Skip to main content
PLOS One logoLink to PLOS One
. 2020 Jun 18;15(6):e0234557. doi: 10.1371/journal.pone.0234557

An autoencoder and artificial neural network-based method to estimate parity status of wild mosquitoes from near-infrared spectra

Masabho P Milali 1,2,*, Samson S Kiware 1,2, Nicodem J Govella 2, Fredros Okumu 2, Naveen Bansal 1, Serdar Bozdag 3, Jacques D Charlwood 4, Marta F Maia 5,6,7, Sheila B Ogoma 8, Floyd E Dowell 9, George F Corliss 1,10, Maggy T Sikulu-Lord 11,#, Richard J Povinelli 1,10,#
Editor: Jie Zhang12
PMCID: PMC7302571  PMID: 32555660

Abstract

After mating, female mosquitoes need animal blood to develop their eggs. In the process of acquiring blood, they may acquire pathogens, which may cause different diseases in humans such as malaria, zika, dengue, and chikungunya. Therefore, knowing the parity status of mosquitoes is useful in control and evaluation of infectious diseases transmitted by mosquitoes, where parous mosquitoes are assumed to be potentially infectious. Ovary dissections, which are currently used to determine the parity status of mosquitoes, are very tedious and limited to few experts. An alternative to ovary dissections is near-infrared spectroscopy (NIRS), which can estimate the age in days and the infectious state of laboratory and semi-field reared mosquitoes with accuracies between 80 and 99%. No study has tested the accuracy of NIRS for estimating the parity status of wild mosquitoes. In this study, we train an artificial neural network (ANN) models on NIR spectra to estimate the parity status of wild mosquitoes. We use four different datasets: An. arabiensis collected from Minepa, Tanzania (Minepa-ARA); An. gambiae s.s collected from Muleba, Tanzania (Muleba-GA); An. gambiae s.s collected from Burkina Faso (Burkina-GA); and An.gambiae s.s from Muleba and Burkina Faso combined (Muleba-Burkina-GA). We train ANN models on datasets with spectra preprocessed according to previous protocols. We then use autoencoders to reduce the spectra feature dimensions from 1851 to 10 and re-train the ANN models. Before the autoencoder was applied, ANN models estimated parity status of mosquitoes in Minepa-ARA, Muleba-GA, Burkina-GA and Muleba-Burkina-GA with out-of-sample accuracies of 81.9±2.8 (N = 274), 68.7±4.8 (N = 43), 80.3±2.0 (N = 48), and 75.7±2.5 (N = 91), respectively. With the autoencoder, ANN models tested on out-of-sample data achieved 97.1±2.2% (N = 274), 89.8 ± 1.7% (N = 43), 93.3±1.2% (N = 48), and 92.7±1.8% (N = 91) accuracies for Minepa-ARA, Muleba-GA, Burkina-GA, and Muleba-Burkina-GA, respectively. These results show that a combination of an autoencoder and an ANN trained on NIR spectra to estimate the parity status of wild mosquitoes yields models that can be used as an alternative tool to estimate parity status of wild mosquitoes, especially since NIRS is a high-throughput, reagent-free, and simple-to-use technique compared to ovary dissections.

Introduction

Evaluation of existing malaria control interventions such as insecticide-treated nets (ITNs) and indoor residual spraying (IRS) relies upon, among other factors, the assessment of the changes occurring in the mosquito parity structure prior to and after implementation of an intervention [13]. The parity status of mosquitoes corresponds with their capability to transmit Plasmodium parasites, with an assumption that parous mosquitoes are more highly capable than nulliparous mosquitoes, as they may have accessed parasite-infected blood. A shift in the parity structure towards a population with more nulliparous mosquitoes signifies a reduction in the risk of disease transmission [2, 4, 5], as the chances that mosquitoes carry the malaria parasite declines [6].

The current standard technique for estimating the parity status of female mosquitoes involves dissection of their ovaries to separate mosquitoes into those that have previously laid eggs, known as the parous group (assumed to be old and potentially infectious), and those that do not have a gonotrophic history, known as the nulliparous group (assumed to be young and non-infectious) [7]. Another standard technique also based on the dissection of ovaries determines the number of times a female mosquito has laid eggs [8]. However, both techniques are laborious, time consuming, and require skilled technicians. These technical difficulties lead to analysis of small sample sizes that often fail to capture the heterogeneity of a mosquito population.

Near infrared spectroscopy (NIRS) complimented by techniques from machine learning, have been demonstrated to be alternative tools for predicting age, species, and infectious status of laboratory and semi-field raised mosquitoes [920]. NIRS is a rapid, non-invasive, reagent-free technique that requires minimal skills to operate, allowing hundreds of samples to be analyzed in a day. However, the accuracy of NIRS techniques for predicting the parity status of wild mosquitoes has not been tested. Moreover, recently, it has been reported that models trained on NIR spectra using an artificial neural network (ANN) estimate the age of laboratory-reared An. arabiensis, An.gambiae, Aedes aegypti, and Aedes albopictus with accuracies higher than models trained on NIR spectra using partial least squares (PLS) [20].

In this study, we train ANN models on NIR spectra preprocessed according to an existing protocol [9] to estimate the parity status of wild An. gambiae s.s. and An. arabiensis. We then apply autoencoders to reduce the spectra feature space from 1851 to 10 and re-train ANN models. The ANN model achieved an average accuracy of 72% and 93% before and after applying the autoencoder, respectively. These results suggest ANN models trained on autoencoded NIR spectra as an alternative tool to estimate the parity status of wild An. gambiae and An. arabiensis. High-throughput, non-invasive, reagent free, and simple to use NIRS analyses compliment the limitations of ovary dissections.

Materials and methods

Ethics approvals

Ethics approvals for collecting mosquitoes in Minepa-ARA, Burkina-GA and Muleba-GA datasets from residents’ homes were obtained from Ethics Review Boards of the Ifakara Health Institute (IHI-IRB/No. 17–2015), the Colorado State University (approval No. 09-1148H), and the Kilimanjaro Christian Medical College (Certificate No. 781), respectively.

Data

We use data from wild An. arabiensis (Minepa-ARA) collected from Minepa, a village in southeastern Tanzania (published in [21] and publicly available for reuse), from wild An. gambiae s.s (Muleba-GA) collected from Muleba, northwestern Tanzania (mosquitoes published in [22], permission to reuse was obtained from the senior author) and from wild An. gambiae s.s collected from Bougouriba and Diarkadou-gou villages in Burkina Faso (Burkina-GA) (published in [12] and publicly available for reuse).

