Search

Motivation Gene expression data are commonly used at the intersection of cancer research and machine learning for better understanding of the molecular status of tumour tissue. Deep learning predictive models have been employed for gene expression data due to their ability to scale and remove the need for manual feature engineering. However, gene expression data are often very high dimensional, noisy and presented with a low number of samples. This poses significant problems for learning algorithms: models often overfit, learn noise and struggle to capture biologically relevant information. In this article, we utilize external biological knowledge embedded within structures of gene interaction graphs such as protein–protein interaction (PPI) networks to guide the construction of predictive models. Results We present Gene Interaction Network Constrained Construction (GINCCo), an unsupervised method for automated construction of computational graph models for gene expression data that are structurally constrained by prior knowledge of gene interaction networks. We employ this methodology in a case study on incorporating a PPI network in cancer phenotype prediction tasks. Our computational graphs are structurally constructed using topological clustering algorithms on the PPI networks which incorporate inductive biases stemming from network biology research on protein complex discovery. Each of the entities in the GINCCo computational graph represents biological entities such as genes, candidate protein complexes and phenotypes instead of arbitrary hidden nodes of a neural network. This provides a biologically relevant mechanism for model regularization yielding strong predictive performance while drastically reducing the number of model parameters and enabling guided post-hoc enrichment analyses of influential gene sets with respect to target phenotypes. Our experiments analysing a variety of cancer phenotypes show that GINCCo often outperforms support vector machine, Fully Connected Multi-layer Perceptrons (MLP) and Randomly Connected MLPs despite greatly reduced model complexity. Availability and implementation https://github.com/paulmorio/gincco contains the source code for our approach. We also release a library with algorithms for protein complex discovery within PPI networks at https://github.com/paulmorio/protclus. This repository contains implementations of the clustering algorithms used in this article. Supplementary information Supplementary data are available at Bioinformatics online.

Deep learning models are receiving increasing attention in clinical decision-making, however the lack of interpretability and explainability impedes their deployment in day-to-day clinical practice. We propose REM, an interpretable and explainable methodology for extracting rules from deep neural networks and combining them with other data-driven and knowledge-driven rules. This allows integrating ma- chine learning and reasoning for investigating applied and basic biological research questions. We evaluate the utility of REM on the predictive tasks of classifying histological and immunohistochemical breast cancer subtypes from genotype and phenotype data. We demonstrate that REM efficiently extracts accurate, compre- hensible and, biologically relevant rulesets from deep neural networks that can be readily integrated with rulesets obtained from tree-based approaches. REM provides explanation facilities for predictions and enables the clinicians to vali- date and calibrate the extracted rulesets with their domain knowledge. With these functionalities, REM caters for a novel and direct human-in-the-loop approach in clinical decision making.

Artificial intelligence (AI) has boundless potential in healthcare. In this chapter, we consider how to facilitate interactions between healthcare practitioners and AI systems. We discuss how AI can extend a practitioner’s expertise by leveraging the predictive power of AI systems. When AI systems are aligned with human values, practitioners can place appropriate trust in AI systems. Current applications of AI systems in clinical settings are limited to model-driven systems, some of which explicitly encode practitioner preferences as rules. We explore how AI systems can scrutinize datasets for insights, find new drugs or treatments, or provide clinical decision support to practitioners. Moreover, AI systems can show their trustworthiness to practitioners, by displaying predictability, procedural transparency, algorithmic transparency, and robustness. Practitioners are essential to the successful deployment of AI systems. The merit of AI in healthcare will come from AI deployed responsibly with practitioners in mind.

