Application of abductive ILP to learning metabolic network inhibition from temporal data

In this paper we use a logic-based representation and a combination of Abduction and Induction to model inhibition in metabolic networks. In general, the integration of abduction and induction is required when the following two conditions hold. Firstly, the given background knowledge is incomplete. Secondly, the problem must require the learning of general rules in the circumstance in which the hypothesis language is disjoint from the observation language. Both these conditions hold in the application considered in this paper. Inhibition is very important from the therapeutic point of view since many substances designed to be used as drugs can have an inhibitory effect on other enzymes. Any system able to predict the inhibitory effect of substances on the metabolic network would therefore be very useful in assessing the potential harmful side-effects of drugs. In modelling the phenomenon of inhibition in metabolic networks, background knowledge is used which describes the network topology and functional classes of inhibitors and enzymes. This background knowledge, which represents the present state of understanding, is incomplete. In order to overcome this incompleteness hypotheses are considered which consist of a mixture of specific inhibitions of enzymes (ground facts) together with general (non-ground) rules which predict classes of enzymes likely to be inhibited by the toxin. The foreground examples are derived from in vivo experiments involving NMR analysis of time-varying metabolite concentrations in rat urine following injections of toxins. The model’s performance is evaluated on training and test sets randomly generated from a real metabolic network. It is shown that even in the case where the hypotheses are restricted to be ground, the predictive accuracy increases with the number of training examples and in all cases exceeds the default (majority class). Experimental results also suggest that when sufficient training data is provided, non-ground hypotheses show a better predictive accuracy than ground hypotheses. The model is also evaluated in terms of the biological insight that it provides.

[1]  Edward Mackinnon.  Aspects of Scientific Explanation: and Other Essays in the Philosophy of Science , 1967 .

[2]  J. Davies,et al.  Molecular Biology of the Cell , 1983, Bristol Medico-Chirurgical Journal.

[3]  Gary James Jason,et al.  The Logic of Scientific Discovery , 1988 .

[4]  Stephen Muggleton,et al.  Learning Programs in the Event Calculus , 1997, ILP.

[5]  E Holmes,et al.  Metabonomic investigations into hydrazine toxicity in the rat. , 2001, Chemical research in toxicology.

[6]  Hiroyuki Ogata,et al.  KEGG: Kyoto Encyclopedia of Genes and Genomes , 1999, Nucleic Acids Res..

[7]  Stephen Muggleton,et al.  Induction of Enzyme Classes from Biological Databases , 2003, ILP.

[8]  Krysia Broda,et al.  Hybrid Abductive Inductive Learning: A Generalisation of Progol , 2003, ILP.

[9]  Katsumi Inoue.  Inverse Entailment for Full Clausal Theories , 2001 .

[10]  Akihiro Yamamoto,et al.  Which Hypotheses Can Be Found with Inverse Entailment? , 1997, ILP.

[11]  R. Botting,et al.  Actions of paracetamol on cyclooxygenases in tissue and cell homogenates of mouse and rabbit. , 2002, Medical science monitor : international medical journal of experimental and clinical research.

[12]  Peter A. Flach,et al.  Abductive and inductive reasoning: background and issues , 2000 .

[13]  Ivan Bratko,et al.  GenePath: a system for automated construction of genetic networks from mutant data , 2003, Bioinform..

[14]  L. Magnani.  Abduction, Reason, and Science. Process of Discovery and Explanation , 2001 .

[15]  Stephen Anthony Moyle.  An investigation into theory completion techniques in inductive logic programming , 2003 .

[16]  Luc De Raedt,et al.  Inductive Logic Programming: Theory and Methods , 1994, J. Log. Program..

[17]  Katsumi Inoue,et al.  Induction, Abduction, and Consequence-Finding , 2001, ILP.

[18]  B. Palsson,et al.  Metabolic Flux Balancing: Basic Concepts, Scientific and Practical Use , 1994, Bio/Technology.

[19]  Michal Linial,et al.  Using Bayesian Networks to Analyze Expression Data , 2000, J. Comput. Biol..

