Automated High-Throughput Damage Scoring of Zebrafish Lateral Line Hair Cells After Ototoxin Exposure

Rohit C. Philip, Jeffrey J Rodriguez, Maki Niihori, Ross H. Francis, Jordan A. Mudery, Justin S. Caskey, Elizabeth A Krupinski, Abraham Jacob

Research output: Contribution to journalArticle

2 Citations (Scopus)

Abstract

Zebrafish have emerged as a powerful biological system for drug development against hearing loss. Zebrafish hair cells, contained within neuromasts along the lateral line, can be damaged with exposure to ototoxins, and therefore, pre-exposure to potentially otoprotective compounds can be a means of identifying promising new drug candidates. Unfortunately, anatomical assays of hair cell damage are typically low-throughput and labor intensive, requiring trained experts to manually score hair cell damage in fluorescence or confocal images. To enhance throughput and consistency, our group has developed an automated damage-scoring algorithm based on machine-learning techniques that produce accurate damage scores, eliminate potential operator bias, provide more fidelity in determining damage scores that are between two levels, and deliver consistent results in a fraction of the time required for manual analysis. The system has been validated against trained experts using linear regression, hypothesis testing, and the Pearson's correlation coefficient. Furthermore, performance has been quantified by measuring mean absolute error for each image and the time taken to automatically compute damage scores. Coupling automated analysis of zebrafish hair cell damage to behavioral assays for ototoxicity produces a novel drug discovery platform for rapid translation of candidate drugs into preclinical mammalian models of hearing loss.

Original languageEnglish (US)
Pages (from-to)145-155
Number of pages11
JournalZebrafish
Volume15
Issue number2
DOIs
StatePublished - Apr 1 2018

Fingerprint

Zebrafish
Danio rerio
hairs
hearing
Hearing Loss
drugs
Pharmaceutical Preparations
cells
new drugs
artificial intelligence
assays
Drug Discovery
Linear Models
labor
Fluorescence
fluorescence
testing
methodology

Keywords

  • anatomical assays
  • hearing and hearing loss
  • lateral line
  • neuromast damage
  • ototoxicity
  • zebrafish

ASJC Scopus subject areas

  • Animal Science and Zoology
  • Developmental Biology

Cite this

Automated High-Throughput Damage Scoring of Zebrafish Lateral Line Hair Cells After Ototoxin Exposure. / Philip, Rohit C.; Rodriguez, Jeffrey J; Niihori, Maki; Francis, Ross H.; Mudery, Jordan A.; Caskey, Justin S.; Krupinski, Elizabeth A; Jacob, Abraham.

In: Zebrafish, Vol. 15, No. 2, 01.04.2018, p. 145-155.

Research output: Contribution to journalArticle

Philip, Rohit C. ; Rodriguez, Jeffrey J ; Niihori, Maki ; Francis, Ross H. ; Mudery, Jordan A. ; Caskey, Justin S. ; Krupinski, Elizabeth A ; Jacob, Abraham. / Automated High-Throughput Damage Scoring of Zebrafish Lateral Line Hair Cells After Ototoxin Exposure. In: Zebrafish. 2018 ; Vol. 15, No. 2. pp. 145-155.
@article{783e8cee73774d50b239114dc75355b5,
title = "Automated High-Throughput Damage Scoring of Zebrafish Lateral Line Hair Cells After Ototoxin Exposure",
abstract = "Zebrafish have emerged as a powerful biological system for drug development against hearing loss. Zebrafish hair cells, contained within neuromasts along the lateral line, can be damaged with exposure to ototoxins, and therefore, pre-exposure to potentially otoprotective compounds can be a means of identifying promising new drug candidates. Unfortunately, anatomical assays of hair cell damage are typically low-throughput and labor intensive, requiring trained experts to manually score hair cell damage in fluorescence or confocal images. To enhance throughput and consistency, our group has developed an automated damage-scoring algorithm based on machine-learning techniques that produce accurate damage scores, eliminate potential operator bias, provide more fidelity in determining damage scores that are between two levels, and deliver consistent results in a fraction of the time required for manual analysis. The system has been validated against trained experts using linear regression, hypothesis testing, and the Pearson's correlation coefficient. Furthermore, performance has been quantified by measuring mean absolute error for each image and the time taken to automatically compute damage scores. Coupling automated analysis of zebrafish hair cell damage to behavioral assays for ototoxicity produces a novel drug discovery platform for rapid translation of candidate drugs into preclinical mammalian models of hearing loss.",
keywords = "anatomical assays, hearing and hearing loss, lateral line, neuromast damage, ototoxicity, zebrafish",
author = "Philip, {Rohit C.} and Rodriguez, {Jeffrey J} and Maki Niihori and Francis, {Ross H.} and Mudery, {Jordan A.} and Caskey, {Justin S.} and Krupinski, {Elizabeth A} and Abraham Jacob",
year = "2018",
month = "4",
day = "1",
doi = "10.1089/zeb.2017.1451",
language = "English (US)",
volume = "15",
pages = "145--155",
journal = "Zebrafish",
issn = "1545-8547",
publisher = "Mary Ann Liebert Inc.",
number = "2",

