Modeling Aqueous Solubility

This paper describes the development of an aqueous solubility model based on solubility data from the Syracuse database, calculated octanol−water partition coefficient, and 51 2D molecular descriptors. Two different statistical packages, SIMCA and Cubist, were used and the results were compared. The...

Full description

Saved in:
Bibliographic Details
Published in:Journal of Chemical Information and Computer Sciences 2003-05, Vol.43 (3), p.837-841
Main Authors: Butina, Darko, Gola, Joelle M. R
Format: Article
Language:English
Subjects:
Models, Chemical
Organic Chemicals - chemistry
Quantitative Structure-Activity Relationship
Solubility
Water - chemistry
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
cited_by cdi_FETCH-LOGICAL-a349t-69685124048d1a5bf3396be932ddb0bacdc1ad842b2c988dc0693562ed8e09263
cites cdi_FETCH-LOGICAL-a349t-69685124048d1a5bf3396be932ddb0bacdc1ad842b2c988dc0693562ed8e09263
container_end_page 841
container_issue 3
container_start_page 837
container_title Journal of Chemical Information and Computer Sciences
container_volume 43
creator Butina, Darko
Gola, Joelle M. R
description This paper describes the development of an aqueous solubility model based on solubility data from the Syracuse database, calculated octanol−water partition coefficient, and 51 2D molecular descriptors. Two different statistical packages, SIMCA and Cubist, were used and the results were compared. The Cubist model, which comprises a collection of rules, each of which has an associated Multiple Linear Regression model (MLR), gave better overall results on a test set of 640 compounds with an overall squared correlation coefficient of 0.74 and an absolute average error of 0.68 log units. Both training and independent test sets had similar distributions of structures in terms of the different functionalities present60% neutral, 14% acidic, 8% phenolic, 11% monobasic, 4% polybasic, and 3% zwitterionic molecules. Sets were designed by random selection, with 2688 (81%) and 640 (19%) molecules, respectively, forming the training and the test sets.
doi_str_mv 10.1021/ci020279y
format article
fullrecord <record><control><sourceid>proquest_cross</sourceid><recordid>TN_cdi_proquest_miscellaneous_73322675</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>73322675</sourcerecordid><originalsourceid>FETCH-LOGICAL-a349t-69685124048d1a5bf3396be932ddb0bacdc1ad842b2c988dc0693562ed8e09263</originalsourceid><addsrcrecordid>eNpt0M9LwzAUB_AgipvTg2dBdlHwUH15adLkOOZvJiqb4C2kSSad3bo1Lbj_3o6OefH0Du_D-_El5JTCNQWkNzYDBEzUeo90KY9VpAR87pMugOIRMiY75CiEGQBjSuAh6VBMREJj2iVnL4Xzebb46g9WtS_q0B8XeZ1meVatj8nB1OTBn2xrj3zc302Gj9Ho9eFpOBhFhsWqioQSklOMIZaOGp5ON1tSrxg6l0JqrLPUOBljilZJ6SwIxbhA76QHhYL1yGU7d1kWzRGh0vMsWJ_nZrG5SCeMIYqEN_CqhbYsQij9VC_LbG7KtaagN0noXRKNPd8OrdO5d39y-3oDohZkofI_u74pv7VIWML15G2s2e3w_RkmIz1u_EXrjQ16VtTlosnkn8W_PgRyDQ</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>73322675</pqid></control><display><type>article</type><title>Modeling Aqueous Solubility</title><source>American Chemical Society:Jisc Collections:American Chemical Society Read &amp; Publish Agreement 2022-2024 (Reading list)</source><creator>Butina, Darko ; Gola, Joelle M. R</creator><creatorcontrib>Butina, Darko ; Gola, Joelle M. R</creatorcontrib><description>This paper describes the development of an aqueous solubility model based on solubility data from the Syracuse database, calculated octanol−water partition coefficient, and 51 2D molecular descriptors. Two different statistical packages, SIMCA and Cubist, were used and the results were compared. The Cubist model, which comprises a collection of rules, each of which has an associated Multiple Linear Regression model (MLR), gave better overall results on a test set of 640 compounds with an overall squared correlation coefficient of 0.74 and an absolute average error of 0.68 log units. Both training and independent test sets had similar distributions of structures in terms of the different functionalities present60% neutral, 14% acidic, 8% phenolic, 11% monobasic, 4% polybasic, and 3% zwitterionic molecules. Sets were designed by random selection, with 2688 (81%) and 640 (19%) molecules, respectively, forming the training and the test sets.