Comparing LD50/LC50 Machine Learning Models for Multiple Species

The lethal dose or concentration which kills 50% of the animals (LD50 or LC50) is an important parameter for scientists to understand the toxicity of chemicals in different scenarios that can be used to make go-no-go decisions, and ultimately assist in the choice of the right personal protective equ...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:ACS Chemical Health & Safety. Ročník 30; číslo 2; s. 83
Hlavní autoři: Lane, Thomas R, Harris, Joshua, Urbina, Fabio, Ekins, Sean
Médium: Journal Article
Jazyk:angličtina
Vydáno: 27.03.2023
ISSN:1878-0504, 1878-0504
On-line přístup:Zjistit podrobnosti o přístupu
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Abstract The lethal dose or concentration which kills 50% of the animals (LD50 or LC50) is an important parameter for scientists to understand the toxicity of chemicals in different scenarios that can be used to make go-no-go decisions, and ultimately assist in the choice of the right personal protective equipment needed for containment. The LD50 assessment process has also required the use of many animals although modern methods have reduced the number of rats needed. Since a compound is usually considered highly toxic when the LD50 is lower than 25 mg/kg, such a classification provides potentially valuable safety information to synthetic chemists and other safety assessment scientists. The need for finding alternative approaches such as computational methods is important to ultimately reduce animal use for this testing further still. We now summarize our efforts to use public data for building in vivo LD50 or LC50 classification and regression machine learning models for various species (rat, mouse, fish and daphnia) and their 5-fold cross validation statistics with different machine learning algorithms as well as an external curated test set for mouse LD50. These datasets consist of different molecule classes, may cover different activity ranges, and also have a range of dataset sizes. The challenges of using such computational models are that their applicability domain will also need to be understood so that they can be used to make reliable predictions for novel molecules. These machine learning models will also need to be backed up with experimental validation. However, such models could also be used for efforts to bridge gaps in individual toxicity datasets. Making such models available also opens them up to potential misuse or dual use. We will summarize these efforts and propose that they could be used for scoring the millions of commercially available molecules, most of which likely do not have a known LD50 or for that matter any data in vitro or in vivo for toxicity.The lethal dose or concentration which kills 50% of the animals (LD50 or LC50) is an important parameter for scientists to understand the toxicity of chemicals in different scenarios that can be used to make go-no-go decisions, and ultimately assist in the choice of the right personal protective equipment needed for containment. The LD50 assessment process has also required the use of many animals although modern methods have reduced the number of rats needed. Since a compound is usually considered highly toxic when the LD50 is lower than 25 mg/kg, such a classification provides potentially valuable safety information to synthetic chemists and other safety assessment scientists. The need for finding alternative approaches such as computational methods is important to ultimately reduce animal use for this testing further still. We now summarize our efforts to use public data for building in vivo LD50 or LC50 classification and regression machine learning models for various species (rat, mouse, fish and daphnia) and their 5-fold cross validation statistics with different machine learning algorithms as well as an external curated test set for mouse LD50. These datasets consist of different molecule classes, may cover different activity ranges, and also have a range of dataset sizes. The challenges of using such computational models are that their applicability domain will also need to be understood so that they can be used to make reliable predictions for novel molecules. These machine learning models will also need to be backed up with experimental validation. However, such models could also be used for efforts to bridge gaps in individual toxicity datasets. Making such models available also opens them up to potential misuse or dual use. We will summarize these efforts and propose that they could be used for scoring the millions of commercially available molecules, most of which likely do not have a known LD50 or for that matter any data in vitro or in vivo for toxicity.
