Loading…

In silico formulation prediction of drug/cyclodextrin/polymer ternary complexes by machine learning and molecular modeling techniques

Ternary cyclodextrin (CD) complexes (drug/CD/polymer) can effectively improve the solubility of water-insoluble drugs with large size than binary CD formulations. However, ternary formulations are screened by a trial-and-error approach, which is laborious and material-wasting. Current research aims...

Full description

Saved in:
Bibliographic Details
Published in:Carbohydrate polymers 2022-01, Vol.275, p.118712-118712, Article 118712
Main Authors: Li, Junjun, Gao, Hanlu, Ye, Zhuyifan, Deng, Jiayin, Ouyang, Defang
Format: Article
Language:English
Subjects:
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-c431t-fa15a1504b534fc3348facacdb1e8b7809ef1a3ce04f7c5d4c6455fa12650a0f3
cites cdi_FETCH-LOGICAL-c431t-fa15a1504b534fc3348facacdb1e8b7809ef1a3ce04f7c5d4c6455fa12650a0f3
container_end_page 118712
container_issue
container_start_page 118712
container_title Carbohydrate polymers
container_volume 275
creator Li, Junjun
Gao, Hanlu
Ye, Zhuyifan
Deng, Jiayin
Ouyang, Defang
description Ternary cyclodextrin (CD) complexes (drug/CD/polymer) can effectively improve the solubility of water-insoluble drugs with large size than binary CD formulations. However, ternary formulations are screened by a trial-and-error approach, which is laborious and material-wasting. Current research aims to develop a prediction model for ternary CD formulations by combined machine learning and molecular modeling. 596 ternary formulations data were collected to build a prediction model by machine learning. The random forest model achieved good performance with R2 = 0.887 in ST prediction and R2 = 0.815 in ST/SB prediction. Two ternary formulations (Hydrocortisone/β-CD/HPMC and dovitinib/γ-CD/CMC) were used to validate the prediction model. Molecular modeling results showed that HPMC not only warped around hydrocortisone but also prevented CD molecules from self-aggregation to increase solubility. In conclusion, a prediction model for the ternary CD formulations was successfully developed, which will significantly accelerate the formulation screening process to benefit the formulation development of water-insoluble drugs. [Display omitted] •Random forest model did well in ternary cyclodextrin formulation prediction.•Factors that may impact solubilization was ranked by random forest model.•Molecular dynamic simulation was performed to investigate molecular mechanism.
doi_str_mv 10.1016/j.carbpol.2021.118712
format article
fullrecord <record><control><sourceid>proquest_cross</sourceid><recordid>TN_cdi_proquest_miscellaneous_2595119776</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><els_id>S0144861721010997</els_id><sourcerecordid>2595119776</sourcerecordid><originalsourceid>FETCH-LOGICAL-c431t-fa15a1504b534fc3348facacdb1e8b7809ef1a3ce04f7c5d4c6455fa12650a0f3</originalsourceid><addsrcrecordid>eNqFUcGO1DAMjRCIHRY-AZQjl84kTdJ2TgitFlhpJS5wjlLH2c0oTUrSop0P4L_JMANXLEu2rPf8ZD9C3nK25Yx3u8MWTB7nFLYta_mW86Hn7TOyqXXfcCHlc7JhXMpm6Hh_RV6VcmA1Os5ekishe9lK0W_Ir7tIiw8eEnUpT2swi0-Rzhmthz9tctTm9WEHRwjJ4tOSfdxV3eOEmS6Yo8lHCmmaAz5hoeORTgYefUQa0OTo4wM10dIpBYS6PtfOYjiNF4TH6H-sWF6TF86Egm8u9Zp8_3T77eZLc__1893Nx_sGpOBL4wxXNZkclZAOhJCDM2DAjhyHsR_YHh03ApBJ14OyEjqpVGW1nWKGOXFN3p_3zjmddBc9-QIYgomY1qJbtVec7_u-q1B1hkJOpWR0es5-qrdqzvTJAX3QFwf0yQF9dqDy3l0k1nFC-4_19-UV8OEMwHroT49ZF_AYoT48IyzaJv8fid_pwZ4o</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2595119776</pqid></control><display><type>article</type><title>In silico formulation prediction of drug/cyclodextrin/polymer ternary complexes by machine