Dataset Information

Classification of containers with Aedes aegypti pupae using a Neural Networks model.

ABSTRACT: INTRODUCTION:This paper discusses the presence of Aedes aegypti pupae in different types of containers considering: volume, pH of the container, among other variables. METHODS:A nonlinear method for selection was applied, based on Mutual Information, by placing in order of importance the most appropriate variables for identifying containers with and without Aedes aegypti pupae. Such variables were used for input into a Neural Network in layers for classification. RESULTS:Among the experiments carried out, the best result obtained used the first eight variables selected by order of importance. The percentage of hits for containers which had no Aedes aegypti pupae was 73.3%, and 80.9% for those which did have Aedes aegypti pupae in the containers. This Neural Network method, a model with the capacity to emulate non-linear data, got better results in comparison with the discriminant power of the Logistic Regression model. Thus, the outcomes of using the Neural Networks method achieved better separability in classifying the containers with pupae and those with no pupae. CONCLUSION:This type of analysis will aid in the efforts to design an efficient program to control Aedes aegypti that can concentrate principally on containers which present the greatest productivity.

SUBMITTER: Medronho RA

PROVIDER: S-EPMC6072124 | biostudies-literature | 2018 Jul

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Classification of containers with Aedes aegypti pupae using a Neural Networks model.

Medronho Roberto de Andrade RA Câmara Volney de Magalhães VM Macrini Leonardo L

PLoS neglected tropical diseases 20180723 7

<h4>Introduction</h4>This paper discusses the presence of Aedes aegypti pupae in different types of containers considering: volume, pH of the container, among other variables.<h4>Methods</h4>A nonlinear method for selection was applied, based on Mutual Information, by placing in order of importance the most appropriate variables for identifying containers with and without Aedes aegypti pupae. Such variables were used for input into a Neural Network in layers for classification.<h4>Results</h4>Am ...[more]

PMID: 30036370

Similar Datasets

Project description:BackgroundAedes aegypti carries several viruses of public health importance, including the dengue virus. Dengue is the most rapidly spreading mosquito-borne viral disease in the world. Prevention and control of dengue mainly rely on mosquito control as there is no antiviral treatment or a WHO-approved vaccine. To reduce the Ae. aegypti population, studying the characteristics of their habitats is necessary. Aedes aegypti prefer breeding in artificial water holding containers in peridomestic or domestic settings. Their juveniles (1st - 4th instar larvae and pupae) have a tendency to cluster in certain types of containers. To inform control strategies, it is important to assess whether the pupae subgroup has a distinct distribution by container type as compared to the overall group of juveniles. The objective of this study was to assess for distinct predictors (location, season, and function) of Ae. aegypti juveniles and pupae numbers in water holding containers by applying hurdle model analyses.MethodologyThe field component of this study was carried out from November 2013 to July 2015 in Southern Taiwan where annual autochthonous dengue has been reported for decades. Water holding containers with stagnant water were identified in a predefined urban area in Kaohsiung City (KH) and a rural area in Pingtung County. Given that mosquito survey data often include many containers with zero Ae. aegypti, a negative binomial hurdle model was applied to model the association between location, seasonal and functional characteristics of the water holding containers and the number of Ae. aegypti in each container.ResultsThe results showed that Ae. aegypti were almost exclusively present in the urban area. In this area, the negative binomial hurdle model predicted significantly more juveniles as well as pupae Ae. aegypti in water holding containers during the wet season when compared to the dry season. Notably, the model predicted more juveniles in containers located on private property compared to those on government property, irrespective of season. As for pupae, the model predicted higher amounts in indoor containers used for water storage compared to outdoor water storage containers, irrespective of season. However, for the specific category 'other water receptacle', higher amounts of pupae were predicted in outdoor compared to indoor in water receptacles, such as flower pot saucers and water catchment buckets.ConclusionsThe difference in predictors for juveniles and the pupae subgroup was identified and it may be of importance to the control strategies of the authorities in KH. At present the authorities focus control activities on all water holding containers found on government property. To improve the ongoing control efforts in KH, the focus of control activities maintained by the KH authorities should be expanded to indoor water storage containers and outdoor water receptacles on both private and government properties to adequately address habitats harboring greater numbers of pupae. In addition, it is proposed to increase community engagement in managing water in all types of water holding containers located on privately owned properties (indoor and outdoor), especially during wet season.

