Abstract
The rational development of new drugs is a complex and expensive process, comprising several steps. Typically, it starts by screening databases of small organic molecules for chemical structures with potential of binding to a target receptor and prioritizing the most promising ones. Only a few of these will be selected for biological evaluation and further refinement through chemical synthesis. Despite the accumulated knowledge by pharmaceutical companies that continually improve the process of finding new drugs, a myriad of factors affect the activity of putative candidate molecules in vivo and the propensity for causing adverse and toxic effects is recognized as the major hurdle behind the current "target-rich, lead-poor" scenario. In this study we evaluate the use of several Machine Learning algorithms to find useful rules to the elucidation and prediction of toxicity using ID and 2D molecular descriptors. The results indicate that: i) Machine Learning algorithms can effectively use ID molecular descriptors to construct accurate and simple models; ii) extending the set of descriptors to include 2D descriptors improve the accuracy of the models.

Abstract
Logic programming provides an ideal framework for tackling complex data, such as the multi-dimensional vector-based data used to represent spatial databases. Unfortunately, the usefulness of logic programming systems if often hampered by the fact that most of these systems have to rely on a single unification-based mechanism as the only way to search in the database. While unification can usually take effective advantage of hash-based indexing, it is often the case that queries over more complex and structured data, such as the vectorial terms stored in spatial databases, cannot. We propose a new extension to Prolog indexing: User Defined Indexing (UDI). In this mechanism, the programmer may add extra information to Prolog indices so that only interesting fragments of the database will be selected. UDI provides a general extension of indexing, and can be used for both instantiated and constrained variables. As a test case, we demonstrate how UDI can be combined with a constraint system to provide an elegant and efficient mechanism to generate and execute range queries and spatial queries. Experimental evaluation shows that this mechanism can achieve orders of magnitude speedups on non-trivial datasets.

Abstract
In this paper we present the work in progress on LogCHEM, an ILP based tool for discriminative interactive mining of chemical fragments. In particular, we describe the integration with a molecule visualisation software that allows the chemist to graphically control the search for interesting patterns in chemical fragments. Furthermore, we show how structured information, such as rings, functional groups like carboxyl, amine, methyl, ester, etc are integrated and exploited in LogCHEM.

Abstract
We present a novel approach to cluster sets of protein sequences, based on Inductive Logic Programming (ILP). Preliminary results show that; the method proposed Produces understand able descriptions/explanations of the clusters. Furthermore, it can be used as a knowledge elicitation tool to explain clusters proposed by other clustering approaches, such as standard phylogenetic programs.

Abstract
Prolog is traditionally not statically typed. Since the benefits of static typing are huge it was decided to grow a. portable type system inside two widely used open source Prolog systems: SWI-Prolog and Yap. This requires close cooperation and agreement, between the two systems. The type system is Hindley-Milner. The main characteristics of the introduction of types in SWI and Yap are that, typing is not mandatory, that typed and untyped code call be mixed, and that the type checker call insert dynamic type checks at the boundaries between typed and untyped code. The basic decisions and the current status of Hie Typed Prolog project are described. as well as the remaining tasks and problems to be solved.

Abstract
Logic Programming and the Prolog language have a major role in Computing. Prolog, and its derived languages, have been widely used in a impressive variety of application domains. Thus, a bit of the history of Logic Programming reflects in the history of systems such as Dec-10 Prolog [32], M-Prolog [15], C-Prolog [19], Quintus Prolog [20], SICStus Prolog [6], BIM-Prolog [17], ECLiPSe [1], BinProlog [30], SWI-Prolog [34], CIAO [14], and B-Prolog [35], to mention but a few. I briefly present the evolution of one such system, YAP, and present a personal perspective on the challenges ahead for YAP (and for Logic Programming). © 2008 Springer Berlin Heidelberg.