  Shape similarity indices are the best predictors of substituted fluoroethane and ether anaesthesia , 1997 .

[32]  A. Mehdipour,et al.  QSAR Studies on the Anesthetic Action of Some Polyhalogenated Ethers , 2007, Chemical biology & drug design.

[33]  Frank R. Burden,et al.  An Optimal Self‐Pruning Neural Network and Nonlinear Descriptor Selection in QSAR , 2009 .

[34]  K. Miller,et al.  The nature of the site of general anesthesia. , 1985, International review of neurobiology.

[35]  Timothy Clark,et al.  QSAR and QSPR based solely on surface properties? , 2004, Journal of molecular graphics & modelling.

[36]  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.