Emmanuel P. Mwanga

Emmanuel P. Mwanga

Auto-generated profile, based on publicly available information

Emmanuel P. Mwanga

Environmental Health and Ecological Sciences Department, Ifakara Health Institute, Morogoro, Tanzania

Research Focus & Metrics

Academic Career Length

8Years (2019-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
21 March 2022 in Nature Communications
Verified
Journal Article
Open access
PDF file
DSDoreen J. Siria
Doreen J. Siria
RSRoger SANOU
Roger SANOU
JMJoshua Mitton
Joshua Mitton
EMEmmanuel P. Mwanga
Emmanuel P. Mwanga
ANAbdoulaye Niang
Abdoulaye Niang
FBFrancesco Baldini
Francesco Baldini
The malaria parasite, which is transmitted by several Anopheles mosquito species, requires more time to reach its human-transmissible stage than the average lifespan of mosquito vectors. Monitoring the species-specific age structure of mosquito populations is critical to evaluating the impact of vector control interventions on malaria risk. We present a rapid, cost-effective surveillance method based on deep learning of mid-infrared spectra of mosquito cuticle that simultaneously identifies the species and age class of three main malaria vectors in natural populations. Using spectra from over 40, 000 ecologically and genetically diverse An. gambiae, An. arabiensis, and An. coluzzii females, we develop a deep transfer learning model that learns and predicts the age of new wild populations in Tanzania and Burkina Faso with minimal sampling effort. Additionally, the model is able to detect the impact of simulated control interventions on mosquito populations, measured as a shift in their age structures. In the future, we anticipate our method can be applied to other arthropod vector-borne diseases.

7 October 2019 in Malaria Journal
Verified
Journal Article
Open access
PDF file
EMEmmanuel P. Mwanga
Emmanuel P. Mwanga
EMElihaika G. Minja
Elihaika G. Minja
EMEmmanuel Mrimi
Emmanuel Mrimi
MJMario González Jiménez
Mario González Jiménez
Johnson Kyeba SwaiJohnson Kyeba Swai
Johnson Kyeba Swai
FOFredros Okumu
Fredros Okumu
Background: Epidemiological surveys of malaria currently rely on microscopy, polymerase chain reaction assays (PCR) or rapid diagnostic test kits for Plasmodium infections (RDTs). This study investigated whether mid-infrared (MIR) spectroscopy coupled with supervised machine learning could constitute an alternative method for rapid malaria screening, directly from dried human blood spots. Methods: Filter papers containing dried blood spots (DBS) were obtained from a cross-sectional malaria survey in 12 wards in southeastern Tanzania in 2018/19. The DBS were scanned using attenuated total reflection-Fourier Transform Infrared (ATR-FTIR) spectrometer to obtain high-resolution MIR spectra in the range 4000 cm−1 to 500 cm−1. The spectra were cleaned to compensate for atmospheric water vapour and CO2 interference bands and used to train different classification algorithms to distinguish between malaria-positive and malaria-negative DBS papers based on PCR test results as reference. The analysis considered 296 individuals, including 123 PCR-confirmed malaria positives and 173 negatives. Model training was done using 80% of the dataset, after which the best-fitting model was optimized by bootstrapping of 80/20 train/test-stratified splits. The trained models were evaluated by predicting Plasmodium falciparum positivity in the 20% validation set of DBS. Results: Logistic regression was the best-performing model. Considering PCR as reference, the models attained overall accuracies of 92% for predicting P. falciparum infections (specificity = 91.7%; sensitivity = 92.8%) and 85% for predicting mixed infections of P. falciparum and Plasmodium ovale (specificity = 85%, sensitivity = 85%) in the field-collected specimen. Conclusion: These results demonstrate that mid-infrared spectroscopy coupled with supervised machine learning (MIR-ML) could be used to screen for malaria parasites in human DBS. The approach could have potential for rapid and high-throughput screening of Plasmodium in both non-clinical settings (e.g., field surveys) and clinical settings (diagnosis to aid case management). However, before the approach can be used, we need additional field validation in other study sites with different parasite populations, and in-depth evaluation of the biological basis of the MIR signals. Improving the classification algorithms, and model training on larger datasets could also improve specificity and sensitivity. The MIR-ML spectroscopy system is physically robust, low-cost, and requires minimum maintenance.

18 September 2019 in Malaria Journal
Verified
Journal Article
Open access
PDF file
EMEmmanuel P. Mwanga
Emmanuel P. Mwanga
AMArnold S. Mmbando
Arnold S. Mmbando
PMPaul C. Mrosso
Paul C. Mrosso
Caleb SticaCaleb Stica
Caleb Stica
SMSalum A. Mapua
Salum A. Mapua
FOFredros O. Okumu
Fredros O. Okumu
Background: Eave ribbons treated with spatial repellents effectively prevent human exposure to outdoor-biting and indoor-biting malaria mosquitoes, and could constitute a scalable and low-cost supplement to current interventions, such as insecticide-treated nets (ITNs). This study measured protection afforded by transfluthrin-treated eave ribbons to users (personal and communal protection) and non-users (only communal protection), and whether introducing mosquito traps as additional intervention influenced these benefits. Methods: Five experimental huts were constructed inside a 110 m long, screened tunnel, in which 1000 Anopheles arabiensis were released nightly. Eave ribbons treated with 0.25 g/m2 transfluthrin were fitted to 0, 1, 2, 3, 4 or 5 huts, achieving 0, 20, 40, 60, 80 and 100% coverage, respectively. Volunteers sat near each hut and collected mosquitoes attempting to bite them from 6 to 10 p.m. (outdoor-biting), then went indoors to sleep under untreated bed nets, beside which CDC-light traps collected mosquitoes from 10 p.m. to 6 a.m. (indoor-biting). Caged mosquitoes kept inside the huts were monitored for 24 h-mortality. Separately, eave ribbons, UV–LED mosquito traps (Mosclean) or both the ribbons and traps were fitted, each time leaving the central hut unfitted to represent non-user households and assess communal protection. Biting risk was measured concurrently in all huts, before and after introducing interventions. Results: Transfluthrin-treated eave ribbons provided 83% and 62% protection indoors and outdoors respectively to users, plus 57% and 48% protection indoors and outdoors to the non-user. Protection for users remained constant, but protection for non-users increased with eave ribbons coverage, peaking once 80% of huts were fitted. Mortality of mosquitoes caged inside huts with eave ribbons was 100%. The UV–LED traps increased indoor exposure to users and non-users, but marginally reduced outdoor-biting. Combining the traps and eave ribbons did not improve user protection relative to eave ribbons alone. Conclusion: Transfluthrin-treated eave ribbons protect both users and non-users against malaria mosquitoes indoors and outdoors. The mosquito-killing property of transfluthrin can magnify the communal benefits by limiting unwanted diversion to non-users, but should be validated in field trials against pyrethroid-resistant vectors. Benefits of the UV–LED traps as an intervention alone or alongside eave ribbons were however undetectable in this study. These findings extend the evidence that transfluthrin-treated eave ribbons could complement ITNs.

27 August 2019 in Parasites & Vectors
Verified
Journal Article
Open access
PDF file
EMEmmanuel P. Mwanga
Emmanuel P. Mwanga
HNHalfan S. Ngowo
Halfan S. Ngowo
SMSalum A. Mapua
Salum A. Mapua
AMArnold S. Mmbando
Arnold S. Mmbando
EKEmmanuel W. Kaindoa
Emmanuel W. Kaindoa
FOFredros Okumu
Fredros Okumu
Improved surveillance techniques are required to accelerate efforts against major arthropod-borne diseases such as malaria, dengue, filariasis, Zika and yellow-fever. Light-emitting diodes (LEDs) are increasingly used in mosquito traps because they improve energy efficiency and battery longevity relative to incandescent bulbs. This study evaluated the efficacy of a new ultraviolet LED trap (Mosclean) against standard mosquito collection methods. The study was conducted in controlled semi-field settings and in field conditions in rural south-eastern Tanzania. The Mosclean trap was compared to commonly used techniques, namely CDC-light traps, human landing catches (HLCs), BG-Sentinel traps and Suna traps. When simultaneously placed inside the same semi-field chamber, the Mosclean trap caught twice as many Anopheles arabiensis as the CDC-light trap, and equal numbers to HLCs. Similar results were obtained when traps were tested individually in the chambers. Under field settings, Mosclean traps caught equal numbers of An. arabiensis and twice as many Culex mosquitoes as CDC-light traps. It was also better at trapping malaria vectors compared to both Suna and BG-Sentinel traps, and was more efficient in collecting mosquitoes indoors than outdoors. The majority of An. arabiensis females caught by Mosclean traps were parous (63.6%) and inseminated (89.8%). In comparison, the females caught by CDC-light traps were 43.9% parous and 92.8% inseminated. The UV LED trap (Mosclean trap) was efficacious for sampling Anopheles and Culex mosquitoes. Its efficacy was comparable to and in some instances better than traps commonly used for vector surveillance. The Mosclean trap was more productive in sampling mosquitoes indoors compared to outdoors. The trap can be used indoors near human-occupied nets, or outdoors, in which case additional CO2 improves catches. We conclude that this trap may have potential for mosquito surveillance. However, we recommend additional field tests to validate these findings in multiple settings and to assess the potential of LEDs to attract non-target organisms, especially outdoors.

30 May 2019 in Malaria Journal
Verified
Journal Article
Open access
PDF file
EMEmmanuel P. Mwanga
Emmanuel P. Mwanga
SMSalum A. Mapua
Salum A. Mapua
DSDoreen J. Siria
Doreen J. Siria
HNHalfan S. Ngowo
Halfan S. Ngowo
FNFrancis Nangacha
Francis Nangacha
FOFredros O. Okumu
Fredros O. Okumu
The propensity of different Anopheles mosquitoes to bite humans instead of other vertebrates influences their capacity to transmit pathogens to humans. Unfortunately, determining proportions of mosquitoes that have fed on humans, i.e. Human Blood Index (HBI), currently requires expensive and time-consuming laboratory procedures involving enzyme-linked immunosorbent assays (ELISA) or polymerase chain reactions (PCR). Here, mid-infrared (MIR) spectroscopy and supervised machine learning are used to accurately distinguish between vertebrate blood meals in guts of malaria mosquitoes, without any molecular techniques. Laboratory-reared Anopheles arabiensis females were fed on humans, chickens, goats or bovines, then held for 6 to 8 h, after which they were killed and preserved in silica. The sample size was 2000 mosquitoes (500 per host species). Five individuals of each host species were enrolled to ensure genotype variability, and 100 mosquitoes fed on each. Dried mosquito abdomens were individually scanned using attenuated total reflection-Fourier transform infrared (ATR-FTIR) spectrometer to obtain high-resolution MIR spectra (4000 cm−1 to 400 cm−1). The spectral data were cleaned to compensate atmospheric water and CO2 interference bands using Bruker-OPUS software, then transferred to Python™ for supervised machine-learning to predict host species. Seven classification algorithms were trained using 90% of the spectra through several combinations of 75–25% data splits. The best performing model was used to predict identities of the remaining 10% validation spectra, which had not been used for model training or testing. The logistic regression (LR) model achieved the highest accuracy, correctly predicting true vertebrate blood meal sources with overall accuracy of 98.4%. The model correctly identified 96% goat blood meals, 97% of bovine blood meals, 100% of chicken blood meals and 100% of human blood meals. Three percent of bovine blood meals were misclassified as goat, and 2% of goat blood meals misclassified as human. Mid-infrared spectroscopy coupled with supervised machine learning can accurately identify multiple vertebrate blood meals in malaria vectors, thus potentially enabling rapid assessment of mosquito blood-feeding histories and vectorial capacities. The technique is cost-effective, fast, simple, and requires no reagents other than desiccants. However, scaling it up will require field validation of the findings and boosting relevant technical capacity in affected countries.

9 January 2023 in BMC Bioinformatics
Verified
Journal Article
Open access
PDF file
EMEmmanuel P. Mwanga
Emmanuel P. Mwanga
DSDoreen J. Siria
Doreen J. Siria
JMJoshua Mitton
Joshua Mitton
IMIssa H. Mshani
Issa H. Mshani
MGMario González-Jiménez
Mario González-Jiménez
SBSimon A. Babayan
Simon A. Babayan
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.