learning and molecular modeling techniques</title><source>ScienceDirect Freedom Collection 2022-2024</source><creator>Li, Junjun ; Gao, Hanlu ; Ye, Zhuyifan ; Deng, Jiayin ; Ouyang, Defang</creator><creatorcontrib>Li, Junjun ; Gao, Hanlu ; Ye, Zhuyifan ; Deng, Jiayin ; Ouyang, Defang</creatorcontrib><description>Ternary cyclodextrin (CD) complexes (drug/CD/polymer) can effectively improve the solubility of water-insoluble drugs with large size than binary CD formulations. However, ternary formulations are screened by a trial-and-error approach, which is laborious and material-wasting. Current research aims to develop a prediction model for ternary CD formulations by combined machine learning and molecular modeling. 596 ternary formulations data were collected to build a prediction model by machine learning. The random forest model achieved good performance with R2 = 0.887 in ST prediction and R2 = 0.815 in ST/SB prediction. Two ternary formulations (Hydrocortisone/β-CD/HPMC and dovitinib/γ-CD/CMC) were used to validate the prediction model. Molecular modeling results showed that HPMC not only warped around hydrocortisone but also prevented CD molecules from self-aggregation to increase solubility. In conclusion, a prediction model for the ternary CD formulations was successfully developed, which will significantly accelerate the formulation screening process to benefit the formulation development of water-insoluble drugs. [Display omitted] •Random forest model did well in ternary cyclodextrin formulation prediction.•Factors that may impact solubilization was ranked by random forest model.•Molecular dynamic simulation was performed to investigate molecular mechanism.</description><identifier>ISSN: 0144-8617</identifier><identifier>EISSN: 1879-1344</identifier><identifier>DOI: 10.1016/j.carbpol.2021.118712</identifier><identifier>PMID: 34742437</identifier><language>eng</language><publisher>England: Elsevier Ltd</publisher><subject>Benzimidazoles - chemistry ; Cyclodextrins - chemistry ; Drug Compounding ; Hydrocortisone - chemistry ; Machine Learning ; Models, Molecular ; Molecular modeling ; Polymers - chemistry ; Quinolones - chemistry ; Random forest ; Solubility prediction ; Ternary cyclodextrin complexes</subject><ispartof>Carbohydrate polymers, 2022-01, Vol.275, p.118712-118712, Article 118712</ispartof><rights>2021 Elsevier Ltd</rights><rights>Copyright © 2021 Elsevier Ltd. All rights reserved.</rights><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c431t-fa15a1504b534fc3348facacdb1e8b7809ef1a3ce04f7c5d4c6455fa12650a0f3</citedby><cites>FETCH-LOGICAL-c431t-fa15a1504b534fc3348facacdb1e8b7809ef1a3ce04f7c5d4c6455fa12650a0f3</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/34742437$$D View this record in MEDLINE/PubMed$$Hfree_for_read</backlink></links><search><creatorcontrib>Li, Junjun</creatorcontrib><creatorcontrib>Gao, Hanlu</creatorcontrib><creatorcontrib>Ye, Zhuyifan</creatorcontrib><creatorcontrib>Deng, Jiayin</creatorcontrib><creatorcontrib>Ouyang, Defang</creatorcontrib><title>In silico formulation prediction of drug/cyclodextrin/polymer ternary complexes by machine learning and molecular modeling techniques</title><title>Carbohydrate polymers</title><addtitle>Carbohydr Polym</addtitle><description>Ternary cyclodextrin (CD) complexes (drug/CD/polymer) can effectively improve the solubility of water-insoluble drugs with large size than binary CD formulations. However, ternary formulations are screened by a trial-and-error approach, which is laborious and material-wasting. Current research aims to develop a prediction model for ternary CD formulations by combined machine learning and molecular modeling. 