Applicability domain-expansion studies for machine learning models reveal new inhibitors of CYP2B6

CYP2B6 is an important enzyme in the phase 1 metabolism of key pharmaceuticals, and inhibition of this enzyme can lead to adverse drug events. Machine learning models can potentially predict interactions with CYP2B6; however, there is limited data with which to train these models in the public domai...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Drug metabolism and disposition Ročník 53; číslo 10; s. 100160
Hlavní autoři: Vignaux, Patricia A, Harris, Joshua S, Urbina, Fabio, Ekins, Sean
Médium: Journal Article
Jazyk:angličtina
Vydáno: Netherlands 01.10.2025
Témata:
ISSN:1521-009X, 1521-009X
On-line přístup:Zjistit podrobnosti o přístupu
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Abstract CYP2B6 is an important enzyme in the phase 1 metabolism of key pharmaceuticals, and inhibition of this enzyme can lead to adverse drug events. Machine learning models can potentially predict interactions with CYP2B6; however, there is limited data with which to train these models in the public domain. We proposed enhancing the applicability domain and improving the predictive capability of our CYP2B6 inhibition model by selecting a small, diverse set of compounds to test in vitro and adding the results to our model training set. We used a distance-based approach to define the applicability domain of the model and then measured the chemical diversity by creating t-distributed stochastic neighbor embedding plots to represent the chemical space of our model. After comparing this chemical space with a 49-plate drug-repurposing library, we were able to identify a plate with the highest average minimum Euclidean distance from the model training set. We then performed in vitro testing of this plate for CYP2B6 inhibition activity at 10 μM and added this new data to our machine learning model. A one-class classification approach was used to evaluate the efficacy of our applicability domain-expansion technique. The results showed that this method did not appreciably increase the performance of the model or the applicability domain, but we did increase the diversity of the training set. Additionally, the in vitro experiments identified vilanterol and allylestrenol as inhibitors of CYP2B6 with IC values in the sub to low micromolar range. SIGNIFICANCE STATEMENT: CYP2B6 inhibition can affect the metabolism of important drugs, like methadone and propofol, and result in variability that can lead to adverse events. Machine learning models can help uncover new molecules with inhibitory potential against CYP2B6, but only if predictions of these models are reliable. This study illustrates how the intentional expansion of a machine learning model's applicability domain is neither a simple nor straightforward task, but even a conservative effort can reveal new molecules with CYP2B6 inhibition activity.
AbstractList CYP2B6 is an important enzyme in the phase 1 metabolism of key pharmaceuticals, and inhibition of this enzyme can lead to adverse drug events. Machine learning models can potentially predict interactions with CYP2B6; however, there is limited data with which to train these models in the public domain. We proposed enhancing the applicability domain and improving the predictive capability of our CYP2B6 inhibition model by selecting a small, diverse set of compounds to test in vitro and adding the results to our model training set. We used a distance-based approach to define the applicability domain of the model and then measured the chemical diversity by creating t-distributed stochastic neighbor embedding plots to represent the chemical space of our model. After comparing this chemical space with a 49-plate drug-repurposing library, we were able to identify a plate with the highest average minimum Euclidean distance from the model training set. We then performed in vitro testing of this plate for CYP2B6 inhibition activity at 10 μM and added this new data to our machine learning model. A one-class classification approach was used to evaluate the efficacy of our applicability domain-expansion technique. The results showed that this method did not appreciably increase the performance of the model or the applicability domain, but we did increase the diversity of the training set. Additionally, the in vitro experiments identified vilanterol and allylestrenol as inhibitors of CYP2B6 with IC50 values in the sub to low micromolar range. SIGNIFICANCE STATEMENT: CYP2B6 inhibition can affect the metabolism of important drugs, like methadone and propofol, and result in variability that can lead to adverse events. Machine learning models can help uncover new molecules with inhibitory potential against CYP2B6, but only if predictions of these models are reliable. This study illustrates how the intentional expansion of a machine learning model's applicability domain is neither a simple nor straightforward task, but even a conservative effort can reveal new molecules with CYP2B6 inhibition activity.CYP2B6 is an important enzyme in the phase 1 metabolism of key pharmaceuticals, and inhibition of this enzyme can lead to adverse drug events. Machine learning models can potentially predict interactions with CYP2B6; however, there is limited data with which to train these models in the public domain. We proposed enhancing the applicability domain and improving the predictive capability of our CYP2B6 inhibition model by selecting a small, diverse set of compounds to test in vitro and adding the results to our model training set. We used a distance-based approach to define the applicability domain of the model and then measured the chemical diversity by creating t-distributed stochastic neighbor embedding plots to represent the chemical space of our model. After comparing this chemical space with a 49-plate drug-repurposing library, we were able to identify a plate with the highest average minimum Euclidean distance from the model training set. We then performed in vitro testing of this plate for CYP2B6 inhibition activity at 10 μM and added this new data to our machine learning model. A one-class classification approach was used to evaluate the efficacy of our applicability domain-expansion technique. The results showed that this method did not appreciably increase the performance of the model or the applicability domain, but we did increase the diversity of the training set. Additionally, the in vitro experiments identified vilanterol and allylestrenol as inhibitors of CYP2B6 with IC50 values in the sub to low micromolar range. SIGNIFICANCE STATEMENT: CYP2B6 inhibition can affect the metabolism of important drugs, like methadone and propofol, and result in variability that can lead to adverse events. Machine learning models can help uncover new molecules with inhibitory potential against CYP2B6, but only if predictions of these models are reliable. This study illustrates how the intentional expansion of a machine learning model's applicability domain is neither a simple nor straightforward task, but even a conservative effort can reveal new molecules with CYP2B6 inhibition activity.
CYP2B6 is an important enzyme in the phase 1 metabolism of key pharmaceuticals, and inhibition of this enzyme can lead to adverse drug events. Machine learning models can potentially predict interactions with CYP2B6; however, there is limited data with which to train these models in the public domain. We proposed enhancing the applicability domain and improving the predictive capability of our CYP2B6 inhibition model by selecting a small, diverse set of compounds to test in vitro and adding the results to our model training set. We used a distance-based approach to define the applicability domain of the model and then measured the chemical diversity by creating t-distributed stochastic neighbor embedding plots to represent the chemical space of our model. After comparing this chemical space with a 49-plate drug-repurposing library, we were able to identify a plate with the highest average minimum Euclidean distance from the model training set. We then performed in vitro testing of this plate for CYP2B6 inhibition activity at 10 μM and added this new data to our machine learning model. A one-class classification approach was used to evaluate the efficacy of our applicability domain-expansion technique. The results showed that this method did not appreciably increase the performance of the model or the applicability domain, but we did increase the diversity of the training set. Additionally, the in vitro experiments identified vilanterol and allylestrenol as inhibitors of CYP2B6 with IC values in the sub to low micromolar range. SIGNIFICANCE STATEMENT: CYP2B6 inhibition can affect the metabolism of important drugs, like methadone and propofol, and result in variability that can lead to adverse events. Machine learning models can help uncover new molecules with inhibitory potential against CYP2B6, but only if predictions of these models are reliable. This study illustrates how the intentional expansion of a machine learning model's applicability domain is neither a simple nor straightforward task, but even a conservative effort can reveal new molecules with CYP2B6 inhibition activity.
Author Vignaux, Patricia A
Harris, Joshua S
Urbina, Fabio
Ekins, Sean
Author_xml – sequence: 1
  givenname: Patricia A
  surname: Vignaux
  fullname: Vignaux, Patricia A
  organization: Collaborations Pharmaceuticals, Inc, Raleigh, North Carolina
– sequence: 2
  givenname: Joshua S
  surname: Harris
  fullname: Harris, Joshua S
  organization: Collaborations Pharmaceuticals, Inc, Raleigh, North Carolina
– sequence: 3
  givenname: Fabio
  surname: Urbina
  fullname: Urbina, Fabio
  organization: Collaborations Pharmaceuticals, Inc, Raleigh, North Carolina
– sequence: 4
  givenname: Sean
  surname: Ekins
  fullname: Ekins, Sean
  email: sean@collaborationspharma.com
  organization: Collaborations Pharmaceuticals, Inc, Raleigh, North Carolina. Electronic address: sean@collaborationspharma.com
BackLink https://www.ncbi.nlm.nih.gov/pubmed/41061300$$D View this record in MEDLINE/PubMed
BookMark eNpNkEtLxDAUhYOMOA_9AW4kSzetSZp2muU4-IIBXSjoquRx62RIk9q06vx7C47g6p7v8HEWd44mPnhA6JySlBJaXO1S05iUEZaPPBbkCM1ozmhCiHid_MtTNI9xNyqcZ-IETTklBc0ImSG1altntVTW2X6PTWik9Ql8t9JHGzyO_WAsRFyHDjdSb60H7EB23vp33AQDLuIOPkE67OELW7-1yvahizjUeP32xK6LU3RcSxfh7HAX6OX25nl9n2we7x7Wq02iM7LsE1VIloEiIwgmSqlUbpRWinFleD1CaWohs9IInZdgSl4QnRcUNOeC6kyyBbr83W278DFA7KvGRg3OSQ9hiFXGckGWSyrIqF4c1EE1YKq2s43s9tXfX9gPL0toxQ
ContentType Journal Article
Copyright Copyright © 2025 American Society for Pharmacology and Experimental Therapeutics. Published by Elsevier Inc. All rights reserved.
Copyright_xml – notice: Copyright © 2025 American Society for Pharmacology and Experimental Therapeutics. Published by Elsevier Inc. All rights reserved.
DBID CGR
CUY
CVF
ECM
EIF
NPM
7X8
DOI 10.1016/j.dmd.2025.100160
DatabaseName Medline
MEDLINE
MEDLINE (Ovid)
MEDLINE
MEDLINE
PubMed
MEDLINE - Academic
DatabaseTitle MEDLINE
Medline Complete
MEDLINE with Full Text
PubMed
MEDLINE (Ovid)
MEDLINE - Academic
DatabaseTitleList MEDLINE - Academic
MEDLINE
Database_xml – sequence: 1
  dbid: NPM
  name: PubMed
  url: http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed
  sourceTypes: Index Database
– sequence: 2
  dbid: 7X8
  name: MEDLINE - Academic
  url: https://search.proquest.com/medline
  sourceTypes: Aggregation Database
DeliveryMethod no_fulltext_linktorsrc
Discipline Pharmacy, Therapeutics, & Pharmacology
EISSN 1521-009X
ExternalDocumentID 41061300
Genre Journal Article
GroupedDBID ---
.GJ
0R~
18M
2WC
4.4
53G
5GY
5RE
5VS
AALRI
AAXUO
ABJNI
ABSQV
ACGFO
ACGFS
ACIWK
ACPRK
ADBBV
AENEX
AERNN
AFFNX
AFRAH
AI.
ALMA_UNASSIGNED_HOLDINGS
BAWUL
BTFSW
CGR
CS3
CUY
CVF
DIK
DU5
E3Z
EBS
ECM
EIF
EJD
F5P
F9R
FDB
GX1
H13
HZ~
IH2
INIJC
KQ8
LSO
M41
NPM
O9-
OK1
P2P
R0Z
RHI
ROL
RPT
SJN
TR2
VH1
W8F
WH7
WOQ
YHG
ZGI
ZXP
~KM
7X8
ID FETCH-LOGICAL-c307t-b6a23eb03079298abb5dbcbb24bd4fb5d8df9a38d9c58ed8460c561ec4491c3a2
IEDL.DBID 7X8
ISICitedReferencesCount 0
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001592286000002&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 1521-009X
IngestDate Thu Oct 09 19:00:39 EDT 2025
Sat Nov 01 14:17:09 EDT 2025
IsPeerReviewed true
IsScholarly true
Issue 10
Keywords t-SNE
CYP2B6
Applicability domain
Drug–drug interaction
Machine learning
Language English
License Copyright © 2025 American Society for Pharmacology and Experimental Therapeutics. Published by Elsevier Inc. All rights reserved.
