Improving ensemble docking for drug discovery by machine learning

Chung F. Wong

doi:10.1142/S0219633619200013

Improving ensemble docking for drug discovery by machine learning

Chung F. Wong

University of Missouri-St. Louis

Research output: Contribution to journal › Article › peer-review

Abstract

Ensemble docking has provided an inexpensive method to account for receptor flexibility in molecular docking. However, it is still unclear how best to use the docking scores from multiple structures to classify compounds into actives and inactives. Previous studies have also found that the performance of classification could decrease rather than increase with the number of structures included in the ensemble. Machine learning could help to alleviate these problems.

Original language	American English
Journal	Journal of Theoretical and Computational Chemistry
Volume	18
DOIs	https://doi.org/10.1142/S0219633619200013
State	Published - Jun 18 2019

Keywords

Ensemble docking
Naïve Bayesian model
autodock Vina
epidermal growth factor receptor (EGFR)
machine learning
virtual screening

Disciplines

Artificial Intelligence and Robotics

Access to Document

10.1142/S0219633619200013License: Unspecified

Cite this

@article{dc7eb9bbe11b4c999fe70b702f3525f6,

title = "Improving ensemble docking for drug discovery by machine learning",

abstract = " Ensemble docking has provided an inexpensive method to account for receptor flexibility in molecular docking. However, it is still unclear how best to use the docking scores from multiple structures to classify compounds into actives and inactives. Previous studies have also found that the performance of classification could decrease rather than increase with the number of structures included in the ensemble. Machine learning could help to alleviate these problems. ",

keywords = "Ensemble docking, Na{\"i}ve Bayesian model, autodock Vina, epidermal growth factor receptor (EGFR), machine learning, virtual screening",

author = "Wong, {Chung F.}",

note = "During this period, E-commerce and registration of new users may not be available for up to 12 hours. For online purchase, please visit us again. Contact us at[email protected] for any enquiries.",

year = "2019",

month = jun,

day = "18",

doi = "10.1142/S0219633619200013",

language = "American English",

volume = "18",

journal = "Journal of Theoretical and Computational Chemistry",

}

TY - JOUR

T1 - Improving ensemble docking for drug discovery by machine learning

AU - Wong, Chung F.

N1 - During this period, E-commerce and registration of new users may not be available for up to 12 hours. For online purchase, please visit us again. Contact us at[email protected] for any enquiries.

PY - 2019/6/18

Y1 - 2019/6/18

N2 - Ensemble docking has provided an inexpensive method to account for receptor flexibility in molecular docking. However, it is still unclear how best to use the docking scores from multiple structures to classify compounds into actives and inactives. Previous studies have also found that the performance of classification could decrease rather than increase with the number of structures included in the ensemble. Machine learning could help to alleviate these problems.

AB - Ensemble docking has provided an inexpensive method to account for receptor flexibility in molecular docking. However, it is still unclear how best to use the docking scores from multiple structures to classify compounds into actives and inactives. Previous studies have also found that the performance of classification could decrease rather than increase with the number of structures included in the ensemble. Machine learning could help to alleviate these problems.

KW - Ensemble docking

KW - Naïve Bayesian model

KW - autodock Vina

KW - epidermal growth factor receptor (EGFR)

KW - machine learning

KW - virtual screening

UR - https://www.worldscientific.com/doi/10.1142/S0219633619200013

U2 - 10.1142/S0219633619200013

DO - 10.1142/S0219633619200013

M3 - Article

VL - 18

JO - Journal of Theoretical and Computational Chemistry

JF - Journal of Theoretical and Computational Chemistry

ER -

Improving ensemble docking for drug discovery by machine learning

Abstract

Keywords

Disciplines

Access to Document

Other files and links

Cite this