Emotion regulation is among the most important skills that children and adolescents need to be successful in their social lives. Individuals with autism spectrum disorder have serious deficit in regulating their emotions. Various treatments have been used to improve emotion regulation in children with autism including using video games designed to improve emotion regulation, has attracted many researchers, treating autism or other groups of children with special needs. These games can be used with or without a therapist presence which would save money and energy. This study aimed to evaluate the effects of EmoGalaxy, a video game designed to improve emotion regulation of children with autism spectrum disorder, compared to a card games with emotion regulation approach. Effectiveness of both interventions were evaluated by a quasi-experimental research with pretest-posttest and a control group. 10 students in the first experimental group played with EmoGalaxy, while the second experimental group, with 10 students, played regular cards games. The control group, consisted of 10 students did not receive any treatment and waited to receive the intervention after the experimental group intervention period. The instrument used in this study to evaluate the emotion regulation of the participants was the emotion regulation checklist (Shields & Cicchetti, 2004). The obtained data was analyzed by Multiple Analysis of the Covariance (MANCOVA). The results of the study showed that computer cognitive games led to significant changes compared to the other experimental group and the control group in emotion regulation (p

Multi-Agent Reinforcement Learning (MARL) encompasses a powerful class of methodologies that have been applied in a wide range of fields. An effective way to further empower these methodologies is to develop libraries and tools that could expand their interpretability and explainability. In this work, we introduce MARLeME: a MARL model extraction library, designed to improve explainability of MARL systems by approximating them with symbolic models. Symbolic models offer a high degree of interpretability, well-defined properties, and verifiable behaviour. Consequently, they can be used to inspect and better understand the underlying MARL system and corresponding MARL agents, as well as to replace all/some of the agents that are particularly safety and security critical., Presented at the KR2ML workshop at the 33rd Conference on Neural Information Processing Systems (NeurIPS 2019), Vancouver, Canada

In a normative environment, an agent’s actions are directed not only by its goals but also by the norms activated by its actions and those of other actors. The potential for conflict between agent goals and norms makes decision making challenging, in that it requires looking ahead to consider the longer-term consequences of which goal to satisfy or which norm to comply with in face of conflict. We therefore seek to determine the actions an agent should select at each point in time, taking account of its temporal goals, norms, and their conflicts. We propose a solution in which a normative planning problem is the basis for practical reasoning based on argumentation. Various types of conflict within goals, within norms, and between goals and norms are identified based on temporal properties of these entities. The properties of the best plan(s) with respect to goal achievement and norm compliance are mapped to arguments, followed by mapping their conflicts to attack between arguments, all of which are used to identify why a plan is justified.

International initiatives such as the Molecular Taxonomy of Breast Cancer International Consortium (METABRIC), Cancer Genome Atlas (TCGA), and the International Cancer Genome Consortium (ICGC) are collecting multiple data sets at different genome-scales with the aim to identify novel cancer bio-markers and predict patient survival. To analyse such data, several machine learning, bioinformatics and statistical methods have been applied, among them neural networks such as autoencoders. Although these models provide a good statistical learning framework to analyse multi-omic and/or clinical data, there is a distinct lack of work on how to integrate diverse patient data and identify the optimal design best suited to the available data. In this paper, we investigate several autoencoder architectures that integrate a variety of cancer patient data types (e.g., multi-omics and clinical data). We perform extensive analyses of these approaches and provide a clear methodological and computational framework for designing systems that enable clinicians to investigate cancer traits and translate the results into clinical applications. We demonstrate how these networks can be designed, built and, in particular, applied to tasks of integrative analyses of heterogeneous breast cancer data. The results show that these approaches yield relevant data representations that, in turn, lead to accurate and stable diagnosis.

This study deals with the application of the sequential function specification method for estimating the unknown time-dependent base temperature in a porous fin based on the temperature measurement...

The aim of this study is to investigate the effects of nanoparticles type, nanoparticles size, and droplet size on the ignition probability of the diesel fuel. Also, the effect of metal oxide nanoparticles on the ignition delay of diesel fuel droplets is studied. A series of hot plate ignition tests are conducted for diesel fuel with and without Al 2 O 3 , TiO 2 and Fe 3 O 4 nanoparticles at different concentrations (up to 0.05 wt.%). The experimental results show that the ignition probability of the diesel fuel significantly increases in the presence of metal oxide nanoparticles. The ignition probabilities of diesel/Al 2 O 3 and diesel/Fe 3 O 4 nanofuels are almost similar and higher than that of diesel/TiO 2 nanofuel. Results for diesel/Al 2 O 3 show that the nanoparticle size does not affect the ignition probability of nanofuel. Moreover, results indicate that the ignition probability decreases by increasing the droplet size. Investigations show that the ignition delay for diesel fuel droplets decreases in the presence of Al 2 O 3 nanoparticles.