AbstractList The lethal dose or concentration which kills 50% of the animals (LD50 or LC50) is an important parameter for scientists to understand the toxicity of chemicals in different scenarios that can be used to make go-no-go decisions, and ultimately assist in the choice of the right personal protective equipment needed for containment. The LD50 assessment process has also required the use of many animals although modern methods have reduced the number of rats needed. Since a compound is usually considered highly toxic when the LD50 is lower than 25 mg/kg, such a classification provides potentially valuable safety information to synthetic chemists and other safety assessment scientists. The need for finding alternative approaches such as computational methods is important to ultimately reduce animal use for this testing further still. We now summarize our efforts to use public data for building in vivo LD50 or LC50 classification and regression machine learning models for various species (rat, mouse, fish and daphnia) and their 5-fold cross validation statistics with different machine learning algorithms as well as an external curated test set for mouse LD50. These datasets consist of different molecule classes, may cover different activity ranges, and also have a range of dataset sizes. The challenges of using such computational models are that their applicability domain will also need to be understood so that they can be used to make reliable predictions for novel molecules. These machine learning models will also need to be backed up with experimental validation. However, such models could also be used for efforts to bridge gaps in individual toxicity datasets. Making such models available also opens them up to potential misuse or dual use. We will summarize these efforts and propose that they could be used for scoring the millions of commercially available molecules, most of which likely do not have a known LD50 or for that matter any data in vitro or in vivo for toxicity.The lethal dose or concentration which kills 50% of the animals (LD50 or LC50) is an important parameter for scientists to understand the toxicity of chemicals in different scenarios that can be used to make go-no-go decisions, and ultimately assist in the choice of the right personal protective equipment needed for containment. The LD50 assessment process has also required the use of many animals although modern methods have reduced the number of rats needed. Since a compound is usually considered highly toxic when the LD50 is lower than 25 mg/kg, such a classification provides potentially valuable safety information to synthetic chemists and other safety assessment scientists. The need for finding alternative approaches such as computational methods is important to ultimately reduce animal use for this testing further still. We now summarize our efforts to use public data for building in vivo LD50 or LC50 classification and regression machine learning models for various species (rat, mouse, fish and daphnia) and their 5-fold cross validation statistics with different machine learning algorithms as well as an external curated test set for mouse LD50. These datasets consist of different molecule classes, may cover different activity ranges, and also have a range of dataset sizes. The challenges of using such computational models are that their applicability domain will also need to be understood so that they can be used to make reliable predictions for novel molecules. These machine learning models will also need to be backed up with experimental validation. However, such models could also be used for efforts to bridge gaps in individual toxicity datasets. Making such models available also opens them up to potential misuse or dual use. We will summarize these efforts and propose that they could be used for scoring the millions of commercially available molecules, most of which likely do not have a known LD50 or for that matter any data in vitro or in vivo for toxicity.
Author Lane, Thomas R
Urbina, Fabio
Ekins, Sean
Harris, Joshua
Author_xml – sequence: 1
  givenname: Thomas R
  surname: Lane
  fullname: Lane, Thomas R
– sequence: 2
  givenname: Joshua
  surname: Harris
  fullname: Harris, Joshua
– sequence: 3
  givenname: Fabio
  surname: Urbina
  fullname: Urbina, Fabio
– sequence: 4
  givenname: Sean
  surname: Ekins
  fullname: Ekins, Sean
BookMark eNpNjD1PwzAURS1UJErpzuiRJa39YicvGyh8SokYgLmy3Rca5NohTv4_IBiY7pHO0T1nixADMXYpxUYKkFvj0sYdTNqAE0IgnrClxBIzoYVa_OMztk7p4zuBXOZKV0t2XcfjYMY-vPPmVottU2vBW-MOfSDekBnDj2rjnnziXRx5O_upHzzxl4FcT-mCnXbGJ1r_7Yq93d-91o9Z8_zwVN80mQGdT5myUBpZWQOlAltKpbFyUCkrisJYpConANR7tB0WrnQWAY1DS4CdsLmDFbv6_R3G-DlTmnbHPjny3gSKc9oB5lgoJYsSvgAUbE81
ContentType Journal Article
DBID 7X8
DOI 10.1021/acs.chas.2c00088
DatabaseName MEDLINE - Academic
DatabaseTitle MEDLINE - Academic
DatabaseTitleList MEDLINE - Academic
Database_xml – sequence: 1
  dbid: 7X8
  name: MEDLINE - Academic
  url: https://search.proquest.com/medline
  sourceTypes: Aggregation Database
DeliveryMethod no_fulltext_linktorsrc
Discipline Medicine
EISSN 1878-0504
GroupedDBID --K
--M
.~1
0R~
1B1
1~.
1~5
4.4
457
4G.