</description><identifier>ISSN: 0095-2338</identifier><identifier>EISSN: 1549-960X</identifier><identifier>DOI: 10.1021/ci020279y</identifier><identifier>PMID: 12767141</identifier><language>eng</language><publisher>United States: American Chemical Society</publisher><subject>Models, Chemical ; Organic Chemicals - chemistry ; Quantitative Structure-Activity Relationship ; Solubility ; Water - chemistry</subject><ispartof>Journal of Chemical Information and Computer Sciences, 2003-05, Vol.43 (3), p.837-841</ispartof><rights>Copyright © 2003 American Chemical Society</rights><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-a349t-69685124048d1a5bf3396be932ddb0bacdc1ad842b2c988dc0693562ed8e09263</citedby><cites>FETCH-LOGICAL-a349t-69685124048d1a5bf3396be932ddb0bacdc1ad842b2c988dc0693562ed8e09263</cites></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>314,780,784,27924,27925</link.rule.ids><backlink>$$Uhttps://www.ncbi.nlm.nih.gov/pubmed/12767141$$D View this record in MEDLINE/PubMed$$Hfree_for_read</backlink></links><search><creatorcontrib>Butina, Darko</creatorcontrib><creatorcontrib>Gola, Joelle M. R</creatorcontrib><title>Modeling Aqueous Solubility</title><title>Journal of Chemical Information and Computer Sciences</title><addtitle>J. Chem. Inf. Comput. Sci</addtitle><description>This paper describes the development of an aqueous solubility model based on solubility data from the Syracuse database, calculated octanol−water partition coefficient, and 51 2D molecular descriptors. Two different statistical packages, SIMCA and Cubist, were used and the results were compared. The Cubist model, which comprises a collection of rules, each of which has an associated Multiple Linear Regression model (MLR), gave better overall results on a test set of 640 compounds with an overall squared correlation coefficient of 0.74 and an absolute average error of 0.68 log units. Both training and independent test sets had similar distributions of structures in terms of the different functionalities present60% neutral, 14% acidic, 8% phenolic, 11% monobasic, 4% polybasic, and 3% zwitterionic molecules. Sets were designed by random selection, with 2688 (81%) and 640 (19%) molecules, respectively, forming the training and the test sets.</description><subject>Models, Chemical</subject><subject>Organic Chemicals - chemistry</subject><subject>Quantitative Structure-Activity Relationship</subject><subject>Solubility</subject><subject>Water - chemistry</subject><issn>0095-2338</issn><issn>1549-960X</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2003</creationdate><recordtype>article</recordtype><recordid>eNpt0M9LwzAUB_AgipvTg2dBdlHwUH15adLkOOZvJiqb4C2kSSad3bo1Lbj_3o6OefH0Du_D-_El5JTCNQWkNzYDBEzUeo90KY9VpAR87pMugOIRMiY75CiEGQBjSuAh6VBMREJj2iVnL4Xzebb46g9WtS_q0B8XeZ1meVatj8nB1OTBn2xrj3zc302Gj9Ho9eFpOBhFhsWqioQSklOMIZaOGp5ON1tSrxg6l0JqrLPUOBljilZJ6SwIxbhA76QHhYL1yGU7d1kWzRGh0vMsWJ_nZrG5SCeMIYqEN_CqhbYsQij9VC_LbG7KtaagN0noXRKNPd8OrdO5d39y-3oDohZkofI_u74pv7VIWML15G2s2e3w_RkmIz1u_EXrjQ16VtTlosnkn8W_PgRyDQ</recordid><startdate>20030501</startdate><enddate>20030501</enddate><creator>Butina, Darko</creator><creator>Gola, Joelle M. R</creator><general>American Chemical Society</general><scope>BSCLL</scope><scope>CGR</scope><scope>CUY</scope><scope>CVF</scope><scope>ECM</scope><scope>EIF</scope><scope>NPM</scope><scope>AAYXX</scope><scope>CITATION</scope><scope>7X8</scope></search><sort><creationdate>20030501</creationdate><title>Modeling