Mosquitoes in the Minepa-ARA and Muleba-GA datasets were captured using CDC light traps placed inside residential homes. Mosquitoes that were morphologically identified as members of the Anopheles gambiae complex were processed further. Prior to scanning, wild mosquitoes collected in Minepa were killed by freezing them for 20 minutes in a freezer that is calibrated to -20º C. After freezing the mosquitoes were re-equilibrated to room temperature for 30 minutes. Wild mosquitoes collected in Muleba were killed using 75% ethanol, dissected according to the technique described by Detinova [23] to determine their parity status, and preserved in silica gel. Mosquitoes in Minepa-ARA were dissected after scanning. Following a previous published protocol to collect spectra [9], mosquitoes in both Minepa-ARA and Muleba-GA were scanned using a LabSpec 5000 near-infrared spectrometer with an integrated light source (ASD Inc., Malvern, UK). After spectra collection, mosquitoes in Minepa-ARA were dissected to score their parity status. Then polymerase chain reaction (PCR) was conducted on DNA extracted from mosquito legs (in both Minepa-ARA and Muleba-GA) to identify species type as previously described [24]. Each mosquito was labeled with a unique identifier code linking each NIR spectrum to parity dissection and PCR information.

Data from wild An. gambiae s.s from Burkina Faso were published in [12] and publicly available for reuse. These mosquitoes are referred to as independent test sets 2 and 3 (ITS 2 and ITS 3) in [12]. ITS 2 has 40 nulliparous and 40 parous mosquitoes, and ITS 3 has 40 nulliparous and 38 parous mosquitoes. In this study, we combine these two datasets into one dataset and refer it as Burkina-GA. Mosquitoes in Burkina-GA (N = 158) were collected in 2013 in Burkina Faso from Bougouriba and Diarkadou-gou villages using either indoor aspiration or a human baited tent trap, and their ovaries were dissected according to the Detinova method [23]. Mosquitoes were preserved in silica gel before their spectra were collected using a LabSpec4i spectrometer (ASD Inc., Boulder, CO, USA).

Model training and testing

We trained models on four datasets, namely Minepa-ARA, Muleba-GA, Burkina-GA, and Muleba-Burkina-GA (Muleba-GA and Burkina-GA combined). Before training models, spectra in all datasets were pre-processed according to the previously published protocol [9] and divided into two groups (nulliparous and parous). Spectra in the nulliparous and parous groups were labeled zero and one, respectively. The two groups were then merged, randomized, and divided into a training set (75%; N = 927 for Minepa-ARA, N = 140 for the Muleba-GA, N = 158 for Burkina-GA and N = 298 for Muleba-Burkina-GA) and a test set (the remaining 25% in each dataset). On each dataset, using ten Monte-Carlo cross validations [20, 25] and Levenberg-Marquardt optimization, a one hidden layer, ten-neuron feed-forward ANN model with logistic regression as a transfer function was trained and tested in MATLAB (Fig 1).

Fig 1. Training and testing ANN model on spectra preprocessed according to Mayagaya et al. [9].

Fig 1

M” is either Minepa-ARA, Muleba-GA, Burkina-GA, or Muleba-Burkina-GA.

Based on the accuracy of the model presented in Table 1 in the Results and Discussion section, we explored how to improve the model accuracy. Normally a parous class, unlike a nulliparous class, often is represented by a limited number of samples, posing a problem of data imbalance during model training. In this case, a large amount of data is required to obtain enough samples in a parous class for a model to learn and characterize it accurately. Obtaining enough data for model training is always challenging. The most common ways of dealing with the data imbalance are either to discard samples from a nulliparous class to equal the number of samples in a parous class or to bootstrap samples in a parous class [26]. However, discarding data to equalize the data distribution in two classes in the training set leaves an imbalanced test set. Also, it is this imbalanced scenario to which the model will be applied in real cases. In addition, throwing away samples, especially from data sets with a high dimension feature space, can lead to over-fitting the model. Alternatively, for datasets with a high dimension feature space, instead of discarding data from a class with a large number of samples, feature reduction techniques are employed [26]. Feature reduction reduces the size of the hypothesis space initially presented in the original data, thereby reducing the size of data required to adequately train the model. Principal component analysis (PCA) and partial least squares (PLS) are the commonly used unsupervised and supervised feature reduction methods, respectively, especially for cases whose features are linearly related [27, 28]. Autoencoders recently are used as an alternative to PCA in cases involving both linear and non-linear relationships [2932].

Table 1. Accuracies of reconstructing original feature spaces from encoded feature spaces.

MSE = mean square error.

Metric Steps Encoded-Minepa-ARA Encoded-Muleba-GA Encoded-Burkina-GA
MSE Step 1 0.0046 0.0029 0.0031
Step 2 0.00005 0.0027 0.0022
Step 3 0.00008 0.0029 0.0011

An autoencoder is an unsupervised ANN that learns both linear and non-linear relationships present in data and represents them in a new reduced dimension data space (which also can be used to regenerate the original data space) without losing important information [3335]. The autoencoder has two parts, the encoder part, where an original dataset is encoded to a desired reduced feature space (encoded dataset) and the decoder part where the encoded dataset is decoded to an original dataset to determine how accurately the encoded dataset represents the original dataset. Fig 2 illustrates an example of an autoencoder in which an 1850-feature dataset is stepwise encoded to a 10-feature dataset. There is no formula for the number and size of steps to take to get to a desired feature size. However, taking several steps results on losing very little information, compared with taking a single step.

Fig 2. Autoencoder reducing feature space dimension.

Fig 2

Once an encoded feature space can reconstruct the original feature space with an acceptable accuracy, the decoder is detached, and a desired model (in our case an ANN binary classifier) is trained on the encoded feature space as shown in Fig 3.

Fig 3. ANN model trained on a dataset with an encoded feature space.

Fig 3

Egg laying appears to be affected by both linear and non-linear relationships. Hence, we separately train autoencoders on the Minepa-ARA, Muleba-GA, Burkina-GA, and Muleba-Burkina-GA datasets to reduce spectra feature dimensions from 1851 to 10 (Fig 4).

Fig 4. Reducing spectra feature space using an autoencoder and re-constructing original feature spaces from their respective encoded feature spaces (reconstruction accuracies presented in Table 1).

Fig 4

Figures generated from MATLAB.

Table 1 presents accuracies of reconstructing original feature spaces from their respective encoded feature spaces. We refer to the autoencoded Minepa-ARA, Muleba-GA, Burkina-GA, and Muleba-Burkina-GA datasets as Encoded-Minepa-ARA, Encoded-Muleba-GA, Encoded-Burkina-GA, and Encoded-Muleba-Burkina-GA, respectively. We then train ANN models on Encoded-Minepa-ARA, Encoded-Muleba-GA, Encoded-Burkina-GA, and Encoded-Muleba-Burkina-GA (Fig 5).

Fig 5. Training and testing of ANN model on autoencoded spectra.

Fig 5

M is either Minepa-ARA, Muleba-GA, Burkina-GA, or Muleba-Burkina-GA dataset.

Finally, we used the Encoded-Burkina-GA and the Encoded-Muleba-GA datasets as independent test sets to test accuracies of ANN models trained on the Encoded-Muleba-GA dataset and on the Encoded-Burkina-GA dataset, respectively (Fig 6A and 6B).

Fig 6. Independent testing of ANN model trained on encoded datasets.