}

TY - JOUR

T1 - Automated High-Throughput Damage Scoring of Zebrafish Lateral Line Hair Cells After Ototoxin Exposure

AU - Philip, Rohit C.

AU - Rodriguez, Jeffrey J

AU - Niihori, Maki

AU - Francis, Ross H.

AU - Mudery, Jordan A.

AU - Caskey, Justin S.

AU - Krupinski, Elizabeth A

AU - Jacob, Abraham

PY - 2018/4/1

Y1 - 2018/4/1

N2 - Zebrafish have emerged as a powerful biological system for drug development against hearing loss. Zebrafish hair cells, contained within neuromasts along the lateral line, can be damaged with exposure to ototoxins, and therefore, pre-exposure to potentially otoprotective compounds can be a means of identifying promising new drug candidates. Unfortunately, anatomical assays of hair cell damage are typically low-throughput and labor intensive, requiring trained experts to manually score hair cell damage in fluorescence or confocal images. To enhance throughput and consistency, our group has developed an automated damage-scoring algorithm based on machine-learning techniques that produce accurate damage scores, eliminate potential operator bias, provide more fidelity in determining damage scores that are between two levels, and deliver consistent results in a fraction of the time required for manual analysis. The system has been validated against trained experts using linear regression, hypothesis testing, and the Pearson's correlation coefficient. Furthermore, performance has been quantified by measuring mean absolute error for each image and the time taken to automatically compute damage scores. Coupling automated analysis of zebrafish hair cell damage to behavioral assays for ototoxicity produces a novel drug discovery platform for rapid translation of candidate drugs into preclinical mammalian models of hearing loss.

AB - Zebrafish have emerged as a powerful biological system for drug development against hearing loss. Zebrafish hair cells, contained within neuromasts along the lateral line, can be damaged with exposure to ototoxins, and therefore, pre-exposure to potentially otoprotective compounds can be a means of identifying promising new drug candidates. Unfortunately, anatomical assays of hair cell damage are typically low-throughput and labor intensive, requiring trained experts to manually score hair cell damage in fluorescence or confocal images. To enhance throughput and consistency, our group has developed an automated damage-scoring algorithm based on machine-learning techniques that produce accurate damage scores, eliminate potential operator bias, provide more fidelity in determining damage scores that are between two levels, and deliver consistent results in a fraction of the time required for manual analysis. The system has been validated against trained experts using linear regression, hypothesis testing, and the Pearson's correlation coefficient. Furthermore, performance has been quantified by measuring mean absolute error for each image and the time taken to automatically compute damage scores. Coupling automated analysis of zebrafish hair cell damage to behavioral assays for ototoxicity produces a novel drug discovery platform for rapid translation of candidate drugs into preclinical mammalian models of hearing loss.

KW - anatomical assays

KW - hearing and hearing loss

KW - lateral line

KW - neuromast damage

KW - ototoxicity

KW - zebrafish

UR - http://www.scopus.com/inward/record.url?scp=85044746905&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85044746905&partnerID=8YFLogxK

U2 - 10.1089/zeb.2017.1451

DO - 10.1089/zeb.2017.1451

M3 - Article

VL - 15

SP - 145

EP - 155

JO - Zebrafish

JF - Zebrafish

SN - 1545-8547

IS - 2

ER -