Project description:Cancer has been a leading cause of death in the United States with significant health care costs. Accurate prediction of cancers at an early stage and understanding the genomic mechanisms that drive cancer development are vital to the improvement of treatment outcomes and survival rates, thus resulting in significant social and economic impacts. Attempts have been made to classify cancer types with machine learning techniques during the past two decades and deep learning approaches more recently. In this paper, we established four models with graph convolutional neural network (GCNN) that use unstructured gene expressions as inputs to classify different tumor and non-tumor samples into their designated 33 cancer types or as normal. Four GCNN models based on a co-expression graph, co-expression+singleton graph, protein-protein interaction (PPI) graph, and PPI+singleton graph have been designed and implemented. They were trained and tested on combined 10,340 cancer samples and 731 normal tissue samples from The Cancer Genome Atlas (TCGA) dataset. The established GCNN models achieved excellent prediction accuracies (89.9-94.7%) among 34 classes (33 cancer types and a normal group). In silico gene-perturbation experiments were performed on four models based on co-expression graph, co-expression+singleton, PPI graph, and PPI+singleton graphs. The co-expression GCNN model was further interpreted to identify a total of 428 markers genes that drive the classification of 33 cancer types and normal. The concordance of differential expressions of these markers between the represented cancer type and others are confirmed. Successful classification of cancer types and a normal group regardless of normal tissues' origin suggested that the identified markers are cancer-specific rather than tissue-specific. Novel GCNN models have been established to predict cancer types or normal tissue based on gene expression profiles. We demonstrated the results from the TCGA dataset that these models can produce accurate classification (above 94%), using cancer-specific markers genes. The models and the source codes are publicly available and can be readily adapted to the diagnosis of cancer and other diseases by the data-driven modeling research community.

Project description:BACKGROUND: Domestic water storage containers constitute major Aedes aegypti breeding sites. We present for the first time a comparative analysis of the bacterial communities associated with Ae. aegypti larvae and water from domestic water containers. METHODS: The 16S rRNA-temporal temperature gradient gel electrophoresis (TTGE) was used to identify and compare bacterial communities in fourth-instar Ae. aegypti larvae and water from larvae positive and negative domestic containers in a rural village in northeastern Thailand. Water samples were cultured for enteric bacteria in addition to TTGE. Sequences obtained from TTGE and bacterial cultures were clustered into operational taxonomic units (OTUs) for analyses. RESULTS: Significantly lower OTU abundance was found in fourth-instar Ae. aegypti larvae compared to mosquito positive water samples. There was no significant difference in OTU abundance between larvae and mosquito negative water samples or between mosquito positive and negative water samples. Larval samples had significantly different OTU diversity compared to mosquito positive and negative water samples, with no significant difference between mosquito positive and negative water samples. The TTGE identified 24 bacterial taxa, belonging to the phyla Proteobacteria, Firmicutes, Actinobacteria, Bacteroidetes and TM7 (candidate phylum). Seven of these taxa were identified in larval samples, 16 in mosquito positive and 13 in mosquito negative water samples. Only two taxa, belonging to the phyla Firmicutes and Actinobacteria, were common to both larvae and water samples. Bacilli was the most abundant bacterial class identified from Ae. aegypti larvae, Gammaproteobacteria from mosquito positive water samples, and Flavobacteria from mosquito negative water samples. Enteric bacteria belonging to the class Gammaproteobacteria were sparsely represented in TTGE, but were isolated from both mosquito positive and negative water samples by selective culture. CONCLUSIONS: Few bacteria from water samples were identified in fourth-instar Ae. aegypti larvae, suggesting that established larval bacteria, most likely acquired at earlier stages of development, control the larval microbiota. Further studies at all larval stages are needed to fully understand the dynamics involved. Isolation of enteric bacteria from water samples supports earlier outcomes of E. coli contamination in Ae. aegypti infested domestic containers, suggesting the need to further explore the role of enteric bacteria in Ae. aegypti infestation.

Dataset Information

Classification of containers with Aedes aegypti pupae using a Neural Networks model.

Publications

Classification of containers with Aedes aegypti pupae using a Neural Networks model.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets