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

Abstract

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 Mach Learn (2006) 64:209-230 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.

ILP turns 20

“…Among many applications, advances in those fundamental ILP techniques are wellsuited to learning and discovering knowledge in systems biology (King et al 2004;Tamaddoni-Nezhad et al 2006;Synnaeve et al 2011). Using logic modeling of biological systems, relations between elements can be declaratively described as constraints or networks, and background theories contain prior biological knowledge and databases of gene/protein/metabolites and their interrelations.…”

“…Another important goal of systems biology is the revision of biological networks (Tamaddoni-Nezhad et al 2006, 2007. This requires not only building theories but updating them.…”

Variation of Background Knowledge in an Industrial Application of ILP

“…, K, where K is a distance threshold corresponding to the original background knowledge base 2.1.k-rn={}, for each c ∈ (k − 1)-cn k-rn = k-rn ∪{r | consumed by(c, r) ∨ produced by(c, r)}; 2.2.ks-rn = sample(k-rn,sr), where sr is a manually set sampling rate; 2.3.k-cn={}, for each r ∈ ks-rn k-cn = k-cn ∪{c | consumed by(c, r) ∨ produced by(c, r)}; 2.4.output k-cn. The datasets and variations of ground background knowledge were given to the abductive ILP [13] system Progol5.0 [10] together with a set of non-ground rules, which describe the underlying transitive behaviour of concentrations of metabolites and enzymes. Progol5.0 was then required to derive inhibition on reactions.…”

“…Through an iterative process of experimentation and modelling, Systems Biology aims to understand how individual components interact to govern the functioning of the system as a whole. In several recent papers [13,3], Inductive Logic Programing (ILP) has been applied to Systems Biology problems, in which it has been used to fill gaps in the descriptions of biological networks.…”

Brave induction: a logical framework for learning from incomplete information

“…To infer master reactions correctly from biochemical pathways, it is necessary to set background knowledge appropriately. This task often involves abduction (Tamaddoni-Nezhad et al 2006;Yamamoto et al 2009), but causal rules given in background knowledge are often incomplete. Brave induction can thus be useful to complete missing causal rules in these applications.…”