53G
7-5
71M
7X8
8P~
AAEDT
AAIKJ
AAKOC
AALRI
AAOAW
AARLI
ABBLG
ABJNI
ABLBI
ABNUV
ABQRX
ACDAQ
ACGFS
ACS
ADBBV
ADECG
ADEWK
ADEZE
AEKER
AFTJW
AGHFR
AGUBO
AGYEJ
AHGAQ
ALMA_UNASSIGNED_HOLDINGS
BAANH
BLXMC
CS3
CUPRZ
DU5
EBS
ENUVR
EO8
EO9
EP2
EP3
FDB
FEDTE
FLBIZ
FNPLU
G-Q
GBLVA
GGK
HVGLF
IHE
J1W
MO0
N9A
O-L
O9-
OAUVE
OZT
P-8
P-9
P2P
PC.
Q38
RPZ
SDF
SES
SSZ
VF5
VG9
~G-
~HD
ID FETCH-LOGICAL-a253t-4b27a19ba2742b714589c294b066ab8e93e2285d8bf86c7cb828ac8be28f0b3c2
IEDL.DBID 7X8
ISICitedReferencesCount 22
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000937129800001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 1878-0504
IngestDate Wed Oct 01 13:10:05 EDT 2025
IsDoiOpenAccess false
IsOpenAccess true
IsPeerReviewed true
IsScholarly true
Issue 2
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-a253t-4b27a19ba2742b714589c294b066ab8e93e2285d8bf86c7cb828ac8be28f0b3c2
Notes ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
OpenAccessLink https://pmc.ncbi.nlm.nih.gov/articles/PMC10348353/pdf/nihms-1904611.pdf
PQID 2838644167
PQPubID 23479
ParticipantIDs proquest_miscellaneous_2838644167
PublicationCentury 2000
PublicationDate 20230327
PublicationDateYYYYMMDD 2023-03-27
PublicationDate_xml – month: 03
  year: 2023
  text: 20230327
  day: 27
PublicationDecade 2020
PublicationTitle ACS Chemical Health & Safety.
PublicationYear 2023
SSID ssj0002313459
Score 2.3770013
Snippet The lethal dose or concentration which kills 50% of the animals (LD50 or LC50) is an important parameter for scientists to understand the toxicity of chemicals...
SourceID proquest
SourceType Aggregation Database
StartPage 83
Title Comparing LD50/LC50 Machine Learning Models for Multiple Species
URI https://www.proquest.com/docview/2838644167
Volume 30
WOSCitedRecordID wos000937129800001&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/eLvHCXMwpV1NT8MwDI2AIcSFb8S3gsS1rE3Txj0BGkwctokDSLtNSZqOSagDOvj92FkGBy5I3HOIbMfvxbb8GLsAQFAyVRlBkheRNNrhm7NVZKocbGJzAnUvNqEGAxgOi4dQcGvCWOUiJ_pEXU4t1cjbCINA2J2rq9e3iFSjqLsaJDSWWStFKkNRrYbwXWNB7pJKr5eWAC2SzWIZOpWIbG1t0avPurkUlpAQfmVjDzHdzf9ebottBHLJb-bRsM2WXL3D1vqhfb7Lrjtz1cF6zHu3WdzudbKY9_04peNh0-qYkzzaS8ORzfJ-GDfkXqbeNXvsqXv32LmPgoRCpEWWztD4QumkMJo6skYlMoPCikIaZBragCtSJwRkJZgKcquswQ-YtmCcgCo2qRX7bKWe1u6Acfp6GRdra2jLmkoNMhtajpbL0qGf5SE7X9hmhCFKfQddu-lHM_qxztEfzhyzdZJ0pzkvoU5Yq8Jn6E7Zqv2cTZr3M-_hL-oXrZc
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=Comparing+LD50%2FLC50+Machine+Learning+Models+for+Multiple+Species&rft.jtitle=ACS+Chemical+Health+%26+Safety.&rft.au=Lane%2C+Thomas+R&rft.au=Harris%2C+Joshua&rft.au=Urbina%2C+Fabio&rft.au=Ekins%2C+Sean&rft.date=2023-03-27&rft.issn=1878-0504&rft.eissn=1878-0504&rft.volume=30&rft.issue=2&rft.spage=83&rft_id=info:doi/10.1021%2Facs.chas.2c00088&rft.externalDBID=NO_FULL_TEXT
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1878-0504&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1878-0504&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1878-0504&client=summon