Loading…

Retro Drug Design: From Target Properties to Molecular Structures

To generate drug molecules of desired properties with computational methods is the holy grail in pharmaceutical research. Here we describe an AI strategy, retro drug design, or RDD, to generate novel small molecule drugs from scratch to meet predefined requirements, including but not limited to biol...

Full description

Saved in:
Bibliographic Details
Published in:arXiv.org 2021-05
Main Authors: Wang, Yuhong, Sam, Michael, Huang, Ruili, Zhao, Jinghua, Recabo, Katlin, Bougie, Danielle, Shu, Qiang, Shinn, Paul, Sun, Hongmao
Format: Article
Language:English
Subjects:
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
cited_by
cites
container_end_page
container_issue
container_start_page
container_title arXiv.org
container_volume
creator Wang, Yuhong
Sam, Michael
Huang, Ruili
Zhao, Jinghua
Recabo, Katlin
Bougie, Danielle
Shu, Qiang
Shinn, Paul
Sun, Hongmao
description To generate drug molecules of desired properties with computational methods is the holy grail in pharmaceutical research. Here we describe an AI strategy, retro drug design, or RDD, to generate novel small molecule drugs from scratch to meet predefined requirements, including but not limited to biological activity against a drug target, and optimal range of physicochemical and ADMET properties. Traditional predictive models were first trained over experimental data for the target properties, using an atom typing based molecular descriptor system, ATP. Monte Carlo sampling algorithm was then utilized to find the solutions in the ATP space defined by the target properties, and the deep learning model of Seq2Seq was employed to decode molecular structures from the solutions. To test feasibility of the algorithm, we challenged RDD to generate novel drugs that can activate {\mu} opioid receptor (MOR) and penetrate blood brain barrier (BBB). Starting from vectors of random numbers, RDD generated 180,000 chemical structures, of which 78% were chemically valid. About 42,000 (31%) of the valid structures fell into the property space defined by MOR activity and BBB permeability. Out of the 42,000 structures, only 267 chemicals were commercially available, indicating a high extent of novelty of the AI-generated compounds. We purchased and assayed 96 compounds, and 25 of which were found to be MOR agonists. These compounds also have excellent BBB scores. The results presented in this paper illustrate that RDD has potential to revolutionize the current drug discovery process and create novel structures with multiple desired properties, including biological functions and ADMET properties. Availability of an AI-enabled fast track in drug discovery is essential to cope with emergent public health threat, such as pandemic of COVID-19.
format article
fullrecord <record><control><sourceid>proquest</sourceid><recordid>TN_cdi_proquest_journals_2525913878</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2525913878</sourcerecordid><originalsourceid>FETCH-proquest_journals_25259138783</originalsourceid><addsrcrecordid>eNqNysEKgkAQgOElCJLyHQY6C7rbpnWLTLoEkd5FZBLFHJudff869ACd_sP3L1SgjUmibKf1SoXODXEc632qrTWBOj1QmCBn30GOru-mIxRML6ga7lDgzjQjS48OhOBGI7Z-bBhKYd-KZ3QbtXw2o8Pw17XaFpfqfI1mprdHJ_VAnqcv1dpqe0hMlmbmv-sDTbI5Tw</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2525913878</pqid></control><display><type>article</type><title>Retro Drug Design: From Target Properties to Molecular Structures</title><source>Publicly Available Content Database</source><source>Coronavirus Research Database</source><creator>Wang, Yuhong ; Sam, Michael ; Huang, Ruili ; Zhao, Jinghua ; Recabo, Katlin ; Bougie, Danielle ; Shu, Qiang ; Shinn, Paul ; Sun, Hongmao</creator><creatorcontrib>Wang, Yuhong ; Sam, Michael ; Huang, Ruili ; Zhao, Jinghua ; Recabo, Katlin ; Bougie, Danielle ; Shu, Qiang ; Shinn, Paul ; Sun, Hongmao</creatorcontrib><description>To generate drug molecules of desired properties with computational methods is the holy grail in pharmaceutical