Distinguishing classes of neuroactive drugs based on computational physicochemical properties and experimental phenotypic profiling in planarians

Abstract

AbstractMental illnesses put a tremendous burden on afflicted individuals and society. Identification of novel drugs to treat such conditions is intrinsically challenging due to the complexity of neuropsychiatric diseases and the need for a systems-level understanding that goes beyond single molecule-target interactions. Thus far, drug discovery approaches focused on target-basedin silicoorin vitrohigh-throughput screening (HTS) have had limited success because they cannot capture pathway interactions or predict how a compound will affect the whole organism. Organismal behavioral testing is needed to fill the gap, but mammalian studies are too time-consuming and cost-prohibitive for the early stages of drug discovery. Behavioral HTS in small organisms promises to address this need and complementin silicoandin vitroHTS to improve the discovery of novel neuroactive compounds. Here, we used cheminformatics and HTS in the freshwater planarianDugesia japonica– an invertebrate system used for neurotoxicant HTS – to evaluate the extent to which complementary insight could be gained from the two data streams. In this pilot study, our goal was to classify 19 neuroactive compounds into their functional categories: antipsychotics, anxiolytics, and antidepressants. Drug classification was performed with the same computational methods, using either physicochemical descriptors or planarian behavioral profiling. As it was not obviousa prioriwhich classification method was most suited to this task, we compared the performance of four classification approaches. We used principal coordinate analysis or uniform manifold approximation and projection, each coupled with linear discriminant analysis, and two types of machine learning models –artificial neural net ensembles and support vector machines. Classification based on physicochemical properties had comparable accuracy to classification based on planarian profiling, especially with the machine learning models that all had accuracies of 90-100%. Planarian behavioral HTS correctly identified drugs with multiple therapeutic uses, thus yielding additional information compared to cheminformatics. Given that planarian behavioral HTS is an inexpensive true 3R (refine, reduce, replace) alternative to vertebrate testing and requires zeroa prioriknowledge about a chemical, it is a promising experimental system to complementin silicoHTS to identify new drug candidates.Author summaryIdentifying drugs to treat neuropsychiatric diseases is difficult because the complexity of the human brain remains incompletely understood. Pathway interactions and compensatory mechanisms make it challenging to identify new compounds using computational models and cell-based assays that evaluate potential interactions with specific protein targets. Despite major efforts, neither of these approaches alone nor in combination have been particularly successful in identifying novel neuroactive drugs. Here, we test the hypothesis that rapid behavioral screening using an aquatic invertebrate flatworm, the planarianDugesia japonica,augments the information obtained from computational models based on the physical and chemical properties of neuroactive drugs. Using 19 drugs classified by the vendor as antipsychotics, antidepressants, or anxiolytics, we found that planarian screening could correctly classify most of the drugs based on behavior alone. For compounds known to have multiple therapeutic uses, planarian phenotyping correctly identified the “off-label” class, thereby uncovering effects that were not predicted using the physicochemical properties of the drug alone. This pilot study is the first to show that behavioral phenotyping in a flatworm can be used to classify neuroactive drugs.