Research output: Contribution to journal › Article › peer-review
Artificial intelligence-driven phenotyping of zebrafish psychoactive drug responses. / Bozhko, Dmitrii V; Myrov, Vladislav O; Kolchanova, Sofia M; Polovian, Aleksandr I; Galumov, Georgii K; Demin, Konstantin A; Zabegalov, Konstantin N; Strekalova, Tatiana; de Abreu, Murilo S; Petersen, Elena V; Kalueff, Allan V.
In: Progress in Neuro-Psychopharmacology and Biological Psychiatry, Vol. 112, 110405, 10.01.2022, p. 110405.Research output: Contribution to journal › Article › peer-review
}
TY - JOUR
T1 - Artificial intelligence-driven phenotyping of zebrafish psychoactive drug responses
AU - Bozhko, Dmitrii V
AU - Myrov, Vladislav O
AU - Kolchanova, Sofia M
AU - Polovian, Aleksandr I
AU - Galumov, Georgii K
AU - Demin, Konstantin A
AU - Zabegalov, Konstantin N
AU - Strekalova, Tatiana
AU - de Abreu, Murilo S
AU - Petersen, Elena V
AU - Kalueff, Allan V
N1 - Publisher Copyright: © 2021
PY - 2022/1/10
Y1 - 2022/1/10
N2 - Zebrafish (Danio rerio) are rapidly emerging in biomedicine as promising tools for disease modelling and drug discovery. The use of zebrafish for neuroscience research is also growing rapidly, necessitating novel reliable and unbiased methods of neurophenotypic data collection and analyses. Here, we applied the artificial intelligence (AI) neural network-based algorithms to a large dataset of adult zebrafish locomotor tracks collected previously in vivo experiments with multiple established psychotropic drugs. We first trained AI to recognize various drugs from a wide range of psychotropic agents tested, and then confirmed prediction accuracy of trained AI by comparing several agents with known similar behavioral and pharmacological profiles. Presenting a framework for innovative neurophenotyping, this proof-of-concept study aims to improve AI-driven movement pattern classification in zebrafish, thereby fostering drug discovery and development utilizing this key model organism.
AB - Zebrafish (Danio rerio) are rapidly emerging in biomedicine as promising tools for disease modelling and drug discovery. The use of zebrafish for neuroscience research is also growing rapidly, necessitating novel reliable and unbiased methods of neurophenotypic data collection and analyses. Here, we applied the artificial intelligence (AI) neural network-based algorithms to a large dataset of adult zebrafish locomotor tracks collected previously in vivo experiments with multiple established psychotropic drugs. We first trained AI to recognize various drugs from a wide range of psychotropic agents tested, and then confirmed prediction accuracy of trained AI by comparing several agents with known similar behavioral and pharmacological profiles. Presenting a framework for innovative neurophenotyping, this proof-of-concept study aims to improve AI-driven movement pattern classification in zebrafish, thereby fostering drug discovery and development utilizing this key model organism.
KW - neural network
KW - Artificial intelligence
KW - locomotion
KW - Zebrafish
KW - CNS drug screening
KW - Locomotion
KW - Neural network
KW - SYSTEM
KW - ANXIETY
KW - BEHAVIOR
KW - MODEL
KW - ADULT ZEBRAFISH
KW - CANCER
KW - DEEP
KW - NEURAL-NETWORKS
KW - FRAMEWORK
KW - TOOLS
UR - http://www.scopus.com/inward/record.url?scp=85114049485&partnerID=8YFLogxK
UR - https://www.mendeley.com/catalogue/6e5f395a-c58d-3cd3-a210-c002c8a6942e/
U2 - 10.1016/j.pnpbp.2021.110405
DO - 10.1016/j.pnpbp.2021.110405
M3 - Article
C2 - 34320403
VL - 112
SP - 110405
JO - Progress in Neuro-Psychopharmacology and Biological Psychiatry
JF - Progress in Neuro-Psychopharmacology and Biological Psychiatry
SN - 0278-5846
M1 - 110405
ER -
ID: 84590998