Guidance for good practice in the application of machine learning in development of toxicological quantitative structure-activity relationships (QSARs)
Recent years have seen a substantial growth in the adoption of machine learning approaches for the purposes of quantitative structure-activity relationship (QSAR) development. Such a trend has coincided with desire to see a shifting in the focus of methodology employed within chemical safety assessm...
Uložené v:
| Vydané v: | PloS one Ročník 18; číslo 5; s. e0282924 |
|---|---|
| Hlavní autori: | , , , |
| Médium: | Journal Article |
| Jazyk: | English |
| Vydavateľské údaje: |
United States
Public Library of Science
10.05.2023
|
| Predmet: | |
| ISSN: | 1932-6203, 1932-6203 |
| On-line prístup: | Získať plný text |
| Tagy: |
Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
|
| Abstract | Recent years have seen a substantial growth in the adoption of machine learning approaches for the purposes of quantitative structure-activity relationship (QSAR) development. Such a trend has coincided with desire to see a shifting in the focus of methodology employed within chemical safety assessment: away from traditional reliance upon animal-intensive
in vivo
protocols, and towards increased application of
in silico
(or computational) predictive toxicology. With QSAR central amongst techniques applied in this area, the emergence of algorithms trained through machine learning with the objective of toxicity estimation has, quite naturally, arisen. On account of the pattern-recognition capabilities of the underlying methods, the statistical power of the ensuing models is potentially considerable–appropriate for the handling even of vast, heterogeneous datasets. However, such potency comes at a price: this manifesting as the general practical deficits observed with respect to the reproducibility, interpretability and generalisability of the resulting tools. Unsurprisingly, these elements have served to hinder broader uptake (most notably within a regulatory setting). Areas of uncertainty liable to accompany (and hence detract from applicability of) toxicological QSAR have previously been highlighted, accompanied by the forwarding of suggestions for “best practice” aimed at mitigation of their influence. However, the scope of such exercises has remained limited to “classical” QSAR–that conducted through use of linear regression and related techniques, with the adoption of comparatively few features or descriptors. Accordingly, the intention of this study has been to extend the remit of best practice guidance, so as to address concerns specific to employment of machine learning within the field. In doing so, the impact of strategies aimed at enhancing the transparency (feature importance, feature reduction), generalisability (cross-validation) and predictive power (hyperparameter optimisation) of algorithms, trained upon real toxicity data through six common learning approaches, is evaluated. |
|---|---|
| AbstractList | Recent years have seen a substantial growth in the adoption of machine learning approaches for the purposes of quantitative structure-activity relationship (QSAR) development. Such a trend has coincided with desire to see a shifting in the focus of methodology employed within chemical safety assessment: away from traditional reliance upon animal-intensive
in vivo
protocols, and towards increased application of
in silico
(or computational) predictive toxicology. With QSAR central amongst techniques applied in this area, the emergence of algorithms trained through machine learning with the objective of toxicity estimation has, quite naturally, arisen. On account of the pattern-recognition capabilities of the underlying methods, the statistical power of the ensuing models is potentially considerable–appropriate for the handling even of vast, heterogeneous datasets. However, such potency comes at a price: this manifesting as the general practical deficits observed with respect to the reproducibility, interpretability and generalisability of the resulting tools. Unsurprisingly, these elements have served to hinder broader uptake (most notably within a regulatory setting). Areas of uncertainty liable to accompany (and hence detract from applicability of) toxicological QSAR have previously been highlighted, accompanied by the forwarding of suggestions for “best practice” aimed at mitigation of their influence. However, the scope of such exercises has remained limited to “classical” QSAR–that conducted through use of linear regression and related techniques, with the adoption of comparatively few features or descriptors. Accordingly, the intention of this study has been to extend the remit of best practice guidance, so as to address concerns specific to employment of machine learning within the field. In doing so, the impact of strategies aimed at enhancing the transparency (feature importance, feature reduction), generalisability (cross-validation) and predictive power (hyperparameter optimisation) of algorithms, trained upon real toxicity data through six common learning approaches, is evaluated. Recent years have seen a substantial growth in the adoption of machine learning approaches for the purposes of quantitative structure-activity relationship (QSAR) development. Such a trend has coincided with desire to see a shifting in the focus of methodology employed within chemical safety assessment: away from traditional reliance upon animal-intensive in vivo protocols, and towards increased application of in silico (or computational) predictive toxicology. With QSAR central amongst techniques applied in this area, the emergence of algorithms trained through machine learning with the objective of toxicity estimation has, quite naturally, arisen. On account of the pattern-recognition capabilities of the underlying methods, the statistical power of the ensuing models is potentially considerable-appropriate for the handling even of vast, heterogeneous datasets. However, such potency comes at a price: this manifesting as the general practical deficits observed with respect to the reproducibility, interpretability and generalisability of the resulting tools. Unsurprisingly, these elements have served to hinder broader uptake (most notably within a regulatory setting). Areas of uncertainty liable to accompany (and hence detract from applicability of) toxicological QSAR have previously been highlighted, accompanied by the forwarding of suggestions for "best practice" aimed at mitigation of their influence. However, the scope of such exercises has remained limited to "classical" QSAR-that conducted through use of linear regression and related techniques, with the adoption of comparatively few features or descriptors. Accordingly, the intention of this study has been to extend the remit of best practice guidance, so as to address concerns specific to employment of machine learning within the field. In doing so, the impact of strategies aimed at enhancing the transparency (feature importance, feature reduction), generalisability (cross-validation) and predictive power (hyperparameter optimisation) of algorithms, trained upon real toxicity data through six common learning approaches, is evaluated. Recent years have seen a substantial growth in the adoption of machine learning approaches for the purposes of quantitative structure-activity relationship (QSAR) development. Such a trend has coincided with desire to see a shifting in the focus of methodology employed within chemical safety assessment: away from traditional reliance upon animal-intensive in vivo protocols, and towards increased application of in silico (or computational) predictive toxicology. With QSAR central amongst techniques applied in