We describe the application of genetic programming, an evolutionary computing method, to predicting whether small molecules will block the HERG cardiac potassium channel. Models based on a molecular fragment-based descriptor set achieve an accuracy of 85-90% in predicting whether the IC(50) of a 'blind' set of compounds is <1 microM. Analysis of the models provides a 'meta-SAR', which predicts a pharmacophore of two hydrophobic features, one preferably aromatic and one preferably nitrogen-containing, with a protonatable nitrogen asymmetrically situated between them. Our experience of the approach suggests that it is robust, and requires limited scientist input to generate valuable predictive results and structural understanding of the target.
The Creep-and-Merge (CAM) segmentation system (described in [3,2]) is a novel architecture for region-based segmentation; it is designed to be efficient, insensitive to noise, scale and image geometry, capable of applying the widest range of statistical models, and to contain no adjustable parameters. This paper describes the continuing development of higher-level processing models utilising this system: we present a geometric ("true") corner detector with good performance, and give qualitative and quantitative comparisons with other leading systems.
We present a new taxonomy for describing the conditions and implementation of interactions. Current mechanisms for embedding interaction in software promote a hard separation between the programmers who produce the software, and the communities who go on to use it. In order to support open ecologies of function and fabrication, where this separation is negotiated by communities of users and designers, we need to reconceive those mechanisms. We describe interaction in two phases: Co-occurrence, the prerequisite conditions for an interaction to take place; and entanglement, the temporary coupling and interplay between elements participating in the interaction. We then sketch a blueprint of a system where those phases and their adjacent mechanisms enable communities of users to build and use interactive software. There are many ways of conceiving this new design space, and we present three dominant metaphors which we have employed so far, based on chemical reactions, quantum physics and cooking. We exhibit different systems which we have implemented based on these metaphors, and sketch how future systems will further empower citizens to design and inhabit their own interactions, express ownership over them and share them with communities of interest. CCS CONCEPTS • Human-centered computing → Interaction paradigms; Interactive systems and tools;
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.