Design of mosquito repellent molecules via the integration of hyperbox machine learning and computer aided molecular design
The use of mosquito repellents is an efficient way to prevent mosquito-borne diseases. Despite the accumulation of information about repellents, there remains the challenge of the lack of understanding of their mechanism of action. There is also a need for systematic methods for discovering new alte...
Main Authors: | , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Elsevier
2022-06-01
|
Series: | Digital Chemical Engineering |
Subjects: | |
Online Access: | http://www.sciencedirect.com/science/article/pii/S2772508122000096 |
_version_ | 1811258006520725504 |
---|---|
author | Mohamad Hatamleh Jia Wen Chong Raymond R. Tan Kathleen B. Aviso Jose Isagani B. Janairo Nishanth G. Chemmangattuvalappil |
author_facet | Mohamad Hatamleh Jia Wen Chong Raymond R. Tan Kathleen B. Aviso Jose Isagani B. Janairo Nishanth G. Chemmangattuvalappil |
author_sort | Mohamad Hatamleh |
collection | DOAJ |
description | The use of mosquito repellents is an efficient way to prevent mosquito-borne diseases. Despite the accumulation of information about repellents, there remains the challenge of the lack of understanding of their mechanism of action. There is also a need for systematic methods for discovering new alternatives that mitigate the drawbacks of repellents currently in use. To address these research gaps, a computer-aided molecular design (CAMD) framework is developed for the optimal molecular design of mosquito repellents. In this framework, the mosquito repelling attribute of molecules are predicted using a data-driven hyperbox-based machine learning approach in the absence of a mechanistic prediction model. The best set of rules is selected from plausible alternative models developed. For the prediction of important physical properties, a group contribution-based method using reliable models is implemented. Subsequently, the CAMD formulation is developed as a mixed-integer linear programming model to obtain structures with minimum viscosity. Results show that of the structures generated, the hyperbox classifier correctly predicted the repelling ability of all molecules found to be known repellents in literature. The molecules not found in the databases provide key insights on where experimental research to develop new repellents should be targeted. Thus, this newly developed framework can be applied as a systematic technique to screen and narrow down the search space for candidate mosquito repellent molecules before final experimental verification. |
first_indexed | 2024-04-12T18:06:29Z |
format | Article |
id | doaj.art-a3c77cda296f4d1d899328c234834f0a |
institution | Directory Open Access Journal |
issn | 2772-5081 |
language | English |
last_indexed | 2024-04-12T18:06:29Z |
publishDate | 2022-06-01 |
publisher | Elsevier |
record_format | Article |
series | Digital Chemical Engineering |
spelling | doaj.art-a3c77cda296f4d1d899328c234834f0a2022-12-22T03:21:59ZengElsevierDigital Chemical Engineering2772-50812022-06-013100018Design of mosquito repellent molecules via the integration of hyperbox machine learning and computer aided molecular designMohamad Hatamleh0Jia Wen Chong1Raymond R. Tan2Kathleen B. Aviso3Jose Isagani B. Janairo4Nishanth G. Chemmangattuvalappil5Department of Chemical and Environmental Engineering, University of Nottingham Malaysia, Broga Road, 43500 Selangor D.E., MalaysiaDepartment of Chemical and Environmental Engineering, University of Nottingham Malaysia, Broga Road, 43500 Selangor D.E., MalaysiaCenter for Engineering and Sustainable Development Research, De La Salle University, 2401 Taft Avenue, 0922 Manila, PhilippinesCenter for Engineering and Sustainable Development Research, De La Salle University, 2401 Taft Avenue, 0922 Manila, PhilippinesDepartment of Biology, De La Salle University, 2401 Taft Avenue, 0922 Manila, PhilippinesDepartment of Chemical and Environmental Engineering, University of Nottingham Malaysia, Broga Road, 43500 Selangor D.E., Malaysia; Corresponding author at: Department of Chemical and Environmental Engineering, Nottingham Malaysia, Selangor, Malaysia.The use of mosquito repellents is an efficient way to prevent mosquito-borne diseases. Despite the accumulation of information about repellents, there remains the challenge of the lack of understanding of their mechanism of action. There is also a need for systematic methods for discovering new alternatives that mitigate the drawbacks of repellents currently in use. To address these research gaps, a computer-aided molecular design (CAMD) framework is developed for the optimal molecular design of mosquito repellents. In this framework, the mosquito repelling attribute of molecules are predicted using a data-driven hyperbox-based machine learning approach in the absence of a mechanistic prediction model. The best set of rules is selected from plausible alternative models developed. For the prediction of important physical properties, a group contribution-based method using reliable models is implemented. Subsequently, the CAMD formulation is developed as a mixed-integer linear programming model to obtain structures with minimum viscosity. Results show that of the structures generated, the hyperbox classifier correctly predicted the repelling ability of all molecules found to be known repellents in literature. The molecules not found in the databases provide key insights on where experimental research to develop new repellents should be targeted. Thus, this newly developed framework can be applied as a systematic technique to screen and narrow down the search space for candidate mosquito repellent molecules before final experimental verification.http://www.sciencedirect.com/science/article/pii/S2772508122000096Mosquito repellentsComputer-aided molecular designMachine learningHyperbox classifierCheminformaticsMixed-integer linear programming |
spellingShingle | Mohamad Hatamleh Jia Wen Chong Raymond R. Tan Kathleen B. Aviso Jose Isagani B. Janairo Nishanth G. Chemmangattuvalappil Design of mosquito repellent molecules via the integration of hyperbox machine learning and computer aided molecular design Digital Chemical Engineering Mosquito repellents Computer-aided molecular design Machine learning Hyperbox classifier Cheminformatics Mixed-integer linear programming |
title | Design of mosquito repellent molecules via the integration of hyperbox machine learning and computer aided molecular design |
title_full | Design of mosquito repellent molecules via the integration of hyperbox machine learning and computer aided molecular design |
title_fullStr | Design of mosquito repellent molecules via the integration of hyperbox machine learning and computer aided molecular design |
title_full_unstemmed | Design of mosquito repellent molecules via the integration of hyperbox machine learning and computer aided molecular design |
title_short | Design of mosquito repellent molecules via the integration of hyperbox machine learning and computer aided molecular design |
title_sort | design of mosquito repellent molecules via the integration of hyperbox machine learning and computer aided molecular design |
topic | Mosquito repellents Computer-aided molecular design Machine learning Hyperbox classifier Cheminformatics Mixed-integer linear programming |
url | http://www.sciencedirect.com/science/article/pii/S2772508122000096 |
work_keys_str_mv | AT mohamadhatamleh designofmosquitorepellentmoleculesviatheintegrationofhyperboxmachinelearningandcomputeraidedmoleculardesign AT jiawenchong designofmosquitorepellentmoleculesviatheintegrationofhyperboxmachinelearningandcomputeraidedmoleculardesign AT raymondrtan designofmosquitorepellentmoleculesviatheintegrationofhyperboxmachinelearningandcomputeraidedmoleculardesign AT kathleenbaviso designofmosquitorepellentmoleculesviatheintegrationofhyperboxmachinelearningandcomputeraidedmoleculardesign AT joseisaganibjanairo designofmosquitorepellentmoleculesviatheintegrationofhyperboxmachinelearningandcomputeraidedmoleculardesign AT nishanthgchemmangattuvalappil designofmosquitorepellentmoleculesviatheintegrationofhyperboxmachinelearningandcomputeraidedmoleculardesign |