this area, the emergence of algorithms trained through machine learning with the objective of toxicity estimation has, quite naturally, arisen. On account of the pattern-recognition capabilities of the underlying methods, the statistical power of the ensuing models is potentially considerable-appropriate for the handling even of vast, heterogeneous datasets. However, such potency comes at a price: this manifesting as the general practical deficits observed with respect to the reproducibility, interpretability and generalisability of the resulting tools. Unsurprisingly, these elements have served to hinder broader uptake (most notably within a regulatory setting). Areas of uncertainty liable to accompany (and hence detract from applicability of) toxicological QSAR have previously been highlighted, accompanied by the forwarding of suggestions for "best practice" aimed at mitigation of their influence. However, the scope of such exercises has remained limited to "classical" QSAR-that conducted through use of linear regression and related techniques, with the adoption of comparatively few features or descriptors. Accordingly, the intention of this study has been to extend the remit of best practice guidance, so as to address concerns specific to employment of machine learning within the field. In doing so, the impact of strategies aimed at enhancing the transparency (feature importance, feature reduction), generalisability (cross-validation) and predictive power (hyperparameter optimisation) of algorithms, trained upon real toxicity data through six common learning approaches, is evaluated.Recent years have seen a substantial growth in the adoption of machine learning approaches for the purposes of quantitative structure-activity relationship (QSAR) development. Such a trend has coincided with desire to see a shifting in the focus of methodology employed within chemical safety assessment: away from traditional reliance upon animal-intensive in vivo protocols, and towards increased application of in silico (or computational) predictive toxicology. With QSAR central amongst techniques applied in this area, the emergence of algorithms trained through machine learning with the objective of toxicity estimation has, quite naturally, arisen. On account of the pattern-recognition capabilities of the underlying methods, the statistical power of the ensuing models is potentially considerable-appropriate for the handling even of vast, heterogeneous datasets. However, such potency comes at a price: this manifesting as the general practical deficits observed with respect to the reproducibility, interpretability and generalisability of the resulting tools. Unsurprisingly, these elements have served to hinder broader uptake (most notably within a regulatory setting). Areas of uncertainty liable to accompany (and hence detract from applicability of) toxicological QSAR have previously been highlighted, accompanied by the forwarding of suggestions for "best practice" aimed at mitigation of their influence. However, the scope of such exercises has remained limited to "classical" QSAR-that conducted through use of linear regression and related techniques, with the adoption of comparatively few features or descriptors. Accordingly, the intention of this study has been to extend the remit of best practice guidance, so as to address concerns specific to employment of machine learning within the field. In doing so, the impact of strategies aimed at enhancing the transparency (feature importance, feature reduction), generalisability (cross-validation) and predictive power (hyperparameter optimisation) of algorithms, trained upon real toxicity data through six common learning approaches, is evaluated. |
| Audience | Academic |
| Author | Belfield, Samuel J. Firman, James W. Enoch, Steven J. Cronin, Mark T.D. |
| AuthorAffiliation | School of Pharmacy and Biomolecular Sciences, Liverpool John Moores University, Liverpool, United Kingdom Jeonbuk Natiomal University, REPUBLIC OF KOREA |
| AuthorAffiliation_xml | – name: School of Pharmacy and Biomolecular Sciences, Liverpool John Moores University, Liverpool, United Kingdom – name: Jeonbuk Natiomal University, REPUBLIC OF KOREA |
| Author_xml | – sequence: 1 givenname: Samuel J. orcidid: 0000-0002-6532-2532 surname: Belfield fullname: Belfield, Samuel J. – sequence: 2 givenname: Mark T.D. surname: Cronin fullname: Cronin, Mark T.D. – sequence: 3 givenname: Steven J. surname: Enoch fullname: Enoch, Steven J. – sequence: 4 givenname: James W. orcidid: 0000-0003-0319-1407 surname: Firman fullname: Firman, James W. |
| BackLink | https://www.ncbi.nlm.nih.gov/pubmed/37163504$$D View this record in MEDLINE/PubMed |
| BookMark | eNqNk91q3DAQhU1JaX7aNyitoVCSi91K_pHl3JQQ2jQQCE3a3oqJPNpV0EqOJC_Jk_R1K282JRtCKbqwGH_njH2k2c22rLOYZW8pmdKyoZ-u3eAtmGmfylNS8KItqhfZDm3LYsIKUm492m9nuyFcE1KXnLFX2XbSs7Im1U72-2TQHViJuXI-nznX5b0HGXWqaJvHOebQ90ZLiNrZ3Kl8AXKuLeYGwVttZyPW4RKN6xdo44hEd6ulM26WZCa_GcBGHZPBEvMQ_SDj4HEyNlnqeJd7NCvzMNd9yPe_Xx5dhIPX2UsFJuCb9XMv-_n1y4_jb5Oz85PT46OziWRFEyfIyyvGagBOFVOSNy2jilMEXnegeFkBVx2QhrbsirXQVlQRQJCEsI4WCsq97P29b29cEOtMgyg4pW1BC84T8XlNDFcL7GT6Rw9G9F4vwN8JB1psvrF6LmZuKSihKWbSJof9tYN3NwOGKBY6SDQGLLph1ayoSVNVJKEfnqDPf9KamoFBoa1yqbEcTcVRU_GmblldJGr6DJVWh4t0PBaVTvUNwcGGIDERb-MMhhDE6eXF_7PnvzbZj4_YOYKJ8-DMsDr0TfDd46j_ZvxwXRNweA9I70LwqIRcXSw3Jq9NilyMs_EQmhhnQ6xnI4mrJ-IH_3_K_gBG7xa1 |
| CitedBy_id | crossref_primary_10_1016_j_toxlet_2024_07_337 crossref_primary_10_1186_s13321_025_01041_0 crossref_primary_10_1186_s13677_024_00600_4 crossref_primary_10_1016_j_comtox_2025_100374 crossref_primary_10_1016_j_jhazmat_2025_139134 crossref_primary_10_1016_j_comtox_2025_100367 crossref_primary_10_1016_j_comtox_2024_100303 crossref_primary_10_1016_j_tox_2025_154230 crossref_primary_10_1016_j_comtox_2024_100338 crossref_primary_10_1016_j_heliyon_2023_e23810 crossref_primary_10_1016_j_scitotenv_2024_170173 crossref_primary_10_1021_acs_jcim_4c02363 crossref_primary_10_1038_s41597_023_02612_2 crossref_primary_10_1016_j_chemosphere_2024_142362 crossref_primary_10_1016_j_yrtph_2024_105716 crossref_primary_10_3389_fchem_2023_1292027 crossref_primary_10_1007_s00204_024_03803_5 crossref_primary_10_1080_14740338_2025_2460439 crossref_primary_10_1007_s11030_025_11133_6 |
| Cites_doi | 10.1080/17460441.2018.1542428 10.3850/978-981-09-5247-1_017 10.1021/tx025589p 10.1002/widm.1200 10.1021/ci900203n 10.1007/s41965-019-00023-0 10.1080/1062936X.2011.604100 10.1016/j.isci.2021.103052 10.1088/1742-6596/1168/2/022022 10.1145/3359786 10.1001/jama.2019.20866 10.1016/j.drudis.2018.05.010 10.1002/qsar.200610151 10.1021/ci00028a014 10.1002/srin.202000053 10.1186/s13321-019-0383-2 10.1186/1758-2946-3-33 10.1142/S0219530516400042 10.1007/s10822-013-9664-4 10.1080/105172397243079 10.1021/ci980033m 10.1002/9780470116449.ch6 10.1186/s13321-021-00519-x 10.1021/ci00057a005 10.1021/ci500747n 10.1111/j.1600-0587.2012.07348.x 10.1080/10629360412331319808 10.1002/wcms.1475 10.1016/j.ecoenv.2020.110179 10.1021/acs.chemrestox.0c00373 10.1021/ci00037a002 10.1002/minf.201000173 10.1038/s41598-018-24783-4 10.1038/s41592-021-01256-7 10.1002/minf.201600118 10.1016/j.eswa.2022.117230 10.1016/j.chemolab.2011.08.007 10.1021/acs.jcim.6b00591 10.1016/j.yrtph.2021.104956 10.1109/ACCESS.2021.3119110 10.1609/aaai.v32i1.11503 10.1186/s13321-020-0408-x 10.1038/s42256-019-0138-9 10.1016/j.jeconom.2015.02.006 10.1021/acs.jcim.2c01422 10.1177/026119291304100111 10.1016/j.yrtph.2019.04.007 10.3390/electronics8080832 10.2174/157340906778992346 10.1016/j.conbuildmat.2019.07.224 10.1089/big.2018.0175 10.1177/2053951716670189 10.1007/BF00994018 10.1021/ci200409x 10.1021/jm4004285 10.1093/toxsci/kfac042 10.1093/bioinformatics/btq134 10.1007/s10822-008-9240-5 10.1023/A:1010933404324 10.1016/j.chemosphere.2009.12.055 10.1007/s11229-022-03485-5 10.1002/jcc.21707 10.1177/0261192920965977 10.1093/toxsci/kfac075 10.1021/acs.est.0c06551 |
| ContentType | Journal Article |
| Copyright | Copyright: © 2023 Belfield et al. This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited. COPYRIGHT 2023 Public Library of Science 2023 Belfield et al. This is an open access article distributed under the terms of the Creative Commons Attribution License: http://creativecommons.org/licenses/by/4.0/ (the “License”), which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited. Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License. 2023 Belfield et al 2023 Belfield et al 2023 Belfield et al. This is an open access article distributed under the terms of the Creative Commons Attribution License: http://creativecommons.org/licenses/by/4.0/ (the “License”), which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited. Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License. |
| Copyright_xml | – notice: Copyright: © 2023 Belfield et al. This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited. – notice: COPYRIGHT 2023 Public Library of Science – notice: 2023 Belfield et al. This is an open access article distributed under the terms of the Creative Commons Attribution License: http://creativecommons.org/licenses/by/4.0/ (the “License”), which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited. Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License. – notice: 2023 Belfield et al 2023 Belfield et al – notice: 2023 Belfield et al. This is an open access article distributed under the terms of the Creative Commons Attribution License: http://creativecommons.org/licenses/by/4.0/ (the “License”), which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited. Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License. |
| DBID | AAYXX CITATION CGR CUY CVF ECM EIF NPM IOV ISR 3V. 7QG 7QL 7QO 7RV 7SN 7SS 7T5 7TG 7TM 7U9 7X2 7X7 7XB 88E 8AO 8C1 8FD 8FE 8FG 8FH 8FI 8FJ 8FK ABJCF ABUWG AEUYN AFKRA ARAPS ATCPS AZQEC BBNVY BENPR BGLVJ BHPHI C1K CCPQU D1I DWQXO FR3 FYUFA GHDGH GNUQQ H94 HCIFZ K9. KB. KB0 KL. L6V LK8 M0K M0S M1P M7N M7P M7S NAPCQ P5Z P62 P64 PATMY PDBOC PHGZM PHGZT PIMPY PJZUB PKEHL PPXIY PQEST PQGLB PQQKQ PQUKI PRINS PTHSS PYCSY RC3 7X8 5PM |
| DOI | 10.1371/journal.pone.0282924 |
| DatabaseName | CrossRef Medline MEDLINE MEDLINE (Ovid) MEDLINE MEDLINE PubMed Gale In Context: Opposing Viewpoints Gale In Context: Science ProQuest Central (Corporate) Animal Behavior Abstracts Bacteriology Abstracts (Microbiology B) Biotechnology Research Abstracts Nursing & Allied Health Database Ecology Abstracts Entomology Abstracts (Full archive) Immunology Abstracts Meteorological & Geoastrophysical Abstracts Nucleic Acids Abstracts Virology and AIDS Abstracts Agricultural Science Collection Health & Medical Collection (Proquest) ProQuest Central (purchase pre-March 2016) Medical Database (Alumni Edition) ProQuest Pharma Collection Proquest Public Health Database Technology Research Database ProQuest SciTech Collection ProQuest Technology Collection ProQuest Natural Science Collection Hospital Premium Collection Hospital Premium Collection (Alumni Edition) ProQuest Central (Alumni) (purchase pre-March 2016) ProQuest MSED ProQuest Central (Alumni) ProQuest One Sustainability ProQuest Central UK/Ireland Advanced Technologies & Computer Science Collection Agricultural & Environmental Science Collection ProQuest Central Essentials Biological Science Collection ProQuest Central ProQuest Technology Collection Natural Science Collection Environmental Sciences and Pollution Management ProQuest One ProQuest Materials Science Collection ProQuest Central Korea Engineering Research Database ProQuest Health & Medical Collection Health Research Premium Collection (Alumni) ProQuest Central Student AIDS and Cancer Research Abstracts SciTech Premium Collection ProQuest Health & Medical Complete (Alumni) Materials Science Database Nursing & Allied Health Database (Alumni Edition) Meteorological & Geoastrophysical Abstracts - Academic ProQuest Engineering Collection ProQuest Biological Science Collection Agricultural Science Database ProQuest Health & Medical Collection Medical Database Algology Mycology and Protozoology Abstracts (Microbiology C) Biological Science Database Engineering Database Nursing & Allied Health Premium Advanced Technologies & Aerospace Database ProQuest Advanced Technologies & Aerospace Collection Biotechnology and BioEngineering Abstracts Environmental Science Database Materials Science Collection ProQuest Central Premium ProQuest One Academic (New) Publicly Available Content Database ProQuest Health & Medical Research Collection ProQuest One Academic Middle East (New) ProQuest One Health & Nursing ProQuest One Academic Eastern Edition (DO NOT USE) ProQuest One Applied & Life Sciences ProQuest One Academic (retired) ProQuest One Academic UKI Edition ProQuest Central China Engineering Collection Environmental Science Collection Genetics Abstracts MEDLINE - Academic PubMed Central (Full Participant titles) |
| DatabaseTitle | CrossRef MEDLINE Medline Complete MEDLINE with Full Text PubMed MEDLINE (Ovid) Agricultural Science Database Publicly Available Content Database ProQuest Central Student ProQuest Advanced Technologies & Aerospace Collection ProQuest Central Essentials Nucleic Acids Abstracts SciTech Premium Collection ProQuest Central China Environmental Sciences and Pollution Management ProQuest One Applied & Life Sciences ProQuest One Sustainability Health Research Premium Collection Meteorological & Geoastrophysical Abstracts Natural Science Collection Health & Medical Research Collection Biological Science Collection ProQuest Central (New) ProQuest Medical Library (Alumni) Engineering Collection Advanced Technologies & Aerospace Collection Engineering Database Virology and AIDS Abstracts ProQuest Biological Science Collection ProQuest One Academic Eastern Edition Agricultural Science Collection ProQuest Hospital Collection ProQuest Technology Collection Health Research Premium Collection (Alumni) Biological Science Database Ecology Abstracts ProQuest Hospital Collection (Alumni) Biotechnology and BioEngineering Abstracts Environmental Science Collection Entomology Abstracts Nursing & Allied Health Premium ProQuest Health & Medical Complete ProQuest One Academic UKI Edition Environmental Science Database ProQuest Nursing & Allied Health Source (Alumni) Engineering Research Database ProQuest One Academic Meteorological & Geoastrophysical Abstracts - Academic ProQuest One Academic (New) Technology Collection Technology Research Database ProQuest One Academic Middle East (New) Materials Science Collection ProQuest Health & Medical Complete (Alumni) ProQuest Central (Alumni Edition) ProQuest One Community College ProQuest One Health & Nursing ProQuest Natural Science Collection ProQuest Pharma Collection ProQuest Central ProQuest Health & Medical Research Collection Genetics Abstracts ProQuest Engineering Collection Biotechnology Research Abstracts Health and Medicine Complete (Alumni Edition) ProQuest Central Korea Bacteriology Abstracts (Microbiology B) Algology Mycology and Protozoology Abstracts (Microbiology C) Agricultural & Environmental Science Collection AIDS and Cancer Research Abstracts Materials Science Database ProQuest Materials Science Collection ProQuest Public Health ProQuest Nursing & Allied Health Source ProQuest SciTech Collection Advanced Technologies & Aerospace Database ProQuest Medical Library Animal Behavior Abstracts Materials Science & Engineering Collection Immunology Abstracts ProQuest Central (Alumni) MEDLINE - Academic |
