The emerging paradigm of Precision Oncology 3.0 uses panomics and sophisticated methods of statistical reverse engineering to hypothesize the putative networks that drive a given patient's tumour, and to attack these drivers with combinations of targeted therapies. Here, we review a paradigm termed Rapid Learning Precision Oncology wherein every treatment event is considered as a probe that simultaneously treats the patient and provides an opportunity to validate and refine the models on which the treatment decisions are based. Implementation of Rapid Learning Precision Oncology requires overcoming a host of challenges that include developing analytical tools, capturing the information from each patient encounter and rapidly extrapolating it to other patients, coordinating many patient encounters to efficiently search for effective treatments, and overcoming economic, social and structural impediments, such as obtaining access to, and reimbursement for, investigational drugs.

We propose a computational model for interpreting line drawings as threedimensional surfaces, based on constraints on local surface orientation along extremal and discontinuity boundaries. Specific techniques are described for two key processes: recovering the three-dimensional conformation of a space curve (e.g., a surface boundary) from its two-dimensional projection in an image, and interpolating smooth surfaces from orientation constraints along extremal boundaries.

While advanced melanoma remains one of the most challenging cancers, recent developments in our understanding of the molecular drivers of this disease have uncovered exciting opportunities to guide personalized therapeutic decisions. Genetic analyses of melanoma have uncovered several key molecular pathways that are involved in disease onset and progression, as well as prognosis. These advances now make it possible to create a "Molecular Disease Model" (MDM) for melanoma that classifies individual tumors into molecular subtypes (in contrast to traditional histological subtypes), with proposed treatment guidelines for each subtype including specific assays, drugs, and clinical trials. This paper describes such a Melanoma Molecular Disease Model reflecting the latest scientific, clinical, and technological advances.

Cancer kills millions of people each year. From an AI perspective, finding effective treatments for cancer is a high-dimensional search problem characterized by many molecularly distinct cancer subtypes, many potential targets and drug combinations, and a dearth of high quality data to connect molecular subtypes and treatments to responses. The broadening availability of molecular diagnostics and electronic medical records, presents both opportunities and challenges to apply AI techniques to personalize and improve cancer treatment. We discuss these in the context of Cancer Commons, a “rapid learning” community where patients, physicians, and researchers collect and analyze the molecular and clinical data from every cancer patient, and use these results to individualize therapies. Research opportunities include: adaptively-planning and executing individual treatment experiments across the whole patient population, inferring the causal mechanisms of tumors, predicting drug response in individuals, and generalizing these findings to new cases. The goal is to treat each patient in accord with the best available knowledge, and to continually update that knowledge to benefit subsequent patients. Achieving this goal is a worthy grand challenge for AI.

Imagine an Internet-scale knowledge system where people and intelligent agents can collaborate on solving complex problems in business, engineering, science, medicine, and other endeavors. Its resources include semantically tagged websites, wikis, and blogs, as well as social networks, vertical search engines, and a vast array of web services from business processes to AI planners and domain models. Research prototypes of decentralized knowledge systems have been demonstrated for years, but now, thanks to the web and Moore's law, they appear ready for prime time. This article introduces the architectural concepts for incrementally growing an Internet-scale knowledge system and illustrates them with scenarios drawn from e-commerce, e-science, and e-life.

We introduce SOBA (Service Oriented Business Applications) Fabric, an architectural framework for Business Services Networks (BSN). BSNs extend the enterprise service bus concept beyond the boundaries of a single enterprise, enabling companies to build on each other's applications and create new loosely-coupled, network-centric business models. SOBA Fabric facilitates dynamic integration of people, processes, and information across business and technology boundaries by providing: 1) Dynamic provisioning and service personalization so that subscribers can quickly customize a business process to work with their systems and processes; 2) Industry-specific Service Level Agreements; 3) An industry-specific business services catalog supporting dynamic discovery and composition; 4) Business Process Management tools interface tailored to industry requirements; and 5) Visibility and exception handling across the BSN. Most importantly, SOBA Fabric provides industry-specific semantic "dial tones" that enable applications to plug and play at the business process level, using standardized XML business vocabularies. We describe the SOBA Architecture and present a case study from a successful deployment in the Insurance sector.

The fundamental challenge of e-commerce is enabling companies to do business with one another across a network, despite different business processes and computer systems. Traditionally, these problems were overcome through custom point-to-point integration or Electronic Data Interchange (EDI) networks. These expensive, time-consuming approaches make economic sense only when companies do a lot of business together. The promise of the Internet, by contrast, is an open e-business platform where companies can do business spontaneously with anyone, anywhere, anytime. Business Services Networks fulfill that vision. This vision paper also presents CommerceNet's role in catalyzing industrial adoption.

