Repurposed High-Throughput Images Enable Biological Activity Prediction For Drug Discovery

Jaak Simm; Günter Klambauer; Adam Arany; Marvin Steijaer; Jörg Wegner; Emmanuel Gustin; Vladimir Chupakhin; Yolanda T. Chong; Jorge Vialard; Peter Buijnsters; Ingrid Velter; Alexander Vapirev; Shantanu Singh; Anne Carpenter; Roel Wuyts; Sepp Hochreiter; Yves Moreau; Hugo Ceulemans

doi:10.1101/108399

Repurposed High-Throughput Images Enable Biological Activity Prediction For Drug Discovery

Jaak Simm, Günter Klambauer, Adam Arany, Marvin Steijaer, Jörg Wegner, Emmanuel Gustin, Vladimir Chupakhin, Yolanda T. Chong, Jorge Vialard, Peter Buijnsters, Ingrid Velter, Alexander Vapirev, Shantanu Singh, Anne Carpenter, Roel Wuyts, Sepp Hochreiter, Yves Moreau, Hugo Ceulemans

Institute for Machine Learning

Research output: Working paper and reports › Preprint

Abstract

We repurpose a High-Throughput (cell) Imaging (HTI) screen of a glucocorticoid receptor assay to predict target protein activity in multiple other seemingly unrelated assays. In two ongoing drug discovery projects, our repurposing approach increased hit rates by 60- to 250-fold over that of the primary project assays while increasing the chemical structure diversity of the hits. Our results suggest that data from available HTI screens are a rich source of information that can be reused to empower drug discovery efforts.

Original language	English
Number of pages	13
DOIs	https://doi.org/10.1101/108399
Publication status	Published - 2017

Publication series

Name	bioRxiv
ISSN (Print)	2692-8205

Fields of science

303 Health Sciences
304 Medical Biotechnology
304003 Genetic engineering
305 Other Human Medicine, Health Sciences
101004 Biomathematics
101018 Statistics
102 Computer Sciences
102001 Artificial intelligence
102004 Bioinformatics
102010 Database systems
102015 Information systems
102019 Machine learning
106023 Molecular biology
106002 Biochemistry
106005 Bioinformatics
106007 Biostatistics
106041 Structural biology
301 Medical-Theoretical Sciences, Pharmacy
302 Clinical Medicine

JKU Focus areas

Computation in Informatics and Mathematics
Nano-, Bio- and Polymer-Systems: From Structure to Function
Medical Sciences (in general)
Health System Research
Clinical Research on Aging

Access to Document

10.1101/108399

Cite this

Simm, J., Klambauer, G., Arany, A., Steijaer, M., Wegner, J., Gustin, E., Chupakhin, V., Chong, Y. T., Vialard, J., Buijnsters, P., Velter, I., Vapirev, A., Singh, S., Carpenter, A., Wuyts, R., Hochreiter, S., Moreau, Y., & Ceulemans, H. (2017). Repurposed High-Throughput Images Enable Biological Activity Prediction For Drug Discovery. (bioRxiv). https://doi.org/10.1101/108399

@techreport{273914a57ad8474ca14b6e0dd184efb7,

title = "Repurposed High-Throughput Images Enable Biological Activity Prediction For Drug Discovery",

abstract = "We repurpose a High-Throughput (cell) Imaging (HTI) screen of a glucocorticoid receptor assay to predict target protein activity in multiple other seemingly unrelated assays. In two ongoing drug discovery projects, our repurposing approach increased hit rates by 60- to 250-fold over that of the primary project assays while increasing the chemical structure diversity of the hits. Our results suggest that data from available HTI screens are a rich source of information that can be reused to empower drug discovery efforts.",

author = "Jaak Simm and G{\"u}nter Klambauer and Adam Arany and Marvin Steijaer and J{\"o}rg Wegner and Emmanuel Gustin and Vladimir Chupakhin and Chong, \{Yolanda T.\} and Jorge Vialard and Peter Buijnsters and Ingrid Velter and Alexander Vapirev and Shantanu Singh and Anne Carpenter and Roel Wuyts and Sepp Hochreiter and Yves Moreau and Hugo Ceulemans",

year = "2017",

doi = "10.1101/108399",

language = "English",

series = "bioRxiv",

type = "WorkingPaper",

}

TY - UNPB

T1 - Repurposed High-Throughput Images Enable Biological Activity Prediction For Drug Discovery

AU - Simm, Jaak

AU - Klambauer, Günter

AU - Arany, Adam

AU - Steijaer, Marvin

AU - Wegner, Jörg

AU - Gustin, Emmanuel

AU - Chupakhin, Vladimir

AU - Chong, Yolanda T.

AU - Vialard, Jorge

AU - Buijnsters, Peter

AU - Velter, Ingrid

AU - Vapirev, Alexander

AU - Singh, Shantanu

AU - Carpenter, Anne

AU - Wuyts, Roel

AU - Hochreiter, Sepp

AU - Moreau, Yves

AU - Ceulemans, Hugo

PY - 2017

Y1 - 2017

N2 - We repurpose a High-Throughput (cell) Imaging (HTI) screen of a glucocorticoid receptor assay to predict target protein activity in multiple other seemingly unrelated assays. In two ongoing drug discovery projects, our repurposing approach increased hit rates by 60- to 250-fold over that of the primary project assays while increasing the chemical structure diversity of the hits. Our results suggest that data from available HTI screens are a rich source of information that can be reused to empower drug discovery efforts.

AB - We repurpose a High-Throughput (cell) Imaging (HTI) screen of a glucocorticoid receptor assay to predict target protein activity in multiple other seemingly unrelated assays. In two ongoing drug discovery projects, our repurposing approach increased hit rates by 60- to 250-fold over that of the primary project assays while increasing the chemical structure diversity of the hits. Our results suggest that data from available HTI screens are a rich source of information that can be reused to empower drug discovery efforts.

UR - http://www.bioinf.jku.at/publications/

U2 - 10.1101/108399

DO - 10.1101/108399

M3 - Preprint

T3 - bioRxiv

BT - Repurposed High-Throughput Images Enable Biological Activity Prediction For Drug Discovery

ER -

Repurposed High-Throughput Images Enable Biological Activity Prediction For Drug Discovery

Abstract

Publication series

Fields of science

JKU Focus areas

Access to Document

Other files and links

Cite this