In this paper, we introduce ChemicalX, a PyTorch-based deep learning library designed for providing a range of state of the art models to solve the drug pair scoring task. The primary objective of the library is to make deep drug pair scoring models accessible to machine learning researchers and practitioners in a streamlined framework. The design of ChemicalX reuses existing high level model training utilities, geometric deep learning, and deep chemistry layers from the PyTorch ecosystem. Our system provides neural network layers, custom pair scoring architectures, data loaders, and batch iterators for end users. We showcase these features with example code snippets and case studies to highlight the characteristics of ChemicalX. A range of experiments on real world drug-drug interaction, polypharmacy side effect, and combination synergy prediction tasks demonstrate that the models available in ChemicalX are effective at solving the pair scoring task. Finally, we show that ChemicalX could be used to train and score machine learning models on large drug pair datasets with hundreds of thousands of compounds on commodity hardware.

This paper examines the problem of giving mobile users a possibility to access interoperability services based on ontologies and predefined concepts providing various meaningful objects and mechanisms to search, discover, invoke, compose and monitor appropriate grid-based services, applications as well as data sources in the Virtual Organization (VO) from any place in the world using mobile devices. Since mobiles as end devices are naturally used by humans to see a ’human-readable’ content, in our opinion, they should also allow them to specify ’human-readable’ queries instead of direct computer-interpretable queries to unknown remote service providers or databases. Based on the knowledge located in the interoperability space user’s requests from mobile devices can be mapped and forwarded automatically to appropriate remote interfaces to take advantages of various functionalities offered by the grid and service providers available today in the Internet. Therefore, more efficient interaction between the user and remote service provider(s) can be established. In our approach, the real ontology services are available from mobile devices via the gateway due to weaknesses of mobile devices and the complexity of the ontology layer within the grid infrastructure. In this paper we describe several grid-based services developed for mobile users as well as some core services which have been adopted to work with mobile devices. Roles of a mobile client, grid-services and gateway played in some novel scenarios of ontology usage are also described. Finally, in this paper we discuss issues related to obstacles and limitations that we have been facing while using the chosen J2ME technology, and the ways we are solving them.

Abstract A recursive enumerator for a function h is an algorithm f which enumerates for an input x finitely many elements including h(x). f is a k(n)-enumerator if for every input x of length n. h(x) is among the first k(n) elements enumerated by f. If there is a k(n)-enumerator for h then h is called k(n)-enumerable. We also consider enumerators which are only A-recursive for some oracle A.