Aqueous Solubility</title><author>Butina, Darko ; Gola, Joelle M. R</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-a349t-69685124048d1a5bf3396be932ddb0bacdc1ad842b2c988dc0693562ed8e09263</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2003</creationdate><topic>Models, Chemical</topic><topic>Organic Chemicals - chemistry</topic><topic>Quantitative Structure-Activity Relationship</topic><topic>Solubility</topic><topic>Water - chemistry</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Butina, Darko</creatorcontrib><creatorcontrib>Gola, Joelle M. R</creatorcontrib><collection>Istex</collection><collection>Medline</collection><collection>MEDLINE</collection><collection>MEDLINE (Ovid)</collection><collection>MEDLINE</collection><collection>MEDLINE</collection><collection>PubMed</collection><collection>CrossRef</collection><collection>MEDLINE - Academic</collection><jtitle>Journal of Chemical Information and Computer Sciences</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Butina, Darko</au><au>Gola, Joelle M. R</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Modeling Aqueous Solubility</atitle><jtitle>Journal of Chemical Information and Computer Sciences</jtitle><addtitle>J. Chem. Inf. Comput. Sci</addtitle><date>2003-05-01</date><risdate>2003</risdate><volume>43</volume><issue>3</issue><spage>837</spage><epage>841</epage><pages>837-841</pages><issn>0095-2338</issn><eissn>1549-960X</eissn><abstract>This paper describes the development of an aqueous solubility model based on solubility data from the Syracuse database, calculated octanol−water partition coefficient, and 51 2D molecular descriptors. Two different statistical packages, SIMCA and Cubist, were used and the results were compared. The Cubist model, which comprises a collection of rules, each of which has an associated Multiple Linear Regression model (MLR), gave better overall results on a test set of 640 compounds with an overall squared correlation coefficient of 0.74 and an absolute average error of 0.68 log units. Both training and independent test sets had similar distributions of structures in terms of the different functionalities present60% neutral, 14% acidic, 8% phenolic, 11% monobasic, 4% polybasic, and 3% zwitterionic molecules. Sets were designed by random selection, with 2688 (81%) and 640 (19%) molecules, respectively, forming the training and the test sets.</abstract><cop>United States</cop><pub>American Chemical Society</pub><pmid>12767141</pmid><doi>10.1021/ci020279y</doi><tpages>5</tpages></addata></record>
fulltext fulltext
identifier ISSN: 0095-2338
ispartof Journal of Chemical Information and Computer Sciences, 2003-05, Vol.43 (3), p.837-841
issn 0095-2338
1549-960X
language eng
recordid cdi_proquest_miscellaneous_73322675
source American Chemical Society:Jisc Collections:American Chemical Society Read & Publish Agreement 2022-2024 (Reading list)
subjects Models, Chemical
Organic Chemicals - chemistry
Quantitative Structure-Activity Relationship
Solubility
Water - chemistry
title Modeling Aqueous Solubility
url http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-27T09%3A05%3A23IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_cross&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Modeling%20Aqueous%20Solubility&rft.jtitle=Journal%20of%20Chemical%20Information%20and%20Computer%20Sciences&rft.au=Butina,%20Darko&rft.date=2003-05-01&rft.volume=43&rft.issue=3&rft.spage=837&rft.epage=841&rft.pages=837-841&rft.issn=0095-2338&rft.eissn=1549-960X&rft_id=info:doi/10.1021/ci020279y&rft_dat=%3Cproquest_cross%3E73322675%3C/proquest_cross%3E%3Cgrp_id%3Ecdi_FETCH-LOGICAL-a349t-69685124048d1a5bf3396be932ddb0bacdc1ad842b2c988dc0693562ed8e09263%3C/grp_id%3E%3Coa%3E%3C/oa%3E%3Curl%3E%3C/url%3E&rft_id=info:oai/&rft_pqid=73322675&rft_id=info:pmid/12767141&rfr_iscdi=true