دورية أكاديمية
أعرض في EDS

Using transfer learning and dimensionality reduction techniques to improve generalisability of machine-learning predictions of mosquito ages from mid-infrared spectra.

التفاصيل البيبلوغرافية
العنوان: Using transfer learning and dimensionality reduction techniques to improve generalisability of machine-learning predictions of mosquito ages from mid-infrared spectra.
المؤلفون: Mwanga EP; Environmental Health and Ecological Sciences Department, Ifakara Health Institute, Morogoro, Tanzania. emwanga@ihi.or.tz.; School of Biodiversity, One Health, and Veterinary Medicine, University of Glasgow, Glasgow, G12 8QQ, UK. emwanga@ihi.or.tz., Siria DJ; Environmental Health and Ecological Sciences Department, Ifakara Health Institute, Morogoro, Tanzania., Mitton J; School of Biodiversity, One Health, and Veterinary Medicine, University of Glasgow, Glasgow, G12 8QQ, UK.; School of Computing Science, University of Glasgow, Glasgow, G12 8QQ, UK., Mshani IH; Environmental Health and Ecological Sciences Department, Ifakara Health Institute, Morogoro, Tanzania.; School of Biodiversity, One Health, and Veterinary Medicine, University of Glasgow, Glasgow, G12 8QQ, UK., González-Jiménez M; School of Chemistry, University of Glasgow, Glasgow, G12 8QQ, UK., Selvaraj P; Institute for Disease Modelling, Bellevue, WA, 98005, USA., Wynne K; School of Chemistry, University of Glasgow, Glasgow, G12 8QQ, UK., Baldini F; School of Biodiversity, One Health, and Veterinary Medicine, University of Glasgow, Glasgow, G12 8QQ, UK., Okumu FO; Environmental Health and Ecological Sciences Department, Ifakara Health Institute, Morogoro, Tanzania.; School of Biodiversity, One Health, and Veterinary Medicine, University of Glasgow, Glasgow, G12 8QQ, UK.; School of Public Health, University of Witwatersrand, Johannesburg, South Africa., Babayan SA; School of Biodiversity, One Health, and Veterinary Medicine, University of Glasgow, Glasgow, G12 8QQ, UK.
المصدر: BMC bioinformatics [BMC Bioinformatics] 2023 Jan 09; Vol. 24 (1), pp. 11. Date of Electronic Publication: 2023 Jan 09.
نوع المنشور: Journal Article
اللغة: English
بيانات الدورية: Publisher: BioMed Central Country of Publication: England NLM ID: 100965194 Publication Model: Electronic Cited Medium: Internet ISSN: 1471-2105 (Electronic) Linking ISSN: 14712105 NLM ISO Abbreviation: BMC Bioinformatics Subsets: MEDLINE
أسماء مطبوعة: Original Publication: [London] : BioMed Central, 2000-
مواضيع طبية MeSH: Anopheles* , Malaria*, Animals ; Adult ; Female ; Humans ; Mosquito Vectors ; Machine Learning
مستخلص: Background: Old mosquitoes are more likely to transmit malaria than young ones. Therefore, accurate prediction of mosquito population age can drastically improve the evaluation of mosquito-targeted interventions. However, standard methods for age-grading mosquitoes are laborious and costly. We have shown that Mid-infrared spectroscopy (MIRS) can be used to detect age-specific patterns in mosquito cuticles and thus can be used to train age-grading machine learning models. However, these models tend to transfer poorly across populations. Here, we investigate whether applying dimensionality reduction and transfer learning to MIRS data can improve the transferability of MIRS-based predictions for mosquito ages.
Methods: We reared adults of the malaria vector Anopheles arabiensis in two insectaries. The heads and thoraces of female mosquitoes were scanned using an attenuated total reflection-Fourier transform infrared spectrometer, which were grouped into two different age classes. The dimensionality of the spectra data was reduced using unsupervised principal component analysis or t-distributed stochastic neighbour embedding, and then used to train deep learning and standard machine learning classifiers. Transfer learning was also evaluated to improve transferability of the models when predicting mosquito age classes from new populations.
Results: Model accuracies for predicting the age of mosquitoes from the same population as the training samples reached 99% for deep learning and 92% for standard machine learning. However, these models did not generalise to a different population, achieving only 46% and 48% accuracy for deep learning and standard machine learning, respectively. Dimensionality reduction did not improve model generalizability but reduced computational time. Transfer learning by updating pre-trained models with 2% of mosquitoes from the alternate population improved performance to ~ 98% accuracy for predicting mosquito age classes in the alternative population.
Conclusion: Combining dimensionality reduction and transfer learning can reduce computational costs and improve the transferability of both deep learning and standard machine learning models for predicting the age of mosquitoes. Future studies should investigate the optimal quantities and diversity of training data necessary for transfer learning and the implications for broader generalisability to unseen datasets.
(© 2023. The Author(s).)
References: Wellcome Open Res. 2019 May 1;4:76. (PMID: 31544155)
Malar J. 2019 May 30;18(1):187. (PMID: 31146762)
Parasit Vectors. 2013 Oct 14;6(1):298. (PMID: 24499515)
Bioinformatics. 2021 Sep 09;:. (PMID: 34499112)
IEEE Trans Neural Netw. 2011 Feb;22(2):199-210. (PMID: 21095864)
Sci Rep. 2018 Mar 27;8(1):5274. (PMID: 29588452)
Monogr Ser World Health Organ. 1962;47:13-191. (PMID: 13885800)
Nat Commun. 2022 Mar 21;13(1):1501. (PMID: 35314683)
Nature. 2015 Oct 8;526(7572):207-211. (PMID: 26375008)
Am J Trop Med Hyg. 2009 Oct;81(4):622-30. (PMID: 19815877)
Parasit Vectors. 2018 Mar 12;11(1):178. (PMID: 29530073)
Sci Rep. 2018 Jun 25;8(1):9590. (PMID: 29941924)
BMC Bioinformatics. 2022 Jul 3;23(1):262. (PMID: 35786378)
Sci Rep. 2020 Dec 18;10(1):22295. (PMID: 33339842)
معلومات مُعتمدة: 214643/Z/18/Z United Kingdom Wellcome Trust; MR/P025501/1 United Kingdom Medical Research Council; MR/P025501/1 United Kingdom Medical Research Council; MR/P025501/1 United Kingdom Medical Research Council; MR/P025501/1 United Kingdom Medical Research Council; MR/P025501/1 United Kingdom Medical Research Council; MR/P025501/1 United Kingdom Medical Research Council
فهرسة مساهمة: Keywords: Anopheles arabiensis; Convolutional neural network; Dimensionality reduction; Generalisability; Standard machine learning; Transfer learning
تواريخ الأحداث: Date Created: 20230109 Date Completed: 20230111 Latest Revision: 20230112
رمز التحديث: 20231215
مُعرف محوري في PubMed: PMC9830685
DOI: 10.1186/s12859-022-05128-5
PMID: 36624386
قاعدة البيانات: MEDLINE
الوصف
تدمد:1471-2105
DOI:10.1186/s12859-022-05128-5