Fig 6

A) Applying an ANN model trained on the Encoded-Muleba-GA dataset to estimate the parity status of mosquitoes in the autoencoded Burkina-GA dataset. B) Applying the ANN model trained on the Encoded-Burkina-GA dataset to estimate the parity status of mosquitoes in the Encoded-Muleba-GA dataset.

Results and discussion

In this study, we demonstrated that near-infrared spectroscopy (NIRS) can estimate accurately the parity status of wild collected An. arabiensis and An. gambiae s.s. Referring to the published results in [11] (ANN models achieve higher accuracies than PLS models), we trained and tested an ANN model on NIRS spectra in four different datasets, pre-processed according to a previously published protocol [9]. The model achieved accuracies between 68.7 and 81.9% (Table 2, Figs 7 and 8). Table 2 further presents various metrics to score the performance of our classifiers, namely sensitivity, specificity, precision, and area under the receiver operating characteristic (ROC) curve (AUC). We calculated sensitivity, specificity, precision and accuracy of the model using Equs 1, 2, 3, and 4, respectively [3639]. Sensitivity (also known as recall) is the percentage of correctly predicted parous mosquitoes, specificity is the percentage of correctly predicted nulliparous mosquitoes [20], and precision is the proportion of true parous mosquitoes out of all mosquitoes estimated by the model as parous [39]. We presented both sensitivity and precision because different scholars prefer one metric to another especially for cases with imbalanced data [39].

Table 2. Performance of an ANN model trained on 75% of mosquito spectra with 1851 features (before autoencoder) and tested on the remaining 25% spectra (out of the sample testing).

AUC values are the area of the ROC curves in Fig 8. Minepa-ARA (Nulliparous = 656, Parous = 271), Muleba-GA (Nulliparous = 119, Parous = 21) Burkina-GA (Nulliparous = 80, Parous = 78).

Minepa-ARA (N = 927) Muleba-GA (N = 140) Burkina-GA (N = 158) Muleba-Burkina-GA (N = 298)
Accuracy (%) 81.9 ± 2.8 68.7 ± 4.8 80.3 ± 2.0 75.7 ± 2.5
Sensitivity (%) 79.7 ± 3.2 37.8 ± 6.6 76.5 ± 2.1 70.2 ± 3.1
Specificity (%) 86.0 ± 1.6 80.1 ± 2.7 88.3 ± 2.3 77.6 ± 2.9
Precision (%) 74.3 ± 3.4 31.3 ± 5.2 77.8 ± 1.8 68.8 ± 3.2
AUC (%) 77.2 55.9 83.6 76.4

Fig 7. Box plots of parity estimation score when ANN models trained on 75% of spectra before the autoencoder was applied and tested on the remaining spectra (25%) (out of the sample testing).

Fig 7

A, B, C, and D represent results for the Minepa-ARA, Muleba-GA, Burkina-GA, and Muleba-Burkina-GA (mosquitoes in Muleba-GA and Burkina-GA datasets combined) datasets, respectively.

Fig 8. ROC curves (AUCs presented in the last row of Table 2) showing results when ANN models trained on 75% of spectra before the autoencoder was applied and tested on the remaining spectra (25%) (out of the sample testing).

Fig 8

A, B, C, and D represent results for the Minepa-ARA, Muleba-GA, Burkina-GA, and Muleba-Burkina-GA (mosquitoes in Muleba-GA and Burkina-GA datasets combined) datasets, respectively. In each ROC curve, a threshold of 0.5 was used to compute true positive rate and false positive rate.

Let

  • True Positive (TP) = Number of mosquitoes correctly classified by the model as parous,

  • False Positive (FP) = Number of mosquitoes wrongly classified by the model as parous,

  • True Negative (TN) = Number of mosquitoes correctly classified by the model as nulliparous,

  • Positive (P) = Total number of mosquitoes in test set that are parous, and

  • Negative (N) = Total number of mosquitoes in test set that are nulliparous.

Then

Sensitivity=TPP, (1)
Specificity=TNN, (2)
Accuracy=TP+TNP+N,and (3)
Precision=TPTP+FP. (4)

AUC was computed from the receiver operating characteristic (ROC) curve shown in Fig 8 generated by plotting the true parous rate against the false parous rate at different threshold settings. A higher AUC is interpreted as higher predictivity performance of the model [40, 41]. The ROC curve normally presents the performance of the model at different thresholds (cut off points), providing more information on the accuracy of the classifier [40, 41]. Table 3 provides confusion matrices from the last (tenth) Monte-Carlo cross validation showing model accuracy in absolute values.

Table 3. Confusion matrices showing accuracies of the models in absolute values when the models were trained on spectra before feature reduction by autoencoder.

A) Minepa-ARA, B) Muleba-GA, C) Burkina-GA and D) Muleba-Burkina-GA. Results from the last Monte-Carlo cross validation.

Actual Parity
Estimates Nulliparous Parous Total
Nulliparous 165 17 182
A Parous 31 61 92
Total 196 78 274
Nulliparous 28 4 32
B Parous 8 3 11
Total 36 7 43
Nulliparous 20 6 26
C Parous 4 18 22
Total 24 24 48
Nulliparous 46 9 55
D Parous 14 22 36
Total 60 31 91

We hypothesized that results presented in Tables 2 and 3, and in Figs 7 and 8 were influenced by the size of a dataset used to train the model. The model that was trained on a dataset with a relatively larger number of mosquitoes, especially in the parous class, performed better than the model trained on the dataset with fewer mosquitoes.

The current standard preprocessing technique [9] leaves a mosquito spectrum with an 1851- dimensional feature space. Mathematically, binary inputs with a 1851-dimensional feature space present 22(1851) hypothesis space dimensions for the model to learn [4244]. Successful learning of such hypothesis space dimensions requires many data points (mosquitoes in our case). Finding enough wild mosquitoes, especially parous mosquitoes, for a model to learn such a hypothesis space is expensive and time consuming. Feature reduction is an alternative to overcome this, as it reduces the hypothesis space dimension initially presented by the original data, hence lowering the number of data required to train the model efficiently. Techniques such as principal component analysis (PCA) [27, 28], partial least squares (PLS) [27, 45, 46], singular value decomposition (SVD) [30, 46, 47], and autoencoders can reduce a feature space to a size that can be learned by the available data without losing important information. PCA, PLS, and SVD are commonly used when features are linearly dependent [27, 28], otherwise, an autoencoder, which can be thought as a nonlinear version of PCA, is used [2932].

Therefore, we applied an autoencoder as illustrated in Figs 2 and 4 to reduce the spectra feature space from 1851 features to 10 features (Table 1 presents the accuracies of reconstructing original feature spaces from the encoded (reduced) feature spaces), cutting down the hypothesis space dimensions from 22(1851) to 22(10), and re-trained ANN models (Figs 3 and 5). As presented in Tables 4 and 5, and in Figs 9 and 10, the accuracy of the model improved from an average of 72% to 93%, suggesting an ANN model trained on autoencoded NIR spectra as an appropriate tool to estimate the parity status of wild mosquitoes.

Table 4. Performance of an ANN model trained on 75% of the encoded mosquito spectra (10 features) and tested on the remaining 25% of the encoded mosquito spectra.

