Simultaneous analysis of neuroactive compounds in zebrafish

Abstract

Purpose: Compounds that act on the central nervous system (CNS) are crucial tools in drug discovery and neuroscience. To discover compounds with novel mechanisms of action, researchers have developed behavioral screens in larval zebrafish including various methods to identify and classify hit compounds. However, these methods typically do not admit intuitive numerical scores of screen performance. This study describes methods to classify compounds simultaneously in zebrafish and quantify screen performance.Methods: We collected randomized, highly replicated data for two sets of compounds: 16 quality-control (QC) compounds and a reference set of 648 known CNS ligands. Machine learning models were trained to discriminate between compound-induced phenotypes, compare performance between protocols, and detect hit compounds.Results: Classification accuracy on the QC set was 94.3%. In addition, 106 of 648 CNS ligands were identified as phenotypically active, and hits were enriched for dopaminergic and serotonergic targets. The raw data is included to facilitate replication and data mining.Significance: This study describes methods to evaluate behavioral phenotyping assays, which can be used to facilitate comparison and standardization of data within the zebrafish phenotyping community.

Deep phenotypic profiling of neuroactive drugs in larval zebrafish

“…Various stimuli, such as acoustic sounds, light stimulus, and physical tapping of the multi-well plate stage, are performed to elicit diverse behavioral responses in the fish, as optimized previously 7 . We record videos of the fish's behavior throughout the experiment.…”

“…The mechanism of action of central nervous system (CNS) drugs remains poorly understood, even for those used for decades (e.g., ketamine 1 ). The complex nature of G-Protein Coupled Receptor (GPCR) and ion channel-mediated pathways of the vertebrate nervous system [2][3][4][5][6][7][8][9][10][11] exacerbate the problem. Because of the prevalence of polypharmacology in neuroactive drugs 12 , a "magic bullet" single-target approach to drug discovery 13 falls short 14 .…”

“…Despite historically limited throughput, rapid phenotypic profiling of thousands of compounds in vivo is now possible using larval zebrafish [17][18][19][20][21] . These vertebrates have high levels of shared genetics 22,23 and CNS anatomy 24 (with humans) and scale to high-throughput testing of complex behavioral readouts [2][3][4][5][6][7][8][9][10][11] . Phenotypic screening in larval zebrafish, combined with human-target-based cheminformatic methods such as the Similarity Ensemble Approach (SEA 25,26 ), and enrichment factor (EF) calculations 27,10,28,29 , have enabled novel drug discovery and target deconvolution for neuroactive phenotypes in mammals.…”

Identification of compounds producing non-visual photosensation via TRPA1 in zebrafish

“…Phenotypes were induced and recorded using a custom-built instrument that includes a camera, lighting, and various light, audio, and physical stimuli, as described in Myers-Turnbull et al 2020 45 and McCarroll et al 2019 29 . Briefly, plates were illuminated with a 760nm infrared light, and an AVT Pike digital camera (Allied Vision) fitted with an infrared-passing/visible light-blocking filter (LEE Filters LE8744 polyester #87) and mounted to a telecentric lens captured images at 25fps.…”

Prioritizing Virtual Screening with Interpretable Interaction Fingerprints

“…In the last few decades, machine learning (ML) and, in particular, deep neural networks (DNN) have opened up new opportunities in all stages of drug discovery and development. − In particular, ML has the potential to revolutionize structural-based virtual screening (SBVS) campaigns through the prioritization and automatic selection of promising compounds. SBVS nowadays − commonly involves a manual and intensive process called hit-picking, in which researchers evaluate and determine hit selection through molecular graphics programs to inspect the binding modes of hundreds of top-scoring compounds.…”