| DatabaseTitleList | CrossRef MEDLINE - Academic Agricultural Science Database 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: PIMPY name: Publicly Available Content Database url: http://search.proquest.com/publiccontent sourceTypes: Aggregation Database |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Sciences (General) |
| DocumentTitleAlternate | Good practice in application of machine learning for toxicology QSAR |
| EISSN | 1932-6203 |
| ExternalDocumentID | 2811921288 PMC10171609 A748759652 37163504 10_1371_journal_pone_0282924 |
| Genre | Journal Article |
| GeographicLocations | United Kingdom United States--US |
| GeographicLocations_xml | – name: United Kingdom – name: United States--US |
| GroupedDBID | --- 123 29O 2WC 53G 5VS 7RV 7X2 7X7 7XC 88E 8AO 8C1 8CJ 8FE 8FG 8FH 8FI 8FJ A8Z AAFWJ AAUCC AAWOE AAYXX ABDBF ABIVO ABJCF ABUWG ACCTH ACGFO ACIHN ACIWK ACPRK ACUHS ADBBV AEAQA AENEX AEUYN AFFHD AFKRA AFPKN AFRAH AHMBA ALMA_UNASSIGNED_HOLDINGS AOIJS APEBS ARAPS ATCPS BAIFH BAWUL BBNVY BBTPI BCNDV BENPR BGLVJ BHPHI BKEYQ BPHCQ BVXVI BWKFM CCPQU CITATION CS3 D1I D1J D1K DIK DU5 E3Z EAP EAS EBD EMOBN ESX EX3 F5P FPL FYUFA GROUPED_DOAJ GX1 HCIFZ HH5 HMCUK HYE IAO IEA IGS IHR IHW INH INR IOV IPY ISE ISR ITC K6- KB. KQ8 L6V LK5 LK8 M0K M1P M48 M7P M7R M7S M~E NAPCQ O5R O5S OK1 OVT P2P P62 PATMY PDBOC PHGZM PHGZT PIMPY PJZUB PPXIY PQGLB PQQKQ PROAC PSQYO PTHSS PV9 PYCSY RNS RPM RZL SV3 TR2 UKHRP WOQ WOW ~02 ~KM ADRAZ ALIPV BBORY CGR CUY CVF ECM EIF IPNFZ NPM RIG 3V. 7QG 7QL 7QO 7SN 7SS 7T5 7TG 7TM 7U9 7XB 8FD 8FK AZQEC C1K DWQXO ESTFP FR3 GNUQQ H94 K9. KL. M7N P64 PKEHL PQEST PQUKI PRINS RC3 7X8 PUEGO 5PM AAPBV ABPTK N95 |
| ID | FETCH-LOGICAL-c627t-e83b665aa81f6fc87961f81ea85daf834a8fda07196b69a941f0aeac006d12fa3 |
| IEDL.DBID | 7RV |
| ISICitedReferencesCount | 25 |
| ISICitedReferencesURI | http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001022290100001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| ISSN | 1932-6203 |
| IngestDate | Sun Jul 02 11:03:49 EDT 2023 Tue Nov 04 02:06:46 EST 2025 Sun Sep 28 01:07:44 EDT 2025 Tue Oct 07 08:10:50 EDT 2025 Sat Nov 29 13:00:19 EST 2025 Sat Nov 29 09:48:07 EST 2025 Wed Nov 26 11:10:40 EST 2025 Wed Nov 26 11:29:57 EST 2025 Thu May 22 21:20:06 EDT 2025 Thu Apr 03 07:07:17 EDT 2025 Tue Nov 18 22:01:44 EST 2025 Sat Nov 29 03:27:20 EST 2025 |
| IsDoiOpenAccess | true |
| IsOpenAccess | true |
| IsPeerReviewed | true |
| IsScholarly | true |
| Issue | 5 |
| Language | English |
| License | Copyright: © 2023 Belfield et al. This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited. This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited. Creative Commons Attribution License |
| LinkModel | DirectLink |
| MergedId | FETCHMERGED-LOGICAL-c627t-e83b665aa81f6fc87961f81ea85daf834a8fda07196b69a941f0aeac006d12fa3 |
| Notes | ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14 content type line 23 Competing Interests: The authors have declared that no competing interests exist. |
| ORCID | 0000-0003-0319-1407 0000-0002-6532-2532 |
| OpenAccessLink | https://www.proquest.com/docview/2811921288?pq-origsite=%requestingapplication% |
| PMID | 37163504 |
| PQID | 2811921288 |
| PQPubID | 1436336 |
| PageCount | e0282924 |
| ParticipantIDs | plos_journals_2811921288 pubmedcentral_primary_oai_pubmedcentral_nih_gov_10171609 proquest_miscellaneous_2812507440 proquest_journals_2811921288 gale_infotracmisc_A748759652 gale_infotracacademiconefile_A748759652 gale_incontextgauss_ISR_A748759652 gale_incontextgauss_IOV_A748759652 gale_healthsolutions_A748759652 pubmed_primary_37163504 crossref_citationtrail_10_1371_journal_pone_0282924 crossref_primary_10_1371_journal_pone_0282924 |
| PublicationCentury | 2000 |
| PublicationDate | 2023-05-10 |
| PublicationDateYYYYMMDD | 2023-05-10 |
| PublicationDate_xml | – month: 05 year: 2023 text: 2023-05-10 day: 10 |
| PublicationDecade | 2020 |
| PublicationPlace | United States |
| PublicationPlace_xml | – name: United States – name: San Francisco – name: San Francisco, CA USA |
| PublicationTitle | PloS one |
| PublicationTitleAlternate | PLoS One |
| PublicationYear | 2023 |
| Publisher | Public Library of Science |
| Publisher_xml | – name: Public Library of Science |
| References | C Cortes (pone.0282924.ref034) 1995; 20 R Henckaerts (pone.0282924.ref053) 2022; 202 OE Gundersen (pone.0282924.ref084) 2020; 41 M Hewitt (pone.0282924.ref059) 2011; 22 C Gao (pone.0282924.ref090) 2018; 8 Z Lin (pone.0282924.ref017) 2022; 189 AL Beam (pone.0282924.ref085) 2020; 323 G Hooker (pone.0282924.ref075) 2019 D Fryer (pone.0282924.ref077) 2021; 9 TW Schultz (pone.0282924.ref058) 2002; 15 YH Zhao (pone.0282924.ref056) 2010; 79 HK Jabbar (pone.0282924.ref062) 2014 A Cherkasov (pone.0282924.ref002) 2014; 57 B Ghojogh (pone.0282924.ref093) 2019 R. Andonie (pone.0282924.ref045) 2019; 1 Y-C Lo (pone.0282924.ref011) 2018; 23 Association for Computing Machinery (pone.0282924.ref071) 2016 M Sapounidou (pone.0282924.ref080) 2021; 55 P Sugimura (pone.0282924.ref087) 2018 PM Khan (pone.0282924.ref050) 2018; 13 M Matveieva (pone.0282924.ref091) 2021; 13 T Chen (pone.0282924.ref026) 2016 J Ma (pone.0282924.ref040) 2015; 55 V Vakharia (pone.0282924.ref065) 2019; 225 NM O’Boyle (pone.0282924.ref020) 2011; 3 VE Kuz’min (pone.0282924.ref070) 2011; 30 V Ruusmann (pone.0282924.ref021) 2013; 27 U. Sahlin (pone.0282924.ref081) 2013; 41 W Zheng (pone.0282924.ref036) 2000; 40 P. Gramatica (pone.0282924.ref042) 2007; 26 DM Hawkins (pone.0282924.ref061) 2004; 44 DS Watson (pone.0282924.ref078) 2021 O. Ivanciuc (pone.0282924.ref035) 2007 VS Rose (pone.0282924.ref004) 1991; 10 Chollet F. Keras (pone.0282924.ref027) 2015 F. Thoreau (pone.0282924.ref052) 2016; 3 Lecture Notes in Computer Science (pone.0282924.ref055) 2008 MBA McDermott (pone.0282924.ref089) 2021; 13 D Gadaleta (pone.0282924.ref023) 2019; 11 F Pedregosa (pone.0282924.ref025) 2011; 12 J Hemmerich (pone.0282924.ref005) 2020; 10 J Mao (pone.0282924.ref006) 2021; 24 S Scardapane (pone.0282924.ref086) 2017; 7 A Altmann (pone.0282924.ref046) 2010; 26 HN Mhaskar (pone.0282924.ref039) 2016; 14 J Bergstra (pone.0282924.ref044) 2012; 13 Addition Wesley Publishing Company (pone.0282924.ref038) 1991 T Zhu (pone.0282924.ref079) 2020; 190 S Wold (pone.0282924.ref003) 1982; 23 R. Guha (pone.0282924.ref067) 2008; 22 T Ghafourian (pone.0282924.ref049) 2005; 16 C Recaido (pone.0282924.ref066) 2022 Association for Computing Machinery (pone.0282924.ref043) 2019 L. Breiman (pone.0282924.ref031) 2001; 45 S Lundberg (pone.0282924.ref047) 2017 CW Yap (pone.0282924.ref024) 2011; 32 JC Madden (pone.0282924.ref001) 2020; 48 Humana (pone.0282924.ref010) 2020 AF Agarap (pone.0282924.ref030) 2018 BJ Heil (pone.0282924.ref088) 2021; 18 Weininger (pone.0282924.ref019) 1988; 28 PG Polishchuk (pone.0282924.ref032) 2009; 49 L Wu (pone.0282924.ref068) 2021; 34 LS Carlsson (pone.0282924.ref076) 2020; 91 DA Winkler (pone.0282924.ref041) 2017; 37 A Varnek (pone.0282924.ref008) 2012; 52 M Abadi (pone.0282924.ref028) 2015 SJ Belfield (pone.0282924.ref012) 2021; 123 SM Lundberg (pone.0282924.ref048) 2020; 2 X. Ying (pone.0282924.ref016) 2019; 1168 DV Carvalho (pone.0282924.ref069) 2019; 8 HAA Alfeilat (pone.0282924.ref037) 2019; 7 Y Zhang (pone.0282924.ref064) 2015; 187 OE Gundersen (pone.0282924.ref015) 2018; 32 PM Khan (pone.0282924.ref092) 2018; 13 Humana (pone.0282924.ref007) 2020 DS Watson (pone.0282924.ref014) 2022; 200 MT Cronin (pone.0282924.ref018) 2019; 106 MT Cronin (pone.0282924.ref057) 2006; 2 B Kovalerchuk (pone.0282924.ref072) 2020 N Schaduangrat (pone.0282924.ref083) 2020; 12 DP Kingma (pone.0282924.ref029) 2014 GP Dexter (pone.0282924.ref063) 2020 TA Soares (pone.0282924.ref009) 2022; 62 TW Schultz (pone.0282924.ref022) 1997; 7 M Du (pone.0282924.ref073) 2019; 63 LH Hall (pone.0282924.ref074) 1995; 35 pone.0282924.ref013 AL Karmaus (pone.0282924.ref060) 2022; 188 J Pineau (pone.0282924.ref082) 2021; 22 CF Dormann (pone.0282924.ref054) 2013; 36 PK Ojha (pone.0282924.ref051) 2011; 109 N Srivastava (pone.0282924.ref094) 2014; 15 RP Sheridan (pone.0282924.ref033) 2016; 56 |
