A Data Mining Approach to In Vivo Classification of Psychopharmacological Drugs

Abstract

Data mining is a powerful bioinformatics strategy that has been successfully applied in vitro to screen for gene-expression profiles predicting toxicological or carcinogenic response ('class predictors'). In this report we used a data mining algorithm named Pattern Array (PA) in vivo to analyze mouse open-field behavior and characterize the psychopharmacological effects of three drug classesFpsychomotor stimulant, opioid, and psychotomimetic. PA represents rodent movement with B100 000 complex patterns, defined as multiple combinations of several ethologically relevant variables, and mines them for those that maximize any effect of interest, such as the difference between drug classes. We show that PA can discover behavioral predictors of all three drug classes, thus developing a reliable drug-classification scheme in small group sizes. The discovered predictors showed orderly dose dependency despite being explicitly mined only for class differences, with the high doses scoring 4-10 standard deviations from the vehicle group. Furthermore, these predictors correctly classified in a dose-dependent manner four 'unknown' drugs (ie that were not used in the training process), and scored a mixture of a psychomotor stimulant and an opioid as being intermediate between these two classes. The isolated behaviors were highly heritable (h 2 450%) and replicable as determined in 10 inbred strains across three laboratories. PA can in principle be applied for mining behaviors predicting additional properties, such as within-class differences between drugs and within-drug dose-response, all of which can be measured automatically in a single session per animal in an open-field arena, suggesting a high potential as a tool in psychotherapeutic drug discovery.

Ethological concepts enhance the translational value of animal models

“…Golani and coworkers were among the first who illustrated the application of an automated recording of the development of locomotion patterns (e.g. Benjamini et al, 2010;Drai et al, 2001;Kafkafi et al, 2009;Lipkind et al, 2004). For example, when a mouse is allowed to explore a big circular open arena from an adjacent familiar cage, i.e.…”

“…It demonstrates that explorative behavior is not just the time spent in an open area or along the walls, but has a much more complex development of very specific behavioral sequences. Such an ethological approach shows that the analysis of temporal development of locomotion paths could yield very reliable behavioral endpoints with a high degree of discriminability (Benjamini et al, 2010;Drai et al, 2001;Kafkafi et al, 2009;Lipkind et al, 2004).…”

Challenges in the Search for Drugs to Treat Central Nervous System Disorders

“…The evolving behavioral data mining approaches (Tecott and Nestler, 2004;Arguello and Gogos, 2006;Kafkafi et al, 2008) recapitulate, to a degree, the pharmacometric approach to CNS drug discovery. They make possible the characterization of NCEs in vivo in a matter of weeks rather than years, are cost-and time-effective, and require only small quantities of test agent.…”

“…Advances in robotics, computer vision, and machine learning have led to the development of high-throughput, automated screens such as Psychogenics' SmartCube (Tecott and Nestler, 2004) and Pattern Array (Kafkafi et al, 2008) to characterize mouse behavior. SmartCube can collect many thousands of behavioral measurements in seconds, generating detailed behavioral phenotypes in response to an NCE that can then be compared to databases of existing CNS drugs and drug class "fingerprints" to predict therapeutic utility or side effect liability.…”

A Geometric Framework for Detection of Critical Points in a Trajectory Using Convex Hulls

“…Events and activities that are associated to either stop points or movements also give useful insights for studying trajectory differences and similarities [49,50]. When considering geometric properties, structuring a trajectory by line segments based on curvature points has been suggested as a valuable method for identifying the main characteristics and facilitating the search for trajectory patterns [28,[51][52][53][54][55]. Additional parameters such as velocity, direction, turning points and angle, acceleration, sinuosity, distance, and travel time surely provide further insights [56,57].…”