AutoQSAR: an automated machine learning tool for best-practice quantitative structure-activity relationship modeling

We introduce AutoQSAR, an automated machine-learning application to build, validate and deploy quantitative structure-activity relationship (QSAR) models. The process of descriptor generation, feature selection and the creation of a large number of QSAR models has been automated into a single workfl...

Full description

Saved in:
Bibliographic Details
Published in:Future medicinal chemistry 2016-10, Vol.8 (15), p.1825-1839
Main Authors: Dixon, Steven L, Duan, Jianxin, Smith, Ethan, Von Bargen, Christopher D, Sherman, Woody, Repasky, Matthew P
Format: Article
Language:English
Subjects:
binding affinity prediction
blood-brain barrier permeability
carcinogenicity
fish bioconcentration factor
mutagenicity
QSAR
solubility
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-c343t-81b9e0eb026a36c991b447f842be18c49343e14b1db227f71cc9d13af4f289513
cites cdi_FETCH-LOGICAL-c343t-81b9e0eb026a36c991b447f842be18c49343e14b1db227f71cc9d13af4f289513
container_end_page 1839
container_issue 15
container_start_page 1825
container_title Future medicinal chemistry
container_volume 8
creator Dixon, Steven L
Duan, Jianxin
Smith, Ethan
Von Bargen, Christopher D
Sherman, Woody
Repasky, Matthew P
description We introduce AutoQSAR, an automated machine-learning application to build, validate and deploy quantitative structure-activity relationship (QSAR) models. The process of descriptor generation, feature selection and the creation of a large number of QSAR models has been automated into a single workflow within AutoQSAR. The models are built using a variety of machine-learning methods, and each model is scored using a novel approach. Effectiveness of the method is demonstrated through comparison with literature QSAR models using identical datasets for six end points: protein-ligand binding affinity, solubility, blood-brain barrier permeability, carcinogenicity, mutagenicity and bioaccumulation in fish. AutoQSAR demonstrates similar or better predictive performance as compared with published results for four of the six endpoints while requiring minimal human time and expertise.
doi_str_mv 10.4155/fmc-2016-0093
format article
fullrecord <record><control><sourceid>pubmed_cross</sourceid><recordid>TN_cdi_crossref_primary_10_4155_fmc_2016_0093</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>27643715</sourcerecordid><originalsourceid>FETCH-LOGICAL-c343t-81b9e0eb026a36c991b447f842be18c49343e14b1db227f71cc9d13af4f289513</originalsourceid><addsrcrecordid>eNp1kEtLAzEQx4MottQevUq-QDTZzT7irRRfUBBf5yXJTmxkHzXJFvrtzbLam7lMhvnNH-aH0CWj15xl2Y1pNUkoywmlIj1Bc1ZkOSlFUpwe_0zM0NL7LxpfmpQiz87RLClynhYsm6OwGkL_8rZ6vcWywzI2rQxQ41bqre0ANyBdZ7tPHPq-waZ3WIEPZOekDlYD_h5kF2yQwe4B--AGHQYHZJzubThgB02c9Z3f2h1u-xqaGHaBzoxsPCx_6wJ93N-9rx_J5vnhab3aEJ3yNJCSKQEUFE1ymeZaCKY4L0zJEwWs1FxEChhXrFZJUpiCaS1qlkrDTTw0Y-kCkSlXu957B6baOdtKd6gYrUaBVRRYjQKrUWDkryZ-N6gW6iP9pysCYgLMMJ7ptYVOQzV1ccPq6Oyf8B8kCYHX</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype></control><display><type>article</type><title>AutoQSAR: an automated machine learning tool for best-practice quantitative structure-activity relationship modeling</title><source>PMC</source><creator>Dixon, Steven L ; Duan, Jianxin ; Smith, Ethan ; Von Bargen, Christopher D ; Sherman, Woody ; Repasky, Matthew P</creator><creatorcontrib>Dixon, Steven L ; Duan, Jianxin ; Smith, Ethan ; Von Bargen, Christopher D ; Sherman, Woody ; Repasky, Matthew P</creatorcontrib><description>We introduce AutoQSAR, an automated machine-learning application to build, validate and deploy quantitative structure-activity relationship (QSAR) models. The process of descriptor generation, feature selection and the creation of a large number of QSAR models has been automated into a single workflow within AutoQSAR. The models are built using a variety of machine-learning methods, and each model is scored using a novel approach. Effectiveness of the method is demonstrated through comparison with literature QSAR models using identical datasets for six end points: protein-ligand binding affinity, solubility, blood-brain barrier permeability, carcinogenicity, mutagenicity and bioaccumulation in fish. AutoQSAR demonstrates similar or better predictive performance as compared with published results for four of the six endpoints while requiring minimal human time and expertise.