AUC values are the area of the ROC curves in Fig 10. Minepa-ARA (Nulliparous = 656, Parous = 271), Muleba-GA (Nulliparous = 119, Parous = 21), Burkina-GA (Nulliparous = 80, Parous = 78).

Minepa-ARA (N = 927) Muleba-GA (N = 140) Burkina-GA (N = 158) Muleba-Burkina-GA (N = 298)
Accuracy (%) 97.1 ± 2.2 89.8 ± 1.7 93.3 ± 1.2 92.7 ± 1.8
Sensitivity (%) 94.9 ± 1.6 70.1 ± 2.3 91.7 ± 1.9 88.2 ± 2.9
Specificity (%) 98.6 ± 1.3 96.9 ± 1.2 96.4 ± 1.6 94.7 ± 2.1
Precision (%) 93.7 ± 2.4 62.5 ± 3.2 91.3 ± 1.4 93.1 ± 2.5
AUC (%) 96.7 91.5 93.1 94.9

Table 5. Confusion matrices showing accuracies of the models in absolute values when the models were trained on spectra after feature reduction by autoencoder.

A) Minepa-ARA, B) Muleba-GA, C) Burkina-GA, and D) Muleba-Burkina-GA. Results from the last Monte-Carlo cross validation.

Actual Parity
Estimates Nulliparous Parous Total
Nulliparous 192 7 199
A Parous 4 71 95
Total 196 78 274
Nulliparous 33 2 35
B Parous 3 5 8
Total 36 7 43
Nulliparous 22 3 25
C Parous 2 21 23
Total 24 24 48
Nulliparous 58 4 62
D Parous 2 27 29
Total 60 31 91

Fig 9. Box plots showing results when ANN models trained on 75% of encoded spectra in datasets were tested on the remaining encoded spectra (25%).

Fig 9

A, B, C, and D represent results for the Encoded-Minepa-ARA, Encoded-Muleba-GA, Encoded-Burkina-GA, and Encoded-Muleba & Burkina-GA (mosquitoes in Encoded-Muleba-GA and Encoded-Burkina-GA datasets combined) datasets, respectively.

Fig 10. ROC curves (AUCs presented in the last row of Table 4) showing results when ANN models trained on 75% of encoded spectra were tested on the remaining encoded spectra (25%).

Fig 10

A, B, C, and D represent results for the Encoded-Minepa-ARA, Encoded-Muleba-GA, Encoded-Burkina-GA, and Encoded-Muleba-Burkina-GA (mosquitoes in Encoded-Muleba-GA and Encoded-Burkina-GA datasets combined) datasets, respectively. In all ROC curves, a 0.5 threshold was used to calculate false positive rate and true positive rate.

We further applied a model trained on encoded Muleba-GA dataset to estimate the parity status of mosquitoes in the encoded Burkina-GA dataset and a model trained on encoded Burkina-GA dataset to estimate the parity status of mosquitoes in encoded Muleba-GA. Here we wanted to test how the model performs on mosquitoes from different cohorts. As presented in Table 6, the model performed with accuracies of 68.6% and 88.3%, respectively, showing a model trained on encoded Burkina-GA dataset extrapolates well to mosquitoes from a different cohort than a model trained on the encoded Muleba-GA dataset.

Table 6. Independent testing of ANN models trained on Muleba-GA and Burkina-GA encoded datasets.

ANN model trained on Encoded-Muleba-GA, tested on Encoded-Burkina-GA ANN model trained on Encoded-Burkina-GA, tested on Encoded-Muleba-GA
Accuracy (%) 68.6 88.3
Sensitivity (%) 26.5 86.1
Specificity (%) 94.4 92.2

A possible explanation of the results shown in Table 6 could be that, unlike for the Burkina-GA dataset, the number of parous mosquitoes (N = 21) in the Muleba-GA dataset was not representative enough for a model to learn important characteristics that extrapolate to mosquitoes in a cohort other than the one used to train the model. Although the Muleba-GA model had the poor sensitivity as presented in Table 6, the Burkina-GA model results still suggest that ANN model trained on acceptable number of both encoded parous and nulliparous can be applied to estimate parity status of mosquitoes from different cohorts other than the one used to train the model.

Conclusion

These results suggest that applying autoencoders and artificial neural networks to NIRS spectra as an appropriate complementary method to ovary dissections to estimate parity status of wild mosquitoes. The high-throughput nature of near-infrared spectroscopy provides a statistically acceptable sample size to draw conclusions on parity status of a particular wild mosquito population. Before this method can be used as a stand-alone method to estimate the parity status of wild mosquitoes, we suggest repeating of the analysis on different datasets with much larger mosquito sample sizes to test the reproducibility of the results. Hence, with the results presented in this manuscript, we recommend complementing ovary dissection with ANN models trained on NIRS spectra with their feature reduced by an autoencoder to estimate parity status of wild mosquito population.

Supporting information

S1 Appendix. Zip folder with Minepa-ARA, Muleba-GA and Burkina-GA datasets.

Column header, wavelengths in ‘nm’.

(ZIP)

Acknowledgments

We extend our gratitude to Benjamin Krajacich for allowing us to use his already-published datasets (Burkina-GA dataset) in our analyses; the USDA, Agricultural Research Service, Center for Grain and Animal Health Research, USA for loaning us the near-infrared spectrometer used to scan the mosquitoes; and Gustav Mkandawile who worked tirelessly to make sure we obtained mosquitoes in the Minepa-ARA and Muleba-GA datasets.

Mention of trade names or commercial products in this publication is solely for the purpose of providing specific information and does not imply recommendation or endorsement by the U.S. Department of Agriculture. USDA is an equal opportunity provider and employer.

Data Availability

All relevant data are within the manuscript and its Supporting Information files.

Funding Statement

Data collection was funded by: Grand Challenges Canada Stars for Global Health funded by the government of Canada grant 043901 awarded to MTSL; DFID/MRC/Wellcome Trust through the Joint Health Trials Scheme awarded to JDC (Award Number MR/L004437/1); National Institute of Allergy and Infectious Diseases grant R01-AI094349-01A1; and Marquette University Graduate School, for studentship awarded to MPM.