research. Here we describe an AI strategy, retro drug design, or RDD, to generate novel small molecule drugs from scratch to meet predefined requirements, including but not limited to biological activity against a drug target, and optimal range of physicochemical and ADMET properties. Traditional predictive models were first trained over experimental data for the target properties, using an atom typing based molecular descriptor system, ATP. Monte Carlo sampling algorithm was then utilized to find the solutions in the ATP space defined by the target properties, and the deep learning model of Seq2Seq was employed to decode molecular structures from the solutions. To test feasibility of the algorithm, we challenged RDD to generate novel drugs that can activate {\mu} opioid receptor (MOR) and penetrate blood brain barrier (BBB). Starting from vectors of random numbers, RDD generated 180,000 chemical structures, of which 78% were chemically valid. About 42,000 (31%) of the valid structures fell into the property space defined by MOR activity and BBB permeability. Out of the 42,000 structures, only 267 chemicals were commercially available, indicating a high extent of novelty of the AI-generated compounds. We purchased and assayed 96 compounds, and 25 of which were found to be MOR agonists. These compounds also have excellent BBB scores. The results presented in this paper illustrate that RDD has potential to revolutionize the current drug discovery process and create novel structures with multiple desired properties, including biological functions and ADMET properties. Availability of an AI-enabled fast track in drug discovery is essential to cope with emergent public health threat, such as pandemic of COVID-19.</description><identifier>EISSN: 2331-8422</identifier><language>eng</language><publisher>Ithaca: Cornell University Library, arXiv.org</publisher><subject>Algorithms ; Biological activity ; Biological properties ; COVID-19 ; Drugs ; Machine learning ; Molecular structure ; Prediction models ; Public health ; Random numbers</subject><ispartof>arXiv.org, 2021-05</ispartof><rights>2021. This work is published under http://creativecommons.org/licenses/by-nc-nd/4.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://www.proquest.com/docview/2525913878?pq-origsite=primo$$EHTML$$P50$$Gproquest$$Hfree_for_read</linktohtml><link.rule.ids>780,784,25753,37012,38516,43895,44590</link.rule.ids></links><search><creatorcontrib>Wang, Yuhong</creatorcontrib><creatorcontrib>Sam, Michael</creatorcontrib><creatorcontrib>Huang, Ruili</creatorcontrib><creatorcontrib>Zhao, Jinghua</creatorcontrib><creatorcontrib>Recabo, Katlin</creatorcontrib><creatorcontrib>Bougie, Danielle</creatorcontrib><creatorcontrib>Shu, Qiang</creatorcontrib><creatorcontrib>Shinn, Paul</creatorcontrib><creatorcontrib>Sun, Hongmao</creatorcontrib><title>Retro Drug Design: From Target Properties to Molecular Structures</title><title>arXiv.org</title><description>To generate drug molecules of desired properties with computational methods is the holy grail in pharmaceutical research. Here we describe an AI strategy, retro drug design, or RDD, to generate novel small molecule drugs from scratch to meet predefined requirements, including but not limited to biological activity against a drug target, and optimal range of physicochemical and ADMET properties. Traditional predictive models were first trained over experimental data for the target properties, using an atom typing based molecular descriptor system, ATP. Monte Carlo sampling algorithm was then utilized to find the solutions in the ATP space defined by the target properties, and the deep learning model of Seq2Seq was employed to decode molecular structures from the solutions. To test feasibility of the algorithm, we challenged RDD to generate novel drugs that can activate {\mu} opioid receptor (MOR) and penetrate blood brain barrier (BBB). Starting from vectors of random numbers, RDD generated 180,000 chemical structures, of which 78% were chemically valid. About 42,000 (31%) of the valid structures fell into the property space defined by MOR activity and BBB permeability. Out of the 42,000 structures, only 267 chemicals were commercially available, indicating a high extent of novelty of the AI-generated compounds. We purchased and assayed 96 compounds, and 25 of which were found to be MOR agonists. These compounds also have excellent BBB scores. The results presented in this paper illustrate that RDD has potential to revolutionize the current drug discovery process and create novel structures with multiple desired properties, including biological functions and ADMET properties. Availability of an AI-enabled fast track in drug discovery is essential to cope with emergent public health threat, such as pandemic of COVID-19.</description><subject>Algorithms</subject><subject>Biological activity</subject><subject>Biological properties</subject><subject>COVID-19</subject><subject>Drugs</subject><subject>Machine learning</subject><subject>Molecular structure</subject><subject>Prediction models</subject><subject>Public health</subject><subject>Random numbers</subject><issn>2331-8422</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2021</creationdate><recordtype>article</recordtype><sourceid>COVID</sourceid><sourceid>PIMPY</sourceid><recordid>eNqNysEKgkAQgOElCJLyHQY6C7rbpnWLTLoEkd5FZBLFHJudff869ACd_sP3L1SgjUmibKf1SoXODXEc632qrTWBOj1QmCBn30GOru-mIxRML6ga7lDgzjQjS48OhOBGI7Z-bBhKYd-KZ3QbtXw2o8Pw17XaFpfqfI1mprdHJ_VAnqcv1dpqe0hMlmbmv-sDTbI5Tw</recordid><startdate>20210511</startdate><enddate>20210511</enddate><creator>Wang, Yuhong</creator><creator>Sam, Michael</creator><creator>Huang, Ruili</creator><creator>Zhao, Jinghua</creator><creator>Recabo, Katlin</creator><creator>Bougie, Danielle</creator><creator>Shu, Qiang</creator><creator>Shinn, Paul</creator><creator>Sun, Hongmao</creator><general>Cornell University Library, arXiv.org</general><scope>8FE</scope><scope>8FG</scope><scope>ABJCF</scope><scope>ABUWG</scope><scope>AFKRA</scope><scope>AZQEC</scope><scope>BENPR</scope><scope>BGLVJ</scope><scope>CCPQU</scope><scope>COVID</scope><scope>DWQXO</scope><scope>HCIFZ</scope><scope>L6V</scope><scope>M7S</scope><scope>PIMPY</scope><scope>PQEST</scope><scope>PQQKQ</scope><scope>PQUKI</scope><scope>PRINS</scope><scope>PTHSS</scope></search><sort><creationdate>20210511</creationdate><title>Retro Drug Design: From Target Properties to Molecular Structures</title><author>Wang, Yuhong ; Sam, Michael ; Huang, Ruili ; Zhao, Jinghua ; Recabo, Katlin ; Bougie, Danielle ; Shu, Qiang ; Shinn, Paul ; Sun, Hongmao</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-proquest_journals_25259138783</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2021</creationdate><topic>Algorithms</topic><topic>Biological activity</topic><topic>Biological properties</topic><topic>COVID-19</topic><topic>Drugs</topic><topic>Machine learning</topic><topic>Molecular structure</topic><topic>Prediction models</topic><topic>Public health</topic><topic>Random numbers</topic><toplevel>online_resources</toplevel><creatorcontrib>Wang, Yuhong</creatorcontrib><creatorcontrib>Sam, Michael</creatorcontrib><creatorcontrib>Huang, Ruili</creatorcontrib><creatorcontrib>Zhao, Jinghua</creatorcontrib><creatorcontrib>Recabo, Katlin</creatorcontrib><creatorcontrib>Bougie, Danielle</creatorcontrib><creatorcontrib>Shu, Qiang</creatorcontrib><creatorcontrib>Shinn, Paul</creatorcontrib><creatorcontrib>Sun, Hongmao</creatorcontrib><collection>ProQuest SciTech Collection</collection><collection>ProQuest Technology Collection</collection><collection>Materials Science &amp; Engineering Collection</collection><collection>ProQuest Central (Alumni)</collection><collection>ProQuest Central</collection><collection>ProQuest Central Essentials</collection><collection>AUTh Library subscriptions: ProQuest Central</collection><collection>Technology Collection</collection><collection>ProQuest One Community College</collection><collection>Coronavirus Research Database</collection><collection>ProQuest Central Korea</collection><collection>SciTech Premium Collection</collection><collection>ProQuest Engineering Collection</collection><collection>Engineering Database</collection><collection>Publicly Available Content Database</collection><collection>ProQuest One Academic Eastern Edition (DO NOT USE)</collection><collection>ProQuest One Academic</collection><collection>ProQuest One Academic UKI Edition</collection><collection>ProQuest Central China</collection><collection>Engineering Collection</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Wang, Yuhong</au><au>Sam, Michael</au><au>Huang, Ruili</au><au>Zhao, Jinghua</au><au>Recabo, Katlin</au><au>Bougie, Danielle</au><au>Shu, Qiang</au><au>Shinn, Paul</au><au>Sun, Hongmao</au><format>book</format><genre>document</genre><ristype>GEN</ristype><atitle>Retro Drug Design: From Target Properties to Molecular Structures</atitle><jtitle>arXiv.org</jtitle><date>2021-05-11</date><risdate>2021</risdate><eissn>2331-8422</eissn><abstract>To generate drug molecules of desired properties with computational methods is the holy grail in pharmaceutical research. Here we describe an AI strategy, retro drug design, or RDD, to generate novel small molecule drugs from scratch to meet predefined requirements, including but not limited to biological activity against a drug target, and optimal range of physicochemical and ADMET properties. Traditional predictive models were first trained over experimental data for the target properties, using an atom typing based molecular descriptor system, ATP. Monte Carlo sampling algorithm was then utilized to find the solutions in the ATP space defined by the target properties, and the deep learning model of Seq2Seq was employed to decode molecular structures from the solutions. To test feasibility of the algorithm, we challenged RDD to generate novel drugs that can activate {\mu} opioid receptor (MOR) and penetrate blood brain barrier (BBB). Starting from vectors of random numbers, RDD generated 180,000 chemical structures, of which 78% were chemically valid. About 42,000 (31%) of the valid structures fell into the property space defined by MOR activity and BBB permeability. Out of the 42,000 structures, only 267 chemicals were commercially available, indicating a high extent of novelty of the AI-generated compounds. We purchased and assayed 96 compounds, and 25 of which were found to be MOR agonists. These compounds also have excellent BBB scores. The results presented in this paper illustrate that RDD has potential to revolutionize the current drug discovery process and create novel structures with multiple desired properties, including biological functions and ADMET properties. Availability of an AI-enabled fast track in drug discovery is essential to cope with emergent public health threat, such as pandemic of COVID-19.</abstract><cop>Ithaca</cop><pub>Cornell University Library, arXiv.org</pub><oa>free_for_read</oa></addata></record>
fulltext fulltext
identifier EISSN: 2331-8422
ispartof arXiv.org, 2021-05
issn 2331-8422
language eng
recordid cdi_proquest_journals_2525913878
source Publicly Available Content Database; Coronavirus Research Database
subjects Algorithms
Biological activity
Biological properties
COVID-19
Drugs
Machine learning
Molecular structure
Prediction models
Public health
Random numbers
title Retro Drug Design: From Target Properties to Molecular Structures
url http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-24T17%3A39%3A53IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest&rft_val_fmt=info:ofi/fmt:kev:mtx:book&rft.genre=document&rft.atitle=Retro%20Drug%20Design:%20From%20Target%20Properties%20to%20Molecular%20Structures&rft.jtitle=arXiv.org&rft.au=Wang,%20Yuhong&rft.date=2021-05-11&rft.eissn=2331-8422&rft_id=info:doi/&rft_dat=%3Cproquest%3E2525913878%3C/proquest%3E%3Cgrp_id%3Ecdi_FETCH-proquest_journals_25259138783%3C/grp_id%3E%3Coa%3E%3C/oa%3E%3Curl%3E%3C/url%3E&rft_id=info:oai/&rft_pqid=2525913878&rft_id=info:pmid/&rfr_iscdi=true