| References_xml | – volume: 13 start-page: 1075 year: 2018 ident: pone.0282924.ref050 article-title: Current approaches for choosing feature selection and learning algorithms in quantitative structure-activity relationships (QSAR) publication-title: Expert Opin Drug Discov doi: 10.1080/17460441.2018.1542428 – year: 2014 ident: pone.0282924.ref062 article-title: Methods to Avoid Over-fitting and Under-fitting in Supervised Machine Learning (Comparative Study) publication-title: Computer Science, Communication & Instrumentation Devices doi: 10.3850/978-981-09-5247-1_017 – volume: 15 start-page: 1602 issue: 12 year: 2002 ident: pone.0282924.ref058 article-title: Structure-toxicity relationships for aliphatic chemicals evaluated with Tetrahymena pyriformis publication-title: Chem Res Toxicol doi: 10.1021/tx025589p – volume: 7 start-page: e1200 year: 2017 ident: pone.0282924.ref086 article-title: Randomness in neural networks: an overview publication-title: Wiley Interdiscip Rev Data Min Knowl Discov doi: 10.1002/widm.1200 – volume: 49 start-page: 2481 year: 2009 ident: pone.0282924.ref032 article-title: Application of Random Forest Approach to QSAR Prediction of Aquatic Toxicity publication-title: J Chem Inf Model doi: 10.1021/ci900203n – volume: 1 start-page: 279 year: 2019 ident: pone.0282924.ref045 article-title: Hyperparameter optimization in learning systems publication-title: J Membr Comput doi: 10.1007/s41965-019-00023-0 – volume: 22 start-page: 621 year: 2011 ident: pone.0282924.ref059 article-title: Repeatability analysis of the Tetrahymena pyriformis population growth impairment assay publication-title: SAR QSAR Environ Res doi: 10.1080/1062936X.2011.604100 – volume: 41 start-page: 103 issue: 3 year: 2020 ident: pone.0282924.ref084 article-title: The Reproducibility Crisis is Real publication-title: AI Mag – year: 2017 ident: pone.0282924.ref047 article-title: A Unified Approach to Interpreting Model Predictions publication-title: arXiv:1705.07874v2 – volume: 24 start-page: 103052 issue: 9 year: 2021 ident: pone.0282924.ref006 article-title: Comprehensive strategies of machine-learning-based quantitative structure-activity relationship models publication-title: iScience doi: 10.1016/j.isci.2021.103052 – volume: 1168 start-page: 022022 year: 2019 ident: pone.0282924.ref016 article-title: An Overview of Overfitting and its Solutions publication-title: J Phys Conf Ser doi: 10.1088/1742-6596/1168/2/022022 – volume: 10 start-page: 6 issue: 1 year: 1991 ident: pone.0282924.ref004 article-title: An Application of Unsupervised Neural Network Methodology Kohonen Topology-Preserving Mapping to QSAR Analysis publication-title: Mol Inform – volume: 63 start-page: 68 issue: 1 year: 2019 ident: pone.0282924.ref073 article-title: Techniques for Interpretable Machine Learning publication-title: Commun ACM doi: 10.1145/3359786 – start-page: 1135 volume-title: Proceedings of the 22nd ACM SIGKDD international conference on knowledge discovery and data mining year: 2016 ident: pone.0282924.ref071 – volume: 323 start-page: 305 issue: 4 year: 2020 ident: pone.0282924.ref085 article-title: Challenges to the Reproducibility of Machine Learning Models in Health Care publication-title: JAMA doi: 10.1001/jama.2019.20866 – volume: 23 start-page: 1538 year: 2018 ident: pone.0282924.ref011 article-title: Machine learning in chemoinformatics and drug discovery publication-title: Drug Discov Today doi: 10.1016/j.drudis.2018.05.010 – volume: 26 start-page: 694 year: 2007 ident: pone.0282924.ref042 article-title: Principles of QSAR models validation: internal and external publication-title: QSAR Comb Sci doi: 10.1002/qsar.200610151 – start-page: 111 volume-title: Ecotoxicological QSARs, Methods in Pharmacology and Toxicology year: 2020 ident: pone.0282924.ref010 – volume: 35 start-page: 1039 issue: 6 year: 1995 ident: pone.0282924.ref074 article-title: Electrotopological State Indices for Atom Types: A Novel Combination of Electronic, Topological, and Valence State Information publication-title: J Chem Inf Comput Sci doi: 10.1021/ci00028a014 – volume: 91 start-page: 2000053 year: 2020 ident: pone.0282924.ref076 article-title: Interpretable Machine Learning–Tools to interpret the Predictions of a Machine Learning Model Predicting the Electrical Energy Consumption of an Electric Arc Furnace publication-title: Steel Res Int doi: 10.1002/srin.202000053 – volume: 11 start-page: 58 year: 2019 ident: pone.0282924.ref023 article-title: SAR and QSAR modeling of a large collection of LD50 rat acute oral toxicity data publication-title: J Cheminform doi: 10.1186/s13321-019-0383-2 – start-page: 565 volume-title: Knowledge-Based Intelligent Information and Engineering Systems year: 2008 ident: pone.0282924.ref055 – volume: 3 start-page: 33 year: 2011 ident: pone.0282924.ref020 article-title: Open Babel: An open chemical toolbox publication-title: J Cheminform doi: 10.1186/1758-2946-3-33 – volume: 14 start-page: 829 issue: 6 year: 2016 ident: pone.0282924.ref039 article-title: Deep vs. Shallow Networks: an Approximation Theory Perspective publication-title: Anal Appl doi: 10.1142/S0219530516400042 – start-page: 2623 volume-title: Optuna: A Next-generation Hyperparameter Opimization Framework. In: Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining (KDD ‘19) year: 2019 ident: pone.0282924.ref043 – volume: 27 start-page: 583 year: 2013 ident: pone.0282924.ref021 article-title: From data point timelines to a well curated data set, data mining of experimental data and chemical structure data from scientific articles, problems and possible solutions publication-title: J Comput Aided Mol Des doi: 10.1007/s10822-013-9664-4 – year: 2020 ident: pone.0282924.ref072 article-title: Survey of Explainable Machine Learning with Visual and Granular Methods beyond Quasi-explanations publication-title: arXiv:2009.10221v1 – volume: 7 start-page: 289 year: 1997 ident: pone.0282924.ref022 article-title: Tetratox: Tetrahymena pyriformis population growth impairment endpoint–a surrogate for fish lethality publication-title: Toxicol Mech Methods doi: 10.1080/105172397243079 – volume: 40 start-page: 185 year: 2000 ident: pone.0282924.ref036 article-title: Novel Variable Selection Quantitative Structure-Property Relationship Approach Based on the k-Nearest Neighbor Principle publication-title: J Chem Inf Comput Sci doi: 10.1021/ci980033m – year: 2019 ident: pone.0282924.ref075 article-title: Unrestricted Permutation forces Extrapolation: Variable Importance Requires at least One More Model, or There Is No Free Variable Importance publication-title: arXiv:1905.03151 – start-page: 291 year: 2007 ident: pone.0282924.ref035 article-title: Applications of Support Vector Machines in Chemistry publication-title: Reviews in Computational Chemistry doi: 10.1002/9780470116449.ch6 – volume: 13 start-page: 41 year: 2021 ident: pone.0282924.ref091 article-title: Benchmarks for interpretation of QSAR models publication-title: J Cheminform doi: 10.1186/s13321-021-00519-x – volume: 28 start-page: 31 issue: 1 year: 1988 ident: pone.0282924.ref019 article-title: a chemical language and information system. 