[20]  Stephen Muggleton,et al.  Modelling Inhibition in Metabolic Pathways Through Abduction and Induction , 2004, ILP.

[21]  Irene Papatheodorou,et al.  Inference of Gene Relations from Microarray Data by Abduction , 2005, LPNMR.

[22]  Christopher H. Bryant,et al.  Functional genomic hypothesis generation and experimentation by a robot scientist , 2004, Nature.

[23]  Kevin P. Murphy,et al.  Learning the Structure of Dynamic Probabilistic Networks , 1998, UAI.

[25]  Stephen Moyle,et al.  Using Theory Completion to Learn a Robot Navigation Control Program , 2002, ILP.

[26]  John J. Tyson,et al.  The Dynamics of Feedback Control Circuits in Biochemical Pathways , 1978 .

[27]  C. Peirce,et al.  Collected Papers of Charles Sanders Peirce , 1936, Nature.

[28]  T. Baillie,et al.  Drug metabolites in safety testing. , 2002, Toxicology and applied pharmacology.

[29]  Antonis C. Kakas,et al.  Abduction in Logic Programming , 2002, Computational Logic: Logic Programming and Beyond.

[30]  M. Kendall,et al.  The Logic of Scientific Discovery. , 1959 .

[31]  John R. Josephson,et al.  Abductive inference : computation, philosophy, technology , 1994 .

[32]  R. Albert,et al.  The large-scale organization of metabolic networks , 2000, Nature.

[33]  John H. Holland,et al.  Induction: Processes of Inference, Learning, and Discovery , 1987, IEEE Expert.

[34]  Paolo Mancarella,et al.  Abductive Logic Programming , 1992, LPNMR.

[35]  Satoru Miyano,et al.  Estimation of Genetic Networks and Functional Structures Between Genes by Using Bayesian Networks and Nonparametric Regression , 2001, Pacific Symposium on Biocomputing.

[36]  B Hess,et al.  Mechanism of glycolytic oscillation in yeast. I. Aerobic and anaerobic growth conditions for obtaining glycolytic oscillation. , 1968, Hoppe-Seyler's Zeitschrift fur physiologische Chemie.

[37]  Susumu Goto,et al.  KEGG: Kyoto Encyclopedia of Genes and Genomes , 2000, Nucleic Acids Res..

[38]  Jason A. Papin,et al.  Metabolic pathways in the post-genome era. , 2003, Trends in biochemical sciences.

[39]  Michael J E Sternberg,et al.  Evolution of enzymes in metabolism: a network perspective. , 2002, Journal of molecular biology.

[40]  A. Barabasi,et al.  Hierarchical Organization of Modularity in Metabolic Networks , 2002, Science.

[41]  Lawrence J. Marnett,et al.  Determinants of the cellular specificity of acetaminophen as an inhibitor of prostaglandin H2 synthases , 2002, Proceedings of the National Academy of Sciences of the United States of America.

[42]  H. Zimmerman,et al.  Acetaminophen (paracetamol) hepatotoxicity with regular intake of alcohol: Analysis of instances of therapeutic misadventure , 1995, Hepatology.

[43]  Akihiro Yamamoto,et al.  Finding Hypotheses from Examples by Computing the Least Generalization of Bottom Clauses , 1998, Discovery Science.

[44]  Hierarchical Organization of Modularity in Metabolic Networks Supporting Online Material , 2002 .

[45]  E Holmes,et al.  Curve-fitting method for direct quantitation of compounds in complex biological mixtures using 1H NMR: application in metabonomic toxicology studies. , 2005, Analytical chemistry.

[46]  Henrik Antti,et al.  Contemporary issues in toxicology the role of metabonomics in toxicology and its evaluation by the COMET project. , 2003, Toxicology and applied pharmacology.

[47]  C. Peirce,et al.  Essays in the philosophy of science , 1940 .

[48]  Stephen Muggleton,et al.  Theory Completion Using Inverse Entailment , 2000, ILP.