References

  • 1.Robert V, Carnevale P. Influence of Deltamethrin Treatment of Bed Nets on Malaria Transmission in the Kou valley, Burkina Faso. Bull World Health Organ. 1991;69(6):735 [PMC free article] [PubMed] [Google Scholar]
  • 2.Coleman S, Dadzie SK, Seyoum A, Yihdego Y, Mumba P, Dengela D, et al. A Reduction in Malaria Transmission Intensity in Northern Ghana After 7 Years of Indoor Residual Spraying. Malaria Journal. 2017;16(1):324 10.1186/s12936-017-1971-0 [DOI] [PMC free article] [PubMed] [Google Scholar]
  • 3.Magesa SM, Wilkes TJ, Mnzava A, Njunwa KJ, Myamba J, Kivuyo M, et al. Trial of Pyrethroid Impregnated Bednets in An Area of Tanzania Holoendemic for Malaria Part 2. Effects on the Malaria Vector Population. Acta Trop. 1991;49(2):97–108. 10.1016/0001-706x(91)90057-q [DOI] [PubMed] [Google Scholar]
  • 4.Dye C. The Analysis of Parasite Transmission by Bloodsucking Insects. Annu Rev Entomol. 1992;37(1):1–19. [DOI] [PubMed] [Google Scholar]
  • 5.Garrett-Jones C. Prognosis for Interruption of Malaria Transmission Through Assessment of the Mosquito's Vectorial Capacity. Nature. 1964;204(4964):1173–5. [DOI] [PubMed] [Google Scholar]
  • 6.Beier JC. Malaria Parasite Development in Mosquitoes. Annu Rev Entomol. 1998;43(1):519–43. [DOI] [PubMed] [Google Scholar]
  • 7.Detinova TS. Age Grouping Methods in Diptera of Medical Importance With Special Reference to Some Vectors of Malaria. Monogr Ser World Health Organization. 1962; 47:13–108 [PubMed] [Google Scholar]
  • 8.Polovodova VP. Age Changes in Ovaries of Anopheles and Methods of Determination of Age Composition in Mosquito Populations. Med Parazit (Mosk). 1941;10:387. [Google Scholar]
  • 9.Mayagaya VS, Michel K, Benedict MQ, Killeen GF, Wirtz RA, Ferguson HM, et al. Non-destructive Determination of Age and Species of Anopheles gambiae sl Using Near-infrared Spectroscopy. American Journal of Tropical Medicine and Hygiene. 2009;81(4):622–30. 10.4269/ajtmh.2009.09-0192 [DOI] [PubMed] [Google Scholar]
  • 10.Sikulu M, Killeen GF, Hugo LE, Ryan PA, Dowell KM, Wirtz RA, et al. Near-infrared Spectroscopy as a Complementary Age Grading and Species Identification Tool for African Malaria Vectors. Parasites & Vectors. 2010;3(1):1. [DOI] [PMC free article] [PubMed] [Google Scholar]
  • 11.Milali MP, Sikulu-Lord MT, Kiware SS, Dowell FE, Corliss GF, Povinelli RJ. Age Grading An. gambiae and An. Arabiensis Using Near-infrared Spectra and Artificial Neural Networks. BioRxiv. 2018:490326. [DOI] [PMC free article] [PubMed] [Google Scholar]
  • 12.Krajacich B. J., Meyers J. I., Alout H., Dabire R. K., Dowell F. E., Foy B. D. Analysis of Near-infrared Spectra for Age-grading of Wild Populations of Anopheles gambiae. Parasites & Vectors. 2017. January 1,;10(1):1–13. [DOI] [PMC free article] [PubMed] [Google Scholar]
  • 13.Sikulu MT, Majambere S, Khatib BO, Ali AS, Hugo LE, Dowell FE. Using a Near-infrared Spectrometer to Estimate the Age of Anopheles Mosquitoes Exposed to Pyrethroids. PloS One. 2014;9(3):e90657 10.1371/journal.pone.0090657 [DOI] [PMC free article] [PubMed] [Google Scholar]
  • 14.Mayagaya VS, Ntamatungiro AJ, Moore SJ, Wirtz RA, Dowell FE, Maia MF. Evaluating Preservation Methods for Identifying Anopheles gambiae s.s and Anopheles arabiensis Complex Mosquitoes Species Using Near-infrared Spectroscopy. Parasites & Vectors. 2015;8(1):60. [DOI] [PMC free article] [PubMed] [Google Scholar]
  • 15.Dowell FE, Noutcha AE, Michel K. The Effect of Preservation Methods on Predicting Mosquito Age by Near-infrared Spectroscopy. American Journal of Tropical Medicine and Hygiene. 2011;85(6):1093–6. 10.4269/ajtmh.2011.11-0438 [DOI] [PMC free article] [PubMed] [Google Scholar]
  • 16.Ntamatungiro AJ, Mayagaya VS, Rieben S, Moore SJ, Dowell FE, Maia MF. The Influence of Physiological Status on Age Prediction of Anopheles arabiensis Using Near-infrared Spectroscopy. Parasites & Vectors. 2013;6(1):1. [DOI] [PMC free article] [PubMed] [Google Scholar]
  • 17.Sikulu-Lord MT, Milali MP, Henry M, Wirtz RA, Hugo LE, Dowell FE, et al. Near-infrared Spectroscopy, a Rapid Method for Predicting the Age of Male and Female Wild-Type and Wolbachia Infected Aedes aegypti. PLoS Negl Trop Dis. 2016;10(10):e0005040 10.1371/journal.pntd.0005040 [DOI] [PMC free article] [PubMed] [Google Scholar]
  • 18.Sikulu-Lord MT, Maia MF, Milali MP, Henry M, Mkandawile G, Kho EA, et al. Rapid and Non-destructive Detection and Identification of Two Strains of Wolbachia in Aedes aegypti by Near-infrared Spectroscopy. PLoS Negl Trop Dis. 2016;10(6):e0004759 10.1371/journal.pntd.0004759 [DOI] [PMC free article] [PubMed] [Google Scholar]
  • 19.Maia MF, Kapulu M, Muthui M, Wagah MG, Ferguson HM, Dowell FE, et al. Detection of Plasmodium falciparum Infected Anopheles gambiae Using Near-infrared Spectroscopy. Malaria Journal. 2019;18(1):85 10.1186/s12936-019-2719-9 [DOI] [PMC free article] [PubMed] [Google Scholar]
  • 20.Milali MP, Sikulu-Lord MT, Kiware SS, Dowell FE, Corliss GF, Povinelli RJ. Age Grading An. gambiae and An. arabiensis Using Near-infrared Spectra and Artificial Neural Networks. PloS One. 2019;14(8):e0209451 10.1371/journal.pone.0209451 [DOI] [PMC free article] [PubMed] [Google Scholar]
  • 21.Milali MP, Sikulu-Lord MT, Kiware SS, Dowell FE, Povinelli RJ, Corliss GF. Do NIR Spectra Collected from Laboratory-reared Mosquitoes Differ from Those Collected from Wild Mosquitoes? PloS One. 2018;13(5):e0198245 10.1371/journal.pone.0198245 [DOI] [PMC free article] [PubMed] [Google Scholar]
  • 22.LeClair C, Cronery J, Kessy E, Tomás EV, Kulwa Y, Mosha FW, et al. ‘Repel All Biters’: An Enhanced Collection of Endophilic Anopheles gambiae and Anopheles arabiensis in CDC light-traps, from the Kagera Region of Tanzania, in the Presence of a Combination Mosquito Net Impregnated with Piperonyl Butoxide and Permethrin. Malaria Journal. 2017;16(1):336 10.1186/s12936-017-1972-z [DOI] [PMC free article] [PubMed] [Google Scholar]
  • 23.Detinova TS. Determination of the Physiological Age of the Females of Anopheles by the Changes in the Tracheal System of the Ovaries. Medical Parasitology. 1945;14(2):45–49. [PubMed] [Google Scholar]
  • 24.Paskewitz SM, Collins FH. Use of the Polymerase Chain Reaction to Identify Mosquito Species of the Anopheles gambiae Complex. Med Vet Entomol. 1990;4(4):367–73. 10.1111/j.1365-2915.1990.tb00453.x [DOI] [PubMed] [Google Scholar]
  • 25.Xu Q, Liang Y, Du Y. Monte Carlo Cross‐validation for Selecting a Model and Estimating the Prediction Error in Multivariate Calibration. A Journal of the Chemometrics Society. 2004;18(2):112–20. [Google Scholar]
  • 26.Storkey A. When Training and Test Sets are Different: Characterizing Learning Transfer. Dataset Shift in Machine Learning. 2009:3–28. [Google Scholar]
  • 27.Mouazen AM, Kuang B, De Baerdemaeker J, Ramon H. Comparison Among Principal Component, Partial Least Squares and Back Propagation Neural Network Analyses for Accuracy of Measurement of Selected Soil Properties with Visible and Near-infrared Spectroscopy. Geoderma. 2010;158(1):23–31. [Google Scholar]
  • 28.Shlens J. A Tutorial on Principal Component Analysis. ArXiv Preprint ArXiv:1404.1100. 2014.
  • 29.Chicco D, Sadowski P, Baldi P. Deep Autoencoder Neural Networks for Gene Ontology Annotation Predictions. Proceedings of the 5th ACM Conference on Bioinformatics, Computational Biology, and Health Informatics; ACM; 2014.
  • 30.Bourlard H. Auto-association by Multilayer Perceptrons and Singular Value Decomposition. 2000. [DOI] [PubMed] [Google Scholar]
  • 31.Kingma DP, Welling M. Auto-encoding Variational Bayes. ArXiv Preprint ArXiv:1312.6114. 2013.
  • 32.Liu Y, Wu L. High Performance Geological Disaster Recognition Using Deep Learning. Procedia Computer Science. 2018;139:529–36. [Google Scholar]
  • 33.Baldi P. Autoencoders, Unsupervised Learning, and Deep Architectures. Proceedings of ICML Workshop on Unsupervised and Transfer Learning; 2012.
  • 34.Liou C, Huang J, Yang W. Modeling Word Perception Using the Elman Network. Neurocomputing. 2008;71(16–18):3150–7. [Google Scholar]
  • 35.Liou C., Cheng W., Liou J., and Liou D. Autoencoder for Words. Neurocomputing. 2014;139:84–96. [Google Scholar]
  • 36.Altman DG, Bland JM. Statistics Notes: Diagnostic Tests 1: Sensitivity and Specificity. BMJ. 1994. June 11;308(6943):1552 10.1136/bmj.308.6943.1552 [DOI] [PMC free article] [PubMed] [Google Scholar]
  • 37.Smith C. Diagnostic Tests (1)–Sensitivity and Specificity. Phlebology. 2012. August;27(5):250–1. 10.1258/phleb.2012.012J05 [DOI] [PubMed] [Google Scholar]
  • 38.Lalkhen AG, McCluskey A. Clinical Tests: Sensitivity and Specificity. Continuing Education in Anaesthesia, Critical Care & Pain. 2008. December;8(6):221–3. [Google Scholar]
  • 39.Saito T, Rehmsmeier M. The Precision-recall Plot is More Informative than the ROC Plot When Evaluating Binary Classifiers on Imbalanced Datasets. PloS One. 2015;10(3):e0118432. [DOI] [PMC free article] [PubMed] [Google Scholar]
  • 40.Powers DM. Evaluation From Precision, Recall and F-measure to ROC, Informedness, Markedness and Correlation. 2011. [Google Scholar]
  • 41.Fawcett T. An Introduction to ROC Analysis. Pattern Recog Lett. 2006;27(8):861–74. [Google Scholar]
  • 42.Stone P, Veloso M. Layered Learning. European Conference on Machine Learning; Springer; 2000.
  • 43.Dietterich TG. Machine-learning Research. AI Magazine. 1997;18(4):97. [Google Scholar]
  • 44.Domingos PM. A Few Useful Things to Know About Machine Learning. Commun ACM. 2012;55(10):78–87. [Google Scholar]
  • 45.Abdi H. Partial Least Square Regression (PLS Regression). Encyclopedia for Research Methods for the Social Sciences. 2003;6(4):792–5. [Google Scholar]
  • 46.Golub GH, Reinsch C. Singular Value Decomposition and Least Squares Solutions In Linear Algebra. Springer; 1971. p. 134–51. [Google Scholar]
  • 47.De Lathauwer L, De Moor B, Vandewalle J. A Multilinear Singular Value Decomposition. SIAM Journal on Matrix Analysis and Applications. 2000;21(4):1253–78. [Google Scholar]