6066 Background: ASCO abstracts are a leading source of cancer research information. The ASCO Breast Cancer Information Exchange (BCIE) project was developed to better organize and access abstracts in breast cancer for a faster, more precise, and targeted search. Methods: Traditional web search engines allow simple keyword-based queries. Improvements in precision and ease of use require software that “knows” the domain. We developed XML/Java models of breast cancer clinical studies, from molecular diagnostics to disease stages. From these models, we developed a study characterization form, included as a voluntary author step in the 2003 Annual Meeting abstract submission process, to capture the study clinical parameters. We also developed a corresponding user search form, publicly available onhttp://webapp.asco.org/bcie. Results: Almost 95% of breast cancer abstract first authors (352) participated, completing the web-based form to characterize their studies from a uniform descriptive variable set. Since 8/02, www.asco.org visitors have used the BCIE search tool to formulate queries. Analysis of a subset of queries (N=691) revealed that 90% selected form-based search variables exclusively or combined with traditional open keyword search terms. On average, 7 search variables were entered per search. The three most selected search variables were study phase, patient sex, and chemotherapeutic agent. In addition, the repository of characterized studies created a detailed index of author-selected consistent-variable descriptors, offering potential for examination of abstract trends within one disease-type, including study types, prognostic factors, therapies, diagnostics, and biomarkers. Heretofore, such analysis has been time consuming, performed manually, and not reflective of authors direct involvement. Conclusions: The BCIE project demonstrates the feasibility of a new technology and process for uniform XML-Java indexing, search, and analysis of published material. The project continues in 2004. Author Disclosure Employment or Leadership Consultant or Advisory Stock Ownership Honoraria Research Funding Expert Testimony Other Remuneration Medstory Medstory

article Free AccessAn XML framework for agent-based E-commerce Authors: Robert J. Glushko Veo Systems, Inc., Mountain View, CA Veo Systems, Inc., Mountain View, CAView Profile , Jay M. Tenenbaum Veo Systems, Inc., Mountain View, CA Veo Systems, Inc., Mountain View, CAView Profile , Bart Meltzer Veo Systems, Inc., Mountain View, CA Veo Systems, Inc., Mountain View, CAView Profile Authors Info & Claims Communications of the ACMVolume 42Issue 3March 1999 pp 106–ff.https://doi.org/10.1145/295685.295720Published:01 March 1999Publication History 170citation3,843DownloadsMetricsTotal Citations170Total Downloads3,843Last 12 Months171Last 6 weeks16 Get Citation AlertsNew Citation Alert added!This alert has been successfully added and will be sent to:You will be notified whenever a record that you have chosen has been cited.To manage your alert preferences, click on the button below.Manage my AlertsNew Citation Alert!Please log in to your account Save to BinderSave to BinderCreate a New BinderNameCancelCreateExport CitationPublisher SiteView all FormatsPDF

eb information systems are revolutionizing commerce. For starters, the Web reduces to nearly nothing many marginal costs of doing business, such as communications and customer service. Startup companies such as Amazon.com and CDNow have outperformed the leading national chains by successfully adapting traditional telephone and catalog sales models to exploit these radical economics. Similar competitive advantages are now being achieved in the services sector by Web-based banks, stock traders, insurance brokers, and travel agents. Indeed, the Web’s advantages are even more pronounced with services because fulfillment as well as sales can be completed online. A handful of supersites now offer customers the opportunity to compare thousands of insurance policies and loans. No wonder expensive networks of brokers and bank branches, with their limited selection of proprietary products and inefficient paper-based processes, are increasingly seen as liabilities rather than assets. These early successes, though impressive, barely tap the Web’s potential for transforming commerce. The next generation of Web-based businesses will not merely adapt existing business models and organizations; they will invent fundamentally new ones that are inconceivable without the Net. Their focus will not be on selling things from a Web site but rather on using the Web to link buyers, sellers, and organizations in innovative ways. Moreover, they will exploit emerging technology that is making the Web accessible to computers as well as people. Today’s Web provides people with unprecedented access to online information and services. However, because the information is unstructured, computers cannot readily understand it. This limitation helps explain why search engines and automated shopping agents don’t work very well. Tomorrow’s Web will provide information and services in a structured form that is readily accessible to both people and computers. Companies will publish data sheets, price lists, airline schedules, stock reports, bank statements and the like directly on the