An Exhaustive, Non-Euclidean, Non-Parametric Data Mining Tool for Unraveling the Complexity of Biological Systems – Novel Insights into Malaria

Abstract

Complex, high-dimensional data sets pose significant analytical challenges in the post-genomic era. Such data sets are not exclusive to genetic analyses and are also pertinent to epidemiology. There has been considerable effort to develop hypothesis-free data mining and machine learning methodologies. However, current methodologies lack exhaustivity and general applicability. Here we use a novel non-parametric, non-euclidean data mining tool, HyperCube®, to explore exhaustively a complex epidemiological malaria data set by searching for over density of events in m-dimensional space. Hotspots of over density correspond to strings of variables, rules, that determine, in this case, the occurrence of Plasmodium falciparum clinical malaria episodes. The data set contained 46,837 outcome events from 1,653 individuals and 34 explanatory variables. The best predictive rule contained 1,689 events from 148 individuals and was defined as: individuals present during 1992–2003, aged 1–5 years old, having hemoglobin AA, and having had previous Plasmodium malariae malaria parasite infection ≤10 times. These individuals had 3.71 times more P. falciparum clinical malaria episodes than the general population. We validated the rule in two different cohorts. We compared and contrasted the HyperCube® rule with the rules using variables identified by both traditional statistical methods and non-parametric regression tree methods. In addition, we tried all possible sub-stratified quantitative variables. No other model with equal or greater representativity gave a higher Relative Risk. Although three of the four variables in the rule were intuitive, the effect of number of P. malariae episodes was not. HyperCube® efficiently sub-stratified quantitative variables to optimize the rule and was able to identify interactions among the variables, tasks not easy to perform using standard data mining methods. Search of local over density in m-dimensional space, explained by easily interpretable rules, is thus seemingly ideal for generating hypotheses for large datasets to unravel the complexity inherent in biological systems.

Micro-, Meso- and Macro-Dynamics of the Brain

“…One data mining tool-Hypercube©-has already been used in medical research (Loucoubar et al 2011). We have preliminary data with this algorithm on a set of 200 patients from the Alzheimer's Disease Neuroimaging Initiative (ADNI) database (http://www.three-city-study.com/les-publications-scientifiques-de-l-etudedes-trois-cites.php) and also from a subset of 500 elderly subjects from the 3 Cities study (http://adni.loni.ucla.edu) and associated image-genetics-clinical-psychology cohorts followed in France for 10 years.…”

The Gracefully Aging Immune System

“…In the case of anti-in+ uenza vaccination, the intradermal inoculum appeared to yield a small improvement, both in the elderly and in people with chronic diseases (35). Approaches to counterbalancing the ef ects of immunosenescence (such as by improving the BMI) can also increase the response to vaccination (36).…”

Human Genetic Contribution to the Outcome of Infection with Malaria Parasites

“…This suggests that common mechanisms do govern susceptibility to infection by P. vivax and control of P. falciparum density but not control of P. vivax density. Given the differences in red blood cell tropism, although blood disorders may be implicated, the involvement of shared immunological mechanisms is likely, supporting the hypothesis that there is significant cross-species protective immunity (Loucoubar et al, 2011b).…”

“…The duration of a single infection varies significantly: P. malariae seemingly lasts up to 30 years despite no evidence of the existence of exo-erythrocytic latent stages; P. vivax and most probably P. ovale have latent hypnozoite stages and thus although a single blood stage infection may be short-lived (less than a year), relapse extends the duration of a single infection; P. falciparum infections can last up to 2 years. Thus, whilst the current emphasis on P. falciparum has led to the identification of genetic factors controlling certain clinical and biological phenotypes, their relevance to other species may not be certain and there is much to be done with respect to the three non-falciparum species infecting man (Louicharoen et al, 2009). Plasmodium knowlesi, although shown to infect man, has yet to be sufficiently studied to be amenable for human genetic study.…”