596 ternary formulations data were collected to build a prediction model by machine learning. The random forest model achieved good performance with R2 = 0.887 in ST prediction and R2 = 0.815 in ST/SB prediction. Two ternary formulations (Hydrocortisone/β-CD/HPMC and dovitinib/γ-CD/CMC) were used to validate the prediction model. Molecular modeling results showed that HPMC not only warped around hydrocortisone but also prevented CD molecules from self-aggregation to increase solubility. In conclusion, a prediction model for the ternary CD formulations was successfully developed, which will significantly accelerate the formulation screening process to benefit the formulation development of water-insoluble drugs. [Display omitted] •Random forest model did well in ternary cyclodextrin formulation prediction.•Factors that may impact solubilization was ranked by random forest model.•Molecular dynamic simulation was performed to investigate molecular mechanism.</description><subject>Benzimidazoles - chemistry</subject><subject>Cyclodextrins - chemistry</subject><subject>Drug Compounding</subject><subject>Hydrocortisone - chemistry</subject><subject>Machine Learning</subject><subject>Models, Molecular</subject><subject>Molecular modeling</subject><subject>Polymers - chemistry</subject><subject>Quinolones - chemistry</subject><subject>Random forest</subject><subject>Solubility prediction</subject><subject>Ternary cyclodextrin complexes</subject><issn>0144-8617</issn><issn>1879-1344</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2022</creationdate><recordtype>article</recordtype><recordid>eNqFUcGO1DAMjRCIHRY-AZQjl84kTdJ2TgitFlhpJS5wjlLH2c0oTUrSop0P4L_JMANXLEu2rPf8ZD9C3nK25Yx3u8MWTB7nFLYta_mW86Hn7TOyqXXfcCHlc7JhXMpm6Hh_RV6VcmA1Os5ekishe9lK0W_Ir7tIiw8eEnUpT2swi0-Rzhmthz9tctTm9WEHRwjJ4tOSfdxV3eOEmS6Yo8lHCmmaAz5hoeORTgYefUQa0OTo4wM10dIpBYS6PtfOYjiNF4TH6H-sWF6TF86Egm8u9Zp8_3T77eZLc__1893Nx_sGpOBL4wxXNZkclZAOhJCDM2DAjhyHsR_YHh03ApBJ14OyEjqpVGW1nWKGOXFN3p_3zjmddBc9-QIYgomY1qJbtVec7_u-q1B1hkJOpWR0es5-qrdqzvTJAX3QFwf0yQF9dqDy3l0k1nFC-4_19-UV8OEMwHroT49ZF_AYoT48IyzaJv8fid_pwZ4o</recordid><startdate>20220101</startdate><enddate>20220101</enddate><creator>Li, Junjun</creator><creator>Gao, Hanlu</creator><creator>Ye, Zhuyifan</creator><creator>Deng, Jiayin</creator><creator>Ouyang, Defang</creator><general>Elsevier Ltd</general><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>20220101</creationdate><title>In silico formulation prediction of drug/cyclodextrin/polymer ternary complexes by machine learning and molecular modeling techniques</title><author>Li, Junjun ; Gao, Hanlu ; Ye, Zhuyifan ; Deng, Jiayin ; Ouyang, Defang</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c431t-fa15a1504b534fc3348facacdb1e8b7809ef1a3ce04f7c5d4c6455fa12650a0f3</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2022</creationdate><topic>Benzimidazoles - chemistry</topic><topic>Cyclodextrins - chemistry</topic><topic>Drug Compounding</topic><topic>Hydrocortisone - chemistry</topic><topic>Machine Learning</topic><topic>Models, Molecular</topic><topic>Molecular modeling</topic><topic>Polymers - chemistry</topic><topic>Quinolones - chemistry</topic><topic>Random forest</topic><topic>Solubility prediction</topic><topic>Ternary cyclodextrin complexes</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Li, Junjun</creatorcontrib><creatorcontrib>Gao, Hanlu</creatorcontrib><creatorcontrib>Ye, Zhuyifan</creatorcontrib><creatorcontrib>Deng, Jiayin</creatorcontrib><creatorcontrib>Ouyang, Defang</creatorcontrib><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>Carbohydrate