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-c307t-b6a23eb03079298abb5dbcbb24bd4fb5d8df9a38d9c58ed8460c561ec4491c3a2
Notes ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
PMID 41061300
PQID 3259077190
PQPubID 23479
ParticipantIDs proquest_miscellaneous_3259077190
pubmed_primary_41061300
PublicationCentury 2000
PublicationDate 2025-10-01
PublicationDateYYYYMMDD 2025-10-01
PublicationDate_xml – month: 10
  year: 2025
  text: 2025-10-01
  day: 01
PublicationDecade 2020
PublicationPlace Netherlands
PublicationPlace_xml – name: Netherlands
PublicationTitle Drug metabolism and disposition
PublicationTitleAlternate Drug Metab Dispos
PublicationYear 2025
SSID ssj0014439
Score 2.4798818
Snippet CYP2B6 is an important enzyme in the phase 1 metabolism of key pharmaceuticals, and inhibition of this enzyme can lead to adverse drug events. Machine learning...
SourceID proquest
pubmed
SourceType Aggregation Database
Index Database
StartPage 100160
SubjectTerms Cytochrome P-450 CYP2B6 - metabolism
Humans
Machine Learning
Title Applicability domain-expansion studies for machine learning models reveal new inhibitors of CYP2B6
URI https://www.ncbi.nlm.nih.gov/pubmed/41061300
https://www.proquest.com/docview/3259077190
Volume 53
WOSCitedRecordID wos001592286000002&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
hasFullText
inHoldings 1
isFullTextHit
isPrint
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV27TsMwFLWAMrDwfpSXjIQ61SKN7TwmVBAVA1QZCipT5FcgQ5NCCqJ_z7WTqgsDEkukDJYs--b6-N6TcxC6DGlgIqMEoSrkhGW-IhJuPyQ0KlTcQnZX73h-CIfDaDyOk6bgVjW0ykVOdIlal8rWyK8o4HQvDGHs9fSdWNco211tLDRWUYsClLGUrnC87CIw5pzE7BFFAEuMF11Nx-_SEysU6nOnQtQoVP6KMN1JM9j67xy30WaDMXG_DoodtGKKXdRJapHqeRePlv9cVV3cwclSvnq-h2S_7mk71uwc63Ii8oKYb0gbtrKGq5p5iAHt4omjYhrceE-8YmesU2GrCwUzAMiO8-Itl7n19MFlhm9fEv8m2EdPg7vR7T1pnBiIghwwIzIQPjXSJgSAU5GQkmuppPSZ1CyDl0hnsaCRjhWPjAZM4ykAZkYxFvcUFf4BWivKwhwhzKUOIqGN9rlhoheJQMVM8lgGkpuY0za6WKxtCpFu2xeiMOVnlS5Xt40O6w1Kp7UkR8rszZZ63vEfRp-gDbvvNSPvFLUy-M7NGVpXX7O8-jh3IQTPYfL4AzA00wQ
linkProvider ProQuest
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=Applicability+domain-expansion+studies+for+machine+learning+models+reveal+new+inhibitors+of+CYP2B6&rft.jtitle=Drug+metabolism+and+disposition&rft.au=Vignaux%2C+Patricia+A&rft.au=Harris%2C+Joshua+S&rft.au=Urbina%2C+Fabio&rft.au=Ekins%2C+Sean&rft.date=2025-10-01&rft.eissn=1521-009X&rft.volume=53&rft.issue=10&rft.spage=100160&rft_id=info:doi/10.1016%2Fj.dmd.2025.100160&rft_id=info%3Apmid%2F41061300&rft_id=info%3Apmid%2F41061300&rft.externalDocID=41061300
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1521-009X&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1521-009X&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1521-009X&client=summon