Autonomous software agents operating in dynamic environments need toconstantly reason about actions in pursuit of their goals, while taking intoconsideration norms which might be imposed on those actions. Normativepractical reasoning supports agents making decisions about what is best forthem to (not) do in a given situation. What makes practical reasoning chal-lenging is the interplay between goals that agents are pursuing and the normsthat the agents are trying to uphold. We offer a formalisation to allow agentsto plan for multiple goals and norms in the presence of durative actions thatcan be executed concurrently. We compare plans based on decision-theoreticnotions (i.e. utility) such that the utility gain of goals and utility loss of normviolations are the basis for this comparison. The set of optimal plans consistsof plans that maximise the overall utility, each of which can be chosen by theagent to execute. We provide an implementation of our proposal in AnswerSet Programming, thus allowing us to state the original problem in terms ofa logic program that can be queried for solutions with specific properties.

When formalising the rules of trust in the remote attesta- tion of TPM-based computer systems it is paramount that the rules are precisely understood, supporting unambiguous communication of infor- mation about system requirements between engineers. We present a dia- grammatic approach to modelling rules of trust using an extended version of concept diagrams. Within the context of our proof-of-concept Net- work Function Virtualisation and Attestation environment, these rules allow different level of trust to be explored and, importantly, allow us to identify when a computer system should not be trusted. To ensure that the modelling approach can be applied to general systems, we in- clude generic patterns for extending our domain model and rules of trust. Consequently, through the use of a formal, yet accessible, diagrammatic notation, domain experts can define rules of trust for their systems.

Research in psychology about reasoning has often been restricted to relatively inexpressive statements involving quantifiers (e.g. syllogisms). This is limited to situations that typically do not arise in practical settings, like ontology engineering. In order to provide an analysis of inference, we focus on reasoning tasks presented in external graphic representations where statements correspond to those involving multiple quantifiers and unary and binary relations. Our experiment measured participants’ performance when reasoning with two notations. The first notation used topological constraints to convey information via node-link diagrams (i.e. graphs). The second used topological and spatial constraints to convey information (Euler diagrams with additional graph-like syntax). We found that topo-spatial representations were more effective for inferences than topological representations alone. Reasoning with statements involving multiple quantifiers was harder than reasoning with single quantifiers in topological representations, but not in topo-spatial representations. These findings are compared to those in sentential reasoning tasks.

Ontologies are notoriously hard to define, express and reason about. Many tools have been developed to ease the debugging and the reasoning process with ontologies, however they often lack accessibility and formalisation. A visual representation language, concept diagrams, was developed for expressing and reasoning about ontologies in an accessible way. Indeed, empirical studies show that concept diagrams are cognitively more accessible to users in ontology debugging tasks. In this paper we answer the question of “ How can concept diagrams be used to reason about inconsistencies and incoherence of ontologies?”. We do so by formalising a set of inference rules for concept diagrams that enables stepwise verification of the inconsistency and/or incoherence of a set of ontology axioms. The design of inference rules is driven by empirical evidence that concise (merged) diagrams are easier to comprehend for users than a set of lower level diagrams that offer a one-to-one translation of OWL ontology axioms into concept diagrams. We prove that our inference rules are sound, and exemplify how they can be used to reason about inconsistencies and incoherence. Finally, we indicate how our rules can serve as a foundation for new rules required when representing ontologies in diverse new domains.