Decision Letter 0

Jie Zhang

1 Apr 2020

PONE-D-20-02482

An Autoencoder and Artificial Neural Network-based Method to Estimate Parity Status of Wild Mosquitoes from Near-infrared Spectra

PLOS ONE

Dear Mr Milali,

Thank you for submitting your manuscript to PLOS ONE. After careful consideration, we feel that it has merit but does not fully meet PLOS ONE’s publication criteria as it currently stands. Therefore, we invite you to submit a revised version of the manuscript that addresses the points raised during the review process.

Please revise the paper by taking into account the reviewer's comments.

We would appreciate receiving your revised manuscript by May 16 2020 11:59PM. When you are ready to submit your revision, log on to https://www.editorialmanager.com/pone/ and select the 'Submissions Needing Revision' folder to locate your manuscript file.

If you would like to make changes to your financial disclosure, please include your updated statement in your cover letter.

To enhance the reproducibility of your results, we recommend that if applicable you deposit your laboratory protocols in protocols.io, where a protocol can be assigned its own identifier (DOI) such that it can be cited independently in the future. For instructions see: http://journals.plos.org/plosone/s/submission-guidelines#loc-laboratory-protocols

Please include the following items when submitting your revised manuscript:

  • A rebuttal letter that responds to each point raised by the academic editor and reviewer(s). This letter should be uploaded as separate file and labeled 'Response to Reviewers'.

  • A marked-up copy of your manuscript that highlights changes made to the original version. This file should be uploaded as separate file and labeled 'Revised Manuscript with Track Changes'.

  • An unmarked version of your revised paper without tracked changes. This file should be uploaded as separate file and labeled 'Manuscript'.

Please note while forming your response, if your article is accepted, you may have the opportunity to make the peer review history publicly available. The record will include editor decision letters (with reviews) and your responses to reviewer comments. If eligible, we will contact you to opt in or out.

We look forward to receiving your revised manuscript.

Kind regards,

Jie Zhang

Academic Editor

PLOS ONE

Journal Requirements:

When submitting your revision, we need you to address these additional requirements.