1. Introduction to methodology and encoding rules publication-title: J Chem Inf Comput Sci doi: 10.1021/ci00057a005 – volume: 55 start-page: 263 issue: 2 year: 2015 ident: pone.0282924.ref040 article-title: Deep Neural Nets as a Method for Quantitative Structure−Activity Relationships publication-title: J Chem Inf Model doi: 10.1021/ci500747n – volume: 36 start-page: 27 year: 2013 ident: pone.0282924.ref054 article-title: Collinearity: a review of methods to deal with it and a simulation study evaluating their performance publication-title: Ecography doi: 10.1111/j.1600-0587.2012.07348.x – volume: 16 start-page: 171 year: 2005 ident: pone.0282924.ref049 article-title: The impact of variable selection on the modelling of oestrogenicity publication-title: SAR QSAR Environ Res doi: 10.1080/10629360412331319808 – volume: 15 start-page: 1929 issue: 1 year: 2014 ident: pone.0282924.ref094 article-title: Dropout: a simple way to prevent neural networks from overfitting publication-title: J Mach Learn Res – volume: 10 start-page: e1475 year: 2020 ident: pone.0282924.ref005 article-title: In silico toxicology: From structure–activity relationships towards deep learning and adverse outcome pathways publication-title: Wiley Interdiscip Rev Comput. Mol Sci doi: 10.1002/wcms.1475 – volume: 190 start-page: 110179 year: 2020 ident: pone.0282924.ref079 article-title: Development of pp-LFER and QSPR models for predicting the diffusion coefficients of hydrophobic organic compounds in LDPE publication-title: Ecotoxicol Environ Saf doi: 10.1016/j.ecoenv.2020.110179 – year: 2018 ident: pone.0282924.ref030 article-title: Deep Learning using Rectified Linear Units (ReLU) publication-title: arXiv:1803.08375 – volume: 34 start-page: 541 issue: 2 year: 2021 ident: pone.0282924.ref068 article-title: Trade-off Predictivity and Explainability for Machine-Learning Powered Predictive Toxicology: An in-Depth Investigation with Tox21 Data Sets publication-title: Chem Res Toxicol doi: 10.1021/acs.chemrestox.0c00373 – volume: 23 start-page: 6 issue: 1 year: 1982 ident: pone.0282924.ref003 article-title: Multivariate Quantitative Structure-Activity Relationships (QSAR): Conditions for Their Applicability publication-title: J Chem Inf Comput Sci doi: 10.1021/ci00037a002 – volume: 30 start-page: 593 issue: 6–7 year: 2011 ident: pone.0282924.ref070 article-title: Interpretation of QSAR Models Based on Random Forest Methods publication-title: Mol Inform doi: 10.1002/minf.201000173 – ident: pone.0282924.ref013 – volume: 13 issue: 586 year: 2021 ident: pone.0282924.ref089 article-title: Reproducibility in Machine Learning for Health publication-title: Sci Transl Med – volume: 8 start-page: 7129 year: 2018 ident: pone.0282924.ref090 article-title: Model-based and Model-free Machine Learning Techniques for Diagnostic Prediction and Classification of Clinical Outcomes in Parkinson’s Disease publication-title: Sci Rep doi: 10.1038/s41598-018-24783-4 – start-page: 152 year: 2020 ident: pone.0282924.ref063 article-title: Generalization of Machine Learning Approaches to Identify Notifiable Conditions from a Statewide Health Information Exchange publication-title: AMIA Jt Summits Transl Sci Proc – volume: 18 start-page: 1132 year: 2021 ident: pone.0282924.ref088 article-title: Reproducibility standards for machine learning in the life sciences publication-title: Nat Methods doi: 10.1038/s41592-021-01256-7 – year: 2016 ident: pone.0282924.ref026 article-title: XGBoost: A Scalable Tree Boosting System publication-title: arXiv:1603.02754 – volume: 44 start-page: 1 year: 2004 ident: pone.0282924.ref061 article-title: 2004. The Problem of Overfitting publication-title: J Chem Inf Comput Sci – volume: 37 start-page: 1600118 year: 2017 ident: pone.0282924.ref041 article-title: Performance of Deep and Shallow Neural Networks, the Universal Approximation Theorem, Activity Cliffs, and QSAR publication-title: Mol Inform doi: 10.1002/minf.201600118 – volume: 202 start-page: 117230 year: 2022 ident: pone.0282924.ref053 article-title: When stakes are high: Balancing accuracy and transparency with Model-Agnostic Interpretable Data-driven suRRogates publication-title: Expert Syst Appl doi: 10.1016/j.eswa.2022.117230 – volume: 109 start-page: 146 issue: 2 year: 2011 ident: pone.0282924.ref051 article-title: Comparative QSARs for antimalarial endochins: Importance of descriptor-thinning and noise reduction prior to feature selection publication-title: Chemom Intell Lab Syst doi: 10.1016/j.chemolab.2011.08.007 – volume: 56 start-page: 2353 year: 2016 ident: pone.0282924.ref033 article-title: Extreme Gradient Boosting as a Method for Quantitative Structure-Activity Relationships publication-title: J Chem Inf Model doi: 10.1021/acs.jcim.6b00591 – volume: 123 start-page: 104956 year: 2021 ident: pone.0282924.ref012 article-title: Determination of “fitness-for-purpose” of quantitative structure-activity relationship (QSAR) models to predict (eco-) toxicological endpoints for regulatory use publication-title: Regul Toxicol Pharmacol doi: 10.1016/j.yrtph.2021.104956 – volume: 9 start-page: 144352 year: 2021 ident: pone.0282924.ref077 article-title: Shapley Values for Feature Selection: The Good, the Bad, and the Axioms publication-title: IEEE Access doi: 10.1109/ACCESS.2021.3119110 – volume: 12 start-page: 2825 year: 2011 ident: pone.0282924.ref025 article-title: Scikit-learn: Machine Learning in Python publication-title: J Mach Learn Res – volume: 32 issue: 1 year: 2018 ident: pone.0282924.ref015 article-title: State of the Art: Reproducibility in Artificial Intelligence publication-title: Proceedings of the AAAI Conference on Artificial Intelligence doi: 10.1609/aaai.v32i1.11503 – volume: 12 start-page: 9 year: 2020 ident: pone.0282924.ref083 article-title: Towards reproducible computational drug discovery publication-title: J Cheminform doi: 10.1186/s13321-020-0408-x – volume: 2 start-page: 56 year: 2020 ident: pone.0282924.ref048 article-title: From local explanations to global understanding with explainable AI for trees publication-title: Nat Mach Intell doi: 10.1038/s42256-019-0138-9 – year: 2015 ident: pone.0282924.ref028 article-title: TensorFlow: Large-scale machine learning on heterogeneous systems publication-title: arXiv:1603.04467v2 – volume: 187 start-page: 95 year: 2015 ident: pone.0282924.ref064 article-title: Cross-validation for selecting a model selection procedure publication-title: J Econom doi: 10.1016/j.jeconom.2015.02.006 – start-page: 151 volume-title: Ecotoxicological QSARs, Methods in Pharmacology and Toxicology year: 2020 ident: pone.0282924.ref007 – volume: 13 start-page: 1075 year: 2018 ident: pone.0282924.ref092 article-title: Current approaches for choosing feature selection and learning algorithms in quantitative structure-activity relationships (QSAR) publication-title: Expert Opin Drug Discov doi: 10.1080/17460441.2018.1542428 – volume: 62 start-page: 5317 issue: 22 year: 2022 ident: pone.0282924.ref009 article-title: The (Re)-Evolution of Quantitative Structure–Activity Relationship (QSAR) Studies Propelled by the Surge of Machine Learning Methods publication-title: J Chem Inf Model doi: 10.1021/acs.jcim.2c01422 – volume-title: Neural Networks Algorithms, Applications, and Programming Techniques year: 1991 ident: pone.0282924.ref038 – volume: 41 start-page: 111 year: 2013 ident: pone.0282924.ref081 article-title: Uncertainty in QSAR predictions publication-title: Altern Lab Anim doi: 10.1177/026119291304100111 – volume: 106 start-page: 90 year: 2019 ident: pone.0282924.ref018 article-title: Identification and description of the uncertainty, variability, bias and influence in quantitative structure-activity relationships (QSARs) for toxicity prediction publication-title: Regul Toxicol Pharmacol doi: 10.1016/j.yrtph.2019.04.007 – volume: 8 start-page: 832 issue: 8 year: 2019 ident: pone.0282924.ref069 article-title: Machine Learning Interpretability: A Survey on Methods and Metrics publication-title: Electronics doi: 10.3390/electronics8080832 – volume: 13 start-page: 281 year: 2012 ident: pone.0282924.ref044 