© Springer International Publishing AG 2017. Ontologies are notoriously hard to define, express and reason about. Many tools have been developed to ease the ontology debugging and reasoning, however they often lack accessibility and formalisation. A visual representation language, concept diagrams, was developed for expressing ontologies, which has been empirically proven to be cognitively more accessible to ontology users. In this paper we answer the question of “How can concept diagrams be used to reason about inconsistencies and incoherence of ontologies?". We do so by formalising a set of inference rules for concept diagrams that enables stepwise verification of the inconsistency and incoherence of a set of ontology axioms. The design of inference rules is driven by empirical evidence that concise (merged) diagrams are easier to comprehend for users than a set of lower level diagrams that are a one-to-one translation from OWL ontology axioms. We prove that our inference rules are sound, and exemplify how they can be used to reason about inconsistencies and incoherence.

The present study experimentally investigates the effect of metal oxide nanoparticles on the ignition probability, ignition zone, and burning time of the diesel fuel. For this purpose, a series of hot plate ignition tests are conducted on the diesel fuel droplets with and without nanoparticles. The comparative performances of the pure diesel and diesel fuel containing 0.03 and 0.05 wt% of Al2O3, CeO2, Fe3O4, and TiO2 nanoparticles are examined. The thermo-physical properties of the nanofuels, including thermal conductivity, viscosity, and heat capacity are also measured. The experimental results show that in the presence of metal oxide nanoparticles, the ignition probability significantly increases. It is observed that cerium oxide nanoparticles show the greatest effect on the ignition probability. In addition, it is found that the minimum hot plate ignition temperature decreases. Results show that the burning time and the ignition zone decrease by adding metal oxide nanoparticles.

High-tech systems are ubiquitous and often safety and security critical: reasoning about their correctness is paramount. Thus, precise modelling and formal reasoning are necessary in order to convey knowledge unambiguously and accurately. Whilst mathematical modelling adds great rigour, it is opaque to many stakeholders which leads to errors in data handling, delays in product release, for example. This is a major motivation for the development of diagrammatic approaches to formalisation and reasoning about models of knowledge. In this paper, we present an interactive theorem prover, called iCon, for a highly expressive diagrammatic logic that is capable of modelling OWL 2 ontologies and, thus, has practical relevance. Significantly, this work is the first to design diagrammatic inference rules using insights into what humans find accessible. Specifically, we conducted an experiment about relative cognitive benefits of primitive (small step) and derived (big step) inferences, and use the results to guide the implementation of inference rules in iCon.

© 2017 ACM. Ontologies describe complex world knowledge in that they consist of hierarchical relations, such as is-a, which can be expressed by quantifiers or sets, and various binary relations, which can be expressed by links or networks. Should hierarchical relations be distinguished from other binary relations as essentially different ones in building cognitively accessible systems of ontologies? In this study, two kinds of ontology visualizations, a network-based visualization (SOVA) and a set-based visualization (concept diagrams), are empirically compared in the case of consistency checking. Participants were presented with one diagram and then asked to answer the question of whether the meaning of the diagram was contradictory. Our results showed that SOVA is more effective than concept diagrams, suggesting that to represent hierarchical and binary relations of ontologies in a way based on networks suits human cognition when checking ontologies' consistencies.

Analysis and evaluation of land use patterns are of prime importance for natural resources management. Recent studies on land use allocation have been mainly based on linear programming optimization. Although these methods have the ability to solve multi-objective problems, spatial aspects of optimization are not considered when they are used for land use management. This study applied the non-dominated sorting genetic algorithm II (NSGA-II) to optimize land-use allocation in the Taleghan watershed, northwest of Karaj, Iran. The four land use classes of irrigated farming, dry farming, rangeland, and other uses were extracted from the ETM+ image. The objective functions of the proposed model were erosion, economic return, suitability, and compactness-compatibility. A novel crossover operator called exchange randomly block (ERB) was used to exchange information between individuals. Results showed that the optimization model can find a set of optimal land use combinations in accordance with the proposed conditions. For comparison purposes, land use allocation was also done using the combined goal attainment-multi-objective land allocation (GoA-MOLA) approach. The results showed that NSGA-II performance acceptably when compared to GoA-MOLA.

