Bayesian models leveraging bioactivity and cytotoxicity information for drug discovery

Sean Ekins, Robert C. Reynolds, Hiyun Kim, Mi Sun Koo, Marilyn Ekonomidis, Meliza Talaue, Steve D. Paget, Lisa K. Woolhiser, Anne J. Lenaerts, Barry A. Bunin, Nancy Connell, Joel S. Freundlich

Research output: Contribution to journalArticle

Abstract

Identification of unique leads represents a significant challenge in drug discovery. This hurdle is magnified in neglected diseases such as tuberculosis. We have leveraged public high-throughput screening (HTS) data to experimentally validate a virtual screening approach employing Bayesian models built with bioactivity information (single-event model) as well as bioactivity and cytotoxicity information (dual-event model). We virtually screened a commercial library and experimentally confirmed actives with hit rates exceeding typical HTS results by one to two orders of magnitude. This initial dual-event Bayesian model identified compounds with antitubercular whole-cell activity and low mammalian cell cytotoxicity from a published set of antimalarials. The most potent hit exhibits the in vitro activity and in vitro/in vivo safety profile of a drug lead. These Bayesian models offer significant economies in time and cost to drug discovery.

Original languageEnglish (US)
Pages (from-to)370-378
Number of pages9
JournalChemistry and Biology
Volume20
Issue number3
DOIs
StatePublished - Mar 21 2013
Externally publishedYes

Fingerprint

Drug Discovery
Cytotoxicity
Bioactivity
Neglected Diseases
Bayes Theorem
Antimalarials
Screening
Libraries
Tuberculosis
Safety
Costs and Cost Analysis
Throughput
Pharmaceutical Preparations
Identification (control systems)
Cells
In Vitro Techniques
Costs
Lead

ASJC Scopus subject areas

  • Biochemistry
  • Molecular Medicine
  • Molecular Biology
  • Pharmacology
  • Drug Discovery
  • Clinical Biochemistry

Cite this

Ekins, S., Reynolds, R. C., Kim, H., Koo, M. S., Ekonomidis, M., Talaue, M., ... Freundlich, J. S. (2013). Bayesian models leveraging bioactivity and cytotoxicity information for drug discovery. Chemistry and Biology, 20(3), 370-378. https://doi.org/10.1016/j.chembiol.2013.01.011

Bayesian models leveraging bioactivity and cytotoxicity information for drug discovery. / Ekins, Sean; Reynolds, Robert C.; Kim, Hiyun; Koo, Mi Sun; Ekonomidis, Marilyn; Talaue, Meliza; Paget, Steve D.; Woolhiser, Lisa K.; Lenaerts, Anne J.; Bunin, Barry A.; Connell, Nancy; Freundlich, Joel S.

In: Chemistry and Biology, Vol. 20, No. 3, 21.03.2013, p. 370-378.

