Itemset mining: A constraint programming perspective

The field of data mining has become accustomed to specifying constraints on patterns of interest. A large number of systems and techniques has been developed for solving such constraint-based mining problems, especially for mining itemsets. The approach taken in the field of data mining contrasts with the constraint programming principles developed within the artificial intelligence community. While most data mining research focuses on algorithmic issues and aims at developing highly optimized and scalable implementations that are tailored towards specific tasks, constraint programming employs a more declarative approach. The emphasis lies on developing high-level modeling languages and general solvers that specify what the problem is, rather than outlining how a solution should be computed, yet are powerful enough to be used across a wide variety of applications and application domains.This paper contributes a declarative constraint programming approach to data mining. More specifically, we show that it is possible to employ off-the-shelf constraint programming techniques for modeling and solving a wide variety of constraint-based itemset mining tasks, such as frequent, closed, discriminative, and cost-based itemset mining. In particular, we develop a basic constraint programming model for specifying frequent itemsets and show that this model can easily be extended to realize the other settings. This contrasts with typical procedural data mining systems where the underlying procedures need to be modified in order to accommodate new types of constraint, or novel combinations thereof. Even though the performance of state-of-the-art data mining systems outperforms that of the constraint programming approach on some standard tasks, we also show that there exist problems where the constraint programming approach leads to significant performance improvements over state-of-the-art methods in data mining and as well as to new insights into the underlying data mining problems. Many such insights can be obtained by relating the underlying search algorithms of data mining and constraint programming systems to one another. We discuss a number of interesting new research questions and challenges raised by the declarative constraint programming approach to data mining.     

The Protective Effects of the Autophagic and Lysosomal Machinery in Vascular and Valvular Calcification: A Systematic Review

Background: Autophagy is a highly conserved catabolic homeostatic process, crucial for cell survival. It has been shown that autophagy can modulate different cardiovascular pathologies, including vascular calcification (VCN). Objective: To assess how modulation of autophagy, either through induction or inhibition, affects vascular and valvular calcification and to determine the therapeutic applicability of inducing autophagy. Data sources: A systematic review of English language articles using MEDLINE/PubMed, Web of Science (WoS) and the Cochrane library. The search terms included autophagy, autolysosome, mitophagy, endoplasmic reticulum (ER)-phagy, lysosomal, calcification and calcinosis. Study characteristics: Thirty-seven articles were selected based on pre-defined eligibility criteria. Thirty-three studies (89%) studied vascular smooth muscle cell (VSMC) calcification of which 27 (82%) studies investigated autophagy and six (18%) studies lysosomal function in VCN. Four studies (11%) studied aortic valve calcification (AVCN). Thirty-four studies were published in the time period 2015–2020 (92%). Conclusion: There is compelling evidence that both autophagy and lysosomal function are critical regulators of VCN, which opens new perspectives for treatment strategies. However, there are still challenges to overcome, such as the development of more selective pharmacological agents and standardization of methods to measure autophagic flux.     

Q-measures and betweenness centrality in a collaboration network: a case study of the field of informetrics

We study global and local Q-measures, as well as betweenness centrality, as indicators of international collaboration in research. After a brief review of their definitions, we introduce the concepts of external and internal inter-group geodesics. These concepts are applied to a collaboration network of 1129 researchers from different countries, which is based on publications in bibliometrics, informetrics, webometrics, and scientometrics (BIWS in short) from the period 1990–2009. It is thus illustrated how international collaboration (among authors from different countries) in BIWS is carried out. Our results suggest that average scores for local Q-measures are typically higher, indicating a relatively low degree of international collaboration in BIWS. The dominating form of international collaboration is bilateral, whereas multilateral collaboration is relatively rare in the field of BIWS. We also identify and visualize the most important global and local actors. Dividing the entire period in four 5-year periods, it is found that most international collaboration in the field has happened in the last time slice (2005–2009). A comparison of the different time slices reveals the non-linear growth of the indicators studied and the international expansion of the field.     

Doxorubicin Impairs Smooth Muscle Cell Contraction: Novel Insights in Vascular Toxicity

Clinical and animal studies have demonstrated that chemotherapeutic doxorubicin (DOX) increases arterial stiffness, a predictor of cardiovascular risk. Despite consensus about DOX-impaired endothelium-dependent vasodilation as a contributing mechanism, some studies have reported conflicting results on vascular smooth muscle cell (VSMC) function after DOX treatment. The present study aimed to investigate the effects of DOX on VSMC function. To this end, mice received a single injection of 4 mg DOX/kg, or mouse aortic segments were treated ex vivo with 1 μM DOX, followed by vascular reactivity evaluation 16 h later. Phenylephrine (PE)-induced VSMC contraction was decreased after DOX treatment. DOX did not affect the transient PE contraction dependent on Ca²⁺ release from the sarcoplasmic reticulum (0 mM Ca²⁺), but it reduced the subsequent tonic phase characterised by Ca²⁺ influx. These findings were supported by similar angiotensin II and attenuated endothelin-1 contractions. The involvement of voltage-gated Ca²⁺ channels in DOX-decreased contraction was excluded by using levcromakalim and diltiazem in PE-induced contraction and corroborated by similar K⁺ and serotonin contractions. Despite the evaluation of multiple blockers of transient receptor potential channels, the exact mechanism for DOX-decreased VSMC contraction remains elusive. Surprisingly, DOX reduced ex vivo but not in vivo arterial stiffness, highlighting the importance of appropriate timing for evaluating arterial stiffness in DOX-treated patients.     

Publication patterns in the social sciences and humanities: evidence from eight European countries

Scientometrics - The increasing number of open-access full-text scientific documents promotes the transformation from metadata- to content-based studies, which is more detailed and semantic. Along...     

Learning constraints in spreadsheets and tabular data

Spreadsheets, comma separated value files and other tabular data representations are in wide use today. However, writing, maintaining and identifying good formulas for tabular data and spreadsheets can be time-consuming and error-prone. We investigate the automatic learning of constraints (formulas and relations) in raw tabular data in an unsupervised way. We represent common spreadsheet formulas and relations through predicates and expressions whose arguments must satisfy the inherent properties of the constraint. The challenge is to automatically infer the set of constraints present in the data, without labeled examples or user feedback. We propose a two-stage generate and test method where the first stage uses constraint solving techniques to efficiently reduce the number of candidates, based on the predicate signatures. Our approach takes inspiration from inductive logic programming, constraint learning and constraint satisfaction. We show that we are able to accurately discover constraints in spreadsheets from various sources.     

Recommending research collaborations using link prediction and random forest classifiers

We introduce a method to predict or recommend high-potential future (i.e., not yet realized) collaborations. The proposed method is based on a combination of link prediction and machine learning techniques. First, a weighted co-authorship network is constructed. We calculate scores for each node pair according to different measures called predictors. The resulting scores can be interpreted as indicative of the likelihood of future linkage for the given node pair. To determine the relative merit of each predictor, we train a random forest classifier on older data. The same classifier can then generate predictions for newer data. The top predictions are treated as recommendations for future collaboration. We apply the technique to research collaborations between cities in Africa, the Middle East and South-Asia, focusing on the topics of malaria and tuberculosis. Results show that the method yields accurate recommendations. Moreover, the method can be used to determine the relative strengths of each predictor.     

A comparison of cognitive and organizational classification of publications in the social sciences and humanities

Scientometrics - We study the discrepancy between two ways of classifying publications in the social sciences and humanities (SSH): on the basis of the contents of publications and publication...