</description><identifier>ISSN: 1756-8919</identifier><identifier>EISSN: 1756-8927</identifier><identifier>DOI: 10.4155/fmc-2016-0093</identifier><identifier>PMID: 27643715</identifier><language>eng</language><publisher>England: Future Science Ltd</publisher><subject>binding affinity prediction ; blood-brain barrier permeability ; carcinogenicity ; fish bioconcentration factor ; mutagenicity ; QSAR ; solubility</subject><ispartof>Future medicinal chemistry, 2016-10, Vol.8 (15), p.1825-1839</ispartof><rights>Future Science Ltd</rights><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c343t-81b9e0eb026a36c991b447f842be18c49343e14b1db227f71cc9d13af4f289513</citedby><cites>FETCH-LOGICAL-c343t-81b9e0eb026a36c991b447f842be18c49343e14b1db227f71cc9d13af4f289513</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/27643715$$D View this record in MEDLINE/PubMed$$Hfree_for_read</backlink></links><search><creatorcontrib>Dixon, Steven L</creatorcontrib><creatorcontrib>Duan, Jianxin</creatorcontrib><creatorcontrib>Smith, Ethan</creatorcontrib><creatorcontrib>Von Bargen, Christopher D</creatorcontrib><creatorcontrib>Sherman, Woody</creatorcontrib><creatorcontrib>Repasky, Matthew P</creatorcontrib><title>AutoQSAR: an automated machine learning tool for best-practice quantitative structure-activity relationship modeling</title><title>Future medicinal chemistry</title><addtitle>Future Med Chem</addtitle><description>We introduce AutoQSAR, an automated machine-learning application to build, validate and deploy quantitative structure-activity relationship (QSAR) models. The process of descriptor generation, feature selection and the creation of a large number of QSAR models has been automated into a single workflow within AutoQSAR. The models are built using a variety of machine-learning methods, and each model is scored using a novel approach. Effectiveness of the method is demonstrated through comparison with literature QSAR models using identical datasets for six end points: protein-ligand binding affinity, solubility, blood-brain barrier permeability, carcinogenicity, mutagenicity and bioaccumulation in fish. AutoQSAR demonstrates similar or better predictive performance as compared with published results for four of the six endpoints while requiring minimal human time and expertise.</description><subject>binding affinity prediction</subject><subject>blood-brain barrier permeability</subject><subject>carcinogenicity</subject><subject>fish bioconcentration factor</subject><subject>mutagenicity</subject><subject>QSAR</subject><subject>solubility</subject><issn>1756-8919</issn><issn>1756-8927</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2016</creationdate><recordtype>article</recordtype><recordid>eNp1kEtLAzEQx4MottQevUq-QDTZzT7irRRfUBBf5yXJTmxkHzXJFvrtzbLam7lMhvnNH-aH0CWj15xl2Y1pNUkoywmlIj1Bc1ZkOSlFUpwe_0zM0NL7LxpfmpQiz87RLClynhYsm6OwGkL_8rZ6vcWywzI2rQxQ41bqre0ANyBdZ7tPHPq-waZ3WIEPZOekDlYD_h5kF2yQwe4B--AGHQYHZJzubThgB02c9Z3f2h1u-xqaGHaBzoxsPCx_6wJ93N-9rx_J5vnhab3aEJ3yNJCSKQEUFE1ymeZaCKY4L0zJEwWs1FxEChhXrFZJUpiCaS1qlkrDTTw0Y-kCkSlXu957B6baOdtKd6gYrUaBVRRYjQKrUWDkryZ-N6gW6iP9pysCYgLMMJ7ptYVOQzV1ccPq6Oyf8B8kCYHX</recordid><startdate>20161001</startdate><enddate>20161001</enddate><creator>Dixon, Steven L</creator><creator>Duan, Jianxin</creator><creator>Smith, Ethan</creator><creator>Von Bargen, Christopher D</creator><creator>Sherman, Woody</creator><creator>Repasky, Matthew P</creator><general>Future Science Ltd</general><scope>NPM</scope><scope>AAYXX</scope><scope>CITATION</scope></search><sort><creationdate>20161001</creationdate><title>AutoQSAR: an automated machine learning tool for best-practice