polymers</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Li, Junjun</au><au>Gao, Hanlu</au><au>Ye, Zhuyifan</au><au>Deng, Jiayin</au><au>Ouyang, Defang</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>In silico formulation prediction of drug/cyclodextrin/polymer ternary complexes by machine learning and molecular modeling techniques</atitle><jtitle>Carbohydrate polymers</jtitle><addtitle>Carbohydr Polym</addtitle><date>2022-01-01</date><risdate>2022</risdate><volume>275</volume><spage>118712</spage><epage>118712</epage><pages>118712-118712</pages><artnum>118712</artnum><issn>0144-8617</issn><eissn>1879-1344</eissn><abstract>Ternary cyclodextrin (CD) complexes (drug/CD/polymer) can effectively improve the solubility of water-insoluble drugs with large size than binary CD formulations. However, ternary formulations are screened by a trial-and-error approach, which is laborious and material-wasting. Current research aims to develop a prediction model for ternary CD formulations by combined machine learning and molecular modeling. 596 ternary formulations data were collected to build a prediction model by machine learning. The random forest model achieved good performance with R2 = 0.887 in ST prediction and R2 = 0.815 in ST/SB prediction. Two ternary formulations (Hydrocortisone/β-CD/HPMC and dovitinib/γ-CD/CMC) were used to validate the prediction model. Molecular modeling results showed that HPMC not only warped around hydrocortisone but also prevented CD molecules from self-aggregation to increase solubility. In conclusion, a prediction model for the ternary CD formulations was successfully developed, which will significantly accelerate the formulation screening process to benefit the formulation development of water-insoluble drugs. [Display omitted] •Random forest model did well in ternary cyclodextrin formulation prediction.•Factors that may impact solubilization was ranked by random forest model.•Molecular dynamic simulation was performed to investigate molecular mechanism.</abstract><cop>England</cop><pub>Elsevier Ltd</pub><pmid>34742437</pmid><doi>10.1016/j.carbpol.2021.118712</doi><tpages>1</tpages></addata></record>
fulltext fulltext
identifier ISSN: 0144-8617
ispartof Carbohydrate polymers, 2022-01, Vol.275, p.118712-118712, Article 118712
issn 0144-8617
1879-1344
language eng
recordid cdi_proquest_miscellaneous_2595119776
source ScienceDirect Freedom Collection 2022-2024
subjects Benzimidazoles - chemistry
Cyclodextrins - chemistry
Drug Compounding
Hydrocortisone - chemistry
Machine Learning
Models, Molecular
Molecular modeling
Polymers - chemistry
Quinolones - chemistry
Random forest
Solubility prediction
Ternary cyclodextrin complexes
title In silico formulation prediction of drug/cyclodextrin/polymer ternary complexes by machine learning and molecular modeling techniques
url http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-25T08%3A00%3A29IST&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=In%20silico%20formulation%20prediction%20of%20drug/cyclodextrin/polymer%20ternary%20complexes%20by%20machine%20learning%20and%20molecular%20modeling%20techniques&rft.jtitle=Carbohydrate%20polymers&rft.au=Li,%20Junjun&rft.date=2022-01-01&rft.volume=275&rft.spage=118712&rft.epage=118712&rft.pages=118712-118712&rft.artnum=118712&rft.issn=0144-8617&rft.eissn=1879-1344&rft_id=info:doi/10.1016/j.carbpol.2021.118712&rft_dat=%3Cproquest_cross%3E2595119776%3C/proquest_cross%3E%3Cgrp_id%3Ecdi_FETCH-LOGICAL-c431t-fa15a1504b534fc3348facacdb1e8b7809ef1a3ce04f7c5d4c6455fa12650a0f3%3C/grp_id%3E%3Coa%3E%3C/oa%3E%3Curl%3E%3C/url%3E&rft_id=info:oai/&rft_pqid=2595119776&rft_id=info:pmid/34742437&rfr_iscdi=true