1. Please ensure that your manuscript meets PLOS ONE's style requirements, including those for file naming. The PLOS ONE style templates can be found at

https://journals.plos.org/plosone/s/file?id=wjVg/PLOSOne_formatting_sample_main_body.pdf and

https://journals.plos.org/plosone/s/file?id=ba62/PLOSOne_formatting_sample_title_authors_affiliations.pdf

[Note: HTML markup is below. Please do not edit.]

Reviewers' comments:

Reviewer's Responses to Questions

Comments to the Author

1. Is the manuscript technically sound, and do the data support the conclusions?

The manuscript must describe a technically sound piece of scientific research with data that supports the conclusions. Experiments must have been conducted rigorously, with appropriate controls, replication, and sample sizes. The conclusions must be drawn appropriately based on the data presented.

Reviewer #1: Yes

**********

2. Has the statistical analysis been performed appropriately and rigorously?

Reviewer #1: Yes

**********

3. Have the authors made all data underlying the findings in their manuscript fully available?

The PLOS Data policy requires authors to make all data underlying the findings described in their manuscript fully available without restriction, with rare exception (please refer to the Data Availability Statement in the manuscript PDF file). The data should be provided as part of the manuscript or its supporting information, or deposited to a public repository. For example, in addition to summary statistics, the data points behind means, medians and variance measures should be available. If there are restrictions on publicly sharing data—e.g. participant privacy or use of data from a third party—those must be specified.

Reviewer #1: Yes

**********

4. Is the manuscript presented in an intelligible fashion and written in standard English?

PLOS ONE does not copyedit accepted manuscripts, so the language in submitted articles must be clear, correct, and unambiguous. Any typographical or grammatical errors should be corrected at revision, so please note any specific errors here.

Reviewer #1: Yes

**********

5. Review Comments to the Author

Please use the space provided to explain your answers to the questions above. You may also include additional comments for the author, including concerns about dual publication, research ethics, or publication ethics. (Please upload your review as an attachment if it exceeds 20,000 characters)

Reviewer #1: In this paper, authors have trained ANN models on NIR spectra to estimate the parity status of wild mosquitoes based on four different datasets. Applying autoencoders in ANN is a way to develop smart chemometrics for rapid detections based on NIR technology. It is a somewhat valuable research. Nevertheless, some issues are also developing. I cordially raise some opinions for consideration and hope they can be of help for improving the paper.

Line 103: please clarify the way you control the killing temperature at -20oC?

Lines 127-129: how can you determine the division for training and test samples at the ratio of 75%/25%? I suppose 75% for training is over large because you don’t have a third sample set for model evaluation. Did you try other ratios?

Line 128: we can see that Minepa-ARA sample is much more than other samples, which will severely affect the prediction results for classification. Please demonstrate the methods for treating the problem of sample imbalance.

Line 280: please interpret the meaning of 2^2^(1851).

In Fig.2, how can you determine to use 10 feature nodes in the encoded feature space?

In Fig.4, can you explain why using logistic function for encoder’s activation but a linear function for decoder’s?

In Fig.8, you should identify the thresholds for each ROC curve.

**********

6. PLOS authors have the option to publish the peer review history of their article (what does this mean?). If published, this will include your full peer review and any attached files.

If you choose “no”, your identity will remain anonymous but your review may still be made public.

Do you want your identity to be public for this peer review? For information about this choice, including consent withdrawal, please see our Privacy Policy.

Reviewer #1: No

[NOTE: If reviewer comments were submitted as an attachment file, they will be attached to this email and accessible via the submission site. Please log into your account, locate the manuscript record, and check for the action link "View Attachments". If this link does not appear, there are no attachment files to be viewed.]

While revising your submission, please upload your figure files to the Preflight Analysis and Conversion Engine (PACE) digital diagnostic tool, https://pacev2.apexcovantage.com/. PACE helps ensure that figures meet PLOS requirements. To use PACE, you must first register as a user. Registration is free. Then, login and navigate to the UPLOAD tab, where you will find detailed instructions on how to use the tool. If you encounter any issues or have any questions when using PACE, please email us at figures@plos.org. Please note that Supporting Information files do not need this step.

PLoS One. 2020 Jun 18;15(6):e0234557. doi: 10.1371/journal.pone.0234557.r002

Author response to Decision Letter 0


15 May 2020

May 7, 2020

Re: Resubmission of a Manuscript PONE-D-20-02482, An Autoencoder and Artificial Neural Network-based Method to Estimate Parity Status of Wild Mosquitoes from Near-infrared Spectra

Jie Zhang

Academic Editor

PLOS ONE

Dear Editor:

Thank you for the opportunity to revise our manuscript PONE-D-20-02482, An Autoencoder and Artificial Neural Network-based Method to Estimate Parity Status of Wild Mosquitoes from Near-infrared Spectra. We appreciate the careful review and constructive suggestions from you and the reviewer. It is our belief that the manuscript is substantially improved after making the suggested edits.

Following this letter are the editor and reviewer comments with our responses, including how and where the text was modified. As suggested, we also have uploaded an unmarked version of the revised manuscript, along with a marked-up copy highlighting changes made to the original version. The revision has been developed in consultation with all co-authors, and each author has given approval to the final form of this revision.

Thank you for your consideration.

Sincerely,

Masabho P. Milali.

Reviewers’ comments:

General Comment

In this paper, authors have trained ANN models on NIR spectra to estimate the parity status of wild mosquitoes based on four different datasets. Applying autoencoders in ANN is a way to develop smart chemometrics for rapid detections based on NIR technology. It is a somewhat valuable research. Nevertheless, some issues are also developing. I cordially raise some opinions for consideration and hope they can be of help for improving the paper.

Author’s response:

Thank you.

Specific Comments

Comment # 1:

Line 103: please clarify the way you control the killing temperature at -20o C?

Author’s response:

Prior to scanning, mosquitoes were killed by freezing them for 20 minutes in a freezer that is calibrated to -20o C. After freezing the mosquitoes were re-equilibrated to room temperature for 30 minutes. We have reflected this on lines 102 – 104.

Comment # 2

Lines 127-129: how can you determine the division for training and test samples at the ratio of 75%/25%? I suppose 75% for training is over large because you don’t have a third sample set for model evaluation. Did you try other ratios?

Author’s response:

The ratio was picked based on the size of the data. We tried 70% / 30% data division and the results were consistent with the 75% / 25% split.

Training and testing of the models presented in the manuscript was performed in MATLAB using 10-fold Monte Carlo cross validation. The technique generates estimates of variance and was described by Korjus et al (1). The library in MATLAB divides the 75% data into training, validation and testing making our 25% sample as the third sample set for model evaluation.

We have modified the text on lines 130 – 133.

Comment # 3

Line 128: we can see that Minepa-ARA sample is much more than other samples, which will severely affect the prediction results for classification. Please demonstrate the methods for treating the problem of sample imbalance.

Author’s response:

To make sure that results from Minepa-ARA are not influenced by class imbalance, we repeated analysis while the number of mosquitoes in classes were matched (by randomly selecting mosquitoes from the class with large samples to match the number of mosquitoes from the class with few samples) and the results were similar. Furthermore, we computed and presented precision and recall (sensitivity) that are known to capture data imbalance (2). (Line 224 – 229).