quantitative structure-activity relationship modeling</title><author>Dixon, Steven L ; Duan, Jianxin ; Smith, Ethan ; Von Bargen, Christopher D ; Sherman, Woody ; Repasky, Matthew P</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c343t-81b9e0eb026a36c991b447f842be18c49343e14b1db227f71cc9d13af4f289513</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2016</creationdate><topic>binding affinity prediction</topic><topic>blood-brain barrier permeability</topic><topic>carcinogenicity</topic><topic>fish bioconcentration factor</topic><topic>mutagenicity</topic><topic>QSAR</topic><topic>solubility</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Dixon, Steven L</creatorcontrib><creatorcontrib>Duan, Jianxin</creatorcontrib><creatorcontrib>Smith, Ethan</creatorcontrib><creatorcontrib>Von Bargen, Christopher D</creatorcontrib><creatorcontrib>Sherman, Woody</creatorcontrib><creatorcontrib>Repasky, Matthew P</creatorcontrib><collection>PubMed</collection><collection>CrossRef</collection><jtitle>Future medicinal chemistry</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Dixon, Steven L</au><au>Duan, Jianxin</au><au>Smith, Ethan</au><au>Von Bargen, Christopher D</au><au>Sherman, Woody</au><au>Repasky, Matthew P</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>AutoQSAR: an automated machine learning tool for best-practice quantitative structure-activity relationship modeling</atitle><jtitle>Future medicinal chemistry</jtitle><addtitle>Future Med Chem</addtitle><date>2016-10-01</date><risdate>2016</risdate><volume>8</volume><issue>15</issue><spage>1825</spage><epage>1839</epage><pages>1825-1839</pages><issn>1756-8919</issn><eissn>1756-8927</eissn><abstract>We introduce AutoQSAR, an automated machine-learning application to build, validate and deploy quantitative structure-activity relationship (QSAR) models. The process of descriptor generation, feature selection and the creation of a large number of QSAR models has been automated into a single workflow within AutoQSAR. The models are built using a variety of machine-learning methods, and each model is scored using a novel approach. Effectiveness of the method is demonstrated through comparison with literature QSAR models using identical datasets for six end points: protein-ligand binding affinity, solubility, blood-brain barrier permeability, carcinogenicity, mutagenicity and bioaccumulation in fish. AutoQSAR demonstrates similar or better predictive performance as compared with published results for four of the six endpoints while requiring minimal human time and expertise.</abstract><cop>England</cop><pub>Future Science Ltd</pub><pmid>27643715</pmid><doi>10.4155/fmc-2016-0093</doi><tpages>15</tpages></addata></record>
fulltext fulltext
identifier ISSN: 1756-8919
ispartof Future medicinal chemistry, 2016-10, Vol.8 (15), p.1825-1839
issn 1756-8919
1756-8927
language eng
recordid cdi_crossref_primary_10_4155_fmc_2016_0093
source PMC
subjects binding affinity prediction
blood-brain barrier permeability
carcinogenicity
fish bioconcentration factor
mutagenicity
QSAR
solubility
title AutoQSAR: an automated machine learning tool for best-practice quantitative structure-activity relationship modeling
url http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-05T05%3A12%3A33IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-pubmed_cross&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=AutoQSAR:%20an%20automated%20machine%20learning%20tool%20for%20best-practice%20quantitative%20structure-activity%20relationship%20modeling&rft.jtitle=Future%20medicinal%20chemistry&rft.au=Dixon,%20Steven%20L&rft.date=2016-10-01&rft.volume=8&rft.issue=15&rft.spage=1825&rft.epage=1839&rft.pages=1825-1839&rft.issn=1756-8919&rft.eissn=1756-8927&rft_id=info:doi/10.4155/fmc-2016-0093&rft_dat=%3Cpubmed_cross%3E27643715%3C/pubmed_cross%3E%3Cgrp_id%3Ecdi_FETCH-LOGICAL-c343t-81b9e0eb026a36c991b447f842be18c49343e14b1db227f71cc9d13af4f289513%3C/grp_id%3E%3Coa%3E%3C/oa%3E%3Curl%3E%3C/url%3E&rft_id=info:oai/&rft_id=info:pmid/27643715&rfr_iscdi=true