The solution of an inverse, conduction-radiation problem in a two-dimensional rectangle is analyzed to determine the temperature-dependent emissivity at the boundary. The medium is gray, absorbing, emitting and isotropically scattering. The bounding surfaces are assumed to be opaque and diffuse. The inverse problem is solved by minimizing the performance function, which is expressed by the sum of square residuals between estimated and exact heat fluxes, using a combined method of genetic algorithm and conjugate gradient. The emissivity is assumed to be represented as a function of boundary temperature with unknown variables. Therefore, the inverse problem is treated by the estimation of these variables. Finally, four examples are presented to show the accuracy of the algorithm. The effect of the measurement errors on the accuracy of the inverse analysis is also investigated. Results show the algorithm can estimate the unknown emissivity when the measurement errors are neglected. Also it is found that increasing the measurement error decreases the accuracy of estimation of temperature-dependent emissivity.

In this paper we propose a labelling based dialogue game for determining whether a single argument within a Dung argumentation framework is skeptically preferred. Our game consists of two phases, and determines the membership of a single argument within the extension, assuming optimal play by dialogue participants. In the first phase, one player attempts to advance arguments to construct an extension not containing the argument under consideration, while the second phase verifies that the extension is indeed a preferred one. Correctness within this basic game requires perfect play by both players, and we therefore also introduce an overarching game to overcome this limitation.

Autonomous agents operating in a dynamic environment need constantly to reason about actions in pursuit of their goals, while taking into consideration possible norms imposed on those actions. Normative practical reasoning supports agents decision making about what is best for an agent to do in a given situation. What makes practical reasoning challenging is the conflict between goals that the agent is pursuing and the norms that the agent is trying to uphold. We offer a formal model that allows the agents to plan for conflicting goals and norms in presence of durative actions that can be executed concurrently. We compare plans based on decision-theoretic notions (i.e. utility) such that the utility gain of goals and utility loss of norm violations are the basis of this comparison. The set of optimal plans consists of plans that maximise the overall utility, each of which can be chosen by the agent to execute. The formal model is implemented computationally using answer set programming, which in turns permits the statement of the problem in terms of a logic program that can be queried for solutions with specific properties. We demonstrate how a normative practical reasoning problem can be mapped into an answer set program such that the optimal plans of the former can be obtained as the answer sets of the latter.

Reasoning about what is best for an agent to do in a particular situation is a challenging task. What makes it even more challenging in a dynamic environment is the existence of norms that aim to regulate a self-interested agent’s behaviour. Practical reasoning is reasoning about what to do in a given situation, particularly in the presence of conflicts between the agent’s practical attitude such as goals, plans and norms. In this paper we: (i) introduce a formal model for normative practical reasoning that allows an agent to plan for multiple and potentially conflicting goals and norms at the same time (ii) identify the best plan(s) for the agent to execute by means of argumentation schemes and critical questions (iii) justify the best plan(s) via an argumentation-based persuasion dialogue for grounded semantics.

In this paper we propose ArgPROLEG, a normative framework for legal reasoning based on PROLEG, an implementation of the Japanese “theory of presupposed ultimate facts”(JUF). This theory was mainly developed with the purpose of modelling the process of decision making by judges in the court. Not having complete and accurate information about each case, makes uncertainty an unavoidable part of decision making for judges. In the JUF theory each party that puts forward a claim, due to associated burden of proof to each claim, it needs to prove it as well. Not being able to provide such a proof for a claim, enables the judges to discard that claim although they might not be certain about the truth. The framework that we offer benefits from the use of argumentation theory as well as normative framework in multi-agent systems, to bring the reasoning closer to the user. The nature of argumentation in dealing with incomplete information on the one hand and being presentable in the form of dialogues on the other hand, has furthered the emergence and popularity of argumentation in modelling legal disputes. In addition, the use of multiple agents allows more flexibility for the behaviour of the parties involved.