Applications of machine learning in GPCR bioactive ligand discovery

Research output: Contribution to journalReview articleResearchpeer-review

Abstract

GPCRs constitute the largest druggable family having targets for 475 Food and Drug Administration (FDA) approved drugs. As GPCRs are of great interest to pharmaceutical industry, enormous efforts are being expended to find relevant and potent GPCR ligands as lead compounds. There are tens of millions of compounds present in different chemical databases. In order to scan this immense chemical space, computational methods, especially machine learning (ML) methods, are essential components of GPCR drug discovery pipelines. ML approaches have applications in both ligand-based and structure-based virtual screening. We present here a cheminformatics overview of ML applications to different stages of GPCR drug discovery. Focusing on olfactory receptors, which are the largest family of GPCRs, a case study for predicting agonists for an ectopic olfactory receptor, OR1G1, compares four classical ML methods.

LanguageEnglish
Pages66-76
Number of pages11
JournalCurrent Opinion in Structural Biology
Volume55
DOIs
Publication statusPublished - Apr 2019

Fingerprint

Odorant Receptors
Ligands
Drug Discovery
Chemical Databases
Drug Industry
United States Food and Drug Administration
Machine Learning
Pharmaceutical Preparations

Cite this

@article{bbaedb6b773e4dccb296fabd4e9d2e10,
title = "Applications of machine learning in GPCR bioactive ligand discovery",
abstract = "GPCRs constitute the largest druggable family having targets for 475 Food and Drug Administration (FDA) approved drugs. As GPCRs are of great interest to pharmaceutical industry, enormous efforts are being expended to find relevant and potent GPCR ligands as lead compounds. There are tens of millions of compounds present in different chemical databases. In order to scan this immense chemical space, computational methods, especially machine learning (ML) methods, are essential components of GPCR drug discovery pipelines. ML approaches have applications in both ligand-based and structure-based virtual screening. We present here a cheminformatics overview of ML applications to different stages of GPCR drug discovery. Focusing on olfactory receptors, which are the largest family of GPCRs, a case study for predicting agonists for an ectopic olfactory receptor, OR1G1, compares four classical ML methods.",
author = "Amara Jabeen and Shoba Ranganathan",
year = "2019",
month = "4",
doi = "10.1016/j.sbi.2019.03.022",
language = "English",
volume = "55",
pages = "66--76",
journal = "Current Opinion in Structural Biology",
issn = "0959-440X",
publisher = "Elsevier",

}

Applications of machine learning in GPCR bioactive ligand discovery. / Jabeen, Amara; Ranganathan, Shoba.

In: Current Opinion in Structural Biology, Vol. 55, 04.2019, p. 66-76.

Research output: Contribution to journalReview articleResearchpeer-review

TY - JOUR

T1 - Applications of machine learning in GPCR bioactive ligand discovery

AU - Jabeen, Amara

AU - Ranganathan, Shoba

PY - 2019/4

Y1 - 2019/4

N2 - GPCRs constitute the largest druggable family having targets for 475 Food and Drug Administration (FDA) approved drugs. As GPCRs are of great interest to pharmaceutical industry, enormous efforts are being expended to find relevant and potent GPCR ligands as lead compounds. There are tens of millions of compounds present in different chemical databases. In order to scan this immense chemical space, computational methods, especially machine learning (ML) methods, are essential components of GPCR drug discovery pipelines. ML approaches have applications in both ligand-based and structure-based virtual screening. We present here a cheminformatics overview of ML applications to different stages of GPCR drug discovery. Focusing on olfactory receptors, which are the largest family of GPCRs, a case study for predicting agonists for an ectopic olfactory receptor, OR1G1, compares four classical ML methods.

AB - GPCRs constitute the largest druggable family having targets for 475 Food and Drug Administration (FDA) approved drugs. As GPCRs are of great interest to pharmaceutical industry, enormous efforts are being expended to find relevant and potent GPCR ligands as lead compounds. There are tens of millions of compounds present in different chemical databases. In order to scan this immense chemical space, computational methods, especially machine learning (ML) methods, are essential components of GPCR drug discovery pipelines. ML approaches have applications in both ligand-based and structure-based virtual screening. We present here a cheminformatics overview of ML applications to different stages of GPCR drug discovery. Focusing on olfactory receptors, which are the largest family of GPCRs, a case study for predicting agonists for an ectopic olfactory receptor, OR1G1, compares four classical ML methods.

UR - http://www.scopus.com/inward/record.url?scp=85064326748&partnerID=8YFLogxK

UR - http://purl.org/au-research/grants/arc/DP180102727

U2 - 10.1016/j.sbi.2019.03.022

DO - 10.1016/j.sbi.2019.03.022

M3 - Review article

VL - 55

SP - 66

EP - 76

JO - Current Opinion in Structural Biology

T2 - Current Opinion in Structural Biology

JF - Current Opinion in Structural Biology

SN - 0959-440X

ER -