Comment # 4

Line 280: please interpret the meaning of 2^2^(1851).

Author’s response:

Let n be the number of binary features, then the number of hypotheses is 2^(2^n). To better understand why this is so, we need to split the problem into two parts. First, we need to determine how many unique instances there are. Second, we need to determine the number of possible sets of instance we can form. The answer to the second question is the size of the power set of X (2^|X|). The first is easy if we have binary features, just take 2 to the number of features we have. So, for one binary feature, we have two (2^1) unique instances; x = 0 or x = 1. The size of the power set of two instances is 2^2 or four. So we have four possible hypotheses for a single binary feature. The hypotheses are "never in the class", "when x == 0 in the class", "when x == 1 in the class", and "always in the class".

Comment # 5

In Fig.2, how can you determine to use 10 feature nodes in the encoded feature space?

Author’s response:

The number 10 was chosen to allow the salient features of the data to be identified. This is based on our knowledge of the data.

Comment # 6

In Fig.4, can you explain why using logistic function for encoder’s activation but a linear function for decoder’s?

Author’s response:

We used logistic function for encoder part to capture the non-linear relationship between features. We used linear function for decoder to regenerate features in the domain similar to the original feature space.

Comment # 7

In Fig.8, you should identify the thresholds for each ROC curve.

Author’s response:

In all ROC curves, we calculated false positive rate and true positive rate using a 0.5 threshold. Reflected on lines 270 – 271, 325 – 326.

References

1. Korjus K, Hebart MN, Vicente R. An Efficient Data Partitioning to Improve Classification Performance While Keeping Parameters Interpretable. PloS One. 2016;11(8):e0161788.

2. Saito T, Rehmsmeier M. The Precision-recall Plot is More Informative than the ROC Plot When Evaluating Binary Classifiers on Imbalanced Datasets. PloS One. 2015;10(3):e0118432.

Decision Letter 1

Jie Zhang

29 May 2020

An Autoencoder and Artificial Neural Network-based Method to Estimate Parity Status of Wild Mosquitoes from Near-infrared Spectra

PONE-D-20-02482R1

Dear Dr. Milali,

We are pleased to inform you that your manuscript has been judged scientifically suitable for publication and will be formally accepted for publication once it complies with all outstanding technical requirements.

Within one week, you will receive an e-mail containing information on the amendments required prior to publication. When all required modifications have been addressed, you will receive a formal acceptance letter and your manuscript will proceed to our production department and be scheduled for publication.

Shortly after the formal acceptance letter is sent, an invoice for payment will follow. To ensure an efficient production and billing process, please log into Editorial Manager at https://www.editorialmanager.com/pone/, click the "Update My Information" link at the top of the page, and update your user information. If you have any billing related questions, please contact our Author Billing department directly at authorbilling@plos.org.

If your institution or institutions have a press office, please notify them about your upcoming paper to enable them to help maximize its impact. If they will be preparing press materials for this manuscript, you must inform our press team as soon as possible and no later than 48 hours after receiving the formal acceptance. Your manuscript will remain under strict press embargo until 2 pm Eastern Time on the date of publication. For more information, please contact onepress@plos.org.

With kind regards,

Jie Zhang

Academic Editor

PLOS ONE

Additional Editor Comments (optional):

Reviewers' comments:

Reviewer's Responses to Questions

Comments to the Author

1. If the authors have adequately addressed your comments raised in a previous round of review and you feel that this manuscript is now acceptable for publication, you may indicate that here to bypass the “Comments to the Author” section, enter your conflict of interest statement in the “Confidential to Editor” section, and submit your "Accept" recommendation.

Reviewer #1: All comments have been addressed

**********

2. Is the manuscript technically sound, and do the data support the conclusions?

The manuscript must describe a technically sound piece of scientific research with data that supports the conclusions. Experiments must have been conducted rigorously, with appropriate controls, replication, and sample sizes. The conclusions must be drawn appropriately based on the data presented.

Reviewer #1: Partly

**********

3. Has the statistical analysis been performed appropriately and rigorously?

Reviewer #1: Yes

**********

4. Have the authors made all data underlying the findings in their manuscript fully available?

The PLOS Data policy requires authors to make all data underlying the findings described in their manuscript fully available without restriction, with rare exception (please refer to the Data Availability Statement in the manuscript PDF file). The data should be provided as part of the manuscript or its supporting information, or deposited to a public repository. For example, in addition to summary statistics, the data points behind means, medians and variance measures should be available. If there are restrictions on publicly sharing data—e.g. participant privacy or use of data from a third party—those must be specified.

Reviewer #1: Yes

**********

5. Is the manuscript presented in an intelligible fashion and written in standard English?

PLOS ONE does not copyedit accepted manuscripts, so the language in submitted articles must be clear, correct, and unambiguous. Any typographical or grammatical errors should be corrected at revision, so please note any specific errors here.

Reviewer #1: Yes

**********

6. Review Comments to the Author

Please use the space provided to explain your answers to the questions above. You may also include additional comments for the author, including concerns about dual publication, research ethics, or publication ethics. (Please upload your review as an attachment if it exceeds 20,000 characters)

Reviewer #1: Authors have carefully modified the manuscript. I think the paper can be accepted at its current version.

**********

7. PLOS authors have the option to publish the peer review history of their article (what does this mean?). If published, this will include your full peer review and any attached files.

If you choose “no”, your identity will remain anonymous but your review may still be made public.

Do you want your identity to be public for this peer review? For information about this choice, including consent withdrawal, please see our Privacy Policy.

Reviewer #1: No

Acceptance letter

Jie Zhang

5 Jun 2020

PONE-D-20-02482R1

An Autoencoder and Artificial Neural Network-based Method to Estimate Parity Status of Wild Mosquitoes from Near-infrared Spectra

Dear Dr. Milali:

I'm pleased to inform you that your manuscript has been deemed suitable for publication in PLOS ONE. Congratulations! Your manuscript is now with our production department.

If your institution or institutions have a press office, please let them know about your upcoming paper now to help maximize its impact. If they'll be preparing press materials, please inform our press team within the next 48 hours. Your manuscript will remain under strict press embargo until 2 pm Eastern Time on the date of publication. For more information please contact onepress@plos.org.

If we can help with anything else, please email us at plosone@plos.org.

Thank you for submitting your work to PLOS ONE and supporting open access.

Kind regards,

PLOS ONE Editorial Office Staff

on behalf of

Dr. Jie Zhang

Academic Editor

PLOS ONE

Associated Data

    This section collects any data citations, data availability statements, or supplementary materials included in this article.

    Supplementary Materials

    S1 Appendix. Zip folder with Minepa-ARA, Muleba-GA and Burkina-GA datasets.

    Column header, wavelengths in ‘nm’.

    (ZIP)

    Data Availability Statement

    All relevant data are within the manuscript and its Supporting Information files.


    Articles from PLoS ONE are provided here courtesy of PLOS

    RESOURCES