article-title: Random Search for Hyper-Parameter Optimization publication-title: J Mach Learn Res – year: 2018 ident: pone.0282924.ref087 article-title: Building a Reproducible Machine Learning Pipeline publication-title: arXiv:1810.04570 – volume: 2 start-page: 405 issue: 4 year: 2006 ident: pone.0282924.ref057 article-title: The role of hydrophobicity in toxicity prediction publication-title: Curr Comput Aided Drug Des doi: 10.2174/157340906778992346 – year: 2019 ident: pone.0282924.ref093 article-title: The Theory Behind Overfitting, Cross Validation, Regularization, Bagging, and Boosting: Tutorial publication-title: arXiv:1905.12787 – volume: 225 start-page: 292 year: 2019 ident: pone.0282924.ref065 article-title: Prediction of compressive strength and Portland cement composition using cross-validation and feature ranking techniques publication-title: Constr Build Mater doi: 10.1016/j.conbuildmat.2019.07.224 – volume: 7 start-page: 221 issue: 4 year: 2019 ident: pone.0282924.ref037 article-title: Effects of Distance Measure Choice on K-Nearest Neighbor Classifier Performance: A Review publication-title: Big Data doi: 10.1089/big.2018.0175 – volume: 3 issue: 2 year: 2016 ident: pone.0282924.ref052 article-title: A mechanistic interpretation, if possible’: How does predictive modelling causality affect the regulation of chemicals? publication-title: Big Data Soc doi: 10.1177/2053951716670189 – year: 2015 ident: pone.0282924.ref027 – volume: 20 start-page: 273 year: 1995 ident: pone.0282924.ref034 article-title: Support-vector networks publication-title: Mach Learn doi: 10.1007/BF00994018 – volume: 52 start-page: 1413 issue: 6 year: 2012 ident: pone.0282924.ref008 article-title: Machine Learning Methods for Property Prediction in Chemoinformatics: Quo Vadis? publication-title: J Chem Inf Model doi: 10.1021/ci200409x – volume: 57 start-page: 4977 issue: 12 year: 2014 ident: pone.0282924.ref002 article-title: QSAR Modeling: Where Have You Been? Where Are You Going To? publication-title: J Med Chem doi: 10.1021/jm4004285 – volume: 188 start-page: 34 year: 2022 ident: pone.0282924.ref060 article-title: Evaluation of Variability Across Rat Acute Oral Systemic Toxicity Studies publication-title: Toxicol Sci doi: 10.1093/toxsci/kfac042 – volume: 22 start-page: 1 year: 2021 ident: pone.0282924.ref082 article-title: Improving Reproducibility in Machine Learning Research (A Report from the NeurIPS 2019 Reproducibility Program) publication-title: J Mach Learn Res – volume: 26 start-page: 1340 issue: 10 year: 2010 ident: pone.0282924.ref046 article-title: Permutation importance: a corrected feature importance measure publication-title: Bioinformatics doi: 10.1093/bioinformatics/btq134 – volume: 22 start-page: 857 year: 2008 ident: pone.0282924.ref067 article-title: On the interpretation and interpretability of quantitative structure-activity relationship models publication-title: J Comput Aided Mol Des doi: 10.1007/s10822-008-9240-5 – volume: 45 start-page: 5 year: 2001 ident: pone.0282924.ref031 article-title: Random Forests publication-title: Mach Learn doi: 10.1023/A:1010933404324 – year: 2014 ident: pone.0282924.ref029 article-title: Adam: A Method for Stochastic Optimization publication-title: arXiv:1412.6980 – volume: 79 start-page: 72 issue: 1 year: 2010 ident: pone.0282924.ref056 article-title: Toxicity of organic chemicals to Tetrahymena pyriformis: Effect of polarity and ionization on toxicity publication-title: Chemosphere doi: 10.1016/j.chemosphere.2009.12.055 – volume: 200 start-page: 65 year: 2022 ident: pone.0282924.ref014 article-title: Conceptual challenges for interpretable machine learning publication-title: Synthese doi: 10.1007/s11229-022-03485-5 – volume: 32 start-page: 1466 year: 2011 ident: pone.0282924.ref024 article-title: PaDEL-descriptor: An open source software to calculate molecular descriptors and fingerprints publication-title: J Comput Chem doi: 10.1002/jcc.21707 – year: 2021 ident: pone.0282924.ref078 article-title: Rational Shapley Values publication-title: arXiv:2106.10191v2 – volume: 48 start-page: 146 issue: 4 year: 2020 ident: pone.0282924.ref001 article-title: A Review of In Silico Tools as Alternatives to Animal Testing: Prinicples, Resources and Applications publication-title: Altern Lab Anim doi: 10.1177/0261192920965977 – volume: 189 start-page: 7 issue: 1 year: 2022 ident: pone.0282924.ref017 article-title: Machine Learning and Artificial Intelligence in Toxicological Sciences publication-title: Toxicol Sci doi: 10.1093/toxsci/kfac075 – year: 2022 ident: pone.0282924.ref066 article-title: Interpretable Machine Learning for Self-Service High-Risk Decision-Making publication-title: arXiv:2205.04032 – volume: 55 start-page: 1897 issue: 3 year: 2021 ident: pone.0282924.ref080 article-title: Development of an Enhanced Mechanistically Driven Mode of Action Classification Scheme for Adverse Effects on Environmental Species publication-title: Environ Sci Technol doi: 10.1021/acs.est.0c06551 |
| SSID | ssj0053866 |
| Score | 2.530932 |
| Snippet | Recent years have seen a substantial growth in the adoption of machine learning approaches for the purposes of quantitative structure-activity relationship... |
| SourceID | plos pubmedcentral proquest gale pubmed crossref |
| SourceType | Open Website Open Access Repository Aggregation Database Index Database Enrichment Source |
| StartPage | e0282924 |
| SubjectTerms | Algorithms Analysis Animals Best practice Biocompatibility Biology and Life Sciences Computer and Information Sciences Datasets Decision trees Learning algorithms Machine Learning Medicine and Health Sciences Mitigation Neural networks Optimization Pattern recognition Physical Sciences Principles Quantitative Structure-Activity Relationship Regression analysis Reproducibility of Results Research and Analysis Methods Software Statistical analysis Statistical methods Structure-activity relationships Toxicity Toxicological interactions Toxicology Uncertainty |
| SummonAdditionalLinks | – databaseName: Public Library of Science (PLoS) Journals Open Access dbid: FPL link: http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV3fb9MwELag8MALMH5shQEGIcEeMuoktZ3HClFAmsbYAO0tchy7izSS0jSI_4R_lzvHyZZpE_Dsz61zubucdXffEfIyEgmmM20wkUYEsZE6yIQSQZLFOdLXGaYdZf6e2N-Xx8fJwdlF8UIGPxLsjZfp7rIqza5L_IXxdXIjjDjHy9b8YK_zvGC7nPv2uKt2Dj4_3gmPlqdVfVmEebFQ8tyXZ37nf898l9z2MSadtUqxQa6Z8h7Z8FZc09eeanrnPvn9vilyfO8UYle6qKqcdm1TtCgpBIf0XIabVpZ-d8WXhvppEwuE5WeFRwhZV78K3flU-qNRpWtkA7dKW7baZmUC_BMcW0FXXTXeSbGEs30-mh3WOw_I1_m7L28_BH5UQ6B5KNaBkVHG-VQpySy3WoqEMyuZUXKaKyujWEmbKwhnEp7xRCUxsxMFPh9sPmehVdFDMipBWFuE5lyYDKdoySlcHYVUodXoRaI8lnFs2ZhE3RtMtecxx3Eap6lLzgm4z7RiTlH6qZf-mAT9rmXL4_EX_DNUjrTtRu3dQDoTeMNL-DQckxcOgSQaJVbpLFRT1-nHT9_-AXR0OAC98iBbwZNo5Tsj4DhIzjVAbg-Q4Ar0YHkLVbl7oDoNJUO-u1BK2Nmp9-XLz_tl_FGsvCtN1TgMRMlIIzkmm6019AIE4UG8OgFhyYGd9ADkLh-ulMWJ4zBnjqdpkjy6-siPya0QIsrAUeVukxFoqHlCbuqf66JePXWW_we4cFwh priority: 102 providerName: Public Library of Science |
| Title | Guidance for good practice in the application of machine learning in development of toxicological quantitative structure-activity relationships (QSARs) |
| URI | https://www.ncbi.nlm.nih.gov/pubmed/37163504 https://www.proquest.com/docview/2811921288 https://www.proquest.com/docview/2812507440 https://pubmed.ncbi.nlm.nih.gov/PMC10171609 http://dx.doi.org/10.1371/journal.pone.0282924 |
| Volume | 18 |
