A machine learning approach in predicting mosquito repellency of plant – derived compounds
The increasing prevalence of mosquito – borne diseases has prompted intensified efforts in the prevention of being bitten by the vector. Among the various strategies of vector control, the application of repellents provides instant and effective protection from mosquitoes. However, emerging concerns...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
SciCell s.r.o.
2018-07-01
|
| Series: | Nova Biotechnologica et Chimica |
| Subjects: | |
| Online Access: | http://www.degruyter.com/view/j/nbec.2018.17.issue-1/nbec-2018-0006/nbec-2018-0006.xml?format=INT |
| _version_ | 1818200411567292416 |
|---|---|
| author | Janairo Jose Isagani B. Janairo Gerardo C. Co Frumencio F. |
| author_facet | Janairo Jose Isagani B. Janairo Gerardo C. Co Frumencio F. |
| author_sort | Janairo Jose Isagani B. |
| collection | DOAJ |
| description | The increasing prevalence of mosquito – borne diseases has prompted intensified efforts in the prevention of being bitten by the vector. Among the various strategies of vector control, the application of repellents provides instant and effective protection from mosquitoes. However, emerging concerns regarding the safety of the widely used repellent, DEET, has led to initiatives to explore natural alternatives. In order to fully realize the potential of natural repellents, focusing on the discovery of natural compounds eliciting repellency is of paramount importance. In this paper, machine learning was utilized to establish association between the mosquito repellent activity of 33 natural compounds using 20 chemical descriptors. Individually, the descriptors had insignificant monotonic relationship with the response variable. But when optimized, the formulated model through boosted trees regression exhibited reliable predictive ability (r2 train = 0.93, r2 test = 0.66, r2 overall = 0.87). The findings presented have also introduced new descriptors that exhibited association with repellency through ensemble learning such as heat capacity, Log P, entropy, enthalpy, Gibb’s free energy, energy, and zero-point energy. |
| first_indexed | 2024-12-12T02:37:14Z |
| format | Article |
| id | doaj.art-e7a16896f6db4a1596246bb2113142f1 |
| institution | Directory Open Access Journal |
| issn | 1338-6905 |
| language | English |
| last_indexed | 2024-12-12T02:37:14Z |
| publishDate | 2018-07-01 |
| publisher | SciCell s.r.o. |
| record_format | Article |
| series | Nova Biotechnologica et Chimica |
| spelling | doaj.art-e7a16896f6db4a1596246bb2113142f12022-12-22T00:41:15ZengSciCell s.r.o.Nova Biotechnologica et Chimica1338-69052018-07-01171586510.2478/nbec-2018-0006nbec-2018-0006A machine learning approach in predicting mosquito repellency of plant – derived compoundsJanairo Jose Isagani B.0Janairo Gerardo C.1Co Frumencio F.2De La Salle University, 2401 Taft Avenue, Manila0922, PhilippinesDe La Salle University, 2401 Taft Avenue, Manila0922, PhilippinesDe La Salle University, 2401 Taft Avenue, Manila0922, PhilippinesThe increasing prevalence of mosquito – borne diseases has prompted intensified efforts in the prevention of being bitten by the vector. Among the various strategies of vector control, the application of repellents provides instant and effective protection from mosquitoes. However, emerging concerns regarding the safety of the widely used repellent, DEET, has led to initiatives to explore natural alternatives. In order to fully realize the potential of natural repellents, focusing on the discovery of natural compounds eliciting repellency is of paramount importance. In this paper, machine learning was utilized to establish association between the mosquito repellent activity of 33 natural compounds using 20 chemical descriptors. Individually, the descriptors had insignificant monotonic relationship with the response variable. But when optimized, the formulated model through boosted trees regression exhibited reliable predictive ability (r2 train = 0.93, r2 test = 0.66, r2 overall = 0.87). The findings presented have also introduced new descriptors that exhibited association with repellency through ensemble learning such as heat capacity, Log P, entropy, enthalpy, Gibb’s free energy, energy, and zero-point energy.http://www.degruyter.com/view/j/nbec.2018.17.issue-1/nbec-2018-0006/nbec-2018-0006.xml?format=INTEnsemble learningQuantitative structure-activity relationshipQuantum descriptors |
| spellingShingle | Janairo Jose Isagani B. Janairo Gerardo C. Co Frumencio F. A machine learning approach in predicting mosquito repellency of plant – derived compounds Nova Biotechnologica et Chimica Ensemble learning Quantitative structure-activity relationship Quantum descriptors |
| title | A machine learning approach in predicting mosquito repellency of plant – derived compounds |
| title_full | A machine learning approach in predicting mosquito repellency of plant – derived compounds |
| title_fullStr | A machine learning approach in predicting mosquito repellency of plant – derived compounds |
| title_full_unstemmed | A machine learning approach in predicting mosquito repellency of plant – derived compounds |
| title_short | A machine learning approach in predicting mosquito repellency of plant – derived compounds |
| title_sort | machine learning approach in predicting mosquito repellency of plant derived compounds |
| topic | Ensemble learning Quantitative structure-activity relationship Quantum descriptors |
| url | http://www.degruyter.com/view/j/nbec.2018.17.issue-1/nbec-2018-0006/nbec-2018-0006.xml?format=INT |
| work_keys_str_mv | AT janairojoseisaganib amachinelearningapproachinpredictingmosquitorepellencyofplantderivedcompounds AT janairogerardoc amachinelearningapproachinpredictingmosquitorepellencyofplantderivedcompounds AT cofrumenciof amachinelearningapproachinpredictingmosquitorepellencyofplantderivedcompounds AT janairojoseisaganib machinelearningapproachinpredictingmosquitorepellencyofplantderivedcompounds AT janairogerardoc machinelearningapproachinpredictingmosquitorepellencyofplantderivedcompounds AT cofrumenciof machinelearningapproachinpredictingmosquitorepellencyofplantderivedcompounds |