An autonomous debating system.

Artificial intelligence (AI) is defined as the ability of machines to perform tasks that are usually associated with intelligent beings. Argument and debate are fundamental capabilities of human intelligence, essential for a wide range of human activities, and common to all human societies. The development of computational argumentation technologies is therefore an important emerging discipline in AI research1. Here we present Project Debater, an autonomous debating system that can engage in a competitive debate with humans. We provide a complete description of the system's architecture, a thorough and systematic evaluation of its operation across a wide range of debate topics, and a detailed account of the system's performance in its public debut against three expert human debaters. We also highlight the fundamental differences between debating with humans as opposed to challenging humans in game competitions, the latter being the focus of classical 'grand challenges' pursued by the AI research community over the past few decades. We suggest that such challenges lie in the 'comfort zone' of AI, whereas debating with humans lies in a different territory, in which humans still prevail, and for which novel paradigms are required to make substantial progress.

Evicase: an evidence-based case structuring approach for personalized healthcare.

The personalized medicine era stresses a growing need to combine evidence-based medicine with case based reasoning in order to improve the care process. To address this need we suggest a framework to generate multi-tiered statistical structures we call Evicases. Evicase integrates established medical evidence together with patient cases from the bedside. It then uses machine learning algorithms to produce statistical results and aggregators, weighted predictions, and appropriate recommendations. Designed as a stand-alone structure, Evicase can be used for a range of decision support applications including guideline adherence monitoring and personalized prognostic predictions.

Automatic detection of inconsistencies between free text and coded data in Sarcoma discharge letters.

Discordance between data stored in Electronic Health Records (EHR) may have a harmful effect on patient care. Automatic identification of such situations is an important yet challenging task, especially when the discordance involves information stored in free text fields. Here we present a method to automatically detect inconsistencies between data stored in free text and related coded fields. Using EHR data we train an ensemble of classifiers to predict the value of coded fields from the free text fields. Cases in which the classifiers predict with high confidence a code different from the clinicians' choice are marked as potential inconsistencies. Experimental results over discharge letters of sarcoma patients, verified by a domain expert, demonstrate the validity of our method.

Knowledge-analytics synergy in Clinical Decision Support.

Clinical Decision Support (CDS) systems hold tremendous potential for improving patient care. Most existing systems are knowledge-based tools that rely on relatively simple rules. More recent approaches rely on analytics techniques to automatically mine EHR data to reveal meaningful insights. Here, we propose the Knowledge-Analytics Synergy paradigm for CDS, in which we synergistically combine existing relevant knowledge with analytics applied to EHR data. We propose a framework for implementing such a paradigm and demonstrate its principles over real-world clinical and genomic data of hypertensive patients.

Prognostic data-driven clinical decision support - formulation and implications.

Existing Clinical Decision Support Systems (CDSSs) typically rely on rule-based algorithms and focus on tasks like guidelines adherence and drug prescribing and monitoring. However, the increasing dominance of Electronic Health Record technologies and personalized medicine suggest great potential for prognostic data-driven CDSS. A major goal for such systems would be to accurately predict the outcome of patients' candidate treatments by statistical analysis of the clinical data stored at a Health Care Organization. We formally define the concepts involved in the development of such a system, highlight an inherent difficulty arising from bias in treatment allocation, and propose a general strategy to address this difficulty. Experiments over hypertension clinical data demonstrate the validity of our approach.

Exploring transcription regulation through cell-to-cell variability.

The regulation of cellular protein levels is a complex process involving many regulatory mechanisms, each introducing stochastic events, leading to variability of protein levels between isogenic cells. Previous studies have shown that perturbing genes involved in transcription regulation affects the amount of cell-to-cell variability in protein levels, but to date there has been no systematic characterization of variability in expression as a phenotype. In this research, we use single-cell expression levels of two fluorescent reporters driven by two different promoters under a wide range of genetic perturbations in Saccharomyces cerevisiae, to identify proteins that affect variability in the expression of these reporters. We introduce computational methodology to determine the variability caused by each perturbation and distinguish between global variability, which affects both reporters in a coordinated manner (e.g., due to cell size variability), and local variability, which affects the individual reporters independently (e.g., due to stochastic events in transcription initiation). Classifying genes by their variability phenotype (the effect of their deletion on reporter variability) identifies functionally coherent groups, which broadly correlate with the different stages of transcriptional regulation. Specifically, we find that most processes whose perturbation affects global variability are related to protein synthesis, protein transport, and cell morphology, whereas most processes whose perturbations affect local variability are related to DNA maintenance, chromatin regulation, and RNA synthesis. Moreover, we demonstrate that the variability phenotypes of different protein complexes provide insights into their cellular functions. Our results establish the utility of variability phenotype for dissecting the regulatory mechanisms involved in gene expression.

Modularity and directionality in genetic interaction maps.

MOTIVATION: Genetic interactions between genes reflect functional relationships caused by a wide range of molecular mechanisms. Large-scale genetic interaction assays lead to a wealth of information about the functional relations between genes. However, the vast number of observed interactions, along with experimental noise, makes the interpretation of such assays a major challenge. RESULTS: Here, we introduce a computational approach to organize genetic interactions and show that the bulk of observed interactions can be organized in a hierarchy of modules. Revealing this organization enables insights into the function of cellular machineries and highlights global properties of interaction maps. To gain further insight into the nature of these interactions, we integrated data from genetic screens under a wide range of conditions to reveal that more than a third of observed aggravating (i.e. synthetic sick/lethal) interactions are unidirectional, where one gene can buffer the effects of perturbing another gene but not vice versa. Furthermore, most modules of genes that have multiple aggravating interactions were found to be involved in such unidirectional interactions. We demonstrate that the identification of external stimuli that mimic the effect of specific gene knockouts provides insights into the role of individual modules in maintaining cellular integrity. AVAILABILITY: We designed a freely accessible web tool that includes all our findings, and is specifically intended to allow effective browsing of our results (http://compbio.cs.huji.ac.il/GIAnalysis). SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.