| WOSCitedRecordID | wos001022290100001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| hasFullText | 1 |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| journalDatabaseRights | – providerCode: PRVAON databaseName: DOAJ Directory of Open Access Journals customDbUrl: eissn: 1932-6203 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0053866 issn: 1932-6203 databaseCode: DOA dateStart: 20060101 isFulltext: true titleUrlDefault: https://www.doaj.org/ providerName: Directory of Open Access Journals – providerCode: PRVHPJ databaseName: ROAD: Directory of Open Access Scholarly Resources customDbUrl: eissn: 1932-6203 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0053866 issn: 1932-6203 databaseCode: M~E dateStart: 20060101 isFulltext: true titleUrlDefault: https://road.issn.org providerName: ISSN International Centre – providerCode: PRVPQU databaseName: Advanced Technologies & Aerospace Database customDbUrl: eissn: 1932-6203 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0053866 issn: 1932-6203 databaseCode: P5Z dateStart: 20061201 isFulltext: true titleUrlDefault: https://search.proquest.com/hightechjournals providerName: ProQuest – providerCode: PRVPQU databaseName: Agricultural Science Database customDbUrl: eissn: 1932-6203 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0053866 issn: 1932-6203 databaseCode: M0K dateStart: 20061201 isFulltext: true titleUrlDefault: https://search.proquest.com/agriculturejournals providerName: ProQuest – providerCode: PRVPQU databaseName: Biological Science Database customDbUrl: eissn: 1932-6203 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0053866 issn: 1932-6203 databaseCode: M7P dateStart: 20061201 isFulltext: true titleUrlDefault: http://search.proquest.com/biologicalscijournals providerName: ProQuest – providerCode: PRVPQU databaseName: Engineering Database customDbUrl: eissn: 1932-6203 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0053866 issn: 1932-6203 databaseCode: M7S dateStart: 20061201 isFulltext: true titleUrlDefault: http://search.proquest.com providerName: ProQuest – providerCode: PRVPQU databaseName: Environmental Science Database customDbUrl: eissn: 1932-6203 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0053866 issn: 1932-6203 databaseCode: PATMY dateStart: 20061201 isFulltext: true titleUrlDefault: http://search.proquest.com/environmentalscience providerName: ProQuest – providerCode: PRVPQU databaseName: Health & Medical Collection customDbUrl: eissn: 1932-6203 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0053866 issn: 1932-6203 databaseCode: 7X7 dateStart: 20061201 isFulltext: true titleUrlDefault: https://search.proquest.com/healthcomplete providerName: ProQuest – providerCode: PRVPQU databaseName: Materials Science Database customDbUrl: eissn: 1932-6203 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0053866 issn: 1932-6203 databaseCode: KB. dateStart: 20061201 isFulltext: true titleUrlDefault: http://search.proquest.com/materialsscijournals providerName: ProQuest – providerCode: PRVPQU databaseName: Nursing & Allied Health Database customDbUrl: eissn: 1932-6203 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0053866 issn: 1932-6203 databaseCode: 7RV dateStart: 20061201 isFulltext: true titleUrlDefault: https://search.proquest.com/nahs providerName: ProQuest – providerCode: PRVPQU databaseName: ProQuest Central Database Suite (ProQuest) customDbUrl: eissn: 1932-6203 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0053866 issn: 1932-6203 databaseCode: BENPR dateStart: 20061201 isFulltext: true titleUrlDefault: https://www.proquest.com/central providerName: ProQuest – providerCode: PRVPQU databaseName: Public Health Database customDbUrl: eissn: 1932-6203 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0053866 issn: 1932-6203 databaseCode: 8C1 dateStart: 20061201 isFulltext: true titleUrlDefault: https://search.proquest.com/publichealth providerName: ProQuest – providerCode: PRVPQU databaseName: Publicly Available Content Database customDbUrl: eissn: 1932-6203 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0053866 issn: 1932-6203 databaseCode: PIMPY dateStart: 20061201 isFulltext: true titleUrlDefault: http://search.proquest.com/publiccontent providerName: ProQuest – providerCode: PRVATS databaseName: Public Library of Science (PLoS) Journals Open Access customDbUrl: eissn: 1932-6203 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0053866 issn: 1932-6203 databaseCode: FPL dateStart: 20060101 isFulltext: true titleUrlDefault: http://www.plos.org/publications/ providerName: Public Library of Science |
| link | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV3fb9MwELag44EXYPxaYRSDkGAP6eokjZ0n1E0rTNtKaGEqvERuYneVRtI1LeI_4d_lznG6BU2AxMu9-HMb2-fz2T5_R8grj4d4namdjlDc8ZVInAmX3Aknfor0dYolhjL_mA8GYjwOI3vgVtiwysomGkOd5gmeke-6giF1lyvE2_mFg1mj8HbVptC4STYY-sagz3x4WllimMtBYJ_LeZzt2tFpz_NMtc0VouvXliNrlBvz87y4zuP8PXDyykrUv_u_bbhH7lgflPZKpdkkN1R2n2zaWV7QN5aKeucB-fluNUtRLyj4tnSa5ymtnlXRWUbBeaRXbsBpruk3E5ypqM1GMUVYehmYhJBl_mOWVDaXXqxkZh66gdmlJZvtaqEc_BNMa0EXVbTe2WwO3_Zx1BsWOw_J5_7Bp_33jk3l4CSBy5eOEt4kCLpSCqYDnQgeBkwLpqToplILz5dCpxLcnTCYBKEMfaY7EtYEsAkpc7X0HpFGBsO2RWgacDXBLFuiC1tLLqSrE7QyXuoL39esSbxqROPE8pxjuo3z2FzecdjvlN0cox7EVg-axFnXmpc8H3_BP0dlicvXqmszEfc47gDDoOs2yUuDQJKNDKN4pnJVFPHhh9N_AI2GNdBrC9I5tCSR9uUEfA6Sd9WQ2zUkmIqkVryFql01qIgvFRJqVip7ffGLdTH-KEbmZSpfGQx40Ugz2SSPy9mx7kDoPPBnO9BZojZv1gDkNq-XZLMzw3HODI9TJ3zy5-96Sm674HU6hk53mzRAS9Uzciv5vpwVi5axBijH3EgBUuyzFtnYOxhEw5Y5gAHZj45BHu21QZ50jlDyyMgRyKj7FWpEhyfRl1-6CHp- |
| linkProvider | ProQuest |
| linkToHtml | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMw1V1Lb9NAEF6VgAQXoLwaKHRBINrDtn7Fuz4gFAGlUUMobUEVF7Oxd1NLxU7jhMcv4V_wG5lZr9MaVcClB8772bEn81rvzDeEPPZ5hMeZmjlCcRYokbAhl5xFwyBF-jrlJoYyv88HA3FwEO0skJ91LwyWVdY-0TjqtEjwG_mGJ1yk7vKEeD4-Zjg1Ck9X6xEalVpsq-9fYctWPuu9hP_3iedtvtp_scXsVAGWhB6fMiX8YRh2pBSuDnUieBS6WrhKik4qtfADKXQqIfJG4TCMZBS42pHgnkA9U9fT0of7XiAXg8Bz0Ip2Oh9rzw--Iwxte57P3Q2rDevjIlfr5sjSCxrhzwaB1vioKM_KcH8v1DwV-Tav_W8yu06u2hybdiujWCQLKr9BFq0XK-mqpdpeu0l-vJ5lKeo9hdydjooipXXbGM1yCskxPXXCTwtNP5viU0XttI0RwtKTwiuETItvWVLHFHo8k7lp5IOwQiu23tlEMfwRHNtBJ3U14mE2hmd7t9fdLddukffnIqDbpJWDmiwRmoZcDXGKmOjA1pkL6ekEvaifBiIItNsmfq1BcWJ53HGcyFFsDic57OcqMceod7HVuzZh86vGFY_JX_ArqJxx1Y07d4Nxl-MONwo7Xps8MggkEcmxSmkkZ2UZ995--AfQ3m4D9NSCdAFvkkjbGQKPg-RkDeRyAwmuMGksL6Ep1S9UxicGAFfWJnL28sP5Mt4UKw9zVcwMBnYJSKPZJncqa5wLEIQH-boDwhINO50DkLu9uZJnh4bD3TU8VU5098_PtUIub-2_6cf93mD7HrniQYbNDHXwMmmBxqr75FLyZZqVkwfGE1Hy6bzN-Bfse8xT |
| linkToPdf | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMw1V1Lb9NAEF6VgBAXoLwaKHRBIOjBbfyId31AKKIEolYhtAVVXMx6vZtaKnYaJzx-Cf-FX8fMep3WqAIuPXDesb0ez9M78w0hj30W4XGmdjpcMSdQXDoJE8yJkiBF-DrlSgOZv8OGQ35wEI2WyM-6FwbLKmubaAx1Wkj8R77pcRehuzxI2LQtixht9V9Mjh2cIIUnrfU4jUpEttX3r5C-lc8HW_Ctn3he_9X-yzeOnTDgyNBjM0dxPwnDrhDc1aGWnEWhq7mrBO-mQnM_EFynArxwFCZhJKLA1R0BpgpENXU9LXy47wVykUGOieWEo-7H2guAHQlD26rnM3fTSsbGpMjVhjm-9IKGK7QOoTU5Ksqzot3fizZPecH-tf-Zf9fJVRt7016lLMtkSeU3yLK1biV9ZiG412-SH6_nWYr6QCGmp-OiSGndTkaznELQTE-d_NNC08-mKFVRO4VjjGTpSUEWksyKb5msfQ09novcNPiBu6EViu98qhx8CI7zoNO6SvEwm8De3u31dsv1W-T9uTDoNmnlIDIrhKYhUwlOF-NdSKkZF56WaF39NOBBoN028WtpiqXFd8cxI0exObRkkOdVbI5RBmMrg23iLK6aVPgmf6FfQ0GNqy7dhXmMewwz3yjsem3yyFAguEiOYjYW87KMB28__APR3m6D6Kkl0gW8iRS2YwS2g6BlDcrVBiWYSNlYXkG1ql-ojE-UAa6s1eXs5YeLZbwpViTmqpgbGsgeEF6zTe5UmrlgIDAP4vgOMIs3dHZBgJjuzZU8OzTY7q7Br-pEd_-8rzVyGbQ33hkMt--RKx4E3o5BFF4lLRBYdZ9ckl9mWTl9YIwSJZ_OW4t_Ae_u1R0 |
| 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=Guidance+for+good+practice+in+the+application+of+machine+learning+in+development+of+toxicological+quantitative+structure-activity+relationships+%28QSARs%29&rft.jtitle=PloS+one&rft.au=Belfield%2C+Samuel+J&rft.au=Cronin%2C+Mark+T+D&rft.au=Enoch%2C+Steven+J&rft.au=Firman%2C+James+W&rft.date=2023-05-10&rft.eissn=1932-6203&rft.volume=18&rft.issue=5&rft.spage=e0282924&rft_id=info:doi/10.1371%2Fjournal.pone.0282924&rft_id=info%3Apmid%2F37163504&rft.externalDocID=37163504 |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1932-6203&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1932-6203&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1932-6203&client=summon |