Bacterial classification with convolutional neural networks based on different data reduction layers

Abstract

For high accuracy classification of DNA sequences through Convolutional Neural Networks (CNNs), it is essential to use an efficient sequence representation that can accelerate similarity comparison between DNA sequences. In addition, CNN networks can be improved by avoiding the dimensionality problem associated with multi-layer CNN features. This paper presents a new approach for classification of bacterial DNA sequences based on a custom layer. A CNN is used with Frequency Chaos Game Representation (FCGR) of DNA. The FCGR is adopted as a sequence representation method with a suitable choice of the frequency k-lengthen words occurrence in DNA sequences. The DNA sequence is mapped using FCGR that produces an image of a gene sequence. This sequence displays both local and global patterns. A pre-trained CNN is built for image classification. First, the image is converted to feature maps through convolutional layers. This is sometimes followed by a down-sampling operation that reduces the spatial size of the feature map and removes redundant spatial information using the pooling layers. The Random Projection (RP) with an activation function, which carries data with a decent variety with some randomness, is suggested instead of the pooling layers. The feature reduction is achieved while keeping the high accuracy for classifying bacteria into taxonomic levels. The simulation results show that the proposed CNN based on RP has a trade-off between accuracy score and processing time.     

Sporadic Carriers of Human T-Lymphotropic Virus Type I in Northern Egypt

Sera from 3,158 individuals living in northern Egypt were tested for the presence of antibodies against human T-lymphotropic virus type I (HTLV-I) by the newly developed particle agglutination (PA) test. Ten sera gave a positive reaction in the PA test. Eight of these sera were examined further by Western blotting and all of them gave several bands corresponding to HTLV-I structural proteins. Two of the 8 sera gave positive results in the indirect immunofluorescence test. The results indicate the presence of HTLV-I carriers in this area, although at very low incidence (0.063%).     

Antigens of Coccidioides posadasii as an Important Tool for the Immunodiagnosis of Coccidioidomycosis

Serologic diagnosis has been presented as a safe alternative for coccidioidomycosis. However, commercial kits based on coccidioidal antibodies available in the USA are considered too expensive for laboratories outside that country. In this study, we describe the preparation of antigens for detection of human coccidioidal antibodies by the immunodiffusion test (ID) and enzyme immunoassay (EIA). Antigens were tested against serum samples from patients with coccidioidomycosis, histoplasmosis and paracoccidioidomycosis, as well as healthy individuals. The highest reactivity in the ID tests was seen in the F0-90 antigen. In the EIAs, the best results were obtained with the F60-90 antigen. None of the serum samples from healthy individuals were recognized by any of the antigen extracts tested by ID or EIA. In conclusion, the F0-90 and F60-90 antigens have the potential to be commercially employed in presumptive diagnosis of coccidioidomycosis by ID or EIA, respectively. The tests could improve serological diagnosis of coccidioidomycosis in South America.     

Does biofilm origin matter? Biofilm responses to non-flow period in permanent and temporary streams

1. In some regions, climate change is increasing the variability of rainfall and the frequency of extreme events such as drought. Consequently, non-flow periods have grown in length and frequency, both in temporary and in formerly permanent streams. Water abstraction for human use may further prolong these dry periods.
2. We analysed the resistance and resilience of biofilms from permanent and temporary streams to non-flow conditions. This was achieved by exposing cobbles (collected from permanent and temporary streams) with intact biofilm to 31 days of non-flow, followed by 20 days of stream flow in artificial stream channels. Biofilm resistance and resilience were assessed at a structural (algal biomass, pigment composition, and algae and cyanobacteria composition) and functional level (photosynthetic efficiency and community metabolism).
3. Algal taxa in biofilms from permanent and temporary streams differed throughout the experiment. Biofilms from permanent streams were less resistant to non-flow than those from temporary streams at structural level. Permanent stream biofilms also presented lower resilience at a structural level, but responded similarly to temporary stream biofilms at a functional level.
4. Our investigation shows how the non-flow period disturbed permanent stream biofilms, and suggests that temporary stream biofilms will have greater adaptive capacity as hydroperiod becomes shorter due to climate change.

     

A generalized threshold mixed model for analyzing nonnormal nonlinear time series, with application to plague in Kazakhstan

We introduce the generalized threshold mixed model for piecewise-linearstochastic regression with possibly nonnormal time-series data.It is assumed that the conditional probability distributionof the response variable belongs to the exponential family,and the conditional mean response is linked to some piecewise-linearstochastic regression function. We study the particular casewhere the response variable equals zero in the lower regime.Some large-sample properties of a likelihood-based estimationscheme are derived. Our approach is motivated by the need formodelling nonlinearity in serially correlated epizootic events.Data coming from monitoring conducted in a natural plague focusin Kazakhstan are used to illustrate this model by obtainingbiologically meaningful conclusions regarding the thresholdrelationship between prevalence of plague and some covariatesincluding past abundance of great gerbils and other climaticvariables.     

Quercetin handles cellular oxidant/antioxidant systems and mitigates immunosenescence hallmarks in human PBMCs: An in vitro study

Immunosenescence, oxidative stress, and low vaccine efficacy are important symptoms of aging. The goal of our study was to test if quercetin had antiaging and stimulating effects on peripheral blood mononuclear cell (PBMC) immune cells in vitro in the presence of concanavalin a, PBMCs were isolated from healthy elderly and young people and cultured in a complete Roswell Park Memorial Institute 1640 medium supplemented with quercetin. Cell proliferation was assessed using the 3-(4,5-dimethyl-2-thiazolyl)-2,5-diphenyl-2H-tetrazolium bromide colorimetric assay after a 48-h incubation period. Spectrophotometric assays were used to assess oxidative biomarkers (proteins carbonyl [PC], malondialdehydes [MDA], and reduced glutathione [GSH]). The enzyme-linked immunosorbent assay method was used to determine the amount of interleukin (IL)-2 released. A Griess reagent was used to investigate inducible nitrite oxide synthase (iNOS) activity. When compared to young control cells, aged PBMCs had lower proliferation potency, lower IL-2 and NO release, and higher MDA and PC levels. Importantly, quercetin-treated aged PBMCs have a high proliferative response comparable to young cells, restored iNOS activity, and increased levels of GSH antioxidant defences. In comparison to untreated aged PBMCs, treated PBMCs have lower lipo-oxidative damage but higher PC levels. Quercetin may be used as a promising dietary vaccinal adjuvant in the elderly, it has significant effects in reducing immunosenescence hallmarks, as well as mitigating the lipo-oxidative stress in PBMCs cells.