Research output: Contribution to journalArticle

Ekins, S, Reynolds, RC, Kim, H, Koo, MS, Ekonomidis, M, Talaue, M, Paget, SD, Woolhiser, LK, Lenaerts, AJ, Bunin, BA, Connell, N & Freundlich, JS 2013, 'Bayesian models leveraging bioactivity and cytotoxicity information for drug discovery', Chemistry and Biology, vol. 20, no. 3, pp. 370-378. https://doi.org/10.1016/j.chembiol.2013.01.011
Ekins, Sean ; Reynolds, Robert C. ; Kim, Hiyun ; Koo, Mi Sun ; Ekonomidis, Marilyn ; Talaue, Meliza ; Paget, Steve D. ; Woolhiser, Lisa K. ; Lenaerts, Anne J. ; Bunin, Barry A. ; Connell, Nancy ; Freundlich, Joel S. / Bayesian models leveraging bioactivity and cytotoxicity information for drug discovery. In: Chemistry and Biology. 2013 ; Vol. 20, No. 3. pp. 370-378.
@article{0801e0d7d2324d60acc318a0163f9862,
title = "Bayesian models leveraging bioactivity and cytotoxicity information for drug discovery",
abstract = "Identification of unique leads represents a significant challenge in drug discovery. This hurdle is magnified in neglected diseases such as tuberculosis. We have leveraged public high-throughput screening (HTS) data to experimentally validate a virtual screening approach employing Bayesian models built with bioactivity information (single-event model) as well as bioactivity and cytotoxicity information (dual-event model). We virtually screened a commercial library and experimentally confirmed actives with hit rates exceeding typical HTS results by one to two orders of magnitude. This initial dual-event Bayesian model identified compounds with antitubercular whole-cell activity and low mammalian cell cytotoxicity from a published set of antimalarials. The most potent hit exhibits the in vitro activity and in vitro/in vivo safety profile of a drug lead. These Bayesian models offer significant economies in time and cost to drug discovery.",
author = "Sean Ekins and Reynolds, {Robert C.} and Hiyun Kim and Koo, {Mi Sun} and Marilyn Ekonomidis and Meliza Talaue and Paget, {Steve D.} and Woolhiser, {Lisa K.} and Lenaerts, {Anne J.} and Bunin, {Barry A.} and Nancy Connell and Freundlich, {Joel S.}",
year = "2013",
month = "3",
day = "21",
doi = "10.1016/j.chembiol.2013.01.011",
language = "English (US)",
volume = "20",
pages = "370--378",
journal = "Cell Chemical Biology",
issn = "2451-9448",
publisher = "Elsevier Inc.",
number = "3",

}

TY - JOUR

T1 - Bayesian models leveraging bioactivity and cytotoxicity information for drug discovery

AU - Ekins, Sean

AU - Reynolds, Robert C.

AU - Kim, Hiyun

AU - Koo, Mi Sun

AU - Ekonomidis, Marilyn

AU - Talaue, Meliza

AU - Paget, Steve D.

AU - Woolhiser, Lisa K.

AU - Lenaerts, Anne J.

AU - Bunin, Barry A.

AU - Connell, Nancy

AU - Freundlich, Joel S.

PY - 2013/3/21

Y1 - 2013/3/21

N2 - Identification of unique leads represents a significant challenge in drug discovery. This hurdle is magnified in neglected diseases such as tuberculosis. We have leveraged public high-throughput screening (HTS) data to experimentally validate a virtual screening approach employing Bayesian models built with bioactivity information (single-event model) as well as bioactivity and cytotoxicity information (dual-event model). We virtually screened a commercial library and experimentally confirmed actives with hit rates exceeding typical HTS results by one to two orders of magnitude. This initial dual-event Bayesian model identified compounds with antitubercular whole-cell activity and low mammalian cell cytotoxicity from a published set of antimalarials. The most potent hit exhibits the in vitro activity and in vitro/in vivo safety profile of a drug lead. These Bayesian models offer significant economies in time and cost to drug discovery.

AB - Identification of unique leads represents a significant challenge in drug discovery. This hurdle is magnified in neglected diseases such as tuberculosis. We have leveraged public high-throughput screening (HTS) data to experimentally validate a virtual screening approach employing Bayesian models built with bioactivity information (single-event model) as well as bioactivity and cytotoxicity information (dual-event model). We virtually screened a commercial library and experimentally confirmed actives with hit rates exceeding typical HTS results by one to two orders of magnitude. This initial dual-event Bayesian model identified compounds with antitubercular whole-cell activity and low mammalian cell cytotoxicity from a published set of antimalarials. The most potent hit exhibits the in vitro activity and in vitro/in vivo safety profile of a drug lead. These Bayesian models offer significant economies in time and cost to drug discovery.

UR - http://www.scopus.com/inward/record.url?scp=84875428496&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84875428496&partnerID=8YFLogxK

U2 - 10.1016/j.chembiol.2013.01.011

DO - 10.1016/j.chembiol.2013.01.011

M3 - Article

C2 - 23521795

AN - SCOPUS:84875428496

VL - 20

SP - 370

EP - 378

JO - Cell Chemical Biology

JF - Cell Chemical Biology

SN - 2451-9448

IS - 3

ER -